To see the other types of publications on this topic, follow the link: X-bar control chart.
Dissertations / Theses on the topic 'X-bar control chart'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 40 dissertations / theses for your research on the topic 'X-bar control chart.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Nam, Kyungdoo T. "A Heuristic Procedure for Specifying Parameters in Neural Network Models for Shewhart X-bar Control Chart Applications." Thesis, University of North Texas, 1993. https://digital.library.unt.edu/ark:/67531/metadc278815/.
Full textAbstract:
This study develops a heuristic procedure for specifying parameters for a neural network configuration (learning rate, momentum, and the number of neurons in a single hidden layer) in Shewhart X-bar control chart applications. Also, this study examines the replicability of the neural network solution when the neural network is retrained several times with different initial weights.
2
Harvey, Martha M. (Martha Mattern). "The Fixed v. Variable Sampling Interval Shewhart X-Bar Control Chart in the Presence of Positively Autocorrelated Data." Thesis, University of North Texas, 1993. https://digital.library.unt.edu/ark:/67531/metadc278763/.
Full textAbstract:
This study uses simulation to examine differences between fixed sampling interval (FSI) and variable sampling interval (VSI) Shewhart X-bar control charts for processes that produce positively autocorrelated data. The influence of sample size (1 and 5), autocorrelation parameter, shift in process mean, and length of time between samples is investigated by comparing average time (ATS) and average number of samples (ANSS) to produce an out of control signal for FSI and VSI Shewhart X-bar charts. These comparisons are conducted in two ways: control chart limits pre-set at ±3σ_x / √n and limits computed from the sampling process. Proper interpretation of the Shewhart X-bar chart requires the assumption that observations are statistically independent; however, process data are often autocorrelated over time. Results of this study indicate that increasing the time between samples decreases the effect of positive autocorrelation between samples. Thus, with sufficient time between samples the assumption of independence is essentially not violated. Samples of size 5 produce a faster signal than samples of size 1 with both the FSI and VSI Shewhart X-bar chart when positive autocorrelation is present. However, samples of size 5 require the same time when the data are independent, indicating that this effect is a result of autocorrelation. This research determined that the VSI Shewhart X-bar chart signals increasingly faster than the corresponding FSI chart as the shift in the process mean increases. If the process is likely to exhibit a large shift in the mean, then the VSI technique is recommended. But the faster signaling time of the VSI chart is undesirable when the process is operating on target. However, if the control limits are estimated from process samples, results show that when the process is in control the ARL for the FSI and the ANSS for the VSI are approximately the same, and exceed the expected value when the limits are fixed.
3
Kimura, Erin A. "RELIABILITY ANALYSIS OF LOW-SILVER BGA SOLDER JOINTS USING FOUR FAILURE CRITERIA." DigitalCommons@CalPoly, 2012. https://digitalcommons.calpoly.edu/theses/867.
Full textAbstract:
The appropriate selection of failure criterion for solder joint studies is necessary to correctly estimate reliability life. The objective of this study is to compare the effect of different failure criteria on the reliability life estimation. The four failure criteria in this study are a 20% resistance increase defined in the IPC-9701A standard, a resistance beyond 500 Ω, an infinite resistance (hard open), and a failure criterion based on X-bar and R control charts. Accelerated thermal cycling conditions of a low-silver BGA study included 0°C to 100 °C with ten minute dwell times and -40°C to 125°C with ten minute dwell times. The results show that the life estimation based on X-bar and R failure criterion is very similar to the life estimation when a 20% resistance increase defined in the IPC-9701A failure criterion is used. The results also show that the reliability life would be overestimated if the failure criterion of a resistance threshold of 500 Ω or an infinite resistance (hard open) is used.
4
Lin, Hung —. Chia, and 林宏嘉. "Revised X-bar Control Chart." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/p6dv4s.
Full textAbstract:
碩士淡江大學
統計學系
91
This paper presents two approaches for constructing control limits of X-bar control chart that can enable the user to begin monitoring the process mean at an earlier stage than the standard approaches. The proposed control limits can be constructed easily and are closed to any specific percentile of run length distribution of the true limits, even when only a few initial subgroups are available. Performances of the proposed approaches are studied by Monte Carlo simulation. The simulation results show that the proposed control limits perform similarly to the true limits even when the limits are estimated using data from only a few initial subgroups.
5
Hsu, Shih-Hsueh, and 徐仕學. "Moving weight average X-bar control chart with variable sampling intervals." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/10866655187044317525.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
94
Reynolds[1998] proposed the standard X-bar control chart with variable sampling intervals (STD VSI X-bar) which is an effective monitoring method. If the newest sample mean falls in the warning region, a short sampling interval is used in the next sampling, whereas a long sampling interval is used. However, compared to other adaptive X-bar control charts, STD VSI X-bar is insensitive to the moderate and small process shift. The reason is that the switching rule of STD VSI X-bar only refers to the newest sample mean to choose the sampling interval. In order to overcome the drawback of the switching rule of STD VSI X-bar, the moving weight average method is applied to give the equal weight to the samples of the recent periods. The moving weight average value is treated as the criterion of choosing the sampling intervals. It is called ‘Moving weight average X-bar control chart with variable sampling intervals, MWA VSI X-bar. The results of the paper show that MWA VSI X-bar not only increases the ability of monitoring the moderate and small process shift but also reduces the average number of switches.
6
Hung, Pei-Yi, and 洪蓓怡. "Economic Design of Variable Sampling Intervals X-bar and R Control Chart." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/52198354504910617532.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
92
The control chart makes the monitoring in process stability to reduce defective production and it can use to estimate process parameters. Then through these messages to determine process production or provide effective information in process improvement, so the control chart is a good tool to solve question and improve quality. The process control must simultaneously maintain the process mean and the process variation, so can help the performers to understand the actual condition about entire process, therefore, in this paper, we uses X-bar and R control chart to monitor process. In this paper, we develop the economic design of the variable sampling intervals（VSI）X-bar and R control chart to determine the values of seven test parameters of the chart, i.e. the sampling size（n）, the sampling interval（h1、h2）, the control limits coefficients（L1、L2）, and the warning limit coefficients（L3、L4）. The purpose is let the expected total cost minimum associated with the test procedure. The genetic algorithm（GA）is used to search for the optimal values of the seven test parameters of VSI X-bar and R control chart, and an example is provided to interpret the solution procedure. And then carried out sensitivity analysis to investigate the effects of model parameters on the solution of the economic design as the basis for making decision.
