论文部分内容阅读
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.
A fault diagnosis method based on dynamic fuzzy neural network and chaos optimization algorithm is proposed, in which the chaos variables are introduced into the fuzzy neural network structure and the optimal search of parameters.The chaotic optimization dynamic fuzzy neural network is used to establish the fault diagnosis model of transformer. Fuzzy rules and the importance of input variables can be evaluated, so that each input variable and fuzzy rules can be amended according to the rate of error reduction.The simulation results show that chaotic dynamic fuzzy neural network algorithm with high accuracy, less iterative steps, convergence Fast, with high accuracy and efficiency in identifying and predicting transformer status, and can be easily and effectively applied to other areas.