Identification of Lubricating Oil Additives Using XGBoost and Ant Colony Optimization Algorithms

To address the problem of identifying multiple types of additives in lubricating oil,a method based on midinfrared spectral band selection using the eXtreme Gradient Boosting(XGBoost)algorithm combined with the ant colony optimization(ACO)algorithm is proposed.The XGBoost algorithm was used to train and test three additives,T534(alkyl diphenylamine),T308(isooctyl acid thiophospholipid octadecylamine),and T306(trimethylphenol phosphate),separately,in order to screen for the optimal combination of spectral bands for each additive.The ACO algorithm was used to optimize the parameters of the XGBoost algorithm to improve the identification accuracy.During this process,the support vector machine(SVM)and hybrid bat algorithms(HBA)were included as a comparison,generating four models:ACO-XGBoost,ACO-SVM,HBA-XGboost,and HBA-SVM.The results showed that all four models could identify the three additives efficiently,with the ACO-XGBoost model achieving 100%recognition of all three additives.In addition,the generalizability of the ACO-XGBoost model was further demonstrated by predicting a lubricating oil containing the three additives prepared in our laboratory and a collected sample of commercial oil currently in use。

Tribological Properties of Few-layer Graphene Oxide Sheets as Oil-Based Lubricant Additives

The performance of a lubricant largely depends on the additives it involves. However, currently used additives cause severe pollution if they are burned and exhausted. Therefore, it is necessary to develop a new generation of green additives. Graphene oxide（GO） consists of only C, H and O and thus is considered to be environmentally friendly. So the tribological properties of the few-layer GO sheet as an additive in hydrocarbon base oil are investigated systematically. It is found that, with the addition of GO sheets, both the coefficient of friction（COF） and wear are decreased and the working temperature range of the lubricant is expanded in the positive direction. Moreover, GO sheets has better performance under higher sliding speed and the optimized concentration of GO sheets is determined to be 0.5wt%. After rubbing, GO is detected on the wear scars through Raman spectroscopy. And it is believed that, during the rubbing, GO sheets adhere to the sliding surfaces, behaving like protective films and preventing the sliding surfaces from contacting with each other directly. This paper proves that the GO sheet is an effective lubricant additive, illuminates the lubrication mechanism, and provides some critical parameters for the practical application of GO sheets in lubrication.

Design of wear-out-failure in-situ repair parts by environment-friendly nanocopper additive

Oleic acid surface-modified Cu nanoparticles with an average size of 20 nm were prepared by liquid phase reducing reaction. The tribological performance and mechanism of nanocopper as additive were studied by means of tribotester, scanning electron microscopy (SEM), energy dispersive X-ray spectroscopy (EDS) and nanoindentation instrument. The results indicate that the modified nanocopper additive can significantly improve the wear resistance and reduce friction coefficient of base oil. A copper protective film is formed and contributes to the excellent tribological properties of nanocopper additive. On the basis of the film forming mechanism, a new in-situ repair method was designed and used to repair wear-out-failure injection pump plunger and barrel. Furthermore, the current research progress of nanoparticles as green energy-saving lubricating oil additives were presented.