7
Yi-RuJhuo and 卓怡如. "Setting Control Limits of X-bar Control Chart Subjected to Short-term Human Resources." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/2jh56g.
Full text
8
Liou, Jia-Hueng, and 劉家宏. "Non-Normality of the Joint Economic Design of X-bar and R Control Chart." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/24656584001280333879.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所
87
Since Duncan’s pioneering work in economically design of X-bar control chart, there were a lot of works toward economically design of different control charts. Saniga who is the first person proposed joint economically optimal design of X-bar and R control chart in 1977. In his research, the quality characteristic is assumed to be normally distributed. But there are cases to have quality characteristic that is not normally distributed in practice. In this research, the Burr distribution is used to represent the distribution of the quality characteristic which is nonnormally distributed, and Saniga’s joint economic design model is used as the basis for developing the joint economic design of X-bar and R control chart. The Genetic Algorithms procedure is employed for searching the optimal solution of those economic design parameters of X-bar and R control chart. A computer program will be developed also to help the practitioner for searching the optimal design parameters. There are two points must be considered before making use of this study, which are described in the following list. 1. The distribution of the quality characteristic of this study that must can be approximated by Burr distribution. 2. To understand the condition of the non-normal distribution of the quality characteristic in advance, and to obtain the skewness coefficient and the kurtosis coefficient of the non-normal distribution before making use of this study. 12 categories of non-normal distribution, and each category includes 81examples are presented for optimal solution in this research. This research found that if the normal model is performed but the distribution of the quality characteristic is nonnormally distributed in practice, the false alarm and the expected cost per unit of output of normal model are more then this research.
9
Hung, Shih-Han, and 洪士涵. "A study of Detecting the Autocorrelated Process by Variable Parameters x-bar Control Chart." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/59392960850452646675.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
95
The traditional statistic process control uses the independent and normal data to determine whether the process has any anomalism situation. It will cause the increase of the false rate of control chart if we use the traditional independent control chart to detect the process. So it is an important issue about how to use the control chart to detect the process effectively when the autocorrelated exists in the process. So this study discusses all the control parameters and investigates the performance of the variable control parameters be used for detecting the autocorrelated process. This study divides the degree of autocorrelated into low, medium and high. No matter how the process correlation is, the VP control chart has a faster speed than the other control chart when they detect the small and medium departure of the process. For getting better detecting speed and sample cost, you should choose the bigger n1 and n2 when detecting the low autocorrelated process or small departure. The bigger control limit coefficient should be chosen when detecting the small departure. The smaller control limit coefficient should be chosen when detecting the big departure. The sample interval, samples, and the coefficient of control limit in high correlated process have no effect on the detecting speed.
10
Lin, Kung-Hong, and 林昆宏. "Non-Normality of the Joint Economic Design of X-bar and S Control Chart." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/56180967728341392283.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
91
Traditionally, observations characteristic is assumed to be normally distributed when control chart is applied for statistic process control. If observations value is not normally distributed, the traditional methods of design about the control chart probably reduce the ability that control chart detects non-chance cause. In according to Burr distribution, Hooke and Jeeves optimal searching rule and the skill of computer simulation, this research develops the joint economic design model of X-bar and S control chart under non-normally distributed. The theme of the thesis discuss that X-bar and S control chart control average and variance about process quality in the same time with Knappenberger and Grandage’s(1969) cost model; besides, it also proposes the economic design to make the max profit on each unit. The purposes of this research are described in the following list: 1. Apply non-normal distributed to the joint of the economic design of X-bar and S control chart. 2. Develop non-normal distributed on control limit to the joint of the economic design of X-bar and S control chart. 3. Optimal solution in different (c,k) and make sensitive analysis.
11
Wu, Cheng-Ming, and 吳政旻. "The Economic Design of Variable Sampling Interval X-bar Control Chart Under Non-normality." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/54295612648584992293.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
90
This research proposed an economic design of VSI (Variable Sampling Interval) X-bar control chart considering non-normally distributed process data. And the sensitivity analysis of those cost and process factors of c1(average cost of searching false alarm), c2(average cost of detecting and eliminating assignable cause), c5(the fixed cost of using control chart), c6(the variable cost of using control chart), g(expected time for every sample to sample, inspect and explain), D(time to search the assignable cause and repair the manufacturing process),δ(coefficient of shift),λ(the rate of assignable cause occurring) and M(loss per unit time when shift) to the design parameters of sample size n, multiple sampling interval d1, d2, d3, d4, and multiples control limits coefficients k1, k2, k3 is performed. This research has come to the following conclusions: 1.Under non-normal data, increasing the skewness and kurtosis coefficient would result in increasing the cost per unit time; Using the model of this research could reduce the cost per unit time efficiently when sampling data of process lapses from normality; 2.Under the model of this research , the sampling interval and control limits from normal data are greater than from non- normality; 3.The cost per unit time is affected by following factors in order ofλ,g,δ, c6, D, c5, M, c2 and c1; 4.Decreasing the factors δ, g or c6 would result in increasing the sample sizes; And increasing the factors c1 or c2 would have the same result; 5.Decreasing the factors δ,λ, M, g,α3 orα4 would result in increasing the sampling interval; And increasing the factors c1, c2, c5 or c6 would have the same result; 6.Decreasing the factors M, g, c6,α3 orα4 would result in increasing the control limits ; And increasing the factors δ, c1 or c2 would have the same result.
