Contribution of Automatic Learning and Ontology to the Prevention of Railway Accidents
Résumé
This paper proposes a Knowledge-based system based which involves a process of learning rules to assist certification experts in their crucial task of analysis and assessment of the safety for railway transport systems in France. The modes of reasoning which are used in the
context of safety analysis (inductive, deductive, and analogical) and the very nature of knowledge about certification (incomplete, evolving, empirical, and qualitative) confirm that a conventional computing solution is not appropriate and the use of artificial intelligence seems more
appropriate. Our research has involved several aspects of artificial intelligence: knowledge acquisition, machine
learning, expert systems and the ontologies to structure and model certain types of safety knowledge. Usually, development of the knowledge base in expert systems requires the use of knowledge acquisition techniques in order to collect, structure and formalizes knowledge. In practice and in the face of a complex certification domain, it has not been possible with knowledge acquisition to extract effectively some types of expert knowledge. Therefore, the use of knowledge acquisition in combination with machine learning appears to be a very promising solution. The
approach which was adopted in order to design and implement an assistance tool for safety analysis involved the
following two main activities:
(I) Extracting, formalizing and storing hazardous situations to produce a library of standard cases which covers the entire problem. This process entailed the use of knowledge acquisition techniques,
(II) Exploiting the stored historical knowledge in order to develop safety analysis know-how which can assist experts to judge the thoroughness of the manufacturer’s suggested safety analysis. This second activity involves the use of machine learning techniques.