HLHeyan Li

Heyan Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Heyan Li has a total of 12 co-authors. Here are the top co-authors by number of shared publications:

  • Jianpeng Wu

    Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, Beijing Information Science and Technology University, Beijing, China

    4 shared publications
  • Liyong Wang

    Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, Beijing Information Science and Technology University, Beijing, China

    4 shared publications
  • Sanhu Su

    Beijing Information Science and Technology University The College of Mechanical and Electrical Engineering Haidian-qu and The Key Laboratory of Modern Measurement and Control Technology of Ministry of Education, Beijing Information Science and Technology University, Haidian-qu, China

    3 shared publications
  • Pengpeng Li

    Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, Beijing Information Science and Technology University, Beijing, China

    2 shared publications
  • Ao Ding

    Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, Beijing Information Science and Technology University, Beijing, China

    1 shared publication
  • Chunhui Wei

    Beijing Institute of Technology School of Mechanical Engineering , Haidian-qu

    1 shared publication

Latest Publications

  • Evolutionary characteristics of fretting wear behaviour in stainless-steel materials for vehicle drivetrain systems

    by Jianpeng Wu, Sanhu Su, Wenya Shu, Heyan Li, Chunhui Wei, Liyong Wang

    Purpose: This study aims to clarify the coupled evolution of frictional hysteresis, energy dissipation, contact stiffness and surface damage in self-mated SS304 rough flat-on-flat fretting contacts. Design/methodology/approach: Self-mated SS304 specimens are tested at five durations. Hysteresis loops, dissipated energy, coefficient of friction (µ), tangential contact stiffness (Kt), gross-slip stiffness (Kp), surface topography and wear morphology are analysed. An energy-dependent Bouc–Wen model is developed to describe the evolution of the hysteretic response. Findings: Kp, Kt and µ generally increase with cumulative dissipated energy. Surface roughness and height distribution evolve progressively, while wear morphology develops from regular grooves to ploughing, plastic smearing, local detachment and debris redistribution. The proposed model reproduces the hysteresis response with an root mean square error of 1.2 N, Normalized root mean square error of 1.0%, R2 of 0.98 and loop-area error of 2.5%. Originality/value: The study establishes cumulative dissipated energy as an effective parameter for linking frictional response, contact stiffness and surface damage and provides an energy-dependent framework for modelling the wear-induced evolution of fretting hysteresis in self-mated SS304 contacts.

  • A self-adaptive PINN for hidden-state degradation feature learning and remaining useful life prediction of wet friction components

    by Jianpeng Wu, Sanhu Su, Heyan Li, Liyong Wang

    Wet friction components serve as critical elements in clutch systems for powertrain and torque regulation, and their remaining useful life (RUL) prediction is of great significance for ensuring the reliable operation of transmission systems. Traditional data-driven methods fall short in fully characterizing the underlying physical degradation mechanisms, while purely physics-based models are often limited by inaccessible parameters and modelling complexity. To address these challenges, the present work proposes a Transformer-based self-adaptive physics-informed neural network (Transformer-SAPINN) for RUL prediction of wet friction components. The proposed approach first employs a Transformer encoder structure to capture temporal dependencies and inter-feature interactions in degradation signals. Moreover, a physics-guided regulator (PGR) is developed to self-adaptively learn the unknown nonlinear partial differential equation (PDE) that governs the degradation evolution, and this physics prior is embedded into the PINN framework. Furthermore, the method introduces a task uncertainty-based adaptive weighting mechanism, which dynamically adjusts the relative contributions of the data and physics loss terms throughout training. Results indicate that the proposed method achieves superior performance compared with other models, with the highest coefficient of determination ( R 2 ) reaching 0.9978, and reductions in mean absolute error ( MAE ) and root mean square error ( RMSE ) up to 89.33% and 85.23%, respectively. Ablation studies reveal that, compared with the model without Transformer, MAE and RMSE are reduced by 65% and 68%, respectively. Furthermore, interpretability analysis identifies the Thickness, maximum circumferential temperature difference ( T c ) and maximum radial temperature difference ( T r ) as the three most critical indicators influencing lifetime prediction.

