Context-enhanced multi-target semantic perception algorithm for power defect detection

doi:10.3785/j.issn.1008-973X.2026.10.010

Journal of ZheJiang University (Engineering Science)

2026, Vol. 60

Issue (10): 2176-2185 DOI: 10.3785/j.issn.1008-973X.2026.10.010

Context-enhanced multi-target semantic perception algorithm for power defect detection

Xin HU1(

),Xiyue YAN1,Yashu CHANG1,Hongliang CHENG2,Jian XIAO2,*(

),Shiwei LUO3,Liang MA3

1. School of Energy and Electrical Engineering, Chang’an University, Xi’an 710018, China
2. School of Electronic and Control Engineering, Chang’an University, Xi’an 710064, China
3. Shaanxi Hechang Electromechanical Equipment Co. Ltd, Xianyang 712000, China

Download:

HTML

PDF(3207KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

The Electric_Data inspection dataset was constructed, and a PDD-SPCIE algorithm based on context information enhancement and multi-target semantic perception was proposed within the RT-DETR framework, in order to improve the detection accuracy of multi-category power defects in complex substation inspection scenarios. The LDDM-ResNet module was designed to extract high- and low-frequency detailed features through multi-kernel parallel convolution. The DA-Encoder module was constructed to enhance the representation of multi-scale and irregularly shaped targets by incorporating deformable attention and dynamic sampling. The LGCA module was introduced to fuse global and local features using atrous convolution and spatial depth transformation convolution. The original framework was improved from the aspects of feature representation, context modeling, and feature fusion, thus enhancing the unified detection ability for multiple defect categories. Experimental results showed that the proposed model achieved a precision of 0.819, a recall of 0.681, and an mAP₅₀ of 0.704 on the self-built dataset, and a precision of 0.719, a recall of 0.642, and an mAP₅₀ of 0.712 on the VOC dataset.

Key words： substation power defect inspection deep learning DETR object detection algorithm context information enhancement multi-target semantic perception

Received: 26 August 2025 Published: 28 July 2026

CLC:

TM 721

Fund: 陕西省秦创原“科学家+工程师”队伍建设项目（2024QCY-KXJ-161）;咸阳市重大科技创新专项（人工智能）（L2025-ZDKJ-ZDGG-RGZN-005）.

Corresponding Authors: Jian XIAO E-mail: huxin@chd.edu.cn;xiaojian@chd.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xin HU
	Xiyue YAN
	Yashu CHANG
	Hongliang CHENG
	Jian XIAO
	Shiwei LUO
	Liang MA

Cite this article:

Xin HU,Xiyue YAN,Yashu CHANG,Hongliang CHENG,Jian XIAO,Shiwei LUO,Liang MA. Context-enhanced multi-target semantic perception algorithm for power defect detection. Journal of ZheJiang University (Engineering Science), 2026, 60(10): 2176-2185.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2026.10.010 OR https://www.zjujournals.com/eng/Y2026/V60/I10/2176

基于上下文增强与多目标语义感知的电力缺陷检测算法

为了提升复杂变电站巡检场景下多类别电力缺陷的检测精度，构建电力缺陷巡检数据集Electric_Data，并基于RT-DETR框架提出基于上下文信息增强与多目标语义感知的PDD-SPCIE算法. 设计LDDM-ResNet网络，通过多核并行卷积提取高低频细节特征；设计DA-Encoder模块，通过可变形注意力和动态采样增强多尺度、形态不规则目标的特征表达；设计LGCA模块，通过空洞卷积和空间深度转换卷积实现全局-局部特征融合. 上述模块分别从特征表达、上下文建模与特征融合3方面对原框架进行改进，增强了模型对多类别缺陷的统一检测能力. 实验结果表明，该模型在自建数据集上的精确度、召回率和mAP₅₀分别为0.819、0.681和0.704，在VOC数据集上的精确度、召回率和mAP₅₀分别为0.719、0.642和0.712.

