FJFei Jiang

Fei Jiang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Fei Jiang has a total of 69 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Direct numerical simulations of streamwise-aligned riblets: Investigations of the blockage ratio

    by Yue Zhang, Fei Jiang, Zhaoqian Wu, Zhi Zhong, Shaohui Zhang, Weihua Li

    Direct numerical simulation is employed to investigate turbulent flows over streamwise-aligned rectangular riblets in a half-channel at a friction Reynolds number of (Reτ) of 180. The effects of the blockage ratio BR = w/s (the ratio of riblet width to spacing) are examined for BR = 0.05–0.8 at three viscous-scaled spacings s+ = 20, 30, and 40, with a fixed height-to-spacing ratio h/s = 0.335. The results show that s+ is the primary parameter determining whether the surface reduces or increases drag, while BR plays a secondary modulating role. The mean velocity profiles confirm that the riblet influence is confined to the near-wall region and that outer-layer similarity persists for all geometries. Using the Fukagata–Iwamoto–Kasagi (FIK) identity, the total drag is decomposed into laminar, turbulent, and dispersive contributions. The dispersive term, arising from secondary flows (SFs), remains below 4% of the total drag for all cases. Pearson correlation analysis reveals that the turbulent contribution correlates strongly with s+, whereas the dispersive contribution exhibits a strong negative correlation with BR at each fixed s+. SF vortices induced by spanwise heterogeneity are an order of magnitude weaker than the background turbulence and diminish with increasing BR and decreasing s+. The spatial redistribution of turbulent kinetic energy production demonstrates a strong link between the geometric parameters (s+, BR) and vortex organization. Overall, the primary drag-modification mechanism is the direct interaction between riblet geometry and near-wall turbulence, with s+ governing the drag regime and BR controlling the spanwise flow heterogeneity.

  • GDTS-YOLOv8: Gather-and-Distribute Mechanism With Two-Stage Self-Fine-Tuning Strategy for Multiscale Capacitor Defect Detection Under Imbalanced Data

    by Gen Chen, Fei Jiang, Shaohui Zhang, Zhi Zhong, Zhaoqian Wu, Weihua Li

    Capacitors are essential in industrial applications due to their ability to store and release electrical energy rapidly. However, capacitors, with their complex manufacturing processes and heterogeneous characteristics, pose two critical challenges to conventional detection algorithms: 1) the difficulty in detecting small-scale defects amid multiscale defect variations and 2) the inherently imbalanced distribution of defects. To address these issues, the GDTS-YOLOv8 detection framework is introduced, which leverages a gather-and-distribute (GD) mechanism and a two-stage self-fine-tuning (TS) strategy with a frozen backbone. First, GD is constructed to enhance the efficiency of multiscale feature extraction and fusion in the YOLOv8 feature fusion layer. Centered on optimizing cross-level information exchange and reducing information loss, this mechanism can effectively address the issue of poor detection performance for small targets in multiscale scenarios. Second, TS is proposed to address the inherent imbalance problem, comprising: 1) a rare-defect upweighting pretraining stage with label reduction of frequent defects and 2) a full-data fine-tuning stage integrating label reintroduction of frequent defects with backbone freezing for optimal performance. Experimental results confirm the proposed method’s effectiveness, enhancing capacitor detection precision by over 5% (75.3% peak accuracy) and demonstrating significant improvements in small-defect detection and imbalanced sample handling.

  • Vibration modulation features of planetary gear train with cracked planet gear based on flexible transfer paths and signal convolution model

    by Yue Zhang, Jie Lai, Bo Zhao, Zuozhou Pan, Fei Jiang

    Fault mechanism feature analysis of planetary gear trains using vibration signals is of great significance. However, affected by numerous internal excitation forces and complex external transfer paths, the corresponding vibration features of planetary gear trains are weakened and become much more complicated, especially existing crack faults in gears. Aiming at resolving this problem, a rigid–flexible coupling dynamics model and a signal convolution model of planetary gear trains are proposed to reveal the vibration modulation mechanisms under a cracked state. Firstly, numerous internal excitation forces that are mainly derived from the meshing stiffness are calculated through a combination of the lumped parameter model and energy method. Secondly, multiple external transfer paths with full consideration of flexible housing are acquired by the finite-element-method, whose time-varying properties are described by modal parameters with clear physical meaning. Finally, based on the constructed signal convolution model, the full-band vibration signals with normal and cracked planet gears are synthesized through the convolution of multiple excitation and multiple paths. We conclude that three groups of resonance modulation features effectively indicate the planet crack state in simulations, and the corresponding vibration response mechanism is further revealed. The experimental signals of planetary gear trains also verify the correctness of the proposed models and the concluded modulation features.

