Welcome to Francis Academic Press

Academic Journal of Engineering and Technology Science, 2023, 6(9); doi: 10.25236/AJETS.2023.060906.

Deep Koopman Neural Network Based Process Monitoring for Stochastic Production System


Yanhui Liu, Xin Jin, Saiwei Wang

Corresponding Author:
Yanhui Liu

Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, China


Stochastic production system (SPS) refers to a production process that is influenced by a large number of random factors, typical examples including industrial biosystem, composite material production system, and batch chemical reaction system. Notably, SPS is notorious for significant uncertainty and stochasticity, thereby making implementing process monitoring to ensure product quality a daunting task. One of the major underlying obstacles is how to accurately detect anomalies thereof in real time. To resolve so, this paper proposes a deep Koopman neural network based approach, wherein two deep neural networks constitute a bijective mapping between original data space and a linear high-dimensional space, and a linear operator describes dynamic evolution in the linear space. The performance of the proposed method is tested on two examples of SPS, which are of significant intrinsic stochastic dynamics, hence arguably constituting a novel class of benchmarks for performance comparing of various process monitoring algorithms, and becoming another contribution of this paper.


Koopman Operator Theory, Stochastic Production System, Deep Learning, Anomaly Detection, Process Monitoring

Cite This Paper

Yanhui Liu, Xin Jin, Saiwei Wang. Deep Koopman Neural Network Based Process Monitoring for Stochastic Production System. Academic Journal of Engineering and Technology Science (2023) Vol. 6, Issue 9: 31-42. https://doi.org/10.25236/AJETS.2023.060906.


[1] Wang, G., Haringa, C., Noorman, H., Chu, J., and Zhuang, Y. (2020). Developing a Computational Framework to Advance Bioprocess Scale-Up. Trends in Biotechnology, 38(8), 846-856.

[2] Lu, J., Cao, Z., Zhao, C., and Gao, F. (2019). 110th Anniversary: An Overview on Learning-Based Model Predictive Control for Batch Processes. Industrial & Engineering Chemistry Research, 58(37), 17164-17173.

[3] Jiang, Q., Wang, Z., Yan, S., and Cao, Z. (2022). Data-Driven Soft Sensing for Batch Processes Using Neural Network-Based Deep Quality-Relevant Representation Learning. IEEE Transactions on Artificial Intelligence.

[4] Cao, Z., Yu, J., Wang, W., Lu, H., Xia, X., Xu, H., and Zhang, L. (2020). Multi-Scale Data-Driven Engineering for Biosynthetic Titer Improvement. Current Opinion in Biotechnology, 65, 205-212.

[5] Gao, J., Feng, E., and Zhang, W. (2022). Modeling and Parameter Identification of Microbial Batch Fermentation under Environmental Disturbances. Applied Mathematical Modelling, 108, 205-219.

[6] Soukoulis, C., Panagiotidis, P., Koureli, R., and Tzia, C. (2007). Industrial Yogurt Manufacture: Monitoring of Fermentation Process and Improvement of Final Product Quality. Journal of dairy science, 90(6), 2641-2654.

[7] Sriramula, S., and Chryssanthopoulos, M. K. (2009). Quantification of Uncertainty Modelling in Stochastic Analysis of FRP Composites. Composites Part A: Applied Science and Manufacturing, 40(11), 1673-1684.

[8] Lu, H., Plataniotis, K. N., and Venetsanopoulos, A. N. (2008). MPCA: Multilinear Principal Component Analysis of Tensor Objects. IEEE transactions on Neural Networks, 19(1), 18-39.

[9] Lee, J. M., Yoo, C., and Lee, I. B. (2004). Fault Detection of Batch Processes Using Multiway Kernel Principal Component Analysis. Computers & Chemical Engineering, 28(9), 1837-1847.

