A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network. (January 2020)

• Record Type: Journal Article
• Authors: Wang, Yalin; Pan, Zhuofu; Yuan, Xiaofeng; Yang, Chunhua; Gui, Weihua
• Is Part Of: ISA transactions. Volume 96(2020)
• Page Start: 457
• Page End: 467
• Publication Date: 2020-01
• Subjects: Fault detection and diagnosis -- Deep learning -- Deep belief network -- Extended DBN; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2019.07.001
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Deep learning networks have been recently utilized for fault detection and diagnosis (FDD) due to its effectiveness in handling industrial process data, which are often with high nonlinearities and strong correlations. However, the valuable information in the raw data may be filtered with the layer-wise feature compression in traditional deep networks. This cannot benefit for the subsequent fine-tuning phase of fault classification. To alleviate this problem, an extended deep belief network (EDBN) is proposed to fully exploit useful information in the raw data, in which raw data is combined with the hidden features as inputs to each extended restricted Boltzmann machine (ERBM) during the pre-training phase. Then, a dynamic EDBN-based fault classifier is constructed to take the dynamic characteristics of process data into consideration. Finally, to test the performance of the proposed method, it is applied to the Tennessee Eastman (TE) process for fault classification. By comparing EDBN and DBN under different network structures, the results show that EDBN has better feature extraction and fault classification performance than traditional DBN. Highlights: An extended DBN is proposed for feature extraction and fault classification. Raw data is combined with hidden features at previous ERBM as inputs for next one. EDBN is beneficial for retaining enough valuable information from raw data. High classification performance of the extended DBN is validated on TE process.