Pub Date : 2006-10-23DOI: 10.1109/WCICA.2006.1713346
Qiang Wang, Changmin Yuan, Jianyun Zhu
To monitor third-party damage (TPD) activities on oil transmission pipeline such as man-made drilling, hammering and excavating on metallic pipe, acoustic method is proposed based on wavelet packet energy feature extraction and least square support vector machine (LS-SVM). To effectively detect and classify pipe TPD signals with small sampling, multi-class LS-SVM classifier algorithm and a novel feature extraction method is presented. Original TPD signal is divided into third level with wavelet transform, then approximation signal which covers main information of TPD signal is extracted to be decomposed into third level with wavelet packet decomposition. Wavelet packet energy is selected as feature to LS-SVMs. Feature extraction method reduces computation cost of on-line implement. When detection spacing is 600m, four TPD signals: normal, drilling, hammering and excavating conditions, classification success rate is more than 85%. The monitoring system can effectively detect and classify pipe acoustic TPD signal
{"title":"Buried Pipeline Third-Party Damage Signals Classification Based on LS-SVM","authors":"Qiang Wang, Changmin Yuan, Jianyun Zhu","doi":"10.1109/WCICA.2006.1713346","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1713346","url":null,"abstract":"To monitor third-party damage (TPD) activities on oil transmission pipeline such as man-made drilling, hammering and excavating on metallic pipe, acoustic method is proposed based on wavelet packet energy feature extraction and least square support vector machine (LS-SVM). To effectively detect and classify pipe TPD signals with small sampling, multi-class LS-SVM classifier algorithm and a novel feature extraction method is presented. Original TPD signal is divided into third level with wavelet transform, then approximation signal which covers main information of TPD signal is extracted to be decomposed into third level with wavelet packet decomposition. Wavelet packet energy is selected as feature to LS-SVMs. Feature extraction method reduces computation cost of on-line implement. When detection spacing is 600m, four TPD signals: normal, drilling, hammering and excavating conditions, classification success rate is more than 85%. The monitoring system can effectively detect and classify pipe acoustic TPD signal","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129116958","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1712400
Ruiyue Lin
In many applications of DEA approach, there is often a fixed cost or resource which is imposed on all decision making units. One nature question then is: how can this cost or resource be assigned in a reasonable way to various DMUs? To obtain this cost or resource allocation, in this paper we propose a DEA approach, which is based on three assumptions: invariance, minimal distance to average allocation and positive. For illustrating the method, numerical results for an example from the literature are presented
{"title":"An Equitable Allocation of Fixed Costs and Resources: A DEA Approach","authors":"Ruiyue Lin","doi":"10.1109/WCICA.2006.1712400","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1712400","url":null,"abstract":"In many applications of DEA approach, there is often a fixed cost or resource which is imposed on all decision making units. One nature question then is: how can this cost or resource be assigned in a reasonable way to various DMUs? To obtain this cost or resource allocation, in this paper we propose a DEA approach, which is based on three assumptions: invariance, minimal distance to average allocation and positive. For illustrating the method, numerical results for an example from the literature are presented","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129210161","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1713943
Yi-fan Xu, Fang Li, Tao Hu
Kernel Fisher discriminant analysis (KFD) has good performance in practice as a classification method. However, KFD is initially developed for binary classification. To solving multi-class classification problems, multi-class KFD (MKFD) was designed to minimize total deviation. By Lagrange multiplier method, MKFD was transformed to be a quadratic optimization problem that can avoid solving eigenproblem and be less numerical demanding relatively. Moreover it is shown that MKFD is a direct generalization of the binary classification. Finally the performance of MKFD was tested on the benchmark datasets in experiments. The results support usefulness of MKFD, compared with other methods such as support vector machines
{"title":"A Method of Kernel Fisher Discriminant for Multi-class Classification","authors":"Yi-fan Xu, Fang Li, Tao Hu","doi":"10.1109/WCICA.2006.1713943","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1713943","url":null,"abstract":"Kernel Fisher discriminant analysis (KFD) has good performance in practice as a classification method. However, KFD is initially developed for binary classification. To solving multi-class classification problems, multi-class KFD (MKFD) was designed to minimize total deviation. By Lagrange multiplier method, MKFD was transformed to be a quadratic optimization problem that can avoid solving eigenproblem and be less numerical demanding relatively. Moreover it is shown that MKFD is a direct generalization of the binary classification. Finally the performance of MKFD was tested on the benchmark datasets in experiments. The results support usefulness of MKFD, compared with other methods such as support vector machines","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123801392","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1712671
Zheng Xiaoqing, Shao Zhijiang
Automatic differentiation is the approach of differentiation without truncation error introduced. In this paper, two ways of automatic differentiation based on source transformation and operator overloading are investigated and applied to the optimization of distillation column. After comparing with the traditional finite difference method, the result proves the automatic differentiation approach based on source transformation the highest efficient in the optimization
