机床与液压
機床與液壓
궤상여액압
Machine Tool & Hydraulics
2015年
18期
33-38
,共6页
航空发动机%气路故障诊断%遗传算法%BP 神经网络
航空髮動機%氣路故障診斷%遺傳算法%BP 神經網絡
항공발동궤%기로고장진단%유전산법%BP 신경망락
Aero-engine%Gas path fault diagnosis%Genetic algorithm%BP neural network
为提高 BP 神经网络诊断发动机气路故障的准确率,利用遗传算法对 BP 神经网络的初始连接权值和阀值在解空间内进化寻优,再将优化结果赋给网络以梯度下降算法进行二次训练,再对待检故障样本进行诊断。结果表明:GA-BP 网络在输出精度、收敛速度及收敛曲线平滑性上明显优于普通 BP 网络,为航空发动机故障诊断领域的研究提出了新的思路和方法,具有一定研究价值。
為提高 BP 神經網絡診斷髮動機氣路故障的準確率,利用遺傳算法對 BP 神經網絡的初始連接權值和閥值在解空間內進化尋優,再將優化結果賦給網絡以梯度下降算法進行二次訓練,再對待檢故障樣本進行診斷。結果錶明:GA-BP 網絡在輸齣精度、收斂速度及收斂麯線平滑性上明顯優于普通 BP 網絡,為航空髮動機故障診斷領域的研究提齣瞭新的思路和方法,具有一定研究價值。
위제고 BP 신경망락진단발동궤기로고장적준학솔,이용유전산법대 BP 신경망락적초시련접권치화벌치재해공간내진화심우,재장우화결과부급망락이제도하강산법진행이차훈련,재대대검고장양본진행진단。결과표명:GA-BP 망락재수출정도、수렴속도급수렴곡선평활성상명현우우보통 BP 망락,위항공발동궤고장진단영역적연구제출료신적사로화방법,구유일정연구개치。
In order to improve the accuracy rate of aero-engine gas-path fault diagnosis based on BP neural net-work,this research uses the genetic algorithm to optimize the initial weights and thresholds of BP neural network in their solution space,retrains the results by gradient descent algorithm and uses the optimized network to testify the fault samples.The result shows that GA-BP network has a higher precision and converges faster,and its con-vergence curve is smoother than that of the common BP network.This work can put forward new ideas and meth-ods for aero-engine fault diagnosis and has a certain research value.