[10] Jia, Z. Y., Wang, P., and Gao, X. J. (2012). Process Monitoring and Fault Diagnosis of Penicillin Fermentation Based on Improved MICA. Advanced Materials Research, 591, 1783-1788.

[11] Zhao, C., Gao, F., and Wang, F. (2009). Nonlinear Batch Process Monitoring Using Phase-Based Kernel-Independent Component Analysis−Principal Component Analysis (KICA−PCA). Industrial & Engineering Chemistry Research, 48(20), 9163-9174.

[12] Peng, C., Chunhao, D., and Qiankun, Z. (2020). Fault Diagnosis of Microbial Pharmaceutical Fermentation Process with Non-Gaussian and Nonlinear Coexistence. Chemometrics and Intelligent Laboratory Systems, 199, 103931.

[13] Yang, C., and Hou, J. (2016). Fed-Batch Fermentation Penicillin Process Fault Diagnosis and Detection Based on Support Vector Machine. Neurocomputing, 190, 117-123.

[14] Ding, J., Cao, Y., Mpofu, E., and Shi, Z. (2012). A Hybrid Support Vector Machine and Fuzzy Reasoning Based Fault Diagnosis and Rescue System for Stable Glutamate Fermentation. Chemical Engineering Research and Design, 90(9), 1197-1207.

[15] Hornik, K., Stinchcombe, M., and White, H. (1989). Multilayer Feedforward Networks Are Universal Approximators. Neural Networks, 2(5), 359-366. 

[16] Shimizu, H., Yasuoka, K., Uchiyama, K., and Shioya, S. (1997). On-Line Fault Diagnosis for Optimal Rice a-Amylase Production Process of a Temperature-Sensitive Mutant of Saccharomyces Cerevisiae by an Autoassociative Neural Network. Journal of Fermentation and Bioengineering, 83(5), 435-442.

[17] Lopes, J. A., and Menezes, J. C. (2004). Multivariate Monitoring of Fermentation Processes with Non-Linear Modelling Methods. Analytica Chimica Acta, 515(1), 101-108. 

[18] Yu, J., Zhang, C., and Wang, S. (2021). Multichannel One-Dimensional Convolutional Neural Network-Based Feature Learning for Fault Diagnosis of Industrial Processes. Neural Computing and Applications, 33, 3085-3104.

[19] Chen, S., Yu, J., and Wang, S. (2020). One-Dimensional Convolutional Auto-Encoder-Based Feature Learning for Fault Diagnosis of Multivariate Processes. Journal of Process Control, 87, 54-67.

[20] Peng, C., Lu, R., Kang, O., and Kai, W. (2020). Batch Process Fault Detection for Multi-Stage Broad Learning System. Neural Networks, 129, 298-312. 

[21] Chen, H., Liu, Z., Alippi, C., Huang, B., and Liu, D. (2022). Explainable Intelligent Fault Diagnosis for Nonlinear Dynamic Systems: From Unsupervised to Supervised Learning. IEEE Transactions on Neural Networks and Learning Systems.

[22] Chen, H., Chai, Z., Dogru, O., Jiang, B., and Huang, B. (2021). Data-Driven Designs of Fault Detection Systems Via Neural Network-Aided Learning. IEEE Transactions on Neural Networks and Learning Systems, 33(10), 5694-5705.

[23] Sherstinsky, A. (2020). Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network. Physica D: Nonlinear Phenomena, 404, 132306.

[24] Zhang, M., Li, X., and Wang, R. (2021). Incipient Fault Diagnosis of Batch Process Based on Deep Time Series Feature Extraction. Arabian Journal for Science and Engineering, 1-12.

[25] Ren, J., and Ni, D. (2020). A Batch-Wise LSTM-Encoder Decoder Network for Batch Process Monitoring. Chemical Engineering Research and Design, 164, 102-112.

[26] Koopman, B. O. (1931). Hamiltonian Systems and Transformation in Hilbert Space. Proceedings of the National Academy of Sciences, 17(5), 315-318.

