Fault identification for quality monitoring of molten iron in blast furnace ironmaking based on KPLS with improved contribution rate

Abstract Blast furnace (BF) ironmaking is one of the most important production links in modern iron–steel making. The operation conditions of BF and the molten iron quality (MIQ) should be monitored and analyzed in real-time to realize high quality with low energy consumption. Aiming at the problems of strong nonlinearity and few fault samples in BF processes, a novel fault identification method for MIQ monitoring based on kernel partial least squares (KPLS) with improved contribution rate is proposed in this paper. First of all, a KPLS model is established with the actual historical data in order to detect the quality-related faults accurately. The T2 and SPE statistics are used to monitor the operation conditions of process from different aspects. Second, in view of the unclear physical meaning and complex computation of the existing fault identification methods based on KPLS with contribution rate, a scale factor vector is introduced into the new samples to calculate the T2 and SPE statistics, so as to construct the monitoring indicators functions. By performing Taylor approximation on these constructed functions near the scale factor with the value of 1, two new statistics are obtained from the absolute value of the first-order partial derivative representing the contribution rate of each variable. Finally, in order to further improve the effect of fault identification, the relative contribution rate of each variable is used to identify the final faulty variables. The tests of MIQ monitoring in BF ironmaking process using actual industrial data verify the validity and practicability of the proposed method.

[1]  Si-Zhao Joe Qin,et al.  Reconstruction-based contribution for process monitoring , 2009, Autom..

[2]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[3]  Tianyou Chai,et al.  Data-Driven Robust RVFLNs Modeling of a Blast Furnace Iron-Making Process Using Cauchy Distribution Weighted M-Estimation , 2017, IEEE Transactions on Industrial Electronics.

[4]  Qiang Liu,et al.  Comprehensive monitoring of nonlinear processes based on concurrent kernel projection to latent structures , 2016, IEEE Transactions on Automation Science and Engineering.

[5]  Alain Rakotomamonjy,et al.  Variable Selection Using SVM-based Criteria , 2003, J. Mach. Learn. Res..

[6]  Hong Wang,et al.  Data-Driven Nonlinear Subspace Modeling for Prediction and Control of Molten Iron Quality Indices in Blast Furnace Ironmaking , 2017, IEEE Transactions on Control Systems Technology.

[7]  A. J. Morris,et al.  Non-linear projection to latent structures revisited (the neural network PLS algorithm) , 1999 .

[8]  Zhiqiang Ge,et al.  Two-level PLS model for quality prediction of multiphase batch processes , 2014 .

[9]  Renquan Lu,et al.  Fault Identification of Nonlinear Processes , 2013 .

[10]  Jin Hyun Park,et al.  Fault detection and identification of nonlinear processes based on kernel PCA , 2005 .

[11]  Age K. Smilde,et al.  Generalized contribution plots in multivariate statistical process monitoring , 2000 .

[12]  In-Beum Lee,et al.  Multiblock PLS-based localized process diagnosis , 2005 .

[13]  Lars Renberg,et al.  Non‐linear modelling with a coupled neural network — PLS regression system , 1996 .

[14]  Weihua Gui,et al.  Temperature Measurement and Compensation Method of Blast Furnace Molten Iron Based on Infrared Computer Vision , 2019, IEEE Transactions on Instrumentation and Measurement.

[15]  Youxian Sun,et al.  Robust Principal Component Pursuit for Fault Detection in a Blast Furnace Process , 2018 .

[16]  Zhiqiang Ge,et al.  Distributed predictive modeling framework for prediction and diagnosis of key performance index in plant-wide processes , 2017 .

[17]  Youxian Sun,et al.  Subspace decomposition approach of fault deviations and its application to fault reconstruction , 2013, Proceedings of the 32nd Chinese Control Conference.

[18]  Roman Rosipal,et al.  Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space , 2002, J. Mach. Learn. Res..

[19]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[20]  Hao Ye,et al.  Fault Diagnosis for Blast Furnace Ironmaking Process Based on Two-stage Principal Component Analysis , 2014 .

[21]  Chunhui Zhao,et al.  A full‐condition monitoring method for nonstationary dynamic chemical processes with cointegration and slow feature analysis , 2018 .

[22]  Bo Zhou,et al.  Process monitoring of iron-making process in a blast furnace with PCA-based methods , 2016 .

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

[24]  Lina Yao,et al.  Design of new fault diagnosis and fault tolerant control scheme for non-Gaussian singular stochastic distribution systems , 2012, Autom..

[25]  Gang Li,et al.  Online Contribution Rate Based Fault Diagnosis for Nonlinear Industrial Processes , 2014 .

[26]  Heng Zhou,et al.  Hybrid-Model-Based Intelligent Optimization of Ironmaking Process , 2020, IEEE Transactions on Industrial Electronics.

[27]  Weihua Gui,et al.  Optimal control strategy of working condition transition for copper flash smelting process , 2016 .

[28]  Fuli Wang,et al.  Nonlinear process monitoring based on kernel dissimilarity analysis , 2009 .