Fault Detection and Diagnosis for Plasticizing Process of Single-Base Gun Propellant Using Mutual Information Weighted MPCA under Limited Batch Samples Modelling

Aiming at the lack of reliable gradual fault detection and abnormal condition alarm and evaluation ability in the plasticizing process of single-base gun propellant, a fault detection and diagnosis method based on normalized mutual information weighted multiway principal component analysis (NMI-WMPCA) under limited batch samples modelling was proposed. In this method, the differences of coupling correlation among multi-dimensional process variables and the coupling characteristics of linear and nonlinear relationships in the process are considered. NMI-WMPCA utilizes the generalization ability of a multi-model to establish an accurate fault detection model in limited batch samples, and adopts fault diagnosis methods based on a multi-model SPE statistic contribution plot to identify the fault source. The experimental results demonstrate that the proposed method is effective, which can realize the rapid detection and diagnosis of multiple faults in the plasticizing process.

[1]  Michael Baldea,et al.  A geometric method for batch data visualization, process monitoring and fault detection , 2017, Journal of Process Control.

[2]  Murat Kulahci,et al.  Real-time fault detection and diagnosis using sparse principal component analysis , 2017, Journal of Process Control.

[3]  Xuefeng Yan,et al.  Relevant and independent multi-block approach for plant-wide process and quality-related monitoring based on KPCA and SVDD. , 2018, ISA transactions.

[4]  Javier M. Moguerza,et al.  A review of machine learning kernel methods in statistical process monitoring , 2020, Comput. Ind. Eng..

[5]  Davide Astolfi,et al.  Perspectives on SCADA Data Analysis Methods for Multivariate Wind Turbine Power Curve Modeling , 2021 .

[6]  J. Janiszewski,et al.  On Influence of Mechanical Properties of Gun Propellants on Their Ballistic Characteristics Determined in Closed Vessel Tests , 2020, Materials.

[7]  Xiaoyu Fang,et al.  Industrial process monitoring based on Fisher discriminant global-local preserving projection , 2019, Journal of Process Control.

[8]  Chunhui Zhao.  Phase analysis and statistical modeling with limited batches for multimode and multiphase process monitoring , 2014 .

[9]  S. Joe Qin,et al.  Analysis and generalization of fault diagnosis methods for process monitoring , 2011 .

[11]  Hongbo Shi,et al.  A Novel Mutual Information and Partial Least Squares Approach for Quality-Related and Quality-Unrelated Fault Detection , 2021 .

[12]  Michel José Anzanello,et al.  Fault detection in batch processes through variable selection integrated to multiway principal component analysis , 2019 .

[13]  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.

[14]  Chunhui Zhao,et al.  Robust Monitoring and Fault Isolation of Nonlinear Industrial Processes Using Denoising Autoencoder and Elastic Net , 2020, IEEE Transactions on Control Systems Technology.

[15]  Zukui Li,et al.  Change point and fault detection using Kantorovich Distance , 2019, Journal of Process Control.

[16]  Chunhui Zhao,et al.  Subspace decomposition and critical phase selection based cumulative quality analysis for multiphase batch processes , 2017 .

[17]  H. Herrera-Hernández,et al.  A Bayesian Approach for Estimating the Thinning Corrosion Rate of Steel Heat Exchanger in Hydrodesulfurization Plants , 2018, Advances in Materials Science and Engineering.

[18]  J. Corriou,et al.  Sub-period division strategies combined with multiway principle component analysis for fault diagnosis on sequence batch reactor of wastewater treatment process in paper mill , 2021 .

[19]  Dazhi Wang,et al.  Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning , 2020, Sensors.

[20]  Special Issue on “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes” , 2021, Processes.

[21]  Yajun Wang,et al.  Online monitoring method for multiple operating batch processes based on local collection standardization and multi‐model dynamic PCA , 2016 .

[22]  Fuli Wang,et al.  A Novel Strategy of the Data Characteristics Test for Selecting a Process Monitoring Method Automatically , 2016 .

[23]  Furong Gao,et al.  110th Anniversary: An Overview on Learning-Based Model Predictive Control for Batch Processes , 2019, Industrial & Engineering Chemistry Research.

[24]  Ke Wang,et al.  Learning Domain-Independent Deep Representations by Mutual Information Minimization , 2019, Comput. Intell. Neurosci..

[25]  Svatopluk Zeman,et al.  Sensitivity and Performance of Energetic Materials , 2016 .

[26]  Zhiwei Gao,et al.  An Overview on Fault Diagnosis, Prognosis and Resilient Control for Wind Turbine Systems , 2021, Processes.

[27]  Shu-Kai S. Fan,et al.  A Review on Fault Detection and Process Diagnostics in Industrial Processes , 2020, Processes.

[28]  V. Venkatasubramanian.  The promise of artificial intelligence in chemical engineering: Is it here, finally? , 2018, AIChE Journal.

[29]  Jie Yu,et al.  Maximized mutual information based non-Gaussian subspace projection method for quality relevant process monitoring and fault detection , 2013, 52nd IEEE Conference on Decision and Control.

[30]  Biao Huang,et al.  Performance-Driven Distributed PCA Process Monitoring Based on Fault-Relevant Variable Selection and Bayesian Inference , 2016, IEEE Transactions on Industrial Electronics.

[31]  Biao Huang,et al.  Review and Perspectives of Data-Driven Distributed Monitoring for Industrial Plant-Wide Processes , 2019, Industrial & Engineering Chemistry Research.

[32]  Chudong Tong,et al.  Fault detection and diagnosis of dynamic processes using weighted dynamic decentralized PCA approach , 2017 .

[33]  S. Joe Qin,et al.  Comparative study on monitoring schemes for non-Gaussian distributed processes , 2016, Journal of Process Control.

[34]  K. Gao,et al.  Effect of DGTN Content on Mechanical and Thermal Properties of Modified Single‐Base Gun Propellant Containing NQ and RDX , 2019 .

[35]  P. Gujrati.  Jensen inequality and the second law , 2019, 1901.11176.

[36]  Xuefeng Yan,et al.  Plant-wide process monitoring based on mutual information-multiblock principal component analysis. , 2014, ISA transactions.

[37]  Geert Gins,et al.  Industrial Process Monitoring in the Big Data/Industry 4.0 Era: from Detection, to Diagnosis, to Prognosis , 2017 .

[38]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[39]  Yi Cao,et al.  A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring , 2019, Processes.

[40]  Hanyuan Zhang,et al.  Batch Process Monitoring Based on Multiway Global Preserving Kernel Slow Feature Analysis , 2017, IEEE Access.

[41]  S. Joe Qin,et al.  A novel dynamic PCA algorithm for dynamic data modeling and process monitoring , 2017 .

[42]  Zhi-huan Song,et al.  Distributed PCA Model for Plant-Wide Process Monitoring , 2013 .

[43]  Akilu Yunusa-Kaltungo,et al.  Integrated Fault Detection Framework for Classifying Rotating Machine Faults Using Frequency Domain Data Fusion and Artificial Neural Networks , 2018, Machines.

[44]  Xuefeng Yan,et al.  Quality Relevant and Independent Two Block Monitoring Based on Mutual Information and KPCA , 2017, IEEE Transactions on Industrial Electronics.