Bridging control and artificial intelligence theories for diagnosis: A survey

Diagnosis is the process of identifying or determining the nature and root cause of a failure, problem, or disease from the symptoms resulting from selected measurements, checks or tests. The different facets of this problem and the wide spectrum of classes of systems make it interesting to several communities and require bridging several theories. Diagnosis is actually a functional fragment in fault management architectures and it must smoothly interact with other functions. This paper presents diagnosis as it is understood in the Control and Artificial Intelligence fields, and exemplifies how different theories of these fields can be synergistically integrated to provide better diagnostic solutions and to achieve improved fault management in different environments.