Pub Date : 2024-01-26DOI: 10.1109/ICPECA60615.2024.10471149
Junhong Ni, Mengqi Cui
Electricity consumption is the barometer and weathervane of economic development. In this research, a deep learning long term electricity consumption prediction model based on data enhancement is proposed, and the long term power time series is investigated by using the deep learning method and data enhancement techniques. Firstly, the monthly power quantity is upsampled by interpolation method to generate data with finer granularity, and data points are extracted at equal intervals to form a data series with the same dimension as the original data. Secondly, the augmented data are used as inputs to the deep learning model, so as to allow the deep learning model to have a better generalization ability in the presence of more training data, thus attenuating the over fitting problem of the model. The deep learning model is adopted respectively. LSTM model, Bi-LSTM model, GRU model and MLP model were used. Finally, the model was verified to have a high prediction accuracy using the electricity consumption of urban residents in a province.
{"title":"Long Term Electricity Consumption Forecast Based on DA-LSTM","authors":"Junhong Ni, Mengqi Cui","doi":"10.1109/ICPECA60615.2024.10471149","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471149","url":null,"abstract":"Electricity consumption is the barometer and weathervane of economic development. In this research, a deep learning long term electricity consumption prediction model based on data enhancement is proposed, and the long term power time series is investigated by using the deep learning method and data enhancement techniques. Firstly, the monthly power quantity is upsampled by interpolation method to generate data with finer granularity, and data points are extracted at equal intervals to form a data series with the same dimension as the original data. Secondly, the augmented data are used as inputs to the deep learning model, so as to allow the deep learning model to have a better generalization ability in the presence of more training data, thus attenuating the over fitting problem of the model. The deep learning model is adopted respectively. LSTM model, Bi-LSTM model, GRU model and MLP model were used. Finally, the model was verified to have a high prediction accuracy using the electricity consumption of urban residents in a province.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"10 8","pages":"196-200"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530117","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/ICPECA60615.2024.10471128
Zhiyong Liu
Following the proposal of ‘carbon neutrality and carbon peaking’ goals, a high proportion of renewable energy is expected to be connected to the transmission network. In response to the significant challenges posed by the strong randomness and centralized, high-capacity integration of wind and photovoltaic power, which affects the safe operation of the transmission network and the consumption of new energy, this approach considers the uncertainty and time correlation of wind and photovoltaic output. This paper proposes a method of distributed by the transmission channel of high -proportion new energy access channels and energy storage. In this method, the planning of external transmission channels and energy storage is jointly used as decision variables. Surplus renewable energy resources are dispatched through the external transmission channels, while energy storage functions are utilized for peak shaving, valley filling, and suppressing the random fluctuations of new energy, thereby promoting the full consumption of renewable energy. Then, using techniques such as second-order cone convex relaxation and Taylor series expansion, the original mixed integer non-convex nonlinear programming model is transformed into a mixed integer convex programming model to achieve efficient solution. Finally, an improved IEEE 39-bus transmission system is taken as a case study to verify the validity of the proposed model and method.
{"title":"Distributionally Robust Collaborative Planning Method for Transmission Network External Channel and Energy Storage with High Proportion of Renewable Energy","authors":"Zhiyong Liu","doi":"10.1109/ICPECA60615.2024.10471128","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471128","url":null,"abstract":"Following the proposal of ‘carbon neutrality and carbon peaking’ goals, a high proportion of renewable energy is expected to be connected to the transmission network. In response to the significant challenges posed by the strong randomness and centralized, high-capacity integration of wind and photovoltaic power, which affects the safe operation of the transmission network and the consumption of new energy, this approach considers the uncertainty and time correlation of wind and photovoltaic output. This paper proposes a method of distributed by the transmission channel of high -proportion new energy access channels and energy storage. In this method, the planning of external transmission channels and energy storage is jointly used as decision variables. Surplus renewable energy resources are dispatched through the external transmission channels, while energy storage functions are utilized for peak shaving, valley filling, and suppressing the random fluctuations of new energy, thereby promoting the full consumption of renewable energy. Then, using techniques such as second-order cone convex relaxation and Taylor series expansion, the original mixed integer non-convex nonlinear programming model is transformed into a mixed integer convex programming model to achieve efficient solution. Finally, an improved IEEE 39-bus transmission system is taken as a case study to verify the validity of the proposed model and method.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"22 5-6","pages":"69-76"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530126","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/ICPECA60615.2024.10471035
Miaofang Shen
The relationships between entities in a document are extracted according to natural language processing methods. Deep neural network is used to recognize the required multi-label text. According to the general specification, the system is optimized, and the design and implementation of the system are obtained. This project explores four major NLP modes such as ALBERT, RNN Search, BERT-CRF, Text ING based on the high-performance hardware of the Centeno platform. According to the element relation, tree structure and network structure, a general MNet construction method is proposed. The extracted correlation information is used to determine whether the matching conditions of each security requirement template are established, and then the final set of security requirement templates is screened. The extracted security requirements are modeled and instantiated in this way. Simulation results show that the model can deal with semantic dependency and human-computer interaction in complex systems. By analyzing the semantics of the operation interface in SCADA system, it is transformed into a general MNet construction, which lays a foundation for realizing the semantic analysis of users.
