HSHongyan Sun

Hongyan Sun

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hongyan Sun has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TDRPFormer: Texture-Debiased Reliable Prototype Transformer for Pixel-Level Steel Surface Defect Segmentation

    by Mingxiang Zhu, Zhizhen Li, Hongyan Sun, Yu Wang, Jue Wang

    Steel surface defect segmentation is a critical task in industrial visual inspection, with direct implications for quality assessment, process control, and in-service safety. However, complex steel-surface images often contain strong background textures, local reflections, machining traces, and low-contrast defects, which cause existing methods to be distracted by normal textures and to produce false positives or missed detections in slender structures, blurred boundaries, and weak-response regions. To address these challenges, we propose a Texture-Debiased Reliable Prototype Transformer (TDRPFormer) for pixel-level steel surface defect segmentation. Within a query-driven mask prediction framework, TDRPFormer first derives pixel-level confidence and boundary cues from intermediate segmentation priors and then aggregates normal texture prototypes from high-confidence background regions. A Texture Debiasing Module (TDM) is introduced to suppress the interference of normal textures in defect representations. Next, a Reliable Prototype Routing (RPR) module compresses the debiased spatial features into a small set of high-reliability prototypes, thereby reducing ineffective interactions between queries and redundant background pixels. Finally, a Structural Continuity Modulation (SCM) module enhances high-resolution mask features, improving the recovery of slender defects, weak-response regions, and blurred boundaries. We conduct systematic experiments on the ESDIs-SOD and NEU-DET steel surface defect datasets. TDRPFormer achieves the best overall performance on both datasets. On ESDIs-SOD, the mean absolute error (MAE), weighted F-measure (Fβw), S-measure (Sα), and mean E-measure (mEξ) reach 0.0185, 0.8824, 0.9070, and 0.9626, respectively. On NEU-DET, the corresponding values are 0.0210, 0.8858, 0.9017, and 0.9662. Further ablation studies and response visualizations confirm the complementary roles of texture debiasing, reliable prototype routing, and structural continuity modulation. These results demonstrate that TDRPFormer improves discriminability, stability, and structural recovery under complex industrial backgrounds, providing an effective solution for pixel-level steel surface defect segmentation.

  • Open Access

    Bifurcation and Firing Behavior Analysis of the Tabu Learning Neuron with FPGA Implementation

    by Hongyan Sun, Yujie Chen, Fuhong Min

    Neuronal firing behaviors are fundamental to brain information processing, and their abnormalities are closely associated with neurological disorders. This study conducts a comprehensive bifurcation and firing-behavior analysis of an improved Tabu Learning neuron model using a semi-analytical discrete implicit mapping framework. First, a discrete implicit mapping is constructed for the Tabu Learning neuron, enabling high-precision localization of stable and unstable periodic orbits within chaotic regimes and overcoming the limitations of conventional time-domain integration. Second, an eigenvalue-centered analysis is used to classify bifurcation types and stability, summarized in explicit bifurcation tables that reveal self-similar offset bifurcation routes, coexisting periodic and chaotic attractors, and chaotic bubbling firing patterns. Third, the proposed neuron model and its discrete mapping are implemented on an FPGA platform, where hardware experiments faithfully reproduce the analytically predicted stable and unstable motions, thereby tightly linking theoretical analysis and digital neuromorphic hardware. Overall, this work establishes a unified analytical–numerical–hardware framework for exploring complex neuronal dynamics and provides a potential basis for neuromodulation strategies and neuromorphic computing system design.

  • Open Access

    Impacts of disturbances on bifurcation behaviors in an interconnected power systems

    by Hongyan Sun, Hanxi Liu, Biaoming Ye, Fuhong Min

    The reliable and stable operation of the power grid is crucial to the national economy, and the existing complex nonlinear phenomena related to disturbances, such as chaotic oscillation accompanied by bifurcation behaviors, are potential threats to safety and stability. Therefore, it is of great practical significance to explore the relationship among complex phenomena, chaos, and bifurcation in the power system. In this paper, the dynamical behaviors of a dual-machine interconnected power system are investigated in view of the constructed discrete mapping framework. Specifically, the bifurcation pathways from periodic motion to complex oscillations and even chaos, as well as their triggering conditions under different levels of load disturbance, are clearly revealed. The analysis of eigenvalues also provides an effective basis for fast and reliable prediction of bifurcation points. Hence, the results contribute to the understanding of the seemingly random oscillation or sudden voltage collapse in the power system caused by load disturbance and further provide a reference for the prevention and suppression of chaotic oscillations.

  • Open Access

    Analysis of Amplitude and Angle of Crosstalk in Frequency Domain of Three-Core Twisted Wires

    by Hongyan Sun, Wentao Xu, Wu Zhang, Mengxia Zhou, Wei Yan

    In this paper, a geometric model of multi-core twisted wire is established to analyze the amplitude-frequency and angular-frequency characteristics of crosstalk in electromagnetic compatibility (EMC). The random combination of the cross-section of the multi-core twisted wire is used to accurately simulate the randomness of the actual multi-core twisted wire. The rotation transformation of the cross-section and the random transposition transformation between the conductors and the neural network model are used to obtain the per unit length (p.u.l) parameters at any position. And bring it into the method of chain parameters to find the crosstalk. The results show that the crosstalk amplitude-frequency and angular-frequency characteristics of the different cores of the multi-core twisted wire under the fixed model are very similar. Under the random model, the crosstalk of multi-core twisted wires is very close in the low frequency range, and satisfies a certain envelope value in the high frequency range. Through comparison with full-wave simulation, the reliability of the proposed method is proved.


  • Research on Crosstalk Prediction of Stranded Cable Based on GA-BP Neural Network Algorithm

    by Hongyan Sun, Dong Xu, Shiding Wu, Wentao Xu, Zenan Chen, Guoqiang Wang

    Based on the research of genetic algorithm (GA) to optimize the Back propagation (BP) neural network algorithm, this paper proposes a method for predicting stranded wire crosstalk based on the algorithm. First, the equivalent circuit model of multi-conductor transmission line is established. Combined with the idea of modulus decoupling, the multi-conductor transmission line equation is solved. Then the mathematical model of the stranded wire is established and its structural characteristics are analyzed, and the GA-BP neural network algorithm is used to realize the mapping of the electromagnetic parameter matrix of the stranded wire and the position of the stranded wire. Finally, the mapping relationship is substituted into the transmission line equation, and the near-end crosstalk (NEXT) and the far-end crosstalk (FEXT) of an example three-core twisted wire are predicted based on the idea of cascade combined with the modulus decoupling method. By comparing with the transmission line matrix method (TLM), it can be seen that the method proposed in this paper is in good agreement with the crosstalk results obtained by the electromagnetic field numerical method, which verifies the effectiveness of the GA-BP neural network algorithm combined with modulus decoupling to predict the crosstalk of twisted wires.