Fault diagnosis in assembly processes based on engineering-driven rules and PSOSAEN algorithm

The ability to detect and isolate process fault for product quality control in assembly processes plays an essential role in the success of a manufacturing enterprise in today's globally competitive marketplace. However, the complexity of assembly processes makes it fairly challenging to diagnose process faults. One novel fixture fault diagnosis methodology has been developed in this study. The relationship between fixture fault patterns and part variation motion patterns is firstly off-line built, then |S| control chart is used as the detector of abnormal signals, and an improved Particle Swarm Optimization with Simulated Annealing-based selective neural network Ensemble (PSOSAEN) algorithm is explored for on-line identifying the part variation motion patterns triggering the out-of-control signals. Finally, an unknown fixture fault is identified based on the output of PSOSAEN algorithm and explored diagnosis rules. The method has excellent noise tolerance in real time, requires no hypothesis on statistical distribution of measurements, and has explicit engineering interpretation of the diagnostic process. The data from the real-world aircraft horizontal stabilizer assembly process were collected to validate the developed methodology. The analysis results indicate that the developed diagnosis methodology can perform effectively for fixture fault diagnosis in assembly processes. All of the analysis from this study provides guidelines in developing selective neural network ensemble and statistical process control-based fault diagnosis systems with integration of engineering knowledge in assembly processes.