Soft Sensor Transferability: A Survey
Source abstract
Abstract
Soft Sensors (SSs) are inferential dynamical models employed in industries to perform prediction of process hard-to-measure variables based on their relation with easily accessible ones. They allow implementation of real-time control and monitoring of the plants and present other advantages in terms of costs and efforts. Given the complexity of industrial processes, these models are generally designed with data-driven black-box machine learning (ML) techniques. ML methods work well only if the data on which the prediction is performed share the same distribution with the one on which the model was trained. This is not always possible, since plants can often show new working conditions. Even similar plants show different data distributions, making SSs not scalable between them. Models should then be created from scratch with highly time-consuming procedures. Transfer Learning (TL) is a field of ML that re-uses the knowledge from one task to learn a new different, but related, one. TL techniques are mainly used for classification tasks. Only recently TL techniques have been adopted in the SS field. The proposed survey reports the state of the art of TL techniques for nonlinear dynamical SSs design. Methods and applications are discussed and the new directions of this research field are depicted.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Machine Learning and ELM · Mineral Processing and Grinding
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mathematics and Computer Science, University of Palermo, 90123 Palermo, Italy
Department of Engineering, University of Messina, 98166 Messina, Italy
References (79)
Show source-provided references
1. Data Quality Assessment for System Identification in the Age of Big Data and Industry 4.010.1016/j.ifacol.2020.12.103 ↗
2. Fortuna, L., Graziani, S., Rizzo, A., and Xibilia, M.G. (2007). Soft Sensors for Monitoring and Control of Industrial Processes, Springer.
3. Data-driven soft sensors in the process industry10.1016/j.compchemeng.2008.12.012 ↗
4. Graziani, S., and Xibilia, M.G. (2020). Deep learning for soft sensor design. Development and Analysis of Deep Learning Architectures, Springer.10.1007/978-3-030-31764-5_2 ↗
5. A theory of learning from different domains10.1007/s10994-009-5152-4 ↗
6. Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective, MIT Press.
7. Review of adaptation mechanisms for data-driven soft sensors10.1016/j.compchemeng.2010.07.034 ↗
8. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings10.1016/j.ymssp.2018.12.051 ↗
9. A survey on transfer learning10.1109/TKDE.2009.191 ↗
10. Curreri, F., Patanè, L., and Xibilia, M.G. (2021). RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process. Sensors, 21.10.3390/s21030823 ↗
11. Farahani, H.S., Fatehi, A., Nadali, A., and Shoorehdeli, M.A. (2020). A Novel Method For Designing Transferable Soft Sensors And Its Application. arXiv.
12. Raghu, M., Zhang, C., Kleinberg, J., and Bengio, S. (2019). Transfusion: Understanding transfer learning for medical imaging. arXiv.
13. Alibadi, Z., and Vidal, J.M. (2018, January 12–14). To Read or To Do? That’s The Task: Using Transfer Learning to Detect the Intent of an Email. Proceedings of the 2018 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA.10.1109/CSCI46756.2018.00214 ↗
14. Wang, D., and Zheng, T.F. (2015, January 16–19). Transfer learning for speech and language processing. Proceedings of the 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Hong Kong, China.10.1109/APSIPA.2015.7415532 ↗
15. Deep transfer learning for industrial automation10.1109/MIE.2020.3034884 ↗
16. Virtual instruments in refineries10.1109/MIM.2005.1518619 ↗
17. Input selection methods for data-driven Soft sensors design: Application to an industrial process10.1016/j.ins.2020.05.028 ↗
18. Echo-state networks for soft sensor design in an SRU process10.1016/j.ins.2021.03.013 ↗
