The article presents a systematic analysis of the application of information technologies in tribology, including traditional methods, machine learning and artificial intelligence. The main goal of the study is to generalize and classify tribological informatics methods to improve the efficiency of tribological process analysis. The methodology is based on a review of key algorithms (ANN, support vector machines, K-nearest neighbors, random forest methods), determining their role in tribological research and analyzing information aimed at monitoring the technical condition, predicting behavior and optimizing tribological systems. It is determined that the use of artificial intelligence and machine learning algorithms significantly improves the accuracy of tribological system diagnostics, allows predicting their operational life and optimizing the operating parameters of tribological systems and machine mechanisms. A classification of tribological informatics methods is presented according to their functions: regression, classification, clustering, dimensionality reduction. This makes it possible to determine the most effective approaches for different types of tribological analysis. The practical focus of using intelligent modeling methods is the possibility of integrating the obtained results into production processes, which contributes to increasing the reliability of mechanical systems, reducing the costs of their maintenance and creating more accurate methods for predicting tribological characteristics, properties and tribological efficiency of the functioning of system components and assemblies of machines and mechanisms. It is shown that triboinformatics opens up new prospects for improving tribological research, providing more accurate monitoring, effective forecasting and optimization of tribological systems.
Аулін et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: