[1]赵振兵,马腾,景群,等.融合因果知识的变电站仪表外观缺陷检测算法[J].智能系统学报,2026,21(4):988-1003.[doi:10.11992/tis.202508018]
ZHAO Zhenbing,MA Teng,JING Qun,et al.Substation instrument appearance defect detection algorithm integrating causal knowledge[J].CAAI Transactions on Intelligent Systems,2026,21(4):988-1003.[doi:10.11992/tis.202508018]
点击复制
ZHAO Zhenbing,MA Teng,JING Qun,et al.Substation instrument appearance defect detection algorithm integrating causal knowledge[J].CAAI Transactions on Intelligent Systems,2026,21(4):988-1003.[doi:10.11992/tis.202508018]
融合因果知识的变电站仪表外观缺陷检测算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第4期
页码:
988-1003
栏目:
学术论文—智能系统
出版日期:
2026-07-05
- Title:
- Substation instrument appearance defect detection algorithm integrating causal knowledge
- Keywords:
- target detection; substation instrument; appearance defect detection; attention mechanism; global-local feature extraction; cross-layer context feature pyramid network; causal knowledge association; loss function
- 分类号:
- TP391
- 摘要:
- 针对变电站仪表外观缺陷检测中存在外观缺陷多尺度特征提取困难及缺陷类别不平衡等问题，提出一种融合因果知识的变电站仪表外观缺陷检测算法。在骨干网络引入全局-局部特征提取模块，增强模型对全局和局部缺陷特征的提取能力；在颈部加入跨层上下文特征金字塔网络，增强模型的特征融合能力；通过深入挖掘变电站仪表外观缺陷的因果机理，提出因果知识关联模块，使用融合因果知识权重的损失函数，辅助模型进行训练，提高模型在复杂的变电站场景下对于表计缺陷检测的准确性。实验结果表明，相较于基线模型，改进算法将平均精确率提升了4.1%，有效地提升了变电站仪表外观缺陷检测的效果。
- Abstract:
- To address the challenges of multi-scale feature extraction for appearance defects and class imbalance in substation meter defect detection, a substation meter appearance defect detection algorithm integrating causal knowledge is proposed. First, a global-to-local feature extraction block (GLFEB) is introduced into the backbone network to enhance the model’s ability to capture both global and local defect features. Then, a cross-layer context feature pyramid network (CCFPN) is incorporated into the neck to strengthen the model’s feature fusion capability. Finally, by deeply exploring the causal mechanisms underlying substation meter appearance defects, a causal knowledge association block (CKAB) is proposed. A loss function incorporating causal knowledge weights is designed to assist model training, thereby improving detection accuracy in complex substation environments. Experimental results demonstrate that, compared with the baseline model, the proposed method improves the mean average precision (mAP) by 4.1%, effectively enhancing the performance of substation meter appearance defect detection.
- 参考文献/References:
-
[1] 和敬涵, 罗国敏, 程梦晓, 等. 新一代人工智能在电力系统故障分析及定位中的研究综述[J]. 中国电机工程学报, 2020, 40(17): 5506-5516 HE Jinghan, LUO Guomin, CHENG Mengxiao, et al. A research review on application of artificial intelligence in power system fault analysis and location[J]. Proceedings of the CSEE, 2020, 40(17): 5506-5516
[2] 张铭泉, 邢福德, 刘冬. 基于改进Faster R-CNN的变电站设备外部缺陷检测[J]. 智能系统学报, 2024, 19(2): 290-298 ZHANG Mingquan, XING Fude, LIU Dong. External defect detection of transformer substation equipment based onimproved Faster R-CNN[J]. CAAI transactions on intelligent systems, 2024, 19(2): 290-298
[3] 赵振兵, 冯烁, 赵文清, 等. 融合知识迁移和改进 YOLOv6 的变电设备热像检测方法[J]. 智能系统学报, 2023, 18(6): 1213-1222 ZHAO Zhenbing, FENG Shuo, ZHAO Wenqing, et al. Thermd image detection method for substation equipment by incorporating knowledge migration and improved YOLOv6[J]. CAAI transactions on intelligent systems, 2023, 18(6): 1213-1222
[4] 赵振兵, 席悦, 冯烁, 等. 面向复杂场景的变电设备锈蚀检测方法[J]. 智能系统学报, 2025, 20(3): 679-688 ZHAO Zhenbing, XI Yue, FENG Shuo, et al. A corrosion detection method of substation equipment for complex scenarios[J]. CAAI transactions on intelligent systems, 2025, 20(3): 679-688
