Jianwei Wu

Jianwei Wu


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2025 in Energies
Verified
Journal Article
Open access
PDF file
JZJian Zhang
Jian Zhang
JWJiajin Wang
Jiajin Wang
HLHongbo Li
Hongbo Li
QZQin Zhang
Qin Zhang
HXHe Xiangning
He Xiangning
JWJianwei Wu
Jianwei Wu
The thermal aging of insulation systems in electrical machines is a critical factor influencing their reliability and lifetime, particularly in modern high-performance electrical equipment. However, evaluating and predicting insulation lifetime under thermal aging poses significant challenges due to the complex aging mechanisms. Thermal aging not only leads to the degradation of macroscopic properties such as dielectric strength and breakdown voltage but also causes progressive changes in the microstructure, making the correlation between aging stress and aging indicators fundamental for lifetime evaluation and prediction. This review first summarizes the performance indicators reflecting insulation thermal aging. Subsequently, it systematically reviews current methods for reliability assessment and lifetime prediction in the thermal aging process of electrical machine insulation, with a focus on the application of different modeling approaches such as physics-of-failure (PoF) models, data-driven models, and stochastic process models in insulation lifetime modeling. The theoretical foundations, modeling processes, advantages, and limitations of each method are discussed. In particular, PoF-based models provide an in-depth understanding of degradation mechanisms to predict lifetime, but the major challenge remains in dealing with complex failure mechanisms that are not well understood. Data-driven methods, such as artificial intelligence or curve-fitting techniques, offer precise predictions of complex nonlinear relationships. However, their dependence on high-quality data and the lack of interpretability remain limiting factors. Stochastic process models, based on Wiener or Gamma processes, exhibit clear advantages in addressing the randomness and uncertainty in degradation processes, but their applicability in real-world complex operating conditions requires further research and validation. Furthermore, the potential applications of thermal lifetime models, such as electrical machine design optimization, fault prognosis, health management, and standard development are reviewed. Finally, future research directions are proposed, highlighting opportunities for breakthroughs in model coupling, multi-physical field analysis, and digital twin technology. These insights aim to provide a scientific basis for insulation reliability studies and lay the groundwork for developing efficient lifetime prediction tools.

18 December 2023 in Journal of Mechanical Design
Verified
Journal Article
Closed access
PDF file
WHWeifei Hu
Weifei Hu
FZFeng Zhao
Feng Zhao
XDXiaoyu Deng
Xiaoyu Deng
FCFeiyun Cong
Feiyun Cong
JWJianwei Wu
Jianwei Wu
JTJianrong Tan
Jianrong Tan

26 March 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JWJiajin Wang
Jiajin Wang
JWJianwei Wu
Jianwei Wu
JZJian Zhang
Jian Zhang
QZQin Zhang
Qin Zhang
YFYoutong Fang
Youtong Fang
Xiaoyan HuangXiaoyan Huang
Xiaoyan Huang
The degradation process of high-reliability products commonly has two-phase characteristics. For such products, accurate change point estimation and proper degradation model play crucial roles in remaining useful life (RUL) prediction. However, due to the long-lifetime nature of high-reliability products, lacking sufficient condition monitoring data will result in inaccurate parameter estimation, which further leads to a large error in RUL prediction. To address the issue, this paper proposes a RUL prediction method that integrates two-phase accelerated degradation data and field information. Specifically, change points are estimated based on accelerated degradation data, which effectively solves the difficulty of deriving the change point distribution owing to the lack of data. On this basis, a two-phase degradation model considering change point distribution is proposed by combining Wiener process and acceleration equation, which can be extrapolated to predict the lifetime at any stress level. In addition, taking the accelerated degradation data as prior information, all model parameters are updated by integrating field information using Bayesian method. When new change points are detected, their distribution is also updated to improve the accuracy of next individual RUL prediction. The effectiveness of the proposed method is validated through simulation studies and empirical analysis of motor insulation.

31 July 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
QZQin Zhang
Qin Zhang
JWJianwei Wu
Jianwei Wu
JWJiajin Wang
Jiajin Wang
Xiaoyan HuangXiaoyan Huang
Xiaoyan Huang
YFYoutong Fang
Youtong Fang
JZJian Zhang
Jian Zhang
Currently, most existing remaining useful life (RUL) prediction models for generators’ main wall insulation (MI) focuses on the statistical life distributions for a large population of products. The shortcoming of these models is that they cannot incorporate individual degradation information of a single product. To address the challenge of fusing common and individual degradation information, this paper proposes a digital-twin-driven two-phase RUL prediction model, composing of three parts: common representation model (CRM), individual representation model (IRM), dynamic evolution model. The proposed digital twin framework integrates the Wiener process model, Kalman filtering (KF) algorithm, and support vector machine (SVM) model. Specifically, a CRM based on two-phase Wiener process was established to reflect common features. Then, with CRM acting as the state equation, an IRM was established based on KF, which can fuse MI’s individual degradation information with common degradation information to reflect the individual features of single product. Additionally, SVM is utilized to address the issue that the covariance matrix of KF algorithm cannot be updated in prediction domains of long-life products, achieving the dynamic evolution of the digital twin system. Finally, the effectiveness and engineering application value of the model were verified through experiments.

15 November 2024 in Measurement Science and Technology
Verified
Journal Article
Closed access
FXFan Xu
Fan Xu
JWJianwei Wu
Jianwei Wu
DHDuo Hong
Duo Hong
FZFeng Zhao
Feng Zhao
JWJunhui Wu
Junhui Wu
WHWeifei Hu
Weifei Hu
Various data-driven methods based on acoustic emission (AE) signals have been proposed to monitor and accurately identify the wear stages of the grinding wheel. However, extracting effectively generalized and discriminative features from AE signals remains a challenging task. This paper proposes a new lightweight hybrid deep learning model that combines enhanced convolution with enhanced vision transformer (ViT) to effectively address the above challenges. Specifically, the key contributions of this paper are three-fold: (1) A two-stage signal preprocessing mechanism based on variational mode decomposition and continuous wavelet transform is proposed to improve the signal-to-noise ratio and feature representation of the AE signals. (2) To prevent model overfitting, a new regularization strategy based on stabilizing sparse convolutional weights and a weight penalty mechanism is designed. This approach improves the hybrid mode’s capacity to extract generalized features. (3) To concentrate on capturing multi-scale discriminative features between different wear conditions, a parameter-efficient residual convolution module based on the dropout depthwise convolution is designed, which is utilized to reconstruct the encoder of the ViT. In particular, to improve the training efficiency of the model, a lightweight mechanism using a stage-stride decreasing strategy is used to compress the spatial dimensions of the feature maps in the attention mechanism. The ablation experiment demonstrates the rationality of the proposed model structure. Comparative experiments show that the proposed method achieves a diagnostic accuracy of 99.6% on the test set and outperforms other state-of-the-art deep learning methods.

7 June 2018 in International Journal of Technology and Design Education
Verified
Journal Article
Closed access
PDF file
YJYu Ji
Yu Ji
QQqy qiu
qy qiu
PFPeien Feng
Peien Feng
JWJianwei Wu
Jianwei Wu