Abstract:In order to realize intelligent video surveillance of substation, this paper presents a substation robot working state monitoring system based on video surveillance. In this paper, the intelligent monitoring system of substation robot working state is constructed by combining virtual reality technology. Through the cooperation of each unit in the system, the real-time monitoring of substation robot working state and the early warning of abnormal working state are realized. The system can transmit video data at… Show more
“…In this paper, we use one-dimensional convolution to extract local spatial features of network traffic data using two convolution kernel lengths of k. The computational equation is shown in formula (2).…”
Section: Feature Extraction and Detection 1) 1d Convolutionmentioning
confidence: 99%
“…As intelligent substations become increasingly networked and digitalized, the intelligence level of terminals is rising and the traffic information attached to terminals is also exploding. Due to the openness of TCP/IP architecture, denial-ofservice attacks, APT, port scanning, and other malicious attack methods are emerging, bringing a severe test to substation network security [1][2]. Intrusion Detection System (IDS) is a network security technology that instantly monitors network security and responds proactively to network attacks [3].…”
Massive wireless debugging terminals and complex and diverse access requirements pose significant challenges to the secure access of substation terminal equipment. It is crucial to detect anomaly network traffic to ensure the security of terminal access to the substation. At present, network traffic anomaly detection based on traditional deep learning often has the problem of low computational efficiency or weak representation ability. Given the low computational efficiency of traditional deep learning, the residual network is used to extract spatial features of data, which can effectively improve convergence speed and time efficiency. Aiming at the problem of weak representation ability of traditional machine learning methods, the long short-term memory network (LSTM) is used to improve the representation ability to learn while learning the temporal characteristics of traffic and prevent the gradient from disappearing and network degradation. Experimental results show that compared with the traditional deep learning method, the accuracy of the proposed method is improved, the F1 score reaches 90.09, and the AUC is up to 0.981. By improving anomaly detection accuracy, the paper further guarantees terminal security.
“…In this paper, we use one-dimensional convolution to extract local spatial features of network traffic data using two convolution kernel lengths of k. The computational equation is shown in formula (2).…”
Section: Feature Extraction and Detection 1) 1d Convolutionmentioning
confidence: 99%
“…As intelligent substations become increasingly networked and digitalized, the intelligence level of terminals is rising and the traffic information attached to terminals is also exploding. Due to the openness of TCP/IP architecture, denial-ofservice attacks, APT, port scanning, and other malicious attack methods are emerging, bringing a severe test to substation network security [1][2]. Intrusion Detection System (IDS) is a network security technology that instantly monitors network security and responds proactively to network attacks [3].…”
Massive wireless debugging terminals and complex and diverse access requirements pose significant challenges to the secure access of substation terminal equipment. It is crucial to detect anomaly network traffic to ensure the security of terminal access to the substation. At present, network traffic anomaly detection based on traditional deep learning often has the problem of low computational efficiency or weak representation ability. Given the low computational efficiency of traditional deep learning, the residual network is used to extract spatial features of data, which can effectively improve convergence speed and time efficiency. Aiming at the problem of weak representation ability of traditional machine learning methods, the long short-term memory network (LSTM) is used to improve the representation ability to learn while learning the temporal characteristics of traffic and prevent the gradient from disappearing and network degradation. Experimental results show that compared with the traditional deep learning method, the accuracy of the proposed method is improved, the F1 score reaches 90.09, and the AUC is up to 0.981. By improving anomaly detection accuracy, the paper further guarantees terminal security.
“…The main factors of mis-action are the operation value of the relay (voltage and power) and the distributed capacitance value of the cable to the ground [4] . Therefore, it is urgent to monitor the distributed capacitance value of the cable and analyze the changing trend, and predict the mis-action chance of the relay [5] . Therefore, based on the analysis and study of the allowable critical value of distributed capacitance under different faults, it is necessary to build a digital model to check whether the low voltage DC system has a mis-action risk for certainly distributed capacitance [6][7][8] .…”
The digital model for the typical faults of low voltage DC system is analyzed, and the analyzation system is developed to offline calculate and pre-analyses whether the fault results in mis-action of the low voltage DC system. Firstly, the digital model for typical faults of low voltage DC is analyzed based on the analytical method, and the mis-action power for typical faults is found. Secondly, the software for verification of the above analysis is developed, and typical cases are used to further verify the correctness and effectiveness of the developed software. In the tested case, the developed software can flexibly pre-analyses the mis-action of low voltage DC system for the targeted typical faults.
“…Therefore, many researchers use new technologies and methods to make substations more intelligent and reduce the use of manpower and resources. Such as in [5], the intelligent monitoring system of the substation robot's working state is constructed by combining virtual reality technology. And to improve the intelligence and automation for adapting to the development of prosumer substations, Wang et al [6] propose an isolation switch opening and closing position discrimination method based on intelligent image recognition technology.…”
This article designs a rapid debugging and automatic acceptance system for the comprehensive automation system of substations, mainly used for the automatic acceptance of information in intelligent substation monitoring systems. It achieves functions such as static verification of remote configuration, synchronous acceptance of remote information and on-site monitoring information, dynamic closed-loop verification of remote information, automatic triggering of remote information, and archiving of acceptance reports; By using computer software technology, communication technology, and other technological means to improve the automation level of the comprehensive automation system acceptance of substations, reduce the participation of various departments in the acceptance process, and reduce the workload of manual operation of primary and secondary equipment addition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.