(Department of Chemical Engineering, Chung Yuan Christian University, Taiwan, Province of China)(2) Sai Kit Ooi
(United Microelectronics Corporation (Singapore Branch), Singapore)(3) * Junghui Chen
(Chung Yuan Christian University, Taiwan, Province of China)*corresponding author
AbstractIn the competitive market, process monitoring can ensure the quality of products, but strong nonlinearities, slow dynamics, and uncertainties characterize the complexities of the large-scale chemical plant. When the fault occurs, it will not influence the process instantaneously but will react after a few time points. After all the products affected by the faults are inspected, it is too late to fix the process. Conventional approaches neither do nor care about early detection before any disturbance significantly affects the process. To estimate disturbances propagated through the process, a multi-step prediction model is essential. The purpose of early process monitoring is to detect any problem with the currently running process as early as possible. In this paper, a multi-step prediction system is proposed. The system is a dynamic model that can capture the dynamic relationship of past process input variables and future process output variables. It provides a lower dimension and a lower noise-contaminated space for data analysis. Particularly, the past input and output process data can be mapped from the observation space into the latent space to acquire their intrinsic properties. The latent variables preserve the dynamic information for future multi-step prediction so that early warning can be achieved. An industrial example of the PVC dying process is presented to show the multistep predictive ability of the proposed method.
|
DOIhttps://doi.org/10.26555/ijain.v10i2.1528 |
Article metricsAbstract views : 185 | PDF views : 29 |
Cite |
Full Text Download
|
References
[1] M. H. Kaspar and W. Harmon Ray, “Dynamic PLS modelling for process control,” Chem. Eng. Sci., vol. 48, no. 20, pp. 3447–3461, Oct. 1993, doi: 10.1016/0009-2509(93)85001-6.
[2] Y. Dong and S. J. Qin, “Regression on dynamic PLS structures for supervised learning of dynamic data,” J. Process Control, vol. 68, pp. 64–72, 2018, doi: 10.1016/j.jprocont.2018.04.006.
[3] M. Wozniak, J. Silka, M. Wieczorek, and M. Alrashoud, “Recurrent neural network model for IoT and networking malware threat detection,” IEEE Trans. Ind. Informatics, vol. 17, no. 8, pp. 5583–5594, 2021, doi: 10.1109/TII.2020.3021689.
[4] M. Wozniak, M. Wieczorek, J. Silka, and D. Polap, “Body pose prediction based on motion sensor data and recurrent neural network,” IEEE Trans. Ind. Informatics, vol. 17, no. 3, pp. 2101–2111, 2021, doi: 10.1109/TII.2020.3015934.
[5] R. C. Staudemeyer and E. R. Morris, “Understanding LSTM – A tutorial into Long Short-Term Memory Recurrent Neural Networks,” arXiv, pp. 1–42, 2019. [Online]. Available at: https://arxiv.org/abs/1909.09586.
[6] Y. Han, C. Fan, M. Xu, Z. Geng, and Y. Zhong, “Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism,” Appl. Therm. Eng., vol. 160, no. July 2018, p. 114072, 2019, doi: 10.1016/j.applthermaleng.2019.114072.
[7] Y. Li, Z. Zhu, D. Kong, H. Han, and Y. Zhao, “EA-LSTM: Evolutionary attention-based LSTM for time series prediction,” Knowledge-Based Syst., vol. 181, p. 104785, 2019, doi: 10.1016/j.knosys.2019.05.028.
[8] Q. Sun and Z. Ge, “Probabilistic Sequential Network for Deep Learning of Complex Process Data and Soft Sensor Application,” IEEE Trans. Ind. Informatics, vol. 15, no. 5, pp. 2700–2709, 2019, doi: 10.1109/TII.2018.2869899.
[9] X. Yin, Z. Niu, Z. He, Z. Li, and D. hee Lee, “Ensemble deep learning based semi-supervised soft sensor modeling method and its application on quality prediction for coal preparation process,” Adv. Eng. Informatics, vol. 46, no. June, p. 101136, 2020, doi: 10.1016/j.aei.2020.101136.
[10] L. Feng, C. Zhao, and Y. Sun, “Dual attention-based encoder-decoder: A customized sequence-to-sequence learning for soft sensor development,” IEEE Trans. Neural Networks Learn. Syst., pp. 1–12, 2020, doi: 10.1109/tnnls.2020.3015929.
[11] J. M. P. Menezes and G. A. Barreto, “Long-term time series prediction with the NARX network: An empirical evaluation,” Neurocomputing, vol. 71, no. 16–18, pp. 3335–3343, 2008, doi: 10.1016/j.neucom.2008.01.030.
[12] A. Grigorievskiy, Y. Miche, A. M. Ventelä, E. Séverin, and A. Lendasse, “Long-term time series prediction using OP-ELM,” Neural Networks, vol. 51, pp. 50–56, 2014, doi: 10.1016/j.neunet.2013.12.002.
[13] R. M. Adnan, Z. Liang, S. Trajkovic, M. Zounemat-Kermani, B. Li, and O. Kisi, “Daily streamflow prediction using optimally pruned extreme learning machine,” J. Hydrol., vol. 577, no. July, p. 123981, 2019, doi: 10.1016/j.jhydrol.2019.123981.
