Dissertations / Theses on the topic 'GIS- Gas Insulated Switchgears'

Sulphur hexafluoride gas is the dominant insulation and interruption material in high voltage gas insulated substation. Its usage remains a concern of transmission system operators owing to the global warming potential of the gas. The work carried out in this thesis aims to find the environment-friendly materials that can replace SF6. These candidates are required to have a strong dielectric strength for high voltage busbar insulation and well arc extinguishing capability necessary for high voltage circuit breaker.A range of alternative insulation types including CF3I gas and its mixture, high pressure air and solid insulating foam are considered as substitute of SF6. Theoretical studies on the dimensions of busbars used in substations are carried out for these options. The dimension of the dielectric system and its ampacity of respect system are calculated using heat transfer models considering their boiling point and proper working pressure which is related with the dielectric strength of some gas.On the other hand, SF6 gas circuit breaker is extremely popular on the medium and high voltage power networks owning to its effective arc extinguishing performance. It would be ideal if a substitute material could be found for SF6 as an interruption material. Biodegradable oil PTFE ablation, other gas candidates including N2, CF3I are investigated as possible replacement of SF6 through literature study.The usage of vacuum circuit breaker is eventually capable to operate in high voltage transmission system. Simulations have been carried out with software ATP/EMTP to investigate the influence of different characteristics of vacuum circuit breaker including chopping current level, the dielectric strength of vacuum gap and the opening time. And then the probability of overvoltages when vacuum circuit breakers installed is studied by statistical study in MATLAB.

This work is focused on the measurement of partial discharges in gas insulated conductors manufactured by ABB. The theoretical part contains the definition of partial discharges, their analysis and detection methods. It also deals with the general description of gas-insulated substations and then with the concrete components manufactured at ABB in the Brno-Slatina production plant. The practical part describes the course of measurement, definition of the main problems and their explanation. The output from the practical part is a measurement library with given characteristics, which show the location and character of the problem in detecting partial discharge in a given encapsulated assembly.

This thesis deals with the design of gas insulated switchgear produced in company ABB s.r.o. Theoretically describes the basics of project engineering in the 2D and 3D environments as well as the construction, partition and properties of the switchgear substations. In thesis is included practical designs and comparison of a gas insulated switchgear draft in 2D and 3D interface in the offer phase.

