面向系统层级的复杂工业过程全息故障诊断
|
摘要
复杂工业过程具有长流程、系统层级多、故障潜在分布空间范围较广的特点,是当前故障诊断领域的热门研究方向。首先,对主流故障诊断技术进行了分类和概述;其次,采用定量与定性相结合思路,提出了面向系统层级的复杂工业过程全息故障诊断框架,为复杂工业全流程的过程监测提供一整套技术和解决方案。相比于目前的故障诊断方法,该框架不仅包括故障检测和故障辨识,还包括故障根源诊断、故障传播路径识别、故障的定量诊断与评估,可有效解决复杂工业过程系统的综合故障诊断问题,实用性强,能够有效地减少或避免故障发生、保证产品的质量、提高企业的生产效率与生产安全;最后对故障诊断技术的发展趋势和亟待解决的问题进行了展望。
Complex industrial process has long processes, many system levels and a wide range of potential fault distribution space, which is a hotspot in the current fault diagnosis field. Firstly, the current mainstream faultdiagnosis methods in process monitoring are classified and summarized. Secondly, this study adopts thecombination of quantitative and qualitative, which is based on data and knowledge. A system-level holographicfault diagnosis framework for complex industrial process is proposed, which provides a complete set of techniquesand solutions for process monitoring in complex industrial plant-wide process. Compared with current faultdiagnosis methods, the framework not only includes fault detection and fault identification, but also includes rootcause diagnosis, fault propagation path identification, quantitative fault diagnosis and evaluation. It is quite apractical method for process systems, which can effectively reduce or avoid the fault occurrence, guarantee thequality of the product, and improve the production efficiency and safety of enterprises. Finally, the development trend of fault diagnosis technology and problems to be solved are prospected.
Complex industrial process has long processes, many system levels and a wide range of potential fault distribution space, which is a hotspot in the current fault diagnosis field. Firstly, the current mainstream faultdiagnosis methods in process monitoring are classified and summarized. Secondly, this study adopts thecombination of quantitative and qualitative, which is based on data and knowledge. A system-level holographicfault diagnosis framework for complex industrial process is proposed, which provides a complete set of techniquesand solutions for process monitoring in complex industrial plant-wide process. Compared with current faultdiagnosis methods, the framework not only includes fault detection and fault identification, but also includes rootcause diagnosis, fault propagation path identification, quantitative fault diagnosis and evaluation. It is quite apractical method for process systems, which can effectively reduce or avoid the fault occurrence, guarantee thequality of the product, and improve the production efficiency and safety of enterprises. Finally, the development trend of fault diagnosis technology and problems to be solved are prospected.
引文
[1]葛志强.复杂工业过程统计监测方法研究[D].杭州:浙江大学,2009.Ge Z Q. Statistical process monitoring methods for complex processes[D]. Hangzhou:Zhejiang University, 2009.
[2] Beard R V. Failure accommodation in linear systems through selfreorganization[D]. Massachusetts:MIT, 1971.
[3] Venkatasubramanian V, Rengaswamy R, Yin K. A review of process fault detection and diagnosis(II):Quantitative models and search strategies[J]. Computers and Chemical Engineering, 2003,27:313-326.
[4] Venkatasubramanian V, Rengaswamy R, Yin K. A review of process fault detection and diagnosis(III):Process history based methods[J]. Computers and Chemical Engineering, 2003, 27:327-346.
[5]周东华,席裕庚,张钟俊.故障检测与诊断技术[J].控制理论与应用, 1991, 8(1):1-10.Zhou D H, Xi Y G, Zhang Z J. A survey on fault detection and diagnostics techniques[J]. Control theory and applications, 1991, 8(1):1-10.
[6] MacGregor J F, Jaeckle C, Kiparissides C, et al. Process monitoring and diagnosis by multiblock PLS methods[J]. AIChE Journal, 1994, 40(5):826-838.
[7] Westerhuis J A, Kourti T, MacGregor J F. Analysis of multiblock and hierarchical PCA and PLS models[J]. Journal of Chemometrics, 1998, 12(5):301-321.
[8] Qin S J, Valle S, Piovoso M J. On unifying multiblock analysis with application to decentralized process monitoring[J]. Journal of Chemometrics, 2001, 15(9):715-742.
[9] Yuan T, Qin S J. Root cause diagnosis of plant-wide oscillations using Granger causality[J]. Journal of Process Control, 2014, 24(2):450-459.
[10] Ge Z Q, Song Z H. Distributed PCA model for plant-wide process monitoring[J]. Industrial&Engineering Chemistry Research,2013, 52(5):1947-1957.