关键词： 变电站电力缺陷巡检, 深度学习, DETR目标检测算法, 上下文信息增强, 多目标语义感知

Tab.1 Defect types and sample distribution of Electric_Data

Fig.1 LDDM-ResNet model framework

Fig.2 Structure of high-low frequency convolution module

Fig.3 Flowchart of DA-Encoder module

Fig.4 Structure of LGCA module

Fig.5 Overall framework of PDD-SPCIE

Tab.2 Experimental environment configuration

Tab.3 Channel-ratio experiment of high-low frequency convolution module

Tab.4 Multi-kernel combination experiment（LDDM-ResNet）

Tab.5 Dilation rate parameter experiment of atrous convolution for LGCA module

Tab.6 Ablation experiment results on Electric_Data

Tab.7 Comparison experiments of network models

Tab.8 Comparison of core modules and mainstream methods

Fig.6 Comparison of visual effects


[1]	李鹏, 刘念, 胡秦然, 等 “新型电力系统数字化关键技术综述”专辑评述[J]. 电力系统自动化, 2024, 48 (6): 1- 12 LI Peng, LIU Nian, HU Qinran, et al Commentary on special issue of reviews on key technologies for digitalization of new power system[J]. Automation of Electric Power Systems, 2024, 48 (6): 1- 12 doi: 10.7500/AEPS20240201001

[2]	李运堂, 李恒杰, 张坤, 等基于新型编码解码网络的复杂输电线识别[J]. 浙江大学学报: 工学版, 2024, 58 (6): 1133- 1141 LI Yuntang, LI Hengjie, ZHANG Kun, et al Recognition of complex power lines based on novel encoder-decoder network[J]. Journal of Zhejiang University: Engineering Science, 2024, 58 (6): 1133- 1141

[3]	周远翔, 陈健宁, 赵亮, 等电力设备数智化发展历程与大语言模型智能体应用展望[J]. 高电压技术, 2025, 51 (8): 4089- 4109 ZHOU Yuanxiang, CHEN Jianning, ZHAO Liang, et al Evolution of digitization and intelligence of power equipment and prospects for application of large language model based agent[J]. High Voltage Engineering, 2025, 51 (8): 4089- 4109

[4]	刘传洋, 吴一全基于深度学习的输电线路视觉检测方法研究进展[J]. 中国电机工程学报, 2023, 43 (19): 7423- 7445 LIU Chuanyang, WU Yiquan Research progress of vision detection methods based on deep learning for transmission lines[J]. Proceedings of the CSEE, 2023, 43 (19): 7423- 7445 doi: 10.13334/j.0258-8013.pcsee.221139

[5]	GIRSHICK R. Fast R-CNN [C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2016: 1440–1448.

[6]	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [C]// Computer Vision – ECCV 2016. Cham: Springer, 2016: 21–37.

[7]	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779–788.

[8]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Advances in Neural Information Processing Systems 30. Long Beach: Curran Associates, 2017: 5998−6008.

[9]	CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]// Computer Vision – ECCV 2020. Cham: Springer, 2020: 213–229.

[10]	ZHU X, SU W, LU L, et al. Deformable DETR: deformable transformers for end-to-end object detection [EB/OL]. [ 2025−07−01]. https://arxiv.org/abs/2010.04159.

[11]	ZHAO Y, LV W, XU S, et al. DETRs beat YOLOs on real-time object detection [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 16965–16974.

[12]	ZHANG Q, ZHANG J, LI Y, et al ID-YOLO: a multimodule optimized algorithm for insulator defect detection in power transmission lines[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 3505611 doi: 10.1109/tim.2025.3527530

[13]	HOEFLER M A, MUELLER K, SAMEK W. XAI-guided insulator anomaly detection for imbalanced datasets [C]// Computer Vision – ECCV 2024 Workshops. Cham: Springer, 2025: 65–81.

[14]	LIU Z, LIN Y, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2022: 9992–10002.

[15]	LIU Z, MAO H, WU C Y, et al. A ConvNet for the 2020s [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 11966–11976.

[16]	WU K, ZUO Y, GE J, et al. Insulator defect detection in power grids based on improved YOLOv8 [C]// Proceedings of the IEEE 26th China Conference on System Simulation Technology and its Applications. Shenzhen: IEEE, 2025: 540–545.

[17]	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module [C]// Computer Vision – ECCV 2018. Cham: Springer, 2018: 3–19.

[18]	TANG S, ZHU R, JI C, et al. Intelligent detection of insulator defects on transmission lines in complex backgrounds based on improved DETR visual perception model [C]// Proceedings of the International Conference on Artificial Intelligence and Power Systems. Chengdu: IEEE, 2024: 83–89.

