Pub Date : 2019-06-01DOI: 10.1109/ICIEA.2019.8833717
Shijie Wu, Lei Li, Weiwei Liu
This article briefly introduces the working principle of dual active half-bridge(DAHB) and the reasons for current mismatch at first, then describes a sensorless current sharing method for two module input-parallel output-parallel(IPOP) connected DAHB converter. This method estimates module parameters ratio by a single perturbation. The duty ratio of the module with larger parameters is compensated by a calculated correction amount according to estimated module parameter ratio. Simulations show that this estimation and compensation method can achieve sensorless current sharing well.
{"title":"Sensorless Current Sharing Method for Two Module Input-Parallel Output-Parallel(IPOP) Connected Dual Active Half-Bridge(DAHB) Converters","authors":"Shijie Wu, Lei Li, Weiwei Liu","doi":"10.1109/ICIEA.2019.8833717","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833717","url":null,"abstract":"This article briefly introduces the working principle of dual active half-bridge(DAHB) and the reasons for current mismatch at first, then describes a sensorless current sharing method for two module input-parallel output-parallel(IPOP) connected DAHB converter. This method estimates module parameters ratio by a single perturbation. The duty ratio of the module with larger parameters is compensated by a calculated correction amount according to estimated module parameter ratio. Simulations show that this estimation and compensation method can achieve sensorless current sharing well.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127612172","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8834117
Binquan Wang, Zeyuan Wu, Zakir Ullah Khan, Chenglin Liu, Ming Zhu
The deep ConvNets is suitable for learning the mapping between CXR gradients. This paper proposes an example segmentation algorithm based on deep learning applied to xray medical image automatic segmentation annotation. The basic convolutional neural network is used to extract the feature map of the image, and the corresponding branch structure: classification, regression, and mask that can complete the automatic analysis of the image's infrastructure. Our method is evaluated on a dataset that consisted of 180 cases of real two-exposure dual-energy subtraction chest radiographs. Meanwhile, we design histogram averaging and data augmentation to enhance the low contrast image. Finally, we visualize the image and the good results have been achieved in the segmentation and labeling of clavicle and rib. We hope that our research will provide a good prospect for the application of deep learning in automatic segmentation and labeling of medical images.
{"title":"Deep Convolutional Neural Network with Segmentation Techniques for Chest X-Ray Analysis","authors":"Binquan Wang, Zeyuan Wu, Zakir Ullah Khan, Chenglin Liu, Ming Zhu","doi":"10.1109/ICIEA.2019.8834117","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8834117","url":null,"abstract":"The deep ConvNets is suitable for learning the mapping between CXR gradients. This paper proposes an example segmentation algorithm based on deep learning applied to xray medical image automatic segmentation annotation. The basic convolutional neural network is used to extract the feature map of the image, and the corresponding branch structure: classification, regression, and mask that can complete the automatic analysis of the image's infrastructure. Our method is evaluated on a dataset that consisted of 180 cases of real two-exposure dual-energy subtraction chest radiographs. Meanwhile, we design histogram averaging and data augmentation to enhance the low contrast image. Finally, we visualize the image and the good results have been achieved in the segmentation and labeling of clavicle and rib. We hope that our research will provide a good prospect for the application of deep learning in automatic segmentation and labeling of medical images.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126315574","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833694
Weizhang Song, N. An, You-yun Wang
A bidirectional DC breaker based on T-source series circuit is presented in this paper, which can work in the application where require bi-directional power flow between different nodes of microgrid and loads. When a short-circuit fault occurs, the proposed topology utilizes a T-source transformer to naturally commutate off the thyristor(SCR) by coupling and reducing the current to zero through the thyristor, thus avoiding circuit breaking under high current operating condition, furthermore, this topology allows a response to faults on either the source or load side only using a single controlled switch, no additional passive components are required compared with the unidirectional series T-source circuit breaker topology. The analysis is performed to find the fault conditions that cause the bi-directional circuit breaker to trip when operating in a single load power system, the transfer function of this breaker circuit is deduced and circuit parameters is designed. Finally, the operation principle of the bi-directional circuit breaker is evaluated for both source and load side faults by using a simulation platform PSIM.