[5] 彭明智, 许尧, 胡永波, 等. 基于人工智能技术的变电站二次设备智能巡检技术[J]. 高电压技术, 2023, 49(S1): 90-96 PENG Mingzhi, XU Yao, HU Yongbo, et al. Intelligent inspection technology for substation secondary equipment based on artificial intelligence[J]. High voltage engineering, 2023, 49(S1): 90-96
[6] 胡欣, 刘瑞峰, 肖剑, 等. 面向变电站嵌入式设备的指针式仪表识别方法[J]. 电子测量与仪器学报, 2025, 39(1): 253-263 HU Xin, LIU Ruifeng, XIAO Jian, et al. Pointer meter identification method for embedded devices in substations[J]. Journal of electronic measurement and instrumentation, 2025, 39(1): 253-263
[7] 何敏, 秦亮, 刘开培, 等. 变电站电力仪表智能检测算法研究[J]. 高电压技术, 2024, 50(7): 2942-2954 HE Min, QIN Liang, LIU Kaipei, et al. Research on intelligent detection algorithms for substation power instruments[J]. High voltage engineering, 2024, 50(7): 2942-2954
[8] FAN Zizhu, SHI Linrui, XI Chao, et al. Real time power equipment meter recognition based on deep learning[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 1-15
[9] CAO Yue, XU Jiarui, LIN S, et al. GCnet: non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the IEEE/CVF international conference on computer vision workshops. Seoul: IEEE, 2019: 1971-1980.
[10] SHI Huibin, HUA Zexi, CHEN Jianyi, et al. Detection and recognition of digital instrument in substation using improved YOLOv3[J]. Signal, image and video processing, 2023, 17(6): 2971-2979
[11] SHEN Jiaquan, LIU Ningzhong, SUN Han, et al. An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features[J]. IEEE transactions on instrumentation and measurement, 2024, 73: 1-16
[12] HAO Zhaoming, ZHANG Xiaoqiong, LI Hongyan, et al. Real-time detection algorithm for digital meters based on multi-scale feature fusion and GCS[J]. Journal of real-time image processing, 2024, 21(2): 35
[13] DONG Hao, YUAN Mu, WANG Shu, et al. PHAM-YOLO: a parallel hybrid attention mechanism network for defect detection of meter in substation[J]. Sensors, 2023, 23(13): 6052
[14] 赵振兵, 马迪雅, 石颖, 等. 基于改进 YOLOX 的变电站仪表外观缺陷检测算法[J]. 图学学报, 2023, 44(5): 937-946 ZHAO Zhenbing, MA Diya, SHI Ying, et al. Appearance defect detection algorithm of substation instrument based on improved YOLOX[J]. Journal of graphics, 2023, 44(5): 937-946
[15] XU Shanyong, CHEN Xiulong, HUANG Yourui, et al. Defect detection of substation instrumentation equipment based on improved YOLOv4 algorithm[C]//2023 China Automation Congress. Chongqing: IEEE, 2023: 9091-9096.
[16] SANDLER M, HOWARD A, ZHU Menglong, et al. Mobilenetv2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[17] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
[18] 李峰, 王琦, 胡健雄, 等. 数据与知识联合驱动方法研究进展及其在电力系统中应用展望[J]. 中国电机工程学报, 2021, 41(13): 4377-4390 LI Feng, WANG Qi, HU Jianxiong, et al. Combined data-driven and knowledge-driven methodology research advances and its applied prospect in power systems[J]. Proceedings of the CSEE, 2021, 41(13): 4377-4390
[19] LIN T, DOLL?R P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2117-2125.
[20] SHI Dai. TransNeXt: robust foveal visual perception for vision transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 17773-17783.
[21] LIU Shu, QI Lu, QIN Haifang, et al. Path aggregation network for instance segmentation[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759-8768.
[22] XU Xianzhe, JIANG Yiqi, CHEN Weihua, et al. Damo-yolo: a report on real-time object detection design [EB/OL]. (2022-11-23) [2025-07-25]. https://arxiv.org/abs/2211.15444.
