A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring

Abstract

Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the
collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.

Keywords

Process monitoring / Multimode process / Dictionary learning / Transfer learning

References

[[1]] Qian F, Zhong W, Du W. Fundamental theories and key technologies for smart and optimal manufacturing in the process industry. Engineering 2017;3 (2):154–60.

[[2]] Mao S, Wang B, Tang Y, Qian F. Opportunities and challenges of artificial intelligence for green manufacturing in the process industry. Engineering 2019;5(6):995–1002.

[[3]] Zhao C, Sun Y. Multispace total projection to latent structures and its application to online process monitoring. IEEE Trans Control Syst Technol 2014;22(3):868–83.

[[4]] Liu Q, Qin SJ, Chai T. Multiblock concurrent PLS for decentralized monitoring of continuous annealing processes. IEEE Trans Ind Electron 2014;61 (11):6429–37.

[[5]] Jiang Q, Yan X, Huang B. Review and perspectives of data-driven distributed monitoring for industrial plant-wide processes. Ind Eng Chem Res 2019;58 (29):12899–912.

[[6]] Shang C, You F. Data analytics and machine learning for smart process manufacturing: recent advances and perspectives in the big data era. Engineering 2019;5(6):1010–6.

[[7]] Zhang W, Yang D, Wang H. Data-driven methods for predictive maintenance of industrial equipment: a survey. IEEE Syst J 2019;13(3):2213–27.

[[8]] Zhou P, Zhang R, Xie J, Liu J, Wang H, Chai T. Data-driven monitoring and diagnosing of abnormal furnace conditions in blast furnace ironmaking: an integrated PCA–ICA method. IEEE Trans Ind Electron 2021;68(1):622–31.

[[9]] Sankavaram C, Pattipati BR, Kodali A, Pattipati K, Azam M, Kumar S, et al. Model-based and data-driven prognosis of automotive and electronic systems. In: Proceedings of 2009 IEEE International Conference on Automation Science and Engineering; 2009 Aug 22–25; Bangalore, India. New York City: Curran Associates; 2009. p. 22–5.

[[10]] Feng L, Zhao C. Fault description based attribute transfer for zero-sample industrial fault diagnosis. IEEE Trans Ind Inform 2021;17(3):1852–62.

[[11]] Liang YC, Wang S, Li WD, Lu X. Data-driven anomaly diagnosis for machining processes. Engineering 2019;5(4):646–52.

[[12]] Jiang Q, Yan X, Huang B. Deep discriminative representation learning for nonlinear process fault detection. IEEE Trans Autom Sci Eng 2020;17 (3):1410–9.

[[13]] Jiang Q, Yan S, Yan X, Yi H, Gao F. Data-driven two-dimensional deep correlated representation learning for nonlinear batch process monitoring. IEEE Trans Ind Inform 2020;16(4):2839–48.

[[14]] Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng 2010;22(10):1345–59.

[[15]] Chai Z, Zhao C. A fine-grained adversarial network method for cross-domain industrial fault diagnosis. IEEE Trans Autom Sci Eng 2020;17(3):1432–42.

[[16]] Huang K, Wen H, Zhou C, Yang C, Gui W. Transfer dictionary learning method for cross-domain multimode process monitoring and fault isolation. IEEE Trans Instrum Meas 2020;69(11):8713–24.

[[17]] Wang J, Zhao C. Mode-cloud data analytics based transfer learning for soft sensor of manufacturing industry with incremental learning ability. Control Eng Pract 2020;98:104392.

[[18]] Hou R, Wang H, Xiao Y, Xu W. Incremental PCA based online model updating for multivariate process monitoring. In: Proceedings of the 10th World Congress on Intelligent Control and Automation; 2012 Jul 6–8; Beijing, China. New York City: Curran Associates; 2012.

[[19]] Jiang LY, Xie L, Wang SQ, Wang N. Monitoring batch processes using multimodel discriminant partial least squares. In: Proceedings of 2005 International Conference on Machine Learning and Cybernetics; 2005 Aug 18–21; Guangzhou, China. New York City: Curran Associates; 2005.

[[20]] Zhang Y, You D, Gao X, Katayama S. Online monitoring of welding status based on a DBN model during laser welding. Engineering 2019;5(4):671–8.

[[21]] Zeng J, Gao C, Luo S, Li Q. Online Process Monitoring Based on Incremental LPP. In: Process Monitoring Based on Incremental LPP; 2011 Jul 22–24; Yantai, China. New York City: Curran Associates; 2011.