[27] Brunton, S. L. (2019). Notes on Koopman Operator Theory. Universität Von Washington, Department of Mechanical Engineering, Zugriff, 30.

[28] Rowley, C. W., Mezić, I., Bagheri, S., Schlatter, P., and Henningson, D. S. (2009). Spectral Analysis of Nonlinear Flows. Journal of Fluid Mechanics, 641, 115-127.

[29] Schmid, P. J. (2010). Dynamic Mode Decomposition of Numerical and Experimental Data. Journal of Fluid Mechanics, 656, 5-28.

[30] Williams, M. O., Kevrekidis, I. G., and Rowley, C. W. (2015). A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition. Journal of Nonlinear Science, 25, 1307-1346.

[31] Korda, M., and Mezić, I. (2018). Linear Predictors for Nonlinear Dynamical Systems: Koopman Operator Meets Model Predictive Control. Automatica, 93, 149-160.

[32] Brunton, S. L., Brunton, B. W., Proctor, J. L., and Kutz, J. N. (2016). Koopman Invariant Subspaces and Finite Linear Representations of Nonlinear Dynamical Systems for Control. Plos One, 11(2), e0150171.

[33] Lusch, B., Kutz, J. N., and Brunton, S. L. (2018). Deep Learning for Universal Linear Embeddings of Nonlinear Dynamics. Nature Communications, 9(1), 4950.

[34] Yeung, E., Kundu, S., and Hodas, N. (2019, July). Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems. In 2019 American Control Conference (ACC) (pp. 4832-4839). IEEE.

[35] Dubey, R., Samantaray, S. R., Panigrahi, B. K., and Venkoparao, V. G. (2016). Koopman Analysis Based Wide-Area Back-Up Protection and Faulted Line Identification for Series-Compensated Power Network. IEEE Systems Journal, 12(3), 2634-2644.

[36] Dang, Z., Lv, Y., Li, Y., and Wei, G. (2018). Improved Dynamic Mode Decomposition and Its Application to Fault Diagnosis of Rolling Bearing. Sensors, 18(6), 1972.

[37] Cheng, C., Ding, J., and Zhang, Y. (2020). A Koopman Operator Approach for Machinery Health Monitoring and Prediction with Noisy and Low-Dimensional Industrial Time Series. Neurocomputing, 406, 204-214.

[38] Liu, B., Xiao, Y., Cao, L., Hao, Z., and Deng, F. (2013). Svdd-Based Outlier Detection on Uncertain Data. Knowledge and Information Systems, 34, 597-618.

[39] Larsson, A. J., Johnsson, P., Hagemann-Jensen, M., Hartmanis, L., Faridani, O. R., Reinius, B., and Sandberg, R. (2019). Genomic Encoding of Transcriptional Burst Kinetics. Nature, 565(7738), 251-254. 

[40] Cao, Z., and Grima, R. (2020). Analytical Distributions for Detailed Models of Stochastic Gene Expression in Eukaryotic Cells. Proceedings of the National Academy of Sciences, 117(9), 4682-4692.

[41] Gillespie, D. T. (1977). Exact Stochastic Simulation of Coupled Chemical Reactions. The Journal of Physical Chemistry, 81(25), 2340-2361.

[42] Fu, X., Zhou, X., Gu, D., Cao, Z., and Grima, R. (2022). DelaySSAToolkit. jl: Stochastic Simulation of Reaction Systems with Time Delays in Julia. Bioinformatics, 38(17), 4243-4245.

[43] Brunton, S. L., Budišić, M., Kaiser, E., and Kutz, J. N. (2021). Modern Koopman Theory for Dynamical Systems. arXiv preprint arXiv:2102.12086.

[44] Cao, Z., and Grima, R. (2018). Linear Mapping Approximation of Gene Regulatory Networks with Stochastic Dynamics. Nature Communications, 9(1), 3305.