Fault detection and diagnosis for reactive distillation based on convolutional neural network

Abstract Reactive distillation (RD) shows its strength in achieving process intensification. However, the complex phenomena integrated in RD usually leads to various abnormal operating states, e.g. catalyst deactivation. Although control schemes have been designed to tackle some disturbances, diagnosing the operating state online is of vital importance for effectively avoiding serious accidents. In the present work, by using intensified process for formic acid production as benchmark, optimal design with stochastic algorithm was firstly performed and dynamic test was carried out to validate effectiveness of control structure. Then thirteen practical faults were considered and the corresponding response was simulated. By considering features in both spatial and temporal domain, historical dynamic process data with measurement noise was used to formulate samples, based on which deep convolutional neural network was trained and validated. The machine learning information in each layer was visualized using t-SNE and fault diagnosis rate shows the significance of the method.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  Dongfeng Zhao,et al.  Fault diagnosis for distillation process based on CNN–DAE , 2019, Chinese Journal of Chemical Engineering.

[3]  Kus Hidajat,et al.  Design, Optimization, and Retrofit of the Formic Acid Process I: Base Case Design and Dividing-Wall Column Retrofit , 2018, Industrial & Engineering Chemistry Research.

[4]  Raghunathan Rengaswamy,et al.  A framework for on-line trend extraction and fault diagnosis , 2010, Eng. Appl. Artif. Intell..

[5]  Jay H. Lee,et al.  Fault detection and classification using artificial neural networks , 2018 .

[6]  Xuefeng Yan,et al.  Gaussian and non-Gaussian Double Subspace Statistical Process Monitoring Based on Principal Component Analysis and Independent Component Analysis , 2015 .

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  Reza Eslamloueyan,et al.  Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee-Eastman process , 2011, Appl. Soft Comput..

[9]  Raghunathan Rengaswamy,et al.  Fault Diagnosis by Qualitative Trend Analysis of the Principal Components , 2005 .

[10]  Xigang Yuan,et al.  Easy-to-Operate and Energy-Efficient Four-Product Dividing Wall Columns with Two Partition Walls , 2020, Industrial & Engineering Chemistry Research.

[11]  Jun Cai,et al.  Multi-fault classification based on support vector machine trained by chaos particle swarm optimization , 2010, Knowl. Based Syst..

[12]  Zhiqiang Ge,et al.  Local ICA for multivariate statistical fault diagnosis in systems with unknown signal and error distributions , 2012 .

[13]  Faisal Khan,et al.  Process Fault Prognosis Using Hidden Markov Model–Bayesian Networks Hybrid Model , 2019, Industrial & Engineering Chemistry Research.

[14]  Hao Wu,et al.  Deep convolutional neural network model based chemical process fault diagnosis , 2018, Comput. Chem. Eng..

[15]  Raghunathan Rengaswamy,et al.  A Signed Directed Graph and Qualitative Trend Analysis-Based Framework for Incipient Fault Diagnosis , 2007 .

[16]  Chun-Chin Hsu,et al.  A novel process monitoring approach with dynamic independent component analysis , 2010 .

[17]  Na Yu,et al.  Composition control and temperature inferential control of dividing wall column based on model predictive control and PI strategies , 2017 .

[18]  Qunxiong Zhu,et al.  Study and Application of Fault Prediction Methods with Improved Reservoir Neural Networks , 2014 .

[19]  Zhanpeng Zhang,et al.  A deep belief network based fault diagnosis model for complex chemical processes , 2017, Comput. Chem. Eng..

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Chenglin Wen,et al.  Analysis of Principal Component Analysis-Based Reconstruction Method for Fault Diagnosis , 2016 .

[22]  Shoutao Ma,et al.  Controllability, Energy-Efficiency, and Safety Comparisons of Different Control Schemes for Producing n-Butyl Acetate in a Reactive Dividing Wall Column , 2019, Industrial & Engineering Chemistry Research.

[23]  Bart De Ketelaere,et al.  A systematic comparison of PCA-based statistical process monitoring methods for high-dimensional, time-dependent processes , 2016 .

[24]  Yingwei Zhang,et al.  Multivariate process monitoring and analysis based on multi-scale KPLS , 2011 .

[25]  Ignacio Díaz Blanco,et al.  Visual analysis of a cold rolling process using a dimensionality reduction approach , 2013, Eng. Appl. Artif. Intell..

[26]  Fuli Wang,et al.  Novel Monitoring Strategy Combining the Advantages of the Multiple Modeling Strategy and Gaussian Mixture Model for Multimode Processes , 2015 .

[27]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[28]  Shuyuan Zhang,et al.  Bidirectional Recurrent Neural Network-Based Chemical Process Fault Diagnosis , 2019, Industrial & Engineering Chemistry Research.

[29]  Xuefeng Yan,et al.  Fault Diagnosis in Chemical Process Based on Self-organizing Map Integrated with Fisher Discriminant Analysis , 2013 .