{"title":"Research on the Application of AI Intelligent Model of Computer Deep Learning in Natural Language Processing","authors":"Miaofang Shen","doi":"10.1109/ICPECA60615.2024.10471035","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471035","url":null,"abstract":"The relationships between entities in a document are extracted according to natural language processing methods. Deep neural network is used to recognize the required multi-label text. According to the general specification, the system is optimized, and the design and implementation of the system are obtained. This project explores four major NLP modes such as ALBERT, RNN Search, BERT-CRF, Text ING based on the high-performance hardware of the Centeno platform. According to the element relation, tree structure and network structure, a general MNet construction method is proposed. The extracted correlation information is used to determine whether the matching conditions of each security requirement template are established, and then the final set of security requirement templates is screened. The extracted security requirements are modeled and instantiated in this way. Simulation results show that the model can deal with semantic dependency and human-computer interaction in complex systems. By analyzing the semantics of the operation interface in SCADA system, it is transformed into a general MNet construction, which lays a foundation for realizing the semantic analysis of users.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"106 1","pages":"970-974"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530469","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/ICPECA60615.2024.10470985
Jifeng Chen, Zhengxi Shao, Qingqi Liu, Mao Lei
This text discusses the real-time monitoring of student behavior in the classroom using deep learning technology. By employing DeepSORT to track student postures and recognize interactive behaviors and utilizing the YOLOv8 model to detect student postures, this study constructs an improved deep learning algorithm to establish a classroom teaching evaluation system. Through statistical analysis and real-time monitoring of student classroom states, quantitative assessment criteria have been formulated to accurately evaluate the level of students' concentration. The research results not only provide specific scores for each student's classroom behaviors but also analyze the behavioral characteristics of students and suggest areas for improvement. The study emphasizes the significance of personalized teaching strategies and, based on students' behavior patterns and changes in class, offers tailored behavior correction strategies to enhance the quality of students' attention during lectures.
{"title":"A Deep Learning-Based System for Monitoring Student Behavior and Analyzing Learning Situations","authors":"Jifeng Chen, Zhengxi Shao, Qingqi Liu, Mao Lei","doi":"10.1109/ICPECA60615.2024.10470985","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470985","url":null,"abstract":"This text discusses the real-time monitoring of student behavior in the classroom using deep learning technology. By employing DeepSORT to track student postures and recognize interactive behaviors and utilizing the YOLOv8 model to detect student postures, this study constructs an improved deep learning algorithm to establish a classroom teaching evaluation system. Through statistical analysis and real-time monitoring of student classroom states, quantitative assessment criteria have been formulated to accurately evaluate the level of students' concentration. The research results not only provide specific scores for each student's classroom behaviors but also analyze the behavioral characteristics of students and suggest areas for improvement. The study emphasizes the significance of personalized teaching strategies and, based on students' behavior patterns and changes in class, offers tailored behavior correction strategies to enhance the quality of students' attention during lectures.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"20 2","pages":"794-798"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530508","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/ICPECA60615.2024.10471162
Mingyuan Shao, Pengfei Deng, Dingzhao Li, Rongbin Lin, Haixin Sun
Specific emitter identification techniques excel in discerning between various devices through their unique radio frequency fingerprints (RFF), thereby enhancing the efficiency of communication among devices. However, in non-cooperative communication environments, the labeled emitter signal is often scarce or even unavailable. We design an effective self-supervised learning (Self-SL) approach based on contrastive learning for SEI to address the extreme scenario with no labeled samples. Specifically, we employ data augmentation in conjunction with deep neural networks featuring contrast loss to extract generic RF fingerprint features from unlabeled data, enabling the discrimination of various devices. Experimental results demonstrate that the acquired generic features can attain 91% recognition accuracy using just a simple linear classifier.
