XLXinzhi Li

Xinzhi 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


Xinzhi Li has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Lightweight Infrared Thermal Image Recognition Network with Thermal Noise Suppression and Dynamic Feature Fusion for Transformer Oil Leakage Detection

    by Wenbi Tan, Tzer Hwai Gilbert Thio, Fei Lu Siaw, Xinzhi Li, Fuyu Shen, Jiazai Yang, Tongyong Zou, Youdong Jia

    Detecting transformer oil leakage from infrared thermal images is challenging due to complex thermal backgrounds, low contrast, and sensor noise. To address these issues, this study proposes IR-OilNet, a lightweight CNN–Transformer fusion network designed for real-time infrared leakage detection in inspection robots. This research contributes to SDG 6 by preventing industrial water pollution resulting from transformer oil runoff, thereby protecting vital water sources in remote environments. The proposed framework integrates three key components: (1) a parameter-free Thermal Noise Suppression (TNS) module that reduces high-frequency thermal noise while preserving structural information; (2) a compact CNN backbone for local thermal texture extraction; and (3) a lightweight Transformer branch for global contextual modeling. To further enhance feature integration, a Dynamic Weight Fusion (DWF) module is introduced to adaptively balance local and global representations. Experiments on an expanded dataset of 2700 infrared thermal images demonstrate that IR-OilNet achieves an accuracy of 0.9992, F1-score of 0.9992, and AUC of 0.9993, while maintaining only 0.20 M parameters and 0.19 GFLOPs with real-time inference at 433 FPS. Compared with representative CNN and Transformer models, the proposed method achieves a superior trade-off between accuracy and computational efficiency, making it suitable for deployment in resource-constrained inspection systems.


  • Open Access

    A Hybrid CNN-SVM for Oil Leakage Detection in Transformer Monitoring

    by Wenbi Tan, Tzer Hwai Gilbert Thio, Fei Lu Siaw, Youdong Jia, Xinzhi Li, Jiazai Yang, Haijun Li

    Oil leakage in oil-immersed power transformers poses a significant threat to grid reliability, potentially causing severe electrical accidents and environmental pollution if not detected in time. Detecting oil leakage outdoors, however, remains challenging due to the impact of weather conditions such as fog, humidity, and rain, which obscure the leakage signs and complicate real-time detection. To address these challenges, we propose a solution that integrates infrared thermal imaging with a CNN-SVM hybrid architecture. The core of this approach lies in shifting from traditional Softmax-cross-entropy-based empirical risk minimization (ERM) to maximum-margin-based structural risk minimization (SRM). A fully fine-tuned MobileNetV3 transforms low-contrast, boundary-softened infrared thermal images—often affected by fog and moisture—into a more discriminative high-dimensional feature space, where positive and negative samples become linearly separable. This is followed by replacing Softmax with a linear SVM and using hinge loss to enforce a margin constraint, which maximizes the classification margin and improves robustness to input perturbations. Experimental results show that our proposed method outperforms all compared models, achieving an accuracy of 0.990, significantly higher than ResNet50_BCE (0.908), EfficientNetB0 (0.925), YOLOv11n-CLS (0.930), and ViT (0.929). In terms of F1-Score (0.989) and AUC (0.995), MobileNetV3-SVM also demonstrates excellent performance, ensuring outstanding classification capability. Additionally, the model achieves an inference latency of only 6.3 ms, demonstrating excellent real-time inference performance, highlighting its potential for transformer oil monitoring applications. This research contributes to SDG 6 by preventing industrial water pollution resulting from transformer oil runoff, thereby protecting vital water sources in remote environments.


  • Open Access

    Research on Magnetic Field of Permanent Magnet Rolls Arranged Periodically in Circumferential—Axial Direction

    by Yuhang Zhang, Mingjiang Jiang, Youdong Jia, Xinzhi Li, Zhengfang Li, Huihua Wang

    The separation of non-magnetic non-ferrous metals such as copper and aluminum from scrapped automobiles is a critical area of research due to the increasing number of end-of-life vehicles. Traditional eddy current separation methods have limitations, particularly in handling large-sized broken copper and aluminum parts. This paper proposes a novel magnetic roller model featuring a circumferential–axial periodic arrangement of permanent magnets. This study explores the external magnetic field distribution of this new roller design by constructing an equivalent current model, solving magnetic scalar potential equations, and employing simulation tools. The findings indicate that the new magnet array enhances both the magnetic field strength and the range of the external magnetic field, leading to improved separation efficiency of large-sized metal fragments. The results provide a theoretical basis for advancing the separation technology of large-sized broken copper and aluminum parts in scrapped automobiles, offering potential improvements in the recycling of non-ferrous metals from end-of-life vehicles.


  • Open Access

    Research on Citrus Fruit Freshness Detection Based on Near-Infrared Spectroscopy

    by Ling Chen, Youdong Jia, Jianrong Zhang, Lei Wang, Rui Yang, Yun Su, Xinzhi Li

    The study developed a novel method for evaluating the freshness of citrus fruits by integrating near-infrared spectroscopy with the non-linear data processing capabilities of a BP neural network. This approach utilizes specific wavelength analysis to distinguish between fresh and non-fresh fruits effectively. Advanced pre-processing techniques are employed to remove spectral anomalies, enhancing the network’s ability to accurately identify crucial quality indicators like sugar content. Concurrently, an experiment utilizing a mathematical computing software -based BP neural network optimized the number of hidden layer nodes, identifying 61 as optimal. This configuration achieves impressive indicators, including a mean square error of 0.0025665 and a root mean square error of 49.8214. More than 1000 training iterations were performed on 100 citrus samples, and the learning rate was 80%. The model demonstrated a high accuracy rate of 97.6275%, confirming its precision and reliability in assessing citrus freshness. This synergy between advanced neural network processing and spectroscopic techniques marks a significant advancement in agricultural quality assessment, setting new standards for speed and efficiency in data processing.