[[22]] Ge Z, Song Z. Online batch process monitoring based on multi-model ICA–PCA method. In: Proceedings of the 2008 7th World Congress on Intelligent Control and Automation; 2008 Jun 25–27; Chongqing, China. New York City: Curran Associates; 2008.

[[23]] Peng X, Tang Y, Du W, Qian F. Multimode process monitoring and fault detection: a sparse modeling and dictionary learning method. IEEE Trans Ind Electron 2017;64(6):4866–75.

[[24]] Chen G, Xiong C, Corso JJ. Dictionary transfer for image denoising via domain adaptation. In: Proceedings of the 19th IEEE International Conference on Image Processing; 2012 Sep 30–Oct 3; Orlando, FL, USA. New York City: Curran Associates; 2013.

[[25]] Zhang K, Yuan M, Xiong Y, Qu L. Common dictionary and domain-specific dictionary based cross-domain image classification. In: Proceedings of 2017 Chinese Automation Congress (CAC); 2017 Oct 20–22; Jinan, China. New York City: Curran Associates; 2017. p. 2824–9.

[[26]] Jie N, Qiang Q, Chellappa R. Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2013 Jun 23–28; Portland, OR, USA. New York City: Curran Associates; 2013. p. 692–9.

[[27]] Long M, Ding G, Wang J, Sun J, Guo Y, Yu PS. Transfer sparse coding for robust image representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2013 Jun 23–28; Portland, OR, USA. New York City: Curran Associates; 2013. p. 407–14.

[[28]] Huang K, Wen H, Ji H, Cen L, Chen X, Yang C. Nonlinear process monitoring using kernel dictionary learning with application to aluminum electrolysis process. Control Eng Pract 2019;89:94–102.

[[29]] Gretton A, Borgwardt K, Rasch MJ, Scholkopf B, Smola AJ. A kernel method for the two-sample problem. 2008. arXiv:0805.2368.

[[30]] Ramirez I, Sprechmann P, Sapiro G. Classification and clustering via dictionary learning with structured incoherence and shared features. In: Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2010 Jun 13–18; San Francisco, CA, USA. New York City: Curran Associates; 2010.

[[31]] Meng Y, Lei Z, Feng X, Zhang D. Fisher discrimination dictionary learning for sparse representation. In: Proceedings of 2011 International Conference on Computer Vision; 2011 Nov 6–13; Barcelona, Spain. New York City: Curran Associates; 2011.

[[32]] Shekhar S, Patel VM, Nguyen HV, Chellappa R. Generalized domain-adaptive dictionaries. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition; 2013 Jun 23–28; Partland, OR, USA. New York City: Curran Associates; 2013. p. 361–8.

[[33]] Huang K, Wu Y, Wen H, Liu Y, Yang C, Gui W. Distributed dictionary learning for high-dimensional process monitoring. Control Eng Pract 2020;98:104386.

[[34]] Kokiopoulou E, Chen J, Saad Y. Trace optimization and eigenproblems in dimension reduction methods. Numer Linear Algebra Appl 2011;18(3):565–602.

[[35]] Schölkopf B, Platt J, Hofmann T. Efficient sparse coding algorithms. Stanford: MIT Press; 2007.

[[36]] Fletcher R. Practical methods of optimization. 2nd ed. New York City: Wiley; 1987.

[[37]] Rebollo-Neira L, Lowe D. Optimized orthogonal matching pursuit approach. IEEE Signal Process Lett 2002;9(4):137–40.

[[38]] Chen Q, Wynne RJ, Goulding P, Sandoz D. The application of principal component analysis and kernel density estimation to enhance process monitoring. Control Eng Pract 2000;8(5):531–43.

[[39]] Huang K, Wu Y, Yang C, Peng G, Shen W. Structure dictionary learning-based multimode process monitoring and its application to aluminum electrolysis process. IEEE Trans Autom Sci Eng 2020;17(4):1989–2003.

[[40]] Thornhill NF, Patwardhan SC, Shah SL. A continuous stirred tank heater simulation model with applications. J Process Control 2008;18(3–4):347–60.

[[41]] Jiang Z, Lin Z, Davis LS. Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 2013;35(11):2651–64.

[[42]] Jeng JC. Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms. J Taiwan Inst Chem Eng 2010;41(4):475–81