Dissertations / Theses on the topic 'Système expert (Informatique)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Système expert (Informatique).'
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.
Vinh, Mau Patrick. "Bakus : système expert gastronomique." Paris 9, 1989. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1989PA090039.
Full textApplication of the technics of expert systems to the domain of gastronomy, by the modelisation of Prolog rules and the realization of a modulus of knowledge's acquisition allowing an expert to generate Prolog rules
Zhang, Jie. "Diagnostic multi-expert : extension de l'approche système expert organisé en réseau du système SUPER." Compiègne, 1991. http://www.theses.fr/1991COMPD405.
Full textNaegel, François. "Bakus : un système expert appliqué à la gastronomie." Paris 9, 1989. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1989PA090038.
Full textRealization of an interface end user knowledge based system to proceed to the appropriateness between wines and dishes
Martin, Gilles Gérard Jean. "Une approche par système expert de l'analyse statistique." Châtenay-Malabry, Ecole centrale de Paris, 1991. http://www.theses.fr/1991ECAP0196.
Full textPerrot, Serge. "Prévision de la sureté de fonctionnement des systèmes : système-expert RAS." Châtenay-Malabry, Ecole centrale de Paris, 1985. http://www.theses.fr/1985ECAP0006.
Full textChatain, Jean-Noël. "Maintenance corrective par système expert : application au métro de Lyon." Lyon 1, 1991. http://www.theses.fr/1991LYO10159.
Full textLeclercq, Claude. "Un problème de système expert temps réel : la gestion de centres informatiques." Lille 1, 1990. http://www.theses.fr/1990LIL10143.
Full textGerlinger, Gilles. "Diagnostic en temps réel par système expert : application à un système de diagnostic embarqué sur automobile." Compiègne, 1991. http://www.theses.fr/1991COMPD366.
Full textLaunay, Jean-Pierre. "Génération de code de protocole de communication par système expert." Paris 9, 1995. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1995PA090030.
Full textLefebvre, Bernard. "Système expert en identification bactérienne : définition et mise en application d'une interface prolog.-SGBD." Lille 1, 1986. http://www.theses.fr/1986LIL10046.
Full textFiol, Jean-Charles. "Logique floue dans un système expert de diagnostic d'entreprise." Paris 1, 1997. http://www.theses.fr/1997PA010041.
Full textDefl2 is an expert system designed for the medium term analysis of a company. A preliminary study has demonstrated that it is necessary to put aside the obligation to settle all propositions on the basis of true or false. The original aspect of this work consists in a particular approach of artificial reasoning in the area of company management. This involves the use of the theory of fuzzy sub-groups and the theory of the possibilities concerning the representation of knowledge and the application of gradual reasoning. The rules, which include deductive knowledge, are written to make use of linguistic analysis, and process imprecise and uncertain information. The meta-rules include procedural knowledge and ensure the piloting of the system, by controlling the comparison of fuzzy data; the optimal use of all the rules regrouped into specific modules is achieved by means of repetition
Benier, Michel. "Oncocin : un système d'assistance à la thérapeutique en cancérologie." Montpellier 1, 1988. http://www.theses.fr/1988MON11099.
Full textBarboucha, Mohamed. "Modélisation structurale des systèmes complexes, extraction et validation des règles d'un système expert." Lille 1, 1987. http://www.theses.fr/1987LIL10098.
Full textSebbag, Marc. "Les foyers de microcalcification en mammographie, digitalisation et système expert." Montpellier 1, 1990. http://www.theses.fr/1990MON11208.
Full textStern, Paul-Eric. "Un système expert en lecture de spectrogrammes." Paris 11, 1986. http://www.theses.fr/1986PA112321.
Full textDespite the extreme variability of the speech signal, some experienced phoneticians are able to decode a visual representation of speech, the spectrogram, with more efficiency than automatic recognition systems do. Mastering this expertise is the key to high-performance phonetic recognition; this may efficiently be undertaken by artificial intelligence techniques. We present an expert system allowing us to model and test such expertise. The system reasoning uses features describing the spectrogram and develops a global strategy on the whole spectrogram, reinforcing confidence value of hypotheses when several features suggest the same hypothesis
Darnault, Régis. "Système expert d'aide à la conception : application au positionnement d'appareils électriques." Grenoble INPG, 1995. http://www.theses.fr/1995INPG0069.
