FAHP和ANN在电力变压器风险评估中的应用

提出了基于模糊层次分析法（FAHP）和人工神经网络（ANN）相结合的电力变压器风险评估方法．采用FAHP分析变压器的层次结构，通过对影响变压器状态的若干因素之间隶属度的判别，构造模糊一致判断矩阵，定量计算出各因素的权重系数；选择权值较大的因素作为变压器ANN模型的输入，简化了ANN的结构．研究结果表明，FAHP-ANN模型克服了传统风险评估方法中ANN模型结构复杂、信号繁多、训练时间长等缺点，提高了评估的速度和结果的精度，实现了预期的目标．

FAHP and ANN in power transformer risk assessment

A risk assessment method based on the combination of FAHP and ANN were presented,FAHP was adopted to analyze the hierarchy structure of power transformer,and by distinguishing membership degree of influential factors of power transformer＇s state,it constructs a fuzzy matrix. Prior to this,the method figures out each factor＇s weight coefficient. By selecting factors of bigger weight coefficient as input of power transformer＇s ANN model, ANN＇s structure is simplified. Results show that the FAHP-ANN method overcome the disadvantages of ANN model structure in traditional risk assessment method, which includes complicated structure, multiple signals and long-time training, it also shortens the time of assessment,increases the precison of the data,achieves the ore-set target.