魏淑娟,齐咏生,刘利强,李永亭,高学金

• 1:内蒙古工业大学电力学院
• 2:大规模储能技术教育部工程研究中心
• 3:内蒙古自治区高等学校智慧能源技术与装备工程研究中心
• 4:中石化西南油气分公司采气二厂

摘要(Abstract)：

针对复杂工业过程数据特征提取困难，且许多故障检测方法需要提前假设数据分布类型，故障检测泛化能力弱等问题，提出一种基于信息增益自适应特征选择（IGA）方法与增强Dempster-Shafer (D-S)证据理论的工业过程故障检测算法。首先，通过决策树计算得到信息增益，利用交叉验证设定k值，自适应选择特征个数，实现数据降维和特征提取；之后，引入三元统计量监测组实现线性故障检测，同时采用自编码器、One-class SVM方法进行非线性故障监测；最后，使用增强D-S证据理论，通过一种新的综合指标，对改进后的加权平均证据体进行融合，修正基本概率分配（BPA）参数获得融合结果，得到更为可靠的检测结果。通过冷水机组数据和田纳西-伊斯曼（Tennessee-Eastman,TE）过程数据进行验证，结果表明，IGA与增强D-S证据理论方法比单独的线性或非线性检测算法的准确率更高，鲁棒性更强，且使用场景不依赖于特定数据分布假设，适用范围灵活，可以有效应用于工业过程故障检测。

关键词(KeyWords)： 信息增益;特征提取;证据理论;故障检测;工业过程

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(62363029,62241309);; 内蒙古科技计划(2020GG0283,2021GG0164);; 内蒙古自然科学基金(2022MS06018,2021MS06018)