19. Graziani, S., and Xibilia, M.G. (2018, January 18–20). Deep structures for a reformer unit soft sensor. Proceedings of the 2018 IEEE 16th International Conference on Industrial Informatics (INDIN), Porto, Portugal.10.1109/INDIN.2018.8471942 ↗
20. Soft sensor for real-time cement fineness estimation10.1016/j.isatra.2014.09.019 ↗
21. Soft Sensor for Flame Temperature Measurement and IoT based Monitoring in Power Plants10.1016/j.matpr.2017.12.359 ↗
22. A reduced order soft sensor approach and its application to a continuous digester10.1016/j.jprocont.2011.02.001 ↗
23. Zhu, X., Rehman, K.U., Wang, B., and Shahzad, M. (2020). Modern soft-sensing modeling methods for fermentation processes. Sensors, 20.10.3390/s20061771 ↗
24. Developing soft sensors for polymer melt index in an industrial polymerization process using deep belief networks10.1007/s11633-019-1203-x ↗
25. Pisa, I., Santín, I., Vicario, J.L., Morell, A., and Vilanova, R. (2019). ANN-based soft sensor to predict effluent violations in wastewater treatment plants. Sensors, 19.10.3390/s19061280 ↗
26. Review of soft sensor methods for regression applications10.1016/j.chemolab.2015.12.011 ↗
27. Pattern Recognition and Machine Learning
28. Ljung, L. (1998). System identification. Signal Analysis and Prediction, Birkhäuser.10.1007/978-1-4612-1768-8_11 ↗
29. Curreri, F., Fiumara, G., and Xibilia, M.G. (2020). Input selection methods for soft sensor design: A survey. Future Internet, 12.10.3390/fi12060097 ↗
30. Soft sensing of product quality in the debutanizer column with principal component analysis and feed-forward artificial neural network10.1016/j.aej.2016.02.016 ↗
31. Dynamic soft sensor development based on convolutional neural networks10.1021/acs.iecr.9b02513 ↗
32. Wang, X. (2018, January 18–21). Data Preprocessing for Soft Sensor Using Generative Adversarial Networks. Proceedings of the 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore.10.1109/ICARCV.2018.8581249 ↗
33. Liu, R., Rong, Z., Jiang, B., Pang, Z., and Tang, C. (2018, January 23–25). Soft Sensor of 4-CBA Concentration Using Deep Belief Networks with Continuous Restricted Boltzmann Machine. Proceedings of the 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), Nanjing, China.10.1109/CCIS.2018.8691166 ↗
34. Chitralekha, S.B., and Shah, S.L. (2010, January 23–25). Support Vector Regression for soft sensor design of nonlinear processes. Proceedings of the 18th Mediterranean Conference on Control and Automation (MED’10), Marrakech, Morocco.10.1109/MED.2010.5547730 ↗
35. Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models10.1016/j.compchemeng.2013.06.014 ↗
36. Tercan, H., Guajardo, A., and Meisen, T. (2019, January 22–25). Industrial Transfer Learning: Boosting Machine Learning in Production. Proceedings of the 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), Helsinki, Finland.10.1109/INDIN41052.2019.8972099 ↗
37. Blitzer, J., Dredze, M., and Pereira, F. (2007, January 24–29). Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic.
38. Wang, Z., Dai, Z., Póczos, B., and Carbonell, J. (2019, January 15–20). Characterizing and avoiding negative transfer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01155 ↗
39. Redko, I., Morvant, E., Habrard, A., Sebban, M., and Bennani, Y. (2019). Advances in Domain Adaptation Theory, Elsevier.10.1016/B978-1-78548-236-6.50002-7 ↗
40. Correcting sample selection bias by unlabeled data
41. Integrating structured biological data by kernel maximum mean discrepancy10.1093/bioinformatics/btl242 ↗
42. Domain adaptation via transfer component analysis10.1109/TNN.2010.2091281 ↗
43. Long, M., Wang, J., Ding, G., Sun, J., and Yu, P.S. (2013, January 1–8). Transfer feature learning with joint distribution adaptation. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.274 ↗
44. On information and sufficiency10.1214/aoms/1177729694 ↗
45. Zhuang, F., Cheng, X., Luo, P., Pan, S.J., and He, Q. (2015, January 25–31). Supervised representation learning: Transfer learning with deep autoencoders. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina.