[11] Ge Z Q, Zhang M G, Song Z H. Nonlinear process monitoring based on linear subspace and Bayesian inference[J]. Journal of Process Control, 2010, 20(5):676-688.
[12] Zhu J L, Ge Z Q, Song Z H, et al. Large-scale plant-wide process modeling and hierarchical monitoring:a distributed Bayesian network approach[J]. Journal of Process Control, 2018, 65:91-106.
[13] Huang J P, Yan X F. Relevant and independent multi-block approach for plant-wide process and quality-related monitoring based on KPCA and SVDD[J]. ISA transactions, 2018, 73:257-267.
[14] Peng K X, Zhang K, You B, et al. Quality-related prediction and monitoring of multi-mode processes using multiple PLS with application to an industrial hot strip mill[J]. Neurocomputing,2015, 168(10):1094-1103.
[15] Peng K X, Zhang K, You B, et al. A quality-based nonlinear fault diagnosis framework focusing on industrial multimode batch processes[J]. IEEE Trans. Ind. Electron., 2016, 63(4):2615-2624.
[16]李伟.复杂系统的智能故障诊断技术现状及其发展趋势[J].计算机仿真, 2004, 21(10):4-7.Li W. Advance of intelligent fault diagnosis for complex system and its present situation[J]. Computer Simulation, 2004, 21(10):4-7.
[17] Lee J M, Qin S J, Lee I B. Fault detection and diagnosis of multivariate process based on modified independent component analysis[J]. AIChE Journal, 2006, 52:3501-3514.
[18] Komulainen T, Sourander M, Jamsa-Jounela S L. An online application of dynamic PLS to a dearomatization process[J].Computer and Chemical Engineering, 2004, 28(12):2611-2619.
[19] Pierre C. Independent component analysis. A new concept?[J].Signal Processing, 1994, 36:287-314.
[20] Huang B. Bayesian methods for control loop monitoring and diagnosis[J]. Journal of Process Control, 2008, 18(9):829-838.
[21] Qin S J. Statistical process monitoring:basics and beyond[J].Journal of Chemometrics, 2003, 17(8/9):480-502.
[22] Ypma A, Tax D M J, Duin R P W. Robust machine fault detection with independent component analysis and support vector data description[C]//Neural Networks for Signal Processing Ix, 1999.Proceedings of the 1999 IEEE Signal Processing Society Workshop. Madison, WI, USA:IEEE, 2002:67-76.
[23] Yoon S, MacGregor J F. Fault diagnosis with multivariate statistical models(I):Using steady state fault signatures[J].Journal of Process Control, 2001, 11(4):387-400.
[24] Li G, Qin S J, Yuan T. Data-driven root cause diagnosis of faults in process industries[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 159:1-11.
[25] MacGregor J F, Kourti T. Statistical process control of multivariate processes[J]. Control Engineering Practice, 1995, 3(3):403-414
[26]姜周曙,翁翔彬,王剑,等.反渗透海水淡化系统“脱盐率与产水量下降”故障树分析[J].化工学报, 2014, 65(6):2172-2178.Jiang Z S, Weng X B, Wang J, et al. Fault tree analysis on decreases of desalination rate and permeate flow rate of seawater reverse osmosis desalination system[J]. CIESC Journal, 2014, 65(6):2172-2178.
[27] Tadao M. Petri nets:properties, analysis and applications[J].Proceeding of the IEEE, 1989, 77(4):541-580.
[28] Granger C W J. Investigating causal relations by econometric models and cross-spectral methods[J]. Econometrica, 1969, 37(3):424-438.
[29] Frank E, Hall M. A simple approach to ordinal classification[C]//European Conference on Machine Learning. London, UK:Springer-Verlag, 2001:145-156.
[30] Cao-Van K, Baets B D. Growing decision trees in an ordinal setting[J]. International Journal of Intelligent Systems, 2003, 18(7):733-750.
[31] Hu Q H, Guo M Z, Yu D R, et al. Information entropy for ordinal classification[J]. Science China Information Sciences, 2010, 53(6):1188-1200.
[32] Ye C, Kilgour D M, Hipel K W. Using a benchmark in case-based multiple-criteria ranking[J]. IEEE Transactions on Systems, Man,and Cybernetics-Part A:Systems and Humans, 2009, 39(2):358-368.
[33]梁晴晴,韩华,崔晓钰,等.基于主元分析-概率神经网络的制冷系统故障诊断[J].化工学报, 2016, 67(3):1022-1031.Liang Q Q, Han H, Cui X Y, et al. Fault diagnosis for refrigeration system based on PCA-PNN[J]. CIESC Journal, 2016, 67(3):1022-1031.
