Dynamic Process Monitoring Based on Dot Product Feature Analysis for Thermal Power Plants

Xin Ma; Tao Chen; Youqing Wang

doi:10.1109/JAS.2024.124908

Volume 12 Issue 3

Mar. 2025

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 19.2, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2025 > 12(3): 563-574

X. Ma, T. Chen, and Y. Wang, “Dynamic process monitoring based on dot product feature analysis for thermal power plants,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 3, pp. 563–574, Mar. 2025. doi: 10.1109/JAS.2024.124908

Citation:

X. Ma, T. Chen, and Y. Wang, “Dynamic process monitoring based on dot product feature analysis for thermal power plants,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 3, pp. 563–574, Mar. 2025. doi: 10.1109/JAS.2024.124908

Citation:

PDF( 1321 KB)

Dynamic Process Monitoring Based on Dot Product Feature Analysis for Thermal Power Plants

doi: 10.1109/JAS.2024.124908

Funds: This work was supported in part by the National Science Fund for Distinguished Young Scholars of China (62225303), the National Natural Science Fundation of China (62303039, 62433004), the China Postdoctoral Science Foundation (BX20230034, 2023M730190), the Fundamental Research Funds for the Central Universities (buctrc202201, QNTD2023-01), and the High Performance Computing Platform, College of Information Science and Technology, Beijing University of Chemical Technology

More Information

Author Bio:
Xin Ma received the B.S. degree in biomedical engineering from Hebei University of Technology in 2017, and the Ph.D. degree in control science and engineering from Beijing University of Chemical Technology in 2022. From August 2022 to February 2023, she was an exchange student at the University of Surrey in the UK. She is currently a Postdoctoral Fellow with the College of Information Science and Technology, Beijing University of Chemical Technology. Her research interests include prognostic and health management, process monitoring, and intelligent fault diagnosis

Tao Chen received the B.Eng. and M.Eng. degrees from the Department of Automation, Tsinghua University in 2000 and 2002, respectively, and the Ph.D. degree in chemical engineering from Newcastle University, U.K., in 2006. From 2006 to 2007, He was a Research Associate with Newcastle University, U.K.. From 2008 to 2010, he was an Assistant Professor with Nanyang Technological University, Singapore. He joined the University of Surrey, U.K. in 2011 and currently holds the position of Professor of digital chemical engineering. His current research interests include process systems engineering and chemometrics, using mathematical modeling for the design, optimization, and control of chemical, agri-food and biomedical processes

Youqing Wang (Senior member, IEEE) received the B.S. degree in mathematics from Shandong University in 2003, and the Ph.D. degree in control science and engineering from Tsinghua University in 2008. He worked chronologically at Hong Kong University of Science and Technology, China; University of California, USA; University of Alberta, Canada; Shandong University of Science and Technology; City University of Hong Kong, China.He is currently a Professor at the Beijing University of Chemical Technology. His research interests include fault diagnosis, fault-tolerant control, state monitoring, and iterative learning control for chemical and biomedical processes.He was a recipient of several honors and awards, including IET Fellow, NSFC Distinguished Young Scientists Fund, Journal of Process Control Survey Paper Prize, and ADCHEM2015 Young Author Prize
Corresponding author: Youqing Wang, e-mail: wang.youqing@ieee.org
Received Date: 2024-04-16
Revised Date: 2024-07-28
Accepted Date: 2024-08-30

Available Online: 2024-11-19

Abstract

Abstract

Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems, such as thermal power plants being studied in this work. Industrial processes are inherently dynamic and need to be monitored using dynamic algorithms. Mainstream dynamic algorithms rely on concatenating current measurement with past data. This work proposes a new, alternative dynamic process monitoring algorithm, using dot product feature analysis (DPFA). DPFA computes the dot product of consecutive samples, thus naturally capturing the process dynamics through temporal correlation. At the same time, DPFA’s online computational complexity is lower than not just existing dynamic algorithms, but also classical static algorithms (e.g., principal component analysis and slow feature analysis). The detectability of the new algorithm is analyzed for three types of faults typically seen in process systems: sensor bias, process fault and gain change fault. Through experiments with a numerical example and real data from a thermal power plant, the DPFA algorithm is shown to be superior to the state-of-the-art methods, in terms of better monitoring performance (fault detection rate and false alarm rate) and lower computational complexity.
- Computational complexity,
- dot product feature analysis (DPFA),
- dynamic process,
- multivariate statistics,
- process monitoring

