Harnessing Machine Learning to Predict MoS 2 Solid Lubricant Performance

Vogel, Dayton Jonathan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000336120699); Babuska, Tomas Farley [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000171920400); Mings, Alexander James [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0009000967656278); MacDonell, Peter Athan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)]; Curry, John F. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000326111297); Larson, Steven R. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000346810749); Dugger, Michael T. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)]

doi:10.1007/s11249-024-01957-y

DOE OSTI · 2999412

Harnessing Machine Learning to Predict MoS 2 Solid Lubricant Performance

Vogel, Dayton Jonathan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000336120699)·Babuska, Tomas Farley [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000171920400)·Mings, Alexander James [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0009000967656278)·MacDonell, Peter Athan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)]·Curry, John F. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000326111297)·Larson, Steven R. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000346810749)·Dugger, Michael T. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)]

View original source ↗Read source document ↗Export metadata ↓

Abstract

Physical vapor deposited (PVD) molybdenum disulfide (MoS 2 ) solid lubricant coatings are an exemplar material system for machine learning methods due to small changes in process variables often causing large variations in microstructure and mechanical/tribological properties. Here, in this work, a gradient boosted regression tree machine learning method is applied to an existing experimental data set containing process, microstructure, and property information to create deeper insights into the process-structure–property relationships for molybdenum disulfide (MoS 2 ) solid lubricant coatings. The optimized and cross-validated models show good predictive capabilities for density, reduced modulus, hardness, wear rate, and initial coefficients of friction. The contribution of individual deposition variables (i.e., argon pressure, deposition power, target conditioning) on coating properties is highlighted through feature importance. The process-property relationships established herein show linear and non-linear relationships and highlight the influence of uncontrolled deposition variables (i.e., target conditioning) on the tribological performance.

Explore related subjects

MoS2 PVD deposition optimization machine learning sputtering thin films tribology

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Vogel, Dayton Jonathan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000336120699), Babuska, Tomas Farley [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000171920400), Mings, Alexander James [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0009000967656278), MacDonell, Peter Athan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)], Curry, John F. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000326111297), Larson, Steven R. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000346810749), Dugger, Michael T. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)]. 2025-01-14. Harnessing Machine Learning to Predict MoS 2 Solid Lubricant Performance. https://doi.org/10.1007/s11249-024-01957-y

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Substrate-Directed Underlayer Growth of Bilayer MoS 2 Revealed by Mo Isotope Labeling

Direct control over the vertical formation sequence and stacking registry in van der Waals (vdW) bilayers is essential for device performance and moiré engineering yet difficult to resolve unambiguously with conventional probes. Here, we use Mo isotope labeling in a two-step chemical vapor deposition process to synthesize bilayer MoS 2 and trace its vertical formation on common substrates. By combining site-selective laser thinning, Raman spectroscopy, time-of-flight secondary ion mass spectrometry, and atomic-resolution scanning transimission electron microscopy (STEM), we find a clear substrate dependence: on SiO 2 /Si, the second layer nucleates and grows beneath the first (underlayer), whereas on sapphire, it forms on top (overlayer). Density functional theory indicates that a larger equilibrium interfacial separation and weaker MoS 2 –substrate interactions on amorphous SiO 2 permit confined interfacial diffusion and underlayer nucleation, whereas stronger interactions and smaller separations on sapphire favor overlayer growth. On SiO 2 , confined epitaxy templates commensurate 2H, 3R, and mixed bilayers, as confirmed by second harmonic generation spectroscopy and STEM. During underlayer coalescence, embedded mirror-twin grain boundaries stitch atomically sharp 2H|3R junctions via alternating 4|8 ring motifs. Molecular-dynamics simulations reveal that these alternating 4|8 motifs accommodate interlayer vdW coupling and locally modulate the stacking registry. These results provide mechanistic insight into confined epitaxial growth and establish isotope labeling as a powerful probe of two-dimensional materials synthesis.

MoS2↗

DOE OSTI2025

Construction of MoS 2 /MoO 3 Heterostructure with Ultrafast-Charged and Superior Low-Temperature Sodium Storage Properties

The electrochemical reaction kinetics of sodium-ion batteries (SIBs) become sluggish at low temperatures, resulting in significant reductions in energy density and power density. Rational design of anode materials with excellent low-temperature performance is of great significance for promoting the application of SIBs under extreme conditions. Here, in this study, the spontaneous hydrolysis and oxidation reactions of MoS 2 in aqueous solution are used to successfully construct the MoS 2 /MoO 3 heterostructure. The formation of built-in electric fields at the MoS 2 /MoO 3 heterointerfaces improves the electrochemical reaction kinetics, thereby enhancing the rate performance. In addition, the dual-phase material can effectively buffer the volume strain during the cycle process, thereby improving the cycle stability. Thus, the MoS 2 /MoO 3 displays ultrafast charging properties at room temperature (up to 244.6 mAh g –1 at 40 A g –1 , discharge/charge in 22 s). Even at −40 °C, it also exhibits a high capacity of 303.7 mAh g –1 and superior cycling performance (capacity retention rate up to 92.9% after 900 cycles at 2 A g –1 ).

MoS2↗

DOE OSTI2025

Microstructural Assessment of Molybdenum Disulfide Coatings Using Nanoindentation Hardness

MoS 2 coatings are used extensively in aerospace and defense applications due to their ultralow friction and high wear resistance. Burnished and resin-bonded MoS 2 coatings are commonly used in these applications due to simplicity in deposition and history of use, despite issues with consistency in coating properties and performance. Physical vapor deposition (PVD) of MoS 2 thin films has emerged as a process alternative in the past 50 years, promising far greater control over film structure and composition but at a greater cost. Despite PVD’s benefits, hesitance to adoption persists in high-consequence applications, not only due to increased costs but variability in resulting coating properties. These variations in properties and subsequent performance are in part due to the complexity of the PVD process and the sensitive interplay between coating process-structure-property relationships. This work aims to demystify the remaining uncertainties of the process-structure-property relationships in PVD MoS 2 . The microstructure and mechanical and tribological properties of 61 different PVD pure MoS 2 coatings are examined herein. Emphasis has been placed on developing performance-based (i.e., hardness, modulus) metrics that can assess microstructural changes (density, orientation, and crystallinity) and be utilized to accelerate process development and coating optimization. Relationships established within suggest that nanoindentation hardness can be used to infer coating performance (i.e., wear rate) and properties (i.e., density, crystalline texture, and stoichiometry). Furthermore, this work demonstrates that PVD MoS 2 coatings close to the theoretical density of MoS 2 consistently have the best tribological performance and can be reliably identified by their hardness.

MoS2↗