The ANN-based approach to identify behavior of a model

The approach to identify the behavior of a model using ANN(Artificial Neural Networks) is presented in this paper. The key idea of model-based diagnosis is to explicitly represent the knowledge about a device as a model of the device structure and of the behavior of its constituents and to organize diagnosis as an inference process based on this Model and the observed behavior. The paper focus on using ANN to learn the model's expected behavior, and using the trained ANN to identify the artifact's actual behavior. The layered perceptron model after trained can detect the conflict between the model's expected behavior and the observed behavior discriminate between the normal behavior and failure behavior, and carry out classification task correctly. Here, we integrate the layered network model into GED (the General Diagnostic Engine).