PLPengpeng Li

Pengpeng 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


Pengpeng Li has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • 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.

  • 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.

  • A thermo-wear dual-parameter Wiener model approach for predicting the remaining useful life of wet friction components

    by Jianpeng Wu, Sanhu Su, Pengpeng Li, Liyong Wang, Shufa Yan, Shuai Han

    Wet friction components perform the critical function of transmission system and controlling torque within clutches, and their lifespan directly determines the stability and safety of wet clutches. Moreover, their primary failure modes are wear failure and thermal failure. In this context, this study conducts accelerated life testing on wet friction components to collect multi-dimensional degradation data and identifies corresponding failure thresholds. Subsequently, we construct the temperature and wear degradation parameters by integrating subjective and objective weighting approaches, enabling a comprehensive characterisation of the component’s degradation state. Thereafter, the Copula function is employed to analyse the dependency structure between the two degradation parameters, leading to the derivation of the joint probability density function of the remaining useful life (RUL). Finally, based on the inverse Gaussian distribution, a dual-parameter Wiener degradation model is developed. The model parameters are estimated using maximum likelihood estimation and Bayesian updating techniques, enabling effective RUL prediction for wet friction components. The results demonstrate that, within the critical degradation phase of 88 h–110 h, the dual-parameter Wiener degradation model yields a root mean square error of 3.053, which is significantly lower than those of the single-parameter models. In this stage, the prediction error is reduced by up to 46.83%. Furthermore, 72.73% of the model’s prediction errors fall within the 0%–10% range. Therefore, these findings confirm the accuracy and advantage of the proposed model in predicting the RUL of wet friction components.


  • Adaptive Multiobjective Shift Strategy for Heavy-Duty Vehicle Based on Performance State Evaluation of the Transmission Mechanism

    by Liyong Wang, Xiaozan Huang, Jianpeng Wu, Pengpeng Li

    Heavy tracked vehicles frequently operate in intricate and demanding driving conditions, where the powertrain, a core component, inevitably experiences performance degradation due to mileage accumulation. This degradation not only undermines vehicle reliability but also constrains the full utilization of its capabilities. To address these challenges, this study proposes a multi-objective optimization approach to developing an adaptive shift strategy that balances the vehicle’s power, fuel economy, and reliability performance. The optimization problem is tackled using the NSGA-II algorithm, which generates the Pareto front of shift speeds by considering the vehicle’s power, economy, and reliability performance. The optimal shift speeds are adaptively selected based on the transmission mechanism performance states, which are calculated using the fuzzy comprehensive evaluation model. During acceleration from 0 to 80 km/h, total friction work is reduced by 6.59% and 23% when the performance state scores are 70 and 40, respectively, compared to a score of 90. Additionally, the maximum jerk is reduced by 45.07% at a score of 40 compared to a score of 90. These reductions in friction work and jerk decrease wear on the transmission mechanism system, thus improving vehicle reliability.


  • The RUL prediction based on improved Wiener degradation model for wet friction components

    by Jianpeng Wu, Pengpeng Li, Liyong Wang, Xiaozan Huang, Jian Yang, Molin Du

    The wet clutch is a critical component of the comprehensive transmission system, and its reliability determines the stability of heavy equipment operation. As the core component of the wet clutch, the life of the wet friction components directly affects the reliability of the wet clutch. To accurately predict the wet friction components remaining useful life (RUL), an improved Wiener degradation model is established. Compared to traditional models, it sets drift parameters as random parameters to consider the randomness of degradation process. The life and degradation data of wet friction components are obtained through accelerated life test, and the composite degradation indicator is constructed by screening and fusing degradation data. Innovatively, we fuse life and degradation data to reduce early errors in RUL prediction of wet friction components. The result shows that the RUL prediction average absolute error of the improved Wiener degradation model is 0.31 h in the accelerated life range of 80 h–110 h, which verifies the accuracy of the model.