Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process

Wu Ping; Ni Yuxuan; Wang Huaimin; Hu Xuguang; Wu Zhenquan; Jiang Jian; Hu Yaowu

doi:null

Your Location：

Home >

Browse articles >

Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process

Updated：2026-03-13

- Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process
- Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process
- 中国化学工程学报（英文） 2026年89卷第1期页码：267-276
- Affiliations：
  
  School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
  Changshan Research Institute, Zhejiang Sci-Tech University, Changshan 324299, China
  Zhejiang Sanhua Automotive Components Co., Ltd., Hangzhou 310018, China
  Zhejiang Deli Machine Manufacturer Co., Ltd., Lishui 321499, China
  Jinyun Research Institute, Zhejiang Sci-Tech University, Jinyun 321499, China
- Author bio：
  
  Corresponding author. School of Information Science and Engineering, Zhe-jiang Sci-Tech University, Hangzhou, 310018, China. E-mail address: pingwu@zstu.edu.cn(P. Wu).
- Funds：
  
  This work was supported in part by the National Natural Sci-ence Foundation of China(62573387);the Natural Science Foun-dation of Zhejiang province, China(LY24F030004);Fundamental Research Funds of Zhejiang Sci-Tech University .(25222139-Y)
- DOI：
  中图分类号：
- 收稿：2025-03-20，
  
  修回：2025-08-21，
  
  录用：2025-08-22，
  
  网络首发：2025-10-15，
  
  纸质出版：2026-01
- Accepted：
Scan QR Code
Wu Ping, Ni Yuxuan, Wang Huaimin, 等. Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process[J]. 中国化学工程学报（英文）, 2026,89(1):267-276.

Wu Ping, Ni Yuxuan, Wang Huaimin, et al. Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process[J]. Chinese Journal of Chemical Engineering, 2026, 89(1): 267-276.
Wu Ping, Ni Yuxuan, Wang Huaimin, 等. Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process[J]. 中国化学工程学报（英文）, 2026,89(1):267-276. DOI：

Wu Ping, Ni Yuxuan, Wang Huaimin, et al. Quality related fault detection based on dynamic-inner convolutional autoencoder and partial least squares and its application to ironmaking process[J]. Chinese Journal of Chemical Engineering, 2026, 89(1): 267-276. DOI：

摘要

Abstract

Partial least squares (PLS) model maximizes the covariance between process variables and quality variables

making it widely used in quality-related fault detection. However

traditional PLS methods focus primarily on linear processes

leading to poor performance in dynamic nonlinear processes. In this paper

a novel quality-related fault detection method

named DiCAE-PLS

is developed by combining dynamic-inner convolutional autoencoder with PLS. In the proposed DiCAE-PLS method

latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables. Then

a PLS model is established to build the relationship between the extracted latent features and the final product quality. To detect quality-related faults

Hotelling's

statistic is employed. The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.

关键词

Keywords

references

Y.Q. Wang, Y.B. Si, B. Huang, Z.J. Lou, Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008—2017, Can. J. Chem. Eng. 96 (10) (2018) 2073—2085.

Q. Joe, C. H, Advances and opportunities in machine learning for process data analytics, Comput. Chem. Eng. 126(2019)465—473.

D.H. Zhou, G. Li, S.J. Qin, Total projection to latent structures for process monitoring, AIChE. J. 56 (1)(2010)168—178.

C.Y. Sun, Y.Z. Yin, H.B. Kang, H.J. Ma, A quality-related fault detection method based on the dynamic data-driven algorithm for industrial systems, IEEE Trans. Autom. Sci. Eng. 19 (4)(2022)3942—3952.

C.H. Hu, Z.Y. Xu, X.Y. Kong, J.Y. Luo, Recursive-CPLS-based quality-relevant and process-relevant fault monitoring with application to the Tennessee Eastman process, IEEE Access 7(2019) 128746—128757.

K.X. Peng, K. Zhang, G. Li, Quality-related process monitoring based on total kernel PLS model and its industrial application, Math. Probl Eng. 2013 (1) (2013)707953.

B. Song, H.B. Shi, S. Tan, Y. Tao, Multisubspace orthogonal canonical correlation analysis for quality-related plant-wide process monitoring, IEEE Trans. Ind. Inform. 17 (9) (2021) 6368—6378.

K. Zhang, K.X. Peng, S.X. Ding, Z.W. Chen, X. Yang, A correlation-based distributed fault detection method and its application to a hot tandem rolling mill process, IEEE Trans. Ind. Electron. 67(3)(2020)2380—2390.

B. Song, X.G. Zhou, H.B. Shi, Y. Tao, Performance-indicator-oriented concurrent subspace process monitoring method, IEEE Trans. Ind. Electron. 66 (7) (2018) 5535—5545.

