Pub Date : 2020-10-23DOI: 10.1109/IAI50351.2020.9262171
Xiaoyi Zhou, Yuanyuan Zou, Shaoyuan Li, Hao Fang
In this paper, a multi-agent cooperative control problem with conflicting temporal logic tasks is studied. Each agent is assigned a temporal logic task which contains a motion task and safety requirements. We consider the cases where the satisfaction of both the motion task and safety requirements may be conflicting due to the limited velocity, so that such a task can not be fulfilled. In order to solve this problem, we give priority to the the safety requirements and the degree of satisfaction of the motion task is slacked. This work proposes a two-stage distributed receding horizon optimization strategy consisting of offline stage and online stage where signal temporal logic (STL) is utilized to formally describe the temporal logic tasks and the receding horizon optimization framework is adopted for cooperative collision avoidance tasks. At offline stage, according to the motion task, a reference robustness evolution curve is presented for each agent by the robust semantics of STL formulas. At online stage, based on the short-term goal region determined by the reference robustness evolution curve, together with the known obstacles' information and agents' real-time information, constraints of both the motion task and safety requirements are constructed in the receding horizon optimization problem for each agent. When conflicting situations happen, the constraint of the motion task is relaxed by a robustness slackness to find a least violating solution. In the proposed framework, the offline stage and the online stage are combined to satisfy the motion task as much as possible and to guarantee the safety requirements. The effectiveness of the framework is verified by simulation results.
{"title":"Distributed Receding Horizon Control for Multi-agent Systems with Conflicting Siganl Temporal Logic Tasks","authors":"Xiaoyi Zhou, Yuanyuan Zou, Shaoyuan Li, Hao Fang","doi":"10.1109/IAI50351.2020.9262171","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262171","url":null,"abstract":"In this paper, a multi-agent cooperative control problem with conflicting temporal logic tasks is studied. Each agent is assigned a temporal logic task which contains a motion task and safety requirements. We consider the cases where the satisfaction of both the motion task and safety requirements may be conflicting due to the limited velocity, so that such a task can not be fulfilled. In order to solve this problem, we give priority to the the safety requirements and the degree of satisfaction of the motion task is slacked. This work proposes a two-stage distributed receding horizon optimization strategy consisting of offline stage and online stage where signal temporal logic (STL) is utilized to formally describe the temporal logic tasks and the receding horizon optimization framework is adopted for cooperative collision avoidance tasks. At offline stage, according to the motion task, a reference robustness evolution curve is presented for each agent by the robust semantics of STL formulas. At online stage, based on the short-term goal region determined by the reference robustness evolution curve, together with the known obstacles' information and agents' real-time information, constraints of both the motion task and safety requirements are constructed in the receding horizon optimization problem for each agent. When conflicting situations happen, the constraint of the motion task is relaxed by a robustness slackness to find a least violating solution. In the proposed framework, the offline stage and the online stage are combined to satisfy the motion task as much as possible and to guarantee the safety requirements. The effectiveness of the framework is verified by simulation results.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133701392","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 non-stationarity and stochastic nature of wind power bring difficult challenges to large-scale grid-connected of wind power. The ultra-short-term forecasting of wind power is used for balancing load and the optimal optimization of spinning reserve, which has high requirements for prediction accuracy. The neural network can solve the problem of feature selection, but in the task of wind power prediction, it is of great concern to find the optimal input features and model structure by mining physical correlation among features. Inspired by the physical formula for wind power, an uncertain factor is calculated, which caused by both environmental disturbance and wind turbine state changes. This paper proposes a method to predict ultra-short-term wind power, which using the features associated with wind power and the uncertain factors. Time series features are predicted through the Gated Recurrent Unit (GRU) Neural Network, and finally all the features were fused to form a hybrid neural network. The effectiveness of the proposed method has been confirmed on the real datasets derived from a wind field. Compared with the conventional time series dependent methods, our proposed method shows more reasonable results in terms of accuracy and availability.
