Control chart pattern recognition for imbalanced data based on multi-feature fusion using convolutional neural network

As the most practical quality control process monitoring tool, control chart patterns (CCPs) can determine abnormal conditions in the production process. Therefore, automatic and accurate recognition of CCP is critical for improving production efficiency and quality in the manufacturing process. In the actual production process, the CCPs data has mixture patterns as well as single patterns, more importantly, the control chart pattern data proportion is imbalanced. Manual recognition is a costly endeavor, and automatic recognition is simpler and more effective. By applying the deep learning method to control chart pattern recognition (CCPR), abnormal patterns can be recognized in real-time. In this paper, the SMOTE method was used to balance the imbalances in data set, then some features in the control chart patterns were extracted and fused with the data. A method of abnormal control chart pattern recognition based on imbalanced data was proposed by using convolutional neural network. A comparison was made between the performance of the convolutional neural network and that of other methods in recognizing imbalanced patterns in control charts. According to the simulation results, compared with the raw data and other classifiers, the proposed multi-feature fusion and convolutional neural network (MFF-CNN) method has a better recognition performance for abnormal CCPs.