Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005548
Xinghui Wu, Min Wang
In the process of multi-target tracking, error observation and noise should be excluded and associated with the actual target observation value. Especially in the case of nonlinear motion, the difficulty of correlation rises sharply. To solve the decreasing correlation accuracy in nonlinear motion, a Generalized Labeled Multi-Bernoulli (GLMB) filter based on an Uncorrelated Conversion (UC) named UC-GLMB filter was proposed in this paper. Firstly, this method can effectively obtain more measurement information and is applied to the linear estimator. Secondly, it is an effective solution for multiple nonlinear moving target tracking problems based on random finite sets (RFS). Thus, the performance of the UC-GLMB filter may be continually improved. Simulation results demonstrate the effectiveness of the proposed estimator compared with some popular multi-target tracking algorithms.
{"title":"GMLB Filter With Uncorrelated Conversion for Multi Nonlinear Targets Tracking","authors":"Xinghui Wu, Min Wang","doi":"10.1109/ICSAI57119.2022.10005548","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005548","url":null,"abstract":"In the process of multi-target tracking, error observation and noise should be excluded and associated with the actual target observation value. Especially in the case of nonlinear motion, the difficulty of correlation rises sharply. To solve the decreasing correlation accuracy in nonlinear motion, a Generalized Labeled Multi-Bernoulli (GLMB) filter based on an Uncorrelated Conversion (UC) named UC-GLMB filter was proposed in this paper. Firstly, this method can effectively obtain more measurement information and is applied to the linear estimator. Secondly, it is an effective solution for multiple nonlinear moving target tracking problems based on random finite sets (RFS). Thus, the performance of the UC-GLMB filter may be continually improved. Simulation results demonstrate the effectiveness of the proposed estimator compared with some popular multi-target tracking algorithms.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128492038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005459
Lin Yuan, Zhen He, Qianqian Wang, Leiyang Xu, Xiang Ma
Human action recognition has been a hot research for decades, and mainstream supervised frameworks include a feature extraction backbone and a softmax classifier to predict daily human actions. When the number of classes applied to the dataset changes, we must retrain the classifier on the well-trained backbone. This pipeline restricts the generalization and transfer ability of the model due to an extra training period. Moreover, replacing action labels with simple number labels discards useful semantic information and can only receive a meaningless classifier at last. In this work, we present a model SkeletonCLIP for skeleton-based human action recognition. We add an alternative text encoder to extract semantic information from labels while keeping the original sequence encoder. We use dot production to measure the similarities of sequence-text pairs in place of traditional classifier head and cross-entropy loss. Experiments from three human action datasets show that our framework can reach a higher recognition accuracy with the help of semantic information when training the network from scratch. The code has been shown at eunseo-v/SkeletonCLIP.
{"title":"SkeletonCLIP: Recognizing Skeleton-based Human Actions with Text Prompts","authors":"Lin Yuan, Zhen He, Qianqian Wang, Leiyang Xu, Xiang Ma","doi":"10.1109/ICSAI57119.2022.10005459","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005459","url":null,"abstract":"Human action recognition has been a hot research for decades, and mainstream supervised frameworks include a feature extraction backbone and a softmax classifier to predict daily human actions. When the number of classes applied to the dataset changes, we must retrain the classifier on the well-trained backbone. This pipeline restricts the generalization and transfer ability of the model due to an extra training period. Moreover, replacing action labels with simple number labels discards useful semantic information and can only receive a meaningless classifier at last. In this work, we present a model SkeletonCLIP for skeleton-based human action recognition. We add an alternative text encoder to extract semantic information from labels while keeping the original sequence encoder. We use dot production to measure the similarities of sequence-text pairs in place of traditional classifier head and cross-entropy loss. Experiments from three human action datasets show that our framework can reach a higher recognition accuracy with the help of semantic information when training the network from scratch. The code has been shown at eunseo-v/SkeletonCLIP.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126167507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The missile interception problem is considered in this article. As in practical applications, the real states are not available due to the existence of measurement noises and model parameter uncertainties, desensitized extended Kalman filter (DEKF) is applied to generate reliable state estimations. Compared to standard extend Kalman filter (EKF), this approach calculates state estimations by optimizing a cost function with one additional term, which reflects the state estimate error sensitivities. Such a design makes the filter less sensitive to model parameter uncertainties and can be considered as a generalization of the standard EKF. Simulation studies are conducted to evaluate the performance of DEKF when applying to integrated missile-target interception model.
