Diagnosing from descriptive knowledge bases

Deals with a diagnostic method using so-called descriptive knowledge bases. It is based on the concept of using a MIMO (multiple-input, multiple output) fuzzy model to represent the information contained in the knowledge base. The model structure and initial parameter values are estimated by applying FMEA (failure mode and effect analysis). Finer parameter estimates are obtained by using a backpropagation learning algorithm. Rules for learning the parameters of a MIMO fuzzy model are derived. An actual diagnostic problem is solved by using an an optimization algorithm for inverting the MIMO fuzzy model.