船用柴油机机械活塞失效时间的预报研究
|
摘要
针对当前船用柴油机机械活塞失效时间的预报方法存在错误大,精度低等严重缺陷,提出了基于小波神经网络的柴油机机械活塞失效时间的预报方法。首先采用小波分析对柴油机机械活塞失效时间数据进行处理,然后采用神经网络对柴油机机械活塞失效时间数据进行学习,建立柴油机机械活塞失效时间预报模型,最后进行了具体实例分析,结果表明,本文方法可以准确、有效地对柴油机机械活塞失效时间进行估计,柴油机机械活塞失效时间预报精度要高于对比方法,失效时间预报效率高,有着较高的实际应用价值。
In view of the serious shortcomings of the current methods for predicting the failure time of marine diesel engine mechanical piston, such as large errors and low accuracy, a method for predicting the failure time of diesel engine mechanical piston based on wavelet neural network is proposed. Firstly, wavelet analysis is used to process the failure time data of diesel engine mechanical piston, then neural network is used to learn the failure time data of diesel engine mechanical piston, and a prediction model of diesel engine mechanical piston failure time is established. Finally, a concrete example is analyzed. The results show that this method can accurately and effectively estimate the failure time of diesel engine mechanical piston. The prediction accuracy of the failure time of the mechanical piston of diesel engine is higher than that of the contrast method. The prediction efficiency of the failure time is high and the practical application value is high.
In view of the serious shortcomings of the current methods for predicting the failure time of marine diesel engine mechanical piston, such as large errors and low accuracy, a method for predicting the failure time of diesel engine mechanical piston based on wavelet neural network is proposed. Firstly, wavelet analysis is used to process the failure time data of diesel engine mechanical piston, then neural network is used to learn the failure time data of diesel engine mechanical piston, and a prediction model of diesel engine mechanical piston failure time is established. Finally, a concrete example is analyzed. The results show that this method can accurately and effectively estimate the failure time of diesel engine mechanical piston. The prediction accuracy of the failure time of the mechanical piston of diesel engine is higher than that of the contrast method. The prediction efficiency of the failure time is high and the practical application value is high.
引文
[1]贾亦敏,史丽萍,严鑫.改进人工鱼群算法优化小波神经网络的变压器故障诊断[J].河南理工大学学报(自然科学版),2019,38(2):103-109.
[2]谢建新,康博,胡雪芳.工程机械柴油机活塞熔顶故障的试验分析[J].筑路机械与施工机械化,2017,34(2):110-113.
[3]张利敏,高峰,李京,等.大功率柴油机活塞连杆组机械损失分析[J].车用发动机,2016,22(6):19-22.
[4]张俊红,何振鹏,张桂昌,等.柴油机活塞热负荷和机械负荷耦合研究[J].内燃机学报,2011,29(1):78-83.
[5]俞小莉,翟昕,刘震涛,等.柴油机燃烧室形状对活塞热负荷与机械负荷的影响[J].内燃机工程,2002,33(1):45-48.
[2]谢建新,康博,胡雪芳.工程机械柴油机活塞熔顶故障的试验分析[J].筑路机械与施工机械化,2017,34(2):110-113.
[3]张利敏,高峰,李京,等.大功率柴油机活塞连杆组机械损失分析[J].车用发动机,2016,22(6):19-22.
[4]张俊红,何振鹏,张桂昌,等.柴油机活塞热负荷和机械负荷耦合研究[J].内燃机学报,2011,29(1):78-83.
[5]俞小莉,翟昕,刘震涛,等.柴油机燃烧室形状对活塞热负荷与机械负荷的影响[J].内燃机工程,2002,33(1):45-48.