混沌动态模糊神经网络及变压器故障诊断的应用

提出一种结合动态模糊神经网络和混沌优化算法的故障诊断方法,将混沌变量引入模糊神经网络结构和参数的优化搜索.利用混沌优化的动态模糊神经网络建立变压器故障诊断模型,此模型不仅能对模糊规则而且能对输入变量的重要性做出评价,从而使得每个输入变量和模糊规则都可根据误差减少率进行修正.仿真结果表明,混沌动态模糊神经网络算法精度高、迭代步骤少、收敛快,对识别和预测变压器状态具有较高的精度和效率,并可方便有效地应用到其他领域.

Chaotic dynamic fuzzy neural network and its application in power transformer fault Diagnosis

An innovative method was present,that combined dynamic fuzzy neural network(DFNN) with chaos optimization for the purpose of Power transformer fault diagnosis.Chaotic variables are applied to the search of FNN structure and all parameters.Chaotic dynamic fuzzy neural network(CDFNN) model was built for power transformer fault diagnosis.This model not only make the evaluation on the importance of the fuzzy rules,but also that of input variables,so that each input variables and fuzzy rules were amended according to the error reduced rate.The experimental results show the precision of the chaotic dynamic fuzzy neural network algorithm is more higher and the iteration steps are more fewer and the speed of convergence is more quicker.It has higher accuracy and efficiency to recognize and predict the state of power transformer,and also effectively and reliably be used in other fields.