Research and prospect of early warning and diagnosis technology for ORC power generation system process

doi:10.11949/0438-1157.20241356

Abstract

Abstract:

Organic Rankine cycle (ORC), as an advanced thermal energy conversion technology, has attracted much attention due to its wide application in the fields of recovering low-grade thermal energy, geothermal energy, solar energy, etc. With the development of automation and artificial intelligence technology in recent years, ORC systems have gradually realized the transformation of whole process automation and intelligence, but the research on the early warning and diagnosis of ORC system process is seriously insufficient. In this context, the paper first introduces the representation method and characteristics of process time series data. Secondly, the application of modeling technology based on analytical models, knowledge-driven, and data-driven in early warning and diagnosis is discussed. Finally, the challenges faced by the application of current technology in the process of ORC systems in the four levels of data, model, system and application are analyzed, and the future research directions are put forward. It aims to promote the technological progress and industrial application of ORC systems in the industrial field, and provide theoretical basis and technical support for the realization of a safer, more efficient and intelligent energy conversion systems.

Key words: process system, process control, organic Rankine cycle, early warning diagnosis, neural network

摘要：

有机朗肯循环（organic Rankine cycle，ORC）作为一种先进的热能转换技术，因其在回收低品位热能、地热能、太阳能等领域的广泛应用而备受关注。近年来，随着自动化与人工智能技术的发展，ORC系统逐渐实现了全流程自动化和智能化的系统转型，但针对ORC系统工艺过程预警诊断的研究严重不足。在这一背景下，首先介绍了工艺时序数据的表示方法和特性；其次，探讨了基于解析模型、知识驱动与数据驱动的建模技术在预警诊断中的应用；最后，分析了当前技术应用于ORC系统工艺过程在数据、模型、系统和应用四个层面所面临的挑战，并提出了未来研究方向。旨在促进ORC系统在工业领域的技术进步和工业应用，为实现更安全、高效和智能的能源转换系统提供理论基础和技术支持。

关键词: 过程系统, 过程控制, 有机朗肯循环, 预警诊断, 神经网络

CLC Number:

TP 273

Jinjiang WANG, Zhenjie LU, Weizheng AN, Fengyun YANG, Xiaogang QIN. Research and prospect of early warning and diagnosis technology for ORC power generation system process[J]. CIESC Journal, 2025, 76(7): 3137-3152.

王金江, 鲁振杰, 安维峥, 杨风允, 秦小刚. ORC发电系统工艺过程预警诊断技术研究与展望[J]. 化工学报, 2025, 76(7): 3137-3152.

