A novel intelligent fault diagnosis method for electrical equipment using infrared thermography

Zeng, Hui; Fuzhen, Huang

doi:10.1016/j.infrared.2015.08.019

Cited by 86 publications

(36 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the algorithm cannot achieve real-time running and only can detect wire-wound foreign objects, while it is powerless to the potential harm caused by construction machinery. In contrast to general object detection in RGB images, there are also some methods to inspect electrical equipment by using infrared thermography [30], [31]. Moreover, [7] also presents a real-time deep learning approach to detect oriented electrical equipment detection in thermal images.…”

Section: Related Work a Image Online Monitoringmentioning

confidence: 99%

“…The traditional generic object detectors are based on the sliding window paradigms or region proposal classification using hand-crafted features [32]- [34]. With the development of deep learning, object detectors based on CNN have become a predominant trend in the field of generic object detection and have led to remarkable breakthroughs in the fields of detection applications [30], [35]- [37]. As the state-of-art object detectors, two-stage detectors such as R-CNN [38] and its descendants [39], [40] first generate class agnostic region proposals and then predict the specific class label and refine the location regression.…”

Section: B Object Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines

et al. 2020

View full text Add to dashboard Cite

Image online monitoring technology has been widely used in transmission lines inspection, but the intelligent and efficient foreign object detection still has a gap with the ideal. In this paper, we propose a deep learning method to detect invading foreign objects for power transmission line inspection. Specifically, we design our network based on the regression strategy with oriented bounding boxes to accurately predict spatial location and orientation angle of foreign objects, as well as their categories in cluttered backgrounds. Moreover, an easy yet effective Scale Histogram Matching method is proposed to be applied to the publicly available dataset, allowing useful patterns to be exploited to detect tiny foreign objects during the pretraining procedure and boosting detection performance even with limited annotated samples. Besides, we construct an image dataset that contains common foreign objects in transmission line scenarios to evaluate proposed methods, on which experiment results show our full model achieves accuracy with 88.1% mean Average Precision (mAP). Additionally, the efficient and compact network structure allows our network to run in real-time, which provides possibilities for practical use. INDEX TERMS Image online monitoring technology, power transmission line inspection, deep learning, oriented bounding boxes, scale histogram matching.

show abstract

Section: Related Work a Image Online Monitoringmentioning

confidence: 99%

Section: B Object Detectionmentioning

confidence: 99%

A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines

et al. 2020

View full text Add to dashboard Cite

show abstract

“…1. Multispectral image of building interior perature) is probably an electric cable in its tube cover [6]. The additional horizontal line appears because the multispectral thermal image is shifted from the digital one.…”

Section: Building Interior Measurementsmentioning

confidence: 99%

Visual Analysis of Heat Transport in a Unique Object

Urzędowski¹,

Wójcicka-Migasiuk²

2015

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

The paper presents a visual analysis of heat propagation in selected elements of a unique building structure. Numerous spots of construction deterioration and weakening are exemplary to the presented method and to the procedure of concluding for the purpose of combined research and education at the third academic level of education. The described procedures use a thermographic camera. The most attention has been put to thermal bridges to avoid energy loss in further modernization of the investigated object and how the conclusion process can be supported. The discussion is based on four parallel types of camera imaging: thermal, multispectral, thermal fusion and digital. The selected important aspects of measurement conditions have been discussed to justify the reliability of presented measurements.

show abstract

“…It can realize the integration of dialectical logic and mathematical logic, the unification of symbolic processing and numerical processing and reasoning process and algorithm process by the concept and process knowledge in order to realize the intelligent fault diagnosis method of equipment. The intelligent fault diagnosis method provides people with the powerful tool for solving the fault diagnosis problem of complex system [3][4][5].At present, a lot of scholars have studied the field of intelligent fault diagnosis and proposed a variety of intelligent fault diagnosis technologies [6][7][8][9][10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid intelligent fault diagnosis method based on improved RBF neural network

Liu¹

2016

Proceedings of the 2016 International Conference on Economics and Management Innovations

View full text Add to dashboard Cite

Abstract. The radial basis function neural network (RBFNN) is a great potential artificial intelligence technology and can effectively realize the fault diagnosis for small sample and nonlinear problem. But the parameters of RBFNN model seriously affects the generalization ability and diagnosis accuracy on the great extent. So an improved differential evolution algorithm based on dynamic adaptive adjustment strategy is proposed to optimize the parameters of RBFNN model for obtaining the optimal RBFNN(DASDERBFNN) method. Then the proposed DASDERBFNN method is used to construct a new fault diagnosis (DSDRBFNFD) method. The experiment results show that the proposed DSDRBFNFD method can obtain the higher accuracy of fault diagnosis and is effective fault diagnosis for the engine.

show abstract

A novel intelligent fault diagnosis method for electrical equipment using infrared thermography

Cited by 86 publications

References 18 publications

A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines

A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines

Visual Analysis of Heat Transport in a Unique Object

A novel hybrid intelligent fault diagnosis method based on improved RBF neural network

Contact Info

Product

Resources

About