Process prediction and detection of faults using probabilistic bidirectional recurrent neural networks on real plant data

Yerimah, Lucky E.; Ghosh, Sambit; Wang, Yajun; Cao, Yanan; Flores‐Cerrillo, Jesus; Bequette, B. Wayne

doi:10.1002/amp2.10124

Title: Process prediction and detection of faults using probabilistic bidirectional recurrent neural networks on real plant data

Journal Article · 09 May 2022 · Journal of Advanced Manufacturing and Processing

DOI: https://doi.org/10.1002/amp2.10124 · OSTI ID:1868938

^[1]; Ghosh, Sambit ^[1]; Wang, Yajun ^[2]; Cao, Yanan ^[2]; Flores‐Cerrillo, Jesus ^[2]; Bequette, B. Wayne ^[1]

Rensselaer Polytechnic Inst., Troy, NY (United States)
Linde, Inc., Tonawanda, NY (United States). Smart Operations, Center of Excellence (COE)

Abstract Attaining Industry 4.0 for manufacturing operations requires advanced monitoring systems and real‐time data analytics of plant data, among other topics. We propose a probabilistic bidirectional recurrent network (PBRN) for industrial process monitoring for the early detection of faults. The model is based on a gated recurrent unit (GRU) neural network that allows the model to retain long‐term dependencies between sensor data along a time horizon, hence learning the dynamic behavior of the process. To reduce the false‐positive detection rate of the model, we compel the model to learn from a highly noisy sensor reading while outputting noise‐free sensor outputs. The performance of the proposed model is compared with other data‐driven statistical process monitoring schemes using real plant data from an industrial air separations unit (ASU) containing noisy sensor readings. We show that the model can learn from noisy data without reducing its performance. Using two different fault cases, we demonstrate the model's ability to carry out early fault detection with average false‐positive rates of 2.9% and 4.9% for both fault cases. The missed detection rates are 0.1% and 0.2%, respectively.

View Accepted Manuscript (DOE)

View Accepted Manuscript (Publisher)

Cite

Export

Save

Research Organization:: Univ. of California, Los Angeles, CA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE); CESMII

Grant/Contract Number:: EE0007613; 4550-G-WA324

OSTI ID:: 1868938

Alternate ID(s):: OSTI ID: 1868151; OSTI ID: 1893184

Journal Information:: Journal of Advanced Manufacturing and Processing, Vol. 4, Issue 4; ISSN 2637-403X

Publisher:: American Institute of Chemical Engineers (AIChE), WileyCopyright Statement

Country of Publication:: United States

Language:: English

References (25)