{"title":"A Novel Bidirectional T-source DC Circuit Breaker for DC Microgrids","authors":"Weizhang Song, N. An, You-yun Wang","doi":"10.1109/ICIEA.2019.8833694","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833694","url":null,"abstract":"A bidirectional DC breaker based on T-source series circuit is presented in this paper, which can work in the application where require bi-directional power flow between different nodes of microgrid and loads. When a short-circuit fault occurs, the proposed topology utilizes a T-source transformer to naturally commutate off the thyristor(SCR) by coupling and reducing the current to zero through the thyristor, thus avoiding circuit breaking under high current operating condition, furthermore, this topology allows a response to faults on either the source or load side only using a single controlled switch, no additional passive components are required compared with the unidirectional series T-source circuit breaker topology. The analysis is performed to find the fault conditions that cause the bi-directional circuit breaker to trip when operating in a single load power system, the transfer function of this breaker circuit is deduced and circuit parameters is designed. Finally, the operation principle of the bi-directional circuit breaker is evaluated for both source and load side faults by using a simulation platform PSIM.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126347881","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833802
Bai Zhang, Jiakun Zhang, Xueliang Kang, Ren Zheng
With the continuous development of optoelectronic information technology, modern manufacturing industry has higher requirements on the response speed, precision and resolution of sensors. A new high-precision continuous displacement sensor is proposed by combining the amplification principle of optical arm with the traditional position sensitive detector (PSD) in this paper. By using the principle of optical triangle amplification, the tiny displacement is transformed to the long side of the triangle, and the reflected laser is measured by the position sensitive detector to obtain the laser displacement of the long side. The structure of triangular wave optical reflector combined with dislocation multi-probe is adopted to realize alternating displacement measurement and extend the measuring range of the sensor. The experimental results show that the measurement principle proposed in this paper is correct, and the low-cost precision measurement of 1 µ m is preliminarily realized.
{"title":"Research on high precision displacement sensor based on optical arm amplification","authors":"Bai Zhang, Jiakun Zhang, Xueliang Kang, Ren Zheng","doi":"10.1109/ICIEA.2019.8833802","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833802","url":null,"abstract":"With the continuous development of optoelectronic information technology, modern manufacturing industry has higher requirements on the response speed, precision and resolution of sensors. A new high-precision continuous displacement sensor is proposed by combining the amplification principle of optical arm with the traditional position sensitive detector (PSD) in this paper. By using the principle of optical triangle amplification, the tiny displacement is transformed to the long side of the triangle, and the reflected laser is measured by the position sensitive detector to obtain the laser displacement of the long side. The structure of triangular wave optical reflector combined with dislocation multi-probe is adopted to realize alternating displacement measurement and extend the measuring range of the sensor. The experimental results show that the measurement principle proposed in this paper is correct, and the low-cost precision measurement of 1 µ m is preliminarily realized.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125450466","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833983
Xiaokun Li, Junwei Lu, W. Water
Unmanned aerial vehicle (UAV) has been widely used in a variety of occasions in recent decades. Due to the lack of battery capacity, its endurance has been limited. To tackle this problem, wireless power transfer (WPT) technology is a great solution to UAV from the charging perspective. In this paper, a data and power wireless transfer system of UAV based on inductive power transfer (IPT) technology is proposed. The key constraint of wireless charging with regards to the inherent magnetic coupling coefficient is investigated. In this paper, ferrite and metglas amorphous alloy are used as a case study of the magnetic coupling problem. The magnetic material is placed next to the secondary coil side to investigate the effects of horizontal displacement and air gap distance on the coupling coefficient and magnetic field distribution. An experimental system platform is implemented, and the commercial finite element software tool Comsol is used to evaluate the performance of the magnetic material. The simulation results showed that amorphous alloy magnetic material is superior to ferrite material, and it is in a good agreement to the experimental results. Furthermore, the attention of using metglass material in the practical application has been discussed.