特定的发射器识别技术能够通过其独特的射频指纹（RFF）区分不同的设备，从而提高设备之间的通信效率。然而，在非合作通信环境中，标记的发射器信号往往很少甚至不可用。我们为 SEI 设计了一种基于对比学习的有效自监督学习（Self-SL）方法，以解决无标记样本的极端情况。具体来说，我们将数据增强与具有对比度损失特征的深度神经网络相结合，从无标记数据中提取通用射频指纹特征，从而实现对各种设备的识别。实验结果表明，仅使用简单的线性分类器，获取的通用特征就能达到 91% 的识别准确率。
{"title":"A Specific Emitter Identification Method Based on Self-Supervised Representation Learning","authors":"Mingyuan Shao, Pengfei Deng, Dingzhao Li, Rongbin Lin, Haixin Sun","doi":"10.1109/ICPECA60615.2024.10471162","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471162","url":null,"abstract":"Specific emitter identification techniques excel in discerning between various devices through their unique radio frequency fingerprints (RFF), thereby enhancing the efficiency of communication among devices. However, in non-cooperative communication environments, the labeled emitter signal is often scarce or even unavailable. We design an effective self-supervised learning (Self-SL) approach based on contrastive learning for SEI to address the extreme scenario with no labeled samples. Specifically, we employ data augmentation in conjunction with deep neural networks featuring contrast loss to extract generic RF fingerprint features from unlabeled data, enabling the discrimination of various devices. Experimental results demonstrate that the acquired generic features can attain 91% recognition accuracy using just a simple linear classifier.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"15 2","pages":"125-128"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530509","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}
Visual speech recognition (VSR) is also known as lip recognition. Recently, it has been widely explored due to the development of deep learning. Lip recognition is a discrimination issue, where the information provided by the delicate movement of the lips is most remarkable of all. This places a higher demand on the model's ability to extract features of minor variation around the lips. In this paper, a three-dimensional convolutional network (3D CNN) multi-branch feature fusion network is proposed for extracting spatiotemporal featuresof continuous images. The features of multi-branch feature fusion network are utilized to fully extract partial and general characteristics from sequential imagery and further enhance the feature information to deliver more accurate function info to the back-end classification network. The excellence of quite a few methods requires the support of huge volume of data, and in favor of test the effect of small-scale data sets. This experimentis conducted using the Oulu Vs2dataset to obtain exciting experimental results. After 20 iterations of the experiment, the maximum accuracy absolutely improves by 0.8% and the average accuracy improves by 1%.
{"title":"Multi-Scale Feature Fusion Network for Lip Recognition","authors":"Haohuai Lin, Bowen Liu, Gangdong Zhang, Qiang Yin, Liuqing Yang, Ping Lan","doi":"10.1109/ICPECA60615.2024.10471068","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471068","url":null,"abstract":"Visual speech recognition (VSR) is also known as lip recognition. Recently, it has been widely explored due to the development of deep learning. Lip recognition is a discrimination issue, where the information provided by the delicate movement of the lips is most remarkable of all. This places a higher demand on the model's ability to extract features of minor variation around the lips. In this paper, a three-dimensional convolutional network (3D CNN) multi-branch feature fusion network is proposed for extracting spatiotemporal featuresof continuous images. The features of multi-branch feature fusion network are utilized to fully extract partial and general characteristics from sequential imagery and further enhance the feature information to deliver more accurate function info to the back-end classification network. The excellence of quite a few methods requires the support of huge volume of data, and in favor of test the effect of small-scale data sets. This experimentis conducted using the Oulu Vs2dataset to obtain exciting experimental results. After 20 iterations of the experiment, the maximum accuracy absolutely improves by 0.8% and the average accuracy improves by 1%.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"55 4","pages":"541-545"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530301","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}
Ensuring the secure and stable operation of the power grid heavily relies on accurate and efficient load forecasting. To advance this endeavor, this study presents an ultra-short-term load forecasting methodology that merges the Ensemble Empirical Mode Decomposition (EEMD) technique with the Autoformer multi-model approach. Firstly, a comprehensive input feature matrix is crafted by selecting load data, historical weather data, and date information, which are meticulously preprocessed before analysis. Subsequently, the EEMD algorithm is enlisted to break down historical load data into distinct frequency components. Each frequency component, combined with weather data, undergoes individualized training and prediction within a separate model. The Autoformer model is harnessed for predicting lower frequency components, while the XGBoost model is employed for higher frequency components. In the final stage, the prediction outputs from each model are amalgamated and reconstructed to yield the ultimate load prediction. To expedite computation, a CPU/GPU heterogeneous collaborative parallel computing strategy is employed, enhancing the model's speed. The proposed approach is validated through real historical data sourced from a specific geographical area. The findings affirm its superiority over traditional models in terms of accuracy. The model showcases high-quality load forecasting capabilities, thereby establishing itself as a promising tool for ensuring the secure and stable operation of power grids.
