BWBingkai Wang

Bingkai Wang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bingkai Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Research on the Bearing Remaining Useful Life Prediction Method Based on Optimized BiLSTM

    by Yi Zou, Wenlei Sun, Tiantian Xu, Bingkai Wang

    The predictive performance of the remaining useful life (RUL) estimation model for bearings is of utmost importance, and the setting method of the bearing degradation threshold is crucial for detecting its early degradation point, as it significantly affects the performance of the RUL prediction model. To solve these problems, a bearing RUL prediction method based on early degradation detection and optimized BiLSTM is proposed: an optimized VMD combined with the Pearson correlation coefficient is used to denoise the bearing signal. Afterward, multi-domain features are extracted and evaluated using different metrics. The optimal degradation feature is then selected. Furthermore, KPCA is used to integrate the features and establish the health indicators (HIs) for early degradation detection of bearings using a sliding window method combined with the 3σ (3-sigma) criterion and the quartile method. The RUL prediction model is developed by combining the BiLSTM network with the attention mechanism and by employing the SSA to adaptively update the network parameters. The proposed RUL prediction model is tested on various datasets to evaluate its generalization ability and applicability. The obtained results demonstrate that the proposed denoising method has high performance. The dynamic 3σ-threshold setting method accurately detects the early degradation points of bearings. The proposed RUL prediction model has high performance and fitting capacity, as well as very high generalization ability and applicability, enabling the early prediction of bearing RUL.


  • Open Access

    A Long-Time Series Forecast Method for Wind Turbine Blade Strain with Incremental Bi-LSTM Learning

    by Bingkai Wang, Wenlei Sun, Hongwei Wang

    This article presents a novel incremental forecast method to address the challenges in long-time strain status prediction for a wind turbine blade (WTB) under wind loading. Taking strain as the key indicator of structural health, a mathematical model is established to characterize the long-time series forecast forecasting process. Based on the Bi-directional Long Short-Term Memory (Bi-LSTM) framework, the proposed method incorporates incremental learning via an error-supervised feedback mechanism, enabling the dynamic self-updating of the model parameters. The experience replay and elastic weight consolidation are integrated to further enhance the prediction accuracy. Ultimately, the experimental results demonstrate that the proposed incremental forecast method achieves a 24% and 4.6% improvement in accuracy over the Bi-LSTM and Transformer, respectively. This research not only provides an effective solution for long-time prediction of WTB health but also offers a novel technical framework and theoretical foundation for long-time series forecasting.

  • Open Access

    Research on the Calculation Method for the Contact Stress of Wind Turbine Main Shaft Bearings Based on Finite Element Analysis

    by Yi Zou, Wenlei Sun, Hongwei Wang, Tiantian Xu, Bingkai Wang

    Under alternating loads, the contact situation for self-aligning roller bearings in the main shaft of a wind turbine is complex. Few methodologies exist for calculating the contact stress of main shaft bearings. We propose a method for calculating the contact stress of main shaft bearings in wind turbines; by simulating alternating loads that affect the turbine’s lifespan with a probability of 99%, analyzing the operational characteristics of the bearings under these loads using the roller slice method, and establishing a load–displacement model, this model serves as the boundary condition for contact stress simulation. We present the approach for building a three-dimensional finite element simulation model of contact stress, followed by model validation. The findings reveal that the maximum stress within the spindle bearing is concentrated in the contact zone, taking on an elliptical configuration. The maximum contact stress, as computed by the proposed method, amounts to 1356.3 MPa, and the bearing’s load-bearing performance adequately fulfills the design requirements. A comparative analysis with the calculation results documented in the existing literature shows that the average discrepancies in the computed outcomes for the roller’s contact with the inner and outer rings are 2.55% and 2.48%, respectively, and this validates the high reliability of the proposed approach. The research conducted in this thesis can further enhance the credibility of the contact stress calculation method for large-scale wind turbine spindle bearings.


