Diagnosis of telephony line card component failures using an artificial neural network
A.B. Thompson, J.C. Sutton, H. Troy Nagle · 2002
The authors describe the development of a modular artificial neural network (MANN) that is suitable for the diagnosis of failures in high-volume printed circuit boards using both analog and digital components. A case study comparing the MANN to an existing expert system used for diagnosing telephony line card component failure is presented. The structure and training strategy for the MANN as well as the current status of the project are discussed.>