Pub Date : 2007-05-23DOI: 10.1109/ICIEA.2007.4318679
Li Xie, Lizi Zhang, Hua Zheng, Ying Xie
Sensitivity analysis is an effective tool to mine the dynamic characteristics of the explanatory variables on the result variable. But due to the complexity of the influence factors, the sensitivity analysis on electricity price is along one of focused and unsolved problems in the researches of electricity market. To solve this problem, a novel model is proposed to analyze the sensitivity of electricity price. The basic and first work here is to mine the quantity explanatory equation of electricity price, which is built based on hybrid algorithm that integrates support vector machine (SVM) with regression. To enhance the accuracy and adaptibility of price model, SVM is applied for price pattern identification. And different regression models are built in terms of their corresponding patterns. After that, the derivatives of all explanatory variables in the equation are computed. Then the sensitivity coefficients of price are obtained. Finally case studies are used to testify the validity of the proposed model.
{"title":"On the Sensitivity Analysis of Electricity Price","authors":"Li Xie, Lizi Zhang, Hua Zheng, Ying Xie","doi":"10.1109/ICIEA.2007.4318679","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318679","url":null,"abstract":"Sensitivity analysis is an effective tool to mine the dynamic characteristics of the explanatory variables on the result variable. But due to the complexity of the influence factors, the sensitivity analysis on electricity price is along one of focused and unsolved problems in the researches of electricity market. To solve this problem, a novel model is proposed to analyze the sensitivity of electricity price. The basic and first work here is to mine the quantity explanatory equation of electricity price, which is built based on hybrid algorithm that integrates support vector machine (SVM) with regression. To enhance the accuracy and adaptibility of price model, SVM is applied for price pattern identification. And different regression models are built in terms of their corresponding patterns. After that, the derivatives of all explanatory variables in the equation are computed. Then the sensitivity coefficients of price are obtained. Finally case studies are used to testify the validity of the proposed model.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116847230","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318518
Tao Xin-min, Chen Wan-hai, Duan Bao-xiang, Xu Yong, Dong Han-Guang
In many bearing fault anomaly detection application, only positive (normal) samples are available for training purposes, other abnormal samples are difficult to be available. In order to solve these practical application problems, a novel model of one-class bearing fault detection based on SVDD and genetic algorithm is presented in this paper. The time domain statistics features are processed as inputs to SVDD for one-class (normal) recognition. Then SVDD is used to describe the normal data distribution characteristics with high data description ability. The SVDD is trained only with a subset of normal samples. This paper also analyzes the behavior of the classifier based on parameter selection and proposes a novel way based on genetic algorithm to determine the optimal threshold parameters. The hybrid one-class classification model of SVDD and genetic algorithm is determined to address the problem of difficultly collecting abnormal samples in bearing fault detection. Comparison of the performance of detection of SVDD with different kernel parameters is experimented. This hybrid approach is compared against other MLP detection techniques. The results show the relative effectiveness of the proposed classifiers in detection of the bearing condition with some concluding remarks.
{"title":"A Novel Model of one-class Bearing Fault Detection using SVDD and Genetic Algorithm","authors":"Tao Xin-min, Chen Wan-hai, Duan Bao-xiang, Xu Yong, Dong Han-Guang","doi":"10.1109/ICIEA.2007.4318518","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318518","url":null,"abstract":"In many bearing fault anomaly detection application, only positive (normal) samples are available for training purposes, other abnormal samples are difficult to be available. In order to solve these practical application problems, a novel model of one-class bearing fault detection based on SVDD and genetic algorithm is presented in this paper. The time domain statistics features are processed as inputs to SVDD for one-class (normal) recognition. Then SVDD is used to describe the normal data distribution characteristics with high data description ability. The SVDD is trained only with a subset of normal samples. This paper also analyzes the behavior of the classifier based on parameter selection and proposes a novel way based on genetic algorithm to determine the optimal threshold parameters. The hybrid one-class classification model of SVDD and genetic algorithm is determined to address the problem of difficultly collecting abnormal samples in bearing fault detection. Comparison of the performance of detection of SVDD with different kernel parameters is experimented. This hybrid approach is compared against other MLP detection techniques. The results show the relative effectiveness of the proposed classifiers in detection of the bearing condition with some concluding remarks.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117005671","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318881
Weiwei Li, Dianguo Xu, Wei Zhang, Hongfei Ma
In this paper, a wind turbine emulator (WTE) is designed and implemented considering different requirements from the development and test of control strategy in a doubly-fed wind power generating system. The WTE is based on a DSP system and a 4.2 kW separately-excited DC motor. The WTE can accurately reproduce the characteristics of real wind turbine. A PC interface is also developed using C language based on LabWindows to provide friendly user interface and real-time control of experiments. The WTE is tested in a grid-connected variable speed constant frequency AC excited doubly-fed wind power generating system, and the experimental results show that the scheme is viable and effective. This paper reports the operating principles, theoretical analyses, wind turbine modeling and the experimental results of the WTE.