FullText(HTML)

References(35)

References

[1]	L. Wen, L. Gao, and X. Li, “A new deep transfer learning based on sparse auto-encoder for fault diagnosis,” IEEE Trans. Syst. Man Cybern.: Syst., vol. 49, no. 1, pp. 136–144, Jan. 2019. doi: 10.1109/TSMC.2017.2754287
[2]	W. G. Fenton, T. M. McGinnity, and L. P. Maguire, “Fault diagnosis of electronic systems using intelligent techniques: A review,” IEEE Trans. Syst., Man, Cybern., Part C (Appl. Rev.), vol. 31, no. 3, pp. 269–281, Aug. 2001. doi: 10.1109/5326.971655
[3]	D. Wu, D. Zhou, M. Chen, J. Zhu, F. Yan, S. Zheng, and E. Guo, “Output-relevant common trend analysis for KPI-related nonstationary process monitoring with applications to thermal power plants,” IEEE Trans. Ind. Informat., vol. 17, no. 10, pp. 6664–6675, Oct. 2021. doi: 10.1109/TII.2020.3041516
[4]	B. Pattipati, C. Sankavaram, and K. Pattipati, “System identification and estimation framework for pivotal automotive battery management system characteristics,” IEEE Trans. Syst., Man, Cybern., Part C (Appl. Rev.), vol. 41, no. 6, pp. 869–884, Nov. 2011.
[5]	Z. Huang, Z. Wang, and H. Zhang, “Multilevel feature moving average ratio method for fault diagnosis of the microgrid inverter switch,” IEEE/CAA J. Autom. Sinica, vol. 4, no. 2, pp. 177–185, Apr. 2017. doi: 10.1109/JAS.2017.7510496
[6]	E. Principi, D. Rossetti, S. Squartini, and F. Piazza, “Unsupervised electric motor fault detection by using deep autoencoders,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 2, pp. 441–451, Mar. 2019. doi: 10.1109/JAS.2019.1911393
[7]	Y. Wang, Y. Si, B. Huang, and Z. Lou, “Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008–2017,” Can. J. Chem. Eng., vol. 96, no. 10, pp. 2073–2085, Oct. 2018. doi: 10.1002/cjce.23249
[8]	B. Pourbabaee, M. J. Roshtkhari, and K. Khorasani, “Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients,” IEEE Trans. Syst., Man, Cybern.: Syst., vol. 48, no. 12, pp. 2095–2104, Dec. 2018. doi: 10.1109/TSMC.2017.2705582
[9]	Y. Jiang and S. Yin, “Recent advances in key-performance-indicator oriented prognosis and diagnosis with a MATLAB toolbox: DB-KIT,” IEEE Trans. Ind. Informat., vol. 15, no. 5, pp. 2849–2858, May 2019.
[10]	X. Wang, X. Liu, and Y. Li, “An incremental model transfer method for complex process fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 5, pp. 1268–1280, Sept. 2019. doi: 10.1109/JAS.2019.1911618
[11]	H. Chen, B. Jiang, N. Lu, and Z. Mao, “Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains,” IEEE Trans. Veh. Technol., vol. 67, no. 6, pp. 4819–4830, Jun. 2018.
[12]	J. Zhang, D. Zhou, and M. Chen, “Adaptive cointegration analysis and modified RPCA with continual learning ability for monitoring multimode nonstationary processes,” IEEE Trans. Cybern., vol. 53, no. 8, pp. 4841–4854, Aug. 2023. doi: 10.1109/TCYB.2021.3140065
[13]	H. Su and G. Zheng, “A partial least squares regression-based fusion model for predicting the trend in drowsiness,” IEEE Trans. Syst., Man, Cybern.—Part A: Syst. Humans, vol. 38, no. 5, pp. 1085–1092, Sept. 2008. doi: 10.1109/TSMCA.2008.2001067
[14]	C. Shang, B. Huang, F. Yang, and D. Huang, “Slow feature analysis for monitoring and diagnosis of control performance,” J. Process Control, vol. 39, pp. 21–34, Mar. 2016. doi: 10.1016/j.jprocont.2015.12.004
[15]	Z. Lou, Y. Wang, Y. Si, and S. Lu, “A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis,” Automatica, vol. 138, p. 110148, Apr. 2022. doi: 10.1016/j.automatica.2021.110148
[16]	Q. Chen, Z. Liu, X. Ma, and Y. Wang, “Artificial neural correlation analysis for performance-indicator-related nonlinear process monitoring,” IEEE Trans. Ind. Informat., vol. 18, no. 2, pp. 1039–1049, Feb. 2022.
[17]	J. Shang, M. Chen, H. Ji, and D. Zhou, “Recursive transformed component statistical analysis for incipient fault detection,” Automatica, vol. 80, pp. 313–327, Jun. 2017. doi: 10.1016/j.automatica.2017.02.028
