Pub Date : 2018-04-01DOI: 10.1109/IGBSG.2018.8393526
X. Kong, Ji Zhang, Yining Xiao, Lingwu Qian, Lumei Su, Benbin Chen, Min Xu
With the development of intelligent technology, the nuclear power plant(NPP) is getting more and more smarter. For the traditional nuclear power plant, the performance of the steam generator level control was greatly determined by a group of preset control parameters. Usually, these parameter settings were not optimal because the tuning process was experience-based, cumbersome and time-consuming. To improve the control performance and make the NPP more smarter, in this paper, a revised Simultaneous Perturbation Stochastic Approximation algorithm(SPSA) was proposed to optimize the control parameters of the steam generator level control system. The effectiveness of this method has been demonstrated through simulation experiments.
{"title":"Performance optimization for steam generator level control based on a revised simultaneous perturbation stochastic approximation algorithm","authors":"X. Kong, Ji Zhang, Yining Xiao, Lingwu Qian, Lumei Su, Benbin Chen, Min Xu","doi":"10.1109/IGBSG.2018.8393526","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393526","url":null,"abstract":"With the development of intelligent technology, the nuclear power plant(NPP) is getting more and more smarter. For the traditional nuclear power plant, the performance of the steam generator level control was greatly determined by a group of preset control parameters. Usually, these parameter settings were not optimal because the tuning process was experience-based, cumbersome and time-consuming. To improve the control performance and make the NPP more smarter, in this paper, a revised Simultaneous Perturbation Stochastic Approximation algorithm(SPSA) was proposed to optimize the control parameters of the steam generator level control system. The effectiveness of this method has been demonstrated through simulation experiments.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130473614","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393578
S. Chou, Aditya Budhi, A. Dewabharata, F. E. Zulvia
Elevator management system has received impressive attention due to its significance to transportation effectiveness for mid and high building. An important thing to improve elevator management system is to collect external information. This paper presents a method to collect number of passenger by using cameras and deep learning. By considering the status inside elevators, the directions of passenger movement, and the number of waiting passengers, the system occasionally allocates multiple elevators for a single hall call, which assists in reducing passengers' waiting time. This study applies deep learning to identify number of people queuing for an elevator. Data is gathered through some cameras to be analyzed with Region Based Convolutional Neural Network (R-CNN). Finally, we optimize the elevator dispatching rule by adding queuing data to the traditional elevator control system. Our goal is to minimize the average waiting time of the passengers.
{"title":"Improving elevator dynamic control policies based on energy and demand visibility","authors":"S. Chou, Aditya Budhi, A. Dewabharata, F. E. Zulvia","doi":"10.1109/IGBSG.2018.8393578","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393578","url":null,"abstract":"Elevator management system has received impressive attention due to its significance to transportation effectiveness for mid and high building. An important thing to improve elevator management system is to collect external information. This paper presents a method to collect number of passenger by using cameras and deep learning. By considering the status inside elevators, the directions of passenger movement, and the number of waiting passengers, the system occasionally allocates multiple elevators for a single hall call, which assists in reducing passengers' waiting time. This study applies deep learning to identify number of people queuing for an elevator. Data is gathered through some cameras to be analyzed with Region Based Convolutional Neural Network (R-CNN). Finally, we optimize the elevator dispatching rule by adding queuing data to the traditional elevator control system. Our goal is to minimize the average waiting time of the passengers.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134487302","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393565
Xiao-Qian Li, Song Zheng
In recent years, the intelligence and automation of building systems have gained further development with the development of communication technology. Based on the characteristics and research progress of the intelligent building system, this paper analyzes some existing problems in the existing intelligent building system, and then puts forward intelligent building universal control platform architecture based on the multi-agent system and communication middleware, which shows significant adaptability and advantages in many aspects, including the heterogeneous devices connection, collaborative control, human-computer interaction and user self-management. This system can greatly improve the energy efficiency of building systems and provide a new route for the intelligent building research.
