Pub Date : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10470937
Jiang Chen, Sun Chuan, Xia Chao
Synchronous condensers offer significant benefits in large reactive power capacity and strong voltage support ability, which can effectively solve prominent problems such as commutation failure and voltage drop of ultra-high voltage DC converters. They are increasingly widely used in power grids. However, the large-capacity condenser has a large volume and complex structure and is prone to faults, which urgently requires research on fault feature analysis and diagnosis technology. This article analyzes the features of large-capacity synchronous condensers and their engineering advantages, such as increasing the short-circuit ratio of the receiving power grid, improving the transmission limit power, working in a forced excitation state for voltage support in the event of a commutation failure at the UHVDC receiving end, absorbing excess reactive power to suppress sudden voltage rise during DC blocking, and providing dynamically adjustable reactive power support for the AC power grid through flexible switching of late or leading phase states. This article provides common faults, such as mass imbalance, misalignment, friction, oil film oscillation, etc. At the same time, the fault characteristics are analyzed using computer simulation analysis, laboratory simulation analysis, and on-site measurement testing methods. A standard fault diagnosis method for synchronous condensers is proposed on this basis, utilizing fault pattern recognition and credibility evaluation. By establishing a library of fault models for the synchronous condenser and employing time-domain and frequency-domain signal analysis techniques, the credibility and nature of the fault are determined by calculating the instantaneous values and rate of change of the sampled signal using eigenvalues. Through the comparison and analysis of pertinent standards and historical data, the severity of the fault is ascertained, along with the trend and severity of the problematic synchronous condenser. The findings of this study have additionally advanced the progress of fault diagnosis technology for synchronous condensers with large capacities.
{"title":"Research on Fault Analysis and Remote Fault Diagnosis Technology of New Large Capacity Synchronous Condenser","authors":"Jiang Chen, Sun Chuan, Xia Chao","doi":"10.1109/ICPECA60615.2024.10470937","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470937","url":null,"abstract":"Synchronous condensers offer significant benefits in large reactive power capacity and strong voltage support ability, which can effectively solve prominent problems such as commutation failure and voltage drop of ultra-high voltage DC converters. They are increasingly widely used in power grids. However, the large-capacity condenser has a large volume and complex structure and is prone to faults, which urgently requires research on fault feature analysis and diagnosis technology. This article analyzes the features of large-capacity synchronous condensers and their engineering advantages, such as increasing the short-circuit ratio of the receiving power grid, improving the transmission limit power, working in a forced excitation state for voltage support in the event of a commutation failure at the UHVDC receiving end, absorbing excess reactive power to suppress sudden voltage rise during DC blocking, and providing dynamically adjustable reactive power support for the AC power grid through flexible switching of late or leading phase states. This article provides common faults, such as mass imbalance, misalignment, friction, oil film oscillation, etc. At the same time, the fault characteristics are analyzed using computer simulation analysis, laboratory simulation analysis, and on-site measurement testing methods. A standard fault diagnosis method for synchronous condensers is proposed on this basis, utilizing fault pattern recognition and credibility evaluation. By establishing a library of fault models for the synchronous condenser and employing time-domain and frequency-domain signal analysis techniques, the credibility and nature of the fault are determined by calculating the instantaneous values and rate of change of the sampled signal using eigenvalues. Through the comparison and analysis of pertinent standards and historical data, the severity of the fault is ascertained, along with the trend and severity of the problematic synchronous condenser. The findings of this study have additionally advanced the progress of fault diagnosis technology for synchronous condensers with large capacities.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"32 1-2","pages":"87-91"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530106","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10471131
Yuying Lu
Power load forecasting is of great significance and plays a vital role in the safe operation of the power system and the stability of power supply. Aiming at the problem of low prediction accuracy of single model, this paper proposes a prediction model based on the combination of Sparrow Search Algorithm (SSA) optimized Long Short-Term Memory Network (LSTM) and integrated algorithm. Multiple weak learners are first integrated through the AdaBoost algorithm to capture patterns and features in the data from multiple perspectives. Secondly, the collective intelligence and group collaboration ability of the SSA algorithm is utilized to ensure the global convergence of the algorithm, thus improving the prediction accuracy and robustness of the LSTM model. Finally, the model is analyzed and compared by examples to verify that the prediction accuracy of the model has been further improved.