Figures/Tables 5

References 88

[1]	赵龙成. 中国能源绿色发展成为全球能源转型引擎[J]. 生态经济, 2024, 40(11): 9-12.
	Zhao L C. China's green energy development has become the engine of global energy transformation[J]. Ecological Economy, 2024, 40(11): 9-12.
[2]	王汝金, 张秀平, 贾磊, 等. 有机朗肯循环技术在低品位余热发电系统中的应用[J]. 电力需求侧管理, 2011, 13(5): 25-28.
	Wang R J, Zhang X P, Jia L, et al. Application of organic Rankine cycletechnology on power generation system utilizing low-grade waste heat[J]. Power Demand Side Management, 2011, 13(5): 25-28.
[3]	郭丛, 杜小泽, 杨立军, 等. 地热源非共沸工质有机朗肯循环发电性能分析[J]. 中国电机工程学报, 2014, 34(32): 5701-5708.
	Guo C, Du X Z, Yang L J, et al. Performance of organic Rankine cycle using zeotropic working fluids for geothermal utilization[J]. Proceedings of the CSEE, 2014, 34(32): 5701-5708.
[4]	毛静雯, 徐斌, 胡宜康, 等. 太阳能有机朗肯循环研究与应用综述[J]. 低温与超导, 2020, 48(6): 77-83.
	Mao J W, Xu B, Hu Y K, et al. Summary of research and application of solar organic Rankine cycle[J]. Cryogenics & Superconductivity, 2020, 48(6): 77-83.
[5]	Ajaj Y, Ali A B M, Kumar A, et al. Innovative biomass waste heat utilization for green hydrogen production: a comparative and optimization study of steam and organic Rankine cycles[J]. Process Safety and Environmental Protection, 2024, 190: 148-174.
[6]	杨先, 李洪斌. 有机朗肯循环发电技术的原理及应用[J]. 大众科技, 2020, 22(9): 61-63.
	Yang X, Li H B. Principle and application organic Rankine cycle power generation technology[J]. Popular Science & Technology, 2020, 22(9): 61-63.
[7]	Yin S, Ding S X, Xie X C, et al. A review on basic data-driven approaches for industrial process monitoring[J]. IEEE Transactions on Industrial Electronics, 2014, 61(11): 6418-6428.
[8]	任磊, 贾子翟, 赖李媛君, 等. 数据驱动的工业智能: 现状与展望[J]. 计算机集成制造系统, 2022, 28(7): 1913-1939.
	Ren L, Jia Z D, Lai L Y J, et al. Data-driven industrial intelligence: current status and future directions[J]. Computer Integrated Manufacturing Systems, 2022, 28(7): 1913-1939.
[9]	赵春晖, 陈旭. 从分解视角出发: 基于多元统计方法的工业时序建模与过程监测综述[J]. 控制与决策, 2024, 39(11): 3521-3546.
	Zhao C H, Chen X. From the decomposition perspective: a survey of industrial time series modeling and process monitoring based on multivariate statistical methods[J]. Control and Decision, 2024, 39(11): 3521-3546.
[10]	Yu W K, Zhao C H. Low-rank characteristic and temporal correlation analytics for incipient industrial fault detection with missing data[J]. IEEE Transactions on Industrial Informatics, 2021, 17(9): 6337-6346.
[11]	徐瑞东, 侯志鹏. 基于相关因子的工业过程数据缺失值填补研究[J]. 自动化博览, 2021, 38(12): 64-67.
	Xu R D, Hou Z P. Research on missing value filling of industrial process data based on correlation factors[J]. Automation Panorama, 2021, 38(12): 64-67.
[12]	Chen X, Zhao C H. Linear and nonlinear hierarchical multivariate time delay analytics for dynamic modeling and process monitoring[J]. Journal of Process Control, 2021, 107: 83-93.
[13]	Zhao C H, Sun H, Tian F. Total variable decomposition based on sparse cointegration analysis for distributed monitoring of nonstationary industrial processes[J]. IEEE Transactions on Control Systems Technology, 2020, 28(4): 1542-1549.
[14]	孙琳. 基于机器学习的故障诊断与预测方法研究[J]. 流体测量与控制, 2024, 5(5): 31-34.
	Sun L. Research on fault diagnosis and prediction methods based on machine learning[J]. Fluid Measurement & Control, 2024, 5(5): 31-34.
[15]	Silva E A, Bradaschia F, Cavalcanti M C, et al. Parameter estimation method to improve the accuracy of photovoltaic electrical model[J]. IEEE Journal of Photovoltaics, 2016, 6(1): 278-285.
[16]	Yu D. Fault diagnosis for a hydraulic drive system using a parameter-estimation method[J]. Control Engineering Practice, 1997, 5(9): 1283-1291.
[17]	Chen T P, Li P, Sun L, et al. A distributed multi-area power system state estimation method based on generalized loss function[J]. Measurement Science and Technology, 2023, 34(11): 115010.