{"title":"Design and Study of Data and Power Wireless Transfer System for UAV","authors":"Xiaokun Li, Junwei Lu, W. Water","doi":"10.1109/ICIEA.2019.8833983","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833983","url":null,"abstract":"Unmanned aerial vehicle (UAV) has been widely used in a variety of occasions in recent decades. Due to the lack of battery capacity, its endurance has been limited. To tackle this problem, wireless power transfer (WPT) technology is a great solution to UAV from the charging perspective. In this paper, a data and power wireless transfer system of UAV based on inductive power transfer (IPT) technology is proposed. The key constraint of wireless charging with regards to the inherent magnetic coupling coefficient is investigated. In this paper, ferrite and metglas amorphous alloy are used as a case study of the magnetic coupling problem. The magnetic material is placed next to the secondary coil side to investigate the effects of horizontal displacement and air gap distance on the coupling coefficient and magnetic field distribution. An experimental system platform is implemented, and the commercial finite element software tool Comsol is used to evaluate the performance of the magnetic material. The simulation results showed that amorphous alloy magnetic material is superior to ferrite material, and it is in a good agreement to the experimental results. Furthermore, the attention of using metglass material in the practical application has been discussed.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125488201","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833645
Muhammad Yousif, Q. Ai, M. T. Anwar, Shuangrui Yin, Yang Gao, Ran Hao
Currently, the electricity generation companies around the world are moving towards low carbon and low-cost generation sources. It is supported by literature that instead of a single type of renewable source located at one place, dispersed and multiple types of the renewable sources can be the promising solution for low carbon and low-cost electricity supply. However, the best combination of these dispersed and different types of renewable sources for a certain area completely depends on the electric load profile and natural occurrences of natural phenomena. Authors model several combinations of renewable sources (e.g. wind turbine, Solar PV) and energy storage systems (e.g. battery, fuel cell) to supply electricity to a large-scale grid. The proposed model calculates the required combination of renewable sources and energy storage using hourly load and meteorological data of a whole year (8760 hours). Authors find out that low carbon and low-cost combinations contain excessive electricity generation capacity. The presented case study shows this excessive generation capacity is about three times the load peak demand. This is because the different types and excessive renewable generation capacity can meet the load using smaller energy storage which lessens the total system cost.
{"title":"Modeling Low Carbon and Low-Cost Electricity Supply for Pakistan","authors":"Muhammad Yousif, Q. Ai, M. T. Anwar, Shuangrui Yin, Yang Gao, Ran Hao","doi":"10.1109/ICIEA.2019.8833645","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833645","url":null,"abstract":"Currently, the electricity generation companies around the world are moving towards low carbon and low-cost generation sources. It is supported by literature that instead of a single type of renewable source located at one place, dispersed and multiple types of the renewable sources can be the promising solution for low carbon and low-cost electricity supply. However, the best combination of these dispersed and different types of renewable sources for a certain area completely depends on the electric load profile and natural occurrences of natural phenomena. Authors model several combinations of renewable sources (e.g. wind turbine, Solar PV) and energy storage systems (e.g. battery, fuel cell) to supply electricity to a large-scale grid. The proposed model calculates the required combination of renewable sources and energy storage using hourly load and meteorological data of a whole year (8760 hours). Authors find out that low carbon and low-cost combinations contain excessive electricity generation capacity. The presented case study shows this excessive generation capacity is about three times the load peak demand. This is because the different types and excessive renewable generation capacity can meet the load using smaller energy storage which lessens the total system cost.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125494920","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833843
D. Jiandong, Yang Yao, Jin Zhuanting, Cheng Yulin
This paper uses ARMA model to model the prediction error of wind power, and obtains the probability distribution of the prediction error by probability statistical analysis to simulate the uncertainty of wind power. Latin hypercube simulation is used to sample typical wind power prediction errors, and a large number of wind power scenarios are reduced. On this basis, taking into account the power-to-gas, a optimal dispatch model of the integrated power and gas systems(IPGS) is established with the objective of minimizing the operation cost of the system. The CPLEX solver is used to complete the solution of the model. Finally, modified 6-bus power system and 7-node natural gas system are used to construct an IPGS. This paper uses this IPGS to do the simulation test and cases studies. Which verifies the effectiveness of the model, and further reveals the advantages of power-to-gas in promoting wind power absorption and improving system operation economy.
