摘要
在“双碳”目标下,电热协同在推动能源梯级利用,提高能源利用率中发挥着重要作用,及时识别并排除系统中电热设备运行异常,有利于保障电热协同系统安全稳定运行。但电热设备运行特性差异较大,导致电热设备健康度实时监测过程存在故障诊断率低、诊断方法鲁棒性差等问题,为此提出一种针对电热协同系统的多分支动态联合故障诊断方法。首先,分析了电热协同故障诊断的候选特征量;然后,研究了分支结果的特征重构与动态加权策略,提出多分支动态联合诊断模型;最后,算例分析结果表明,所提算法在电热协同故障诊断中有效提高了系统设备的故障检测能力,准确率达到了98.2%,且具有较好的鲁棒性,有效支撑了电热协同系统的稳定运行。
Under the background of"double carbon"goal,electric-thermal collaboration plays an important role in promoting energy stepwise utilization and improving energy efficiency.Timely identification and elimination of abnormal operation of electric-thermal equipment in the system is conducive to ensuring the safe and stable operation of the electric-thermal collaboration system.However,due to the large difference in operating characteristics of electric-thermal equipment,Problems such as low fault diagnosis rate and poor robustness of diagnosis method exist in the real-time health monitoring process of electric-thermal equipment.Therefore,this paper proposes a data-driven multi-branch dynamic combination anomaly diagnosis method based on electric-thermal collaboration.Firstly analyzes the candidate feature quantity of electric-thermal collaborative fault diagnosis,then studies the feature reconstruction and dynamic weighting strategy of the branch results,proposes a multi-branch dynamic combination diagnosis model.Finally the proposed algorithm can effectively improve the fault detection ability of the system equipment in the electric-thermal collaborative fault diagnosis,the accuracy rate is 98.2%,and it has good robustness,and effectively supports the stable operation of the electricthermal collaborative system.
作者
李彬
贺富龙
王枫桥
李启明
吴丹
田世明
徐玉婷
LI Bin;HE Fulong;WANG Fengqiao;LI Qiming;WU Dan;TIAN Shiming;XU Yuting(North China Electric Power University,Beijing 100096,China;State Grid Shanghai Electric Power Company,Shanghai 201799,China;China Electric Power Research Institute Co.,Ltd.,Beijing 100192,China)
出处
《供用电》
北大核心
2025年第7期78-85,共8页
Distribution & Utilization
基金
国家电网有限公司科技项目(5400-202355237A-1-1-ZN)。
关键词
电热协同系统
多分支算法
动态联合
故障诊断
鲁棒性
electric-thermal collaborative system
multi-branch algorithm
dynamic joint
fault diagnosis
robustness
