Research on Infrared Image Recognition Method of Power Equipment Based on Deep Learning

Jiang, Anfeng; Niu, Y.; BaoGuo, Shen; Gu, Chunjie; Zhu, Huangru; Huang, Hao

doi:10.1109/ichve49031.2020.9279631

Cited by 16 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The flow chart of the thermal image recognition is shown in Figure 18. Although there are many intelligent fault diagnosis methods, such as neural network, fuzzy and the comprehensive artificial intelligence, the infrared image recognition is often performed by the SVM (Zhao et al , 2020) and DL (Jiang et al , 2020). It is noted that DNN exhibits significant advantages in image recognition (LeCun et al , 2015).…”

Section: Comparative-analysis Of Various Indoor-orbital Electrical In...mentioning

confidence: 99%

See 1 more Smart Citation

A review of indoor-orbital electrical inspection robots in substations

Dong

Liang²,

Li³

et al. 2022

View full text Add to dashboard Cite

Purpose The purpose of this study is to provide an in-depth understanding about the indoor-orbital electrical inspection robot, which is useful for motivating the further investigation on the inspection of electrical equipment. Currently, electric energy has a strong correlation with the economic development of the country. Intelligent substations play an important role in the transmission and distribution of the electricity; the maintenance of the substation has attracted intensive attention due to the requirement of reliability and safety. The indoor-orbital electrical inspection robot has increasingly become the main tool to realize the unmanned. Hence, a systematic review is conducted systematically reviewing the current technical status of the indoor-orbital electrical inspection robot and discuss the existed problems. Design/methodology/approach In this paper, the most essential achievements in the field of indoor-orbital electrical inspection robots were reported to present the current status, and the mechanical structures and key inspective technologies were also discussed. Findings Four recommendations are provided from the analyzed review, which have made constructive comments on the overall structural design, functionality, intelligence and future development direction of the indoor-orbital electrical inspection robot, respectively. Originality/value To the best of the authors’ knowledge, this is the first systematic review study on indoor-orbital electrical inspection robots; it fills the theoretical gap and proffers design ideas and directions for the development of the indoor-orbital electrical inspection robot.

show abstract

Section: Comparative-analysis Of Various Indoor-orbital Electrical In...mentioning

confidence: 99%

“…Template matching method of the image recognition Figure 17 Flow chart of image recognition of LED meters (Zhao et al, 2020) and DL (Jiang et al, 2020). It is noted that DNN exhibits significant advantages in image recognition (LeCun et al, 2015).…”

Section: Thermal Imaging Diagnostic Systemmentioning

confidence: 99%

A review of indoor-orbital electrical inspection robots in substations

Dong

Liang²,

Li³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It is important to know how components are distributed across tower instances because components on a given tower will have been exposed to similar environmental conditions and would therefore degrade at the same rate. Fusion of data from multiple sensors has also been used, e.g., visual and infrared image data [59]. Our experiments use a real-world electricity network inspection dataset comprising of visual images that are representative of the diverse component types and failure modes encountered in real-world inspection scenarios.…”

Section: B Previous Work On Automated Monitoringmentioning

confidence: 99%

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Odo

McKenna²,

Flynn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Electricity networks are critical infrastructure, delivering vital energy services. Due to the significant number, variety and distribution of electrical network overhead line assets, energy network operators spend millions annually on inspection and maintenance programmes. Currently, inspection involves acquiring and manually analysing aerial images. This is labour intensive and subjective. Along with costs associated with helicopter or drone operations, data analysis represents a significant financial burden to network operators. We propose an approach to automating assessment of the condition of electrical towers. Importantly, we train machine learning tower classifiers without using condition labels for individual components of interest. Instead, learning is supervised using only condition labels for towers in their entirety. This enables us to use a real-world industry dataset without needing costly additional human labelling of thousands of individual components. Our prototype first detects instances of components in multiple images of each tower, using Mask R-CNN or RetinaNet. It then predicts tower condition ratings using one of two approaches: (i) component instance classifiers trained using class labels transferred from towers to each of their detected component instances, or (ii) multiple instance learning classifiers based on bags of detected instances. Instance or bag class predictions are aggregated to obtain tower condition ratings. Evaluation used a dataset with representative tower images and associated condition ratings covering a range of component types, scenes, environmental conditions, and viewpoints. We report experiments investigating classification of towers based on the condition of their multiple insulator and U-bolt components. Automated visual detection and analysis of U-bolts has not been previously reported. We demonstrate that tower condition classifiers can be trained effectively without labelling the condition of individual components.

show abstract

“…1400 images of each of the three types of targets are randomly selected as the training samples, and the remaining 600 images are used as the test samples. As a comparison, this paper selects several types of existing relevant methods to conduct experiments at the same time, including the method based on the region moments in [11] (denoted as Region moment), the method using SRC in [5] (denoted as SRC), the method based on SVM in [8] (denoted as SVM), and the method using CNN in [21] (denoted as CNN).…”

Section: Description Of the Datasetmentioning

confidence: 99%

“…Commonly used classifiers in image recognition of power equipment include support vector machines (SVMs) and sparse representationbased classification (SRC). In recent years, the deep learning models represented by the convolutional neural network (CNN) have become a powerful tool in the field of image processing [13][14][15][16] and have also been widely used and verified in the image recognition of power equipment [17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Recognition of Power Equipment Based on Multitask Sparse Representation

Lei¹,

Wu²,

Zheng

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

Image analysis of power equipment has important practical significance for power-line inspection and maintenance. This paper proposes an image recognition method for power equipment based on multitask sparse representation. In the feature extraction stage, based on the two-dimensional (2D) random projection algorithm, multiple projection matrices are constructed to obtain the multilevel features of the image. In the classification process, considering that the image acquisition process will inevitably be affected by factors such as light conditions and noise interference, the proposed method uses the multitask compressive sensing algorithm (MtCS) to jointly represent multiple feature vectors to improve the accuracy and robustness of reconstruction. In the experiment, the images of three types of typical power equipment of insulators, transformers, and circuit breakers are classified. The correct recognition rate of the proposed method reaches 94.32%. In addition, the proposed method can maintain strong robustness under the conditions of noise interference and partial occlusion, which further verifies its effectiveness.

show abstract

Research on Infrared Image Recognition Method of Power Equipment Based on Deep Learning

Cited by 16 publications

References 5 publications

A review of indoor-orbital electrical inspection robots in substations

A review of indoor-orbital electrical inspection robots in substations

Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management

Recognition of Power Equipment Based on Multitask Sparse Representation

Contact Info

Product

Resources

About