Intelligent Detection Technology of Infrared Image of Substation Equipment Based on Deep Learning Algorithm

Zhang, Xiaohua; Lv, Zhirui; Sun, Yunsheng; Huang, Bin; Niu, Zheng; Liu, Guangwei; Mu, Ka

doi:10.1109/ispec53008.2021.9736081

Cited by 11 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research group constructed an accurate identification model of infrared images of substation equipment based on the improved yolov3 algorithm, realized automatic real-time positioning of infrared image target images, and proposed a complete set of fault diagnosis solutions for current and voltage overheating defects [6][7]. The algorithm mainly includes the following parts.…”

Section: Research On Intelligent Detection Technology Of Infrared Ima...mentioning

confidence: 99%

Lossless Compression and Optimization Method of Data Flow Efficiency of Infrared Image Depth Learning Model of Substation Equipment

Liu

Hao

Niu

et al. 2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

Infrared detection of substation equipment has become one of the important means for live detection of power grid equipment. The insulation fault and equipment defect of electrical equipment in operation can be found by using infrared thermal imaging technology. Infrared image deep learning model usually needs a very large computational cost and storage space, which greatly limits the application of deep learning model in embedded terminal. In order to apply the deep learning model well in embedded devices with limited resources, this paper proposes a lossless compression method of infrared image deep learning model of substation equipment, which can reduce the size of the deep learning network model by 35 to 49 times without loss of recognition accuracy. A hybrid sparse matrix storage format based on recursion and a cache blocking method based on multi-core/many-core processors are proposed to optimize the data flow efficiency between processors.

show abstract

Section: Research On Intelligent Detection Technology Of Infrared Ima...mentioning

confidence: 99%

Lossless Compression and Optimization Method of Data Flow Efficiency of Infrared Image Depth Learning Model of Substation Equipment

Liu

Hao

Niu

et al. 2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wang et al [21] proposed an automatic detection method based on MobileNet-SSD, which realized the detection of abnormal electrical components in infrared images while ensuring detection accuracy. Zhang et al [22] implemented automatic identification, localization, and fault diagnosis of electrical components based on YOLOv3, further improving work efficiency and detection quality of transmission lines inspection. In response to the shortcomings of low contrast and blurred boundaries in infrared images, Zhu et al [23] combined Retinex enhancement algorithm with YOLOv3 for substation components (lightning arresters, switches, and current transformers) detection, achieving the detection mAP of 96%.…”

Section: Introductionmentioning

confidence: 99%

Thermal defect detection of electrical components in transmission lines based on infrared images and deep learning

Liu,

et al. 2024

Preprint

View full text Add to dashboard Cite

The safe operation of transmission lines will be an important guarantee for domestic economic construction, and it is urgent to improve the fault diagnosis and identification ability of electrical components in transmission lines. In order to realize electrical components identification and thermal defect detection from massive aerial images, in this study, a cascaded detection method is proposed based on infrared images and YOLO model. Firstly, two infrared datasets used for classification and localization are created, totaling 4887 infrared images. Secondly, to enhance the accuracy and robustness of electrical components identification, similarity-based attention mechanism modules, cross-level weighted feature pyramid network, and Wise IoU are introduced to the original YOLOv7. Finally, the improved YOLOv7 model and comparative models are trained and then tested on the infrared datasets. The mAP of the improved model reaches 97.4%, which is 6% higher than that of the original YOLOv7. More importantly, by cascading the improved YOLOv7 and YOLOv7-tiny for thermal defect detection, the AP value of the proposed method (87.91%) is more than 20% higher than that of YOLOv7 (67.17%). The experimental results show that the cascaded model is superior to mainstream object detection models in electrical components identification and thermal defect detection, and it is expected to be deployed on embedded devices for real-time inspection of transmission lines.

show abstract

“…Compared with the previous common predictors, this method can obtain very low transmission coding speed and improve the coding effect. The research group has carried out relevant research on infrared image intelligent detection technology of substation equipment based on deep learning algorithm and digital image lossless compression technology [8]. On the basis of the research, this paper starts to develop a set of infrared video intelligent diagnosis device for substation equipment based on edge calculation and carry out practical application, so as to realize the local real-time fast processing of infrared video image of patrol inspection of the acquisition device and the timely diagnosis of equipment defects, which greatly improves the safe and stable operation level and power supply reliability of substation equipment.…”

Section: Introductionmentioning

confidence: 99%

Development and Application of Infrared Video Intelligent Diagnosis Device for Substation Equipment Based on Edge Calculation

Liu

et al. 2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

In recent years, infrared detection technology is widely used in the field of state detection of power equipment. It can timely and effectively find equipment defects and avoid the further development of equipment defects. However, the conventional manual inspection has some problems, such as heavy workload, long time-consuming and low efficiency. Based on the research of infrared image intelligent detection technology of substation equipment based on deep learning algorithm and digital image lossless compression technology, a set of infrared video intelligent diagnosis device of substation equipment based on edge calculation is developed and applied in practice. The device realizes local real-time rapid processing and timely diagnosis of equipment defects, and the accuracy of defect identification is about 94.44%, which greatly improves the safe and stable operation level and power supply reliability of substation equipment.

show abstract

Intelligent Detection Technology of Infrared Image of Substation Equipment Based on Deep Learning Algorithm

Cited by 11 publications

References 2 publications

Lossless Compression and Optimization Method of Data Flow Efficiency of Infrared Image Depth Learning Model of Substation Equipment

Lossless Compression and Optimization Method of Data Flow Efficiency of Infrared Image Depth Learning Model of Substation Equipment

Thermal defect detection of electrical components in transmission lines based on infrared images and deep learning

Development and Application of Infrared Video Intelligent Diagnosis Device for Substation Equipment Based on Edge Calculation

Contact Info

Product

Resources

About