[14] H. Li, Y. He, H. Yang, Y. Wei, S. Li, and J. Xu, “Rainfall prediction using optimally pruned extreme learning machines,” Nat. Hazards, vol. 108, no. 1, pp. 799–817, 2021, doi: 10.1007/s11069-021-04706-9.
[15] G. Shi, C. Qin, J. Tao, and C. Liu, “A VMD-EWT-LSTM-based multi-step prediction approach for shield tunneling machine cutterhead torque,” Knowledge-Based Syst., vol. 228, p. 107213, 2021, doi: 10.1016/j.knosys.2021.107213.
[16] Y. Duan, Y. Lv, and F. Y. Wang, “Travel time prediction with LSTM neural network,” IEEE Conf. Intell. Transp. Syst. Proceedings, ITSC, pp. 1053–1058, 2016, doi: 10.1109/ITSC.2016.7795686.
[17] Z. Karevan and J. A. K. Suykens, “Transductive LSTM for time-series prediction: An application to weather forecasting,” Neural Networks, vol. 125, pp. 1–9, 2020, doi: 10.1016/j.neunet.2019.12.030.
[18] A. Zhang, X. Zhao, and L. Wang, “CNN and LSTM based Encoder-Decoder for Anomaly Detection in Multivariate Time Series,” IEEE Inf. Technol. Networking, Electron. Autom. Control Conf. ITNEC 2021, vol. 5, pp. 571–575, 2021, doi: 10.1109/ITNEC52019.2021.9587207.
[19] M. Sibtain et al., “Multifaceted irradiance prediction by exploiting hybrid decomposition-entropy-Spatiotemporal attention based Sequence2Sequence models,” Renew. Energy, vol. 196, pp. 648–682, 2022, doi: 10.1016/j.renene.2022.07.041.
[20] W. Deng, Y. Li, K. Huang, D. Wu, C. Yang, and W. Gui, “LSTMED: An uneven dynamic process monitoring method based on LSTM and Autoencoder neural network,” Neural Networks, vol. 158, pp. 30–41, 2023, doi: 10.1016/j.neunet.2022.11.001.
[21] F. Yan, C. Yang, and X. Zhang, “DSTED: A Denoising Spatial-Temporal Encoder-Decoder Framework for Multistep Prediction of Burn-Through Point in Sintering Process,” IEEE Trans. Ind. Electron., vol. 69, no. 10, pp. 10735–10744, 2022, doi: 10.1109/TIE.2022.3151960.
[22] Z. Li, S. Riaz, M. Waqas, and M. Batool, “An Enhanced Gated Recurrent Unit-Based Adaptive Fault Diagnosis of Rotating Machinery,” Shock Vib., vol. 2022, p. 13, 2022, doi: 10.1155/2022/4648311.
[23] R. Guo and H. Liu, “A Hybrid Mechanism- And Data-Driven Soft Sensor Based on the Generative Adversarial Network and Gated Recurrent Unit,” IEEE Sens. J., vol. 21, no. 22, pp. 25901–25911, 2021, doi: 10.1109/JSEN.2021.3117981.
[24] T. Limouni, R. Yaagoubi, K. Bouziane, K. Guissi, and E. H. Baali, “Accurate one step and multistep forecasting of very short-term PV power using LSTM-TCN model,” Renew. Energy, vol. 205, no. December 2022, pp. 1010–1024, 2023, doi: 10.1016/j.renene.2023.01.118.
[25] H. Zhao, H. Liu, J. Xu, C. Guo, and W. Deng, “Research on a fault diagnosis method of rolling bearings using variation mode decomposition and deep belief network,” J. Mech. Sci. Technol., vol. 33, no. 9, pp. 4165–4172, 2019, doi: 10.1007/s12206-019-0811-2.
[26] Z. Geng, X. Duan, Y. Han, F. Liu, and W. Xu, “Novel variation mode decomposition integrated adaptive sparse principal component analysis and it application in fault diagnosis,” ISA Trans., vol. 128, pp. 21–31, 2022, doi: 10.1016/j.isatra.2021.11.002.
[27] S. Lin, R. Clark, R. Birke, and S. Sch, “Anomaly detection for time series using VAE-LSTM hybrid model,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), Barcelona, 2020, pp. 4322–4326, doi: 10.1109/ICASSP40776.2020.9053558.
[28] Q. Quan, Z. Hao, H. Xifeng, and L. Jingchun, “Research on water temperature prediction based on improved support vector regression,” Neural Comput. Appl., vol. 34, no. 11, pp. 8501–8510, 2022, doi: 10.1007/s00521-020-04836-4.
[29] G. F. Fan, M. Yu, S. Q. Dong, Y. H. Yeh, and W. C. Hong, “Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling,” Util. Policy, vol. 73, no. September, p. 101294, 2021, doi: 10.1016/j.jup.2021.101294.
[30] K. Zhang, H. Cao, J. Thé, and H. Yu, “A hybrid model for multi-step coal price forecasting using decomposition technique and deep learning algorithms,” Appl. Energy, vol. 306, no. October 2021, 2022, doi: 10.1016/j.apenergy.2021.118011.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0