XZXingtuo Zhang

Xingtuo Zhang

*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


Xingtuo Zhang has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Diagnosis and Locating Method for PMSM Interturn Fault Using Less Search Coils

    by Chong Zeng, Li Wang, Xingtuo Zhang, Song Huang, Xiaoyuan Du, Xing Chen, Liang Huang

    Effective diagnosis of inter-turn fault (ITF) is crucial for ensuring motor reliability. Existing methods using search coils (SCs) have good diagnostic and locating performance, but they require a large number of SCs and have problems of complexity and high cost. Aiming at this issue, a novel online ITF diagnosis method, which require less SCs is proposed. The proposed method analyzes the SC fluxes generated by a single stator coil and estimates the healthy SC fluxes based on the stator currents. Then, the estimated SC fluxes are compared with the measured SC fluxes to determine whether ITF exists. Furthermore, the SC fluxes corresponding to the fault in each stator coil are analyzed, and the ITF is located by comparing it with the measured SC fluxes. Simulation and experiment results have shown that the proposed method can effectively diagnose ITF and locate the specific fault coil under different operating conditions and is unaffected by other motor faults. This method can reduce the number of SCs by 67%, effectively solving the problems of complexity and high cost of the traditional SC-based diagnosis methods.


  • FAFNet: An Overhead Transmission Line Component Detection Method Based on Feature Alignment and Fusion

    by Xingtuo Zhang, Yiyi Zhang, Kang Shen, Qi Fu, Huaze Shen

    To ensure the stability of the power supply, the paradigm of using unmanned aerial vehicles (UAVs) to capture images of overhead lines and then using visual recognition technology to identify components and their defects has become widespread. However, significant challenges remain in identifying components with different scales and high aspect ratios from complex backgrounds. From the perspective of feature representation, this paper proposes FAFNet, which includes two novel, simple, and effective modules: the feature alignment (FA) module and the light-weight shared convolutional image pyramid network (LSCIPN) module. FA solves the problem of feature misalignment when merging higher and lower level feature maps, and LSCIPN enhances the low-level detail information of the feature pyramid. The two modules work together to improve the multi-scale detection capability. By conducting extensive experiments on three datasets, namely CPLID, OTLID (constructed in this paper), and IDID, as well as on the VOC and COCO datasets for generic scenarios, we demonstrate the effectiveness and generalization performance of the proposed method. Concretely, FAFNet improved 3.3 mAP, 1.2 mAP, 5.7 mAP, 1.1 mAP, and 1.5 mAP in CPLID, OTLID, IDID, VOC, and COCO, respectively, compared to the baseline model. We hope that FAFNet could serve as an alternative solution for UAV inspection visual recognition systems in the power industry.


  • A Small-Sized Defect Detection Method for Overhead Transmission Lines Based on Convolutional Neural Networks

    by Qi Fu, Jiefeng Liu, Xingtuo Zhang, Yiyi Zhang, Yang Ou, Runnong Jiao, Chuanyang Li, Giovanni Mazzanti

    Insulator defect detection is essential to the reliable operation of overhead transmission lines. However, current automatic algorithms struggle to extract critical features due to the small size of insulator defects in inspection images, which may lead to potential failures. To address this issue, this paper proposes a novel and high-accuracy defect detection method based on deep learning technology, named insulator defect detection network (I2D-Net), which incorporates several innovative modules. First, we design a three-path feature fusion network (TFFN) to improve the network’s ability to extract features from shallow layers. This hierarchical feature fusion mechanism across different network layers preserves spatial and semantic information, thereby maintaining the quality of features at different levels of the pyramid. Second, an enhanced receptive field attention (RFA+) block is incorporated to enable the network to adapt to different-scale defects and effectively distinguish them from the background. Finally, the context perception module (CPM) is introduced to better understand the surrounding features and their relationship with the defects. This improves defect localization capacity in the presence of interfering factors. Experimental results on the transmission line dataset demonstrate that the proposed method can accurately detect insulator defects and electrical components, even in challenging scenarios.


  • Sawtooth-Based FDS for Rapid and Accurate Testing of Transformer Oil–Paper Insulation

    by Xinyang Mao, Yiyi Zhang, Xingtuo Zhang, Wenbo Zhong

    Frequency domain spectroscopy (FDS) is a common nondestructive test method for insulation diagnosis of a transformer. Rapid and accurate testing can help improve the efficiency of FDS. However, the long test duration of conventional FDS and the unsatisfactory accuracy of existing accelerated FDS methods limit the application of insulation conditions of transformers. To tackle these problems, a new testing method named sFDS is proposed, aiming to achieve rapid and accurate testing. The proposed sFDS consists of two main parts to achieve the goal: first, the test duration is reduced by using sawtooth and regression analysis. Second, to ensure test accuracy, a multidomain signal accurate processing technique is proposed. Specifically, first, a filtering algorithm is used to isolate the noise. Second, the phase correction is used to improve the precision of time-frequency conversion. Third, the line interpolation method is utilized to accurately extract spectral data to compute dielectric loss and complex capacitance. To verify the practicality of sFDS, an sFDS test platform is built and compared with existing accelerated FDS techniques through practical experiments. The results indicate that sFDS performs superiorly in rapidity and accuracy. Meanwhile, sFDS has the potential to become a general method for evaluating more electrical objects.