{"title":"Ultra-short-term load forecasting based on the combination of EEMD and Autoformer multi-model","authors":"Yun Dong, Chongfu Yang, Qi Meng, Xuhua Ai, Yuan Yin, Kaijie Liu, Jiacheng Fu, Zhaoli Chen","doi":"10.1109/ICPECA60615.2024.10471039","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471039","url":null,"abstract":"Ensuring the secure and stable operation of the power grid heavily relies on accurate and efficient load forecasting. To advance this endeavor, this study presents an ultra-short-term load forecasting methodology that merges the Ensemble Empirical Mode Decomposition (EEMD) technique with the Autoformer multi-model approach. Firstly, a comprehensive input feature matrix is crafted by selecting load data, historical weather data, and date information, which are meticulously preprocessed before analysis. Subsequently, the EEMD algorithm is enlisted to break down historical load data into distinct frequency components. Each frequency component, combined with weather data, undergoes individualized training and prediction within a separate model. The Autoformer model is harnessed for predicting lower frequency components, while the XGBoost model is employed for higher frequency components. In the final stage, the prediction outputs from each model are amalgamated and reconstructed to yield the ultimate load prediction. To expedite computation, a CPU/GPU heterogeneous collaborative parallel computing strategy is employed, enhancing the model's speed. The proposed approach is validated through real historical data sourced from a specific geographical area. The findings affirm its superiority over traditional models in terms of accuracy. The model showcases high-quality load forecasting capabilities, thereby establishing itself as a promising tool for ensuring the secure and stable operation of power grids.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"71 5","pages":"1273-1279"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530295","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/ICPECA60615.2024.10470991
Li Ma, Ming Zhou, Sheng-wei Lu, Tongyan Zhang, Sirui Shu, Chuanyu Xiong
The timely and high-quality completion of PTT (power transmission and transformation, PTT) project construction has a decisive impact on the power supply quality and efficiency of the power system. So in the construction of PTT projects, we must do a good job in the management and control of construction efficiency and construction progress. The traditional mode of construction progress monitoring of PTT projects is mainly adopts the manual monitoring mode, which is time-consuming and labor-intensive. In order to realize the intelligent monitoring of construction progress of PTT projects, this study proposes an intelligent monitoring method of construction progress of PTT projects based on Mask-RCNN. This method first uses the marker recognition model based on Mask-RCNN to recognize the markers of key nodes in PTT projects, and then judges the construction progress according to the calculation rules for construction progress of PTT projects. We selected 21 kinds of PTT project markers to carry out experiments, and the results showed that the average accuracy of the marker recognition model based on Mask-RCNN can reach 92.16%, which effectively proved the effectiveness of the model. In addition, this article used the proposed method to analyze the construction progress of the Shiyan Hanshui 500kV PTT project, and the results showed that our method could effectively monitor the construction progress of the PTT project. It proved that our method had great application market and potential.