[18]	Bagla G, Patwardhan S C, Valluru J. Intelligent state estimation for fault tolerant integrated frequent RTO and adaptive nonlinear MPC[J]. Journal of Process Control, 2023, 131: 103092.
[19]	Luo L Z, Wang J, Zhou S Y, et al. A broad learning-based state estimation method for power system[J]. Energy Reports, 2022, 8: 1227-1235.
[20]	Xu D X, Hu A Y, Han X L, et al. A nonlinear system state estimation method based on adaptive fusion of multiple kernel functions[J]. Complexity, 2021, 2021(1): 5124841.
[21]	Saravanakumar R, Manimozhi M, Kothari D P, et al. Simulation of sensor fault diagnosis for wind turbine generators DFIG and PMSM using Kalman filter[J]. Energy Procedia, 2014, 54: 494-505.
[22]	Tadić P, Željko Ð. Particle filtering for sensor fault diagnosis and identification in nonlinear plants[J]. Journal of Process Control, 2014, 24(4): 401-409.
[23]	Jonsson G R, Lalot S, Palsson O P, et al. Use of extended Kalman filtering in detecting fouling in heat exchangers[J]. International Journal of Heat and Mass Transfer, 2007, 50(13/14): 2643-2655.
[24]	Li C C, Gao M, Sheng L. Parity space based intermittent fault diagnosis for linear time-varying systems over sensor networks[C]//2022 China Automation Congress (CAC). IEEE: 2022: 1634-1639.
[25]	Zhang P, Ding S X. Brief paper: disturbance decoupling in fault detection of linear periodic systems[J]. Automatica (Journal of IFAC), 2007, 43(8): 1410-1417.
[26]	Tong Z, Li W, Zhang B, et al. Bearing fault diagnosis under variable working conditions based on domain adaptation using feature transfer learning[J]. IEEE Access, 2018, 6: 76187-76197.
[27]	Gao G Q, Zhou L C. Design of fault diagnosis expert system for electronic control system of adaptive optics based on fault tree[C]//Proceedings of the 3rd International Conference on Mechatronics and Industrial Informatics. Zhuhai, China: Atlantis Press, 2015: 18-22.
[28]	El-Shal S M, Morris A S. A fuzzy expert system for fault detection in statistical process control of industrial processes[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2000, 30(2): 281-289.
[29]	李先锋, 颉潭成, 徐彦伟, 等. 轴承故障智能诊断专家系统的研究[J]. 制造业自动化, 2020, 42(1): 7-9, 14.
	Li X F, Xie T C, Xu Y W, et al. The research on the intelligent diagnosis expert system for bearing fault[J]. Manufacturing Automation, 2020, 42(1): 7-9, 14.
[30]	郭沁, 赵结昂. 内燃叉车故障诊断专家系统研究[J]. 特种设备安全技术, 2020(2): 49-52.
	Guo Q, Zhao J A. Research on fault diagnosis expert system for diesel forklift truck[J]. Safety Technology of Special Equipment, 2020(2): 49-52.
[31]	Wu J D, Liu C H. An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network[J]. Expert Systems with Applications, 2009, 36(3): 4278-4286.
[32]	Delrot S, Guerra T M, Dambrine M, et al. Fouling detection in a heat exchanger by observer of Takagi-Sugeno type for systems with unknown polynomial inputs[J]. Engineering Applications of Artificial Intelligence, 2012, 25(8): 1558-1566.
[33]	Duan R X, Zhou H L. A new fault diagnosis method based on fault tree and Bayesian networks[J]. Energy Procedia, 2012, 17: 1376-1382.
[34]	田嘉雯, 王树强. 基于故障树分析法的化工屏蔽泵可靠性分析[J]. 机械工程师, 2024(12): 19-22, 26.
	Tian J W, Wang S Q. Reliability analysis of chemical shielded pump based on fault tree analysis method[J]. Mechanical Engineer, 2024(12): 19-22, 26.
[35]	姜英, 王政, 秦艳, 等. 基于复杂网络的化工过程层次符号有向图模型建立及关键节点识别[J]. 化工进展, 2018, 37(2): 444-451.
	Jiang Y, Wang Z, Qin Y, et al. AHP-SDG model establishment and key node identification of chemical process system based on complex network[J]. Chemical Industry and Engineering Progress, 2018, 37(2): 444-451.
[36]	张贝克, 许欣, 高东, 等. 基于定性趋势与符号有向图的模型校核方法[J]. 化工学报, 2013, 64(12): 4536-4543.
	Zhang B K, Xu X, Gao D, et al. Model verification based on qualitative trend and SDG[J]. CIESC Journal, 2013, 64(12): 4536-4543.
[37]	Gonzalez-Jimenez D, del-Olmo J, Poza J, et al. Data-driven fault diagnosis for electric drives: a review[J]. Sensors, 2021, 21(12): 4024.