12
Lin, Wei-Jhih, and 林韋志. "Improving Fuzzy Statistical Clustering Approach for Estimating the Change in X-bar Control Chart." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/56505966107521144969.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理系
103
Statistical process control (SPC) charts are typically employed to monitor a process shift. If an out-of-control signal occurs in a SPC chart, engineers have to identity the cause and remove it. The method of identity the real time change is knows a change-point estimation problem. In practice, the shift type of a process is uncertain. Engineers need to identify the shift type. When the shift type is a step change, using a linear estimator results an inaccurate estimation. Similarly, if there exists a linear trend change type, using a step estimator yields a considerable delay. A slope coefficient of determination approach was proposed. When an out-of-control signal occurs, the current point and previous point are used to estimate the slope of the linear trend. According to the value of the estimated slope, the fuzzy statistical clustering approach was then used to identify the change point. From the simulation results and practice examples, the proposed approach enables effectively detecting step changes or linear trend changes in a process, thereby facilitating identifying the true process change point.
13
Liao, Li-Fang, and 廖莉芳. "Economical statistical design of combined double sampling and variable sampling interval X-bar control chart." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/53662480514364252113.
Full textAbstract:
碩士雲林科技大學
工業工程與管理研究所碩士班
96
Control charting is applied to monitor the process in manufacturing industry. The traditional Shewhart control is used widely for the process mean. It is sensitive to find an assignable cause for larger shift, but it is not for smaller shift. Then, the DSVSI control chart is proposed. It can not only improve the performance of the Shewhart control chart but also find an assignable cause quickly. In addition, it is very important to think of the cost of manufacturing product. Some researchers consider pursuing lower cost invariably may cause higher false alarm probability. The purpose of this paper is to balance the cost and performance measures. Thus, an economic statistical design model of DSVSI control chart is developed to combine with Duncan’s cost model and some statistical restrictions. An example is given to illustrate the model application. Sensitivity analysis of the cost parameters on the model is also discussed. From researching result, it is suitable to use economic statistical design for small shift since it can give consideration to cost and performance measures. On the other hand, it can only use economic design for larger shift because it performs well on cost and performance measures.
14
Chang, Heng-Chih, and 張恆誌. "Joint Economic Design of Variable Sampling Sizes and Intervals X-bar and R Control Chart." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/84552019306846324786.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
93
The purpose of the control chart is monitoring process to reduce defective production. If only one control chart is used to monitor the process, the power is usually worse than joint two control charts simultaneously. The process control must monitor the process mean and the process variation simultaneously to reveal the actual situation about the process. The variable sample sizes and sampling intervals (VSSI) control chart proposed by Costa in 1999 has proved that its ability in detecting the change of process is better than traditional fixed sample sizes and sampling intervals (FSSI) control chart. The joint economic design of X-bar and R control charts with the variable sampling sizes and intervals（VSSI）is developing in this study. The genetic algorithm（GA） is adopted in searching the optimal values of eight parameters of the chart, i.e. the sampling sizes, the sampling intervals, the warning limit coefficient of X-bar control chart, the control limit coefficient of X-bar control chart, the warning limit coefficient of R control chart, and the control limit coefficient of R control chart. There are some conclusions in this research: 1. Joint VSSI X-bar and R control chart has lower expected cost per time unit (ECTU) than the FSSI and R control chart. 2. Joint VSSI X-bar and R control chart is more efficiency in detecting assignable causes than joint FSSI X-bar and R control chart. 3. The rate of influence (ROI) is an index of influence in ECTU by those parameters and the results show the order of influence as follows: expected time to discover the assignable cause> expected search time associated with a false alarm > the mean time that the process is in control> shift in the process standard deviation> shift in the process mean> expected time to eliminate the assignable cause> variable cost of sampling> cost per unit time of production when the process is in control> fixed cost of sampling> cost per unit time of production when the process is out of control > cost of finding and repairing an assignable cause> cost per false alarm.
15
Chang, Ya-Ting, and 張雅婷. "Applying Non-parametric Bootstrap Method to Construct x-bar Control Chart for Burr Distribution process." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/k699pq.
Full textAbstract:
碩士國立交通大學
工業工程與管理系所
104
The conventional x-bar control chart is usually utilized to analyze or monitor the process mean under the assumption that the process data are independent and follow a normal distribution. However, the probability of committing Type I and Type II errors will increase if the process data follow a non-normal distributions and the control chart will lose the ability of detecting process variation correctly. Bootstrap method is introduced by Efron in 1979. The simulated data can be obtained without any assumption of the underlying distribution. Although some studies utilized bootstrap methods to construct x-bar control limits, most of them only applied the Percentile Bootstrap (PB) confidence interval in constructing the x-bar control limits. Furthermore, they did not compare the effectiveness of four bootstrap confidence intervals in monitoring the process mean under non-normal distributions. This study utilizes two non-parametric bootstrap confidence interval (namely, PB, Bias-Corrected and Percentile Bootstrap (BCa)) to construct x-bar control chart under Burr distribution with negative skew, positive skew and symmetric distributions. The sensitivity analysis is conducted to verify the effectiveness of the proposed x-bar control chart. Some studies showed that BCa performs better than other Bootstrap confidence intervals in estimating the population parameter. However, the simulation result of this study indicates that when the data of a stable process follow a Burr distribution, the x-bar control chart constructed by the PB method has the highest average run length (ARL0), BCa method second and the traditional x-bar control chart has the poorest performance. When the process mean has small or large shift under various sample sizes, the x-bar control chart constructed by the PB and BCa methods perform closely (i.e., both have the lowest average run length (ARL1)) and outperform the traditional x-bar control chart. In summary, when the process data follow a Burr distribution and the sample size is between 2 and 5, the PB x-bar control chart is recommended.
16
Kai-ChunChang and 張凱鈞. "An Economic Design of Adaptive X-bar Control Chart Subjected to Short-term Manpower Shortage." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/qxf6h4.
Full text
17
Hong-Yong, Chang, and 張弘勇. "Application of Multi-Objective Programming for Economic Design of Double Sampling X bar Control Chart." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/47541934624111491971.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理系
102
Statistical process control (SPC) is an important tool of improvement in the quality management. Control charts are widely used for improve quality. However, there are many competitors in industrial. Therefore quality difference was not significant. If enterprises or factories could decrease the cost would create more benefit. Duncan developed the design of economic applied for X bar control chart first. And setting minimization cost as the objective of economic in his model. Actual, enterprises or industries would not consider single objective only, it might consider multiple objective. In this paper the expected cost per time unit, stable process and process with mean shifted number of sampling were considered as objective. Multi-objective genetic algorithms were used to solve multi-objective model. And desirability function was used to integrate objectives. Then compare with traditional double sampling X bar control chart design of economic. Result, the expected cost per time unit, table of process and process mean shifted of sampling number of multi-objective model has better performance than traditional double sampling X bar control chart design of economic.