[30]  Rajagopalan Srinivasan,et al.  Multivariate Temporal Data Analysis Using Self-Organizing Maps. 1. Training Methodology for Effective Visualization of Multistate Operations , 2008 .

[31]  Alireza Behroozsarand,et al.  Multiobjective optimization of reactive distillation with thermal coupling using non-dominated sorting genetic algorithm-II , 2011 .

[32]  Jun Li,et al.  Design and control of different pressure thermally coupled reactive distillation for synthesis of isoamyl acetate , 2019, Chemical Engineering and Processing - Process Intensification.

[33]  Xigang Yuan,et al.  Simulation based approach to optimal design of dividing wall column using random search method , 2014, Comput. Chem. Eng..

[34]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[35]  Jinsong Zhao,et al.  A new unsupervised data mining method based on the stacked autoencoder for chemical process fault diagnosis , 2020, Comput. Chem. Eng..

[36]  Jose A. Romagnoli,et al.  A Deep Learning Approach for Process Data Visualization Using t-Distributed Stochastic Neighbor Embedding , 2019, Industrial & Engineering Chemistry Research.

[37]  Na Yu,et al.  Design and control of a heat pump assisted azeotropic dividing wall column for EDA/water separation , 2017 .

[38]  Wang Cheng-xi.  Study on Hydrolysis of Methyl Formate into Formic Acid in a Catalytic Distillation Column , 2006 .

[39]  In-Beum Lee,et al.  Fault identification for process monitoring using kernel principal component analysis , 2005 .

[40]  Syed Ali Ammar Taqvi,et al.  Multiple Fault Diagnosis in Distillation Column Using Multikernel Support Vector Machine , 2018, Industrial & Engineering Chemistry Research.

[41]  Xuefeng Yan,et al.  Mutual Information–Dynamic Stacked Sparse Autoencoders for Fault Detection , 2019, Industrial & Engineering Chemistry Research.

[42]  Dipesh S. Patle,et al.  Plantwide Control of the Formic Acid Production Process Using an Integrated Framework of Simulation and Heuristics , 2018, Industrial & Engineering Chemistry Research.

[43]  Rui Li,et al.  Design and control of entrainer-assisted reactive distillation for N-propyl propionate production , 2017, Comput. Chem. Eng..

[44]  Jinsong Zhao,et al.  An Online Fault Diagnosis Strategy for Full Operating Cycles of Chemical Processes , 2014 .

[45]  Kus Hidajat,et al.  Design, Optimization, and Retrofit of the Formic Acid Process II: Reactive Distillation and Reactive Dividing-Wall Column Retrofits , 2018, Industrial & Engineering Chemistry Research.

[46]  Zhi-Huan Song,et al.  A novel fault diagnosis system using pattern classification on kernel FDA subspace , 2011, Expert Syst. Appl..

[47]  Biao Huang,et al.  GMM and optimal principal components-based Bayesian method for multimode fault diagnosis , 2016, Comput. Chem. Eng..

[48]  Hongbo Shi,et al.  Hidden Markov Model-Based Fault Detection Approach for a Multimode Process , 2016 .

[49]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[50]  Jinsong Zhao,et al.  Fault Diagnosis of Chemical Processes Using Artificial Immune System with Vaccine Transplant , 2016 .

[51]  Claudia Gutiérrez-Antonio,et al.  Reactive Thermally Coupled Distillation Sequences: Pareto Front , 2011 .

[52]  Chunjie Yang,et al.  Multimode Process Monitoring Approach Based on Moving Window Hidden Markov Model , 2018 .

[53]  Jingzheng Ren,et al.  Optimization and control of energy saving side-stream extractive distillation with heat integration for separating ethyl acetate-ethanol azeotrope , 2020 .

[54]  Jicong Fan,et al.  Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis , 2014, Inf. Sci..

[55]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[56]  Feng Qian,et al.  High dimension feature extraction based visualized SOM fault diagnosis method and its application in p-xylene oxidation process , 2015 .

[57]  Yingwei Zhang,et al.  Fault Detection and Diagnosis of Nonlinear Processes Using Improved Kernel Independent Component Analysis (KICA) and Support Vector Machine (SVM) , 2008 .

[58]  Jin Hyun Park,et al.  Process monitoring using a Gaussian mixture model via principal component analysis and discriminant analysis , 2004, Comput. Chem. Eng..

[59]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[60]  Jinsong Zhao,et al.  Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System , 2011 .

[61]  Faisal Khan,et al.  A Bibliometric Review and Analysis of Data-Driven Fault Detection and Diagnosis Methods for Process Systems , 2018, Industrial & Engineering Chemistry Research.

[62]  Luis Puigjaner,et al.  Performance assessment of a novel fault diagnosis system based on support vector machines , 2009, Comput. Chem. Eng..

[63]  A. A. Kiss,et al.  Reactive Distillation: Stepping Up to the Next Level of Process Intensification , 2018, Industrial & Engineering Chemistry Research.