[38]	郭金玉, 刘玉超, 李元. 加权局部近邻标准化PCA的工业过程故障检测[J]. 沈阳化工大学学报, 2021, 35(3): 265-274.
	Guo J Y, Liu Y C, Li Y. Fault detection of industrial process based on weighed local neighborhood standardization PCA[J]. Journal of Shenyang University of Chemical Technology, 2021, 35(3): 265-274.
[39]	Wen X Q, Xu Z A. Wind turbine fault diagnosis based on ReliefF-PCA and DNN[J]. Expert Systems with Applications, 2021, 178: 115016.
[40]	Tao E P, Shen W H, Liu T L, et al. Fault diagnosis based on PCA for sensors of laboratorial wastewater treatment process[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 128: 49-55.
[41]	程莹. ORC系统的状态监测与故障诊断[D]. 北京: 华北电力大学, 2014.
	Cheng Y. Condition monitoring and fault diagnosis of ORC system[D]. Beijing: North China Electric Power University, 2014.
[42]	郭金玉, 王霞, 李元. 基于ICA和LOF的故障检测[J]. 沈阳大学学报(自然科学版), 2022, 34(3): 197-204.
	Guo J Y, Wang X, Li Y. Fault detection based on LOF of augmented matrix in independent component space[J]. Journal of Shenyang University (Natural Science), 2022, 34(3): 197-204.
[43]	郭金玉, 李涛, 李元. 基于DW-ICA-SVM的工业过程故障检测算法[J]. 河北科技大学学报, 2021, 42(4): 369-379.
	Guo J Y, Li T, Li Y. Fault detection algorithm of industrial process based on DW-ICA-SVM[J]. Journal of Hebei University of Science and Technology, 2021, 42(4): 369-379.
[44]	Xie Y, Zhu Y, Lu Z J. Fault diagnosis of large-scale industrial processes using the multi-block probabilistic kernel partial least squares method[J]. Journal of Intelligent & Fuzzy Systems, 44(2): 2881-2894.
[45]	孔祥玉, 陈雅琳, 罗家宇, 等. 基于偏最小二乘的多特性复杂过程监测方法[J]. 华南理工大学学报(自然科学版), 2022, 50(6): 100-110.
	Kong X Y, Chen Y L, Luo J Y, et al. Multi-feature complex process monitoring method based on partial least squares[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(6): 100-110.
[46]	丁学成, 刘强, 詹志强. 重构与趋势分析相结合的工业过程异常原因诊断[J]. 控制工程, 2022, 29(2): 207-213.
	Ding X C, Liu Q, Zhan Z Q. Reconstruction and trend analysis based abnormality cause diagnosis of industrial processes[J]. Control Engineering of China, 2022, 29(2): 207-213.
[47]	Yin Z Y, Hou J. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes[J]. Neurocomputing, 2016, 174: 643-650.
[48]	李鑫妮, 王亚君, 许晓婷. 基于AOA优化SVM的工业过程故障检测[J]. 现代化工, 2024, 44(S2): 343-347, 354.
	Li X N, Wang Y J, Xu X T. Industrial process fault detection based on AOA optimized SVM[J]. Modern Chemical Industry, 2024, 44(S2): 343-347, 354.
[49]	郭金玉, 李涛, 李元. 基于多模型SVM的多模态过程故障检测[J]. 沈阳化工大学学报, 2023, 37(6): 533-541.
	Guo J Y, Li T, Li Y. Fault detection of multi-modal process based on multi-model SVM[J]. Journal of Shenyang University of Chemical Technology, 2023, 37(6): 533-541.
[50]	孟佳. 基于数据驱动的低温余热发电系统的状态监测和故障诊断[D]. 北京: 华北电力大学, 2015.
	Meng J. Condition monitoring and fault diagnosis of low temperature waste heat power generation system based on data driving[D]. Beijing: North China Electric Power University, 2015.
[51]	汤大可. 基于人工免疫系统的石油化工过程故障诊断应用研究[J]. 天然气与石油, 2022, 40(2): 131-135.
	Tang D K. Research on application of artificial immune system on petrochemical process fault diagnosis[J]. Natural Gas and Oil, 2022, 40(2): 131-135.
[52]	Shu Y D, Zhao J S. Fault diagnosis of chemical processes using artificial immune system with vaccine transplant[J]. Industrial & Engineering Chemistry Research, 2016, 55(12): 3360-3371.
[53]	郭小萍, 滕佳岐, 李元. 基于EEMD-kNN的工业过程微小故障检测[J]. 计算机应用与软件, 2023, 40(4): 36-40, 53.
	Guo X P, Teng J Q, Li Y. Incipient fault detection for industry process based on EEMD-kNN[J]. Computer Applications and Software, 2023, 40(4): 36-40, 53.
[54]	张成, 李秀玉, 逄玉俊, 等. 基于GMM的马氏距离kNN故障检测方法研究[J]. 测控技术, 2014, 33(9): 13-17.
	Zhang C, Li X Y, Pang Y J, et al. Mahalanobis distance kNN fault detection method based on Gaussian mixture model[J]. Measurement & Control Technology, 2014, 33(9): 13-17.