Full textBraham, Najoua. "Organisation d'un système de simulation de cas autour d'un système expert en hématologie." Compiègne, 1986. http://www.theses.fr/1986COMPS144.
Full textMassie, Jean-Marc. "L'avenir du sujet à l'ère des nouvelles technologies de l'information et de la communication : l'impact socio-politique du système expert." Paris 1, 1994. http://www.theses.fr/1994PA010289.
Full textThis research deals with the relationship between the society and new technologies information and communication (NTIC). More precesely it focuses on the relationship between the computer networks and those who use it. In this context, the two following questions must be considered : what futur is therefore an individual's autonomy in this computer age? What are the ideologies behind artificial intelligence system (AI) and particulary by expert system? The author's responds to these questions take the form of two hypotheses : 1. The creator of expert system and more generaly programmers, target and therefore favour the non-autonomus user. 2. The ideologies behind the ntic are the result of mutual determination by emerging techological advances and present day society. In order to prove this hypotheses, he analyses the theory of particulary Simon, Minsky, and Winograd and Flores, all of whom are practicians-thepricians. In short, the author predicts the futur of the expanding and accessible computer area by focusing theoretical and practical. This will enable him to achieve a greater understanding of the underline ideologies of computer development from it's roots up to the present day. This in turn will enable the author to re-evaluate the possibilities of envisaging a more humanist futur for the computer, and to conclude by sketching a computer ethic. This ethic aim to maintain the individual's autonomy by drawning conclusion from expert system and virtual reality technology
Poli, Christine. "S. E. C. C : système expert pour les codes correcteurs d'erreurs." Toulouse 3, 1995. http://www.theses.fr/1995TOU30223.
Full textBenchaouine, Driss. "Système expert en mécanique. : Application au choix et aux montages des éléments technologiques : Sous-titre." Lyon, INSA, 1993. http://www.theses.fr/1993ISAL0024.
Full textThe mechanical engineering design is based on technologie choice of mechanical components. Choices are made from several criteria which can move on time. This dissertation is a contribution in extracting a methodology of mechanical element choice trough two particular case of rolling bearings and belts. A specif methods of expert system have been introduced and inference engine has developed. Knowledge bases and frames are used to organize the know how of the subjects. Further components calculations are introduced in order to take into account local mechanical environment. Thus logic rules and calculations have been implemented and interaction have been studied
Gandelin, Marie-Hélène. "Une approche système expert pour la reconnaissance automatique d'organismes marins à partir d'images monoculaires." Nice, 1989. http://www.theses.fr/1989NICE4311.
Full textFauveau, Armelle. "Construction d'un système expert en économétrie : application à la demande d'énergie." Paris 2, 1992. http://www.theses.fr/1992PA020158.
Full textThe proper use of econometric softwares requires both statistical and economic skill. The main objective of this thesis is to provide the users of regression programs with assistance in the process of regression analysis, by means of expert system technology. We first built an expert system providing general econometric strategy. Then we considered the inclusion of the economic knowledge required to produce a consistent analysis ; we focused on energy demand modelling
Bassano, Jean-Claude. "DIALECT, un système expert pour la recherche documentaire." Paris 11, 1986. http://www.theses.fr/1986PA112008.