[19]	SINGH A, HU R, GOSWAMI V, et al. FLAVA: a foundational language and vision alignment model [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 15617–15629.

[20]	ZHANG K, YANG J, WANG J, et al VLF-DETR: integrating vision-language and high-frequency features for transmission line defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 5506115 doi: 10.1109/tim.2025.3586346

[21]	CHENG Y, LIU D AdIn-DETR: adapting detection transformer for end-to-end real-time power line insulator defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 3528511

[22]	BUSLAEV A, IGLOVIKOV V I, KHVEDCHENYA E, et al Albumentations: fast and flexible image augmentations[J]. Information, 2020, 11 (2): 125 doi: 10.3390/info11020125

[23]	CAI X, LAI Q, WANG Y, et al. Poly kernel inception network for remote sensing detection [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 27706–27716.

[24]	XIA Z, PAN X, SONG S, et al. Vision transformer with deformable attention [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 4784–4793.

[25]	WU T, TANG S, ZHANG R, et al CGNet: a light-weight context guided network for semantic segmentation[J]. IEEE Transactions on Image Processing, 2021, 30: 1169- 1179 doi: 10.1109/TIP.2020.3042065

[1]	Heng YANG,Shaohan WANG,Qing DONG,Keyuan ZHAO,Mingliang YANG. Object pose estimation based on attention enhancement cross-modal multilayer fusion network[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(9): 1872-1880.

[2]	Hongbin LIN,Sijin LV,Chenyang WANG,Tianfang CAI,Pengwei LUO. Radial basis network based on residual/gradient Gaussian adaptive sampling[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 1119-1127.

[3]	Zixiang LI,Kecheng LU,Haibing CAI,Weishuai XIE,Guangdong ZHANG. Concrete crack detection in dark environments based on biomimetic tactile technology[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 915-925.

[4]	Jie WU,Beilin HAN,Yihang ZHANG,Chao ZOU,Lifeng XIN,Shiping HUANG. Method for augmenting crack image datasets via fine-tuning of stable diffusion models[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 926-934.

[5]	Xiaochun WU,Ning GUO. Lightweight detection method of water leakage in tunnel based on HMARU-net[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(3): 468-477.

[6]	Leping LIN,Liang LI,Ning OUYANG. High spatio-temporal resolution precipitation forecast based on dual-polarization radar[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(3): 574-584.

[7]	Minghui YANG,Muyuan SONG,Daxi FU,Yanwei GUO,Xianzhui LU,Wencong ZHANG,Weilong ZHENG. Prediction of shield tunneling-induced soil settlement based on multi-head self-attention-Bi-LSTM model[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(2): 415-424.

[8]	Zhihang ZHU,Yunfeng YAN,Donglian QI. Image generation for power personnel behaviors based on diffusion model with multimodal prompts[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(1): 43-51.

[9]	Yue SUN,Xinglan ZHANG. Targeted adversarial attack method based on dual guidance[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(1): 81-89.

[10]	Jizhong DUAN,Haiyuan LI. Multi-scale parallel magnetic resonance imaging reconstruction based on variational model and Transformer[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1826-1837.

[11]	Fujian WANG,Zetian ZHANG,Xiqun CHEN,Dianhai WANG. Usage prediction of shared bike based on multi-channel graph aggregation attention mechanism[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1986-1995.

[12]	Hong ZHANG,Xuecheng ZHANG,Guoqiang WANG,Panlong GU,Nan JIANG. Real-time positioning and control of soft robot based on three-dimensional vision[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1574-1582.

[13]	Shengju WANG,Zan ZHANG. Missing value imputation algorithm based on accelerated diffusion model[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1471-1480.

[14]	Dongping ZHANG,Dawei WANG,Shuji HE,Siliang TANG,Zhiyong LIU,Zhongqiu LIU. Remaining useful life prediction of aircraft engines based on cross-dimensional feature fusion[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1504-1513.

[15]	Yongqing CAI,Cheng HAN,Wei QUAN,Wudi CHEN. Visual induced motion sickness estimation model based on attention mechanism[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(6): 1110-1118.

Viewed

Full text

Abstract

Cited

Shared

Discussed