18
Lin, Jhe-wei, and 林哲暐. "Economic Design of Variable Sampling Interval X-bar Control Chart by Using Taguchi Loss Function." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/82481332664850965705.
Full textAbstract:
碩士國立臺灣科技大學
工業管理系
96
Control charts are essential in statistical process control and it is widely used to detect changes in process shifts. A conventional practice is to use a sample of size 4 or 5, three sigma control limits, and the sampling interval is decided by quality engineer. Although it is easier to carry out in practice, it may not be economic. Duncan first proposed an economic model to determine the parameters of control charts in 1956. Thereafter, many researches focus on economically-based control charts, virtually all of which references Duncan. This study proposes a variable-sampling-interval scheme to construct the X-bar control charts by comprising the Taguchi loss function. Numerical examples show that using Taguchi loss function will result in a shorter sampling-intervals than the traditional cost model, and the sensitivity analysis shows that three process parameters, the difference between the target, specification limits, and process variance have more significant effects on the loss. When “specification limits” become wider or “process variance” decreases, using variable-sampling-interval scheme has higher improvement than using fixed-sampling-interval scheme.
19
Yit-Ming, Yang, and 楊義明. "The Design of X-bar Control Chart from Economic Viewpoint--With a Weibull Distributed Failure Mechanism." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/97103914561015281118.
Full textAbstract:
博士元智大學
工業工程研究所
89
Abstract We consider an economic design of control charts with a Weibull distributed process failure mechanism in a process when there are possible single assignable cause or multiple assignable causes。There are three different topics considered in this thesis: (1) economic design of control charts in a discrete part process，(2) economic design of control charts in a continuous flow process，and (3) economic design of single observation in a moving average control chart。When the process failure mechanism follows a Weibull model having a increasing failure rate，the sampling frequency is tendency to be increased with the age of the system。 A cost model based on the variable sampling intervals，as opposed to fixed sampling intervals， is formulated and analyzed。 Optimal values of the economic design parameters including the sampling size ( )，the variable sampling intervals ( ) and control limit width ( ) are determined by minimizing loss-cost model based on the varieties of combinations of cost factors and Weibull parameters。The performance of the loss-cost with various Weibull parameters is studies，comparisons between a multiplicity-causes model and a single-cause model are performed under both having same time to failure，a sensitivity analysis is performed to illustrate the effects of incorrectly estimating the cost factors of the proposed models。 There are three major discovery from the numerical and sensitivity analysis。(1) Based on the same mean failure times，higher value of shape parameter ( ) results lower loss-cost。If shape parameter is fixed，larger scale parameter ( ) gives larger loss-cost，vice verso，if scale parameter is fixed，larger shape parameter gives larger loss- cost。(2) Based on the same loss cost，there is no significant difference between single assignable cause and multiple assignable cause model when =1 ( that is exponential distribution )，while as increases，loss cost increases in the single assignable cause model than in the multiple assignable cause model。(3) Loss cost will be affected significantly on the production cost either in control state or out of control state ; However，there is litter affection on the loss cost and time on the costs in discovering and removing causes and finding false alarms。 In practice，the application of economic design is still not popular due to the complex of the mathematical models，difficult to determine the cost parameters and hard to measure time factors。If we can improve production environment，simplify economic design model，enhance the value of usage of economic design and provide friendly interfaces between economic design commercial softwares and users，then economic design of control charts can play an important role in the process control in future time。
20
Zahara, Erwie, and 何怡偉. "The economic design of the X-bar control chart under consideration of costs due to process losses." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/25471288808008253368.
Full textAbstract:
碩士輔仁大學
應用統計學研究所
87
X-bar control chart is one of the most important devices for statistical process control in industries. It provide information, successfully control processes, improve process capability, or continuously control a certain process. But X-bar control chart has been designed only with statistical criteria in mind. The use of a control chart requires that engineers select a sample size, a sampling frequency (or an interval between samples) and the control limits for the chart. Selection of these three parameters is usually called the design of X-bar control chart. Duncan (1956) was the first to consider the economic benefits and costs of using a control chart as the basis of designing the control chart, and the approach is usually called the economic design of the control chart. The mathematical models and their associated optimization schemes in the economic design of the X-bar control chart are relatively complex, and are often presented in a manner that is difficult for the practitioner to understand and use, which results in the lack of practical implementation of this methodology. Due to the aforementioned reason, the motive and objective of my research is to employ concepts in probability (the probabilities of in-control state and out-of-control state on the control chart) and the costs incurred in the process to develop a simpler and easier to understand economic design of the X-bar control chart, and I shall call this method “ The economic design of the X-bar control chart under consideration of costs due to process losses” . Furthermore, to verify the validity of this method, a real-world case is checked against the model constructed with this method. Results obtained from the analysis of this model and the analysis of the degree od sensitivity using the same case match those from management theories and the production conditions of the case, and the process loss curve based on this model is the same as the quality cost curve. In conclusion, this method is viable as its results agree with theories and realities.
21
TSENG, LIN-YOU, and 曾林右. "Change-Point Estimation of the X-bar Control Chart Using Logistic regression and Fuzzy Shift Change-point Algorithms." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/vmzkbc.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理系
105
Control charts are the most popular process tools designed to determine whether a process is in control or not. When control chart generates an out-of- control signal, it means that the disturbance is present in the process, so the engineers should identify the time of assignable cause occurred; this moment is called the change point. Often however, the point in time at which signal is not actually the true change point. Thus, if the change point can identify quickly, it is possible to reduce the amount of time spent by engineers searching for the time of the assignable cause. Common change types are step change, linear change and multi-step change, etc. Assuming the change type is known, the Fuzzy shift change-point (FSCP) and Fuzzy-Statistical Clustering (FSC) estimators can effectively estimate the change points of in X-bar control chart. In practice, the change type is unknown in advance. Therefore, this study applies logistic regression model to FSCP and FSC methods to identify the change type is step change or linear change. Then, the FSCP estimators are employed to identify the process change point. The performance of the FSCP is discussed in comparison with the Fuzzy-Statistical Clustering (FSC) estimator. The results demonstrate that the proposed method offers an accurate estimate of the process change point and identify change type.
