欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
人工神经网络在电力电子电路故障诊断中有广泛的应用。常用的反向传播算法存在着容易陷入局部极小点、对初值要求高的缺点,给故障诊断带来不便。提出了采用遗传算法优化人工神经网络结构的初值,将遗传算法与人工神经网络结合起来,应用于电力电子电路的故障诊断中。仿真实验表明该方法是有效的。
英文摘要：
Artificial Neural Network（ANN） has been widely used in fault diagnosis of power electronic circuits.One of the main weak-points of the back propagation algorithm which is commonly used is that the optimal procedure is easily stacked into the minimal value locally and causes strict demands of initial value.Based on Genetic Algorithm（GA）,GA-ANN algorithm is proposed to optimize the initial value of ANN structure.Some examples are given to prove that GA-ANN algorithm is valid to diagnose the faults of power electronic circuits.
同期刊论文项目
同项目期刊论文
Simulation of grain boundary effect on characteristics of ZnO thin film transistor by considering th
Four optimal design approaches of high-order finite-impulse response filters based on neural network
期刊信息
位置：