[55]	杜建, 张磊, 李继庚, 等. 基于GMM-MD组合算法的过程工业故障预测模型[J]. 中国造纸学报, 2022, 37(2): 81-86.
	Du J, Zhang L, Li J G, et al. Fault prediction model for process industry based on GMM-MD combinational algorithm[J]. Transactions of China Pulp and Paper, 2022, 37(2): 81-86.
[56]	Rajakarunakaran S, Venkumar P, Devaraj D, et al. Artificial neural network approach for fault detection in rotary system[J]. Applied Soft Computing, 2008, 8(1): 740-748.
[57]	胡宇鹏, 郭丽杰, 张子龙, 等. 基于优化卷积神经网络的化工过程故障诊断方法[J]. 燕山大学学报, 2024, 48(6): 550-560.
	Hu Y P, Guo L J, Zhang Z L, et al. Fault diagnosis method based on optimized convolutional neural network for chemical process[J]. Journal of Yanshan University, 2024, 48(6): 550-560.
[58]	Xie Y, Lu Z J. Novel deep-learning method based on LSA-transformer for fault detection and its implementation in penicillin fermentation process[J]. Measurement, 2024, 235: 114871.
[59]	赵丰, 易辉. 基于改进LLE-LSTM的化工过程故障诊断[J]. 中国仪器仪表, 2023(12): 46-51.
	Zhao F, Yi H. Fault diagnosis of chemical process based on improved LLE-LSTM[J]. China Instrumentation, 2023(12): 46-51.
[60]	李启泽, 徐琛, 陶洪峰, 等. 基于优化堆叠自编码器的故障诊断方法[J]. 控制工程, 2024, 31(2): 231-237.
	Li Q Z, Xu C, Tao H F, et al. Fault diagnosis method based on optimized stacked autoencoder[J]. Control Engineering of China, 2024, 31(2): 231-237.
[61]	Jia F, Lei Y G, Lin J, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing, 2016, 72: 303-315.
[62]	刘昕宇, 韩莹, 陈维荣, 等. 基于改进SSA-DBN的质子交换膜燃料电池水故障智能分类方法[J]. 电力自动化设备, 2024, 44(4): 18-24.
	Liu X Y, Han Y, Chen W R, et al. Intelligent classification method of water faults for proton exchange membrane fuel cell based on improved SSA-DBN[J]. Electric Power Automation Equipment, 2024, 44(4): 18-24.
[63]	Almasoudi F M. Enhancing power grid resilience through real-time fault detection and remediation using advanced hybrid machine learning models[J]. Sustainability, 2023, 15(10): 8348.
[64]	任东哲, 邵帅, 王剑峰, 等. 数据-模型混合驱动的无人机电池性能评估方法[J]. 科技与创新, 2024(21): 35-37.
	Ren D Z, Shao S, Wang J F, et al. Evaluation method of battery performance of UAV driven by data-model hybrid[J]. Science and Technology & Innovation, 2024(21): 35-37.
[65]	江昌旭, 周龙灿, 庄鹏威, 等. 基于数据-模型混合驱动方法的多类型移动应急资源优化调度策略[J]. 电网技术, DOI:10.13335/j.1000-3673.pst.2024.1516 .
	Jiang C X, Zhou L C, Zhuang P W, et al. Multi type mobile emergency resource optimization scheduling strategy based on data model hybrid driving method[J]. Power System Technology, DOI:10.13335/j.1000-3673.pst.2024.1516 .
[66]	Zhou D H, Zhu Z W, Li C, et al. A novel model-data fusion method for capacity and battery remaining useful life prediction[J]. Journal of Energy Storage, 2024, 98: 112929.
[67]	Wang J J, Li Y L, Gao R X, et al. Hybrid physics-based and data-driven models for smart manufacturing: modelling, simulation, and explainability[J]. Journal of Manufacturing Systems, 2022, 63: 381-391.
[68]	Xiang Y Y, Pan B S, Luo L P. A new model updating strategy with physics-based and data-driven models[J]. Structural and Multidisciplinary Optimization, 2021, 64(1): 163-176.
[69]	Candès E J, Li X D, Ma Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3): 1-37.
[70]	Pan Y J, Yang C J, An R Q, et al. Robust principal component pursuit for fault detection in a blast furnace process[J]. Industrial & Engineering Chemistry Research, 2018, 57(1): 283-291.
[71]	胡智尧, 于淼. 分布差异感知的联邦学习方法[J]. 信息工程大学学报, 2024, 25(4): 404-410.
	Hu Z Y, Yu M. Distribution divergence-aware federated learning[J]. Journal of Information Engineering University, 2024, 25(4): 404-410.
[72]	吴涛, 马驰. 基于数据对齐的深度ANN机械寿命预测[J]. 机械设计与制造, 2023(2): 63-70.
	Wu T, Ma C. Mechanical life prediction of deep ANN based on data alignment[J]. Machinery Design & Manufacture, 2023(2): 63-70.
[73]	闫栋, 杨富斌, 张红光, 等. 有机朗肯循环机器学习模型关键参数集识别[J]. 哈尔滨工程大学学报, 2023, 44(8): 1368-1374.