{"title":"Application of universal control platform in intelligent building","authors":"Xiao-Qian Li, Song Zheng","doi":"10.1109/IGBSG.2018.8393565","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393565","url":null,"abstract":"In recent years, the intelligence and automation of building systems have gained further development with the development of communication technology. Based on the characteristics and research progress of the intelligent building system, this paper analyzes some existing problems in the existing intelligent building system, and then puts forward intelligent building universal control platform architecture based on the multi-agent system and communication middleware, which shows significant adaptability and advantages in many aspects, including the heterogeneous devices connection, collaborative control, human-computer interaction and user self-management. This system can greatly improve the energy efficiency of building systems and provide a new route for the intelligent building research.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116394097","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393540
Ming Hsu, Yih-Shiou Lo, C. Lin
In order to study and observe images, image enhancement methods are often used to improve low quality images. The purpose of image enhancement is to make the region of interest become clearer, and to weaken or even delete the uninterested regions. In this paper, we use the retinex theory and exposure fusion to enhance the contrast of images. In the proposed method, we only manipulate the V channel of the HSV color space to maintain color consistency as far as possible. First, we estimate the local and the global incident lights respectively, and use the retinex theory to get images with local and global details. Following exposure fusion, the two images and the original image are used to generate the enhanced image. Experiments show that the proposed method can strengthen both the local and global details, and effectively reduce halo, color distortion, and noise problems. In short, the result images look quite nature. In summary, the proposed method can enhance the image quality, and make images easier to be analyzed and understood.
{"title":"Retinex image enhancement based on exposure fusion","authors":"Ming Hsu, Yih-Shiou Lo, C. Lin","doi":"10.1109/IGBSG.2018.8393540","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393540","url":null,"abstract":"In order to study and observe images, image enhancement methods are often used to improve low quality images. The purpose of image enhancement is to make the region of interest become clearer, and to weaken or even delete the uninterested regions. In this paper, we use the retinex theory and exposure fusion to enhance the contrast of images. In the proposed method, we only manipulate the V channel of the HSV color space to maintain color consistency as far as possible. First, we estimate the local and the global incident lights respectively, and use the retinex theory to get images with local and global details. Following exposure fusion, the two images and the original image are used to generate the enhanced image. Experiments show that the proposed method can strengthen both the local and global details, and effectively reduce halo, color distortion, and noise problems. In short, the result images look quite nature. In summary, the proposed method can enhance the image quality, and make images easier to be analyzed and understood.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123434660","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393549
H. T. Likassa, Wen-Hsien Fang, Y. Chuang
This paper proposes an effective and robust algorithm for image alignment on a set of linearly correlated ata. The new algorithm modifies the Robust Algorithm for Sparse and Low rank decomposition (RASL) by utilizing the prior information of partial column rank. To attain this, an extra term is incorporated in the decomposition of data matrix, which enables the new approach to be more resilient to errors, outliers and occlusions. The problem is cast as a constrained optimization problem, which is then solved by convex program. A new set of equations are also derived to update the variables involved in a round-robin manner. Conducted simulations on the recovery of aligned face images and handwritten digits reveal the effectiveness of the new algorithm compared with the main state-of-the-art works.
{"title":"Modified robust image alignment by sparse and low rank decomposition for highly linearly correlated data","authors":"H. T. Likassa, Wen-Hsien Fang, Y. Chuang","doi":"10.1109/IGBSG.2018.8393549","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393549","url":null,"abstract":"This paper proposes an effective and robust algorithm for image alignment on a set of linearly correlated ata. The new algorithm modifies the Robust Algorithm for Sparse and Low rank decomposition (RASL) by utilizing the prior information of partial column rank. To attain this, an extra term is incorporated in the decomposition of data matrix, which enables the new approach to be more resilient to errors, outliers and occlusions. The problem is cast as a constrained optimization problem, which is then solved by convex program. A new set of equations are also derived to update the variables involved in a round-robin manner. Conducted simulations on the recovery of aligned face images and handwritten digits reveal the effectiveness of the new algorithm compared with the main state-of-the-art works.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"42 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121011713","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393545
Cheng-Yu Chen, Jenq-Shiou Leu, S. W. Prakosa
Due to the development of internet, plentiful different data appear rapidly. The amounts of features also increase when the technique for collecting data becomes mature. Observation of different data is usually not an easy task because it needs some background related to data pre-processing. Therefore, dimensionality reduction (DR) becomes a familiar method to reduce the amount of features and keep the critical information. However, the loss of information during the processing of dimensionality reduction is unavoidable. When the targeted dimension is far lower than original dimension, the loss is too high to be endurable. To solve this problem, we use the encoder structure from autoencoder to compare to some common dimensionality reduction methods. We use the simplest autoencoder structure as the preprocessing of Support Vector Machine (SVM) to see the result.
