Modeling and classifying the in-operando effects of wear and metal contaminations of lubricating oil on diesel engine: A machine learning approach
作者：
Highlights：
• Machine learning displays an agreement in supreme depth to data of metal contaminations.
• Applied kernel functions such as polynomial degree 3 and rbf showed the best prediction.
• Fe, Si, and Cr are the significant compelling features on engine critical condition.
• The generalization ability of RBF-NN and SVM were evaluated and ranked, respectively.
• RBF-NN model exhibit superior accuracy to classify diesel engine and deal with it in depth.
摘要
•Machine learning displays an agreement in supreme depth to data of metal contaminations.•Applied kernel functions such as polynomial degree 3 and rbf showed the best prediction.•Fe, Si, and Cr are the significant compelling features on engine critical condition.•The generalization ability of RBF-NN and SVM were evaluated and ranked, respectively.•RBF-NN model exhibit superior accuracy to classify diesel engine and deal with it in depth.
论文关键词：RBF-NN,SVM,Kernel function,Diesel engine,Lubricating Oil
论文评审过程：Received 12 January 2022, Revised 14 April 2022, Accepted 30 April 2022, Available online 6 May 2022, Version of Record 13 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117494