Full textThe aim of the project, with the experimental system DIALECT, is to improve retrieval effectiveness and to suggest some flexible uses for information retrieval systems. This research involves the integration of artificial intelligence (AI) and information retrieval (IR) techniques. The quality of the services usually provided by automatic information retrieval systems has been found inadequate. The particular problem to be solved here by the “expert system” in the environment of information retrieval is the automatic request reformulation: the replacement of the starting entries by a variety of “equivalent” sentence formulations. The request is automatically developed and transformed in order to retrieve additional documents. The system uses rules, meta-rules and linguistic models as meta-rules or another expert level. Starting from a request in natural language, the methods must first retrieve some of the more relevant bibliographical information with necessarily natural language texts. Rules of a linguistic model construct some reformulation rules from these previously selected sentences of texts… So the first document retrieval steps act as the selecting of the candidate reformulation rules. The query reformulation and the search process are highly interactive: they act as rule selecting and rules setting in the “expert system”. The system goes through a cycle: query (re)formulation, retrieval of candidate rules which are explicitly “built” only at this time. So the basic information provided in the “knowledge base”, which gives the inference rules capable of generating new facts from already existing ones, is the document collection itself. Simultaneously a set of relevant documents is proposed. This dynamic process is repeated over and over until it reaches the point where it becomes entitled to stop. This incorporation of linguistic procedures and “query reformulation” knowledge-based expert system in a retrieval setting increases the effectiveness of the system. But, it also leads to added benefits in the form of new and more sophisticated services. The following extensions of the “standard” retrieval service are: (1) the use of natural language front-end allows the user to interact with the system using French in their initial information request. (2) Friendly interfaces are available. We provide the users with a large degree of flexibility in choosing how to interact with the system. The system may operate under several modes: (i) A so called “casual user mode” provides the user with a fully transparent process which decides on its own on any opportunity to improve the request. The user only submits his query in French and lets the system search and display the relevant available information as a list of retrieved documents and/or portions of documents. (ii) The so called “expert assistant-documentalist-mode” allows the trained user to break more frequently into the process, if he wants to improve and control its returns. Such an improvement may consist in redefining some elements of the “semantic classes”, adding or removing propositions, using underlying models of the internal representations such as informative indexes and/or bibliographic information etc. For such a user, the system leads the dialogue: another function of the query reformulation part of this system is then to assist the user in producing complex Boolean descriptions of the required documents. The system is useful for consultation by expert users, but it can also train the unexperienced users… (iii) A so called “specialist mode” provides tracks allowing designeers –linguists, analysts, etc. - to oversee the operating processes and to break in by means of a specialized language in order to “modify the rules”
Chancelier, Jean-Philippe. "Identification de processus de diffusion avec sauts et mise en œuvre dans le cadre d'un système expert." Paris 9, 1989. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1989PA090029.
Full textFezzani, Djamel. "Système expert pour la conception en électronique de puissance." Toulouse, INPT, 1996. http://www.theses.fr/1996INPT008H.
Full textBrangier, Éric. "La modélisation de la cognition dans l'élaboration d'un système expert." Metz, 1991. http://docnum.univ-lorraine.fr/public/UPV-M/Theses/1991/Brangier.Eric.LMZ911.pdf.
Full textThis thesis deals with the problem of cognition modelisation when elaborating a decision aiding expert system in the field of life-insurance. We intend to show that this modelisation can be seen as the design of a functional architecture based on the expert's concepts and reasonings. This architecture consists into a "programmable" circuit in which knowledge is organized in two complementary ways. On the first hand concepts are gathered into categories, which cover the various topics of insurance medecine. In each category, concepts are ordered into classes and classes instances and related to each other through subordination or conceptual dependency relations. On the second hand, the expert reasonings are represented by production rules and inference schemes, whose activation tries to simulate respectively the diagnostic and pronostic activities of the human expert. Therefore, the decision making process can be considered as an activation process of the circuit made up of the concepts categorization, the production rules and the inference schemes. The circuit activation is based on the constant search of the most relevant pieces of knowledge, and seeks to trigger inferences allowed for given logical, syntactical and semantical contents of the knowledge in the different places of the circuit. This particular knowledge with logical, syntactical and semantical contents at once, is called "cognitive operators". Finally, we sought to validate our model by comparing the expert system answers with those of three experts. It appeared that the decisions made by the expert system and the explanation given are considered globally acceptable by the human experts
Ohayon, Maurice. "Apports de la représentation orientée objet dans la conception et la réalisation d'un système expert en psychiatrie." Aix-Marseille 3, 1992. http://www.theses.fr/1992AIX30091.
Full textGiron, Alain. "Système expert dans le diagnostic et la thérapeutique des cancers de l'ovaire : méthodologie d'évaluation." Compiègne, 1990. http://www.theses.fr/1990COMPD287.
Full textRepusseau, Philippe. "Système expert d'assistance à la navigation des hélicoptères à partir de données géographiques numériques." Compiègne, 1988. http://www.theses.fr/1988COMPD151.
