With the advancement of soft measurement, just-in-time learning (JITL) has become a widely adopted framework for online soft-sensing modeling in industrial processes. However, traditional JITL model approaches often rely on simple similarity measures like Euclidean distance, resulting in the underutilization of labeled data. This paper proposes a supervised, improved local Fisher discriminant analysis method based on a JITL framework and local Fisher discriminant analysis (LFDA) to improve data utilization efficiency. In particular, by incorporating the indirect correlation information matrix, this method integrates the inter-class and intra-class dispersion matrix, overcoming the limitation of the LFDA algorithm that only captures direct data correlations. We select two different carbon depositions in the Methanol-to-Olefin reaction system for comparative experiments and use the root mean squared error (RMSE) and R-square (R²) to evaluate the effectiveness of the proposed method. Fitting results show that two kinds of carbon depositions were better than the control model, namely the RMSE of the model were 0.1431 and 0.1513, R² were 0.8952 and 0.8707.

1. [1] S. Imori and H. Shimodaira, “An Information Criterion for Auxiliary Variable Selection in Incomplete Data Analysis,” Entropy, Vol.21, No.3, 2019. https://doi.org/10.3390/e21030281
2. [2] Z. Lou and Y. Wang, “New Nonlinear Approach for Process Monitoring: Neural Component Analysis,” Industrial & Engineering Chemistry Research, Vol.60, No.1, pp. 387-398, 2020. https://doi.org/10.1021/acs.iecr.0c02256
3. [3] Q. Sun and Z. Ge, “A Survey on Deep Learning for Data-Driven Soft Sensors,” IEEE Trans. on Industrial Informatics, Vol.17, No.9, pp. 5853-5866, 2021. https://doi.org/10.1109/TII.2021.3053128
4. [4] Z. Ge and Z. Song, “A Comparative Study of Just-in-Time-Learning Based Methods for Online Soft Sensor Modeling,” Chemometrics and Intelligent Laboratory Systems, Vol.104, No.2, pp. 306-317, 2010. https://doi.org/10.1016/j.chemolab.2010.09.008
5. [5] Y. Bai and M. Bain, “Optimizing Weighted Lazy Learning and Naive Bayes Classification Using Differential Evolution Algorithm,” J. of Ambient Intelligence and Humanized Computing, Vol.13, pp. 3005-3024, 2022. https://doi.org/10.1007/s12652-021-03135-7
6. [6] A. Talamantes and E. Chavez, “Instance-Based Learning Using the Half-Space Proximal Graph,” Pattern Recognition Letters, Vol.156, pp. 88-95, 2022. https://doi.org/10.1016/j.patrec.2022.01.025
7. [7] X. Jiang and Z. Ge, “Improving the Performance of Just-in-Time Learning-Based Soft Sensor Through Data Augmentation,” IEEE Trans. on Industrial Electronics, Vol.69, No.12, pp. 13716-13726, 2022. https://doi.org/10.1109/TIE.2021.3139194
8. [8] Y. Gao, H. Jin, B. Wang, B. Yang, and W. Yu, “An Adaptive Soft Sensor Method Based on Online Deep Evolving Fuzzy System for Industrial Process Data Streams,” 2023 IEEE 12th Data Driven Control and Learning Systems Conf. (DDCLS), pp. 1799-1804, 2023. https://doi.org/10.1109/DDCLS58216.2023.10167235
9. [9] P. Zhou, W. Chen, C. Yi, Z. Jiang, T. Yang, and T. Chai, “Fast Just-in-Time-learning Recursive Multi-Output LSSVR for Quality Prediction and Control of Multivariable Dynamic Systems,” Engineering Applications of Artificial Intelligence, Vol.100, Article No.104168, 2021. https://doi.org/10.1016/j.engappai.2021.104168
10. [10] S. Dong, Y. Li, P. Zhu, X. Pei, X. Pan, X. Xu, L. Liu, B. Xing, and X. Hu, “Rolling bearing performance degradation assessment based on singular value decomposition-sliding window linear regression and improved deep learning network in noisy environment,” Measurement Science and Technology, Vol.33, No.4, Article No.045015, 2022. https://doi.org/10.1088/1361-6501/ac39d1