Cette thèse s’inscrit dans le contexte de la surveillance des postes sous enveloppe métallique (PSEM) en courant continu (DC). La disponibilité de ces équipements étant primordiale pour leurs utilisateurs, il est nécessaire de disposer d’un outil de surveillance (monitoring) permettant de prévenir toute défaillance. Cet outil doit être capable de détecter et d’identifier les défauts présents, afin d’apporter une réponse adaptée. Depuis de nombreuses années, le monitoring des PSEM en AC est réalisé grâce à la mesure des décharges partielles (DP). Malheureusement, les connaissances des DP dans les PSEM en DC sont encore lacunaires, et les techniques d’identification des défauts sont intrinsèquement liées à l’environnement AC. De nouvelles techniques sont donc nécessaires en DC.Ce travail de thèse avait pour but de caractériser les décharges partielles dans les postes sous enveloppe métallique en tension continue, et de mettre en place une solution de reconnaissance automatique des défauts. Pour cela, un banc de mesure des décharges partielles a d’abord été mis en place. Afin de garantir la pertinence des résultats pour des systèmes industriels, les travaux ont été réalisés dans une section de PSEM sous tension continue. Le comportement des DP a été étudié pour deux types de défauts : des pointes sur le conducteur haute-tension et des particules libres métalliques. La caractérisation a porté sur l’influence de plusieurs paramètres : la nature et la pression du gaz, le niveau et la polarité de la tension. La mesure des DP a d’abord été réalisée en conformité avec la norme IEC 60270, permettant ainsi d’évaluer la pertinence de cette méthode pour les applications DC. La caractérisation a été complétée grâce à d’autres chaînes de mesure : une mesure de courant stationnaire, une mesure de courant haute-fréquence, une mesure de lumière, et une mesure des ondes ultra-haute fréquence (UHF). Le travail sur l’identification des défauts a d’abord consisté à construire une signature pertinente à partir des mesures de DP, puis à constituer une base de données, et enfin à implémenter un algorithme de reconnaissance automatique.Ces travaux ont montré que la méthode conventionnelle de mesure des DP présente certaines limites pour la détection des décharges partielles en DC, notamment pour les décharges couronne. Elle a tout de même permis de faire une bonne partie du travail de caractérisation. Les résultats obtenus avec les autres chaînes de mesure utilisées ont permis d’expliquer les lacunes de la méthode conventionnelle. Ils ont également permis un véritable apport pour la caractérisation des DP engendrées par des défauts de type pointe et particule. Enfin, une classification automatique efficace des défauts a été mise en place. Elle s’appuie sur le diagramme q(Δt) issu des données de la mesure conventionnelle des décharges partielles et sur un algorithme de réseau de neurones<br>The framework of this thesis is the monitoring of High-Voltage, Direct Current (HVDC) Gas-Insulated Substations (GIS). The availability of these equipment is crucial for electrical networks operators. That is why they need a preventive diagnosis tool. The solution must be able to detect and identify the insulation defects, so that an appropriate maintenance can be planned. The last 40 years have seen Partial Discharges (PD) measurement become a classic monitoring tool for AC GIS. Unfortunately, there is a lack of scientific information about PD in HVDC GIS, and the known defect identification techniques are very specific to the AC environment. New techniques are thus needed in DC.This thesis aimed to characterize partial discharges in DC gas-insulated substations, and to develop an automatic defect identification tool. The first step of this work was the development of a partial discharge measuring bench. The complete study has been performed in a GIS section, so that the results can be directly applied to industrial equipment. Two kinds of defect have been investigated: protrusions on the high-voltage conductor, and free metallic particles. The influence of parameters such as gas nature and pressure, voltage level and polarity has been evaluated. First, PD have been measured in conformity with the IEC 60270 standard, and the relevance of this method in a DC environment has been evaluated. Then, other measuring chains have been used to improve the characterization of partial discharges: a steady-state current measurement, a high-frequency current measurement, a light measurement and a measurement of Ultra-High Frequency (UHF) waves. Finally, a relevant signature for defect identification has been designed and extracted from DP recordings. A database has been constituted, and an automated recognition algorithm has been implemented.The results show that the conventional PD measurement technique is not fully adapted to partial discharges detection in DC, corona discharges being the most problematic situation. Nevertheless, this method has brought enough information to start the characterization of PD. The limitations of the conventional method have been explained thanks to the results of the other measurements. These other experimental results have led to an actual improvement of the characterization of protrusion and particle-generated partial discharges. An effective automated defect classification solution has been implemented. The signature is derived from the q(Δt) diagram that has been extracted from the data obtained with the partial discharge conventional measurement. The identification algorithm has a neural network structure

En permettant la transmission de fortes puissances sur de grandes distances, les réseaux en haute tension à courant continu (HTCC) représentent l'avenir du transport de l'énergie électrique. Des équipements tels que les postes sous enveloppe métallique (PSEM) seront indispensables dans ces réseaux pour répartir le flux d'énergie, interrompre ou isoler certaines branches. Leur conception nécessite la prise en compte, pour les parties isolantes, de phénomènes spécifiques liés à l’application de champs électriques continus, comme la dépendance de la résistivité avec le champ et la température, mais également l’accumulation de la charge d'espace qui contribue à augmenter sensiblement les risques de claquage. Dans le composite étudié (résine époxyde chargée d’alumine), ce phénomène commence à se manifester dès que les valeurs de champ excèdent quelques kV/mm, correspondant à l’ordre de grandeur des contraintes envisagées dans les futurs PSEM HTCC.Bien que des techniques existent pour déterminer la répartition de ces charges dans les isolants solides, aucune n’est à ce jour directement applicable aux structures isolantes installées dans les PSEM HTCC.L’objectif de ce travail est ainsi de concevoir et de mettre en place une technique de mesure des charges d’espace et du champ électrique interne qui soit à résolution spatiale, non destructive et adaptée à une géométrie d’isolateur cylindrique, de type support isolant de jeu de barres.En utilisant le dispositif expérimental mis en place, le comportement du composite vis-à-vis de la charge d’espace est par la suite étudié, notamment en fonction de différentes contraintes électrothermiques représentatives du fonctionnement des PSEM. Le but final est d'aider à l'optimisation de la conception de ce type d’isolateur, en se basant sur l’analyse des résultats issus de mesures de charges d’espace<br>The trend today is to develop high voltage direct current (HVDC) technology for the future electric network because it offers some advantages for the transmission on long distances. The development of HVDC networks leads to an increasing need of gas insulated substations (GIS). A problem to be dealt with when an insulator is subjected to a continuous electric field is the variation of the resistivity with the electric field and the temperature and the accumulation of space charges that can lead to dielectric breakdown. In alumina-filled epoxy resin, used as insulating material for GIS spacer, the influence of space charge start to come out when the electric fields exceed several kV/mm, corresponding to values envisaged for the future HVDC GIS.Despite that non-destructive methods exist to determine the space charge distribution in solid insulators, none of them are directly applicable to insulation structures installed in the HVDC GIS.So, the main objective of this work is to design and set up a measurement technique to observe the internal electric field and the accumulated charges. The developed method must be non-destructive and adapted for a cylindrical geometry of an insulator used as a busbar insulation support.By using the experimental bench set up, the behavior of the composite material regarding the space charge will be studied, in particular according to different thermoelectric stresses. The final aim is to contribute to the optimization of the design of this type of insulator, based on the results from space charge measurements