{"title":"Hybrid Neural Network Based on GRU with Uncertain Factors for Forecasting Ultra-short-term Wind Power","authors":"Xinyu Meng, Ruihan Wang, Xiping Zhang, Mingjie Wang, Hui Ma, Zhengxia Wang","doi":"10.1109/IAI50351.2020.9262192","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262192","url":null,"abstract":"The non-stationarity and stochastic nature of wind power bring difficult challenges to large-scale grid-connected of wind power. The ultra-short-term forecasting of wind power is used for balancing load and the optimal optimization of spinning reserve, which has high requirements for prediction accuracy. The neural network can solve the problem of feature selection, but in the task of wind power prediction, it is of great concern to find the optimal input features and model structure by mining physical correlation among features. Inspired by the physical formula for wind power, an uncertain factor is calculated, which caused by both environmental disturbance and wind turbine state changes. This paper proposes a method to predict ultra-short-term wind power, which using the features associated with wind power and the uncertain factors. Time series features are predicted through the Gated Recurrent Unit (GRU) Neural Network, and finally all the features were fused to form a hybrid neural network. The effectiveness of the proposed method has been confirmed on the real datasets derived from a wind field. Compared with the conventional time series dependent methods, our proposed method shows more reasonable results in terms of accuracy and availability.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114312274","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262194
Tongbang Jiang, S. Chu, Jeng-Shyang Pan
With the rapid development of information technology, wireless sensor network(WSN) gradually permeates all walks of life. However, WSN is always out of work because of too much energy consumption on certain sensor nodes. This paper presents a new protocol based on parallel charged system search(PCSS) algorithm to balance energy consumption during WSN transmission. Firstly, a novel optimization algorithm named PCSS is presented based on two communication strategies with different conditions. First experiments on 10 benchmark functions in different dimensions demonstrate that the PCSS shows an excellent ability of convergency compared to CSS and PSO and the advantage of PCSS in quickly finding optimum is more obvious with the increasing of dimension. After that, a new clustering model based on PCSS(PCSS-C) is introduced to update cluster heads dynamically according to a designed fitness function, another experimental results illustrate that the proposed protocol is superior to low-energy adaptive clustering hierarchy, LEACH-centralized, and hybrid energy-efficient distributed clustering.
{"title":"Parallel Charged System Search Algorithm for Energy Management in Wireless Sensor Network","authors":"Tongbang Jiang, S. Chu, Jeng-Shyang Pan","doi":"10.1109/IAI50351.2020.9262194","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262194","url":null,"abstract":"With the rapid development of information technology, wireless sensor network(WSN) gradually permeates all walks of life. However, WSN is always out of work because of too much energy consumption on certain sensor nodes. This paper presents a new protocol based on parallel charged system search(PCSS) algorithm to balance energy consumption during WSN transmission. Firstly, a novel optimization algorithm named PCSS is presented based on two communication strategies with different conditions. First experiments on 10 benchmark functions in different dimensions demonstrate that the PCSS shows an excellent ability of convergency compared to CSS and PSO and the advantage of PCSS in quickly finding optimum is more obvious with the increasing of dimension. After that, a new clustering model based on PCSS(PCSS-C) is introduced to update cluster heads dynamically according to a designed fitness function, another experimental results illustrate that the proposed protocol is superior to low-energy adaptive clustering hierarchy, LEACH-centralized, and hybrid energy-efficient distributed clustering.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"734 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116109792","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262196
Tai-Qiang Zhang, F. Zhou, Jun Zhao, Wei Wang
Considering that the blast furnace gas(BFG) tank level scheduling is of great significance for the steel plant's secondary energy system balance, this paper proposed a scheduling model based on deep reinforcement learning. In this model, BFG gas tank scheduling was transformed into searching the best production state under a certain operating condition, and a deep Q-learning network was used to search this state. Moreover, in order to speed up convergence and improve algorithm stability, an experience based pre-training was added to the training session. In order to verify the effectiveness of the proposed method, experiments are carried out with the secondary energy system production data of a domestic steel enterprise. The results show that the proposed method is more effective than artificial scheduling.
{"title":"Deep Reinforcement Learning for Secondary Energy Scheduling in Steel Industry","authors":"Tai-Qiang Zhang, F. Zhou, Jun Zhao, Wei Wang","doi":"10.1109/IAI50351.2020.9262196","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262196","url":null,"abstract":"Considering that the blast furnace gas(BFG) tank level scheduling is of great significance for the steel plant's secondary energy system balance, this paper proposed a scheduling model based on deep reinforcement learning. In this model, BFG gas tank scheduling was transformed into searching the best production state under a certain operating condition, and a deep Q-learning network was used to search this state. Moreover, in order to speed up convergence and improve algorithm stability, an experience based pre-training was added to the training session. In order to verify the effectiveness of the proposed method, experiments are carried out with the secondary energy system production data of a domestic steel enterprise. The results show that the proposed method is more effective than artificial scheduling.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124022249","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262224
Jiabing Chen, Lei Wei, Gaopeng Zhao
Satellite component recognition has always been a hot topic in the field of orbital services. However, it is very challenging to segment the components such as satellite body, solar panel, and antenna in pixel-level accurately due to the poor illumination condition and the scarce image for spaceborne observation. Based on the Mask R-CNN, this paper proposes a lightweight instance segmentation model for satellite component segmentation and recognition. It improves residual module by using deep separable convolution, replacing nonlinear activation function with linear one after deep separable convolution and deleting the dimensionality reduction convolution layer in residual module. Also, the training datasets consist of the synthetic images generated by the 3D max software and the C-DCGAN based image generation method through several known satellite CAD models. The simulation experiments are carried out and the results show that the proposed method can effectively recognize the typical satellite components and achieve better performance than the compared model in aspects of accuracy, model parameters, and model size.