Full textDuring mission, pilots of helicopter share their activities between 80 % for navigation and 20 % for tactics. The present work has been concerned with searching and evaluating means to reverse those ratios. First, I identified coherent tools for helping in strategies development, mission preparation and mission control in real time. Thanks to a pilot's expertise, I propose a modelization of aircraft attitudes related to the ground. Tactical inference stems from the fusion of two factors : security, when the aircraft is directly threatened and safety when it can be seen or recognized. Possible land representations and services they can offer have been identified and classified according to the needs. A particular study has been conducted for a runtime machine. Studying state of the art in architectures, processing and market survey, it appeared that executing artificial intelligence languages at runtime is not efficient. A realistic approach is to take on this problem at the expert system shell level and produce, both, compatible code for dedicated lA workstations with rich environment and for runtime machines faster but with a less powerful environment than the previous one. The “Assistant Tactique” prototype uses the capabilities of the expert system shell named SPOCK to produce different codes : COMMON Lisp and Le lisp for development, C for testing on RISC processors. Object oriented techniques avoid problem of target code translations and speeds up prototyping
Forte, Anne-Marie. "Système basé sur la connaissance pour l'identification, la caractérisation et la mise en correspondance d'entités anatomiques et fonctionnelles en imagerie médicale multimodalité." Tours, 1991. http://www.theses.fr/1991TOUR3302.
Full textNicaud, Jean-François. "Aplusix : un système expert de résolution pédagogique d'exercices d'algèbre." Paris 11, 1987. http://www.theses.fr/1987PA112480.
Full textAPLUSIX is an I. C. A. I. System which purpose is to teach reasoning. The student is freed from calculation during interaction with the system. APLUSIX is a complement for traditional teaching which is more turned towards calculation training. This thesis presents mainly the expert module which realizes pedagogical resolutions. The domain is factorization of polynomials and resolution of equations and inequations. This domain includes a lot of important difficulties in reasoning control when one's does not limit itself to some archetypal exercises. The solver uses expert system technics. It takes care of the student's profile. It solves non trivial exercises, using backtrack when necessary. Its reasoning is close to human reasoning. It contains four features of human reasoning which are only sometimes separately found in artificial solvers:- Subexpression manipulation: most of the solvers use artificial decomposition in subproblemes- A sharp splitting between factual and control knowledge; control knowledge is implemented as meta-rules. - An heuristic reasoning which takes in account the whole deduction tree (many solvers have a local vision about control)- Autonomy: there is neither outside algebraic calculus nor human intervention. APLUSIX has three interaction moods and an ergonomic interface in order to bring a play look to exercises’ solving. The module handling the updating of the student's profile is in process. APLUSIX is written in LISP and runs on Macintosh. Its validation has begun
Ribero, Bernard. "Gcdata : banque de données et système expert d'estimation de propriétés physico-chimiques et thermodynamiques." Aix-Marseille 3, 1989. http://www.theses.fr/1989AIX30083.
Full textDel'homme, Bernard. "Contribution à l'automatisation du diagnostic de gestion dans l'entreprise agricole : élaboration d'un système expert." Bordeaux 4, 1996. http://www.theses.fr/1996BOR40002.
Full textFaced with increasing uncertainty as to the future, the farm needs a regular evaluation of it's technical and financial performances. In order to systematize such a diagnosis, it's modelisation and computerisation has been decided, through an expert system. To build an expert system, it is necessary to define methodological ways. First, solutions in the field of artificial intelligenge and computerized tools must be found. Secondly, an homogeneised diagnosis method on farm management is required. Tereafter, building an expert system is possible. It has been done with nine advisory centers in agriculture, in the north of france. A specifical methodology for building the expert system has been used, from the sot up of diagnisis to the building of the computerized tool. Then, the relevance of the automatized diagnosis is analised; therefore, the expert system tool and the management commentary are assessed. Even if the tool produced brings satisfaction to users, the relevance of the artificial diagnosis releis mostly on the information used. It is first of all in the field of information that improvment can be carried on
Gleizes, Marie-Pierre. "Spécification d'une architecture de système multi-expert." Toulouse 3, 1987. http://www.theses.fr/1987TOU30256.
Full textTanic, Emile Camille. "Contribution à l'étude d'un Système Expert en Planification Urbaine : le projet URBYS." Paris 7, 1986. http://www.theses.fr/1986PA077077.
Full textGrange, Marc. "Conception et réalisation d'un système expert pour l'aide à la prise de décision en gestion." Lyon 3, 1987. http://www.theses.fr/1987LYO33001.
Full textIn this study we describe an approach for coupling experts systems with data-base management systems. The combined use of data base managemengt system and artificial intelligence bases experts systems is interesting for business applications management aided decisions. We first explore and describe essential characteristics of the deductive system we propose. We then show different steps of cooperations between the inference engine and the dbms, and how the expert system gets is data. The main contribution of our work is to propose a prototype of an integrated system which can be seen as a first step toward a knowledge base management system
Dupont, Daniel. "Observation et aide à la décision : application à la conception d'un observateur numérique couplé à un système expert." Lille 1, 1986. http://www.theses.fr/1986LIL10001.