碩士<br>中原大學<br>電機工程研究所<br>95<br>The gas insulated switchgear equipment (GIS) has been widely applied on the substations of utility and customers due to the advantages of reducing the substation space requirement significantly, and making the substation as indoor type thus increasing the benefit of land and preventing the environmental impact for less maintenance of equipments. All of these advantages of GIS will contribute to safety and reliability of substation . In practice, however, some problems of unsuitable grounding and maintenances are arisen from GIS installation which may affect the operation safety of GIS. The grounding problems cover GIS and its interfaces with the cables, while the maintenance problems concern the items, work contents and their reference basis and related difficulty. These problems are discussed in this report based on the study results from literatures and the technical information from manufactures of GIS. Where in ,in addition, improvement strategies can be found.

碩士<br>中原大學<br>機械工程研究所<br>99<br>The gas insulated switchgears are transmission and distribution equipments which have a lot of advantages that are small size, high security, modular design and that can be transported fully assembled. Environmental protection receives much concern in recent years because of the area of transformer substations are difficult to obtain. So the gas insulated switchgears have already replaced the air insulated switchgears gradually and become indispensable products. All of conductors and important accessories of gas insulated switchgears are included in pressure vessels and that must be filled with the gas in suitable pressure. For this reason, when pressure vessels are withstood inner pressure or produced flashover, whether the intensity of pressure vessels is enough or not became the problem that we care about. Analysis of pressure vessels about gas insulated switchgear had be discussed extensively in recent years. The complicated pressure vessels can use the ANSYS-Workbench to design and get the better results. Besides, the empirical formulae are unsuitable to be used on complicated pressure vessels. So, the research purposes provide faster and more reliable method that is used by ANSYS-Workbench. First, according to the gas insulated switchgear which bears the internal pressure and then the model is the literature which adopts predecessors[1] and built by PRO/E. After utilizing CNS spec. to calculate pressure vessels’ minimum thickness and maximum allowable pressure, moreover, to use empirical formulae and ANSYS-Workbench to calculate the stress, and then compare results of empirical formulae and analytic results with the reference. Based on the method that could be used on complicated pressure vessels and the results showed that analytic results meet the requirements, besides, the analysis of ANSYS-Workbench is in conformity with predecessors' literature.

碩士<br>國立臺北科技大學<br>電機工程系研究所<br>98<br>Ferroresonance, as a non-linear resonance, is a complex electrical phenomenon caused by the saturation effect of the core components in a transformer or a voltage transformer. If not removed immediately, resonance which occurs as the nonlinear inductance changes to match the circuit capacitance will result in sustained over voltage and over current in a power system. It may further trigger a rise in the temperature and impair insulation, severely damaging equipments and endangering the safety of related personnel. The major purpose of this research is therefore to eliminate the occurrence of ferroresonance via in-depth exploration of its causes and conditions so as to reduce the risk of power system operation. A 161kV gas insulated switchgear (GIS) at a Taipower substation went through voltage transformer ferroresonance phenomenon, resulting in the voltage transformer burned and the spacer broken. Not only the equipment was damaged, the quality of power supply system was also impaired. In the thesis, the electromagnetic transients program (EMTP) is used to build an electromagnetic transients model based on the GIS-derived parameters. The same operational procedures during the accident are then adopted for simulation; the results confirm the occurrence of ferroresonance on the voltage transformer of GIS. For eliminating ferroresonance, the thesis proposes three methods, including: removing the grading capacitance of the circuit breaker, changing the GIS operational procedures, and modifying the series resistance of the damping reactor on the secondary side of the voltage transformer. Effectiveness of the proposed methods are verified by the results of separate simulations; appropriate changes do contribute to the elimination of ferroresonance and help prevent the occurenace of subsequent accidents and damages. Specific recommendations are then presented to provide reference for equipment manufacturers and operation and maintenance workers.