	Yan D, Yang F B, Zhang H G, et al. Key parameter set identification of the machine learning model of the organic Rankine cycle[J]. Journal of Harbin Engineering University, 2023, 44(8): 1368-1374.
[74]	侯中兰, 魏新利, 马新灵, 等. 循环水流量对ORC余热发电系统性能影响的试验分析[J]. 化工学报, 2019, 70(9): 3283-3290.
	Hou Z L, Wei X L, Ma X L, et al. Experimental analysis of circulating water flow rate on performance of ORC waste heat power generation system[J]. CIESC Journal, 2019, 70(9): 3283-3290.
[75]	谢承辉, 王星, 肖发厚, 等. 轴承故障模式与故障诊断方法综述[J]. 计算机测量与控制, 2025,33(4):1-9.
	Xie C H, Wang X, Xiao F H, et al. Overview of bearing fault modes and fault diagnosis methods[J]. Computer Measurement & Control, 2025,33(4):1-9.
[76]	索晋贤, 张丽萍, 闫盛, 等. 可解释的深度知识追踪方法综述[J]. 计算机应用, DOI:10.11772/j.issn.1001-9081.2024070970 .
	Suo J X, Zhang L P, Yan S, et al. Review of interpretable deep knowledge tracking methods[J]. Journal of Computer Application, DOI:10.11772/j.issn.1001-9081.2024070970 .
[77]	廖勇, 韩小金, 刘金林, 等. 可解释性人工智能研究进展[J]. 计算机工程, DOI:10.19678/j.issn.1000-3428.0069925 .
	Liao Y, Han X J, Liu J L, et al. Research progress of interpretable artificial intelligence[J]. Computer Engineering, DOI:10.19678/j.issn.1000-3428.0069925 .
[78]	司念文, 张文林, 屈丹, 等. 卷积神经网络表征可视化研究综述[J]. 自动化学报, 2022, 48(8): 1890-1920.
	Si N W, Zhang W L, Qu D, et al. Representation visualization of convolutional neural networks: a survey[J]. Acta Automatica Sinica, 2022, 48(8): 1890-1920.
[79]	王廷轩, 刘韬, 王振亚, 等. 知识蒸馏与迁移学习的轴承故障诊断应用研究[J]. 计算机工程与应用, 2023, 59(13): 289-297.
	Wang T X, Liu T, Wang Z Y, et al. Applied research on bearing fault diagnosis based on knowledge distillation and transfer learning[J]. Computer Engineering and Applications, 2023, 59(13): 289-297.
[80]	刘兵, 杨娟, 汪荣贵, 等. 结合记忆与迁移学习的小样本学习[J]. 计算机工程与应用, 2022, 58(19): 242-249.
	Liu B, Yang J, Wang R G, et al. Memory-based transfer learning for few-shot learning[J]. Computer Engineering and Applications, 2022, 58(19): 242-249.
[81]	方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法[J]. 计算机科学, 2022, 49(8): 70-77.
	Fang Y Q, Zhang Z K, Ge J W. Cross-domain recommendation algorithm based on self-attention mechanism and transfer learning[J]. Computer Science, 2022, 49(8): 70-77.
[82]	刘乔寿, 皮胜文, 原炜锡. 基于Z-Score动态压缩的高效联邦学习算法[J]. 计算机应用研究, 2024, 41(7): 2093-2097.
	Liu Q S, Pi S W, Yuan W X. High efficient federated learning algorithm based on Z-Score dynamic compression[J]. Application Research of Computers, 2024, 41(7): 2093-2097.
[83]	曾浩, 母王强, 蒋阳, 等. 模型参数自适应的低复杂度ATPM-VSIMM算法[J]. 通信学报, 2023, 44(9): 25-35.
	Zeng H, Mu W Q, Jiang Y, et al. Low-complexity ATPM-VSIMM algorithm with adaptive model parameters[J]. Journal on Communications, 2023, 44(9): 25-35.
[84]	谭帅, 王一帆, 姜庆超, 等. 基于不同故障传播路径差异化的故障诊断方法[J]. 自动化学报, 2024, 51(1):161-173.
	Tan S, Wang Y F, Jiang Q C, et al. Fault diagnosis method based on different fault propagation path differentiation[J]. Acta Automatica Sinica, 2024, 51(1):161-173.
[85]	马亮, 彭开香, 董洁. 工业过程故障根源诊断与传播路径识别技术综述[J]. 自动化学报, 2022, 48(7): 1650-1663.
	Ma L, Peng K X, Dong J. Review of root cause diagnosis and propagation path identification techniques for faults in industrial processes[J]. Acta Automatica Sinica, 2022, 48(7): 1650-1663.
[86]	张嘉伟, 顾文波, 韩涛, 等. 有机朗肯循环耦合二氧化碳捕集系统运行仿真与性能评估[J/OL]. 洁净煤技术, .
	Zhang J W, Gu W B, Han T, et al. Operation simulation and performance evaluation of organic Rankine cycle coupled CO₂ capture system[J/OL]. Clean Coal Technology, .
[87]	赵鹏, 洪悦. 基于改进动态核主元分析算法的化工过程故障检测[J]. 化工自动化及仪表, 2024, 51(3): 403-409.
	Zhao P, Hong Y. Fault detection of chemical process based on improved dynamic kernel principal component analysis algorithm[J]. Control and Instruments in Chemical Industry, 2024, 51(3): 403-409.
[88]	余辉, 梁镇涛, 鄢宇晨. 多来源多模态数据融合与集成研究进展[J]. 情报理论与实践, 2020, 43(11): 169-178.
	Yu H, Liang Z T, Yan Y C. Review on multi-source and multi-modal data fusion and integration[J]. Information Studies (Theory & Application), 2020, 43(11): 169-178.