{"title":"Using autoencoder to facilitate information retention for data dimension reduction","authors":"Cheng-Yu Chen, Jenq-Shiou Leu, S. W. Prakosa","doi":"10.1109/IGBSG.2018.8393545","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393545","url":null,"abstract":"Due to the development of internet, plentiful different data appear rapidly. The amounts of features also increase when the technique for collecting data becomes mature. Observation of different data is usually not an easy task because it needs some background related to data pre-processing. Therefore, dimensionality reduction (DR) becomes a familiar method to reduce the amount of features and keep the critical information. However, the loss of information during the processing of dimensionality reduction is unavoidable. When the targeted dimension is far lower than original dimension, the loss is too high to be endurable. To solve this problem, we use the encoder structure from autoencoder to compare to some common dimensionality reduction methods. We use the simplest autoencoder structure as the preprocessing of Support Vector Machine (SVM) to see the result.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124632616","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393563
Zhang Changkun, X. Zhihong
MSs (Magnetic switches) have been widely used in situations where frequent on-off load are required. The operating voltage range of the conventional magnetic switch is usually between 85% and 110% of the rated control voltage. When the control voltage sags, the narrow operating voltage range might lead the conventional MS to malfunction causing an unintended operation of load. To address this problem, a control module is designed in this paper: the control parameters of the module are obtained from simulation result of MS by Maxwell, a bi-coefficient feedback control strategy is established to improve the accuracy of coil current control, and a waveform detection strategy is used to shorten the time from the opening operation occurred to the MS switching off the load for increasing the operation frequency.
{"title":"A control strategy in operation process of magnetic switch","authors":"Zhang Changkun, X. Zhihong","doi":"10.1109/IGBSG.2018.8393563","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393563","url":null,"abstract":"MSs (Magnetic switches) have been widely used in situations where frequent on-off load are required. The operating voltage range of the conventional magnetic switch is usually between 85% and 110% of the rated control voltage. When the control voltage sags, the narrow operating voltage range might lead the conventional MS to malfunction causing an unintended operation of load. To address this problem, a control module is designed in this paper: the control parameters of the module are obtained from simulation result of MS by Maxwell, a bi-coefficient feedback control strategy is established to improve the accuracy of coil current control, and a waveform detection strategy is used to shorten the time from the opening operation occurred to the MS switching off the load for increasing the operation frequency.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114884449","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393543
Yi-Chieh Hsu, Li-Sheng Hsu, Jing-Yuan Lin, C. C. Chen
The dual current pumping control technique is presented in this paper to achieve fast-transient response for dc-dc converters. The current buffers are adopted to provide additional current paths with output nodes of dc-dc converter and error amplifier. This method leads to accelerating output level of error amplifier and charging/discharging output capacitor rapidly. The proposed dc-dc converter with dual current pumping control technique is fabricated using TSMC 0.35μm 2P4M CMOS technology. Load current from 50mA to 500mA. Transient recovery time with step-up and step-down are 2.3μs and 1.2μs, respectively. Compared with the conventional dc-dc converter, simulation results demonstrate that the transient recovery time of proposed dc-dc converter with dual current pumping control technique is improved over four times.