{"title":"Missile Interception Guidance With Parameter Uncertainties Using Desensitized Extended Kalman Filter","authors":"Jingsong Yang, Wei Hu, Tianhao Liu, Lingguo Cui, Jia Liang","doi":"10.1109/ICSAI57119.2022.10005408","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005408","url":null,"abstract":"The missile interception problem is considered in this article. As in practical applications, the real states are not available due to the existence of measurement noises and model parameter uncertainties, desensitized extended Kalman filter (DEKF) is applied to generate reliable state estimations. Compared to standard extend Kalman filter (EKF), this approach calculates state estimations by optimizing a cost function with one additional term, which reflects the state estimate error sensitivities. Such a design makes the filter less sensitive to model parameter uncertainties and can be considered as a generalization of the standard EKF. Simulation studies are conducted to evaluate the performance of DEKF when applying to integrated missile-target interception model.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005481
Xuan Liu, Jiachen Ma, Qianqian Wang
Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and has numerous applications. Enhancing the discriminative features extraction ability is one approach to solving this issue. In this work, a sparse transform is used to improve a CNN’s ability to extract features without adding to the network’s computational load. We use a sparse representation layer that is built by the Haar wavelet transform or shearlet transform prior to the convolutional layers of a standard CNN. With the proposed sparse representation layers, we introduce a VGGNet and an AlexNet architecture and conduct experiments on the FER2013 dataset without the use of additional training data. The experimental results demonstrated that the wavelet transform’s sparse representation layer can improve FER performance without increasing an excessive computational burden. We achieved testing accuracy of 73.25 percent on the FER2013 dataset using VGGNet paired with a sparse representation layer built inside a wavelet transform, which is among the best results for a single network.
{"title":"Facial Expression Recognition based on Convolutional Neural Network with Sparse Representation","authors":"Xuan Liu, Jiachen Ma, Qianqian Wang","doi":"10.1109/ICSAI57119.2022.10005481","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005481","url":null,"abstract":"Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) has been a challenge for years because of the significant intra-class variances and interclass similarities. In contrast, facial expression recognition in the wild is vital for human-computer interactions and has numerous applications. Enhancing the discriminative features extraction ability is one approach to solving this issue. In this work, a sparse transform is used to improve a CNN’s ability to extract features without adding to the network’s computational load. We use a sparse representation layer that is built by the Haar wavelet transform or shearlet transform prior to the convolutional layers of a standard CNN. With the proposed sparse representation layers, we introduce a VGGNet and an AlexNet architecture and conduct experiments on the FER2013 dataset without the use of additional training data. The experimental results demonstrated that the wavelet transform’s sparse representation layer can improve FER performance without increasing an excessive computational burden. We achieved testing accuracy of 73.25 percent on the FER2013 dataset using VGGNet paired with a sparse representation layer built inside a wavelet transform, which is among the best results for a single network.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129686186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005363
Minrui Xu, Gang Chen, Shufeng Lu, Zigang Lu, Feng Ji, Zengkai Ouyang
This paper designs an extreme high voltage and highstability test voltage source. First of all, the design of a highstability direct current(DC) voltage source is realized by using a high-frequency transformer and a two-stage boosting method of a voltage-doubling rectifier circuit. In this way, a voltage source with lower ripple factor and higher stability can be obtained. Then, in order to obtain a fast and free experimental platform, this paper designs an integrated voltage doubling and pressure measurement for the structure of the DC voltage source voltage equalization system, and effectively solves the problem of series voltage equalization of high-voltage silicon stacks. According to the scheme of this paper, the voltage source is designed, the output voltage is 1100kV, the ripple coefficient is 0.059%, and the stability is better than 0.05%/h. It reaches the domestic leading level which has been successfully applied to the DC voltage transformer of ±400kV sense converter station in Lhasa.
{"title":"Design of Extreme High Voltage High Stability Test Voltage Source","authors":"Minrui Xu, Gang Chen, Shufeng Lu, Zigang Lu, Feng Ji, Zengkai Ouyang","doi":"10.1109/ICSAI57119.2022.10005363","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005363","url":null,"abstract":"This paper designs an extreme high voltage and highstability test voltage source. First of all, the design of a highstability direct current(DC) voltage source is realized by using a high-frequency transformer and a two-stage boosting method of a voltage-doubling rectifier circuit. In this way, a voltage source with lower ripple factor and higher stability can be obtained. Then, in order to obtain a fast and free experimental platform, this paper designs an integrated voltage doubling and pressure measurement for the structure of the DC voltage source voltage equalization system, and effectively solves the problem of series voltage equalization of high-voltage silicon stacks. According to the scheme of this paper, the voltage source is designed, the output voltage is 1100kV, the ripple coefficient is 0.059%, and the stability is better than 0.05%/h. It reaches the domestic leading level which has been successfully applied to the DC voltage transformer of ±400kV sense converter station in Lhasa.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122234889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In e-commerce, long product titles with rich information help attract users, but they are usually truncated for display on small-screen mobile devices, which results in neglection of important information and in turn low click-through rate. This paper presents a novel product title summarization method via the use of a mask-based text information scoring network. Via quantified evaluation of expressiveness, the most telling points are identified from the original title for a concise version which best retains its content. Our experiments show that, even without external information, our proposed method MPTS outperforms established benchmark models by 1.48% (ROUGE-1), 5.11% (ROUGE-2) and 1.37% (ROUGE-L) respectively.