碩士<br>國立臺灣科技大學<br>電機工程系<br>101<br>In this thesis, the partial discharge (PD) tests are conducted on three gas insulated switchgear (GIS) apparatus with different prefabricated defects. The test voltage is gradually raised to 50kV in order to retrieve partial discharge signals. The resulting signal is filtered and transformed into 104 features. Then, these partial discharge data can be divided into different training frameworks. We calculate recognition rates of the various features via adaptive-network-based fuzzy inference system (ANFIS). From the recognition rates of the various features, appropriate features can be chosen for the identification of defects. After verifying the great exclusive of the features, we choose the eighty-second feature for the defect 1, which is Q-negative-height distribution skewness-sum. The eighth feature for the defect 2 is Q-positive-quantity height-num. The sixteenth feature for the defect 3 meets our need which is Q-positive-phase distribution standard deviation-num. The recognition rates of the chosen features can reach more than 95% and they can be used as references for future identification, saving extraction time of unnecessary features. Using the effective features to determine a defect type quickly is the purpose of the thesis.

碩士<br>國立彰化師範大學<br>電機工程學系<br>99<br>The circuit breaker is the main safety equipment in the primary distribution substation. Nowadays, all circuit breakers are imported directly from foreign sellers. Since the prices, features, functions, and after-sale service (warranty) of the equipment are different. The Taiwan Power Company (TPC) has actively promoted the development of localization of electric power equipment and helps the domestic electrical manufacturers to produce the powerful electrical switchgears with reasonable prices, high efficiency and quality for high technology companies using in the primary distribution substation. This thesis concentrates on studying 161 kV SF6 Gas Insulated Switchgears (161kV GIS) which produced by four major domestic electrical manufacturers. To explore the design, installation, operation, maintenance and other related information of the equipment. Furthermore, to collate and analyze those equipments whether meet the basic requirements of 161kV GIS specifications in TPC. Besides, the design ideas of all GIS manufacturers, the function of equipments, the price variance and other concepts are discussed. Finally, the results of this study can be used as reference selecting and putting to use for high technology companies.

碩士<br>國立臺灣科技大學<br>電機工程系<br>103<br>The partial discharge is a phenomenon that a discharge does not bridge in an insulation material. It has a relationship between partial discharges and the failure of electrical insulation. Partial discharges are the major reason for the aging and failure of an insulation. It is usually accompanied by some phenomena such as voice, light, heat, electrical current pulses, electromagnetic waves, chemical changes. In this paper, the detection method is to capture electromagnetic waves of partial discharges. In order to investigate the partial discharge characteristics of the failure in an electrical equipment. We manufacture four kinds of defect models, such as defect model 1(fixed protrusions), defect model 2(free particals), defect model 3(floating electrodes), defect model 4(insulator surface discharge). Five kinds of voltage (16kV,17kV,18kV, 19kV,20kV)applied to each fault mode. Test procedure according to standard IEC60270. Recording partial discharge phenomena of fault models in the frequency domain. Finally, to do the analysis and conclusion of partial discharge characteristics of each fault model.

碩士<br>國立臺灣科技大學<br>電機工程系<br>103<br>In this thesis, we conducted partial discharge (PD) tests with single gas insulated switchgear (GIS) apparatus including different four prefabricated defects, trying to find out a common insulation deterioration the rules. During the trial in order to capture the partial discharge signals partial discharge device, we can extract 104 characteristic parameters include the resulting signal after noise suppression, data transformation, feature extraction and using moving average method. We find out that the feature of the sum of discharge from positive region- center of phase distribution has the same phenomenon in all the defects. The center towards to the first quadrant (0 degrees) as the data increased and turned again before breakdown. Then using k-means to cluster data and he cluster's center point (turning point) items defined them as medium or late term of aging that use them to train the decision trees, so that the completion of four flawed decision tree model. To comply with the unknown defect diagnosis mechanism under the gas insulated switchgear, the use of fourth of the split point defects (phase) corresponding to the turning point, re-train a decision tree to tree complete model. Find out that the 6 characteristic parameters: fractal dimension, the sum of discharge from negative region - center of phase distribution, the sum of discharge from negative region - center of height distribution, the sum of discharge from negative height standard distribution, the area of the discharge from negative initial phase, the sum of discharge from positive region center of height distribution to be used. Use the features above we can get the overall success rate of GIS：95.8%. To finish the development for the insulation status assessment of high voltage gas insulated switchgear.