{"title":"Study on Short-Term Electricity Load Forecasting Based on SSA-LSTM-AdaBoost Modeling","authors":"Yuying Lu","doi":"10.1109/ICPECA60615.2024.10471131","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471131","url":null,"abstract":"Power load forecasting is of great significance and plays a vital role in the safe operation of the power system and the stability of power supply. Aiming at the problem of low prediction accuracy of single model, this paper proposes a prediction model based on the combination of Sparrow Search Algorithm (SSA) optimized Long Short-Term Memory Network (LSTM) and integrated algorithm. Multiple weak learners are first integrated through the AdaBoost algorithm to capture patterns and features in the data from multiple perspectives. Secondly, the collective intelligence and group collaboration ability of the SSA algorithm is utilized to ensure the global convergence of the algorithm, thus improving the prediction accuracy and robustness of the LSTM model. Finally, the model is analyzed and compared by examples to verify that the prediction accuracy of the model has been further improved.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"79 4-6","pages":"1074-1079"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530475","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 the era of big data, traditional data clustering algorithms have gradually failed to meet the application requirements, and the optimization of data compression and parallelization methods has become a research hotspot. Based on the analysis of the traditional K-means clustering algorithm, this paper optimizes and improves the parallelized K-means algorithm, and proposes the Spark-Kmeans algorithm, which mainly retains the sample set distribution information by random sampling of large samples, and pre-clusters the samples in the nodes, and reclusters the pre-clustering in the convergence node. And it uses this as the initialization clustering center, so as to eliminate the problem of algorithm convergence instability caused by random initialization of the clustering center. Finally, single-node clustering and Spark-Kmeans clustering experiments are performed on the kdd_cup99 dataset and sklearn randomly generated dataset, and the effectiveness of the algorithm is verified by time-consuming, purity, error squared and indexes.
{"title":"Big data clustering method based on parallel K-means","authors":"Haibo Liu, Yongbin Bai, Zhenhao Chen, Zhenfeng Zhang","doi":"10.1109/ICPECA60615.2024.10470970","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470970","url":null,"abstract":"In the era of big data, traditional data clustering algorithms have gradually failed to meet the application requirements, and the optimization of data compression and parallelization methods has become a research hotspot. Based on the analysis of the traditional K-means clustering algorithm, this paper optimizes and improves the parallelized K-means algorithm, and proposes the Spark-Kmeans algorithm, which mainly retains the sample set distribution information by random sampling of large samples, and pre-clusters the samples in the nodes, and reclusters the pre-clustering in the convergence node. And it uses this as the initialization clustering center, so as to eliminate the problem of algorithm convergence instability caused by random initialization of the clustering center. Finally, single-node clustering and Spark-Kmeans clustering experiments are performed on the kdd_cup99 dataset and sklearn randomly generated dataset, and the effectiveness of the algorithm is verified by time-consuming, purity, error squared and indexes.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"120 2","pages":"893-897"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530362","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10471096
Boyu Liu, Wencui Li, Xinyan Wang, Ningxi Song, Zheng Zhou
The issue of privacy in electrical power data within smart grids has drawn increasing attention, with power data leakage posing a serious threat to users' personal privacy. Addressing these concerns, this paper proposes a power data privacy protection method based on secret sharing. Firstly, the method utilizes nodes elected through the leader election algorithm in the Raft protocol to replace traditional aggregators for data verification and aggregation operations. This eliminates the need for a trusted third party and enables fault tolerance for intermediate nodes. Secondly, the method incorporates a dynamic secret sharing homomorphic scheme to achieve secure data aggregation, ensuring that even internal attackers can only access aggregated data without obtaining individual power consumption details. Moreover, the scheme employs batch verification techniques to enhance signature verification speed. Experimental analysis indicates that this method exhibits lower computational and communication overhead compared to alternative approaches.