[34]黄景德,崔山宝,王兴贵.正向推理型故障模糊预测系统的知识表示与推理[J].计算机工程, 2001, 27(2):78-79.Huang J D, Cui S B, Wang X G, et al. Knowledge expression and reasoning of fault fuzzy forecast system based on forewards reasoning[J]. Computer Engineering, 2001, 27(2):78-79.
[35]刘建国,姜秀民,王辉,等.流化床内石英砂的热破碎及其灰色预测模型[J].化工学报, 2008, 59(2):328-334.Liu J G, Jiang X M, Wang H, et al. Thermal fragmentation of quartzite particles in fluidized bed and gray forecasting model[J].Journal of Chemical Industry and Engineering(China), 2008, 59(2):328-334.
[36]李琨,韩莹,佘东生,等.基于IFOA-KELM-MEA模型的游梁式抽油机采油系统井下工况的短期预测[J].化工学报, 2017,68(1):188-198.Li K, Han Y, She D S, et al. IFOA-KELM-MEA model based transient prediction on down-hole working conditions of beam pumping units[J]. CIESC Journal, 2017, 68(1):188-198.
[37]赵旭.基于统计学方法的过程监控与质量控制研究[D].上海:上海交通大学, 2006.Zhao X. Research on process monitoring and quality control based on statistical methods[D]. Shanghai:Shanghai Jiao Tong University, 2006.
[2] Beard R V. Failure accommodation in linear systems through selfreorganization[D]. Massachusetts:MIT, 1971.
[3] Venkatasubramanian V, Rengaswamy R, Yin K. A review of process fault detection and diagnosis(II):Quantitative models and search strategies[J]. Computers and Chemical Engineering, 2003,27:313-326.
[4] Venkatasubramanian V, Rengaswamy R, Yin K. A review of process fault detection and diagnosis(III):Process history based methods[J]. Computers and Chemical Engineering, 2003, 27:327-346.
[5]周东华,席裕庚,张钟俊.故障检测与诊断技术[J].控制理论与应用, 1991, 8(1):1-10.Zhou D H, Xi Y G, Zhang Z J. A survey on fault detection and diagnostics techniques[J]. Control theory and applications, 1991, 8(1):1-10.
[6] MacGregor J F, Jaeckle C, Kiparissides C, et al. Process monitoring and diagnosis by multiblock PLS methods[J]. AIChE Journal, 1994, 40(5):826-838.
[7] Westerhuis J A, Kourti T, MacGregor J F. Analysis of multiblock and hierarchical PCA and PLS models[J]. Journal of Chemometrics, 1998, 12(5):301-321.
[8] Qin S J, Valle S, Piovoso M J. On unifying multiblock analysis with application to decentralized process monitoring[J]. Journal of Chemometrics, 2001, 15(9):715-742.
[9] Yuan T, Qin S J. Root cause diagnosis of plant-wide oscillations using Granger causality[J]. Journal of Process Control, 2014, 24(2):450-459.
[10] Ge Z Q, Song Z H. Distributed PCA model for plant-wide process monitoring[J]. Industrial&Engineering Chemistry Research,2013, 52(5):1947-1957.
[11] Ge Z Q, Zhang M G, Song Z H. Nonlinear process monitoring based on linear subspace and Bayesian inference[J]. Journal of Process Control, 2010, 20(5):676-688.
[12] Zhu J L, Ge Z Q, Song Z H, et al. Large-scale plant-wide process modeling and hierarchical monitoring:a distributed Bayesian network approach[J]. Journal of Process Control, 2018, 65:91-106.
[13] Huang J P, Yan X F. Relevant and independent multi-block approach for plant-wide process and quality-related monitoring based on KPCA and SVDD[J]. ISA transactions, 2018, 73:257-267.
[14] Peng K X, Zhang K, You B, et al. Quality-related prediction and monitoring of multi-mode processes using multiple PLS with application to an industrial hot strip mill[J]. Neurocomputing,2015, 168(10):1094-1103.
[15] Peng K X, Zhang K, You B, et al. A quality-based nonlinear fault diagnosis framework focusing on industrial multimode batch processes[J]. IEEE Trans. Ind. Electron., 2016, 63(4):2615-2624.
[16]李伟.复杂系统的智能故障诊断技术现状及其发展趋势[J].计算机仿真, 2004, 21(10):4-7.Li W. Advance of intelligent fault diagnosis for complex system and its present situation[J]. Computer Simulation, 2004, 21(10):4-7.
