期刊首页 优先出版 当期阅读 过刊浏览 作者中心 关于期刊 English

《工程(英文)》 >> 2021年 第7卷 第9期 doi: 10.1016/j.eng.2020.08.028

一种用于工业过程监测的鲁棒迁移字典学习算法

School of Automation, Central South University, Changsha 410083, China

收稿日期: 2020-05-13 修回日期: 2020-06-27 录用日期: 2020-08-25 发布日期: 2021-08-04

下一篇 上一篇

摘要

由于数据驱动的过程监测方法具有普遍性,且不依赖反应机理,其已经成为复杂工业系统过程监测的主流。然而,大多数数据驱动的过程监测方法均假设历史训练数据和在线测试数据遵循相同的分布。事实上,由于工业系统恶劣的环境,从实际工业过程中收集的数据总是受到许多因素的影响,如多变的操作环境、原材料的变化和生产指标的修改。这些因素通常会使在线监测数据和历史训练数据分布不同,从而导致过程监测任务中的模型失配。因此,当将从训练数据中学习的模型应用于实际的在线监测时,很难实现精确的过程监测。为了解决操作环境变化导致的历史训练数据和在线测试数据之间的分布差异问题,提出了一种鲁棒的迁移字典学习(RTDL)算法用于工业过程监测。RTDL是表示学习和域自适应迁移学习的协同方法。该方法将历史训练数据和在线测试数据分别作为迁移学习问题的源域和目标域。然后将最大均值差异正则化和线性判别分析正则化引入字典学习框架,可以减少源域和目标域之间的分布差异。这样,即使源域和目标域的特征在实际变化的操作环境的干扰下明显不同,仍可以学习鲁棒的字典。这样的字典可以有效地提高过程监测和模态识别的性能。通过数值仿真和两个工业系统的实验验证了该方法的有效性和优越性。

图片

图1

图2

图3

图4

图5

图6

图7

图8

参考文献

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[ 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. 链接1

[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. 链接1

[11] Liang YC, Wang S, Li WD, Lu X. Data-driven anomaly diagnosis for machining processes. Engineering 2019;5(4):646–52. 链接1

[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. 链接1

[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. 链接1

[14] Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng 2010;22(10):1345–59. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[34] Kokiopoulou E, Chen J, Saad Y. Trace optimization and eigenproblems in dimension reduction methods. Numer Linear Algebra Appl 2011;18(3):565–602. 链接1

[35] Schölkopf B, Platt J, Hofmann T. Efficient sparse coding algorithms. Stanford: MIT Press; 2007. 链接1

[36] Fletcher R. Practical methods of optimization. 2nd ed. New York City: Wiley; 1987. 链接1

[37] Rebollo-Neira L, Lowe D. Optimized orthogonal matching pursuit approach. IEEE Signal Process Lett 2002;9(4):137–40. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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. 链接1

[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 链接1

相关研究