{"title":"Research on Wind Turbine Emulation based on DC Motor","authors":"Weiwei Li, Dianguo Xu, Wei Zhang, Hongfei Ma","doi":"10.1109/ICIEA.2007.4318881","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318881","url":null,"abstract":"In this paper, a wind turbine emulator (WTE) is designed and implemented considering different requirements from the development and test of control strategy in a doubly-fed wind power generating system. The WTE is based on a DSP system and a 4.2 kW separately-excited DC motor. The WTE can accurately reproduce the characteristics of real wind turbine. A PC interface is also developed using C language based on LabWindows to provide friendly user interface and real-time control of experiments. The WTE is tested in a grid-connected variable speed constant frequency AC excited doubly-fed wind power generating system, and the experimental results show that the scheme is viable and effective. This paper reports the operating principles, theoretical analyses, wind turbine modeling and the experimental results of the WTE.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129565576","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318661
Yao-hua Li, Weiguo Liu
An improved direct torque control (DTC) scheme based on the effect of voltage vector on torque for permanent magnet synchronous motor (PMSM) is proposed in this paper, which can increase useful voltage vectors in a sector to 6. Simulation results show that can lower unreasonable torque ripple effectively.
{"title":"Simulation Study on the Effect of Voltage Vector on Torque in Direct Torque Control System of Permanent Magnet Synchronous Motor","authors":"Yao-hua Li, Weiguo Liu","doi":"10.1109/ICIEA.2007.4318661","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318661","url":null,"abstract":"An improved direct torque control (DTC) scheme based on the effect of voltage vector on torque for permanent magnet synchronous motor (PMSM) is proposed in this paper, which can increase useful voltage vectors in a sector to 6. Simulation results show that can lower unreasonable torque ripple effectively.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129623255","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318823
B. Lin, Chien-Lan Huang, H. Chiang
A soft switching pulse-width modulation (PWM) Cuk converter with boost type of active clamp is proposed. Active clamp circuit can help the switching devices in the Cuk converter to be operated at zero voltage switching (ZVS) turn-on. Therefore this converter is suitable for high frequency operation to reduce the size of reactive components. The clamp capacitor and auxiliary switch are connected in parallel with the primary switch. When main switch is turned off, the positive inductor current will flow through the anti-parallel diode of auxiliary switch. At this instant, the auxiliary switch can turn on at ZVS. On the other hand, the resonance between the resonant inductor and output capacitor of main switch will create a ZVS condition for main switch. The principle of operation, system analysis, and design consideration are presented in this paper. Experimental results for a laboratory prototype rated at 400 W, input voltage of 150 V~300 V, output voltage of 200 V, and operating at 105 kHz are given to demonstrate the effectiveness of the proposed converter.