Full textIppolito, Serge. "Commande numérique d'un processus industriel et aide à la conduite au moyen d'un système expert." Toulouse 3, 1988. http://www.theses.fr/1988TOU30017.
Full textYacef, Kalina. "Vers un assistant tutoriel intelligent pour la formation d'opérateurs de systèmes complexes et dynamiques." Paris 5, 1999. http://www.theses.fr/1999PA05S017.
Full textLassoued, Abdelhakim. "Set : système expert d'aide au diagnostic thermique : une approche de la représentation des connaissances en conception." Compiègne, 1989. http://www.theses.fr/1989COMPD281.
Full textThe first part describe the knowledge elicitation and representation for an Expert System in Thermal diagnosis : SET. An implementation with the system LAP combining PROLOG and Object Oriented Programming is also described. The second part presents a formalism and an approach suited to knowledge representation and manipulation in DESIGN
Reyssier-Danzart, Annie. "Serebral, un système expert pour l'aide à l'interrogation d'une base de données." Paris 11, 1985. http://www.theses.fr/1985PA112284.
Full textFlexible query of data bases has provoked the interest of researchers in artificial intelligence. We have developed a tool called SEREBRAL that makes it possible to query a data base intelligently. This data base contains descriptions of jobs offered by computer science firms. SEREBRAL is made up of three modules: BASEXP, an expert system that allows a user to carry out a search for a job in computer science, an interface with the data base, a relational data base ORACLE (distributed by ORACLE Corporation) in which descriptions of job vacancies are stored. The main concern of the research carried out was the development of an expert system called BASEXP. This system of knowledge representation and knowledge exploitation uses schemes and rules in association with credibility factors. It can be used in various fields like that which was examined in this study. Ln order to query the data base, we developed an interface that generates the SQL queries, These queries adapt themselves to the constraints generated by BASEXP in the field of computing jobs. The interface then transmits these queries to the DBMS. Finally, it communicates the responses of the base to the user. SEREBRAL is now operational and can dialogue with the job seeker, for whom a job profile can be drawn up so that he can receive those job offers stored in the base that correspond to his profile
Adjaoute, Akli. "Rylm : générateur de systèmes experts pour les problèmes d'aide aux diagnosticsYkra : système d'enseignement." Paris 6, 1988. http://www.theses.fr/1988PA066005.
Full textWang, Gang. "Principes généraux d'aide à la conception et au développement d'un système expert temps réel : application à la fusion multi-sensorielle." Montpellier 2, 1992. http://www.theses.fr/1992MON20286.
Full textDurand, William. "Automated test generation for production systems with a model-based testing approach." Thesis, Clermont-Ferrand 2, 2016. http://www.theses.fr/2016CLF22691/document.
Full textThis thesis tackles the problem of testing (legacy) production systems such as those of our industrial partner Michelin, one of the three largest tire manufacturers in the world, by means of Model-based Testing. A production system is defined as a set of production machines controlled by a software, in a factory. Despite the large body of work within the field of Model-based Testing, a common issue remains the writing of models describing either the system under test or its specification. It is a tedious task that should be performed regularly in order to keep the models up to date (which is often also true for any documentation in the Industry). A second point to take into account is that production systems often run continuously and should not be disrupted, which limits the use of most of the existing classical testing techniques. We present an approach to infer exact models from traces, i.e. sequences of events observed in a production environment, to address the first issue. We leverage the data exchanged among the devices and software in a black-box perspective to construct behavioral models using different techniques such as expert systems, model inference, and machine learning. It results in large, yet partial, models gathering the behaviors recorded from a system under analysis. We introduce a context-specific algorithm to reduce such models in order to make them more usable while preserving trace equivalence between the original inferred models and the reduced ones. These models can serve different purposes, e.g., generating documentation, data mining, but also testing. To address the problem of testing production systems without disturbing them, this thesis introduces an offline passive Model-based Testing technique, allowing to detect differences between two production systems. This technique leverages the inferred models, and relies on two implementation relations: a slightly modified version of the existing trace preorder relation, and a weaker implementation proposed to overcome the partialness of the inferred models.Overall, the thesis presents Autofunk, a modular framework for model inference and testing of production systems, gathering the previous notions. Its Java implementation has been applied to different applications and production systems at Michelin, and this thesis gives results from different case studies. The prototype developed during this thesis should become a standard tool at Michelin
Mourmouris, Jean. "Transport et choix résidentiel : Hestia-Hermès, un système multicritère interactif." Paris 9, 1987. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1987PA090060.