22
Wu, Chiung-Yu, and 吳瓊玉. "A study of Detecting the Autocorrelated Process by Variable Sampling Sizes and Intervals of x-bar control chart." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/14367585466219633293.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
95
Control charts are generally applied to monitor the manufacture process and their purpose is finding the variability of process instantly and reducing producing the bad productions. In recent years, the applications of control charts are not merely the form of fixed parameter, however Costa[1999] proposed the variable sampling size and interval(VSSI ) which ability of detecting process shift is greater than traditional control chart. On the other hand, the all kinds of industries exist in the autocorrelated process, so this issue is be noticed gradually. Reynolds et al.[1996] researched using variable sampling intervals to monitor the autocorrelated process, and came out it’s ability of detecting the autocorrelated process, which performance is better than Shewhart chart(SS ). This study will discuss the effects of monitoring the autocorrelated process by VSSI control chart, and furthermore compare the effects of detecting the shift process with the other adaptive control charts. About the conclusions of this thesis, using VSSI control chart to detect the autocorrelated process with smaller sampling sizes and larger sampling size will get the faster AATS(Adjusted Average Time to Signal) and the less ANOS(Average Number of Observation to Signal) besides less degree of correlation. At the same time, , the process based on VSSI control chart with smaller long sampling interval and larger short sampling interval will get the less ANOS. Comparing VSSI control chart with the other adaptive control charts, the detecting speed of VSSI control chart is faster than the others when the shift process is greater or equal to 2.
23
Lin, Long-Chin, and 林榮慶. "The Rate of False Signals in Various X-bar Control Chart Patterns with Estimated Limits Using Neural Network Method." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/04439515718555180056.
Full textAbstract:
碩士雲林科技大學
工業工程與管理研究所碩士班
96
From practitioner’s viewpoint, control chart patterns used to be important tools in statistical process control (SPC). Unnatural patterns indicate the process affected by assignable causes that corrective actions should be taken. The average run length (ARL) has usually been studied in the in-control statistical properties. We argue that the ARL is a confusing concept when used with estimating limits and the rate of false signals (RFS,which indicates the estimated probability of inverse of ARL also called Type I error). In this thesis we describe a new framework for the analysis and synthesis of the rate of false signals (RFS) of control chart patterns (CCPs) under non-normal distribution,which proposes a back-propagation neural network-based approach for the analysis of both control chart patterns recognition and real dynamic control limits for RFS. We divide this thesis into three sequences of tasks. The first sequence we recognize the classification of unnatural patterns, the second separates which parameter level of deviation which one pattern has presented and the last sequence we concentrate on how to estimate real dynamic control chart limits for RFS. A Monte-Carlo Simulation was used to generate the required sets of CCPs for both training and testing examples. We set up dynamic control limits for Diffidence chart through back-propagation neural network that will be obtained with more precise evaluation of RFS through paired t-test and sensitivity analysis. Finally, experimental results show underlying conclusion : (a) We obtain the sensitivity with all kinds of patterns for robust weights ; (b) corrective BPN-dynamic limits can efficiently prevent the sudden variation of RFS with non-normal from that D.Trietsch provided ; (c) analysis window 24 performs better than analysis widow 16 both pattern recognition and lower RFS when the subgroups are small.
24
Gao, Yi-Ping, and 高依萍. "Consider the Economic Design of the Variable Sampling Intervals X-bar Control Chart under Amin and Letsinger’s Switching Rules." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/97466370424762383400.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
95
Reynolds (1988) is the first to bring out standard X-bar control chart with variable sampling intervals (abbreviated to STD VSI X-bar ). It chooses the length of the sampling intervals by seeing if the average numbers of the sampling locate in the warning area. However, STD VSI X-bar only takes the latest average number of the sampling into consideration to choose the sampling interval, and therefore it is less sensitive to the medium and small range of departure. As a result, this study adopts AL VSI X-bar control chart to monitor the producing process. This study bases on the new rules of VSI X-bar variable sampling intervals built by Amin and Letsinger （1991）, joining with the economic design of VSI X-bar control chart presented by Bai and Lee （1998），and then integrates both modes to construct the economic design of the variable sampling intervals X-bar control chart under Amin and Letsinger’s switching rules. The goal is to minimize the estimated expected cost per unit time. We can induce the following conclusions for this study: （1）From the results of sensitivity analysis we can know that the search cost due to a false alarm , cost of detecting and eliminating an assignable cause, and hourly cost associated with production in the out-of-control period are the largest factors that affect the target values. Therefore, we can do some adjustments in the manufacturing processes and mechanical apparatuses to reduce the occurrences of the extraordinary situations. （2）It will cause the reductions of the target values when the search cost due to a false alarm increase. （3）It will also bring about the reductions of the target values when the cost of detecting and eliminating an assignable cause and hourly cost associated with production in the out-of-control period increases. （4）The combination of detecting ability parameters of the numbers of X-bar fall on the warning areas and the numbers of X-bar fall on the control limits will affect the control limits coefficients . When the levels of the combination of detecting ability parameters of the numbers of X-bar fall on the warning areas and the numbers of X-bar fall on the control limits increase, the control limits coefficients will also increase.
25
Lee, Pei-Hsi, and 李佩熹. "The design of double sampling X-bar control charts." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/59739600046830018922.
Full textAbstract:
博士雲林科技大學
工業工程博士班
97
Double sampling X-bar control chart (DS X-bar control chart) which is a Shewhart type control chart can reduce sample size and detect small process shift fast. In process monitoring of real industry, the process observations may be interdependent and correlated or violate the normality assumption. An original design of DS X-bar control chart will have higher error probabilities in these type processes. In this study, an economic design model and a statistical design model of DS X-bar control chart for correlated and non-normal data are respectively developed for determinations of sample size, sampling interval, and control limits and warring limit coefficients. The performances of DS X-bar control chart for correlated and non-normal data are respectively compared with Variable parameters X-bar control chart (VP X-bar control chart) and Shewhart X-bar control chart. Two real cases of IC packaging are respectively given to illustrate the economic model application for correlated and non-normal data. Sensitivity analysis shows the influence of different cost parameters and population distributions on the optimal design of DS X-bar control chart. From the numerical analysis, DS X-bar control chart has better performance in small process detection for correlated; normal and non-normal data. The control cost is not obviously changed either population is far away form normal distribution or observations occur higher correlation.
