Open Access Research Article Issue
Modeling and prediction of tribological properties of copper/aluminum-graphite self-lubricating composites using machine learning algorithms
Friction 2024, 12 (6): 1322-1340
Published: 02 April 2024
Abstract PDF (3.5 MB) Collect

The tribological properties of self-lubricating composites are influenced by many variables and complex mechanisms. Data-driven methods, including machine learning (ML) algorithms, can yield a better comprehensive understanding of complex problems under the influence of multiple parameters, typically for how tribological performances and material properties correlate. Correlation of friction coefficients and wear rates of copper/aluminum-graphite (Cu/Al-graphite) self-lubricating composites with their inherent material properties (composition, lubricant content, particle size, processing process, and interfacial bonding strength) and the variables related to the testing method (normal load, sliding speed, and sliding distance) were analyzed using traditional approaches, followed by modeling and prediction of tribological properties through five different ML algorithms, namely support vector machine (SVM), K-Nearest neighbor (KNN), random forest (RF), eXtreme gradient boosting (XGBoost), and least-squares boosting (LSBoost), based on the tribology experimental data. Results demonstrated that ML models could satisfactorily predict friction coefficient and wear rate from the material properties and testing method variables data. Herein, the LSBoost model based on the integrated learning algorithm presented the best prediction performance for friction coefficients and wear rates, with R2 of 0.9219 and 0.9243, respectively. Feature importance analysis also revealed that the content of graphite and the hardness of the matrix have the greatest influence on the friction coefficients, and the normal load, the content of graphite, and the hardness of the matrix influence the wear rates the most.

Open Access Research Article Issue
Bioinspired PcBN/hBN fibrous monolithic ceramic: High-temperature crack resistance responses and self-lubricating performances
Journal of Advanced Ceramics 2022, 11 (9): 1391-1403
Published: 05 September 2022
Abstract PDF (1.2 MB) Collect

The high strength and toughness of natural materials are mainly determined by a combination of mechanisms operating at different length scales, which can be used as a strategy to reduce the intrinsic brittleness of ceramics. Inspired by the architectures of bamboo, the polycrystalline cubic boron nitride/hexagonal boron nitride (PcBN/hBN) fibrous monolithic ceramics with a long fiber arrangement structure was constructed with PcBN fiber cells and hBN cell boundaries, and its crack resistance responses and tribological performances were investigated. The composite ceramic failed in a non-brittle manner with the rising resistance curve (R-curve) behavior, which was attributed to multiscale crack effects in the hierarchical architecture. The maximum crack growth toughness was extremely high (approximately 21 MPa·m1/2), corresponding to a 270% increase over the crack initiation toughness. Excellent fracture resistance could be retained even above 1000 ℃. Moreover, the composite ceramic exhibited low and stable friction coefficients (approximately 0.33) when paired with a Si3N4 pin at high temperature (1000 ℃), owing to the lubrication function of hBN cell boundaries with weak van der Waals forces and a small amount of liquid B2O3 produced. As a result, a synergistic improvement of mechanical and tribological properties at high temperature (1000 ℃) was realized by combining bionic structure and tribological design. It provides important theoretical and technical support for expanding the application of self-lubricating composite ceramics in harsh environments.

Open Access Research Article Issue
Influence of binder systems on sintering characteristics, microstructures, and mechanical properties of PcBN composites fabricated by SPS
Journal of Advanced Ceramics 2022, 11 (2): 321-330
Published: 11 January 2022
Abstract PDF (1.6 MB) Collect

Cubic boron nitride (cBN) with high hardness, thermal conductivity, wear resistance, and chemical inertness has become the most promising abrasive and machining material. Due to the difficulty of fabricating pure cBN body, generally, some binders are incorporated among cBN particles to prepare polycrystalline cubic boron nitride (PcBN). Hence, the binders play a critical factor to the performances of PcBN composites. In this study, the PcBN composites with three binder systems containing ceramic and metal phases were fabricated by spark plasma sintering (SPS) from 1400 to 1700 ℃. The sintering behaviors and mechanical properties of the composites were investigated. Results show that the effect of binder formulas on mechanical properties mainly related to the compactness, mechanical performances, and thermal expansion coefficient of binder phases, which affect the carrying capacity of the composites and the bonding strength between binder phases and cBN particles. The PcBN composite with SiAlON phase as binder presented optimal flexural strength (465±29 MPa) and fracture toughness (5.62±0.37 MPa·m1/2), attributing to the synergistic effect similar to transgranular and intergranular fractures. Meanwhile, the excellent mechanical properties can be maintained a comparable level when the temperature even rises to 800 ℃. Due to the weak bonding strength and high porosity, the PcBN composites with Al2O3-ZrO2(3Y) and Al-Ti binder systems exhibited inferior mechanical properties. The possible mechanisms to explain these results were also analyzed.

Total 3