{"title":"A Power Data Privacy Protection Method Based on Secret Sharing","authors":"Boyu Liu, Wencui Li, Xinyan Wang, Ningxi Song, Zheng Zhou","doi":"10.1109/ICPECA60615.2024.10471096","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471096","url":null,"abstract":"The issue of privacy in electrical power data within smart grids has drawn increasing attention, with power data leakage posing a serious threat to users' personal privacy. Addressing these concerns, this paper proposes a power data privacy protection method based on secret sharing. Firstly, the method utilizes nodes elected through the leader election algorithm in the Raft protocol to replace traditional aggregators for data verification and aggregation operations. This eliminates the need for a trusted third party and enables fault tolerance for intermediate nodes. Secondly, the method incorporates a dynamic secret sharing homomorphic scheme to achieve secure data aggregation, ensuring that even internal attackers can only access aggregated data without obtaining individual power consumption details. Moreover, the scheme employs batch verification techniques to enhance signature verification speed. Experimental analysis indicates that this method exhibits lower computational and communication overhead compared to alternative approaches.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"10 3","pages":"1366-1370"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530310","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10471116
Xizhou Wang
With the dramatic growth of video data, the storage and computational resources required to process this huge amount of data have increased significantly. In order to cope with this challenge, it is necessary to extract the key information in the video in a more intelligent and efficient way, while filtering out a large amount of redundant content. In this paper, the traditional CNN model and Transformer model are constructed respectively using video frames of car motion process from video viewpoint as a dataset. The model performance is improved by advanced data preprocessing operations. The bilateral filtering technique is introduced in this study, aiming to improve the image quality and enhance the image processing effect through denoising operations, making it more applicable to the subsequent processing steps. Finally, the Transformer model is verified by the model and the recognition accuracy of the Transformer model is up to about 90%.
{"title":"Deep Learning Based Motion Target Detection Algorithm","authors":"Xizhou Wang","doi":"10.1109/ICPECA60615.2024.10471116","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471116","url":null,"abstract":"With the dramatic growth of video data, the storage and computational resources required to process this huge amount of data have increased significantly. In order to cope with this challenge, it is necessary to extract the key information in the video in a more intelligent and efficient way, while filtering out a large amount of redundant content. In this paper, the traditional CNN model and Transformer model are constructed respectively using video frames of car motion process from video viewpoint as a dataset. The model performance is improved by advanced data preprocessing operations. The bilateral filtering technique is introduced in this study, aiming to improve the image quality and enhance the image processing effect through denoising operations, making it more applicable to the subsequent processing steps. Finally, the Transformer model is verified by the model and the recognition accuracy of the Transformer model is up to about 90%.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"13 13","pages":"943-948"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530135","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10470979
Geng Sun, Guotao Peng, Xiaolei Tian, Lu Li, Yuqi Zhao, Yue Wang
Traditional knowledge graph retrieval techniques ignore node relationship weights, making it difficult to achieve targeted retrieval. Therefore, a nonlinear model AGCN-WGAN is proposed to solve retrieval tasks in relational networks, fully utilizing the advantages of Graph Convolutional Networks (GCN) and Generative Adversarial Networks (GAN). Firstly, AGCN is used to capture the local topological features of a single node; In addition, the use of GAN enhances the ability of AGCN models to generate reasonable weight distribution maps, effectively extracting correlations between nodes, thereby improving the performance of the model in handling large-scale data retrieval tasks. In order to verify the effectiveness of the method, the dispatching operation data in a real business scenario of a city power grid is used for experiments. The experimental results show that the proposed data retrieval method has significantly improved accuracy compared to existing methods.
