Machine Learning Decomposition Onset Temperature of Lubricant Additives
- PDF / 1,618,136 Bytes
- 12 Pages / 593.972 x 792 pts Page_size
- 28 Downloads / 195 Views
JMEPEG https://doi.org/10.1007/s11665-020-05146-5
Machine Learning Decomposition Onset Temperature of Lubricant Additives Yun Zhang
and Xiaojie Xu
(Submitted June 17, 2020; in revised form August 22, 2020; Accepted: 12 September 2020) The thermal stability of lubricant additives is a fundamental parameter in practical applications, which is determined by the molecular structure. The ability to predict thermal properties, particularly lubricant additivesÕ decomposition onset temperature, is of ultimate importance. We develop the Gaussian process regression model to present the relationship between molecular descriptors and onset temperature of decomposition of lubricant additives. This model is highly stable and accurate, which is promising as a fast, robust, and low-cost tool for estimating various types of lubricant additivesÕ decomposition onset temperature. Keywords
decomposition, Gaussian process, lubricant additive, machine learning, temperature
1. Introduction Lubricants are widely used in modern industry for wear and friction coefficient reductions. To increase the mechanical efficiency, further reduce wear and friction, and prevent surface damage, additives are commonly added in lubricants (Ref 1). S- and N-containing additives are utilized to provide protection against pressure of moderate to high levels and metal-to-metal contacts in boundary lubrication. Both open chain and heterocyclic compounds have been investigated extensively, including dithiocarbamates, organic sulfonic acid ammonium salts, alkyl amine salts of thiocyanic acid, 2,5dimercapto-1,3,4-thiadiazole, and 2-mercapto-1,3-benzothiazole (Ref 2). For example, 1,3,4-thiadiazole derivatives are anti-corrosive for metal and have large load-carrying and extreme pressure capacities, which are widely utilized as lubricantsÕ additives, such as ester-based lubricants and rapeseed oil (Ref 3). Moreover, previous research also indicates that N-containing heterocyclic compounds are promising candidates as ‘‘green’’ lubricating oil additives as they have good thermal and thermal stabilities. Certain N-containing heterocyclic compounds, including triazine, benzotriazole, and benzothiazole, are ashless and environmental-friendly (Ref 4, 5). AdditivesÕ tribological properties depend on chemical structures and interactions with metal surfaces (Ref 2). Different Ocontaining groupsÕ effects on N- or N, S-containing heterocyclic compoundsÕ anti-wear performance have been studied. It is demonstrated that by introducing hydroxyl groups into rings, anti-wear properties can be greatly enhanced (Ref 6). Other than tribological properties, the thermal stability is a fundamental parameter that defines the application limitation of certain additives. Experimentally, the thermal stability test is
Yun Zhang and Xiaojie Xu, North Carolina State University, Raleigh, NC 27695. Contact e-mails: [email protected] and [email protected].
Journal of Materials Engineering and Performance
investigated by thermo-gravimetric analysis in an inert atmosphere (Ref 7-10). But this appro
Data Loading...
