Pub Date : 2019-08-01DOI: 10.1109/COASE.2019.8843166
Efe C. Balta, D. Tilbury, K. Barton
Digital twin (DT) and additive manufacturing (AM) technologies are key enablers for smart manufacturing systems. DTs of AM systems are proposed in recent literature to provide additional analysis and monitoring capabilities to the physical AM processes. This work proposes a DT framework for real-time performance monitoring and anomaly detection in fused deposition modeling (FDM) AM process. The proposed DT framework can accommodate AM process measurement data to model the AM process as a cyber-physical system with continuous and discrete event dynamics, and allow for the development of various applications. A new performance metric is proposed for performance monitoring and a formal specification based anomaly detection method is proposed for AM processes. Implementation of the proposed DT on an off-the-shelf FDM printer and experimental results of anomaly detection and process monitoring are presented at the end.
{"title":"A Digital Twin Framework for Performance Monitoring and Anomaly Detection in Fused Deposition Modeling","authors":"Efe C. Balta, D. Tilbury, K. Barton","doi":"10.1109/COASE.2019.8843166","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843166","url":null,"abstract":"Digital twin (DT) and additive manufacturing (AM) technologies are key enablers for smart manufacturing systems. DTs of AM systems are proposed in recent literature to provide additional analysis and monitoring capabilities to the physical AM processes. This work proposes a DT framework for real-time performance monitoring and anomaly detection in fused deposition modeling (FDM) AM process. The proposed DT framework can accommodate AM process measurement data to model the AM process as a cyber-physical system with continuous and discrete event dynamics, and allow for the development of various applications. A new performance metric is proposed for performance monitoring and a formal specification based anomaly detection method is proposed for AM processes. Implementation of the proposed DT on an off-the-shelf FDM printer and experimental results of anomaly detection and process monitoring are presented at the end.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"28 1","pages":"823-829"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89453932","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 : 2019-08-01DOI: 10.1109/COASE.2019.8842996
J. Morales‐Valdez, M. Lopez, Wen Yu
This paper presents a novel approach for damage detection in building structures by using the dissipated energy. In this sense, the hysteretic Bouc-Wen model is introduced as a useful tool for describing the degrading energy, which is directly related to the stiffness loss. Since, parameters and states of this model are unknown, we employ a nonlinear system identification algorithm based on Convolutional Neural Network (CNN) to avoid estimate simultaneously the states and parameters of the model. The used CNN have the sparse connectivity, which ensures that the strong response can be detected by convolution filters. In addition, the shared weights of the CNN reduce the the training complexity and the number of its parameters because the same weights are applied to all inputs. Therefore, the CNN can detect features no matter where they are on the vibration data, also reducing the training complexity. The use of this tool avoids using an adaptive observer, which unlike CNN, the algorithm’s complexity increases with the number of unknown parameters and states. Moreover, the adaptive observer can not guarantee convergence in presence of measurement noise. Experimental results confirmed that the proposed method is promising for real applications.
{"title":"Damage detection of building structure based on vibration data and hysteretic model","authors":"J. Morales‐Valdez, M. Lopez, Wen Yu","doi":"10.1109/COASE.2019.8842996","DOIUrl":"https://doi.org/10.1109/COASE.2019.8842996","url":null,"abstract":"This paper presents a novel approach for damage detection in building structures by using the dissipated energy. In this sense, the hysteretic Bouc-Wen model is introduced as a useful tool for describing the degrading energy, which is directly related to the stiffness loss. Since, parameters and states of this model are unknown, we employ a nonlinear system identification algorithm based on Convolutional Neural Network (CNN) to avoid estimate simultaneously the states and parameters of the model. The used CNN have the sparse connectivity, which ensures that the strong response can be detected by convolution filters. In addition, the shared weights of the CNN reduce the the training complexity and the number of its parameters because the same weights are applied to all inputs. Therefore, the CNN can detect features no matter where they are on the vibration data, also reducing the training complexity. The use of this tool avoids using an adaptive observer, which unlike CNN, the algorithm’s complexity increases with the number of unknown parameters and states. Moreover, the adaptive observer can not guarantee convergence in presence of measurement noise. Experimental results confirmed that the proposed method is promising for real applications.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"19 1","pages":"608-613"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90831068","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843276
Yanran Zhu, A. Matta, Ettore Lanzarone, Na Geng
This paper addresses a home care (HC) scheduling problem faced by a real provider working in New York City area, USA. HC scheduling is an extension of vehicle routing problem with specific constraints and characteristics. The addressed problem is also a matching problem since it considers the caregiver-client matching which depends on the value of each pair’s satisfaction. The novelties of our problem lie in chargeable overtimes, preference matching and several specific constraints from the provider. A mathematical model for the problem is provided with the objective of minimizing the unmatched preferences, the overtime cost paid by provider and the total caregivers’ travel time. A variable neighborhood search algorithm is also proposed to solve the problem and tested on a real instance from considered HC provider. Numerical results show that the proposed algorithm can efficiently provide high quality solutions on real-sized instances.