  • Open Access

    Research on Bearing Remaining Useful Life Prediction Method Based on Double Bidirectional Long Short-Term Memory

    by Yi Zou, Wenlei Sun, Hongwei Wang, Tiantian Xu, Bingkai Wang

    The predictive capability of traditional bearing remaining useful life (RUL) prediction models is insufficient, and the prediction networks lack universality, leading to unsatisfactory results in predicting the RUL of bearings, which leads to untimely maintenance decisions and significant economic losses. In order to solve this problem, this study employs Discrete Wavelet Transform (DWT) to denoise vibration signals and extract multi-domain features; the weighted averages of monotonicity, predictability, trendability, and robustness indicators are first ranked for selecting sensitive feature subsets as inputs for RUL prediction, feature fusion is conducted using the Kernel Principal Component Analysis (KPCA) method to obtain the health index (HI) of the bearing, and the failure threshold of the signal is determined based on the 3-sigma principle. An RUL prediction model, which combines Double Bidirectional Long Short-Term Memory (DBiLSTM) with attention mechanism (A-DBiLSTM), is then developed, and the Bayesian approach is used to adaptively search for network hyperparameters. Experiments were conducted using the PHM2012 dataset and the XJTU-SY dataset; the results indicate that the proposed RUL prediction model demonstrates higher predictive performance, exhibits satisfactory performance across different datasets, and possesses good generalization capability and applicability. This method further enhances the predictive capability of bearing RUL estimation.


  • Open Access

    Intelligent Operation and Maintenance of Wind Turbines Gearboxes via Digital Twin and Multi-Source Data Fusion

    by Tiantian Xu, Xuedong Zhang, Wenlei Sun, Binkai Wang

    Wind turbine operation and maintenance (O&M) faces significant challenges due to the complexity of equipment, harsh operating environments, and the difficulty of real-time fault prediction. Traditional methods often fail to provide timely and accurate warnings, leading to increased downtime and maintenance costs. To address these issues, this study systematically explores an intelligent operation and maintenance method for wind turbines, utilizing digital twin technology and multi-source data fusion. Specifically, it proposes a remote intelligent operation and maintenance (O&M) framework for wind turbines based on digital twin technology. Furthermore, an algorithm model for multi-source operational data analysis of wind turbines is designed, leveraging a Whale Optimization Algorithm-optimized Temporal Convolutional Network with an Attention mechanism (WOA-TCN-Attention). The WOA is used to optimize the hyperparameters of the TCN-Attention model. Then, the gearbox fault alarm threshold and warning threshold are set using the statistical characteristics of the residual values, and the absolute value of the residuals is used to determine the abnormal operating state of the gearbox. Finally, the proposed method was validated using operational data from a wind farm in Xinjiang. With input data from multiple sources, including seven key parameters such as temperature, pressure, and power, the method was evaluated based on EMAE, ERMSE, and EMAPE. The results demonstrated that the proposed method achieved the smallest prediction error and provided effective early warnings 18 h and 33 min prior to actual failures, enabling real-time and efficient operation and maintenance management for wind turbines.


  • Open Access

    Fault Diagnosis of Wind Turbine Planetary Gear Based on a Digital Twin

    by Yi Wang, Wenlei Sun, Liqiang Liu, Bingkai Wang, Shenghui Bao, Renben Jiang

    Aiming at the problems of the traditional planetary gear fault diagnosis method of wind turbines, such as the poor timeliness of data transmission, weak visualization effect of state monitoring, and untimely feedback of fault information, this paper proposes a planetary gear fault diagnosis method for wind turbines based on a digital twin. The method was used to build the digital twin model of wind turbines and analyze the wind turbines’ operating state utilizing virtual and real data. Empirical mode decomposition (EMD) was used, and an atom search optimization–support vector machine (ASO-SVM) model was established for planetary gear fault diagnosis. The digital twin model diagnoses faults and constantly revises the model based on the diagnostic results. The digital twin fault diagnosis system was implemented in the Unity3D platform. The experimental results demonstrate the feasibility of the proposed early-warning system for the real-time diagnosis of planetary gear faults in wind turbines.


  • Open Access

    Location Determination of Impact on the Wind Turbine Blade Surface Based on the FBG and the Time Difference

    by Bingkai Wang, Wenlei Sun, Hongwei Wang, Yunfa Wan, Tiantian Xu

    This paper proposes an approach to the determination of the precise location of an impact on the surface of a wind turbine blade (WTB) based on a fiber Bragg grating (FBG) and the time difference, and its effectiveness is verified by experiments. First, the strain on the WTB surface is detected with an FBG. Then, the signal is decomposed into a series of components via variational mode decomposition (VMD), and some signals with impact characteristics are chosen for reconstruction. The instant energy of the reconstructed signal is then amplified through the Teager energy operator (TEO) to identify the time difference between FBGs. Finally, the coordinate of the impact point is obtained by solving the hyperbolic mode with the time difference. The results of experiments demonstrate that the proposed approach exhibits good performance with high accuracy (97%) and low error (12.3 mm).