摘要
滑油状态的监测与分析是航空发动机状态监测与故障诊断的重要手段。为了解决以往滑油金属质量分数预测模型算法的局部性、收敛速度慢及预测结果误差大等问题,结合遗传算法(GA)收敛速度快、鲁棒性好等优点,对反向传播(BP)神经网络算法进行GA优化,通过GA对参数寻优,并应用于发动机滑油金属质量分数预测。由于滑油的状态参数并不能确定部件故障与否,利用贝叶斯(Bayes)决策规则对诊断结果进行了错误率计算。将所提方法应用于某航空发动机滑油铁质量分数预测,结果表明:采用GA优化后的BP神经网络(GA-BP)得到的预测结果具有更高的精度,其最大预测误差不超过6%,平均预测误差为1.7%,所测数据与原数据具有较好的拟合性,利用Bayes决策规则对诊断结果进行分析,对于部件故障与否的判别更具说服力。
Lubricating oil condition monitoring and analysis is an important means of aeroengine condition monitoring and fault diagnosis.In order to solve the problems of previously proposed prediction algorithms for the metal mass fraction of lubricating oil as local in optimization,slow in convergence,large prediction error,etc.,a Genetic Algorithm(GA)optimized Back Propagation(BP)neural network algorithm was proposed.Taking advantages GA’s fast convergence and robustness,the BP algorithm was optimized through GA parameter optimization and was applied to the prediction of metal mass fraction of engine lubricating oil.Because the state parameters of lubricating oil are unable to be used to determine whether the component is faulty or not,Bayesian decision rules were used to calculate the error rate of diagnosis.The proposed method was applied to predict the mass fraction of lubricating iron in an aeroengine.The results show that the BP neural network optimized by GA is more accurate for the prediction.The maximum prediction error is less than 6%,and the average prediction error is 1.7%.The measured data fit well with the original data.Diagnosis result analyzed using Bayes decision rules is more convincing in judging whether the component is faulty or not.
作者
周良
王华伟
许珊珊
王清薇
ZHOU Liang;WANG Hua-wei;XU Shan-shan;WANG Qing-wei(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211100,China;School of Public Administration,Shandong Normal University,Jinan 250300,China)
出处
《航空发动机》
北大核心
2022年第5期137-142,共6页
Aeroengine
基金
国家自然科学基金(U1833110)资助。
关键词
滑油状态
故障诊断
神经网络
遗传算法
可靠性
航空发动机
lubricating oil condition
fault diagnosis
neural network
genetic algorithm
reliability
aeroengine