Bidirectional recurrent neural networks Schuster, M.; Paliwal, K. K. IEEE Transactions on Signal Processing, Vol. 45, Issue 11 https://doi.org/10.1109/78.650093	journal	January 1997
Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders Liu, Han; Zhou, Jianzhong; Zheng, Yang ISA Transactions, Vol. 77 https://doi.org/10.1016/j.isatra.2018.04.005	journal	June 2018
Product property and production rate control of styrene polymerization Prasad, Vinay; Schley, Matthias; Russo, Louis P. Journal of Process Control, Vol. 12, Issue 3 https://doi.org/10.1016/S0959-1524(01)00044-0	journal	April 2002
Hybrid Modeling in the Era of Smart Manufacturing Yang, Shu; Navarathna, Pranesh; Ghosh, Sambit Computers & Chemical Engineering, Vol. 140 https://doi.org/10.1016/j.compchemeng.2020.106874	journal	September 2020
A novel dynamic PCA algorithm for dynamic data modeling and process monitoring Dong, Yining; Qin, S. Joe Journal of Process Control, Vol. 67 https://doi.org/10.1016/j.jprocont.2017.05.002	journal	July 2018
Dynamic modeling and collocation-based model reduction of cryogenic air separation units Cao, Yanan; Swartz, Christopher L. E.; Flores-Cerrillo, Jesus AIChE Journal, Vol. 62, Issue 5 https://doi.org/10.1002/aic.15164	journal	January 2016
Dynamic-Inner Partial Least Squares for Dynamic Data Modeling Dong, Yining; Qin, S. Joe IFAC-PapersOnLine, Vol. 48, Issue 8 https://doi.org/10.1016/j.ifacol.2015.08.167	journal	January 2015
Nonlinear process monitoring using kernel principal component analysis Lee, Jong-Min; Yoo, ChangKyoo; Choi, Sang Wook Chemical Engineering Science, Vol. 59, Issue 1 https://doi.org/10.1016/j.ces.2003.09.012	journal	January 2004
A combined canonical variate analysis and Fisher discriminant analysis (CVA–FDA) approach for fault diagnosis Jiang, Benben; Zhu, Xiaoxiang; Huang, Dexian Computers & Chemical Engineering, Vol. 77 https://doi.org/10.1016/j.compchemeng.2015.03.001	journal	June 2015
Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey Wei, Ruoqi; Mahmood, Ausif IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2020.3048309	journal	January 2021
Statistical process monitoring of a multiphase flow facility Ruiz-Cárcel, C.; Cao, Y.; Mba, D. Control Engineering Practice, Vol. 42 https://doi.org/10.1016/j.conengprac.2015.04.012	journal	September 2015
Quantum computing assisted deep learning for fault detection and diagnosis in industrial process systems Ajagekar, Akshay; You, Fengqi Computers & Chemical Engineering, Vol. 143 https://doi.org/10.1016/j.compchemeng.2020.107119	journal	December 2020
Interpretation and compensation of backlash error data in machine centers for intelligent predictive maintenance using ANNs Wang, Ke-Sheng; Li, Zhe; Braaten, Jørgen Advances in Manufacturing, Vol. 3, Issue 2 https://doi.org/10.1007/s40436-015-0107-4	journal	May 2015
Smart Manufacturing Davis, Jim; Edgar, Thomas; Graybill, Robert Annual Review of Chemical and Biomolecular Engineering, Vol. 6, Issue 1 https://doi.org/10.1146/annurev-chembioeng-061114-123255	journal	July 2015
Fault detection of process correlation structure using canonical variate analysis-based correlation features Jiang, Benben; Braatz, Richard D. Journal of Process Control, Vol. 58 https://doi.org/10.1016/j.jprocont.2017.09.003	journal	October 2017
Categorization of Anomalies in Smart Manufacturing Systems to Support the Selection of Detection Mechanisms Lopez, Felipe; Saez, Miguel; Shao, Yuru IEEE Robotics and Automation Letters, Vol. 2, Issue 4 https://doi.org/10.1109/LRA.2017.2714135	journal	October 2017
Smart manufacturing and energy systems Edgar, Thomas F.; Pistikopoulos, Efstratios N. Computers & Chemical Engineering, Vol. 114 https://doi.org/10.1016/j.compchemeng.2017.10.027	journal	June 2018
A novel process monitoring approach based on variational recurrent autoencoder Cheng, Feifan; He, Q. Peter; Zhao, Jinsong Computers & Chemical Engineering, Vol. 129 https://doi.org/10.1016/j.compchemeng.2019.106515	journal	October 2019
Information concentrated variational auto-encoder for quality-related nonlinear process monitoring Zhu, Jiazhen; Shi, Hongbo; Song, Bing Journal of Process Control, Vol. 94 https://doi.org/10.1016/j.jprocont.2020.08.002	journal	October 2020
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Process monitoring using causal graphical models, with application to clogging detection in steel continuous casting Yang, Shu; Rebmann, Andreas; Tang, Ming Journal of Process Control, Vol. 105 https://doi.org/10.1016/j.jprocont.2021.08.006	journal	September 2021
Geometric properties of partial least squares for process monitoring Li, Gang; Qin, S. Joe; Zhou, Donghua Automatica, Vol. 46, Issue 1 https://doi.org/10.1016/j.automatica.2009.10.030	journal	January 2010
Statistical process monitoring: basics and beyond Joe Qin, S. Journal of Chemometrics, Vol. 17, Issue 8-9 https://doi.org/10.1002/cem.800	journal	January 2003
Backpropagation through time: what it does and how to do it Werbos, P. J. Proceedings of the IEEE, Vol. 78, Issue 10 https://doi.org/10.1109/5.58337	journal	January 1990
Deep convolutional neural network model based chemical process fault diagnosis Wu, Hao; Zhao, Jinsong Computers & Chemical Engineering, Vol. 115 https://doi.org/10.1016/j.compchemeng.2018.04.009	journal	July 2018

Similar Records

A graph signal processing‐based multiple model Kalman filter ( GSP‐MMKF ) tool for predictive analytics: An air separation unit process application

Journal Article · 2022 · Journal of Advanced Manufacturing and Processing · OSTI ID:1867913

Ghosh, Sambit; Yerimah, Lucky E.; Wang, Yajun; +3 more

Smart connected worker edge platform for smart manufacturing: Part 2—Implementation and on‐site deployment case study

Journal Article · 2022 · Journal of Advanced Manufacturing and Processing · OSTI ID:1872274

Donovan, Richard P.; Kim, Yoon G.; Manzo, Anthony; +8 more

Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing

Journal Article · 2022 · Materials & Design · OSTI ID:1977418

Gaikwad, Aniruddha; Williams, Richard J.; de Winton, Harry; +4 more

Related Subjects

42 ENGINEERING
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Industry 4.0
Probabilistic bidirectional recurrent network
Gated recurrent unit
Air separation unit
industry 4.0
probabilistic bidirectional recurrent network
gated recurrent unit
air separation unit

Title: Process prediction and detection of faults using probabilistic bidirectional recurrent neural networks on real plant data

Citation Formats

References (25)

Similar Records

Related Subjects