Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (2): 370-375.DOI: 10.11772/j.issn.1001-9081.2018061371

Previous Articles     Next Articles

Fault detection method for batch process based on deep long short-term memory network and batch normalization

WANG Shuo1, WANG Peiliang2   

  1. 1. Institute of Electron Devices and Application, Hangzhou Dianzi University, Hangzhou Zhejiang 310018, China;
    2. Institute of Information and Control Technology, Huzhou University, Huzhou Zhejiang 313000, China
  • Received:2018-07-02 Revised:2018-08-19 Online:2019-02-10 Published:2019-02-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61573137).


王硕1, 王培良2   

  1. 1. 杭州电子科技大学 新型电子器件与应用研究所, 杭州 310018;
    2. 湖州师范学院 信息与控制技术研究所, 浙江 湖州 313000
  • 通讯作者: 王培良
  • 作者简介:王硕(1994-),男,山东淄博人,硕士研究生,主要研究方向:人工智能与控制、工业过程故障检测;王培良(1963-),男,浙江湖州人,教授,硕士,主要研究方向:智能检测与控制、系统建模、故障诊断、工业自动化。
  • 基金资助:

Abstract: Traditional fault detection methods for batch process based on data-driven often need to make assumptions about the distribution of process data, and often lead to false positives and false negatives when dealing with non-linear data and other complex data. To solve this problem, a supervised learning algorithm based on Long Short-Term Memory (LSTM) network and Batch Normalization (BN) was proposed, which does not need to make assumptions about the distribution of original data. Firstly, a preprocessing method based on variable-wise unfolding and continuous sampling was applied to the batch process raw data, so that the processed data could be input to the LSTM unit. Then, the improved deep LSTM network was used for feature learning. By adding the BN layer and the representation method of cross entropy loss, the network was able to effectively extract the characteristics of the batch process data and learned quickly. Finally, a simulation experiment was performed on a semiconductor etching process. The experimental results show that compared with Multilinear Principal Component Analysis (MPCA) method, the proposed method can identify more faults types, which can effectively identify various faults, and the overall detection rate of faults reaches more than 95%. Compared with the traditional single-LSTM model, it has higher recognition speed, and its overall detection rate of faults is increased by more than 8%, and it is suitable for dealing with fault detection problems with non-linear and multi-case characteristics in the batch process.

Key words: data driven, deep learning, Long Short-Term Memory (LSTM) network, batch process, fault detection

摘要: 传统的基于数据驱动的间歇过程故障诊断方法往往需要对过程数据的分布进行假设,而且对非线性等复杂数据的监控往往会出现误报和漏报,为此提出一种基于长短期记忆网络(LSTM)与批规范化(BN)结合的监督学习方法,不需要对原始数据的分布进行假设。首先,对间歇过程原始数据运用一种按变量展开并连续采样的预处理方式,使处理后的数据可以向LSTM单元输入;然后,利用改进的深层LSTM网络进行特征学习,该网络通过添加BN层,结合交叉熵损失的表示方法,可以有效提取间歇过程数据的特征并进行快速学习;最后,在一类半导体蚀刻过程上进行仿真实验。实验结果表明,所提方法比多元线性主成分分析(MPCA)方法故障识别的种类更多,可以有效地识别各类故障,对故障的整体检测率达到95%以上;比传统单层LSTM模型建模速度更快,且对故障的整体检测率提高了8个百分点以上,比较适合处理间歇过程中具有非线性、多工况等特征的故障检测问题。

关键词: 数据驱动, 深度学习, 长短期记忆网络, 间歇过程, 故障检测

CLC Number: