收录:
摘要:
Fault monitoring can find out-of-control conditions of equipment operation in a timely manner, which is essential for eliminating faults and for stable operation of industrial systems in batch processes. Many conventional data-driven fault detection methods focus less on the non-Gaussian and Multi-stage characteristics of batch process data, which may result in degradation of monitoring performance. In this paper, a Multi-stage Fourth Order Moment Staked Autoencoder (M-FOM-SAE) is designed to solve the above problems. The proposed method firstly automatically determines the number of clusters and divides the batch process into multiple stages. After that, the FOM-SAE model is established in each sub-stage, which can not only effectively learn the nonlinear features of process data, but also extract the non-Gaussian information. The proposed strategy is applied to real-world industrial processes. Experimental results indicate that it can better capture the non-Gaussian and Multi-stage characteristics of process data, and improve the ability to monitor abnormalities.
关键词:
通讯作者信息:
电子邮件地址:
来源 :
PROCEEDINGS OF THE 32ND 2020 CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2020)
ISSN: 1948-9439
年份: 2020
页码: 721-728
语种: 英文
归属院系: