| 遗传神经网络在模拟电路故障诊断中的应用 |
| |
| 引用本文： | 罗刚,陈小云,陈郁. 遗传神经网络在模拟电路故障诊断中的应用[J]. 长春理工大学学报(自然科学版), 2009, 32(3): 490-493 |
| |
| 作者姓名： | 罗刚 陈小云 陈郁 |
| |
| 作者单位： | 罗刚(成都电子机械高等专科学校,教务处,成都,610031);陈小云,陈郁(长春光学精密机械与物理研究所,长春,130033) |
| |
| 摘 要： | 对模拟电路的故障诊断,本文采用一种将遗传算法和BP神经网络结合的智能诊断方法-GA-BP算法,实现了模拟电路的故障诊断.该方法采用遗传算法优化神经网络的权值和阈值,代替了原来BP网络随机设定的初始权值和阈值,然后再用改进BP算法进行训练.通过仿真结果比较分析,经过遗传算法优化过的神经网络的训练步教大大减少.克服了传统BP算法的收敛速度慢,容易陷入局部极小值的缺点.
|
| 关 键 词： | 神经网络 遗传算法 模拟电路故障诊断 |
Genetic Algorithm(GA) Optimized Neural Networks for Analog Circuit Fault Diagnosis |
| |
| LUO Gang,CHEN Xiaoyun,CHEN Yu. Genetic Algorithm(GA) Optimized Neural Networks for Analog Circuit Fault Diagnosis[J]. Journal of Changchun University of Science and Technology, 2009, 32(3): 490-493 |
| |
| Authors: | LUO Gang CHEN Xiaoyun CHEN Yu |
| |
| Affiliation: | LUO Gang1,CHEN Xiaoyun2,CHEN Yu2(1.Chengdu Elecyromechanical College Academic Administration Chengdu 610031,2.Changchun Institute of optics fine mechanics , physics chinese academy of sciences,Changchun 130033) |
| |
| Abstract: | An intelligent diagnosis method based on integrate genetic algorithm(GA) and BP Neural Networks is adopted in this paper to diagnose the malfunction of the analog circuit.The original weights and biases set by the traditional BP NN are took place by the optimized data set by GA,and then the network is trained by advanced BP algorithm.After comparing simulation results,we can find that the train epochs of GA optimized BP NN decreased a lot.Many disadvantages of tradi-tional BP NN such as low convergence spee... |
| |
| Keywords: | neural networks genetic algorithm analog circuit fault diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
