基于优化灰色BP神经网络的柴油机缸套磨损预测  

Prediction of barrel wear of diesel engines based on optimized grey BP neural network

作　　者：徐红明[1] 蒋更红[1] 方诚[1] 林忠 XU Hongming;JIANG Genghong;FANG Cheng;LIN Zhong

机构地区：[1]浙江交通职业技术学院海运学院,浙江杭州311112 [2]福建新继船舶服务有限公司,福建厦门361000

出　　处：《中国修船》2023年第3期37-41,共5页China Shiprepair

基　　金：浙江省基础公益研究计划项目(LGG18E090001)。

摘　　要：为了精准预测柴油机缸套磨损量,有效预防柴油机故障的发生,文章提出了一种灰色理论与BP神经网络相结合的残差修正算法,通过对缸套磨损量小样本数据建立灰色GM (1,1)模型,生成灰色数据序列,再建立灰色残差值的BP神经网络预测模型。通过验证表明,灰色神经网络组合模型的气缸套磨损量预测精度高,整体性能好,为实现柴油机智能化监测提供新的技术路径。In order to accurately predict the barrel wear amount of diesel engines and effectively avoid diesel engine failure,this paper proposes a residual modification algorithm that combines the grey theory with a BP neural network.A grey GM(1,1)model is established based on the small sample data of the barrel wear amount,and the grey data sequence is generated.Then a BP neural network prediction model of grey residual value is established.The verification results show that the combined grey neural network model has a high prediction accuracy of barrel wear amount and shows excellent overall performance,which provides a new technical path for the intelligent moni⁃toring of diesel engines.

关 键 词：灰色预测 BP神经网络 残差修正 柴油机 缸套磨损量 

分 类 号：U664.121[交通运输工程—船舶及航道工程]