{"title":"Mask-based Text Scoring for Product Title Summarization","authors":"Xinyi Guan, Shun Long, Weiheng Zhu, Silei Cao, Fangting Liao","doi":"10.1109/ICSAI57119.2022.10005399","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005399","url":null,"abstract":"In e-commerce, long product titles with rich information help attract users, but they are usually truncated for display on small-screen mobile devices, which results in neglection of important information and in turn low click-through rate. This paper presents a novel product title summarization method via the use of a mask-based text information scoring network. Via quantified evaluation of expressiveness, the most telling points are identified from the original title for a concise version which best retains its content. Our experiments show that, even without external information, our proposed method MPTS outperforms established benchmark models by 1.48% (ROUGE-1), 5.11% (ROUGE-2) and 1.37% (ROUGE-L) respectively.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"465 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129627069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005557
Khalil Ur Rahman, Huifang Ma, Ali Arshad, Azad Khan Baheer
Heterogeneous Graph Neural Networks (GNNs) have shown good performance as a robust deep learning-based graph representation technique and have gained much research interest. Although it has adequately taken into account networks with a number of links and nodes, heterogeneity and the volume of semantic data provide significant obstacles. The attention mechanism, having great potential in a variety of areas, is one of the most interesting new developments in deep learning. This research demonstrates a system with two crucial attributes for embedding users and movies. The proposed framework achieves multi-level semantic attention using GNNs. We incorporated IMDB and Netflix Movie and TV Show datasets and merged them into a single consolidated dataset that was further utilized for results analysis. This paper mainly contributes a technique for movie recommendation using heterogeneous graphs and multi-level Semitics. We have proposed a framework that incorporates viewer and Director as an entity. During the research, we also combined two datasets in accordance with the proposed framework. After that, we evaluated the performance of the graph neural network on the heterogeneous graph. We discovered that the proposed model outperformed the current methodologies while using the proposed technique. Our model multilevel-Semitics-based framework shows effective results.
{"title":"Movie Recommender System Based On Heterogeneous Graph Neural Networks","authors":"Khalil Ur Rahman, Huifang Ma, Ali Arshad, Azad Khan Baheer","doi":"10.1109/ICSAI57119.2022.10005557","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005557","url":null,"abstract":"Heterogeneous Graph Neural Networks (GNNs) have shown good performance as a robust deep learning-based graph representation technique and have gained much research interest. Although it has adequately taken into account networks with a number of links and nodes, heterogeneity and the volume of semantic data provide significant obstacles. The attention mechanism, having great potential in a variety of areas, is one of the most interesting new developments in deep learning. This research demonstrates a system with two crucial attributes for embedding users and movies. The proposed framework achieves multi-level semantic attention using GNNs. We incorporated IMDB and Netflix Movie and TV Show datasets and merged them into a single consolidated dataset that was further utilized for results analysis. This paper mainly contributes a technique for movie recommendation using heterogeneous graphs and multi-level Semitics. We have proposed a framework that incorporates viewer and Director as an entity. During the research, we also combined two datasets in accordance with the proposed framework. After that, we evaluated the performance of the graph neural network on the heterogeneous graph. We discovered that the proposed model outperformed the current methodologies while using the proposed technique. Our model multilevel-Semitics-based framework shows effective results.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005527
Jiamin Huang, Ming Yan, Jiacheng Zhou, Xiaojun Zhang, YuJie Jiang, Zhi Tao
With the aging Chinese population and the increasing awareness of caring for vulnerable groups such as the blind, how to ensure the safety of medication in the state of living alone has attracted increasing attention. This paper proposes an intelligent recognition method for home medicine boxes. The drug name position is accurately determined after we preprocess the image photographed by the camera. Then the algorithm recognizes the character and puts it into a database for retrieval. According to the information from the retrieved speech, the algorithm tells the user the name of the drug and how to use it. The experimental results show that the method adopted in this paper has a high recognition rate for the information of common drug boxes in the market and a good promotional value.