{"title":"An improved lightweight model based on Mask R-CNN for satellite component recognition","authors":"Jiabing Chen, Lei Wei, Gaopeng Zhao","doi":"10.1109/IAI50351.2020.9262224","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262224","url":null,"abstract":"Satellite component recognition has always been a hot topic in the field of orbital services. However, it is very challenging to segment the components such as satellite body, solar panel, and antenna in pixel-level accurately due to the poor illumination condition and the scarce image for spaceborne observation. Based on the Mask R-CNN, this paper proposes a lightweight instance segmentation model for satellite component segmentation and recognition. It improves residual module by using deep separable convolution, replacing nonlinear activation function with linear one after deep separable convolution and deleting the dimensionality reduction convolution layer in residual module. Also, the training datasets consist of the synthetic images generated by the 3D max software and the C-DCGAN based image generation method through several known satellite CAD models. The simulation experiments are carried out and the results show that the proposed method can effectively recognize the typical satellite components and achieve better performance than the compared model in aspects of accuracy, model parameters, and model size.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115852001","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262191
Da Zhang, Hu Ji, Hao Ji, Qi Lou
In view of the challenging problems of low reliability, small coverage, high cost, poor maintenance and inadequate early warning, which have been the bottleneck in microseismic monitoring of underground mines, a new cloud platform-based micro-power microseismic monitoring IoT system is proposed, which can be used as an effective technical feedback for real-time mining operation optimization. The proposed system has broken through key technologies such as smart sensing, micro-power acquisition, fault diagnosis and online intelligent analysis, has been successfully applied in mining enterprises. Site test shows that the proposed system is more reliable in harsh mining conditions than traditional systems. The microseismic sensor's SNR is increased by 1.4 times, the comprehensive energy consumption is reduced obviously and the online analysis and warning services can be achieved via safety monitoring and analysis cloud platform.
{"title":"A Cloud Platform-based Micro-Power Microseismic Monitoring IoT System for Underground Mine","authors":"Da Zhang, Hu Ji, Hao Ji, Qi Lou","doi":"10.1109/IAI50351.2020.9262191","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262191","url":null,"abstract":"In view of the challenging problems of low reliability, small coverage, high cost, poor maintenance and inadequate early warning, which have been the bottleneck in microseismic monitoring of underground mines, a new cloud platform-based micro-power microseismic monitoring IoT system is proposed, which can be used as an effective technical feedback for real-time mining operation optimization. The proposed system has broken through key technologies such as smart sensing, micro-power acquisition, fault diagnosis and online intelligent analysis, has been successfully applied in mining enterprises. Site test shows that the proposed system is more reliable in harsh mining conditions than traditional systems. The microseismic sensor's SNR is increased by 1.4 times, the comprehensive energy consumption is reduced obviously and the online analysis and warning services can be achieved via safety monitoring and analysis cloud platform.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1519 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128053945","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262183
L. Zhou, Y. Yue, Mingxuan Zhong, F. Jin
With the rapid development of high-speed railways in recent years, the optimization of the rolling stock scheduling has become an important part of transportation organization, which can promote to reduce the number of rolling stocks and improve the efficiency of operation. We take the train timetable as the input condition, adopt the time-space-state network to formulate the optimization problem of rolling stock scheduling, and build the optimization model. The goal is to minimize the total operating time cost of the train, the constraints is the train task assignment unique constraints, flow balance constraints, the first-level maintenance constraints etc. We use the Alternating Direction Method of Multipliers (ADMM) algorithm to solve the model, which is a special case of integer linear programming. The multi rolling stocks scheduling optimization problem is decomposed into the least-cost train path sub-problem of every rolling stock, we solve sub-problems by the improved dynamic programming method. The Beijing-Tianjin high-speed railway instance is tested. We set the value of the lagrange multiplier and the penalty coefficient in ADMM, test this case, and calculate the utilization of every rolling stock. The practicability of the model and algorithm is verified.