[18]	Y. Qin, Y. Yan, H. Ji, and Y. Wang, “Recursive correlative statistical analysis method with sliding windows for incipient fault detection,” IEEE Trans. Ind. Electron., vol. 69, no. 4, pp. 4185–4194, Apr. 2022. doi: 10.1109/TIE.2021.3070521
[19]	Y. Wang, T. Hou, M. Cui, and X. Ma, “Orthogonal stationary component analysis for nonstationary process monitoring,” IEEE Trans. Instrum. Meas., vol. 72, p. 3527309, Aug. 2023.
[20]	C.-Y. Zhang, Z.-L. Yao, H.-Y. Yao, F. Huang, and C. L. P. Chen, “Dynamic representation learning via recurrent graph neural networks,” IEEE Trans. Syst., Man, Cybern.: Syst., vol. 53, no. 2, pp. 1284–1297, Feb. 2023.
[21]	W. Ku, R. H. Storer, and C. Georgakis, “Disturbance detection and isolation by dynamic principal component analysis,” Chemometr. Intell. Lab. Syst., vol. 30, no. 1, pp. 179–196, Nov. 1995. doi: 10.1016/0169-7439(95)00076-3
[22]	Z. Lou, D. Shen, and Y. Wang, “Two-step principal component analysis for dynamic processes monitoring,” Can. J. Chem. Eng., vol. 96, no. 1, pp. 160–170, Jan. 2018. doi: 10.1002/cjce.22855
[23]	C. Shang, B. Huang, and D. Huang, “A systematic approach to dynamic monitoring of industrial processes based on second-order slow feature analysis,” IFAC-PapersOnLine, vol. 51, no. 18, pp. 387–392, Oct. 2018.
[24]	J. Zheng, C. Zhao, and F. Gao, “Retrospective comparison of several typical linear dynamic latent variable models for industrial process monitoring,” Comput. Chem. Eng., vol. 157, p. 107587, Jan. 2022. doi: 10.1016/j.compchemeng.2021.107587
[25]	X. Ma, Y. Si, Z. Yuan, Y. Qin, and Y. Wang, “Multistep dynamic slow feature analysis for industrial process monitoring,” IEEE Trans. Instrum. Meas., vol. 69, no. 12, pp. 9535–9548, Dec. 2020.
[26]	X. Ma, Y. Si, Y. Qin, and Y. Wang, “Fault detection for dynamic processes based on recursive innovational component statistical analysis,” IEEE Trans. Autom. Sci. Eng., vol. 20, no. 1, pp. 310–319, Jan. 2023. doi: 10.1109/TASE.2022.3149591
[27]	J. Shang and M. Chen, “Recursive dynamic transformed component statistical analysis for fault detection in dynamic processes,” IEEE Trans. Ind. Electron., vol. 65, no. 1, pp. 578–588, Jan. 2018. doi: 10.1109/TIE.2017.2721929
[28]	Y. Dong, S. J. Qin, “A novel dynamic PCA algorithm for dynamic data modeling and process monitoring,” J. Process Control, vol. 67, pp. 1–11, Jul. 2018. doi: 10.1016/j.jprocont.2017.05.002
[29]	W. Yu, C. Zhao, and B. Huang, “Recursive cointegration analytics for adaptive monitoring of nonstationary industrial processes with both static and dynamic variations,” J. Process Control, vol. 92, pp. 319–332, Aug. 2020.
[30]	D. Zhou, Y. Zhao, Z. Wang, X. He, and M. Gao, “Review on diagnosis techniques for intermittent faults in dynamic systems,” IEEE Trans. Ind. Electron., vol. 67, no. 3, pp. 2337–2347, Mar. 2020. doi: 10.1109/TIE.2019.2907500
[31]	J. Yu, L. Ye, L. Zhou, Z. Yang, F. Shen, and Z. Song, “Dynamic process monitoring based on variational Bayesian canonical variate analysis,” IEEE Trans. Syst., Man, Cybern.: Syst., vol. 52, no. 4, pp. 2412–2422, Apr. 2022. doi: 10.1109/TSMC.2021.3051054
[32]	C. Zhao and H. Sun, “Dynamic distributed monitoring strategy for large-scale nonstationary processes subject to frequently varying conditions under closed-loop control,” IEEE Trans. Ind. Electron., vol. 66, no. 6, pp. 4749–4758, Jun. 2019. doi: 10.1109/TIE.2018.2864703
[33]	G. H. Golub and C. F. Van Loan, Matrix Computations. 4th ed. Baltimore, USA: JHU Press, 2012.
[34]	H. Ji, “Statistics Mahalanobis distance for incipient sensor fault detection and diagnosis,” Chem. Eng. Sci., vol. 230, p. 116223, Feb. 2021.
[35]	L. Feng and C. Zhao, “Fault description based attribute transfer for zero-sample industrial fault diagnosis,” IEEE Trans. Ind. Informat., vol. 17, no. 3, pp. 1852–1862, Mar. 2021. doi: 10.1109/TII.2020.2988208