{"title":"Analysis of a Soft Switching PWM Active Clamp Cuk Converter","authors":"B. Lin, Chien-Lan Huang, H. Chiang","doi":"10.1109/ICIEA.2007.4318823","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318823","url":null,"abstract":"A soft switching pulse-width modulation (PWM) Cuk converter with boost type of active clamp is proposed. Active clamp circuit can help the switching devices in the Cuk converter to be operated at zero voltage switching (ZVS) turn-on. Therefore this converter is suitable for high frequency operation to reduce the size of reactive components. The clamp capacitor and auxiliary switch are connected in parallel with the primary switch. When main switch is turned off, the positive inductor current will flow through the anti-parallel diode of auxiliary switch. At this instant, the auxiliary switch can turn on at ZVS. On the other hand, the resonance between the resonant inductor and output capacitor of main switch will create a ZVS condition for main switch. The principle of operation, system analysis, and design consideration are presented in this paper. Experimental results for a laboratory prototype rated at 400 W, input voltage of 150 V~300 V, output voltage of 200 V, and operating at 105 kHz are given to demonstrate the effectiveness of the proposed converter.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129631507","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318369
Chunguo Jing, D. Shu, Deying Gu
The remote streetlight monitoring and control system has been applied in urban streetlight. In general, this system monitoring and control scope only reaches the streetlight transformer station. In this work, an experimental system of wireless sensor network was developed to study the feasibility for streetlight monitoring and control system. This system consists of the sensor node, the remote terminal unit and the control center. The sensor node was installed at each lamp pole and used to detect and control lamp. The remote terminal unit serves as relay station between the control center and the sensor nodes. The control center monitor and control all streetlight real time. The hardware of sensor node and remote terminal unit was design. The software was developed for sensor node, remote terminal unit and the control center. The multi-hop used in nodes. The test results show that the system can be used for the streetlight control. The system application in streetlight can extend control scope to each lamp, reduce in streetlight electricity and maintenance cost, and increase availability of streetlight.
{"title":"Design of Streetlight Monitoring and Control System Based on Wireless Sensor Networks","authors":"Chunguo Jing, D. Shu, Deying Gu","doi":"10.1109/ICIEA.2007.4318369","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318369","url":null,"abstract":"The remote streetlight monitoring and control system has been applied in urban streetlight. In general, this system monitoring and control scope only reaches the streetlight transformer station. In this work, an experimental system of wireless sensor network was developed to study the feasibility for streetlight monitoring and control system. This system consists of the sensor node, the remote terminal unit and the control center. The sensor node was installed at each lamp pole and used to detect and control lamp. The remote terminal unit serves as relay station between the control center and the sensor nodes. The control center monitor and control all streetlight real time. The hardware of sensor node and remote terminal unit was design. The software was developed for sensor node, remote terminal unit and the control center. The multi-hop used in nodes. The test results show that the system can be used for the streetlight control. The system application in streetlight can extend control scope to each lamp, reduce in streetlight electricity and maintenance cost, and increase availability of streetlight.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128305813","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318580
Shao-de Zhang, Xiao Zheng
RBF neural network ( RBFN ) based on nearest neighbor clustering algorithm is applied for three phase electrode system in Ladle Furnace ( LF ). Real time on line inverse identification and indirect decoupling of LF three phase electrode system is realized. Hereon, the inverse identification model is applied as inverse control model. The scheme of inverse control based on RBFN and PD control is designed, which is applied to LF electrode system successfully in third iron steel plant of Maanshan P.R.China.
{"title":"Application of The Control Scheme based on RBF Inverse Dynamic Identification in Electrode System of Ladle Furnace","authors":"Shao-de Zhang, Xiao Zheng","doi":"10.1109/ICIEA.2007.4318580","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318580","url":null,"abstract":"RBF neural network ( RBFN ) based on nearest neighbor clustering algorithm is applied for three phase electrode system in Ladle Furnace ( LF ). Real time on line inverse identification and indirect decoupling of LF three phase electrode system is realized. Hereon, the inverse identification model is applied as inverse control model. The scheme of inverse control based on RBFN and PD control is designed, which is applied to LF electrode system successfully in third iron steel plant of Maanshan P.R.China.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128758515","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318882
Z. Xie, C.W. Zhang, X. Zhang, S.Y. Yang, R. Cao
This paper analyzes the stator flux oriented vector control theory for doubly fed induction generator, control strategy of no-load cutting-in based on grid voltage feedback and control strategy of grid connected based on speed feedback are used in this system, the arithmetic of maximum power point tracking independent of the turbine characteristics and air density is used in this system. The results of the experiments performed on an 100kW test-bed with prototype verified the adopted strategies' feasibility in system soft cut-in, decoupled control of active and reactive power, as well as the maximum wind power tracking.