X.W. Dai, Z.W. Gao, From model, signal to knowledge: a data-driven perspective of fault detection and diagnosis, IEEE Trans. Ind. Inform. 9 (4) (2013)2226—2238.

Z.W. Gao, C. Cecati, S.X. Ding, A survey of fault diagnosis and fault-tolerant techniques: part I: fault diagnosis with model-based and signal-based approaches, IEEE Trans. Ind. Electron. 62 (6) (2015) 3757—3767.

Z.Q. Ge, Z.H. Song, F.R. Gao, Review of recent research on data-based process monitoring, Ind. Eng. Chem. Res. 52(10)(2013)3543—3562.

Q.C. Jiang, X.F. Yan, B. Huang, Review and perspectives of data-driven distributed monitoring for industrial plant-wide processes, Ind. Eng. Chem. Res. 58 (29)(2019)12899—12912.

C.H. Zhao, Perspectives on nonstationary process monitoring in the era of industrial artificial intelligence, J. Process Control 116(2022)255—272.

Y.C. Jiang, S. Yin, O. Kaynak, Performance supervised plant-wide process monitoring in industry 4.0: a roadmap, IEEE Open J. Ind. Electron. Soc. 2 (2020) 21—35.

J.S. Zeng, C. Lu, L. Yao, Y. Liu, S.H. Luo, F. Wang, C.H. Gao, Robust stacked probabilistic latent variable model for fault isolation of dynamic process with outliers, IEEE Trans. Autom. Sci. Eng. 21(4)(2023) 6460—6472.

L. Ma, P.P. Yang, K.X. Peng, Multitask learning based collaborative modeling of heterogeneous data for compound fault diagnosis in manufacturing processes, IEEE Trans. Ind. Inform. 20 (12) (2024) 14174—14183.

M. Kano, S. Hasebe, I. Hashimoto, H. Ohno, A new multivariate statistical process monitoring method using principal component analysis, Comput. Chem. Eng. 25(7—8) (2001)1103—1113.

J.M. Lee, C. Yoo, I.B. Lee, Statistical process monitoring with independent component analysis, J. Process Control 14(5)(2004)467—485.

Z.W. Chen, S.X. Ding, K. Zhang, Z.B. Li, Z.K. Hu, Canonical correlation analysisbased fault detection methods with application to alumina evaporation process, Control Eng. Pract. 46 (2016) 51—58.

Y.H. Qin, Z.J. Lou, Y.Q. Wang, S. Lu, P. Sun, An analytical partial least squares method for process monitoring, Control Eng. Pract. 124(2022)105182.

C.Y. Sun, Y.Z. Yin, H.B. Kang, H.J. Ma, A distributed principal component regression method for quality-related fault detection and diagnosis, Inf. Sci. 600(2022)301—322.

Q.Q. Zhu, Q. Liu, S.J. Qin, Concurrent quality and process monitoring with canonical correlation analysis, J. Process Control 60(2017)95—103.

S.J. Qin, Y.Y. Zheng, Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures, AIChE. J. 59(2)(2013)496—504.

S. Yin, G. Wang, H.J. Gao, Data-driven process monitoring based on modified orthogonal projections to latent structures, IEEE Trans. Control Syst. Technol. 24(4) (2016)1480—1487.

G. Li, B.S. Liu, S.J. Qin, D.H. Zhou, Quality relevant data-driven modeling and monitoring of multivariate dynamic processes: the dynamic T-PLS approach, IEEE Trans. Neural Netw. 22(12)(2011)2262—2271.

J. Yang, J.Y. Wang, J.L. Sha, H.Q. Dai, H.B. Liu, Quality-related monitoring of distributed process systems using dynamic concurrent partial least squares, Comput. Ind. Eng. 164(2022)107893.

Y.N. Dong, Q. Joe, Regression on dynamic PLS structures for supervised learning of dynamic data, J. Process Control 68(2018) 64—72.

Y.B. Si, Y.Q. Wang, D.H. Zhou, Key-performance-indicator-related process monitoring based on improved kernel partial least squares, IEEE Trans. Ind. Electron. 68 (3)(2020)2626—2636.

Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521(7553)(2015)436—444.

R. Iqbal, T. Maniak, F. Doctor, C. Karyotis, Fault detection and isolation in industrial processes using deep learning approaches, IEEE Trans. Ind. Inform. 15(5) (2019)3077—3084.

J.B. Yu, Y. Zhang, Challenges and opportunities of deep learning-based process fault detection and diagnosis: a review, Neural Comput. Appl. 35 (1) (2023) 211—252.

J.C. Qian, Z.H. Song, Y. Yao, Z.R. Zhu, X.M. Zhang, A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes, Chemom. Intell. Lab. Syst. 231(2022)104711.

