Search

International audience; Various researches in artificial intelligence are conducted to understand the transfer of expertise problem. Today we perceive two major independent research activities: the acquisition of knowledge which aims to define methods inspired specially from software engineering and cognitive psychology to better understand the transfer of expertise, and the automatic learning proposing the implementation of inductive, deductive, abductive techniques or by analogy to equip the system of learning abilities. The development of a knowledge-based support system “ACASYA” for the analysis of the safety guided transport systems insisted us to use jointly and complementary both approaches. The purpose of this tool is to first, to evaluate the completeness and consistency of accidents scenarios and secondly, to contribute to the generation of new scenarios that could help experts to conclude on the safe character of a new system. “ACASYA” consists of three learning modules: CLASCA, EVALSCA and GENESCA dedicated respectively to the classification, evaluation and generation accident scenarios.

International audience; The study is from a base of accident scenarii in rail transport (feedback) in order to develop a tool to share build and sustain knowledge and safety and secondly to exploit the knowledge stored to prevent the reproduction of accidents / incidents. This tool should ultimately lead to the proposal of prevention and protection measures to minimize the risk level of a new transport system and thus to improve safety. The approach to achieving this goal largely depends on the use of artificial intelligence techniques in order to develop a feasibility model of a Knowledge base system to exploit stored knowledge in order to create know-how that can help stimulate domain experts in the task of analysis, evaluation and certification of a new system.

International audience; This paper describes a contribution to the improvement of the usual safety analysis methods used in automated people mover certification. The methodology is based on the complementary and simultaneous use of knowledge acquisition and machine learning. We used the ACASYA software environment to support the safety analysis aid methodology. It consists of three main modules : CLASCA, EVALSCA and GENESCA, respectively dedicated to the classification, evaluation and generation of accident scenarios. In contrast to traditional failure Diagnosis Systems, ACASYA can be seen as an aid which reveals potential accidents during the design stage of the automated people mover.

International audience; The study is from a base of accident scenarii in rail transport (feedback) in order to develop a tool to share build and sustain knowledge and safety and secondly to exploit the knowledge stored to prevent the reproduction of accidents / incidents. This tool should ultimately lead to the proposal of prevention and protection measures to minimize the risk level of a new transport system and thus to improve safety. The approach to achieving this goal largely depends on the use of artificial intelligence techniques and rarely the use of a method of automatic learning in order to develop a feasibility model of a software tool based on case based reasoning (CBR) to exploit stored knowledge in order to create know-how that can help stimulate domain experts in the task of analysis, evaluation and certification of a new system.

International audience; The purpose of the work described in this paper is to improve the production and assessment of safety analyses for guided transport systems by searching for errors at system level and in the hardware and software. The approach used to achieve this is mainly based on the use of artificial intelligence techniques, in particular knowledge acquisition and modelling techniques, knowledge-based systems, automatic symbolic learning techniques and knowledge validation techniques. This paper presents a general description of three mock-ups of tools which are intended to aid in the analysis and investigation of safety. These are:- SAPRISTI, for aid in the production and assessment of preliminary hazard analyses,- ACAYSA, for aid in the storage, classification and appraisal of accident scenarios,- SAUTREL, for aid in the examination of software error effect analyses.