{"title":"A Variable Neighborhood Search for Home Care Scheduling Under Chargeable Overtime and Preference Matching*","authors":"Yanran Zhu, A. Matta, Ettore Lanzarone, Na Geng","doi":"10.1109/COASE.2019.8843276","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843276","url":null,"abstract":"This paper addresses a home care (HC) scheduling problem faced by a real provider working in New York City area, USA. HC scheduling is an extension of vehicle routing problem with specific constraints and characteristics. The addressed problem is also a matching problem since it considers the caregiver-client matching which depends on the value of each pair’s satisfaction. The novelties of our problem lie in chargeable overtimes, preference matching and several specific constraints from the provider. A mathematical model for the problem is provided with the objective of minimizing the unmatched preferences, the overtime cost paid by provider and the total caregivers’ travel time. A variable neighborhood search algorithm is also proposed to solve the problem and tested on a real instance from considered HC provider. Numerical results show that the proposed algorithm can efficiently provide high quality solutions on real-sized instances.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"37 1","pages":"281-286"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89758320","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843248
Michael A. Mrochen, O. Sawodny
This article considers the transition between pure electrical driving and hybrid driving in a hybrid dual-clutch transmission powertrain while following a prescribed vehicle speed reference. The key aspect here is a fast and smooth engine start without interruption of the demanded driving torque and minimum jerk. A two-degree-of-freedom controller with a flatness-based feedforward control and an asymptotic tracking control is presented for solving this task. We use a scheduled control structure to cope with the switched dynamical characteristics of the internal combustion engine while being started traversing sticktion, cranking and combustion. The control scheme switches from a torque-based control for the break-free of the engine to a speed-based control for the tracking of a reference engine speed trajectory. We illustrate the performance of the control scheme by means of meaningful simulations.
{"title":"Flatness-based Powertrain Control for Engine Start Applications in Hybrid Dual-Clutch Transmissions","authors":"Michael A. Mrochen, O. Sawodny","doi":"10.1109/COASE.2019.8843248","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843248","url":null,"abstract":"This article considers the transition between pure electrical driving and hybrid driving in a hybrid dual-clutch transmission powertrain while following a prescribed vehicle speed reference. The key aspect here is a fast and smooth engine start without interruption of the demanded driving torque and minimum jerk. A two-degree-of-freedom controller with a flatness-based feedforward control and an asymptotic tracking control is presented for solving this task. We use a scheduled control structure to cope with the switched dynamical characteristics of the internal combustion engine while being started traversing sticktion, cranking and combustion. The control scheme switches from a torque-based control for the break-free of the engine to a speed-based control for the tracking of a reference engine speed trajectory. We illustrate the performance of the control scheme by means of meaningful simulations.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"27 1","pages":"1562-1567"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90359826","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843270
Haoming Zhao, Zhanbo Xu, Jiang Wu, Kun Liu, Lei Yang, X. Guan
The stochastic demand of electric vehicles (EVs) charging and building’s heating, ventilation and air conditioning (HVAC) system account for a large proportion in social energy consumption. The photovoltaic (PV) system becomes miniaturized and applied on roof of smart buildings with the development of a sequence of PV power generation technologies. Due to the randomness of weather conditions and human behavior, the power supply is random as well as the power demand. To guarantee the power balance in real-time, it is necessary to coordinate the dispatch of EVs and HVACs with the uncertainties from both sides. A mixed integer programming is formulated to model the coordination of the EVs and HVAC systems. The operation strategies of EVs and HVAC systems under uncertainties in both supply and demand are determined based on the model predictive control (MPC) framework. The performance of the coordination of EVs and HVAC systems is demonstrated using numerical case studies. The results show that coordinating the operation of EVs and HVAC systems can significantly reduce the cost and accommodate the uncertainties in the PV supply.