PTT（输变电工程，Power transmission and transform，简称PTT）工程建设能否按时保质完成，对电力系统的供电质量和效率有着决定性的影响。因此，在 PTT 工程建设中，必须做好施工效率和施工进度的管理与控制。传统的 PTT 工程施工进度监控模式主要采用人工监控模式，耗时耗力。为了实现 PTT 项目施工进度的智能监控，本研究提出了一种基于 Mask-RCNN 的 PTT 项目施工进度智能监控方法。该方法首先利用基于 Mask-RCNN 的标记识别模型对 PTT 工程关键节点的标记进行识别，然后根据 PTT 工程施工进度的计算规则对施工进度进行判断。我们选取了 21 种 PTT 项目标记进行实验，结果表明基于 Mask-RCNN 的标记识别模型的平均准确率可达 92.16%，有效证明了该模型的有效性。此外，本文还利用所提出的方法对十堰汉水 500kV PTT 项目的施工进度进行了分析，结果表明我们的方法可以有效地监测 PTT 项目的施工进度。这证明我们的方法具有巨大的应用市场和潜力。
{"title":"An Intelligent Monitoring Method of Construction Progress of Power Transmission and Transformation Projects Based on Mask-RCNN","authors":"Li Ma, Ming Zhou, Sheng-wei Lu, Tongyan Zhang, Sirui Shu, Chuanyu Xiong","doi":"10.1109/ICPECA60615.2024.10470991","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10470991","url":null,"abstract":"The timely and high-quality completion of PTT (power transmission and transformation, PTT) project construction has a decisive impact on the power supply quality and efficiency of the power system. So in the construction of PTT projects, we must do a good job in the management and control of construction efficiency and construction progress. The traditional mode of construction progress monitoring of PTT projects is mainly adopts the manual monitoring mode, which is time-consuming and labor-intensive. In order to realize the intelligent monitoring of construction progress of PTT projects, this study proposes an intelligent monitoring method of construction progress of PTT projects based on Mask-RCNN. This method first uses the marker recognition model based on Mask-RCNN to recognize the markers of key nodes in PTT projects, and then judges the construction progress according to the calculation rules for construction progress of PTT projects. We selected 21 kinds of PTT project markers to carry out experiments, and the results showed that the average accuracy of the marker recognition model based on Mask-RCNN can reach 92.16%, which effectively proved the effectiveness of the model. In addition, this article used the proposed method to analyze the construction progress of the Shiyan Hanshui 500kV PTT project, and the results showed that our method could effectively monitor the construction progress of the PTT project. It proved that our method had great application market and potential.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"3 1","pages":"459-463"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530120","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/ICPECA60615.2024.10471007
Tianyu Zhong, Jiang Liu, Baigen Cai, Jian Wang
Integrity of a train is a significant characteristic parameter towards a railway train control system in order to guarantee the railway operational safety. The decoupling event between a locomotive and a carriage or two adjacent carriages has become a serious threat for the following train operating along the same track. Conventional train integrity monitoring solutions based on state detection with specific sensors, like the Global Navigation Satellite System (GNSS) receiver and tail wind pressure unit, may not perform effectively and safely under constrained or difficult operation environments. This paper presents a Train Integrity Monitoring System (TIMS) architecture with integration of GNSS, Inertial Measurement Unit (IMU) and Ultra-wide Band (UWB) ranging technique. To realize the effective determination of the train integrity state with multiple detection channels, the fuzzy reasoning theory is adopted for decision-making. By using the simulated Head-of-Train (HoT) and End-of-Train (EoT) platforms, both the normal and decoupling scenarios are investigated through experiments. With the practically collected sensor datasets, the different single-sensor-based methods are compared with the presented fuzzy reasoning-based solution. The comparison results illustrate the advanced performance level under the given experimental conditions, which indicate great potentials of the presented solution in novel train control systems.