博士<br>國立成功大學<br>電機工程學系碩博士班<br>101<br>In this thesis, the electrical and non-electrical methods are both applied in the examinations. The electrical method applies high frequency current transformer (HFCT) and capacitive coupler(CC)measurements, and the non-electrical method applies the acoustic emission (AE) measurement. According to the measured data, they are applied to identify the particle impact, vibration, or partial discharge (PD) inside gas insulated switchgear (GIS). Three AE sensors are stuck as a triangle on GIS crust and measure the sound signals. As particle impact occurs, the location of GIS crust is positioned according to the time difference of three AE signals. If PD occurs, we identify the PD according to the time difference of the AE signals and electric signals by HFCT or CC sensors. With the time difference and the distance detected by the three AE sensors, one can locate the position of PD source on the GIS crust. For a PD source, the measured signals vary greatly among different measuring sensors and/or systems. The characteristics of the spectrums of the signals are different with different measuring sensors and/or systems. This makes it difficult to analyze and compare PD signals measured by using different systems. The study can satisfactorily restore the PD sources signals by operating the transferring function on those PD signals measured from different HFCT measuring systems. Applying this technique to on-line measurements, the PD source signals can also be reconstructed effectively. This thesis proposes an approach to determine the classification of PD events in Gas Insulated Load Break Switches (GILBS). Three kinds of different defects are designed and placed inside three GILBS individually. Discrete wavelet transform (DWT) is employed to suppress noises of measured signals by the HFCT. The skewness and kurtosis of the PD signals are adopted as input variables of Probabilistic neural networks (PNN) and fuzzy C-means (FCM). PNN and FCM clustering approach are used to classify the methods. The noise range is over 70 dB, which belongs to the low noise measurement environment. Classification correctness ratios of the defect models are obtained using PNN and FCM, they are all close to 100 %. For accurately determination of the different defect model, feature extraction and statistics analysis of the measured signals are used in the proposed method. Finally, experimental results validate that the proposed approach can effectively discriminate the PD events in GILBS.

碩士<br>國立臺灣科技大學<br>電機工程系<br>106<br>With the rapid development of science, technology and economic activities, the society has paid more and more attention to the power quality and supply security. Electric power companies increasingly adopt the gas insulated switchgear (GIS). It uses SF6 as insulated materials and contains bus, circuit breakers, disconnect switches, earth switches, current transformers and potential transformers. The design of GIS not only greatly reduces the construction space, but also improves the convenience of maintenance and the safety of operators. In order to effectively cut off the transient overvoltage caused by switching on, one solution is to connect a circuit breaker to a grading capacitance. However, while the circuit breaker opens, there will be a loop between the grading capacitance and the load. If and only if the core of the potential transformer is saturated, it is easy to happen ferroresonance, which causes the abnormally continuous overvoltage and overcurrent between the grading capacitance and the potential transformer. In some serious case, ferroresonance leads to insulation deterioration, short circuit, equipment damage or even blackout. Therefore, this thesis aims to propose a freeoresonance analysis strategy. With the EMTP-RV software, the overvoltage and overcurrent of ferroresonance will be simulated. Different suppression methods will also be evaluated. For related engineering personnel, the strategy can provide a faster way to rebuild the process of ferroresonance faults, accelerate the search of solutions and enhance the reliability of power supply.

碩士<br>國立臺北科技大學<br>電資碩士班<br>96<br>Although the first thesis on Ferroresonance（FR） was published in 1920, FR is still not a fully understood phenomenon. This thesis focuses on single phase FR in Gas Insulated Switchgear（GIS）with inductive potential transformers（PT）, fed by the circuit breaker grading capacitance. In principle, FR is a forced oscillation in a non-linear series resonance circuit including a capacitance and non-linear inductance, which shows significantly distorted voltage and current waveforms. The complex non-linear behaviour of the saturable inductance can cause fundamental FR, subharmonic FR, quasi-periodic and even chaotic oscillations. FR can result in high overvoltage and high overcurrent, which can finally damage the high voltage equipments or PTs due to dielectric and thermal problems. Even if there is the risk of ferroresonance for specific GIS configurations, inductive PTs are used rather than capacitive ones because of their reliability, higher accuracy and stable transformation ratio during the entire lifetime. However, combine the theory, GIS and PT maker,s experiences, this thesis provides an overview of network configurations, parameters influencing the FR behaviour and a number of methods to avoid or suppress FR are discussed. This thesis also presents a ferroresonant experience involving inductive PT in a 161kV substation. A very comprehensive analysis is performed by detailed modelling using time domain simulation with a digital computer transient analysis program such as the EMTP/ATPDraw and compares them with field test and measurements.

