基于有限元和神经网络方法的弹簧触指结构优化设计  

Optimization Design on Spring Contact Finger Structure Based on Finite Element Method and Neural Network Method

作　　者：苏俊天 淡淑恒 SU Juntian;DAN Shuheng(College of Electrical Engineering,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学电气工程学院,上海200090

出　　处：《高压电器》2025年第3期176-183,共8页High Voltage Apparatus

摘　　要：针对电气设备常见的电连接器——弹簧触指结构,提出了一种优化弹簧触指结构参数的方法。首先运用仿真软件Comsol Multiphysics建立弹簧触指结构模型,利用有限元方法进行接触压力和接触电阻计算,分析了簧丝直径、弹簧倾斜角、宽高比、弹簧圈数对性能参数的影响。以接触压力和接触电阻作为目标函数,利用遗传算法改进的BP神经网络模型,拟合了弹簧触指结构参数与目标函数之间的关系,从而对弹簧触指结构进行优化设计。在满足弹簧触指结构插拔力要求的条件下,减小弹簧触指结构的接触电阻,降低工作温度,改善了其电接触性能。文中提出的优化方法克服了单一变量法计算量大、计算时间长的缺点,可为弹簧触指结构的设计提供新思路。Aiming at the spring contact finger structure,a common electrical connector in electrical equipment,a method for optimizing the structural parameters of the spring contact finger is proposed.Firstly,Comsol Multiphysics finite element software is used to set up the structural model of the spring contact finger,the contact pressure and contact resistance are calculated by the finite element method.Then,the influence of the spring diameter,inclination angle,width-height ratio size and the number of spring wire on performance parameters are analyzed.The contact pressure and contact resistance are taken as the objective function,the relationship between the parameters of the spring contact structure and the objective function is fitted by using the BP neural network model which is improved by genetic algorithm,thus optimizing the design of the spring contact structure.Under the condition of meeting the requirements of the insertion and pulling force of the spring contact finger,the contact resistance and working temperature are reduced and the electrical contact performance is improved.The optimization method proposed in this paper overcomes the shortcomings of large calculation and long calculation time of the single variable method and provides a new idea for the design of spring contact finger structure.

关 键 词：弹簧触指结构 有限元法 结构优化 遗传算法 神经网络 

分 类 号：TM503.5[电气工程—电器] TP183[自动化与计算机技术—控制理论与控制工程]