算法类别		算法名称	算法原理
基于解析模型的方法		参数估计法	通过分析过程参数的变化和监测模型来对生产过程进行监测
		等价空间法	通过构造残差生成器，利用等价关系来检测线性系统中的故障
		状态估计法	利用系统的定量模型和测量信号来构建可测变量，实时估计系统的内部状态，直接反映系统的运行状态
基于知识驱动的方法		符号有向图	通过有效地表达复杂系统中各个变量之间的相互关系，包括正向和负向的影响，以及灵活的推理方式和推理算法，判断故障传播的路径，给出故障发生的详细解释
		故障树	通过系统地分析从顶层故障到底层原因的逻辑关系，识别和预防潜在的故障，并在故障发生时快速定位和解决问题
		专家系统	通过构建包含领域专家知识和经验的规则库，利用推理机制模拟人类专家的决策过程
基于数据驱动的方法	统计学习	主成分分析	通过分析数据在某些主成分方向上的偏离程度来识别异常
		核主成分分析	一种基于核函数的主成分分析方法，用来处理非线性可分的数据
		偏最小二乘法	通过提取主成分简化数据结构，用简化后的数据建立与目标变量的回归模型，利用模型监控数据中的异常变化，通过统计量识别不符合模型预期的数据点
		核偏最小二乘法	通过核函数将原始数据映射到高维特征空间，在新的特征空间中应用PLS方法进行建模和预测
		独立成分分析	通过假设观测到的多维信号由若干个统计独立的非高斯分布的源信号线性混合而成来识别和分离异常成分
		定性趋势分析	通过识别和分析数据中的定性趋势变化，及时发现和预警潜在异常
	机器学习	支持向量机	通过找到一个最优超平面，使得不同类别的样本点之间的间隔最大化
		K近邻	通过测量不同特征值之间的距离进行分类
		高斯混合模型	通过建立数据的概率模型，估计数据的概率密度，并根据数据点的概率密度值判断异常
		人工神经网络	自动从大量历史数据中学习和提取特征，识别出正常行为和异常行为之间的模式和规律，无须预先定义具体的规则
		人工免疫系统	模仿生物免疫系统的机制，包括识别、反应、记忆和适应等，识别和处理异常
	深度学习	深度信念网络	由多个受限Boltzmann机堆叠而成的深层生成模型，每一层都能学习到数据的高层特征表示，捕捉数据的复杂结构和模式
		自编码器	基于重构误差识别异常数据点
		降噪自编码器	通过从噪声数据中学习并提取有用特征，利用重构误差识别异常数据，同时具有无监督学习和特征提取的能力
		深度神经网络	自动从大量历史数据中学习和提取特征，识别出正常行为和异常行为之间的模式和规律
		卷积神经网络	通过卷积层和池化层自动学习数据的特征，尤其是图像或时间序列数据中的局部特征和模式，提取与异常相关的特征
		循环神经网络	通过学习训练阶段的时间序列模式，将这些模式与测试阶段的数据进行比较，标记异常点