{"title":"Optimal Dispatch of Integrated Power and Gas Systems Considering Wind Power Uncertainty","authors":"D. Jiandong, Yang Yao, Jin Zhuanting, Cheng Yulin","doi":"10.1109/ICIEA.2019.8833843","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833843","url":null,"abstract":"This paper uses ARMA model to model the prediction error of wind power, and obtains the probability distribution of the prediction error by probability statistical analysis to simulate the uncertainty of wind power. Latin hypercube simulation is used to sample typical wind power prediction errors, and a large number of wind power scenarios are reduced. On this basis, taking into account the power-to-gas, a optimal dispatch model of the integrated power and gas systems(IPGS) is established with the objective of minimizing the operation cost of the system. The CPLEX solver is used to complete the solution of the model. Finally, modified 6-bus power system and 7-node natural gas system are used to construct an IPGS. This paper uses this IPGS to do the simulation test and cases studies. Which verifies the effectiveness of the model, and further reveals the advantages of power-to-gas in promoting wind power absorption and improving system operation economy.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125683508","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8834224
Qi Yang, Jing Liu, Hong Guo, Xiao Zeng, Wei Hu
Information Collection System for Vehicles is also known as Vehicle Traveling Data Recorder, which can be collected and recorded in real-time vehicle status with electronic devices. It is used to ensure traffic safety and plays an important role in the post-analysis when road traffic accidents occurred. The study of the vehicle traveling data recorder is existed very early in inland and outland, 90 years of 20 centuries along with the fast development of technology and science and car market, a lot of graduate schools and company start to research and exploit the vehicle traveling data recorder, and many related productions appear in the market. For enhancing the criterion of the vehicle traveling data recorder, this system is exploited basically according to National standard of vehicle traveling data recorder, uses MSP430 ultra-low power single-chip microcomputer as the master device, Micro SD card as a real-time memory. It can record, collect, process the information of car lights, braking, speeding and wheel speed. Recorder using USB module communications with the PC connected to these records through data analysis data processing software for real-time data recorded in post-processing analysis.
{"title":"A Novel Design of Information Collection System for Vehicles for Real-time Monitoring","authors":"Qi Yang, Jing Liu, Hong Guo, Xiao Zeng, Wei Hu","doi":"10.1109/ICIEA.2019.8834224","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8834224","url":null,"abstract":"Information Collection System for Vehicles is also known as Vehicle Traveling Data Recorder, which can be collected and recorded in real-time vehicle status with electronic devices. It is used to ensure traffic safety and plays an important role in the post-analysis when road traffic accidents occurred. The study of the vehicle traveling data recorder is existed very early in inland and outland, 90 years of 20 centuries along with the fast development of technology and science and car market, a lot of graduate schools and company start to research and exploit the vehicle traveling data recorder, and many related productions appear in the market. For enhancing the criterion of the vehicle traveling data recorder, this system is exploited basically according to National standard of vehicle traveling data recorder, uses MSP430 ultra-low power single-chip microcomputer as the master device, Micro SD card as a real-time memory. It can record, collect, process the information of car lights, braking, speeding and wheel speed. Recorder using USB module communications with the PC connected to these records through data analysis data processing software for real-time data recorded in post-processing analysis.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122014693","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8834001
T. Tang, Bin Yu, Hengbin Cui, Na Wang, Wensheng Song
Multi-phase permanent magnet synchronous motors (PMSM) are potentially used in the field of rail transit and due to theirs high power density and high reliability. For high power applications, Multi-mode modulation strategy based on selective harmonic elimination pulse width modulation (SHEPWM) are often used to achieve excellent current performance at very low switching frequency. However, the current impact caused by transition process of SHEPWM with different carrier ratios is a terrible issue in engineering application. To address this problem, this paper investigates the generation mechanism of current impact in the transition process according to the equivalent circuit model of five-phase PMSM firstly. Furthermore, theoretical analysis results proved that each phase independent switching scheme can achieve different carrier ratio SHEPWM smooth transition. Finally, the simulation results have verified the correctness and effectiveness of the theoretical analysis.