{"title":"A Data Retrieval Method Based on AGCN-WGAN","authors":"Geng Sun, Guotao Peng, Xiaolei Tian, Lu Li, Yuqi Zhao, Yue Wang","doi":"10.1109/ICPECA60615.2024.10470979","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470979","url":null,"abstract":"Traditional knowledge graph retrieval techniques ignore node relationship weights, making it difficult to achieve targeted retrieval. Therefore, a nonlinear model AGCN-WGAN is proposed to solve retrieval tasks in relational networks, fully utilizing the advantages of Graph Convolutional Networks (GCN) and Generative Adversarial Networks (GAN). Firstly, AGCN is used to capture the local topological features of a single node; In addition, the use of GAN enhances the ability of AGCN models to generate reasonable weight distribution maps, effectively extracting correlations between nodes, thereby improving the performance of the model in handling large-scale data retrieval tasks. In order to verify the effectiveness of the method, the dispatching operation data in a real business scenario of a city power grid is used for experiments. The experimental results show that the proposed data retrieval method has significantly improved accuracy compared to existing methods.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"3 6","pages":"13-17"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530114","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10471126
Zhishuai Liu, Zhengyang Wei, Jiangnan Li
With the continuous progress of photovoltaic (PV) technology and the steady reduction of related costs, solar energy, as an important renewable energy source, shows an increasingly strong competitiveness in energy market competition. In the tower solar thermal power station, the arrangement of the heliostat field directly affects the power generation efficiency of the tower power generation system as well as the working cost. Therefore, this paper presents a model based on geometric relationship and particle swarm algorithm for the optimization of the heliostat field arrangement, mathematical modeling and calculating cosine efficiency, truncation efficiency, etc., and effectively improves the output thermal power as well as the optical efficiency of the heliostat field. Geometric planning is utilized to determine the location of the absorption tower, the coordinates of the heliostat arrangement and other layout parameters to optimize the layout of the tower solar system. Drawing on the idea of clustering, the model analyzes the characteristics of the heliostat mirrors in the same region, uses same or similar parameters to minimize the cost of computation, improving the overall optical efficiency of the mirror field. The particle swarm algorithm is utilized to solve the parameters such as mirror length and mirror width of the heliostat to get the suitable size of the heliostat for the heliostat mirror field. After completing all the calculation and optimization steps, the final solution of the model is carried out in this paper. The layout scheme of the heliostat field optimized by the implementation of the model gets a significant performance improvement. Specifically, the average annual thermal power output of the heliostat field is improved by 33.2309 MW, while the average annual optical efficiency is also improved by 43.2%. These improvements effectively enhance the power generation efficiency of the whole system, confirming the effectiveness of the optimization method in this paper.
{"title":"Optimization of Heliostat Field Arrangement Model Based on Geometric Relationship and Particle Swarm Algorithm","authors":"Zhishuai Liu, Zhengyang Wei, Jiangnan Li","doi":"10.1109/ICPECA60615.2024.10471126","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471126","url":null,"abstract":"With the continuous progress of photovoltaic (PV) technology and the steady reduction of related costs, solar energy, as an important renewable energy source, shows an increasingly strong competitiveness in energy market competition. In the tower solar thermal power station, the arrangement of the heliostat field directly affects the power generation efficiency of the tower power generation system as well as the working cost. Therefore, this paper presents a model based on geometric relationship and particle swarm algorithm for the optimization of the heliostat field arrangement, mathematical modeling and calculating cosine efficiency, truncation efficiency, etc., and effectively improves the output thermal power as well as the optical efficiency of the heliostat field. Geometric planning is utilized to determine the location of the absorption tower, the coordinates of the heliostat arrangement and other layout parameters to optimize the layout of the tower solar system. Drawing on the idea of clustering, the model analyzes the characteristics of the heliostat mirrors in the same region, uses same or similar parameters to minimize the cost of computation, improving the overall optical efficiency of the mirror field. The particle swarm algorithm is utilized to solve the parameters such as mirror length and mirror width of the heliostat to get the suitable size of the heliostat for the heliostat mirror field. After completing all the calculation and optimization steps, the final solution of the model is carried out in this paper. The layout scheme of the heliostat field optimized by the implementation of the model gets a significant performance improvement. Specifically, the average annual thermal power output of the heliostat field is improved by 33.2309 MW, while the average annual optical efficiency is also improved by 43.2%. These improvements effectively enhance the power generation efficiency of the whole system, confirming the effectiveness of the optimization method in this paper.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"6 2","pages":"365-373"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530460","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 paper focuses on the control system of pure solar powered electric vehicle Tianjin No.2 and proposes a double fuzzy controller scheme based on PID control system. The method can provide certain algorithm support for the stable and intelligent operation of photovoltaic support mechanisms with large aspect ratio and large light receiving area. The paper is based on the traditional PID control method of DC motors, proposing a fuzzy processing scheme for three parameters of PID, i.e. proportion, integration, and differentiation. At the same time, the sensing signals from wind and sunlight are also computed with fuzzy processing. Finally, through reasonable determination of parameters, adjustment of fuzzy control decisions, and simulation verification, the results show that the proposed method can provide theoretical and practical support for the stable and intelligent movement of this type of support mechanism.