{"title":"Study On The Rotor Convertor Of Doubly Fed Induction Generator Used In Wind Turbine System","authors":"Z. Xie, C.W. Zhang, X. Zhang, S.Y. Yang, R. Cao","doi":"10.1109/ICIEA.2007.4318882","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318882","url":null,"abstract":"This paper analyzes the stator flux oriented vector control theory for doubly fed induction generator, control strategy of no-load cutting-in based on grid voltage feedback and control strategy of grid connected based on speed feedback are used in this system, the arithmetic of maximum power point tracking independent of the turbine characteristics and air density is used in this system. The results of the experiments performed on an 100kW test-bed with prototype verified the adopted strategies' feasibility in system soft cut-in, decoupled control of active and reactive power, as well as the maximum wind power tracking.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128973460","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318454
Zhen Liu, Jinming Shi, Zhongying Bai
A new image segmentation method based on discrete Krawtchouk moments and Quantum neural networks is presented. The Krawtchouk moments in certain local window of each pixel in the image are computed and input to quantum neural network . Quantum neural networks, which use multilevel transfer function, have the inherent fuzzy characteristics. The point accommodates to the connatural uncertainty of fractional image data in image segmentation procession. Experiments confirm that the performance of our proposed methods is more accurate and has less iterative time in comparison with the traditional segmentation methods based on Legendre moments and BP neutral networks.
{"title":"Image Segmentation based on discrete Krawtchouk Moment and Quantum Neural Network","authors":"Zhen Liu, Jinming Shi, Zhongying Bai","doi":"10.1109/ICIEA.2007.4318454","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318454","url":null,"abstract":"A new image segmentation method based on discrete Krawtchouk moments and Quantum neural networks is presented. The Krawtchouk moments in certain local window of each pixel in the image are computed and input to quantum neural network . Quantum neural networks, which use multilevel transfer function, have the inherent fuzzy characteristics. The point accommodates to the connatural uncertainty of fractional image data in image segmentation procession. Experiments confirm that the performance of our proposed methods is more accurate and has less iterative time in comparison with the traditional segmentation methods based on Legendre moments and BP neutral networks.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128975195","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 : 2007-05-23DOI: 10.1109/ICIEA.2007.4318540
Yinhai Zhu, W. Cai, C. Wen
Existing ejector models are either very complex nonlinear ones with coupled equations or empirical correlations suitable for particular ejector geometries and operation conditions, resulting in difficulties for real time applications. Therefore, it is practically important to develop a simple, yet accurate ejector engineering model that will yield better real time control and optimization of ejector refrigeration systems (ERS). In this paper, a new, simple, yet accurate hybrid ejector model is presented, which is induced by shock circle model [1] based on fluid dynamics and energy balance principles. Comparison with the published experimental data shows that the model is robust and gives a better match to real performances of all the 11 different ejectors over the entire operating range when compared to existing models in the literature.
{"title":"Development of Control Model for Critical Operation Ejector","authors":"Yinhai Zhu, W. Cai, C. Wen","doi":"10.1109/ICIEA.2007.4318540","DOIUrl":"https://doi.org/10.1109/ICIEA.2007.4318540","url":null,"abstract":"Existing ejector models are either very complex nonlinear ones with coupled equations or empirical correlations suitable for particular ejector geometries and operation conditions, resulting in difficulties for real time applications. Therefore, it is practically important to develop a simple, yet accurate ejector engineering model that will yield better real time control and optimization of ejector refrigeration systems (ERS). In this paper, a new, simple, yet accurate hybrid ejector model is presented, which is induced by shock circle model [1] based on fluid dynamics and energy balance principles. Comparison with the published experimental data shows that the model is robust and gives a better match to real performances of all the 11 different ejectors over the entire operating range when compared to existing models in the literature.","PeriodicalId":231682,"journal":{"name":"2007 2nd IEEE Conference on Industrial Electronics and Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129244219","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：