An integrated method for variation pattern recognition of BIW OCMM online measurement data

In order to improve the quality of the body-in-white (BIW), optical coordination measurement machines (OCMM) are used to measure the dimensional variation for BIW. The big OCMM online measurement data with low signal-to-noise ratio makes the variation patterns recognition to be difficult and challenges the traditional statistical process control (SPC) technology and the common variation recognition approaches. In this paper, we propose an automatic and integrated method to recognise the control chart patterns (CCPs), which includes three main modules. The Jarque-Bera test is applied in the wavelet denoising module. The feature extraction module extracts a combination set of shape features and statistical features. In the classifier module, a two-hidden-layer Backpropagation neural network (BPN) is trained and tested. In the experiment, the proposed method is also compared with other CCPs recognition methods. Finally, a practice case is studied to show the application of the integrated method and validate the high recognition accuracy of the integrated system.

Automated summary

This study proposes an automatic and integrated method for recognizing control chart patterns, which consists of three main modules: wavelet denoising, feature extraction, and classifier. Through comparison with other methods and application in a practical case, the high recognition accuracy of the integrated method is validated.