{"title":"Buck DC-DC converter for fast transient response using dual current pumping control technique","authors":"Yi-Chieh Hsu, Li-Sheng Hsu, Jing-Yuan Lin, C. C. Chen","doi":"10.1109/IGBSG.2018.8393543","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393543","url":null,"abstract":"The dual current pumping control technique is presented in this paper to achieve fast-transient response for dc-dc converters. The current buffers are adopted to provide additional current paths with output nodes of dc-dc converter and error amplifier. This method leads to accelerating output level of error amplifier and charging/discharging output capacitor rapidly. The proposed dc-dc converter with dual current pumping control technique is fabricated using TSMC 0.35μm 2P4M CMOS technology. Load current from 50mA to 500mA. Transient recovery time with step-up and step-down are 2.3μs and 1.2μs, respectively. Compared with the conventional dc-dc converter, simulation results demonstrate that the transient recovery time of proposed dc-dc converter with dual current pumping control technique is improved over four times.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117223461","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393564
Jierong Zhuang, Zhihong Xu, Yang Wang
Traditional electromagnetic contactor suffers from a lack of controllability when opening. In this paper, the new contactor with the controlled actuator having structure of segregated magnetic path is designed, which generates electromagnetic force in opposite directions. A new control module featuring energy reclaiming and power management for fast opening is proposed. The compensation network is designed by simulated results to confirm that the voltage and current loop is stable during energy storage stage and energy release stage. Cosimulation, in which Multisim software simulates the circuitry and LabVIEW software executes the model of the new controlled contactor, is carried out to analyze energy reclaiming strategy for the closed loop control of opening process. The experiment is reported to validate the accuracy and effectiveness of the module design and the reclaiming strategy.
{"title":"A novel strategy of energy reclaiming for electromagnetic contactor with controlled actuator","authors":"Jierong Zhuang, Zhihong Xu, Yang Wang","doi":"10.1109/IGBSG.2018.8393564","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393564","url":null,"abstract":"Traditional electromagnetic contactor suffers from a lack of controllability when opening. In this paper, the new contactor with the controlled actuator having structure of segregated magnetic path is designed, which generates electromagnetic force in opposite directions. A new control module featuring energy reclaiming and power management for fast opening is proposed. The compensation network is designed by simulated results to confirm that the voltage and current loop is stable during energy storage stage and energy release stage. Cosimulation, in which Multisim software simulates the circuitry and LabVIEW software executes the model of the new controlled contactor, is carried out to analyze energy reclaiming strategy for the closed loop control of opening process. The experiment is reported to validate the accuracy and effectiveness of the module design and the reclaiming strategy.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128011855","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 : 2018-04-01DOI: 10.1109/IGBSG.2018.8393566
Su Jingjing, X. Zhihong, Zhang Changkun
The growing tendency of the abnormity and accident which caused by arc fault has already become the social harmfulness in the power system. With the extensive use of electrical equipment, arc fault has the features of randomness, which further increase the difficulty to recognize arc and set higher requirement on the performance of arc fault protection switch. In this paper, a comprehensive test system is developed to generate arc and study the characteristics of arc fault on the basis of integrated design and multi-threading technique. Then the effectiveness and credibility of arc fault simulation devices have been verified and the characteristics of arc fault are analyzed under different loads. Experiments show that characteristic of arc fault are influenced by the fault reasons and load in series. The system can meet the requirements of arc fault protection switch research, and can provide experimental condition and data support for the research of arc fault detection technique.
{"title":"Design of test system for arc fault protection switch","authors":"Su Jingjing, X. Zhihong, Zhang Changkun","doi":"10.1109/IGBSG.2018.8393566","DOIUrl":"https://doi.org/10.1109/IGBSG.2018.8393566","url":null,"abstract":"The growing tendency of the abnormity and accident which caused by arc fault has already become the social harmfulness in the power system. With the extensive use of electrical equipment, arc fault has the features of randomness, which further increase the difficulty to recognize arc and set higher requirement on the performance of arc fault protection switch. In this paper, a comprehensive test system is developed to generate arc and study the characteristics of arc fault on the basis of integrated design and multi-threading technique. Then the effectiveness and credibility of arc fault simulation devices have been verified and the characteristics of arc fault are analyzed under different loads. Experiments show that characteristic of arc fault are influenced by the fault reasons and load in series. The system can meet the requirements of arc fault protection switch research, and can provide experimental condition and data support for the research of arc fault detection technique.","PeriodicalId":356367,"journal":{"name":"2018 3rd International Conference on Intelligent Green Building and Smart Grid (IGBSG)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114700054","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：