{"title":"Design and Development of a Medicine Box Recognition System Based on Machine Vision","authors":"Jiamin Huang, Ming Yan, Jiacheng Zhou, Xiaojun Zhang, YuJie Jiang, Zhi Tao","doi":"10.1109/ICSAI57119.2022.10005527","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005527","url":null,"abstract":"With the aging Chinese population and the increasing awareness of caring for vulnerable groups such as the blind, how to ensure the safety of medication in the state of living alone has attracted increasing attention. This paper proposes an intelligent recognition method for home medicine boxes. The drug name position is accurately determined after we preprocess the image photographed by the camera. Then the algorithm recognizes the character and puts it into a database for retrieval. According to the information from the retrieved speech, the algorithm tells the user the name of the drug and how to use it. The experimental results show that the method adopted in this paper has a high recognition rate for the information of common drug boxes in the market and a good promotional value.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"70 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120891996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-10DOI: 10.1109/ICSAI57119.2022.10005320
Xiangyuan Zhu, Xiaozhou Dong, Hong Nie, Yusen Cen
Person re-identification (ReID) is a popular research topic in computer vision. It focuses on matching a given person from an image dataset captured by many non-overlapping cameras. It remains challenging duo to the influences of pose, illumination, occlusion, and background confusion. In this paper, an improved ReID approach based on the AlignedReID ++ algorithm is proposed. Three effective training tricks are introduced to improve the effectiveness of the AlignedReID ++ algorithm. Training loss, accuracy, and mean average precision (mAP) are used as measure metrics. Extensive experiments are implemented on the ResNet50 and DenseNet121 backbone networks. Our implementation gains the Rank-1 accuracy and mAP of 93.7% and 91.2%, respectively. The source code of the improved AlignReID ++ method is available on request.
{"title":"An Improved Person Re-Identification Method based on AlignedReID ++ algorithm","authors":"Xiangyuan Zhu, Xiaozhou Dong, Hong Nie, Yusen Cen","doi":"10.1109/ICSAI57119.2022.10005320","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005320","url":null,"abstract":"Person re-identification (ReID) is a popular research topic in computer vision. It focuses on matching a given person from an image dataset captured by many non-overlapping cameras. It remains challenging duo to the influences of pose, illumination, occlusion, and background confusion. In this paper, an improved ReID approach based on the AlignedReID ++ algorithm is proposed. Three effective training tricks are introduced to improve the effectiveness of the AlignedReID ++ algorithm. Training loss, accuracy, and mean average precision (mAP) are used as measure metrics. Extensive experiments are implemented on the ResNet50 and DenseNet121 backbone networks. Our implementation gains the Rank-1 accuracy and mAP of 93.7% and 91.2%, respectively. The source code of the improved AlignReID ++ method is available on request.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121534015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of the power distribution system and equipment diversification, the accuracy of setting values is required to be at a high level to realize well protection coordination for the relay protection system. The inaccurate setting values and defective protections may lead to lots of severe accidents, such as, the arc flash accident, which has been paid more attention recently. In this paper, a relay protection method considering the influence of arc fault is proposed. Then, the electrical engineering software is used to perform a more accurate setting calculation and protection coordination. Also, the arc flash hazard is weakened by the arc flash protection device. Based on the results, the modified configuration of relay protection can protect the power distribution system more effectively.
{"title":"Setting Calculation Method and Protection Coordination for Relay Protection System in Consideration of Arc Flash","authors":"Fang Jinghui, Zhang Bo, Zhong Weidong, Feng Jian, Jin Guozhong, Gao Xijun, Wei Ling","doi":"10.1109/ICSAI57119.2022.10005389","DOIUrl":"https://doi.org/10.1109/ICSAI57119.2022.10005389","url":null,"abstract":"With the development of the power distribution system and equipment diversification, the accuracy of setting values is required to be at a high level to realize well protection coordination for the relay protection system. The inaccurate setting values and defective protections may lead to lots of severe accidents, such as, the arc flash accident, which has been paid more attention recently. In this paper, a relay protection method considering the influence of arc fault is proposed. Then, the electrical engineering software is used to perform a more accurate setting calculation and protection coordination. Also, the arc flash hazard is weakened by the arc flash protection device. Based on the results, the modified configuration of relay protection can protect the power distribution system more effectively.","PeriodicalId":339547,"journal":{"name":"2022 8th International Conference on Systems and Informatics (ICSAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132599739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：