2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI)最新文献

Optimizing Traffic Controllers along the MLK Smart Corridor Using Reinforcement Learning and Digital Twin 利用强化学习和数字孪生优化MLK智能走廊沿线的交通控制器

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998928

Abhilasha J. Saroj, Toan V. Trant, Angshuman Guin, M. Hunter, Mina Sartipi

引用次数: 3

A Driving Strategy Based Integrated Rescheduling Model for High-Speed Railway by Using the Parallel Intelligent Method 基于驱动策略的高速铁路并行智能综合调度模型

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998978

Fan Liu, J. Xun, Min Zhou, Shibo He, Hairong Dong

引用次数: 1

Smart Predictive Maintenance Enabled by Digital Twins and Smart Big Data: A New Framework 由数字孪生和智能大数据实现的智能预测性维护:一个新框架

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998937

F. Guc, YangQuan Chen

引用次数: 0

Terms Development of Additive Manufacturing 术语增材制造的发展

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998939

Tariku Sinshaw Tamir, Gang Xiong, Jingchao Jiang, Zhen Shen, Ehtisham Lodhi, Hub Ali, Li Wan

引用次数: 1

Design and Application of A Parallel Agent 并行Agent的设计与应用

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998899

Libin Dong, Cheng Yang, Keyao Wang, Yi Wang, Quan Li, Jiandong Sun

{"title":"Design and Application of A Parallel Agent","authors":"Libin Dong, Cheng Yang, Keyao Wang, Yi Wang, Quan Li, Jiandong Sun","doi":"10.1109/DTPI55838.2022.9998899","DOIUrl":"https://doi.org/10.1109/DTPI55838.2022.9998899","url":null,"abstract":"The parallel agent learns the model according to the environment feedback, and selects the appropriate amount of action. It consists of automatic modeling system, automatic simulation system and parallel execution system. The automatic modeling system sends an excitation signal to the environment and establishes the model according to the system state data. The automatic simulation system automatically carries out the step response simulation experiment by using predictive dynamic optimization technology. The parallel execution system will automatically switch with the actual system without disturbance, and carry out step disturbance test. If the performance is excellent, it will be put into application. The parallel agent is divided into two processes: learning and experiment. The learning process refers to that agents collect feedback information and learn the model. The experimental process refers to that the agent constructs the predictive dynamic optimization closed-loop control system based on the obtained model and carries out the step response simulation experiment, and switches to the actual system. If the step disturbance test has excellent performance, it will be put into operation. Based on the parallel control theory, the parallel agent automatically completes the whole process according to the step sequence and has a certain adaptive ability.","PeriodicalId":409822,"journal":{"name":"2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123345110","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}

引用次数: 0

Integrated optimization of smart home appliances under energy management system 能源管理系统下的智能家电集成优化

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998973

Li Jing, Zhou Xiangyu, Li Tao, Liu Yue, Wu Qinghua

引用次数: 1

Power Load Forecasting Method Based on Random Matrix Theory and CNN-LSTM Model 基于随机矩阵理论和CNN-LSTM模型的电力负荷预测方法

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998910

Shidong Wu, Cunqiang Huang, Xu Tian, Junxian Li, Bowen Ren, G. Wang, Lidong Qin, Hengrui Ma

引用次数: 0

Weibo Spammer Detection Based On Social Network Digital Twin 基于社交网络数字孪生的微博垃圾邮件检测

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998892

Xin Liu, Shaowen Yu, Qiang Li, Dawei Yang, Yanru Yu, Haiwen Wang

{"title":"Weibo Spammer Detection Based On Social Network Digital Twin","authors":"Xin Liu, Shaowen Yu, Qiang Li, Dawei Yang, Yanru Yu, Haiwen Wang","doi":"10.1109/DTPI55838.2022.9998892","DOIUrl":"https://doi.org/10.1109/DTPI55838.2022.9998892","url":null,"abstract":"Users are increasingly willing to share their comments on the Internet. The popularity of Weibo has spawned spammers. Comments from spammers affect normal Internet public opinion. The traditional spammer detection methods are mainly based on the static characteristics of users and accuracies are not ideal. In this paper, we apply the parallel system framework to build a social network digital twin. The nodes of the digital twin are mapped to the nodes of the graph attention network and the relationships between nodes in the digital twin are mapped to the neighbor nodes in the graph attention network. The feature vectors of nodes are updated by the stacked graph attention layer. We take the output of the attention layer as the input of the full connection layer. The softmax classifier is used to get the classification results. In this paper, we wrote a crawler to collect the individual information and follow the relationship of 2,000 users, screened out 15 user characteristics, and manually annotated them. The experimental results show that the model we proposed has higher accuracy than the naive Bayes model and decision tree.","PeriodicalId":409822,"journal":{"name":"2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124136774","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}

引用次数: 0

Link Flow Estimation for Parallel Transportation Management 并行运输管理中的链路流量估计

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998959

Qiang Li, Runmeng Wang

引用次数: 0

Investigation of building load calculation from the perspective of grand canonical ensemble theory and historical data identification 基于大正则系综理论和历史资料识别的建筑荷载计算研究

2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) Pub Date : 2022-10-24 DOI: 10.1109/DTPI55838.2022.9998970

Junwei Zhang, Xiaojie Lin, Wei Zhong

{"title":"Investigation of building load calculation from the perspective of grand canonical ensemble theory and historical data identification","authors":"Junwei Zhang, Xiaojie Lin, Wei Zhong","doi":"10.1109/DTPI55838.2022.9998970","DOIUrl":"https://doi.org/10.1109/DTPI55838.2022.9998970","url":null,"abstract":"Building energy consumption accounts for over one-third of the global terminal energy, among which the building operation energy consumption of HVAC accounts for the central part, and the energy saving potential is enormous. Load forecasting is significant for building energy management and reducing building energy consumption. The existing building load calculation methods are mainly the mechanism modeling and data-driven prediction methods, which have complex calculation problems, and poor dynamic randomness. In engineering design, the calculation of the infiltration load of the building is simplified, causing specific errors. In this paper, the infiltration load caused by the heat and mass exchange between the air of building inside and the external environment is modeled in detail. It proposes a building load calculation model based on the grand canonical ensemble theory. In the heating and cooling scenarios, the load calculation results of the model and the mechanism model are compared, respectively. The deviation between the two is within the range of 0.191 ± 0.003, combined with the EnergyPlus simulation results to compare and verify the model's accuracy. The load calculation model proposed in this paper clarifies mechanism modeling and can achieve a rapid and accurate evaluation of building load characteristics.","PeriodicalId":409822,"journal":{"name":"2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133796741","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}

引用次数: 0