The multi-objective optimization of Physical Vapor Deposition (PVD), as a predominant modality of vacuum coating, is indispensable for surface engineering, yet its optimization is bottlenecked by the conflict between experimental efficiency and data scale. Traditional trial-and-error and purely data-driven machine learning suffer from low efficiency and severe overfitting under typical "small-sample" constraints, often recommending non-physical or unsafe parameters. To address these challenges, this study proposes a closed-loop Physics-Informed Active Learning (PIAL) framework integrating three core modules: physics-enhanced feature engineering, a Physics-Regularized Heteroscedastic Neural Network (PR-HNN), and a risk-aware dual-point batch acquisition strategy. By embedding fundamental sputtering kinetics into the PR-HNN via continuous partial derivative constraints, the model is softly regularized toward physically plausible monotonic and saturating trends within the investigated CoCrFeNiTi magnetron sputtering process window, while effectively quantifying non-stationary experimental noise. Experimental results demonstrate that physics-based regularization reduces the generalization error of the PR-HNN by 41% compared to purely data-driven baselines, effectively eliminating non-physical fluctuations in sparse data regions. Guided by the risk-aware acquisition function, the framework progressively expanded the initial Pareto front through three closed-loop iterations. The PIAL-optimized coatings achieved a peak hardness of approximately 13.4 GPa and a minimum wear depth of 0.25 μm, while maintaining robust corrosion resistance. This methodology establishes a highly efficient, physically interpretable, and safe paradigm for AI-driven surface engineering and high-performance coating development.

Axial-symmetric vectoring exhaust nozzles (AVENs) enhance aero-platform maneuverability by dynamically modulating exhaust flow. However, the durability of their regulatory mechanisms remains a challenge because of their high temperature, heavy load, and complex multibody kinematics. It is crucial to conduct experiments to investigate AVENs-specific tribological behavior under extreme conditions. This study develops a novel tribometer to simulate the coupling kinematics of roller–cam, pin–hinge, and ball–socket joints, high-temperature operation (up to 800 °C), and heavy-load conditions (up to 30 kN). The setup features a dual-configuration fixture, a hybrid motion-loading module, and a multilayer heating and cooling system. The motion-loading module, comprising two electric cylinders, a hydraulic cylinder, and a rotary motor, enables precise replication of fixed and flexible kinematics under multiforce coupling. A dual-input, dual-output feedback system ensures accurate force and displacement control. Preliminary experiments validated the tribometer’s effectiveness and revealed dominant wear mechanisms, providing insights for AVEN durability improvements and tribological studies of complex aerospace mechanisms.

The triboelectric effect, known since ancient Greece, is the accumulation of electric charges due to electron transfer when materials contact and separate. With technological advancements, the triboelectric effect has been applied in energy harvesting equipment, sensors, and smart devices, including triboelectric nanogenerators (TENGs). This effect shows potential for sustainable energy and next-generation intelligent systems. Triboelectric systems, as a type of tribological system, require state monitoring, behavior prediction, and system optimization. Tribo-informatics is an interdisciplinary field that combines tribology and informatics. By clarifying information representations and flows within tribological systems, tribo-informatics addresses the connections between physical tribological systems and embedded information systems. With a focus on the triboelectric effect, this paper proposes a method for information representation in triboelectric systems from a tribo-informatics perspective and suggests a research approach based on tribo-informatics to achieve research goals. The aim is to enable researchers to collect, process, and analyze tribological information more effectively to achieve specific research objectives.

With remarkable learning capabilities and swift operational speeds, artificial intelligence (AI) can assist researchers in swiftly extracting valuable patterns, trends, and associations from subjective information. Tribological behaviors are characterized by dependence on systems, evolution with time, and multidisciplinary coupling. The friction process involves a variety of phenomena, including mechanics, thermology, electricity, optics, magnetics, and so on. Hence, tribological information possesses the distinct characteristics of being multidisciplinary, multilevel, and multiscale, so that the application of AI in tribology is highly extensive. To delineate the scope, classification, and recent trends of AI implementation in tribology, this review embarks on exploration of the tribology research domain. It comprehensively outlines the utilization of AI in basic theory of tribology, intelligent tribology, component tribology, extreme tribology, bio-tribology, green tribology, and other fields. Finally, considering the emergence of "tribo-informatics" as a novel interdisciplinary field, which combines tribology with informatics, this review elucidates the future directions and research framework of "AI for tribology". In this paper, tribo-system information is divided into 5 categories: input information (I), system intrinsic information (S), output information (O), tribological state information (T_s), and derived state information (D_s). Then, a fusion method among 5 types of tribo-system information and different AI technologies (regression, classification, clustering, and dimension reduction) has been proposed, which enables tribo-informatics methods to solve common problems such as tribological behavior state monitoring, behavior prediction, and system optimization. The purpose of this review is to offer a systematic comprehension of tribo-informatics and to inspire new research ideas of tribo-informatics. Ultimately, it aspires to enhance the efficiency of problem-solving in tribology.

