2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)最新文献_第2页

Simulation-based Design for the Layout and Operation of AGVs in Sustainable and Efficient Manufacturing Systems 可持续高效制造系统中agv布局与运行的仿真设计

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970620

Lucilla Dammacco, Raffaele Carli, V. Lazazzera, M. Fiorentino, M. Dotoli

{"title":"Simulation-based Design for the Layout and Operation of AGVs in Sustainable and Efficient Manufacturing Systems","authors":"Lucilla Dammacco, Raffaele Carli, V. Lazazzera, M. Fiorentino, M. Dotoli","doi":"10.1109/ICCSI55536.2022.9970620","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970620","url":null,"abstract":"Complex manufacturing systems are recently undergoing a green revolution due to manufacturing customization towards sustainable products. A key enabler for the implementation of green and energy efficient production is simulation-based design, which supports system engineers and designers in making decision choices aimed at enhancing the performance of smart and sustainable production. In this context, this work proposes a simulation approach to support the design of the layout and operation of automated guided vehicles (AGVs) in complex production lines. In particular, a case study related to the assembly of electric axles for heavy-duty vehicles is presented: a scenario analysis implemented in the Plant Simulation platform is used to determine the optimal configuration of AGVs in terms of number of vehicles and operation (e.g., definition of charging strategies, scheduling of charging stops, routing). The simulation results first show that the reduction of the AGVs' energy consumption and the increase of production throughput are competing criteria; second, the choice of AGV charging strategies has a significant influence on the energy consumption as well as on the productivity performance.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127620801","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

Research on Digital Twins Technology and Its Future Implementation in Transformer Overload Analysis 数字孪生技术及其在变压器过载分析中的应用研究

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970559

Dexu Zou, Zhirui Zhang, Qingjun Peng, Shan Wang, Yong Shi, Z. Hong, Weiju Dai, Hao Quan

引用次数: 1

SIL Simulation Test Platform Based on Prescan and ROS 基于预扫描和ROS的SIL仿真测试平台

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970607

Chang Xu, Huang Huang, Suijun Duan, Qi Zhao, Liang Liu, Dong Liu

引用次数: 0

Sequential Topology Attack of Supply Chain Networks Based on Reinforcement Learning 基于强化学习的供应链网络顺序拓扑攻击

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970706

Lei Zhang, Jian Zhou, Yizhong Ma, Lijuan Shen

{"title":"Sequential Topology Attack of Supply Chain Networks Based on Reinforcement Learning","authors":"Lei Zhang, Jian Zhou, Yizhong Ma, Lijuan Shen","doi":"10.1109/ICCSI55536.2022.9970706","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970706","url":null,"abstract":"The robustness of supply chain networks (SCNs) against sequential topology attacks is significant for maintaining firm relationships and activities. Although SCNs have experienced many emergencies demonstrating that mixed failures exacerbate the impact of cascading failures, existing studies of sequential attacks rarely consider the influence of mixed failure modes on cascading failures. In this paper, a reinforcement learning (RL)-based sequential attack strategy is applied to SCNs with cascading failures that consider mixed failure modes. To solve the large state space search problem in SCNs, a deep Q-network (DQN) optimization framework combining deep neural networks (DNNs) and RL is proposed to extract features of state space. Then, it is compared with the traditional random-based, degree-based, and load-based sequential attack strategies. Simulation results on Barabasi-Albert (BA), Erdos-Renyi (ER), and Watts-Strogatz (WS) networks show that the proposed RL-based sequential attack strategy outperforms three existing sequential attack strategies. It can trigger cascading failures with greater influence. This work provides insights for effectively reducing failure propagation and improving the robustness of SCNs.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129856672","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: 1

Optimal Allocation and Operation Strategies of Distributed Vanadium Redox Battery Energy Storage System 分布式钒氧化还原电池储能系统的优化配置与运行策略

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970695

Qi-feng Sun, Jiazhi Lei, Zhao Liu

{"title":"Optimal Allocation and Operation Strategies of Distributed Vanadium Redox Battery Energy Storage System","authors":"Qi-feng Sun, Jiazhi Lei, Zhao Liu","doi":"10.1109/ICCSI55536.2022.9970695","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970695","url":null,"abstract":"This paper presented an optimal allocation of distributed vanadium redox battery (VRB) energy storage system (ESS) in active distribution networks (ADNs). Correspondingly, an optimal method of distributed VRB ESS determining the rated power, rated capacity and operation strategies is proposed. Firstly, according to the different operation requirements, several corresponding operation strategies are proposed, also the operation process and constraints of the ESS unit are analyzed. Then, an operation benefit model of the ADNs is constructed, and the operation status of the ADNs allocated with the distributed VRB ESS is intuitively represented by the economic benefit. Finally, the proposed optimal allocation method of distributed VRB ESS considering multiple operation strategies is tested with an experimental case, which verifies the correctness and rationality of the proposed optimal allocation method. The results show that the operation benefits of the ADNs can be increased by 32% by determining the optimal allocation and appropriate operation strategy proposed in this paper.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125295490","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

Migration Effect of Underground Pipelines at Different Depths Based on Time-Wavelet Energy Spectrum Method 基于时间-小波能谱法的地下管道不同深度偏移效应研究

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970690

Yingxian Zhou, Liang Zhang, Sheng Zhang, Zechao Hu

{"title":"Migration Effect of Underground Pipelines at Different Depths Based on Time-Wavelet Energy Spectrum Method","authors":"Yingxian Zhou, Liang Zhang, Sheng Zhang, Zechao Hu","doi":"10.1109/ICCSI55536.2022.9970690","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970690","url":null,"abstract":"With the rapid advancement of urbanization and the vigorous development of urban construction, the number and scale of urban underground pipelines are increasing. The accurate survey of urban underground pipelines is related to urban safety and the improvement of urban comprehensive management level. Ground penetrating radar (GPR) is widely used in underground pipeline detection and investigation due to its advantages of high detection efficiency and intuitive imaging. Based on the principle of time-wavelet energy spectrum and frequency wavenumber (F-K) migration algorithm, this paper carried out the GPR detection and migration imaging analysis of underground pipelines with different buried depths. The results show that the time-wavelet energy spectrum method can accurately determine the time position of singular points in single-channel signals, and the accurate migration speed can be obtained by combining the buried depth of pipelines. The center frequency of the 1600 MHz antenna is more suitable for detection and imaging analysis of shallow pipelines. By selecting an accurate migration velocity and performing migration processing on the pipeline image, the image diffraction waves converge completely, the pipeline echo signals are focused and highlighted, and the pipeline imaging results are close to its real shape.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126854337","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

Efficient Dual Adversarial Cross Modal Retrieval By Advanced Triplet Loss 基于高级三重态损失的高效双对抗交叉模态检索

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970558

Zhichao Han, Huan Zhou, Kezhong Nong, Zhe Li, Guoyong Lin, Chengjia Huang

引用次数: 1

Graph Convolutional Networks-based Label Distribution Learning for Image Classification 基于图卷积网络的图像分类标签分布学习

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970653

Changqing Gong, Shanshan Wang, Yiquan Wu, Chongwen Liu, M. El-Yacoubi, Huafeng Qin

{"title":"Graph Convolutional Networks-based Label Distribution Learning for Image Classification","authors":"Changqing Gong, Shanshan Wang, Yiquan Wu, Chongwen Liu, M. El-Yacoubi, Huafeng Qin","doi":"10.1109/ICCSI55536.2022.9970653","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970653","url":null,"abstract":"The one-hot vector employed for true label representation has been widely applied for image classification. However, the one-hot representation assumes that a single label is only associated with one instance, which is not reasonable because labels are generally not completely independent and instances may relate to multiple labels for the real scenarios. Such one-hot representation may ignore the relevance among labels that provide more supervision information for model training. To capture and explore such significant relevance in image classification, we propose, in this paper, GCNLDL, a Graph Convolutional Network based Label Distribution Learning approach for classification. GCNLDL builds a directed graph over the images, where each node (sample) is represented by the embedding of an image, where GCN learns the relevance between an input image and multiple training images from different classes to obtain the label distribution vector. The resulting vector is further combined with the one-hot label to recover a realistic label distribution of the input image, which is employed to train the state-of-the-art classification models. Furthermore, a multilayer perception is proposed to learn an effective label correlation matrix to guide information propagation among the nodes in GCN. GCNLDL is capable of capturing the relevance among labels by representation learning graph structure among image samples during training process and produces a better label distribution to guide the training of the state-of-the-art image classification models, resulting in a performance improvement of image classification. Rigorous experimental results on four public image classification datasets show that GCNLDL outperforms other approaches and effectively improves the performance of deep learning classification based models.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121108413","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: 1

Resilient Robust Model Predictive Control of Inventory Systems for Perishable Good Under Uncertain Forecast Information 不确定预测信息下易腐货物库存系统的弹性鲁棒模型预测控制

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970646

Beatrice Ietto, V. Orsini

引用次数: 1

An Overview of Correlation-Filter and Deep-Learning Based Single Object Tracking 基于关联滤波和深度学习的单目标跟踪综述

2022 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2022-11-18 DOI: 10.1109/ICCSI55536.2022.9970621

Ying Mi, Chan Liu, Weiwei Bian

引用次数: 0