作者(Author): 魏淑娟,齐咏生,刘利强,李永亭,高学金

参考文献(References)：

• [1] SHANG L, YAN Z, LI J,et al. Canonical residual based incipient fault detection method for industrial process:2020 Chinese Control and Decision Conference(CCDC)[C]. Hefei:IEEE, 2020:987-992.
• [2]柴天佑．工业人工智能的发展方向[J]．数字经济，2021（增刊2）:38-40.CHAI T Y. The development of industrial artificial intelligence[J].Digital Economy, 2021(Suppl. 2):38-40.
• [3] ADUMENE S, ISLAM R, AMIN M T,et al. Advances in nuclear power system design and fault-based condition monitoring towards safety of nuclear-powered ships[J].Ocean Engineering, 2022, 251:111156.
• [4] LI J. Efficient global monitoring statistics for high-dimensional data[J].Quality and Reliability Engineering International, 2020,36(1):18-32.
• [5]王晓慧，王延江，邓晓刚，等．基于加权深度支持向量数据描述的工业过程故障检测[J]．化工学报，2021, 72(11):5707-5716.WANG X H, WANG Y J, DENG X G,et al. Industrial process fault detection using weighted deep support vector data description[J].CIESC Journal, 2021, 72(11):5707-5716.
• [6] PARK Y J, FAN S K S, HSU C Y. A review on fault detection and process diagnostics in industrial processes[J].Processes, 2020,8(9):1123.
• [7] ABID A, KHAN M T, IQBAL J. A review on fault detection and diagnosis techniques:Basics and beyond[J].Artificial Intelligence Review, 2021, 54(5):3639-3664.
• [8] HU H S, FENG D Z, YANG F. A promising nonlinear dimensionality reduction method:Kernel-based within class collaborative preserving discriminant projection[J].IEEE Signal Processing Letters, 2020, 27:2034-2038.
• [9] LIU Z, HAN H G, YANG H Y,et al. Knowledge-aided and data-driven fuzzy decision making for sludge bulking[J].IEEE Transactions on Fuzzy Systems, 2023, 31(4):1189-1201.
• [10] JIANG Q C, YAN X F, HUANG B. Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference[J].IEEE Transactions on Industrial Electronics, 2016, 63(1):377-386.
• [11] KANO M, TANAKA S, HASEBE S,et al. Combined multivariate statistical process control[J].IFAC Proceedings Volumes, 2004,37(1):281-286.
• [12] ZHANG Y W, AN J Y, ZHANG H L. Monitoring of time-varying processes using kernel independent component analysis[J].Chemical Engineering Science, 2013, 88:23-32.
• [13]祝志超，吴定会，岳远昌．基于监督核熵成分分析的发动机磨损故障诊断[J]．系统仿真学报，2022, 34(1):45-52.ZHU Z C, WU D H, YUE Y C. Engine wear fault diagnosis based on supervised kernel entropy component analysis[J].Journal of System Simulation, 2022, 34(1):45-52.
• [14] QI Y S, MENG X B, LU C X,et al. KECA similarity-based monitoring and diagnosis of faults in multi-phase batch processes[J].Entropy, 2019, 21(2):121.
• [15]邓明月，刘建昌，许鹏，等．基于KECA的非线性工业过程故障检测与诊断新方法[J]．化工学报，2020, 71(5):2151-2163.DENG M Y, LIU J C, XU P,et al. New fault detection and diagnosis strategy for nonlinear industrial process based on KECA[J].CIESC Journal, 2020, 71(5):2151-2163.
• [16] SHANG L L, QIU A B, XU P,et al. Canonical variate nonlinear principal component analysis for monitoring nonlinear dynamic processes[J].Journal of Chemical Engineering of Japan, 2022, 55(1):29-37.
• [17] CHAKOUR C, HARKAT M F, DJEGHABA M. Neuronal principal component analysis for nonlinear time-varying processes monitoring[J].IFAC-PapersOnLine, 2015, 48(21):1408-1413.
• [18]张祥，崔哲，董玉玺，等．基于VAE-DBN的故障分类方法在化工过程中的应用[J]．过程工程学报，2018, 18(3):590-594.ZHANG X, CUI Z, DONG Y X,et al. Application of fault classification method based on VAE-DBN in chemical process[J].Journal of Process Engineering, 2018, 18(3):590-594.
• [19] ZHENG S D, ZHAO J S. A new unsupervised data mining method based on the stacked autoencoder for chemical process fault diagnosis[J].Computers&Chemical Engineering, 2020, 135:106755.
• [20] LI J S, YAN X F. Process monitoring using principal component analysis and stacked autoencoder for linear and nonlinear coexisting industrial processes[J].Journal of the Taiwan Institute of Chemical Engineers, 2020, 112:322-329.
• [21] JIANG L, GE Z Q, SONG Z H. Semi-supervised fault classification based on dynamic Sparse Stacked auto-encoders model[J].Chemometrics and Intelligent Laboratory Systems, 2017, 168:72-83.
• [22]程换新，王建庆．改进深度置信网络对TE过程故障诊断研究[J]．电子测量技术，2019, 42(9):117-120.CHENG H X, WANG J Q. Improved DBN for TE process fault diagnosis[J].Electronic measurement technology, 2019, 42(9):117-120.
• [23] SHANNON C E. A mathematical theory of communication[J].The Bell System Technical Journal, 1948, 27(3):379-423.
• [24] LIU L S, ZHI Z, ZHANG H X,et al. Related entropy theories application in condition monitoring of rotating machineries[J].Entropy, 2019, 21(11):1061.
• [25] ELVIRA-ORTIZ D A, SAUCEDO-DORANTES J J, OSORNIO-RIOS R A,et al. An entropy-based condition monitoring strategy for the detection and classification of wear levels in gearboxes[J].Entropy, 2023, 25(3):424.
• [26] GERMáN-SALLóZ. Entropy indices based fault detection[J].Procedia Manufacturing, 2020, 46:549-554.
• [27] LI F, LIU X Q, SHANG L L,et al. Industrial process fault detection based on entropy score contribution analysis[J].IEEE Access,2022, 10:117646-117657.
• [28] SABIROV D S, SHEPELEVICH I S. Information entropy in chemistry:An overview[J].Entropy, 2021, 23(10):1240.
• [29] SHENKER O. Information vs. entropy vs. probability[J].European Journal for Philosophy of Science, 2020, 10(1):5-13.
• [30] KENT J T. Information gain and a general measure of correlation[J].Biometrika, 1983, 70(1):163-173.
• [31] OMUYA E O, OKEYO G O, KIMWELE M W. Feature selection for classification using principal component analysis and information gain[J].Expert Systems with Applications, 2021, 174:114765.
• [32] JENSSEN R, PRINCIPE J C, ERDOGMUS D,et al. The cauchy-schwarz divergence and parzen windowing:Connections to graph theory and mercer kernels[J].Journal of the Franklin Institute, 2006, 343(6):614-629.
• [33] LIU Z G, QIU G H, MERCIER G,et al. A transfer classification method for heterogeneous data based on evidence theory[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems, 2021, 51(8):5129-5141.
• [34] CHEN H T, CHAI Z, DOGRU O,et al. Data-driven designs of fault detection systems via neural network-aided learning[J].IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(10):5694-5705.
• [35]郭文强，李建望，黄梓轩，等．基于互信息-主成分分析-贝叶斯网络的化工过程故障诊断方法[J]．科学技术与工程，2023,23(21):9144-9150.GUO W Q, LI J W, HUANG Z X,et al. MPBN-based fault diagnosis method for chemical processes[J].Science Technology and Engineering, 2023, 23(21):9144-9150.
• [36] WEI Y Q, WENG Z X. Research on TE process fault diagnosis method based on DBN and dropout[J].The Canadian Journal of Chemical Engineering, 2020, 98(6):1293-1306.