{"title":"Selective Harmonic Elimination PWM Switching Principle in Multi-Mode Modulation for Five-Phase Permanent Magnet Synchronous Motors","authors":"T. Tang, Bin Yu, Hengbin Cui, Na Wang, Wensheng Song","doi":"10.1109/ICIEA.2019.8834001","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8834001","url":null,"abstract":"Multi-phase permanent magnet synchronous motors (PMSM) are potentially used in the field of rail transit and due to theirs high power density and high reliability. For high power applications, Multi-mode modulation strategy based on selective harmonic elimination pulse width modulation (SHEPWM) are often used to achieve excellent current performance at very low switching frequency. However, the current impact caused by transition process of SHEPWM with different carrier ratios is a terrible issue in engineering application. To address this problem, this paper investigates the generation mechanism of current impact in the transition process according to the equivalent circuit model of five-phase PMSM firstly. Furthermore, theoretical analysis results proved that each phase independent switching scheme can achieve different carrier ratio SHEPWM smooth transition. Finally, the simulation results have verified the correctness and effectiveness of the theoretical analysis.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132533680","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 : 2019-06-01DOI: 10.1109/ICIEA.2019.8833650
Xuan Ma, Guoxin Ma
In view of the potentially infinite, fast-reaching, single-scan and noise-related characteristics of time series stream data, a method of data driven modeling and predicting is proposed in this paper. In order to enhance the real-time performance and the modeling accuracy of algorithm to the time series stream, we use a double sliding window to divide the time series stream data. One window is designed as a fixed length window to evaluate the fluctuation of the actual data, the other, as a variable length window, is used to establish a prediction model by GEP algorithm and generate prediction data. And then, the actual data and the prediction data calculated by the prediction model are fused to generate a fusion data. The colony climbing algorithm is applied to improve the population diversity of GEP to improve the prediction accuracy of modeling. The numerical simulation to the four test data sets shows that the proposed algorithm has better prediction accuracy than the Hierarchical Temporal Memory algorithm.
{"title":"Research on Modeling and Forecasting Driven by Time Series Stream Data","authors":"Xuan Ma, Guoxin Ma","doi":"10.1109/ICIEA.2019.8833650","DOIUrl":"https://doi.org/10.1109/ICIEA.2019.8833650","url":null,"abstract":"In view of the potentially infinite, fast-reaching, single-scan and noise-related characteristics of time series stream data, a method of data driven modeling and predicting is proposed in this paper. In order to enhance the real-time performance and the modeling accuracy of algorithm to the time series stream, we use a double sliding window to divide the time series stream data. One window is designed as a fixed length window to evaluate the fluctuation of the actual data, the other, as a variable length window, is used to establish a prediction model by GEP algorithm and generate prediction data. And then, the actual data and the prediction data calculated by the prediction model are fused to generate a fusion data. The colony climbing algorithm is applied to improve the population diversity of GEP to improve the prediction accuracy of modeling. The numerical simulation to the four test data sets shows that the proposed algorithm has better prediction accuracy than the Hierarchical Temporal Memory algorithm.","PeriodicalId":311302,"journal":{"name":"2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130115122","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：