Full textThe present methodological character research is based on a D. S. S. (decision support system) development, aiming at analysing the residential choice decision process. Transportation network, residential supply and environmental criteria are taken into account in order to study residential mobility. The system can be viewed both as a decision-making tool for households in moving and as a simulation model for urban growth useful for planners. This multiple-criteria interactive decision aid simulation (MIDAS) is built on new concepts such as subjective interval of preferences, psychological convergence by a trade-off type operation, dynamic visualization and mental map definition of individual spatial perception. These concepts are inspired by interactive approaches, the evolutive target procedure and experimental psychology, and designed to improve information acquisition and processing tools. For the Hestia-Hermès computerized prototype model, fortran-77 is used in a bull-dps 8 multics main-frame system, with a G. K. S. Graphic software and a tektronix4107 color display terminal. Two experiments have been undertaken: one concerning the residential choice behavior of white collars working in the same company and another testing the reliability of the man-machine interaction established by the system. The system proposed focuses on the traditional investigation and sounding substitution, offering simultaneously the opportunity of information acquisition and processing. Consequently the individual is considered at the same time as a source of information and decision-maker. Further development perspectives using Minitel communication network open large application fields. The whole research was designed, developed, realized and implemented in collaboration with : INRETS (national institute of transportation and traffic safety) and LAMSADE (laboratory of system analysis and modelling for decision-making)
Jauffret, Philippe. "Le transfert d'expertise : Application à la réalisation d'un système d'aide à la synthèse en chimie organique." Nancy 1, 1987. http://www.theses.fr/1987NAN10191.
Full textBeurton-Aimar, Marie. "Architecture d'un système d'aide au diagnostic médical : application en rhumatologie inflammatoire." Bordeaux 2, 2000. http://www.theses.fr/2000BOR28712.
Full textAl-Moussa, Yasser. "Un langage de spécification de la connaissance statistique dans un cadre de système expert de contrôle de qualité." Aix-Marseille 3, 1991. http://www.theses.fr/1991AIX32036.
Full textThis work want to define a model of an expert system for representation and resolution of the quality statistical control problem (reception control and by attributs case). The structure of this model is based on the definition of a specification language of statistical knowledge for representation and resolution of the problem by the decisional statistical model (conception methodes of the decision rules according to the differentes statistical principales). The statistical knwledge are sometime heuristic, so they are represented by production rules : algorithmic ones are represented by tangly processes, ordered by the rules. The same type of knowledge are grouped in the same modules. Each module has got one or more tasks, according a general reasoning strategy;. The expertise in the domain (conception methode of a sampling plan) are represebted by strategies, in a module "control strategies". The knowledges of these modules are susceptible to create formal representation by the specification language, by the countershaft of the module "representation by statistic" of the environment and the objectives control" with conceptionof the decisional statistical model
Fahlaoui, Ouafae. "Système expert de génération automatique de Grafcet à partir d'une spécification lexicale libre du cahier des charges." Paris 11, 1987. http://www.theses.fr/1987PA112204.
Full textCharles, Smith. "Conception d'un système expert pour l’étude de la sécurité incendie de bâtiments dans un contexte pluridisciplinaire." Lyon, INSA, 1992. http://www.theses.fr/1992ISAL0025.
Full textFire safety is a component of the technical function of a building. It is generally taken into account by the application of regulations. We propose a different method based on the search of risk factors and the best measures for their elimination. Our method is a systemic one which integrates knowledges about the technical, architectural and economic functions of the building. The works described concern: - a method of risk assessment based on belief-trees combining favourables and unfavourable probabilist hypotheses. - an expert-system for studying the fire safety of buildings providing two modes of expertise : one for the focalised studies, one for the more general expertise guided by a tasks scheduler. - a tool for developing large expert-systems managing many knowledge sources in natural language. - a knowledge elicitation method to enhance the knowledge engineer's performance by the anticipation of what knowledge to extract and how to proceed