[23] LIU Wenze, LU Hao, FU Hongtao, et al. Learning to upsample by learning to sample[C]//Proceedings of the 2023 IEEE International Conference on Computer Vision. Paris: IEEE, 2023: 6027-6037.
[24] CAI Xinhao, LAI Qiuxia, WANG Yuwei, et al. Poly kernel inception network for remote sensing detection[C]//2024 IEEE Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 27706-27716.
[25] JIANG Chenhan, XU Hang, LIANG Xiaodan, et al. Hybrid knowledge routed modules for large-scale object detection[J]. Advances in neural information processing systems, 2018, 31.
[26] ZHANG Haoyang, WANG Ying, DAYOUB F, et al. Varifocalnet: an iou-aware dense object detector[C]//2021 IEEE Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 8514-8523.
[27] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on computer Vision. Springer: Cham, 2018: 3-19.
[28] LAU K, PO L, REHMAN Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN[J]. Expert systems with applications, 2024, 236: 121352
[29] KANG Ming, TING C M, TING F F, et al. CST-YOLO: a novel method for blood cell detection based on improved YOLOv7 and CNN-swin Transformer[C]//2024 IEEE International Conference on Image Processing. Abu Dhabi: IEEE, 2024: 3024-3029.
[30] XU Zhengze, WU Dongyue, YU Changqian, et al. Sctnet: Single-branch cnn with Transformer semantic information for real-time segmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Vancouver: AAAI, 2024: 6378-6386.
[31] REN Shaoqing, HE Kaiming, GIRSHICk R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1137-1149
[32] CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: Delving into high quality object detection[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6154-6162.
[33] FENG Chengjian, ZHONG Yujie, GAO Yu, et al. Tood: task-aligned one-stage object detection[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 3490-3499.
[34] LI Chuyi, LI Lulu, JIANG Hongliang, et al. YOLOv6: a single-stage object detection framework for industrial applications[EB/OL]. (2022-09-07) [2025-07-25]. https://arxiv.org/abs/2209.02976.
[35] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 7464-7475.
[36] ZHAO Yian, LYU Wenyu, XU Shangliang, et al. Detrs beat yolos on real-time object detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 16965-16974.
[37] WANG Zeyu, LI Chen, XU Huiying, et al. Mamba YOLO: SSMs-based YOLO for object detection. [EB/OL]. (2024-06-09) [2025-07-25]. https://arxiv.org/abs/2406.05835.
[38] WANG C Y, YEH I H, LIAO M H Y. Yolov9: Learning what you want to learn using programmable gradient information[C]//European Conference on Computer Vision. Springer: Cham, 2025: 1-21.
[39] WANG Ao, CHEN Hui, LIU Lihao, et al. Yolov10: Real-time end-to-end object detection[EB/OL]. (2024-05-23) [2025-07-25]. https://arxiv.org/abs/2405.14458.
[40] TIAN Yunjie, YE Qixiang, DOERMANN D. Yolov12: Attention-centric real-time object detectors[EB/OL]. (2025-02-18) [2025-07-25]. https://arxiv.org/abs/2502.12524.
[41] LIU Shilong, ZENG Zhaoyang, REN Tianhe, et al. Grounding DINO: marrying DINO with grounded pre-training for open-set object detection[C]//European Conference on Computer Cision. Springer: Cham, 2024: 38-55.
- 相似文献/References:
-
[1]胡光龙,秦世引.动态成像条件下基于SURF和Mean shift的运动目标高精度检测[J].智能系统学报,2012,7(1):61.
HU Guanglong,QIN Shiyin.High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift[J].CAAI Transactions on Intelligent Systems,2012,7():61.