{"title":"GNSS/IMU/UWB-Based Train Integrity Monitoring Using Fuzzy Reasoning","authors":"Tianyu Zhong, Jiang Liu, Baigen Cai, Jian Wang","doi":"10.1109/ICPECA60615.2024.10471007","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471007","url":null,"abstract":"Integrity of a train is a significant characteristic parameter towards a railway train control system in order to guarantee the railway operational safety. The decoupling event between a locomotive and a carriage or two adjacent carriages has become a serious threat for the following train operating along the same track. Conventional train integrity monitoring solutions based on state detection with specific sensors, like the Global Navigation Satellite System (GNSS) receiver and tail wind pressure unit, may not perform effectively and safely under constrained or difficult operation environments. This paper presents a Train Integrity Monitoring System (TIMS) architecture with integration of GNSS, Inertial Measurement Unit (IMU) and Ultra-wide Band (UWB) ranging technique. To realize the effective determination of the train integrity state with multiple detection channels, the fuzzy reasoning theory is adopted for decision-making. By using the simulated Head-of-Train (HoT) and End-of-Train (EoT) platforms, both the normal and decoupling scenarios are investigated through experiments. With the practically collected sensor datasets, the different single-sensor-based methods are compared with the presented fuzzy reasoning-based solution. The comparison results illustrate the advanced performance level under the given experimental conditions, which indicate great potentials of the presented solution in novel train control systems.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"27 3","pages":"569-575"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530124","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/ICPECA60615.2024.10471019
Yannan Chang, Rao Liu, Xiaoyu Zhou, Yiwen Sun, Haixia Wang, Y. Ba, Weidong Li
For obtaining the maximum benefit, the Electrical Fused Magnesium Group Furnace (EFMGF) participate of power system Frequency Regulation Auxiliary Service (FRAS), need to combine their own operating characteristics to develop participation in the service of the operation control strategy, and consider the regulation characteristics and multiple uncertainties to build model for Day-ahead Reported Capacity (DRC) optimization of EFMGF participate in the Primary Frequency Regulation (PFR). Based on analysis of the characteristics of energy use, operating characteristics and adjustment characteristics, the control mechanism for the EFMGF participate in the PFR is proposed and the Frequency Regulation (FR) characteristics of the Electrical Fused Magnesium Furnace (EFMF) is deduced accordingly. With the goal of maximizing the overall profitability of the Electrical Fused Magnesium Enterprise (EFME) and taking into account the quality of products, the limitation of the energy requirement and the demand for FR, the optimized model for FMGF participate in the PFR is established to optimize DRC. Aiming at the multiple uncertainty problems such as the uncertainty of time and power and the randomness of the frequency regulation signals (FRSs) in the conversion of the operating conditions of the EFMF, a two-dimensional scenario matrix is constructed, which can be realized to solve the optimized model containing complex uncertainty factors. Simulation cases verify the effectiveness of the proposed control strategy, and the proposed optimized model can obtain the optimal reported capacity.
{"title":"Day-Ahead Reported Capacity Optimization and Operation Strategy of Electrical Fused Magnesium Group Furnace in Primary Frequency Regulation","authors":"Yannan Chang, Rao Liu, Xiaoyu Zhou, Yiwen Sun, Haixia Wang, Y. Ba, Weidong Li","doi":"10.1109/ICPECA60615.2024.10471019","DOIUrl":"https://doi.org/10.1109/ICPECA60615.2024.10471019","url":null,"abstract":"For obtaining the maximum benefit, the Electrical Fused Magnesium Group Furnace (EFMGF) participate of power system Frequency Regulation Auxiliary Service (FRAS), need to combine their own operating characteristics to develop participation in the service of the operation control strategy, and consider the regulation characteristics and multiple uncertainties to build model for Day-ahead Reported Capacity (DRC) optimization of EFMGF participate in the Primary Frequency Regulation (PFR). Based on analysis of the characteristics of energy use, operating characteristics and adjustment characteristics, the control mechanism for the EFMGF participate in the PFR is proposed and the Frequency Regulation (FR) characteristics of the Electrical Fused Magnesium Furnace (EFMF) is deduced accordingly. With the goal of maximizing the overall profitability of the Electrical Fused Magnesium Enterprise (EFME) and taking into account the quality of products, the limitation of the energy requirement and the demand for FR, the optimized model for FMGF participate in the PFR is established to optimize DRC. Aiming at the multiple uncertainty problems such as the uncertainty of time and power and the randomness of the frequency regulation signals (FRSs) in the conversion of the operating conditions of the EFMF, a two-dimensional scenario matrix is constructed, which can be realized to solve the optimized model containing complex uncertainty factors. Simulation cases verify the effectiveness of the proposed control strategy, and the proposed optimized model can obtain the optimal reported capacity.","PeriodicalId":518671,"journal":{"name":"2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"61 6","pages":"305-310"},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530478","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：