基于神经网络的断路器对流换热系数识别  

Identification of Convective Heat Transfer Coefficient of Circuit Breaker Based on Neural Network

作　　者：孟聪 李海伟[1] 朱坚民[1] 黄扬辉 石园园 Meng Cong;Li Haiwei;Zhu Jianmin;Huang Yanghui;Shi Yuanyuan(University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学,上海市200093

出　　处：《农业装备与车辆工程》2020年第10期80-85,共6页Agricultural Equipment & Vehicle Engineering

摘　　要：针对断路器对流换热系数难以精确确定的问题,以断路器导电系统的对流换热系数、环境温度为优化变量,建立导电系统对流换热系数的神经网络模型。结合神经网络模型的计算结果与断路器温升实验的结果,采用多岛遗传算法和序列二次规划组合优化算法对断路器导电系统的对流换热系数和环境温度进行优化识别。以6300A框架式断路器导电系统为实例进行建模、实验、参数识别等分析。仿真和实验结果表明:采用该方法辨识的参数所建立的断路器导电系统的温度场分布与实验测试的温度误差小于3%,对流换热系数辨识结果具有较高的精度。Aiming at the problem that the convective heat transfer coefficient of the circuit breaker is difficult to be accurately determined,the neural network model of the convective heat transfer coefficient of the conductive system is established,with the convective heat transfer coefficient of the circuit breaker conductive system and the ambient temperature as variables to be optimized.Combined with the calculation results of the neural network model,based on the results of temperature rise test of circuit breaker,the multi-island genetic algorithm and sequential quadratic programming combined optimization algorithm are used to optimize the convective heat transfer coefficient and ambient temperature of the circuit breaker conductive system.The 6300 A frame type circuit breaker conductive system is taken as an example to conduct analysis of modes,experiments,parameter identification,etc.The simulation and experimental results show that the temperature field distribution of the circuit breaker conductive system established by the parameters identified by this method is less than 3%with the experimental test,and the convective heat transfer coefficient identification result has higher precision.

关 键 词：框架式断路器 导电系统 神经网络 组合优化 对流换热系数 环境温度 

分 类 号：TM561[电气工程—电器]