{"title":"Optimal Coordination of EVs and HVAC Systems with Uncertain Renewable Supply","authors":"Haoming Zhao, Zhanbo Xu, Jiang Wu, Kun Liu, Lei Yang, X. Guan","doi":"10.1109/COASE.2019.8843270","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843270","url":null,"abstract":"The stochastic demand of electric vehicles (EVs) charging and building’s heating, ventilation and air conditioning (HVAC) system account for a large proportion in social energy consumption. The photovoltaic (PV) system becomes miniaturized and applied on roof of smart buildings with the development of a sequence of PV power generation technologies. Due to the randomness of weather conditions and human behavior, the power supply is random as well as the power demand. To guarantee the power balance in real-time, it is necessary to coordinate the dispatch of EVs and HVACs with the uncertainties from both sides. A mixed integer programming is formulated to model the coordination of the EVs and HVAC systems. The operation strategies of EVs and HVAC systems under uncertainties in both supply and demand are determined based on the model predictive control (MPC) framework. The performance of the coordination of EVs and HVAC systems is demonstrated using numerical case studies. The results show that coordinating the operation of EVs and HVAC systems can significantly reduce the cost and accommodate the uncertainties in the PV supply.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"74 1","pages":"733-738"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90634551","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843235
L. Xiao, Tao Huang, Bo Wu, Youmin Hu, Jiehan Zhou
In this paper, we propose an instance level hierarchical features based convolution neural network model (H-CNN) for detecting surface defects. The H-CNN uses different convolutional layers’ extracted features to generate defect masks. The H-CNN first generates proposal regions. Then, it proposes a fully convolutional neural network to extract different level’s convolutional features and detect instance level defects. We applied the H-CNN model in freight train detection system for detecting oil-leaks, and the results demonstrate that the H-CNN can effectively identify and generate defect masks. It achieves 92% accuracy on the large reflective oil-leak stain, 86% on the large non-reflective oil-leak stain, 89% on the small reflective oil-leak stain and 74% on the small non-reflective oil-leak stain. Its image process speed is 0.467 s per frame.
{"title":"Surface Defect Detection using Hierarchical Features","authors":"L. Xiao, Tao Huang, Bo Wu, Youmin Hu, Jiehan Zhou","doi":"10.1109/COASE.2019.8843235","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843235","url":null,"abstract":"In this paper, we propose an instance level hierarchical features based convolution neural network model (H-CNN) for detecting surface defects. The H-CNN uses different convolutional layers’ extracted features to generate defect masks. The H-CNN first generates proposal regions. Then, it proposes a fully convolutional neural network to extract different level’s convolutional features and detect instance level defects. We applied the H-CNN model in freight train detection system for detecting oil-leaks, and the results demonstrate that the H-CNN can effectively identify and generate defect masks. It achieves 92% accuracy on the large reflective oil-leak stain, 86% on the large non-reflective oil-leak stain, 89% on the small reflective oil-leak stain and 74% on the small non-reflective oil-leak stain. Its image process speed is 0.467 s per frame.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"31 2 1","pages":"1592-1596"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76777721","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 : 2019-08-01DOI: 10.1109/COASE.2019.8842946
Danilo V. Cunha, F. Lizarralde
This paper considers the pathconstrained trajectory tracking for robot manipulators optimizing a limited energy budget. The proposed strategy is based on a Nonlinear Receding Horizon Predictive Control (NRHPC) using a path parameterization of dimension one. The dynamic of the parameterized trajectory is governed by a predefined linear system, then an energy and a cost functions are defined and a NRHPC based on a Newton method is used to minimize the cost function in real time. The method is presented in both joint and task space. The proposed solution is verified on a 4 DOF manipulator with successful simulation and experimental results.