  • Electrical Insulator Surface Condition Analysis Based on Joint Fully Convolutional and Multiscale Spatial Pooling Attention Network

    by Xingtuo Zhang, Yiyi Zhang, Alu Xu, Chunli Meng, Zhonghuan Su

    Health condition monitoring of insulators is one of the key factors to ensure a stable power supply. This article proposes an automated insulator surface condition analysis approach based on vision measurement and convolutional neural network (CNN). Specifically, we consider the condition analysis of insulators as an image multiclassification problem. An insulator image is first fed into a feature extractor, implemented by leveraging CNN, to extract features automatically. Then a Softmax classifier is utilized to map the feature representation into a probability vector to obtain the analysis results. Considering that not each layer nor each location of features has the same impact on classification performance, we further focus on feature relationships and present a novel attention architectural unit, called the joint fully convolutional and multiscale spatial pooling (JFCMSPA) attention module. This new attention module not only considers the friendly fusion of different pooled information, but also introduces the local similarity property of images into visual attention for the first time. These new insights allow it to efficiently learn feature importance. Finally, experimental results demonstrate the effectiveness of the proposed method and the value of its application in the inspection of power equipment.


  • Research on Time Saving and Accurate Testing Techniques for Frequency Domain Spectroscopy of Transformer Oil–Paper Insulation

    by Yiyi Zhang, Xinyang Mao, Xingtuo Zhang, Chuqi Xu, Gang Wang, Sheng Li

    Frequency domain spectroscopy (FDS) is a nondestructive insulation test method that has been widely applied to the insulation evaluation of power transformers. However, a major shortcoming of conventional FDS is the long test duration. Existing studies on accelerated FDS tests suffer from a lack of accuracy and are difficult to apply to field testing. To tackle this problem, a novel FDS test method (named iFDS) is proposed to reduce the duration and improve the accuracy of the oil–paper insulation test. Specifically, the test duration is reduced first by signal superposition and waveform prediction. Then, the test accuracy is improved from the aspects of the parameters design of excitation, the optimization of the test process, and time–frequency-domain data processing. Finally, a test platform is built based on the above methods to implement iFDS testing. To verify the effectiveness of iFDS, the dielectric parameters (tan $\boldsymbol {\delta }$ and $C\ast$ ) of oil–paper insulation were measured using the iFDS platform and compared with that of the existing FDS methods in terms of duration and accuracy. Comparative experimental results show that iFDS is a superior method for saving time and accurate testing and has the potential to be versatile for evaluating more insulation objects.


  • Study on Space Charge Characteristics of Transformer Insulating Paper Under Different Working Conditions

    by Yiyi Zhang, Gang Wang, Xingtuo Zhang, Wenbo Zhong, Zhicheng Su, Chuqi Xu, Running Wang, Xinyang Mao, Jiefeng Liu

    The space charge effect of transformer insulating paper will distort its internal electric field, and its space charge effect will be more prominent under extremely complex working conditions. At present, the micromechanism of charge transport and electric field distortion characteristics of paperboard are not clear under complex working conditions. So in this article, based on the bipolar carrier transport (BCT) model and the dynamic carrier balance model, the effects of high temperature, aging degree, moisture content, and bent degree on charges accumulation in paperboard are studied under dc high voltage by numerical simulation and the measured data needed for simulation. The results show that the higher temperature strengthens the carrier migration, deepens the injection depth of the charge, and aggravates the distortion of electric field intensity in paperboard. The more extended the aging time of paperboard, the greater the internal trap density and the deeper the trap depth, which lead to charges migration difficultly. Increasing water content in the paperboard will accelerate space charges to reach a steady state, while further increasing it will slow down this process, which is related to the shallow trap getting deeper. When the critical part of paperboard is extruded, many traps are introduced, resulting in charges accumulation seriously. The research results can reference the design of paperboard and the maintenance of transformer insulation system.


  • InsuDet: A Fault Detection Method for Insulators of Overhead Transmission Lines Using Convolutional Neural Networks

    by Xingtuo Zhang, Yiyi Zhang, Jiefeng Liu, Chaohai Zhang, Xueyue Xue, Heng Zhang, Wei Zhang

    One of the key tasks of the overhead line power equipment inspection based on aerial images acquired by unmanned aerial vehicles is to determine whether the insulators are faulty. However, the fault area on the insulator string occupies a relatively small portion of the entire image, which will make detection difficult. This article presents an intelligent fault detection method for overhead line insulators based on aerial images and improved you only look once (YOLOv3) deep learning technology. In our model, a densely connected feature pyramid network (FPN) is proposed. First, this network can improve the utilization rate of the strong semantic information of deep features and the localization information of shallow features, thereby improving the small insulator fault (missing-cap) detection performance of the YOLOv3 model. Second, this network reduces the number of parameters of the YOLOv3 model, resulting in a low risk of network over-fitting for small datasets. The experimental results on the CPLID dataset show that our model has higher detection accuracy in localization of overhead line insulators and detection of insulator missing-cap faults compared with the existing works.