[2]韩峥,刘华平,黄文炳,等.基于Kinect的机械臂目标抓取[J].智能系统学报,2013,8(2):149.[doi:10.3969/j.issn.1673-4785.201212038]
HAN Zheng,LIU Huaping,HUANG Wenbing,et al.Kinect-based object grasping by manipulator[J].CAAI Transactions on Intelligent Systems,2013,8():149.[doi:10.3969/j.issn.1673-4785.201212038]
[3]韩延彬,郭晓鹏,魏延文,等.RGB和HSI颜色空间的一种改进的阴影消除算法[J].智能系统学报,2015,10(5):769.[doi:10.11992/tis.201410010]
HAN Yanbin,GUO Xiaopeng,WEI Yanwen,et al.An improved shadow removal algorithm based on RGB and HSI color spaces[J].CAAI Transactions on Intelligent Systems,2015,10():769.[doi:10.11992/tis.201410010]
[4]曾宪华,易荣辉,何姗姗.流形排序的交互式图像分割[J].智能系统学报,2016,11(1):117.[doi:10.11992/tis.201505037]
ZENG Xianhua,YI Ronghui,HE Shanshan.Interactive image segmentation based on manifold ranking[J].CAAI Transactions on Intelligent Systems,2016,11():117.[doi:10.11992/tis.201505037]
[5]葛园园,许有疆,赵帅,等.自动驾驶场景下小且密集的交通标志检测[J].智能系统学报,2018,13(3):366.[doi:10.11992/tis.201706040]
GE Yuanyuan,XU Youjiang,ZHAO Shuai,et al.Detection of small and dense traffic signs in self-driving scenarios[J].CAAI Transactions on Intelligent Systems,2018,13():366.[doi:10.11992/tis.201706040]
[6]莫宏伟,汪海波.基于Faster R-CNN的人体行为检测研究[J].智能系统学报,2018,13(6):967.[doi:10.11992/tis.201801025]
MO Hongwei,WANG Haibo.Research on human behavior detection based on Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2018,13():967.[doi:10.11992/tis.201801025]
[7]宁欣,李卫军,田伟娟,等.一种自适应模板更新的判别式KCF跟踪方法[J].智能系统学报,2019,14(1):121.[doi:10.11992/tis.201806038]
NING Xin,LI Weijun,TIAN Weijuan,et al.Adaptive template update of discriminant KCF for visual tracking[J].CAAI Transactions on Intelligent Systems,2019,14():121.[doi:10.11992/tis.201806038]
[8]伍鹏瑛,张建明,彭建,等.多层卷积特征的真实场景下行人检测研究[J].智能系统学报,2019,14(2):306.[doi:10.11992/tis.201710019]
WU Pengying,ZHANG Jianming,PENG Jian,et al.Research on pedestrian detection based on multi-layer convolution feature in real scene[J].CAAI Transactions on Intelligent Systems,2019,14():306.[doi:10.11992/tis.201710019]
[9]刘召,张黎明,耿美晓,等.基于改进的Faster R-CNN高压线缆目标检测方法[J].智能系统学报,2019,14(4):627.[doi:10.11992/tis.201905026]
LIU Zhao,ZHANG Liming,GENG Meixiao,et al.Object detection of high-voltage cable based on improved Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2019,14():627.[doi:10.11992/tis.201905026]
[10]单义,杨金福,武随烁,等.基于跳跃连接金字塔模型的小目标检测[J].智能系统学报,2019,14(6):1144.[doi:10.11992/tis.201905041]
SHAN Yi,YANG Jinfu,WU Suishuo,et al.Skip feature pyramid network with a global receptive field for small object detection[J].CAAI Transactions on Intelligent Systems,2019,14():1144.[doi:10.11992/tis.201905041]
备注/Memo
收稿日期:2025-8-27。
基金项目:国家自然科学基金项目（61871182, U21A20486, 62373151, 62371188, 62303184）；河北省自然科学基金项目（F2021502008, F2021502013）；中央高校基本科研业务费专项（2023JC006）.
作者简介:赵振兵，教授，博士生导师，博士，主要研究方向为电力视觉(电力人工智能)。获省级科学技术奖一等奖3 项，主持国家自然科学基金等科研项目 20 余项，以第一完成人获国家专利授权 19 项，以第一作者出版专著 2 部，以第一作者或通信作者发表学术论文 100 余篇。E-mail：zhaozhenbing@ncepu.edu。;马腾，硕士研究生，主要研究方向为电力视觉。E-mail：17547402483@163.com。;景群，硕士研究生，主要研究方向为电力视觉。E-mail：jqun2000@gmail.com。
通讯作者:赵振兵. E-mail：zhaozhenbing@ncepu.edu.cn
更新日期/Last Update:
1900-01-01