journal article·2022-04-28Open access

Thickness-Related Fault Diagnosis of Steel Strip Based on W-KPLS Method Considering Mechanism Weight Optimization

Hesong Guo, Jianliang Sun, Jieyuan Luo, Yan Peng, Chunlin Ye

Applied Sciences· Volume 12· Issue 9

Abstract

Due to the lack of a reasonable mechanism explanation for the data model used in the process of quality-related fault diagnosis, the diagnosis model has insufficient ability to identify faults, resulting in the phenomenon of failure detection or false positive. Therefore, this paper adopted the method of mechanism and data model fusion to solve the problem of insufficient interpretation of the influence of existing diagnosis methods on rolling process variables. Firstly, the KPLS achieves strip quality-related fault detection for nonlinear processes. In order to find out the abnormal variables, a nonlinear contribution plot was introduced to calculate the contribution value of each variable to the monitoring index. Secondly, based on the bounce equation of the rolling process, the static comprehensive analysis of the steady rolling process was carried out to reveal the influence of various variables on strip thickness. Thirdly, based on the above analysis of the steady rolling process mechanism, the influence weight method and kernel function method were used to reconstruct and map the original input matrix. A kernel partial least squares method based on influence weight W optimization (W-KPLS) was proposed for quality-related fault monitoring and diagnosis. Finally, the model was applied in the cold rolling process of an aluminum alloy sheet, and the validity of the model was further verified by practical industrial data. The results show that the new method improves the fault detection rate by more than 20% compared with the traditional monitoring method, and the proportion of data points reaching the early warning limit was increased to more than 95%.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Fault Detection and Control Systems · Mineral Processing and Grinding · Machine Fault Diagnosis Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

National Engineering Research Center for Equipment and Technology of Cold Rolled Strip, Yanshan University, Qinhuangdao 066004, China

Funding

Ministry of Education University–Industry Collaborative Education Program · Central Government Guides Local Science and Technology Development Fund Projects · Hebei Natural Fund Iron and Steel Joint Fund · Hebei Natural Science Foundation · Hebei Provincial Department of Education Postgraduate Innovation Ability Training Funding Project

References (36)

Show source-provided references
1. Whole process quality management and control system of iron and steel based on industrial interconnection
2. A practical propagation path identification scheme for quality-related faults based on nonlinear dynamic latent variable model and partitioned Bayesian network10.1016/j.jfranklin.2018.07.035 ↗
3. Key-Performance-Indicator-Related Process Monitoring Based on Improved Kernel Partial Least Squares10.1109/TIE.2020.2972472 ↗
4. Dynamic statistical process monitoring based on generalized canonical variate analysis10.1016/j.jtice.2020.07.007 ↗
5. Improved Dynamic Optimized Kernel Partial Least Squares for Nonlinear Process Fault Detection10.1155/2021/6677944 ↗
6. Least Squares and Contribution Plot Based Approach for Quality-Related Process Monitoring10.1109/ACCESS.2018.2871455 ↗
7. Review on data-driven modeling and monitoring for plant-wide industrial processes10.1016/j.chemolab.2017.09.021 ↗
8. Review on development of digital and intelligent metallurgical rolling equipment technology
9. Optimization of Metal Rolling Control Using Soft Computing Approaches: A Review10.1007/s11831-019-09380-6 ↗
10. Quality-related fault detection based on the score reconstruction associated with partial least squares
11. Diagnostic study on based thickness deviation of hot rolled strip based on optimized RT-PLS
12. A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches10.1016/j.jprocont.2015.06.007 ↗
13. KPLS–KSER based approach for quality-related monitoring of nonlinear process10.1016/j.isatra.2020.09.006 ↗
14. Fault identification for quality monitoring of molten iron in blast furnace ironmaking based on KPLS with improved contribution rate10.1016/j.conengprac.2020.104354 ↗
15. Quality-Driven Kernel Projection to Latent Structure Model for Nonlinear Process Monitoring10.1109/ACCESS.2019.2920395 ↗
16. Total projection to latent structures for process monitoring10.1002/aic.11977 ↗
17. Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures10.1002/aic.13959 ↗
18. Quality-relevant fault monitoring based on efficient projection to latent structures with application to hot strip mill process10.1049/iet-cta.2014.0732 ↗
19. Review of partial least squares linear models and their nonlinear dynamic expansion models
20. Industrial process monitoring based on Fisher discriminant global-local preserving projection10.1016/j.jprocont.2019.05.010 ↗
21. A P-t-SNE and MMEMPM based quality-related process monitoring method for a variety of hot rolling processes10.1016/j.conengprac.2019.05.006 ↗
22. Hierarchical monitoring for Multi-unit chemical processes based on Local-global correlation features
23. Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations10.1109/TII.2009.2032654 ↗
24. Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes10.1016/j.compchemeng.2018.12.027 ↗
25. Improved latent variable models for nonlinear and dynamic process monitoring10.1016/j.ces.2017.04.048 ↗
26. A nonlinear full condition process monitoring method for hot rolling process with dynamic characteristic10.1016/j.isatra.2020.11.022 ↗
27. Quality-Related Root Cause Diagnosis Based on Orthogonal Kernel Principal Component Regression and Transfer Entropy10.1109/TII.2020.2989810 ↗
28. Fault monitoring based on mutual information feature engineering modeling in chemical process10.1016/j.cjche.2018.11.008 ↗
29. Intelligent control of hot strip rolling based on CPS architecture
30. Key intelligent technologies of steel strip rolling process
31. Mechanism-intelligent coordination shape control model of cold strip
32. Mechanical property prediction model of hot-rolled strip via big data and metallurgical mechanism analysis
33. Nonlinear quality-related fault detection using combined deep variational information bottleneck and variational autoencoder10.1016/j.isatra.2021.01.002 ↗
34. Design and optimization of thickness control system of tandem cold mill
35. Study on shape and gauge control system of cold strip mill
36. Coordinate control of strip thickness-crown-tension based on inverse linear quadratic in tandem hot rolling mill10.1007/s00170-021-07912-8 ↗