{"title":"The Study of Motion Control Algorithm for the Wing Mechanism of Solar-Powered Electric Vehicle","authors":"Mengjun Song, Jinggong Wei, Yaming Wang, Jianfeng Cheng","doi":"10.1109/ICPECA60615.2024.10471154","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471154","url":null,"abstract":"The paper focuses on the control system of pure solar powered electric vehicle Tianjin No.2 and proposes a double fuzzy controller scheme based on PID control system. The method can provide certain algorithm support for the stable and intelligent operation of photovoltaic support mechanisms with large aspect ratio and large light receiving area. The paper is based on the traditional PID control method of DC motors, proposing a fuzzy processing scheme for three parameters of PID, i.e. proportion, integration, and differentiation. At the same time, the sensing signals from wind and sunlight are also computed with fuzzy processing. Finally, through reasonable determination of parameters, adjustment of fuzzy control decisions, and simulation verification, the results show that the proposed method can provide theoretical and practical support for the stable and intelligent movement of this type of support mechanism.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"123 8","pages":"1243-1249"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530464","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10470998
An Ning
This article proposes a platform of container-based continuous integration development and operations. It is a code continuous integration and automation operations platform based on the Kubernetes container environment. The platform leverage the capabilities and features of containers to achieve automation from development to deployment.
{"title":"A Container-Based Continuous Integration Development and Operations Platform","authors":"An Ning","doi":"10.1109/ICPECA60615.2024.10470998","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470998","url":null,"abstract":"This article proposes a platform of container-based continuous integration development and operations. It is a code continuous integration and automation operations platform based on the Kubernetes container environment. The platform leverage the capabilities and features of containers to achieve automation from development to deployment.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"82 1","pages":"1201-1204"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530474","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 : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10470944
Xingtao Bai, Ningguo Wang, Yongliang Li, Hai-Jun Luo, Bo Gao
This paper studied the methods for improving the accuracy and efficiency of the action of power employees by deeply studying the application of neural network algorithm in power safety supervision video. Firstly, this paper summarizes the research status of power safety monitoring system and related action recognition algorithms. For the power industry, timely and accurate identification of workers' movements is essential for accident prevention and management. In this context, various motion recognition algorithms are emerging, among which neural network algorithm has attracted much attention due to its excellent performance in image processing and pattern recognition. Through deep learning, neural networks can automatically learn key features from a large number of video data, providing a more reliable means for human action recognition. Secondly, this paper introduces in detail the proposed method of power safety monitoring video personnel action recognition based on neural network algorithm. Through the optimization of neural network structure and the careful selection of training data, we construct an efficient and accurate action recognition model. The model can quickly and accurately identify the actions of different personnel at work by monitoring the video of electric power operation, including common operation actions and special actions in emergency situations. Our method can more comprehensively understand the various actions of personnel in the electric power environment. Through the analysis of a large number of experimental results, we verify the effectiveness and robustness of the proposed algorithm. Compared with traditional methods, the motion recognition algorithm based on neural network has achieved significant improvement in accuracy and response speed. This proves the practical application prospect of this method in the field of power safety supervision.
{"title":"Research on Power Safety Monitoring Action Recognition Algorithm Through Neural Network and Deep Learning","authors":"Xingtao Bai, Ningguo Wang, Yongliang Li, Hai-Jun Luo, Bo Gao","doi":"10.1109/ICPECA60615.2024.10470944","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470944","url":null,"abstract":"This paper studied the methods for improving the accuracy and efficiency of the action of power employees by deeply studying the application of neural network algorithm in power safety supervision video. Firstly, this paper summarizes the research status of power safety monitoring system and related action recognition algorithms. For the power industry, timely and accurate identification of workers' movements is essential for accident prevention and management. In this context, various motion recognition algorithms are emerging, among which neural network algorithm has attracted much attention due to its excellent performance in image processing and pattern recognition. Through deep learning, neural networks can automatically learn key features from a large number of video data, providing a more reliable means for human action recognition. Secondly, this paper introduces in detail the proposed method of power safety monitoring video personnel action recognition based on neural network algorithm. Through the optimization of neural network structure and the careful selection of training data, we construct an efficient and accurate action recognition model. The model can quickly and accurately identify the actions of different personnel at work by monitoring the video of electric power operation, including common operation actions and special actions in emergency situations. Our method can more comprehensively understand the various actions of personnel in the electric power environment. Through the analysis of a large number of experimental results, we verify the effectiveness and robustness of the proposed algorithm. Compared with traditional methods, the motion recognition algorithm based on neural network has achieved significant improvement in accuracy and response speed. This proves the practical application prospect of this method in the field of power safety supervision.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"11 2","pages":"990-994"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530138","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：