摘要
针对核极限学习机(Kernel Extreme Learning Machine,KELM)用于光伏阵列故障诊断时准确率不高的不足,提出了一种基于TGBA(Tent Mapping and Gaussian Perturbation Strategy Optimize Bat Algorithm)算法优化核极限学习机的光伏阵列故障诊断方法(TGBA-KELM)。首先,建立光伏阵列故障仿真模型,提取光伏阵列故障特征参数;其次,引入Tent映射和高斯扰动策略对蝙蝠算法(Bat Algorithm,BA)进行改进,增加种群多样性,提高了算法的收敛速度和全局寻优能力;再次,利用改进后的蝙蝠算法优化KELM的正则化系数和核函数参数,建立最优的故障诊断模型;最后,采用光伏阵列硬件实验平台收集的故障数据验证了TGBA-KELM算法的准确性和有效性,并与ELM(Extreme Learning Machine,ELM)、KELM、BA-KELM、TGBA-ELM、BP(back prop-agation)算法对比,实验结果表明,TGBA-KELM具有更高的故障诊断准确率,可用于光伏阵列故障诊断。
Aiming at the low accuracy of kernel extreme learning machine(KELM)in photovoltaic array fault diagnosis,a photovoltaic array fault diagnosis method based on TGBA algorithm to optimize kernel extreme learning machine(TGBA-KELM)was proposed.Firstly,the photovoltaic array fault simulation model was established to extract the photovoltaic array fault characteristic parameters;Secondly,introduced tent mapping and gaussian perturbation strategy to improve the bat algorithm(BA),increased the population diversity,and improved the convergence speed and global optimization ability of the algorithm;Thirdly,the regularization coefficient and kernel function parameter of KELM were optimized by using the improved bat algorithm to establish the optimal fault diagnosis model;Finally,the accuracy and effectiveness of TGBA-KELM algorithm were verified by the fault data collected by the photovoltaic array hardware experimental platform,and compared with extreme learning machine(ELM),KELM,BA-KELM,TGBA-ELM and back propagation(BP)algorithm.The experimental results show that TGBA-KELM has higher fault diagnosis accuracy and can be used for photovoltaic array fault diagnosis.
作者
余玲珍
覃涛
龙道银
王霄
杨靖
YU Lingzhen;QIN Tao;LONG Daoyin;WANG Xiao;YANG Jing(Electrical Engineering College,Guizhou University,Guiyang 550025,China;China Power Construction Group Guizhou Engineering Co.,Ltd,Guiyang 550025,China;Guizhou Provincial Key Laboratory of Internet and Intelligent Manufacturing,Guiyang 550025,China)
出处
《激光杂志》
CAS
北大核心
2021年第12期140-148,共9页
Laser Journal
基金
国家自然科学基金(No.61861007,61640014)
贵州省工业攻关项目(黔科合支撑[2019]2152)
贵州省科技基金(黔科合基础[2020]1Y266)
贵州省教育厅创新群体项目(黔教合KY字[2021]012)。
