摘要
径向基函数神经网络是一种前馈型神经网络,具有较强的函数逼近能力和分类能力,学习速度快等优点。本文采用幅值恒定的正弦信号源进行模拟电路的故障仿真,从频域提取输出信号波形的特征值建立故障字典,应用径向基函数神经网络的这些优点进行响应分析和故障诊断,能够实现快速故障诊断及定位,具有准确率高的特点。
Radial basis function neural network is a feed-forward network. It has many good properties, such as powerful ability for function approximation, classification and learning rapidly. Sinusoidal input to the analog circuit with constant amplitude and different frequencies is simulated and frequency domain features of the output response are used to build the fault dictionary. In this paper, a radial basis function neural network method for response analysis and fault diagnosis has been proposed. Results illustrate that this method is feasible and has many powerful features, such as diagnosing and locating faults quickly and exactly.
出处
《电路与系统学报》
CSCD
北大核心
2007年第2期65-68,共4页
Journal of Circuits and Systems
基金
国家自然科学基金资助项目(60372001)
四川省青年科技基金资助项目(04ZQ026-031)
关键词
径向基函数
混合集成电路
故障诊断
神经网络
radial basis function
mixed-signal integrated circuits
fault diagnosis
neural network