{"title":"Real-Time Path-Constrained Trajectory Tracking for Robot Manipulators with Energy Budget Optimization","authors":"Danilo V. Cunha, F. Lizarralde","doi":"10.1109/COASE.2019.8842946","DOIUrl":"https://doi.org/10.1109/COASE.2019.8842946","url":null,"abstract":"This paper considers the pathconstrained trajectory tracking for robot manipulators optimizing a limited energy budget. The proposed strategy is based on a Nonlinear Receding Horizon Predictive Control (NRHPC) using a path parameterization of dimension one. The dynamic of the parameterized trajectory is governed by a predefined linear system, then an energy and a cost functions are defined and a NRHPC based on a Newton method is used to minimize the cost function in real time. The method is presented in both joint and task space. The proposed solution is verified on a 4 DOF manipulator with successful simulation and experimental results.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"151 1","pages":"1327-1332"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74871883","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843138
Ruijiu Mao, Bin Du, Dengfeng Sun, N. Kong
Emergency medical service must be time sensitive. However, in many cases, satisfactory service cannot be ensured due to inconvenient logistics. For its easily deployable and widely accessible nature, unmanned aerial vehicles (UAVs) have the potential to improve the service, especially in areas that are traditionally under-served. In this paper, we develop a service network optimization problem for locating UAV bases, staffing a UAV fleet at each constructed base, and zoning demand nodes. We formulate a location-allocation optimization model with numerically simulated waiting times for the service zones as the objective. We adapt a genetic algorithm to solve the optimization model. We test our network optimization approach on instances of traumatic injury cases. By comparing our approach to a two-phase method in Boutilier et al. [1], we suggest an up to 60% reduction in mean waiting time.
{"title":"Optimizing a UAV-based Emergency Medical Service Network for Trauma Injury Patients*","authors":"Ruijiu Mao, Bin Du, Dengfeng Sun, N. Kong","doi":"10.1109/COASE.2019.8843138","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843138","url":null,"abstract":"Emergency medical service must be time sensitive. However, in many cases, satisfactory service cannot be ensured due to inconvenient logistics. For its easily deployable and widely accessible nature, unmanned aerial vehicles (UAVs) have the potential to improve the service, especially in areas that are traditionally under-served. In this paper, we develop a service network optimization problem for locating UAV bases, staffing a UAV fleet at each constructed base, and zoning demand nodes. We formulate a location-allocation optimization model with numerically simulated waiting times for the service zones as the objective. We adapt a genetic algorithm to solve the optimization model. We test our network optimization approach on instances of traumatic injury cases. By comparing our approach to a two-phase method in Boutilier et al. [1], we suggest an up to 60% reduction in mean waiting time.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"8 1","pages":"721-726"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74877470","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 : 2019-08-01DOI: 10.1109/COASE.2019.8843000
E. Mackensen, Julius Klose, Axel Rombach, Aaron Spitznagel
Smart Home or Smart Building applications are a growing market. An increasing challenge is to design energy efficient Smart Home applications to achieve sustainable and green homes. Using the example of the development of an Indoor Smart Gardening system with wireless monitoring and automated watering this paper is discussing in particular the design issue of energy autonomous working sensors and actuators for home automation. Most important part of the presented Smart Gardening system is a 3D printed smart flower pot for single plants. The smart flower pot has integrated a water reservoir for automated plant irrigation and an electronic for monitoring important plant parameters and the water level of the water reservoir. Energy harvesting with solar cells enables energy autonomous working of the flower pot. A low-power wireless interface also integrated in the flowerpot and an external gateway based on a Raspberry Pi 3 enables wireless networking of multiple of those flower pots. The gateway is used for evaluating the plant parameters and as a user interface. Particularly the architecture of the energy autonomous wireless flower pot will be considered, because fully energy autonomous sensors and actuators for home automation could not be implemented without special concepts for the energy supply and the overall electronic.