博士<br>國立臺灣科技大學<br>電機工程系<br>101<br>Partial discharge (PD) is the main cause of degradation of the insulation in gas-insulated switchgear (GIS). PD phenomena include: surface discharge, cavity discharge, corona discharge, and treeing channel discharge. Previous research has shown that different types of defects in GIS generate different symptoms of PD, which are associated with various degrees of damage to the GIS. Hence, PD detection is essential to the reliable evaluation of insulation systems and the identification of defects in GIS. In this research, the experimental objects were GIS defect models, which were filled with SF6 gas. Three models were designed based on the results of investigations of numerous power equipment failures. Statistical features were extracted from the PD pattern data and were inputs of adaptive neuro-fuzzy inference system (ANFIS). The results reveal that ANFIS classification has a high success rate, reaching an acceptable classification accuracy 90%. In addition to accumulating a huge mass of PD data of GIS, the procedure that proposed in this study can be also used to develop a data base of defect recognition for other power equipment.

博士<br>國立臺灣科技大學<br>電機工程系<br>96<br>Abstract This dissertation is concerned with the analysis and improvement of transient response on potential transformers applied to 161kV gas insulated switchgear (GIS) systems with SF6 insulation. The slow discharging overcurrent through the inherent line capacitance of underground inter-substation power cables may result in large magnetic force shifting and damaging bus potential transformer (BPT) primary windings of local substation when opening circuit breaker of remote substation located several kilometers away. The simulation models are built according to field parameters and the discharging current simulation results agree closely with those of field tests in electric power laboratory. BPT primary winding relocation may cause strongly different effects. Calculations are given to determine whether BPT can survive over the mechanical force resulted from the magnetic field generated by the aforementioned three-phase peak transient currents or not. Based on the newly improved BPT and its line-capacitance withstanding test, recommendations of BPT specification with respect to the maximum allowable line capacitance are also given. In addition, while operating disconnecting switch or circuit breaker in distributed substation, an inductance-capacitance loop is formed from grading capacitor of circuit breaker to metering out-fit potential transformers (MPT) paralleled with the capacitance of GIS. Improper design of gap-core inductance damper equipped on secondary winding of MPT may cause ferro-resonance effect, resulting in over-voltage and serious over-current on windings of MPT to overheat and damage insulation material. Three kinds of efficient strategies are proposed in this dissertation to improve ferro-resonance effect on MPT applied to 161kV GIS, the corresponding equivalent circuit models are established and simulations of ferro-resonance based on the field parameters are given. Simulation and experimental results show that the presented suppressors can quickly inhibit ferro-resonance in field test from damaging MPT, and assure safe and reliable switching operations.

碩士<br>國立臺灣科技大學<br>電機工程系<br>100<br>This paper aims using digital image processing technology with the construction of neural network for gas insulated switchgear internal defect detection. The study mainly divided into partial discharge signals measured in the field and use of neural network for phase resolved pattern defect identification. The study objects are three simple type of gas-insulated switchgear with different prefabricated defects, measurement of partial discharge data, filtering, simplification and data conversion to get phase resolve pattern. Image interpolation and two-dimensional wavelet transform are employed for phase resolve pattern data simplification and feature extraction, and a three-layer feed-forward back-propagation constructs neural network. The image processing of phase resolve pattern can reduce the number of neurons in the input layer. Reducing number of neurons effectively reduces the complexity of the neural network and improves its operation efficiency. Phase resolve pattern through feature extraction is input of the the neural network to identify the internal defects of the gas insulated switchgear and explore for different input network to its success recognition rate, then can find the input low frequency components vector sub-function of similar composition after a two-dimensional wavelet transform that significantly enhances the recognition rate in the selected three voltage levels. The highest recognition rate reaches 96.83%.