{"title":"High-speed Railway Rolling Stock Scheduling Based on ADMM Decomposition Algorithm","authors":"L. Zhou, Y. Yue, Mingxuan Zhong, F. Jin","doi":"10.1109/IAI50351.2020.9262183","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262183","url":null,"abstract":"With the rapid development of high-speed railways in recent years, the optimization of the rolling stock scheduling has become an important part of transportation organization, which can promote to reduce the number of rolling stocks and improve the efficiency of operation. We take the train timetable as the input condition, adopt the time-space-state network to formulate the optimization problem of rolling stock scheduling, and build the optimization model. The goal is to minimize the total operating time cost of the train, the constraints is the train task assignment unique constraints, flow balance constraints, the first-level maintenance constraints etc. We use the Alternating Direction Method of Multipliers (ADMM) algorithm to solve the model, which is a special case of integer linear programming. The multi rolling stocks scheduling optimization problem is decomposed into the least-cost train path sub-problem of every rolling stock, we solve sub-problems by the improved dynamic programming method. The Beijing-Tianjin high-speed railway instance is tested. We set the value of the lagrange multiplier and the penalty coefficient in ADMM, test this case, and calculate the utilization of every rolling stock. The practicability of the model and algorithm is verified.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114904449","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262187
Yijing Fang, Zhaohui Jiang
The silicon content of molten iron is one of the most important molten iron quality parameters. However, the silicon content cannot be measured directly, therefore, accurate prediction for silicon content is of great significant to blast furnace (BF) iron making process. Aiming at the problem of low accuracy, an adaptive weighted echo state network (AW-ESN) based ensemble model is proposed in this paper to construct the prediction intervals (PI) and predict the silicon content of molten iron in BF. First, bootstrap method is utilized to resample the training set to construct subsets, AW-ESN is proposed to estimate silicon content and the corresponding PI is constructed. Then, the correspondence between the width of PI and reliability is established. Finally, the prediction results and the reliability can be obtained. In order to verify the effectiveness of the proposed method, industrial experiments were carried out by using process data of BF. The results demonstrate that the proposed method has higher prediction accuracy and the reliability can be realized, which provide more information to the on-site operators.
{"title":"Use of adaptive weighted echo state network ensemble for construction of prediction intervals and prediction reliability of silicon content in ironmaking process","authors":"Yijing Fang, Zhaohui Jiang","doi":"10.1109/IAI50351.2020.9262187","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262187","url":null,"abstract":"The silicon content of molten iron is one of the most important molten iron quality parameters. However, the silicon content cannot be measured directly, therefore, accurate prediction for silicon content is of great significant to blast furnace (BF) iron making process. Aiming at the problem of low accuracy, an adaptive weighted echo state network (AW-ESN) based ensemble model is proposed in this paper to construct the prediction intervals (PI) and predict the silicon content of molten iron in BF. First, bootstrap method is utilized to resample the training set to construct subsets, AW-ESN is proposed to estimate silicon content and the corresponding PI is constructed. Then, the correspondence between the width of PI and reliability is established. Finally, the prediction results and the reliability can be obtained. In order to verify the effectiveness of the proposed method, industrial experiments were carried out by using process data of BF. The results demonstrate that the proposed method has higher prediction accuracy and the reliability can be realized, which provide more information to the on-site operators.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"33 29","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132939915","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 : 2020-07-06DOI: 10.1109/IAI50351.2020.9262239
J. Viola, Y. Chen, Junchang Wang
Digital Twin allows creating virtual representations of complex physical systems. However, making the Digital Twin behavior matching with the real system is challenging due to the number of unknown parameters. Its search can be done using optimization-based techniques, producing a family of models based on different system datasets. So, a discrimination criterion is required to determine the best Digital Twin model. This paper presents an information theory-based discrimination criterion to determine the best Digital Twin model resulting from a behavioral matching process. The Information Gain of a model is employed as a discrimination criterion. Box-Jenkins models are used to define the family of models for each behavioral matching result. The proposed method is compared with other information-based metrics and the $nu$gap metric. As a study case, the discrimination method is applied to the Digital Twin for a real-time vision feedback infrared temperature uniformity control system. Obtained results show that information-based methodologies are useful for selecting an accurate Digital Twin model representing the system among a family of plants.
