Journal
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
Volume 27, Issue 6, Pages 2526-2540Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCST.2018.2865413
Keywords
Monitoring; Principal component analysis; Feature extraction; Kernel; Eigenvalues and eigenfunctions; Computational modeling; Machine learning; Bayesian inference; deep learning; kernel principal component analysis (KPCA); nonlinear process monitoring
Funding
- Natural Science Foundation of Shandong Province, China [ZR2014FL016, ZR2016FQ21]
- National Natural Science Foundation of China [61403418, 21606256, 61273160]
- Fundamental Research Funds for the Central Universities [17CX02054]
- Shandong Provincial Research and Development Programme [2018GGX101025]
Ask authors/readers for more resources
In order to deeply exploit intrinsic data feature information hidden among the process data, an improved kernel principal component analysis (KPCA) method is proposed, which is referred to as deep principal component analysis (DePCA). Specifically, motivated by the deep learning strategy, we design a hierarchical statistical model structure to extract multilayer data features, including both the linear and nonlinear principal components. To reduce the computation complexity in nonlinear feature extraction, the feature-samples' selection technique is applied to build the sparse kernel model for DePCA. To integrate the monitoring statistics at each feature layer, Bayesian inference is used to transform the monitoring statistics into fault probabilities, and then, two probability-based DePCA monitoring statistics are constructed by weighting the fault probabilities at all the feature layers. Two case studies involving a simulated nonlinear system and the benchmark Tennessee Eastman process demonstrate the superior fault detection performance of the proposed DePCA method over the traditional KPCA-based methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available