H62 brass material is one of the important materials in the process of electrical energy transmission and signal transmission, and has excellent performance in all aspects. Since the wear behavior of electrical contact pairs is particularly complex when they are in service, we evaluated the effects of load, sliding velocity, displacement amplitude, current intensity, and surface roughness on the changes in contact resistance. Machine learning (ML) algorithms were used to predict the electrical contact performance of different factors after wear to determine the correlation between different factors and contact resistance. Random forest (RF), support vector regression (SVR) and BP neural network (BPNN) algorithms were used to establish RF, SVR and BPNN models, respectively, and the experimental data were trained and tested. It was proved that BP neural network model could better predict the stable mean resistance of H62 brass alloy after wear. Characteristic analysis shows that the load and current have great influence on the predicted electrical contact properties. The wear behavior of electrical contacts is influenced by factors such as load, sliding speed, displacement amplitude, current intensity, and surface roughness during operation. Machine learning algorithms can predict the electrical contact performance after wear caused by these factors. Experimental results indicate that an increase in load, current, and surface roughness leads to a decrease in stable mean resistance, while an increase in displacement amplitude and frequency results in an increase in stable mean resistance, leading to a decline in electrical contact performance. To reduce testing time and costs and quickly obtain the electrical contact performance of H62 brass alloy after wear caused by different factors, three algorithms (random forest (RF), support vector regression (SVR), and BP neural network (BPNN)) were used to train and test experimental results, resulting in a machine learning model suitable for predicting the stable mean resistance of H62 brass alloy after wear. The prediction results showed that the BPNN model performed better in predicting the electrical contact performance compared to the RF and SVR models.

Real-time monitoring of the friction coefficient of the moving parts of a machine system is a challenging problem. The development of intelligent perception and data technology provides the possibility to use tribological correlation information to predict the friction coefficient. This paper uses multi-source friction information such as sound during the friction and wear test to form a time-sectioned friction information data set, establishes a K-fold cross-validation double-stacked regression integration model, defines the evaluation indicators for scope evaluation, and the model was tested with a variety of load test data. The results showed that the model can effectively refine the correlation characteristics of friction information, so as to accurately fit and predict the friction coefficient, and has universality for data under different load conditions.

Tribology research mainly focuses on the friction, wear, and lubrication between interacting surfaces. With the continuous increase in the industrialization of human society, tribology research objects have become increasingly extensive. Tribology research methods have also gone through the stages of empirical science based on phenomena, theoretical science based on models, and computational science based on simulations. Tribology research has a strong engineering background. Owing to the intense coupling characteristics of tribology, tribological information includes subject information related to mathematics, physics, chemistry, materials, machinery, etc. Constantly emerging data and models are the basis for the development of tribology. The development of information technology has provided new and more efficient methods for generating, collecting, processing, and analyzing tribological data. As a result, the concept of "tribo-informatics (triboinformatics)" has been introduced. In this paper, guided by the framework of tribo-informatics, the application of tribo-informatics methods in tribology is reviewed. This article aims to provide helpful guidance for efficient and scientific tribology research using tribo-informatics approaches.

Metal matrix nanocomposites (MMNCs) become irreplaceable in tribology industries, due to their supreme mechanical properties and satisfactory tribological behavior. However, due to the dual complexity of MMNC systems and tribological process, the anti-friction and anti-wear mechanisms are unclear, and the subsequent tribological performance prediction and design of MMNCs are not easily possible: A critical up-to-date review is needed for MMNCs in tribology. This review systematically summarized the fabrication, manufacturing, and processing techniques for high-quality MMNC bulk and surface coating materials in tribology. Then, important factors determining the tribological performance (mainly anti-friction evaluation by the coefficient of friction (CoF) and anti-wear assessment with wear rate) in MMNCs have been investigated thoroughly, and the correlations have been analyzed to reveal their potential coupling/synergetic roles of tuning tribological behavior of MMNCs. Most importantly, this review combined the classical metal/alloy friction and wear theories and adapted them to give a (semi-)quantitative description of the detailed mechanisms of improved anti-friction and anti-wear performance in MMNCs. To guarantee the universal applications of these mechanisms, their links with the analyzed influencing factors (e.g., loading forces) and characteristic features like tribo-film have been clarified. This approach forms a solid basis for understanding, predicting, and engineering MMNCs’ tribological behavior, instead of pure phenomenology and experimental observation. Later, the pathway to achieve a broader application for MMNCs in tribo-related fields like smart materials, biomedical devices, energy storage, and electronics has been concisely discussed, with the focus on the potential development of modeling, experimental, and theoretical techniques in MMNCs’ tribological processes. In general, this review tries to elucidate the complex tribo-performances of MMNCs in a fundamentally universal yet straightforward way, and the discussion and summary in this review for the tribological performance in MMNCs could become a useful supplementary to and an insightful guidance for the current MMNC tribology study, research, and engineering innovations.

Friction plays a vital role in energy dissipation, device failure, and even energy supply in modern society. After years of research, data and information on tribology research are becoming increasingly available. Because of the strong systematic and multi-disciplinary coupling characteristics of tribology, tribology information is scattered in various disciplines with different patterns, e.g., technical documents, databases, and papers, thereby increasing the information entropy of the system, which is inconducive to the preservation and circulation of research information. With the development of computer and information science and technology, many subjects have begun to be combined with information technology, and multi-disciplinary informatics has been born. This paper describes the combination of information technology with tribology research, presenting the connotation and architecture of tribo-informatics, and providing a case study on implementing the proposed concept and architecture. The proposal and development of tribo-informatics described herein will improve the research efficiency and optimize the research process of tribology, which is of considerable significance to the development of this field.