Automation of rapid fault diagnosis in manufacturing systems using multiple fuzzy agents

The reasoning process used by humans for fault diagnosis is very difficult to model due to the many factors used in developing a hypothesis. Some of these factors do not correspond to cognitive models. The diagnosis of faults in manufacturing systems is often plagued with human emotions and “gut feelings” which are difficult, if not impossible, to model. Many artificial intelligence approaches to automated fault diagnosis use either structural or symptom-based reasoning. Functional approaches are unable to provide realtime response due to their computational complexity, whereas, symptom-based approaches are only able to handle situations specifically coded in rules. Current hybrid approaches that combine the two methods are too structured in their approach to switching between the reasoning methods and, therefore fail to provide the flexible, rapid response of human experts. This paper presents a robust, extensible approach to fault diagnosis that allows unstructured switching between reasoning models using multiple fuzzy intelligent agents that examine the problem domain from a variety of perspectives.