算法类别		算法名称	算法原理
基于解析模型的方法		参数估计法	通过分析过程参数的变化和监测模型来对生产过程进行监测
		等价空间法	通过构造残差生成器，利用等价关系来检测线性系统中的故障
		状态估计法	利用系统的定量模型和测量信号来构建可测变量，实时估计系统的内部状态，直接反映系统的运行状态
基于知识驱动的方法		符号有向图	通过有效地表达复杂系统中各个变量之间的相互关系，包括正向和负向的影响，以及灵活的推理方式和推理算法，判断故障传播的路径，给出故障发生的详细解释
		故障树	通过系统地分析从顶层故障到底层原因的逻辑关系，识别和预防潜在的故障，并在故障发生时快速定位和解决问题
		专家系统	通过构建包含领域专家知识和经验的规则库，利用推理机制模拟人类专家的决策过程
基于数据驱动的方法	统计学习	主成分分析	通过分析数据在某些主成分方向上的偏离程度来识别异常
		核主成分分析	一种基于核函数的主成分分析方法，用来处理非线性可分的数据
		偏最小二乘法	通过提取主成分简化数据结构，用简化后的数据建立与目标变量的回归模型，利用模型监控数据中的异常变化，通过统计量识别不符合模型预期的数据点
		核偏最小二乘法	通过核函数将原始数据映射到高维特征空间，在新的特征空间中应用PLS方法进行建模和预测
		独立成分分析	通过假设观测到的多维信号由若干个统计独立的非高斯分布的源信号线性混合而成来识别和分离异常成分
		定性趋势分析	通过识别和分析数据中的定性趋势变化，及时发现和预警潜在异常
	机器学习	支持向量机	通过找到一个最优超平面，使得不同类别的样本点之间的间隔最大化
		K近邻	通过测量不同特征值之间的距离进行分类
		高斯混合模型	通过建立数据的概率模型，估计数据的概率密度，并根据数据点的概率密度值判断异常
		人工神经网络	自动从大量历史数据中学习和提取特征，识别出正常行为和异常行为之间的模式和规律，无须预先定义具体的规则
		人工免疫系统	模仿生物免疫系统的机制，包括识别、反应、记忆和适应等，识别和处理异常
	深度学习	深度信念网络	由多个受限Boltzmann机堆叠而成的深层生成模型，每一层都能学习到数据的高层特征表示，捕捉数据的复杂结构和模式
		自编码器	基于重构误差识别异常数据点
		降噪自编码器	通过从噪声数据中学习并提取有用特征，利用重构误差识别异常数据，同时具有无监督学习和特征提取的能力
		深度神经网络	自动从大量历史数据中学习和提取特征，识别出正常行为和异常行为之间的模式和规律
		卷积神经网络	通过卷积层和池化层自动学习数据的特征，尤其是图像或时间序列数据中的局部特征和模式，提取与异常相关的特征
		循环神经网络	通过学习训练阶段的时间序列模式，将这些模式与测试阶段的数据进行比较，标记异常点