  • Multi-parameter data–mechanism collaborative framework for remaining useful life prediction of wet friction components based on adaptive staged Wiener process

    by Jianpeng Wu, Kexin Xing, Heyan Li, Sanhu Su, Pengpeng Li

    Wet friction components are a key part of heavy-duty transmission systems, and accurate remaining useful life (RUL) prediction is essential for equipment reliability. To overcome the limitations of existing methods in adaptive stage division, multi-source feature extraction, and data–mechanism fusion, this paper proposes a convolutional neural network (CNN)–bidirectional long short-term memory (BiLSTM)–attention–Wiener RUL prediction framework. Accelerated degradation tests are conducted to obtain temperature differences, thickness, and Fe/Cu concentrations. A dynamic-threshold adaptive membership function divides the degradation stages, while CNN-BiLSTM-Attention extracts multi-source coupled degradation features. A multi-stage Wiener process is then introduced to describe the stochastic degradation evolution and prediction uncertainty. In addition, the Wiener prediction error is used as feedback, and Adam optimizes the network parameters and composite health indicator mapping, achieving collaborative updating between the data-driven and mechanism-based models. The proposed method achieves a mean absolute error (MAE) of 1.162 h, with a confidence interval of 1.076–1.248 h, demonstrating high prediction accuracy, stability, and engineering applicability.

  • MTL-PINN: an uncertainty-weighted multi-task learning physics-informed neural network for two-dimensional transient temperature field prediction in wet friction components

    by Jianpeng Wu, Jiazhe Wang, Hanshu Zhang, Heyan Li, Liyong Wang

    High power density wet friction components serve as critical transmission components in heavy-duty equipment, and thermal failure induced by prolonged sliding under extreme conditions significantly undermines operational stability. Therefore, accurate prediction of interface temperature and analysis of thermal field characteristics hold substantial engineering value for improving system reliability. To investigate the spatiotemporal evolution and distribution characteristics of the friction interface temperature field, a physics-informed neural network is constructed by integrating neural networks with the two-dimensional transient heat conduction theory of wet friction components that accounts for the time-varying characteristics of key thermodynamic parameters. Data supervision is further incorporated to enhance the model’s capability to characterize the actual temperature evolution process. Meanwhile, the uncertainty-based multi-task learning loss weighting mechanism is introduced to enable the simultaneous optimization of constraint weights and network parameters, thereby achieving dynamic balancing and coordinated optimization among multiple constraint loss terms. In addition, the systematic evaluation of the model architecture and constraint mechanisms is carried out through the multi condition degradation experiment. The model is trained using 64 000 spatiotemporal collocation points and evaluated using 40 temperature measurement points for validation. Results demonstrate that the proposed model markedly improves the prediction accuracy of the temperature field in wet friction components, with a mean absolute percentage error of 0.224%, a relative squared error of 1.884%, and a coefficient of determination of 0.981. Moreover, the model achieves an average computational speed of 37 it/s. The temperature field exhibits a radial distribution that first increases and then decreases from the inner radius to the outer radius, with the highest temperatures observed in the mid-outer regions. Furthermore, the multi condition degradation experiment confirms the validity of the model framework as removing any constraint leads to reduced prediction accuracy and degraded convergence behavior.

  • A Remaining Useful Life Prediction Method of Wet Friction Component Based on Data-Model Interactive Framework

    by Jianpeng Wu, Ao Ding, Pengpeng Li, Heyan Li, Liyong Wang, Shuai Han

    The reliability of wet clutches is critical to the efficient operation of heavy equipment, as the lifespan of the wet friction component directly impacts the clutch’s stable performance. To accurately predict the remaining useful life (RUL) of wet friction components and to address the overfitting and poor robustness often observed in single models, this study proposes an innovative framework that integrates a neural network with a Wiener process model, thereby establishing a novel data–model interaction architecture. The framework gathers multidimensional degradation data from accelerated life tests and uses Particle Swarm Optimization (PSO) and Long Short-Term Memory (LSTM) to derive a composite health index. Subsequently, the composite health index is modeled using the Wiener Degradation Process (Wiener) to estimate the RUL. An objective function based on the prediction error is then defined, and the Adam algorithm adjusts the framework parameters dynamically to minimize this function and improve the RUL prediction accuracy. The prediction results suggest that the mean relative error (MRE) of this model is only 4.47%, confirming its accuracy. This method provides a more reliable RUL prediction solution for wet friction component based on artificial intelligence.