基于多目标粒子群算法的柔性交直流混合配网变电站检修工时预测  

Maintenance Time Prediction of Flexible AC-DC Hybrid Distribution Substation Based on Multi-objective Particle Swarm Optimization Algorithm

作　　者：潘亮亮 PAN Liangliang(State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 750000,China)

机构地区：[1]国网宁夏电力有限公司,宁夏银川750000

出　　处：《微型电脑应用》2024年第6期189-192,共4页Microcomputer Applications

摘　　要：当多个变电站同时需要检修的情况下,受到多种因素限制,难以获取到准确的工时预测结果。为了合理安排工作班组,减少检修时间,设计一种基于多目标粒子群算法的柔性交直流混合配网变电站检修工时预测方法。以检修工时作为目标函数,检修过程中的时间段、检修互斥量、检修班组资源等作为约束条件建立柔性交直流混合配网变电站检修工时预测模型,设计多目标粒子群算法的系数寻优流程,完成变电站检修工时的预测。算例分析结果表明,该方法应用下的预测值与实际值之间标准曲线相关系数更接近1,平均绝对偏差和平均绝对百分比误差更小,预测偏差更低。A flexible AC/DC hybrid distribution substation maintenance man-hour prediction method based on multi-objective particle swarm optimization algorithm is designed to solve the problem that it is difficult to obtain accurate man-hour prediction results due to large multi factor constraints when multiple substations need maintenance at the same time.Taking the maintenance man-hour as the objective function,the time period in the maintenance process,maintenance mutual exclusion,maintenance team resources,etc.as constraints,a maintenance man-hour prediction model of flexible AC/DC hybrid distribution substation is established,and the coefficient optimization process of multi-objective particle swarm optimization algorithm is designed to complete the maintenance man-hour prediction of substation.The results show that the standard curve correlation coefficient between the predicted value and the actual value is closer to 1,the average absolute deviation and the average absolute percentage error are smaller,and the prediction deviation is lower.

关 键 词：多目标粒子群算法 柔性交直流混合配网 变电站检修 预测模型 参数寻优 

分 类 号：TH164[机械工程—机械制造及自动化]