摘要
对变压器的运行状态和潜伏性故障进行有效预测,可避免出现维修不足或过度维修。由于BP神经网络具有对初始值敏感、易陷入局部最小的缺点,因此,其预测精度不高。本文采用遗传算法(GA)优化的BP神经网络对变压器油中气体进行预测和分析,结果表明,所采用的方法可有效提高BP神经网络的预测精度。
It will avoid the shortage of maintenance or excessive maintenance that the operational status and the latent faults of a power transformer are effectively predicted. Because of being sensitive to the initial value and easily falling into local minimum, the values obtained from the prediction by BP neural network is not accurate enough. In this paper, BP neural network optimized by genetic algorithm （GA） is used to predict and analyze the gas-in-oil of a transformer. The result shows that the proposed approach can effectively improve the prediction accuracy of BP neural network.
出处
《西华大学学报（自然科学版）》
CAS
2010年第2期145-147,共3页
Journal of Xihua University:Natural Science Edition
基金
西华大学人才基金资助(R0820902)