{"title":"Energy autonomous automation of Smart Home applications using the example of a wireless Indoor Smart Gardening system","authors":"E. Mackensen, Julius Klose, Axel Rombach, Aaron Spitznagel","doi":"10.1109/COASE.2019.8843000","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843000","url":null,"abstract":"Smart Home or Smart Building applications are a growing market. An increasing challenge is to design energy efficient Smart Home applications to achieve sustainable and green homes. Using the example of the development of an Indoor Smart Gardening system with wireless monitoring and automated watering this paper is discussing in particular the design issue of energy autonomous working sensors and actuators for home automation. Most important part of the presented Smart Gardening system is a 3D printed smart flower pot for single plants. The smart flower pot has integrated a water reservoir for automated plant irrigation and an electronic for monitoring important plant parameters and the water level of the water reservoir. Energy harvesting with solar cells enables energy autonomous working of the flower pot. A low-power wireless interface also integrated in the flowerpot and an external gateway based on a Raspberry Pi 3 enables wireless networking of multiple of those flower pots. The gateway is used for evaluating the plant parameters and as a user interface. Particularly the architecture of the energy autonomous wireless flower pot will be considered, because fully energy autonomous sensors and actuators for home automation could not be implemented without special concepts for the energy supply and the overall electronic.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"57 1","pages":"1087-1092"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84791710","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}
Occupants’ thermal comfort plays a critical role in the optimization of building operation, which has thus attracted more and more attention in recent years. However, diversity and uncertainties in the thermal comfort, which is caused by not only the physical environment, but also the psychology and physiology, provide challenges in the modeling of the thermal comfort. In this paper, based on cyber-physical system framework, we develop a thermal comfort model by a model-driven learning approach to dynamically predict the personalized thermal comfort through online learning and computation. This model consists of a physical part and a data-driven part. The physical part is developed based on the traditional heat balance equation. Since in the physical part there are some parameters (such as skin temperature) are difficult to be measured in practice, a data-driven part is thus developed based on the regression model to estimate the uncertain parameters with the feedback of occupants. By integrating the data-driven part into the physical part, the developed model could take both advantages of the model-driven and data-driven methods. The effectiveness and performance of the developed thermal comfort model are demonstrated using field experiments.
{"title":"A Model-Driven Learning Approach for Predicting the Personalized Dynamic Thermal Comfort in Ordinary Office Environment","authors":"Yadong Zhou, Xukun Wang, Zhanbo Xu, Ying Su, Ting Liu, Chao Shen, X. Guan","doi":"10.1109/COASE.2019.8843073","DOIUrl":"https://doi.org/10.1109/COASE.2019.8843073","url":null,"abstract":"Occupants’ thermal comfort plays a critical role in the optimization of building operation, which has thus attracted more and more attention in recent years. However, diversity and uncertainties in the thermal comfort, which is caused by not only the physical environment, but also the psychology and physiology, provide challenges in the modeling of the thermal comfort. In this paper, based on cyber-physical system framework, we develop a thermal comfort model by a model-driven learning approach to dynamically predict the personalized thermal comfort through online learning and computation. This model consists of a physical part and a data-driven part. The physical part is developed based on the traditional heat balance equation. Since in the physical part there are some parameters (such as skin temperature) are difficult to be measured in practice, a data-driven part is thus developed based on the regression model to estimate the uncertain parameters with the feedback of occupants. By integrating the data-driven part into the physical part, the developed model could take both advantages of the model-driven and data-driven methods. The effectiveness and performance of the developed thermal comfort model are demonstrated using field experiments.","PeriodicalId":6695,"journal":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"739-744"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85233245","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：