46. A just-in-time modeling approach for multimode soft sensor based on Gaussian mixture variational autoencoder10.1016/j.compchemeng.2021.107230 ↗
47. A new metric for probability distributions10.1109/TIT.2003.813506 ↗
48. Dey, S., Madikeri, S., and Motlicek, P. (2016, January 20–25). Information theoretic clustering for unsupervised domain-adaptation. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472745 ↗
49. Activity recognition using transfer learning
50. The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming10.1016/0041-5553(67)90040-7 ↗
51. Regularised transfer learning for hyperspectral image classification10.1049/iet-cvi.2018.5145 ↗
52. Discriminative subspace alignment for unsupervised visual domain adaptation10.1007/s11063-015-9494-6 ↗
53. Gretton, A., Fukumizu, K., Teo, C.H., Song, L., Schölkopf, B., and Smola, A.J. (2007, January 3–6). A kernel statistical test of independence. Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
54. Learning domain-invariant subspace using domain features and independence maximization10.1109/TCYB.2016.2633306 ↗
55. Wang, H., and Yang, Q. (2011, January 7–11). Transfer learning by structural analogy. Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.
56. Markov processes over denumerable products of spaces, describing large systems of automata
57. Shen, J., Qu, Y., Zhang, W., and Yu, Y. (2018, January 2–7). Wasserstein distance guided representation learning for domain adaptation. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11784 ↗
58. Wasserstein distance based Asymmetric Adversarial Domain Adaptation in intelligent bearing fault diagnosis10.1088/1361-6501/ac0a0c ↗
59. Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., and Saminger-Platz, S. (2017). Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv.
60. Central moment discrepancy based domain adaptation for intelligent bearing fault diagnosis10.1016/j.neucom.2020.11.063 ↗
61. Multi-block domain adaptation with central moment discrepancy for fault diagnosis10.1016/j.measurement.2020.108516 ↗
62. Review of metric learning with transfer learning10.1063/1.4992857 ↗
63. Mode-cloud data analytics based transfer learning for soft sensor of manufacturing industry with incremental learning ability10.1016/j.conengprac.2020.104392 ↗
64. A dual modifier adaptation optimization strategy based on process transfer model for new batch process10.1016/j.ifacol.2018.09.266 ↗
65. Transfer learning for batch process optimal control using LV-PTM and adaptive control strategy10.1016/j.jprocont.2019.06.010 ↗
66. Transfer learning for nonlinear batch process operation optimization10.1016/j.jprocont.2021.03.002 ↗
67. A process transfer model-based optimal compensation control strategy for batch process using just-in-time learning and trust region method10.1016/j.jfranklin.2020.10.039 ↗
68. Transfer learning for end-product quality prediction of batch processes using domain-adaption joint-Y PLS10.1016/j.compchemeng.2020.106943 ↗
69. Virtual Sensing f-CaO Content of Cement Clinker Based on Incremental Deep Dynamic Features Extracting and Transferring Model
70. Yang, C., Chen, B., Wang, Z., Yao, Y., and Liu, Y. (2019, January 24–27). Transfer learning soft sensor for product quality prediction in multi-grade processes. Proceedings of the 2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS), Dali, China.10.1109/DDCLS.2019.8908915 ↗
71. Domain adaptation transfer learning soft sensor for product quality prediction10.1016/j.chemolab.2019.103813 ↗
72. Development of adversarial transfer learning soft sensor for multigrade processes10.1021/acs.iecr.0c02398 ↗
73. Hsiao, Y.D., Kang, J.L., and Wong, D.S.H. (2021). Development of Robust and Physically Interpretable Soft Sensor for Industrial Distillation Column Using Transfer Learning with Small Datasets. Processes, 9.10.3390/pr9040667 ↗
74. Soft sensor design using transductive moving window learner10.1016/j.compchemeng.2020.106941 ↗
75. Soft-sensor design via task transferred just-in-time-learning coupled transductive moving window learner10.1016/j.jprocont.2021.03.006 ↗
76. Domain Adversarial Neural Network Regression to design transferable soft sensor in a power plant10.1016/j.compind.2021.103489 ↗
77. Graziani, S., and Xibilia, M.G. (2020, January 25–28). Improving Soft Sensors performance in the presence of small datasets by data selection. Proceedings of the 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Dubrovnik, Croatia.10.1109/I2MTC43012.2020.9128672 ↗
78. Product transfer between plants using historical process data10.1002/aic.690461011 ↗
79. Product transfer between sites using Joint-Y PLS10.1016/j.chemolab.2005.04.009 ↗