基于ISFO-KELM的SF_(6)电气设备故障组分CO_(2)浓度反演模型  

A CO_(2)Concentration Inversion Model for SF_(6)Electrical Equipment Fault Components Based on ISFO-KELM

作　　者：黄杰 张英 张靖[1] 王明伟 HUANG Jie;ZHANG Ying;ZHANG Jing;WANG Mingwei(College of Electrical Engineering,Guizhou University,Guiyang 550025,China;Electric Power Research Institute,Guizhou Power Grid Co.,Ltd.,Guiyang 550002,China;Bijie Power Supply Bureau,Guizhou Power Grid Co.,Ltd.,Bijie 551700,China)

机构地区：[1]贵州大学电气工程学院,贵州贵阳550025 [2]贵州电网有限责任公司电力科学研究院,贵州贵阳550002 [3]贵州电网有限责任公司毕节供电局,贵州毕节551700

出　　处：《电子科技》2024年第11期62-69,共8页Electronic Science and Technology

基　　金：国家自然科学基金(51867005);贵州省科技支撑项目(黔科合支撑2021一般365);南网科技项目(GZKJXM20210348)。

摘　　要：SF_(6)电气设备内部的分解组分可以通过可调谐吸收光谱技术进行检测,其中CO_(2)浓度反映了设备内部的绝缘缺陷情况。因此,通过准确测量CO_(2)浓度可以及时发现设备潜在的绝缘故障。为克服传统最小二乘法浓度反演模型稳定性较差的问题,文中基于改进的旗鱼优化算法(Improved Sailed Fish Optimizer,ISFO)与核极限学习机(Kernel Based Extreme Learning Machine,KELM)建立了ISFO-KELM气体浓度反演模型。利用多策略初始化方法、Levy随机步长、柯西变异和自适应t分布变异等技术提升了旗鱼优化算法寻优能力和跳出局部最优解能力。实验结果表明,该模型具有高精度和鲁棒性,并且在稳定性和泛化能力方面优于最小二乘法、极限学习机、反向传播(Back Propagation,BP)神经网络等传统方法,对评估SF_(6)电气设备运行状态具有重要意义。The decomposition components inside SF_(6)electrical equipment can be detected by tunable absorption spectroscopy technique,in which the concentration of CO_(2)reflects the insulation defect situation inside the equipment.Therefore,potential insulation faults of the equipment can be found in time by measuring the CO_(2)concentration accurately.To overcome the problem of poor stability of traditional least squares concentration inversion model,ISFO-KELM gas concentration inversion model based on ISFO(Improved Sailed Fish Optimizer)and KELM(Kernel Based Extreme Learning Machine)is established in this study.The optimization ability and the ability to jump out of local optimal solution of ISFO are improved by using multi-strategy initialization method,Levy random step length,Cauchy mutation and adaptive t-distribution mutation techniques.The experimental results show that this model has high accuracy and robustness,and is superior to traditional methods such as least squares method,extreme learning machine,BP(Back Propagation)neural network in stability and generalization ability,which has important significance for evaluating the operation state of SF_(6)electrical equipment.

关 键 词：可调谐吸收光谱技术 SF_(6)电气设备 CO_(2)浓度反演 降噪 拟合 变分模态分解 核极限学习机 旗鱼优化器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TM213[自动化与计算机技术—控制科学与工程]