  • Predicting surface pressure fields and lift coefficients of subsonic airfoils by machine-learning-enhanced compressive sensing framework

    by Yue Zhang, Shaohui Zhang, Fei Jiang, Zhaoqian Wu, Weihua Li

    Aerodynamic performance assessment is pivotal in aircraft design optimization, yet traditional airfoil optimization methods remain computationally expensive and inefficient. To address this challenge, we introduce a machine-learning-enhanced compressive sensing (ML-CS) framework that synergizes data-driven learning with compressive sensing to accurately predict surface pressure fields and lift coefficients of subsonic airfoils. A geometry-informed sparse sampling strategy is developed using airfoil camber-thickness curve parameterization, enabling efficient feature extraction from limited training data. The development of the ML-CS framework employs a three-stage process: first, the ML-CS reconstruction efficiency is optimized, achieving more than 92% accuracy in pressure coefficient prediction using only ten sparse sensors; second, a Kriging-surrogate-assisted sensor value prediction method that robustly preserves prediction accuracy despite missing sensor data is proposed; third, a lift coefficient prediction module that reduces errors by 35.5% compared to conventional surrogate models while simultaneously reconstructing surface pressure distributions is proposed. The framework demonstrates superior efficiency and generalizability, offering a paradigm shift in aerodynamic surrogate modeling.


  • Novel rolling bearing state classification method based on probabilistic Jensen–Shannon divergence and decision fusion

    by Zuozhou Pan, Xiyu Pan, Fei Jiang, Yang Guan, Zong Meng, Yuebing Wang, Peng Zhao

    To improve the accuracy of bearing state classification in multi-source monitoring environments, a novel decision fusion method based on probabilistic Jensen–Shannon (PJS) divergence and D-S evidence theory is proposed. Firstly, the initial state probability of each bearing is determined by the bearing state classification score value, and the basic probability assignment (BPA) value of each bearing state is set by obtaining the global credibility of each sensor based on the pre-network test results. Secondly, the PJS divergence is proposed on the basis of the Kullback Leibler (KL) divergence to measure the conflict between the data collected by each sensor, and the weight value of the BPA value of each sensor is reset according to the PJS divergence value, which improves the accuracy of the BPA value. Finally, the D-S evidence theory is used to fuse the BPA value of each sensor and obtain the final bearing state classification result. The experimental part shows the effectiveness using the bearing signals collected in the laboratory, and the generality of this paper’s method is verified by using it in conjunction with other networks.


  • MTSNN: A Few-Shot Fine-Grained Diagnosis Framework for Cross-Machine Fault Diagnosis With Heterogeneous Fault Categories

    by Jipu Li, Ke Yue, Zhaoqian Wu, Fei Jiang, Zhi Zhong, Shaohui Zhang, Weihua Li

    Deep learning (DL)-based intelligent fault diagnosis (IFD) methods are extensively used in mechanical systems. In practical industrial contexts, DL models are constrained by three primary limitations. (1) The performance of DL models heavily relies on a significant volume of high-quality labeled data during the training process. (2) The diagnostic capabilities of DL models are insufficient to handle the complex and variable conditions encountered in mechanical systems. (3) Current DL-based IFD approaches primarily focus on diagnosing coarse-grained faults, while less attention is given to fine-grained fault detection. In response to these limitations, a new Meta-Transfer Spiking Neural Network (MTSNN) is introduced for cross-machine fine-grained fault diagnosis in mechanical equipment. Firstly, a convolutional spiking neural network (CSNN) is constructed to extract the representative features from raw signals by leveraging the low energy consumption, native ability to process time-series data, and high robustness to noise of spiking neural network. Secondly, a novel comprehensive loss function called meta-prototype contrastive loss is proposed, which integrates prototypical learning loss, meta contrastive learning loss, and entropy information maximization loss, allowing the model to effectively transfer diagnostic knowledge across different machines in limited samples scenario. The experimental evaluation conducted on three datasets reveals that the proposed MTSNN significantly outperforms other methods in diagnosing faults, particularly when applied to different machines with heterogeneous fault categories.


  • A tool wear monitoring method driven by workpiece surface quality inversion and EfficientNet

    by Fei Jiang, Zejian Xiao, Xiaohui Yan, Zhaoqian Wu, Shaohui Zhang, Rizwan Ullah

    Tool wear status monitoring plays an important role in the safety of machine and the efficiency of production. Due to the limitation of sensor installation and complex operation conditions, traditional machine vision methods are difficult to directly act on the tool itself to obtain corresponding wear status information. Meanwhile, the surface quality of the machined workpiece can provide indirect insights into the wear status of the tool to a significant degree. Therefore, an indirect tool wear status monitoring method is proposed in this paper by workpiece surface quality inversion and EfficientNet. Firstly, the surface texture data of workpiece are obtained in the form of image by an industrial camera, and the representative features that indirectly reflect tool wear status are further highlighted by using the weighted average image grayscale and the Laplacian operator. Secondly, to monitor tool wear effectively, we have optimized three key settings, width, model depth, and input image resolution, of the EfficientNet backbone network. This optimization boosts its ability to understand and generalize, ensuring it can handle various surface textures and extract crucial information accurately. This, in turn, enhances the accuracy of our tool wear monitoring system. Finally, the improved EfficientNet network is further utilized as a pre-trained network to achieve tool wear state monitoring. Utilizing the powerful representation ability of the pre-trained model and the surface texture features of workpiece, the model can accurately identify and judge the wear degree of the tool. The tool experiment results show that the proposed tool wear monitoring method has achieved remarkable results with recognition accuracy of 97.77%. While other popular methods such as VGG19, ResNet50, and ResNet152, whose training accuracies are 95.66%, 96.37%, and 91.27%, respectively. The comparative results highlight the excellent performance of the proposed method in recognition rate, training time and generalization performance.