Application of Case-Based Reasoning to the safety assessment of critical software used in rail transport

Abstract

The risk assessment of railway accidents requires the implementation of several safety analysis methods such as Preliminary Hazard Analysis, Functional Safety Analysis, Analysis of Failure Modes, their Effects and their Criticality and Software Error Effect Analysis (SEEA). The study proposed within the framework of this article concerns the SEEA method whose objective is to determine the nature and severity of the consequences of software failures, to propose measures to detect errors and improve the robustness of the software. The goal is to develop a new approach to analysis and evaluation of the safety of critical software, based on machine learning and more precisely on the Case-Based Reasoning (CBR). The approach adopted involves two main activities: The first step in acquiring safety knowledge consists in extracting, modeling and archiving dangerous situations to produce a library of standard cases which covers the entire problem. The second stage of machine learning is to exploit historical knowledge (experience feedback) in order to assist safety experts in their critical task of analyzing and assessing the safety of software involved in guided or automated rail transport systems. This second activity involves the use of Case-Based Reasoning (CBR).