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：
为了有效地监测异步电动机定子绕组匝间短路故障，提出了基于对角递归神经网络的匝间故障在线诊断方法。该方法采用2个对角递归神经网络监测匝间短路故障，一个用于估算故障的严重度，另一个用于确定定子绕组故障匝数。同时，提出自适应动态学习算法，训练对角递归神经网络。确定网络最优隐层神经元的个数．使诊断模型更加紧凑和精确。根据该方法构建了试验系统并进行了匝间短路试验，试验结果表明：基于对角递归神经网络的诊断模型．在不同工况下可精确确定定子绕组短路故障的匝数。由于对角递归神经网络具有动态处理能力．和前馈神经网络相比．克服了前馈神经网络故障诊断模型无动态处理能力的局限性。能更有效地监测定子绕组匝间短路故障。
英文摘要：
An approach based on the diagonal recurrent neural network is proposed to effectively detect the inter-turn fault of asynchronous motor stator windings. one for the fault severity estimation and the other for Two diagonal recurrent neural networks are employed, the shorted turns determination. In order to make the detection model more compact and accurate,an adaptive dynamic algorithm is proposed to train the diagonal recurrent neural networks and determine the optimal number of hidden layer neurons. Experiments are carried out on a test system built according to this method. The results show that,the proposed detection model exactly determines the shorted turns under different operating conditions. Owing to its dynamic performance,it is more effective than that the detection model based on feed-forward neural network.
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：