S. Lee, M. Kwak, K.L. Tsui, S.B. Kim, Process monitoring using variational autoencoder for high-dimensional nonlinear processes, Eng. Appl. Artif. Intell. 83(2019)13—27.

F.F. Cheng, Q.P. He, J.S. Zhao, A novel process monitoring approach based on variational recurrent autoencoder, Comput. Chem. Eng. 129 (2019) 106515.

Z.C. Li, L. Tian, Q.C. Jiang, X.F. Yan, Distributed-ensemble stacked autoencoder model for non-linear process monitoring, Inf. Sci. 542(2021)302—316.

W.K. Yu, C.H. Zhao, Robust monitoring and fault isolation of nonlinear industria l processes using denoising autoencoder and elastic net, IEEE Trans. Control Syst. Technol. 28 (3) (2020) 1083—1091.

B.B. Shen, J.C. Qian, Z.Y. Yang, L. Yao, Multirate nonlinear process fault detection based on multiscale hierarchical variational autoencoder, IEEE Sens. J. 24 (10)(2024)16467—16477.

S.M. Chen, J.B. Yu, S.J. Wang, One-dimensional convolutional auto-encoderbased feature learning for fault diagnosis of multivariate processes, J. Process Control 87 (2020) 54—67.

S.Y. Zhang, T. Qiu, A dynamic-inner convolutional autoencoder for process monitoring, Comput. Chem. Eng. 158 (2022)107654.

L. Guo, H.B. Shi, S. Tan, B. Song, Y. Tao, A knowledge-driven spatial-temporal graph neural network for quality-related fault detection, Process. Saf. Environ. Prot. 184(2024)1512—1524.

Y. Ma, H.B. Shi, S. Tan, B. Song, Y. Tao, Relevance variable selection variational auto-encoder network for quality-related nonlinear process monitoring, Appl. Soft Comput. 154 (2024)111333.

J.D. Yang, X.F. Yan, Global—local preserving method of quality-related maximization and its application for process monitoring, Control Eng. Pract. 154(2025)106143.

W. Zhang, Y.P. Gao, J.Z. Wang, M.W. Zhao, Y.Q. Zhu, T.S. Yang, Distributed dynamic graph embedding for quality-related monitoring in the flotation process, IEEE Trans. Instrum. Meas. 73(2024)3516911.

Z.Y. Wang, C.Z. Wang, Y.G. Li, Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection, Eng. Appl. Artif. Intell. 133(2024)108051.

S. de Jong, SIMPLS: an alternative approach to partial least squares regression, Chemom. Intell. Lab. Syst. 18 (3) (1993) 251—263.

J.H. Zhai, S.F. Zhang, J.F. Chen, Q. He, Autoencoder and its various variants. 2018 IEEE International Conference on Systems, Man, and Cybernetics(SMC). Miyazaki, Japan, IEEE, 2018, pp. 415—419.

J. Xu, Z.S. Li, B.W. Du, M.M. Zhang, J. Liu, Reluplex made more practical: leaky ReLU. 2020 IEEE Symposium on Computers and Communications (ISCC), IEEE, Rennes, France, 2020, pp. 1—7.

P.P. Odiowei, Y. Cao, Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations, IEEE Trans. Ind. Inform. 6(1) (2009)36—45.

A. Chaudhuri, D. Kakde, C. Sadek, L. Gonzalez, S. Kong, The mean and Median criteria for kernel bandwidth selection for support vector data description. 2017 IEEE International Conference on Data Mining Workshops (ICDMW), IEEE, New Orleans, LA, USA, 2017, pp.842—849.

Y.N. Dong, Q. Joe, A novel dynamic PCA algorithm for dynamic data modeling and process monitoring, J. Process Control 67 (2018)1—11.

J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem, Comput. Chem. Eng. 17 (3)(1993)245—255.

X.Z. Zhu, D.L. Gao, C. Yang, C.J. Yang, A blast furnace fault monitoring algorithm with low false alarm rate: ensemble of greedy dynamic principal component analysis-Gaussian mixture model, Chin. J. Chem. Eng. 57(2023)151—161.

S.W. Lou, C.J. Yang, X.J. Zhang, H.W. Zhang, P. Wu, Blast furnace ironmaking process monitoring with time-constrained global and local nonlinear analytic stationary subspace analysis, IEEE Trans. Ind. Inform. 20 (3) (2024) 3163—3176.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

From data to insight: Building a knowledge graph for risk analysis of hazardous chemical accidents

Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

Simultaneous hybrid modeling of a nosiheptide fermentation process using particle swarm optimization

A soft sensing method for biomanufacturing processes based on physics-informed variational learning with applications