Abnormal Condition Detection Method of Industrial Processes Based on the Cascaded Bagging-PCA and CNN Classification Network

The accurate detection of abnormal working conditions is very important for the safe and stable operation of production process in process industry. Considering that normal data can be easily obtained in industry, unsupervised learning is one of the important methods of anomaly detection. Different from the experience setting of unsupervised anomaly detection index, supervised learning can set anomaly detection index automatically. But it is mostly used in the research of fault classification. In this article, a new cascaded bootstrap aggregating (Bagging) principal component analysis and convolutional neural network classification network (CBPCA-CNN) was proposed to realize supervised anomaly detection. The proposed CBPCA-CNN method had the advantages of unsupervised feature extraction and supervised classification decision, which was helpful to improve the detection accuracy. The validation results on the standard dataset of the Tennessee–Eastman process showed that the average accuracy of the CBPCA-CNN method was 97.67%, which was higher than the compared methods. This article verified the feasibility of using supervised learning method to solve anomaly detection.