26
Chen, Yan-kwang, and 陳彥匡. "A Fuzzy Diagnosis system for X-bar control charts." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/01894042452244472213.
Full textAbstract:
博士國立交通大學
工業工程與管理系
88
In this dissertation, a control chart based diagnosis system has been developed to assist operators in monitoring whether or not a process is under control. When a process is becoming unstable, the system will give an alarm signal and justify the possible causes of instability. By removing the root cause of instability, the process can be improved. The diagnosis procedure in the system includes two phases: (1) to calculate the relationships between observations and predefined unnatural symptoms. (2) According to the relationships mentioned above and the linkage knowledge between unnatural symptoms and assignable causes, the system will infer whether or not the process is keeping in a control state. If not, then the possible causes of instability might be shown. Therefore, this dissertation firstly proposes the fuzzy rules-test method and the grey relation pattern recognizer to define the relationships between observations and predefined unnatural symptoms. Then, two knowledge acquisition methods: (1) maximum similarity method (MSM) and (2) fuzzy decision tree, are proposed for acquiring the linkage knowledge between unnatural symptoms and assignable causes. Finally, two diagnosis systems are illustrated.
27
Liao, Huang-Sheng, and 廖皇盛. "Design of Double Sampling X-bar Control Charts for Correlated Data." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/76124847807755557903.
Full textAbstract:
碩士雲林科技大學
工業工程與管理研究所碩士班
96
When the process variance occurred, quickly detecting out the process variance can effectively reduce the occurrence of defective products. Double sampling (DS) X-bar control chart can quickly detect the mean shift under using the fewer sample size and reduce the inspection time and cost. In the real process, the observation values of the sample usually occur the correlation. When the correlation had occurred, the type Ι error probability of control charts will increase. In this study, we construct a statistical design model of DS X-bar control chart for monitoring of correlated process. In our model, two objective functions were constructed according to minimize in-control sample size and out-of-control sample size, and the statistical performance is subjected to the requirement of real process monitoring. The multi-objective programming method and genetic algorithm are used to obtain the optimum design of DS X-bar control chart. A real case of IC packaging process is used to illustrate the application of the statistical design model and evaluate the performance of the DS X-bar control chart design. The DS X-bar control chart design proposal in this study can improve the sample size obviously.
28
Lai, Zhi Zhong, and 賴致中. "The Economic Design of x-bar Control Charts under Preventive Maintenance." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/58213805254857418975.
Full textAbstract:
碩士大葉大學
工業工程與科技管理學系
96
The economic design of traditional x-bar control charts generally takes less consideration of preventive maintenance. While some economic design of x-bar control charts when considering the preventive maintenance conducts a preventive maintenance at each sampling. Based on Duncan’s (1956) economic design mode, this study assumed that preventive maintenance is carried out only when the sample statistics falls into the scope between the warning and the action limits to reduce unnecessary maintenance action to establish the economic model of x-bar control charts. Hooke and Jeeves search method was used to obtain the optimized design parameters combination of the number of samples (n), sampling intervals (h) and the width of control limits (k) for the lowest unit time cost E (L). The numerical example was used to illustrate the model’s working and it showed that the unit time costs of control charts can be reduced when taking the preventive maintenance into consideration. Meanwhile, the sensitive analysis showed that the occurrence rate (λ0)and extra-cost(M)when process is out of control are the significant parameters to the control chart design.
29
Liao, Nai-Yi, and 廖乃毅. "The economical-statistical design of double sampling X-bar control charts." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/58423738517293552526.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
95
As today’s manufacturing firms are moving towards agile manufacturing, a fast and economical on-line statistical process control solution is in high demand. Multiple sampling control charts are such an alternative. One successful application of the multiple-sampling control charts is the use of a double sampling (DS) control chart in replacement of traditional control charts for on-line statistical process control in industries. A DS chart is quicker and more sensitive than the traditional Shewhart chart in detecting the mean shift in a process. A control chart design parameters such as sample size, time between sampling and the spread of the control limits from the center line could be determined based on a cost viewpoint. The Duncan’s economical model is widely used to determine optimum control chart design. We modify Duncan’s economical model based on the concept of DS control charting and optimize the cost function in determining the control chart design parameters. The sensitivity analysis was also performed.
30
Huang, Jih-Hung, and 黃日宏. "Shewhart X-Bar Control Charts to Monitor Characteristic Life of Multiply-Censored Data." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/46128162332507602755.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理系
104
In the industrial products often do life test, life test usually care about the average change in manufacturing process, consider the time and cost, often using censored data. Control chart is a good tool monitor the process. But Steiner & Mackay (2000,2001) proposed using traditional control charts monitor censored data, the occurrence of adverse characteristics such as large-alarm rate and low power, therefore right-censored data assumes a life is Normal distribution and Weibull distribution proposed methods to monitor the average change in the process, there are good monitoring capability. Due mostly to the right-censored data the follow-up study as censored data, less discussion of multiply-censored data, it often happens in experiment. Therefore, this study used Steiner & Mackay (2000,2001) proposed the Conditional Expected Value (CEV) X-bar control charts and Weibull CEV、Maximum Likelihood Estimation (MLE) 、Exponential CEV control chart ,multiply-censored data life are Normal distribution and Weibull distribution, establish new control procedures for one-sided control charts to monitor the process of decreasing the average, and discuss using simulated the various parameters in the control chart performance , average run length (ARL) as control charts to detect performance indicators , the results showed that Conditional Expected Value (CEV) X-bar control charts can effectively monitor Normal distribution of multiply-censored data, Other three control charts can effectively monitor the Weibull distribution of multiply-censored data, Can provide in multiply-censored data of life monitoring to avoid the larger Type II error risk.