11. [11] D. Aguado, G. Noriega-Hevia, J. Ferrer, A. Seco, and J. Serralta, “PLS-Based Soft-Sensor to Predict Ammonium Concentration Evolution in Hollow Fibre Membrane Contactors for Nitrogen Recovery,” J. of Water Process Engineering, Vol.47, Article No.102735, 2022. https://doi.org/10.1016/j.jwpe.2022.102735
12. [12] X. Huo, K. Hao, L. Chen, X.-S. Tang, T. Wang, and X. Cai, “A Dynamic Soft Sensor of Industrial Fuzzy Time Series with Propositional Linear Temporal Logic,” Expert Systems with Applications, Vol.201, Article No.117176, 2022. https://doi.org/10.1016/j.eswa.2022.117176
13. [13] J. C. Gower, “Properties of Euclidean and non-Euclidean distance matrices,” Linear Algebra and its Applications, Vol.67, pp. 81-97, 1985. https://doi.org/10.1016/0024-3795(85)90187-9
14. [14] G. Verdier and A. Ferreira, “Adaptive MD and k-Nearest Neighbor Rule for Fault Detection in Semiconductor Manufacturing,” IEEE Trans. on Semiconductor Manufacturing, Vol.24, No.1, pp. 59-68, 2010. https://doi.org/10.1109/TSM.2010.2065531
15. [15] C. Cheng and M. S. Chiu, “A New Data-Based Methodology for Nonlinear Process Modeling,” Chemical Engineering Science, Vol.59, No.13, pp. 2801-2810, 2004. https://doi.org/10.1016/j.ces.2004.04.020
16. [16] Q. Guo, P. Xu, H. Wang, and J. Liu, “Multimode Process Monitoring Strategy Based on Improved Just-in-Time-Learning Associated with Locality Preserving Projections,” The Canadian J. of Chemical Engineering, Vol.101, No.4, pp. 2002-2017, 2023. https://doi.org/10.1002/cjce.24631
17. [17] G. Fan, X. Ruimin, and H. Biao, “A Deep Learning Just-in-Time Modeling Approach for Soft Sensor Based on Variational Autoencoder,” Chemometrics and Intelligent Laboratory Systems, Vol.197, Article No.103922, 2020. https://doi.org/10.1016/j.chemolab.2019.103922
18. [18] J. Zheng, F. Shen, and L. Ye, “Improved MD Based JITL-LSTM Soft Sensor for Multiphase Batch Processes,” IEEE Access, Vol.9, pp. 72172-72182, 2021. http://doi.org/10.1109/ACCESS.2021.3079184
19. [19] M. Sugiyama, “Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis,” J. of Machine Learning Research, Vol.8, No.5, pp. 1027-1061, 2007.
20. [20] P. Xanthopoulos, P. M. Pardalos, and T. B. Trafalis, “Linear Discriminant Analysis,” Robust Data Mining, pp. 27-33, 2013. https://doi.org/10.1007/978-1-4419-9878-1
21. [21] T. Yan, D. Wang, T. Xia, J. Liu, Z. Peng, and L. Xi, “Investigation on Optimal Discriminant Directions of Linear Discriminant Analysis for Locating Informative Frequency Bands for Machine Health Monitoring,” Mechanical Systems and Signal Processing, Vol.180, Article No.109424, 2022. https://doi.org/10.1016/j.ymssp.2022.109424
22. [22] J. Wang, H. Jiang, and Q. Chen, “High-Precision Recognition of Wheat Mildew Degree Based on Colorimetric Sensor Technique Combined with Multivariate Analysis,” Microchemical J., Vol.168, Article No.106468, 2021. https://doi.org/10.1016/j.microc.2021.106468
23. [23] R. Ran, Y. Ren, S. Zhang, and B. Fang, “A Novel Discriminant Locality Preserving Projections Method,” J. of Mathematical Imaging and Vision, Vol.63, pp. 541-554, 2021. https://doi.org/10.1007/s10851-020-01008-w
24. [24] X. Zhu, S. K. Damarla, K. Hao, and B. Huang “Parallel Interaction Spatiotemporal Constrained Variational Autoencoder for Soft Sensor Modeling,” IEEE Trans. on Industrial Informatics, Vol.18, No.8, pp. 5190-5198, 2021. https://doi.org/10.1109/TII.2021.3110197
25. [25] M. Yang, D. Fan, Y. Wei, P. Tian, and Z. Liu, “Recent Progress in Methanol-to-Olefins (MTO) Catalysts,” Advanced Materials, Vol.31, No.50, Article No.1902181, 2019. https://doi.org/10.1002/adma.201902181
26. [26] P. Chen and Y. Lu, “Extremal Optimization for Optimizing Kernel Function and Its Parameters in Support Vector Regression,” J. of Zhejiang University (Science C), Vol.12, No.4, pp. 297-306, 2011. https://doi.org/10.1631/jzus.C1000110