Digital Twin允许创建复杂物理系统的虚拟表示。然而，由于存在大量未知参数，使数字孪生模型的行为与实际系统相匹配是一项挑战。它的搜索可以使用基于优化的技术来完成，生成一系列基于不同系统数据集的模型。因此，需要一个判别标准来确定最佳的数字孪生模型。本文提出了一种基于信息论的判别准则，用以确定行为匹配过程中产生的最佳数字孪生模型。采用模型的信息增益作为判别准则。Box-Jenkins模型用于定义每个行为匹配结果的模型族。将该方法与其他基于信息的度量和$nu$差距度量进行了比较。作为研究实例，将该判别方法应用于实时视觉反馈红外温度均匀性控制系统的数字孪生。得到的结果表明，基于信息的方法对于选择一个精确的数字孪生模型来表示植物家族中的系统是有用的。
{"title":"Information-Based Model Discrimination for Digital Twin Behavioral Matching","authors":"J. Viola, Y. Chen, Junchang Wang","doi":"10.1109/IAI50351.2020.9262239","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262239","url":null,"abstract":"Digital Twin allows creating virtual representations of complex physical systems. However, making the Digital Twin behavior matching with the real system is challenging due to the number of unknown parameters. Its search can be done using optimization-based techniques, producing a family of models based on different system datasets. So, a discrimination criterion is required to determine the best Digital Twin model. This paper presents an information theory-based discrimination criterion to determine the best Digital Twin model resulting from a behavioral matching process. The Information Gain of a model is employed as a discrimination criterion. Box-Jenkins models are used to define the family of models for each behavioral matching result. The proposed method is compared with other information-based metrics and the $nu$gap metric. As a study case, the discrimination method is applied to the Digital Twin for a real-time vision feedback infrared temperature uniformity control system. Obtained results show that information-based methodologies are useful for selecting an accurate Digital Twin model representing the system among a family of plants.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114511359","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 : 2020-07-06DOI: 10.1109/IAI50351.2020.9262160
J. Viola, Carlos Rodriguez, Y. Chen
Thermal processes are one of the most common systems in the industry, making its understanding a mandatory skill for control engineers. So, multiple efforts are focused on developing low-cost and portable experimental training rigs recreating the thermal process dynamics and controls, usually limited to SISO or low order 2×2 MIMO systems. This paper presents PHELP, a low-cost, portable, and high order MIMO educational platform for uniformity temperature control training. The platform is composed of an array of 16 Peltier modules as heating elements, with a lower heating and cooling times, resulting in a 16×16 high order MIMO system. A low-cost realtime infrared thermal camera is employed as a temperature feedback sensor instead of a standard thermal sensor, ideal for high order MIMO system sensing and temperature distribution tracking. The control algorithm is developed in Matlab/Simulink and employs an Arduino board in hardware in the loop configuration to apply the control action to each Peltier module in the array. A temperature control experiment is performed, showing that the platform is suitable for teaching and training experiences not only in the classroom but also for engineers in the industry. Furthermore, various abnormal conditions can be introduced so that smart control engineering features can be tested.
{"title":"PHELP: Pixel Heating Experiment Learning Platform for Education and Research on IAI-based Smart Control Engineering","authors":"J. Viola, Carlos Rodriguez, Y. Chen","doi":"10.1109/IAI50351.2020.9262160","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262160","url":null,"abstract":"Thermal processes are one of the most common systems in the industry, making its understanding a mandatory skill for control engineers. So, multiple efforts are focused on developing low-cost and portable experimental training rigs recreating the thermal process dynamics and controls, usually limited to SISO or low order 2×2 MIMO systems. This paper presents PHELP, a low-cost, portable, and high order MIMO educational platform for uniformity temperature control training. The platform is composed of an array of 16 Peltier modules as heating elements, with a lower heating and cooling times, resulting in a 16×16 high order MIMO system. A low-cost realtime infrared thermal camera is employed as a temperature feedback sensor instead of a standard thermal sensor, ideal for high order MIMO system sensing and temperature distribution tracking. The control algorithm is developed in Matlab/Simulink and employs an Arduino board in hardware in the loop configuration to apply the control action to each Peltier module in the array. A temperature control experiment is performed, showing that the platform is suitable for teaching and training experiences not only in the classroom but also for engineers in the industry. Furthermore, various abnormal conditions can be introduced so that smart control engineering features can be tested.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115777197","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：