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(5) / Tables(5)

Get Citation

PDF

XML

Article Metrics

Article views (875) PDF downloads(207)

Highlights

Stronger Dynamic Information Analysis Capability: DPFA uses the dot product operation to find the relationship between the current sample and the past sample, which directly reflects the dynamic characteristics of the data. Compared with the dynamic algorithm idea of direct dimensional expansion, DPFA’s interpretation of dynamic information is more accurate
Lower Computational Complexity: By comparison, the online calculation complexity of DPFA is lower than those of classic dynamic algorithms and even lower than those of some static algorithms such as PCA and SFA, when the order is smaller than the sample dimension
More Detailed Detectability Analysis: This paper analyzes the detectability of three common faults in dynamic systems, namely sensor bias fault, process fault, and gain change fault. Among them, the first two are additive faults, while the last one is multiplicative faults. The detection analysis of multiplicative faults has always been a difficult research point in process monitoring. We give general fault forms and corresponding sufficient and necessary conditions
Better Monitoring Performance: The fault detection rate (FDR) and false alarm rate (FAR) are equally important in process monitoring. The verification of the actual thermal power plant data showed that the comprehensive performance of DPFA is better than those of other algorithms

Dynamic Process Monitoring Based on Dot Product Feature Analysis for Thermal Power Plants

doi: 10.1109/JAS.2024.124908

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Highlights

Export File

Citation

Format

Content