The Method Research On Mixed-signal Circuit Fault Diagnosis Based On ANNES

It is of great importance to the fault diagnosis on mixed-signal circuits because both analog and digital signal are included in most circuits and systems. Based on some approach, both analog and digital signal characteristics are unified. It has been proved in many documents that the transient response testing (TRT) is an efficient approach on the testing to mixed-signal circuits and it is appropriate for engineering application. The testing was accomplished by TRT in this paper.When a diagnostic ES works, it develops conclusions by analyzing the fault characteristics using the domain knowledge from domain experts. In this paper, we investigated how to build a diagnostic ES for mixed-signal circuits based on TRT. The experimental results show that we can achieve a splendid fault diagnosis efficiency (nearly 100%).By analyzing the advantages and shortcomings of the ES, we built another system called ANNES by recommending artificial neural network (ANNES) which is popular in the diagnostic domain on the base of the ES to improve property of the ES. The diagnostic portion of the system is based on neural-calculation approach, which is used to establish the knowledge base composed of the weigh values and threshold values. With this approach, conclusions are developed directly from the outputs of the net, rather than the domain knowledge in traditional expert system. Compared with the traditional expert system, this system is good at processing data. The experimental results show that the system not only improves the shortcoming of the traditional expert system such as the deficiency on knowledge acquisition and self-learning capability, but also achieves a satisfied fault diagnosis efficiency.Although some conclusions are achieved in this paper, there are still some differences from the practical application. It should be investigated in the future.