Abstract
Intelligence modeling interpretable for incipient fault diagnosis of batch process represents a serious challenge. For the multivariate, nonlinear, and high-dimensionality characteristics of process data, existing fault diagnosis solutions are easily concealed by noise while neglect the low amplitude and noise interference of the incipient faults. In this paper, an intelligent incipient fault diagnosis model based on deep time series feature extraction network is proposed, which integrates denoising autoencoder (DAE), layer normalization and dropout layer added LSTM (LD-LSTM), and stacked autoencoder (SAE) to obtain the efficient features. DAE is applied to restore the data and eliminate noise interference. LD-LSTM is utilized to extract time series features, in which the layer normalization and the dropout layer are added between the layers of the LSTM to solve the problems of slow model convergence and over-fitting. SAE performs the feature extraction to obtain deep time series features and learns more efficient expressions. The softmax function is applied to achieve the incipient fault diagnosis based on the deep time series features. A case study on a fed-batch penicillin fermentation process suggests that the proposed method can obtain an accuracy rate of 98.97%, which has increased an average of 20% than the traditional shallow machine learning. The accuracy of fault recognition and comparative experiments demonstrate the effectiveness and feasibility of this model, and provide a solution for the application of intelligent fault diagnosis in batch industries.
Similar content being viewed by others
Data Availability Statement
All data generated or analyzed during the study are included in the submitted paper or supplemental materials files
References
Gao, X.J.; Xu, Z.D.; Li, Z., et al.: Batch process monitoring using multiway laplacian autoencoders. Can. J. Chem. Eng. 98(6), 1269–1279 (2020)
Franz, D.B.; Oscar, A.P.; Jakob, K.H.: Discrete-continuous dynamic simulation of plantwide batch process continuous dynamic simulation of plantwide batch process systems in MATLAB. Chem. Eng. Res. Des. 159(7), 66–77 (2020)
Zhu, J.L.; Yao, Y.; Gao, F.R.: Multiphase two-dimensional time-slice dynamic system for batch process monitoring. J. Process Control 85(1), 184–198 (2020)
Walid, A.; Abdelkader, K.; Noureddine, L.: Neural observer-based small fault detection and isolation for uncertain nonlinear systems. Int. J. Adapt. Control Signal Process. 34(5), 677–702 (2020)
Hussain, S.; Wang, X.G.; Ahmad, S., et al.: On a class of mixed EWMA-CUSUM median control charts for process monitoring. Quality Reliab. Eng. Int. 36(3), 910–946 (2020)
Nomikos, P.; MacGregor, J.: Multivariate statistical process control charts for batch monitoring of transesterification reactions for biodiesel production based on near-infrared spectroscopy. Comput. Chem. Eng. 94, 343–353 (2016)
Jiang, Q.; Yan, X.: Parallel PCA-KPCA for nonlinear process monitoring. Control Eng Practice 80, 17–25 (2018)
Zhang, H.; Qi, Y.; Wang, L., et al.: Fault detection and diagnosis of chemical process using enhanced KECA. Chem. Intell. Lab. Syst. 161, 61–69 (2017)
Zhang M, Wang R Q, Cai Z Y, et al. Phase partition and identification based on KECA and MSVM_FWA for multi-phase batch process fault diagnosis. Transactions of the Institute of Measurement and Control, First online, https://doi.org/https://doi.org/10.1177/0142331220910885.
Li, H.M.; Huang, J.Y.; Ji, S.W.: Bearing fault diagnosis with a feature fusion method based on an ensemble convolutional neural network and deep neural network. Sensors 19(9), 1–18 (2019)
Zhang, C.L.; He, Y.G.; Du, B.L., et al.: Transformer fault diagnosis method using IoT based monitoring system and ensemble machine learning. Fut. Gener. Comput. Syst. 108, 533–545 (2020)
Hamideh, R.; Blue, J.; Claude, Y.: Automatic equipment fault fingerprint extraction for the fault diagnostic on the batch process data. Appl. Soft Comput. 68(7), 972–989 (2018)
Ji, J.J.; Qu, J.F.; Chai, Y., et al.: An algorithm for sensor fault diagnosis with EEMD-SVM[J]. Trans. Instit. Meas. Control 40(6), 1746–1756 (2018)
Shao, H.D.; Jiang, H.K.; Li, X.Q.: Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine. Knowledge Based Syst. 140, 1–14 (2018)
Zhai M , Xiang X , Zhang R , et al. Optical flow estimation using dual self-attention pyramid networks. IEEE Transactions on Circuits and Systems for Video Technology, 2019, pp (99):1–1.
Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D 404(3), 132306 (2020)
Wang, S.; Wang, P.L.: Fault detection method for batch process based on deep long short-term memory network and batch normalization. J. Comput. Appl. 39(02), 370–375 (2019)
Zhang, X.; Zou, Y.Y.; Li, S.Y., et al.: A weighted auto regressive LSTM based approach for chemical processes modeling. Neurocomputing 367(20), 64–74 (2019)
Pan, Y.T.; He, F.Z.; Yu, H.P.: A correlative denoising autoencoder to model social influence for Top-N recommender system. Front. Comput. Sci. 14(3), 143301 (2020)
Chow, J.K.; Su, Z.; Wu, J., et al.: Anomaly detection of defects on concrete structures with the convolutional autoencoder. Adv. Eng. Inform. 45(8), 101–105 (2020)
Kensuke, H.; Masahiro, W.: Application of the DAE approach to the nonlinear sloshing problem. Nonlinear Dyn. 99(3), 2065–2081 (2020)
Su, C.H.; Jiang, M.S.; Liang, J.Y., et al.: Damage assessments of composite under the environment with strong noise based on synchrosqueezing wavelet transform and stack autoencoder algorithm. Measurement 156(5), 107587 (2020)
Li, F.; Gui, Z.P.; Zhang, Z.Y., et al.: A hierarchical temporal attention-based LSTM encoder-decoder model for individual mobility prediction[J]. Neurocomputing 403(25), 153–166 (2020)
Erdenebayar, U.; Jong-Uk, P.; Kyoung-Joung, L.: Automatic detection of sleep-disordered breathing events using recurrent neural networks from an electrocardiogram signal. Neural Comput. Appl. 32(9), 4733–4742 (2020)
Kang S Q, Zhou Y, Wang Y J, et al. RUL prediction method of a rolling bearing based on improved SAE and Bi-LSTM[J/OL]. Acta Automatica Sinica:1–11[2020–05–18]. https://doi.org/https://doi.org/10.16383/j.aas.c190796(in Chinese).
Lyu, P.Y.; Chen, N.; Mao, S.J., et al.: LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion[J]. Process Saf. Environ. Prot. 137, 93–105 (2020)
Max, S.; Murat, K.: Monitoring batch processes with dynamic time warping and K-nearest neighbours. Chem. Intell. Lab. Syst. 183, 102–112 (2018)
Sun, W.; Meng, Y.; Ahmet, P., et al.: A method for multiphase batch process monitoring based on auto phase identification. J. Process Control 21(4), 627–638 (2010)
Li, K.Q.; Feng, J.: Grouping multi-rate sampling fault detection method for penicillin fermentation process. Can. J. Chem. Eng. 98(6), 1319–1327 (2020)
Acknowledgements
This work is partially supported by China Postdoctoral Science Foundation (No.2020M673279), National Natural Science Foundation of China (NSFC) (No. 51675450), Sichuan Science and Technology Program (No. 2020JDTD0012), and MOE (Ministry of Education in China) Project of Humanities and Social Sciences (No. 18YJC630255).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that there is no conflict of interests regarding the publication of this paper.
Rights and permissions
About this article
Cite this article
Zhang, M., Li, X. & Wang, R. Incipient Fault Diagnosis of Batch Process Based on Deep Time Series Feature Extraction. Arab J Sci Eng 46, 10125–10136 (2021). https://doi.org/10.1007/s13369-021-05388-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-05388-y