Intelligent Diagnosis Method of Power Equipment Faults Based on Single‐Stage Infrared Image Target Detection

Zheng, Hanbo; Ping, Yuan; Cui, Yaohui; Li, Jin‐Heng

doi:10.1002/tee.23681

Cited by 16 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of information technology, the integration of artificial intelligence technology and image processing technology has become the main direction of current scholars' research [8]. Faster-RCNN and YOLO gained good results in fault identification of power equipment [9][10][11][12] and substantiated the positive effect of the application of artificial intelligence technology. AlexNet is a newer convolutional image recognition neural network model, that has a high recognition rate and other parameters, so it is widely used in agriculture, military, industry and other fields.…”

Section: Introductionmentioning

confidence: 98%

Research on power equipment troubleshooting based on improved AlexNet neural network

Xu,

Liu,

Zhang

2024

J. meas. eng.

View full text Add to dashboard Cite

Power equipment is an important component of the whole power system, so that it is obvious that it is required to develop a correct method for accurate analysis of the infrared image features of the equipment in the field of detection and recognition. This study proposes a troubleshooting strategy for the power equipment based on the improved AlexNet neural network. Multi-scale images based on the Pan model are used to determine the equipment features, and to determine the shortcomings of AlexNet neural network, such as slower recognition speed and easy overfitting. After knowing these shortcomings, it would become possible to improve the specific recognition model performance by adding a pooling layer, modifying the activation function, replacing the LRN with BN layer, and optimizing the parameters of the improved WOA algorithm, and other measures. In the simulation experiments, this paper's algorithm was compared with AlexNet, YOLO v3, and Faster R-CNN algorithms in the lightning arrester fault detection, circuit breaker fault detection, mutual transformer fault detection, and insulator fault detection improved by an average of 5.47 %, 4.69 %, and 3.42 %, which showed that the algorithm had a better recognition effect.

show abstract

Section: Introductionmentioning

confidence: 98%

Research on power equipment troubleshooting based on improved AlexNet neural network

Xu,

Liu,

Zhang

2024

J. meas. eng.

View full text Add to dashboard Cite

show abstract

“…The temperature information in infrared images is usually extracted using the accompanying infrared image analysis software, but this software is usually expensive and lacks universality. The color bar is an important medium for converting temperature matrices to infrared images, so the temperature information of each point in the image can be obtained from the color bar in the infrared image [ 19 ]. Traditional infrared image temperature calculation approximates the grayscale and temperature values of each pixel on the image as a linear function.…”

Section: Introductionmentioning

confidence: 99%

“…By fitting the obtained linear function relationship, the temperature value for each pixel is determined. Zheng et al studied the function relationship between pixel grayscale and temperature for the FLIR T640 infrared thermal imager, using grayscale values as independent variables and temperature values as dependent variables to fit a linear function curve for the temperature extraction of power equipment infrared images [ 19 ]. However, the grayscale and temperature of the infrared image do not have a strictly linear correspondence, so the accuracy of temperature estimation using linear functions still needs improvement.…”

Section: Introductionmentioning

confidence: 99%

Optimized OTSU Segmentation Algorithm-Based Temperature Feature Extraction Method for Infrared Images of Electrical Equipment

Liu,

Zhang,

Hao

et al. 2024

Sensors

View full text Add to dashboard Cite

Infrared image processing is an effective method for diagnosing faults in electrical equipment, in which target device segmentation and temperature feature extraction are key steps. Target device segmentation separates the device to be diagnosed from the image, while temperature feature extraction analyzes whether the device is overheating and has potential faults. However, the segmentation of infrared images of electrical equipment is slow due to issues such as high computational complexity, and the temperature information extracted lacks accuracy due to the insufficient consideration of the non-linear relationship between the image grayscale and temperature. Therefore, in this study, we propose an optimized maximum between-class variance thresholding method (OTSU) segmentation algorithm based on the Gray Wolf Optimization (GWO) algorithm, which accelerates the segmentation speed by optimizing the threshold determination process using OTSU. The experimental results show that compared to the non-optimized method, the optimized segmentation method increases the threshold calculation time by more than 83.99% while maintaining similar segmentation results. Based on this, to address the issue of insufficient accuracy in temperature feature extraction, we propose a temperature value extraction method for infrared images based on the K-nearest neighbor (KNN) algorithm. The experimental results demonstrate that compared to traditional linear methods, this method achieves a 73.68% improvement in the maximum residual absolute value of the extracted temperature values and a 78.95% improvement in the average residual absolute value.

show abstract

“…To identify the electrical components in infrared images more accurately, Zheng et al [25] improved YOLOv3 by introducing CSPNet, PANet, Mosaic enhancement technology and CIoU loss function into the original YOLOv3. The detection mAP of power components (arrester, breaker, transformer and insulator) reached 96.04%, which is 1.5%, 3% and 3.5% higher than Faster R-CNN, SSD and the original YOLOv3, respectively.…”

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

Intelligent Diagnosis Method of Power Equipment Faults Based on Single‐Stage Infrared Image Target Detection

Cited by 16 publications

References 32 publications

Research on power equipment troubleshooting based on improved AlexNet neural network

Research on power equipment troubleshooting based on improved AlexNet neural network

Optimized OTSU Segmentation Algorithm-Based Temperature Feature Extraction Method for Infrared Images of Electrical Equipment

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

Contact Info

Product

Resources

About