论文部分内容阅读
故障诊断模型是开展输变电设备状态检修的核心环节之一,文中采用弹性反馈(RPROP)神经网络算法建立主变压器油中溶解气体的神经网络故障诊断模型,通过与带动量因子的标准反向传播(BP)算法、Bold Driver算法、SuperSAB算法相比较,表明了RPROP算法在故障模式识别中具有更好的学习效率与泛化能力,故障诊断的准确度高于传统分析方法,在变电设备状态诊断中具有良好的应用前景。
The fault diagnosis model is one of the key aspects in the condition maintenance of power transmission and transformation equipment. In this paper, a neural network fault diagnosis model of dissolved gas in main transformer oil is established by RPROP neural network algorithm. By contrast with the standard of driving force factor Compared with BP algorithm, Bold Driver algorithm and SuperSAB algorithm, it shows that RPROP algorithm has better learning efficiency and generalization ability in fault pattern recognition. The accuracy of fault diagnosis is higher than that of traditional analysis methods. In substation equipment Status diagnosis has a good prospect.