31
Chung, Chiu-hua, and 鍾佳樺. "The Economic Design of VSSI X-Bar Control Charts under a Preventive Maintenance Policy." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/94318792031450361449.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
92
As the automatic society will come, the rate of utilization of the machinery is raised, carry out proper preventive maintenance that can maintain the quality of the products and lower costs. Increase with machinery service time, the process will deteriorate that having an increasing hazard rate due to wearing and tearing. This study proposes an economic design model of variable sample size and sampling interval x-bar chart with considering preventive maintenance policy. The computational results indicate that the proposed model can detect assignable cause more quickly and save more cost. And scale parameter, shape parameter, shift parameter, the expected time to perform preventive maintenance, cost per unit sampled and the expected cost per false alarm are important factors that will influence total expected cost per unit time.
32
Chiu, Shih-Chen, and 邱士珍. "Economical design of X-bar control charts under the mean shift and variance increasing." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/n46em2.
Full textAbstract:
碩士國立屏東科技大學
工業管理系所
105
Dr. Duncan put forward economical Design of X-bar Control Charts in 1956. This model only considers the mean shift. However, the variation increasing in the process can also possibly occur. Therefore, this study makes the discussion in view of this part and the Duncan’s model was extended. Through the Visual Basic software to carry on a computerized system development and design that optimizes the quality control chart. Apart from considering the mean shift, the variance increases influences on sample size, interval between samples and width of control limits also be considered. Under the goal of minimizing the total unit cost, the optimal combination of n, h and k are found.
33
Chang, Ming-Lun, and 張銘倫. "A Study of Applying Genetic Algorithm to the Economic Design of X-bar Control Charts." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/20747193413457056969.
Full textAbstract:
碩士大葉大學
工業工程與科技管理學系
96
Duncan is the pioneer of the economic design of control charts. One of the main difficulties issues in economic design is the computation of the design parameters. Several different methods have been proposed. In this research, an algorithm of Genetic method is employed to determine the parameters of an X-bar control chart in Duncan’s model. Numerical examples show that this is an accurate and reliable optimum values for the design parameters.
34
Ho, Ming-Han, and 何明翰. "The Economic Design of X-bar Control Charts under Preventive Maintenance and Taguchi Loss Function." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/51861349957369789555.
Full textAbstract:
碩士大葉大學
工業工程與科技管理學系
96
Quality is one of the important indicators of enterprise competitiveness. Reaching a balance between low costs and high quality is a key to the success of an enterprise. Sampling and inspection are conducted during the production process to monitor the product quality in manufacturing process. However, the coming of automated production has gradually increased the plant utilization rate. The failure rate of machines will increase in the manufacturing process due to increased working time. If preventive maintenance can be carried out in proper time, the deficiency rate of the manufacturing process can be reduced to improve the general quality of the products and effectively cut production costs. This study, based on the economic design of X-bar control charts, integrated status-based preventive maintenance to determine whether preventive maintenance of the machine shall be carried out by the statistics of the samples. Taguchi quality loss function was also used to replace the traditional quality cost function to comply with the modern concept of social loss cost to establish the unit time cost analysis model and find out the optimized parameter combination of the economic design of control charts. Meanwhile, numerical examples were employed to illustrate the application of the proposed model. Sensitivity analysis was also conducted to understand which parameters have relative significant effects on costs to provide the industry with a new approach to using control chart design by integrating the preventive maintenance strategy and Taguchi loss function to enhance the competitiveness of the enterprise.
35
Lee, Ming-Chia, and 李明家. "Economic-Statistical Design of X-bar Control Charts with Multiple Assignable Causes using Taguchi's Loss Function." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/47256908897864380426.
Full textAbstract:
碩士國立交通大學
工業工程與管理學系
100
Control Chart is one of the most important tools in statistical process control (SPC). Among many types of control charts, the most often used one is X bar chart. When using X bar chart, the values of sample size(n), sampling interval(h) and coefficient of control limit(k) must be determined. Some studies have developed the economic design and economic-statistical of X bar chart with multiple assignable causes in the process. The economic design or economic-statistical design can determine the optimal values of (n, h, k) with lowest cost. However, these methods did not consider that different values of a quality characteristic of a product may have different effects on customers’ loss. Therefore, this study proposes an revised economic-statistical design of X bar chart with multiple assignable causes in the process using Taguchi’s loss function. After constructing the economic-statistical design, genetic algorithm (GA) is utilized to determine the values of (n, h, k) in the proposed model and sensitivity analysis is carried out to study the effect of the parameters in the proposed model. The results showed that if quality loss is an important index, then the proposed economic-statistical design is better than the developed methods in previous studies in terms of total cost per unit time. Additionally, the most sensitive parameter of the proposed economic-statistical design is the amount of shift in means by certain assignable cause.
36
Tsai, Hsuan-Chun, and 蔡炫君. "The Economic Design of X-Bar Control Charts under a Preventive Maintenance Policy for Multiple Assignable Causes." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/65917591439833959304.
Full textAbstract:
碩士華梵大學
工業管理學系碩士班
87
Traditional design of control chart is based on data which is assumed to be independent identical normal distribution and the occurrence time of an assignable cause follows an exponential distribution. However, this assumption is frequently unpractical. Thus we wish to modify the traditional economic design model, to make the model more consistent with real situation. In this thesis, we study that the occurrences of assignable causes are according to general distribution and its failure rate is increasing. After sampling, we assumed that if the process is in control, a preventive maintenance program could be implemented immediately; otherwise, if the system is out of control, we have to reset the system to in-control state. There are multiple of assignable causes. We derive an economic design of X-Bar control chart, the objective is to determine the design parameters that minimize the long term expected cost per unit time. The numerical analysis is proposed to obtain the optimal sampling sizes, sampling intervals, control limits. In the results, we find that if the increasing failure rate of the system is faster, the cost of saving is larger. When the cost of preventive maintenance is increasing, the average cost per unit time, sampling size, sampling intervals are also increasing, and the control limits is decreasing. When the shift of process （δ1、δ2 ）is small（less than 0.5）, they will have larger long term expected cost per unit time, sampling size and sampling intervals are larger, the control limit is smaller. When the shape parameter（V1、V2） of the assignable causes that according to Weibull distribution equalize to 2, we can obtain the largest sampling size. The values of sampling intervals are decreasing when the value of V1 and V2 are increasing, else the value of control limit is not sensitive to the value of V1 and V2. In the final, we use Visual Basic to develop an application, left as the reference of using control chart to monitor the process.