[17] Lee J M, Qin S J, Lee I B. Fault detection and diagnosis of multivariate process based on modified independent component analysis[J]. AIChE Journal, 2006, 52:3501-3514.
[18] Komulainen T, Sourander M, Jamsa-Jounela S L. An online application of dynamic PLS to a dearomatization process[J].Computer and Chemical Engineering, 2004, 28(12):2611-2619.
[19] Pierre C. Independent component analysis. A new concept?[J].Signal Processing, 1994, 36:287-314.
[20] Huang B. Bayesian methods for control loop monitoring and diagnosis[J]. Journal of Process Control, 2008, 18(9):829-838.
[21] Qin S J. Statistical process monitoring:basics and beyond[J].Journal of Chemometrics, 2003, 17(8/9):480-502.
[22] Ypma A, Tax D M J, Duin R P W. Robust machine fault detection with independent component analysis and support vector data description[C]//Neural Networks for Signal Processing Ix, 1999.Proceedings of the 1999 IEEE Signal Processing Society Workshop. Madison, WI, USA:IEEE, 2002:67-76.
[23] Yoon S, MacGregor J F. Fault diagnosis with multivariate statistical models(I):Using steady state fault signatures[J].Journal of Process Control, 2001, 11(4):387-400.
[24] Li G, Qin S J, Yuan T. Data-driven root cause diagnosis of faults in process industries[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 159:1-11.
[25] MacGregor J F, Kourti T. Statistical process control of multivariate processes[J]. Control Engineering Practice, 1995, 3(3):403-414
[26]姜周曙,翁翔彬,王剑,等.反渗透海水淡化系统“脱盐率与产水量下降”故障树分析[J].化工学报, 2014, 65(6):2172-2178.Jiang Z S, Weng X B, Wang J, et al. Fault tree analysis on decreases of desalination rate and permeate flow rate of seawater reverse osmosis desalination system[J]. CIESC Journal, 2014, 65(6):2172-2178.
[27] Tadao M. Petri nets:properties, analysis and applications[J].Proceeding of the IEEE, 1989, 77(4):541-580.
[28] Granger C W J. Investigating causal relations by econometric models and cross-spectral methods[J]. Econometrica, 1969, 37(3):424-438.
[29] Frank E, Hall M. A simple approach to ordinal classification[C]//European Conference on Machine Learning. London, UK:Springer-Verlag, 2001:145-156.
[30] Cao-Van K, Baets B D. Growing decision trees in an ordinal setting[J]. International Journal of Intelligent Systems, 2003, 18(7):733-750.
[31] Hu Q H, Guo M Z, Yu D R, et al. Information entropy for ordinal classification[J]. Science China Information Sciences, 2010, 53(6):1188-1200.
[32] Ye C, Kilgour D M, Hipel K W. Using a benchmark in case-based multiple-criteria ranking[J]. IEEE Transactions on Systems, Man,and Cybernetics-Part A:Systems and Humans, 2009, 39(2):358-368.
[33]梁晴晴,韩华,崔晓钰,等.基于主元分析-概率神经网络的制冷系统故障诊断[J].化工学报, 2016, 67(3):1022-1031.Liang Q Q, Han H, Cui X Y, et al. Fault diagnosis for refrigeration system based on PCA-PNN[J]. CIESC Journal, 2016, 67(3):1022-1031.
[34]黄景德,崔山宝,王兴贵.正向推理型故障模糊预测系统的知识表示与推理[J].计算机工程, 2001, 27(2):78-79.Huang J D, Cui S B, Wang X G, et al. Knowledge expression and reasoning of fault fuzzy forecast system based on forewards reasoning[J]. Computer Engineering, 2001, 27(2):78-79.
[35]刘建国,姜秀民,王辉,等.流化床内石英砂的热破碎及其灰色预测模型[J].化工学报, 2008, 59(2):328-334.Liu J G, Jiang X M, Wang H, et al. Thermal fragmentation of quartzite particles in fluidized bed and gray forecasting model[J].Journal of Chemical Industry and Engineering(China), 2008, 59(2):328-334.
[36]李琨,韩莹,佘东生,等.基于IFOA-KELM-MEA模型的游梁式抽油机采油系统井下工况的短期预测[J].化工学报, 2017,68(1):188-198.Li K, Han Y, She D S, et al. IFOA-KELM-MEA model based transient prediction on down-hole working conditions of beam pumping units[J]. CIESC Journal, 2017, 68(1):188-198.
[37]赵旭.基于统计学方法的过程监控与质量控制研究[D].上海:上海交通大学, 2006.Zhao X. Research on process monitoring and quality control based on statistical methods[D]. Shanghai:Shanghai Jiao Tong University, 2006.