Control chart recognition based on the parallel model of CNN and LSTM with GA optimization

Abstract

Quality control process has become one of the most critical issues in intelligent manufacturing. As the most practical and prevalent tools for continuously monitoring, control chart patterns (CCPs) can be automatically recognized to judge the fault of production process. However, there are three shortcomings in the previous researches. 1) Insufficient or superfluous features are considered; 2) Few studies simultaneously take the local features and time sequence information into account; 3) With the exception of empiricism, little work has been done on searching for the optimal hyper-parameters for the neural networks. Accordingly, FFR-GACLN, a method for ten CCPs recognition is proposed in this paper. Such a method is comprised of two sections including the fusion feature reduction (FFR) and GACLN model construction. Firstly, the feature extraction comprising of features fusion and feature dimensionality reduction by convolutional auto-encoder is applied to enhance the reliability and performance of the extracted features. Then, such features are input into GACLN, a network combining the convolutional neural network (CNN) and the long-short term memory (LSTM) for achieving the final recognition task. Moreover, genetic algorithm (GA) is applied to search for the optimal hyper-parameters for FFR-GACLN. The quantitative and simulation results demonstrate that the performance of the proposed method is superior over the previous techniques.