37
Chen, Yi-Chun, and 陳易群. "Economical Statistical Design of Combined Double Sampling and Variable Sampling Interval Joint X-bar and S Control Charts." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/39921777903222805107.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
101
In recent years, manufacturers and consumers are more attention to the relationship between the ''quality'' and "costs". The control charts is the most commonly used methods of quality management on Statistical Process Control (SPC). The Shewart Dr. (1924) development the average control chart, by the average number of process monitoring process, but it was not sensitive to the detection process small shift. Later, many researchers design adaptive control charts to improve it, the adaptive control charts adjust to sampling size (n), sampling interval time (h) and control parameter (k), Lee (2012) studies have shown that double sampling and variable interval (DSVSI) mean and standard control chart presents a small shift was more batter than traditional control chart. Therefore, this study based on the double sampling and variable interval (DSVSI) mean and standard control chart and combine Duncan(1956) economic model to establish Economical Statistical Design of Combined Double Sampling and Variable Sampling Interval Joint X-bar and S Control Charts. Finally, using sensitivity analysis and genetic algorithms to solve the model, have to solve the optimal parameters. The results show that Economical Statistical Design of control chart is better than Economical Design of control chart. When shift are (3, 4), (2, 3), (4, 5) that statistics performance were the best. That are improved 12.17%, 8.78% and 7.01%.Furthermore economic sensitivity analysis showed that a greater impact on the cost of E (C'') parameters were a2,C_0 and λ. When a2 change 30% the cost implications 18.87% and 18.38%. When λ change 30% the cost implications 8.63% and 9.29%. When C0 change 30% the cost implications 7.63% and 7.35%.The statistical sensitivity analysis showed that the cost E (C'') and statistical performance greater impact is the shift (δ, γ). When the shift was change the cost implications 22.68% and 21.15%.
38
Li, Chia-Ju, and 李嘉茹. "A Study of X-bar Control Charts Design with Non-normally Data for Optimizing Cost and Monitoring Efficiency." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/jh2k42.
Full textAbstract:
碩士國立虎尾科技大學
工業工程與管理研究所
95
Traditionally, when the issue of designing control chart is discussed, one usually assumes the observations in each sampled subgroup are normally distributed; therefore, the sample mean is also normally distributed. Even if the size of subgroup is large enough, the observations will be distributed normally according to the central limit theorem. However, the assumption may not be acceptable in practice. In this research, an economic-statistical design of X-bar chart with warning limit under Non-normal distributions will be developed using the Burr distribution. In the part of economic design, Gordon and Weindling (1975) cost model is used to minimize average cost per part produced. In the part of statistical design, average run length (ARL) is used as the statistical limiting conditions. The genetic algorithm (GA) is adopted to search for the optimal parameters, i.e. the sampling size (n), the sampling interval (s), the run length (r), the warning limit coefficients (w) and the control limit coefficients (k). By sensitive analysis we can get fixed sampling cost (CF) and cost correcting the assignable cause (CA2) don’t affect average cost per part produced. An increase in variation sampling cost (CV), cost of defective product (CD), cost of searching for assignable cause (CA1) and mean number of shift (θ) leads to increase average cost per part produced. In addition, An increase in shift coefficient (δ) and allowable semi-tolerance leads to increase average cost per part produced.
39
Yeh, Li-Lun, and 葉立綸. "Economic and Economic-Statistical Designs of X-bar Control Charts under Non-Exponential Failure Mechanisms and Non-normal Data." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/10242734514928735642.
Full textAbstract:
博士國立清華大學
工業工程與工程管理學系
97
Statistical approaches have recently been used to solve industrial process control problems. In particular, the control chart technique, developed using a statistical theory by Dr. Shewhart in 1924, is a well-known statistical method and is widely applied to monitor the variance of a manufacturing process, such that it can ensure that the quality of products is consistent with the expectations of customers. Traditionally, when an economic model is applied to determine the parameters of control charts, it is assumed that the occurrence of an assignable cause follows Poisson distribution when the status of a process changes from in-control into out-of-control condition. Furthermore, it is also assumed that the within-group sampled data and the sampling statistics are also normally distributed. However, the exponential distribution is not an appropriate failure mechanism for some components, mechanical equipment, or machines of electronic products, because their hazard functions will gradually increase with an increase in the time of use. In addition, considering the savings on sampling cost and time, soothe industries usually try to reduce sample size when applying control charts for process monitoring. In these situations, the distribution of subgroup data sets violates the assumption of normal distribution since the central limit theorem cannot be applied. This may reduce the capability of a control chart when applying it for the detection of process variations. This research intends to study the economic and economic-statistical design of x-bar control charts based on the assumption of Burr distribution instead of normal distribution. Meanwhile, fixed sampling interval (FSI) and variable sampling interval (VSI) approaches will be employed under the cost model of Weibull and Gamma distributions. Moreover, the non-linear search approach is applied to determine the parameters of the control chart. To evaluate the performance of different control chart designs, three performance indexes, namely, ECT, Type I error, and power, are employed. It is expected that the research results can provide industries a process monitoring tool with reduced cost at same quality level.
40
Yang, Yen Chun, and 楊衍春. "Taguchi''s Loss Function in the Economic Design of the X-bar Control Charts- Under the Weibull Shock Models." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/50521794148875778721.
Full textAbstract:
碩士元智大學
工業工程研究所
88
In this article, a modified Duncan''s (1956) model with Taguchi''s loss function for the economic design of control charts is extended to deal with situations involving the Weibull shock model. When the process failure mechanism follows a Weibull model, it may derive the variable sampling interval decreased with the age of the system. This article is also considered external failure cost and internal failure cost in the cost model. We hope that this article can help the enterprise to choose the 3 design parameters for their control chart from economic viewpoint.