The Fault Diagnosis of Automotive Airbag Assembly Process based on Self-organizing Feature Mapping Network SOM

摘要

Automotive airbag assembly process is complex and nonlinear, and one of its characteristics is that the accuracy of making the threshold comparison for fault diagnosis using field multi-sensor measured value is not high. In this article, adopt self-organizing feature mapping network SOM to realize the fault diagnosis of automotive airbag assembly process, constitute the field function of SOM through wavelet functions, form sub-excitatory neuron to update weights, avoid SOM local optimum, so improve the accuracy of fault diagnosis of automotive airbag assembly process.