An efficient foreign objects detection network for power substation

Xu, Liang; Zhang, Weishan; An, Yunyun; Wang, Ye; Ning, Huansheng

doi:10.1016/j.imavis.2021.104159

Cited by 19 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Energy infrastructure is another application field that demands a high level of safety, when utilizing neural networks for foreign object detection. Using, for example, FODN4PS proposed by Xu et al [66], intrusions of foreign bodies in power substations are detected in order to be able to prevent potential failures of power supplies. Furthermore, there is RCNN4SPTL [68] for the inspection of power transmission lines, which can detect entangled foreign objects like balloons or kites.…”

Section: Outdoormentioning

confidence: 99%

A visual foreign object detection system for wireless charging of electric vehicles

Shahbaz Nejad,

Roch,

Handte

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Wireless charging of electric vehicles can be achieved by installing a transmitter coil into the ground and a receiver coil at the underbody of a vehicle. In order to charge efficiently, accurate alignment of the charging components must be accomplished, which can be achieved with a camera-based positioning system. Due to an air gap between both charging components, foreign objects can interfere with the charging process and pose potential hazards to the environment. Various foreign object detection systems have been developed with the motivation to increase the safety of wireless charging. In this paper, we propose a foreign object detection technique that utilizes the integrated camera of an embedded positioning system. Due to operation in an outdoor environment, we cannot determine the types of objects that may occur in advance. Accordingly, our approach achieves object-type independence by learning the features of the charging surface, to then classify anomalous regions as foreign objects. To examine the capability of detecting foreign objects, we evaluate our approach by conducting experiments with images depicting known and unknown object types. For the experiments, we use an image dataset recorded by a positioning camera of an operating wireless charging station in an outdoor environment, which we published alongside our research. As a benchmark system, we employ YOLOv8 (Jocher et al. in Ultralytics YOLO, 2023), a state-of-the-art neural network that has been used in various contexts for foreign object detection. While we acknowledge the performance of YOLOv8 for known object types, our approach achieves up to 18% higher precision and 46% higher detection success for unknown objects.

show abstract

Section: Outdoormentioning

confidence: 99%

A visual foreign object detection system for wireless charging of electric vehicles

Shahbaz Nejad,

Roch,

Handte

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…The purpose of SVM is to find the maximum margin hyperplane to obtain the best classification effect. According to the data set divided by kmeans, the data input to SVM is D={(x1, y1),(x2, y2),…,(xi, yi)…,(xn, yn)}, where xi represents The input vector of the i-th sample, yi represents the category obtained according to the kmeans algorithm 12 . The linear regression model formulated within the expansive domain of high-dimensional feature space is expressed as follows:…”

Section: Kmeans-svm Model Establishmentmentioning

confidence: 99%

Abnormal data detection method of smart substation based on K-means-SVM

Zhai,

Wu,

et al. 2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

The safe operation of smart substation is an important guarantee to ensure the stability of power supply. Aiming at the problems of substation data anomaly identification caused by large amount of substation data, complex data and high dimension, a smart substation anomaly data detection method based on K-means-SVM is proposed in this paper. Firstly, the unlabeled substation data is transformed into labeled data by K-means method, and then the unsupervised classification results provided by K-means are used as the training data of SVM. After SVM training, use the trained plane to test the two types of data obtained by K-means clustering, use the accurate data predicted by SVM to retrain the SVM segmentation plane, and iteratively update the SVM segmentation plane according to this method until the error number of SVM prediction data is not changed. This method can effectively improve the accuracy and efficiency of substation abnormal data identification, so as to improve the operation and maintenance safety and equipment maintenance ability.

show abstract

“…In recent years, deep learning methods based on computer vision have made great innovations and breakthroughs in the fields of image recognition and classification, target detection, etc. The use of deep learning methods for substation equipment detection technology eliminates the use of manual judgment of substation equipment monitoring video, which is more effective in liberating labour productivity and maximizing economic benefits [2]. Therefore, it is necessary to use the video image data recorded by the equipment status of the high-definition video inspection system of the substation operation and inspection centre to give full play to its role and carry out intelligent identification of abnormal status of equipment, deep learning-based substation equipment detection and identification has great research significance and practical value [3], which can improve the automation and intelligence level of unmanned substations and lay the foundation for further research and application of substation remote viewing methods.…”

Section: Introductionmentioning

confidence: 99%

A substation anomaly detection method based on improved Siamese networks

Cao,

Zhou,

Chen

et al. 2023

Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023)

View full text Add to dashboard Cite

An urgent problem in the process of substation anomaly detection is the scantiness of abnormal substation equipment samples. Conventional anomaly detection methods which use object-based detection are difficult to distinguish every type of equipment and unknown anomalies, leading to poor generalization. A substation anomaly detection method based on lightweight Siamese network is proposed to solve these problems, the distance between the image to be measured and the image of normal will be calculated in the method for detecting anomalies, so our method is able to deal with unknown samples, and data enhancement methods such as rotation, mirroring, and symmetry are used to expand the number of negative samples. The improved Siamese network adds ECA attention module to decrease the interference of background environment, ECA module performs channel feature learning on the compressed feature map, multiplies the original input feature map and the channel feature maps, and finally outputs the feature map with channel attention. The full connection layer calculates the distance of feature vector instead of the conventional Euclidean distance or cosine distance, expanding the difference value between positive and negative samples, and clarifying the threshold selection. This method has a good universality, it can meet the detection of various background environment and has high accuracy of detection work.

show abstract

An efficient foreign objects detection network for power substation

Cited by 19 publications

References 20 publications

A visual foreign object detection system for wireless charging of electric vehicles

A visual foreign object detection system for wireless charging of electric vehicles

Abnormal data detection method of smart substation based on K-means-SVM

A substation anomaly detection method based on improved Siamese networks

Contact Info

Product

Resources

About