{"title":"Research on Automatic Differentiation and the Application to Distillation Column Optimization","authors":"Zheng Xiaoqing, Shao Zhijiang","doi":"10.1109/WCICA.2006.1712671","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1712671","url":null,"abstract":"Automatic differentiation is the approach of differentiation without truncation error introduced. In this paper, two ways of automatic differentiation based on source transformation and operator overloading are investigated and applied to the optimization of distillation column. After comparing with the traditional finite difference method, the result proves the automatic differentiation approach based on source transformation the highest efficient in the optimization","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124238573","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1712704
Dongliang Liu, Weican Yan, Yikang He
Parameters of permanent magnet synchronous motor (PMSM) may occur variety when it is running. It effects performance of system. Adaptive backstepping control is applied to the speed tracking control of PMSM with uncertain parameters. It can estimate stator resistance, friction coefficient and load with real time. The system can remain its good performance when system parameters deviate from normal values. Global ultimate attractiveness of system tracking error and parameters is also proved. The simulated result indicates that the control scheme has the advantage of efficiency and feasibility of the system design
{"title":"Speed Tracking Control of PMSM with Adaptive Backstepping","authors":"Dongliang Liu, Weican Yan, Yikang He","doi":"10.1109/WCICA.2006.1712704","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1712704","url":null,"abstract":"Parameters of permanent magnet synchronous motor (PMSM) may occur variety when it is running. It effects performance of system. Adaptive backstepping control is applied to the speed tracking control of PMSM with uncertain parameters. It can estimate stator resistance, friction coefficient and load with real time. The system can remain its good performance when system parameters deviate from normal values. Global ultimate attractiveness of system tracking error and parameters is also proved. The simulated result indicates that the control scheme has the advantage of efficiency and feasibility of the system design","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"57 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123459982","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1713255
R. Zheng, Huiqiang Wang
Based on BMNSM (bio-inspired multidimensional network security model), this paper briefly states "three-net paralleling (TNP)" mode and proves its state attribute. Because the implementation structure of TNP decides the exertion of each performance of BMNSM, this paper analyses three types of implementation structures - elementary structure (implementation structure of traditional network security), evolutive structure and advanced structure and concludes that the advanced structure owns excellent performances comparing to other implantation structures by quantificational compare
{"title":"Study on Bio-inspired TNP Implementation Structure of BMNSM","authors":"R. Zheng, Huiqiang Wang","doi":"10.1109/WCICA.2006.1713255","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1713255","url":null,"abstract":"Based on BMNSM (bio-inspired multidimensional network security model), this paper briefly states \"three-net paralleling (TNP)\" mode and proves its state attribute. Because the implementation structure of TNP decides the exertion of each performance of BMNSM, this paper analyses three types of implementation structures - elementary structure (implementation structure of traditional network security), evolutive structure and advanced structure and concludes that the advanced structure owns excellent performances comparing to other implantation structures by quantificational compare","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121147414","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1714210
Jie Ying Gao, Shaojun Li, F. Qian
The efficiency of mining association rules is an important field of knowledge discovery in databases. The algorithm a priori is a classical algorithm in mining association rules. A novel procedure was proposed to delete many transactions which need not be scanned repeatedly. The procedure described in this paper reduced the number of database passes to extract frequent item sets. A method was showed to reduce the number of candidate item sets by optimizing the join procedure of frequent item sets. To this end, the I a priori algorithm for mining frequent item sets, which is the improvement algorithm of a priori, is designed in this article. By a number of experiments, the proposed algorithm outperforms the a priori algorithm in computational time. The simulation results of knowledge acquisition for fault diagnosis also show the validity of I a priori algorithm
{"title":"A Method of Improvement and Optimization on Association Rules Apriori Algorithm","authors":"Jie Ying Gao, Shaojun Li, F. Qian","doi":"10.1109/WCICA.2006.1714210","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1714210","url":null,"abstract":"The efficiency of mining association rules is an important field of knowledge discovery in databases. The algorithm a priori is a classical algorithm in mining association rules. A novel procedure was proposed to delete many transactions which need not be scanned repeatedly. The procedure described in this paper reduced the number of database passes to extract frequent item sets. A method was showed to reduce the number of candidate item sets by optimizing the join procedure of frequent item sets. To this end, the I a priori algorithm for mining frequent item sets, which is the improvement algorithm of a priori, is designed in this article. By a number of experiments, the proposed algorithm outperforms the a priori algorithm in computational time. The simulation results of knowledge acquisition for fault diagnosis also show the validity of I a priori algorithm","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114541032","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1712817
Qingfeng Wang, Jian-Zhong Tang
Dredging operation is characterized by considerably high cost. For manually control dredging process is of low production and poor efficiency, in order to raise production and reduce unit cost, automatically controlled dredging equipment is urgently required. Expert system based production optimization and control system proposed in this paper is an initial attempt to tackle these problems with artificial technology in this area. To cope with the complicated control and optimization task, a multi-layer multi-agent scheme is introduced in the structure of the expert system. For the variety of knowledge obtained and its considerably large amount, design of knowledge presentation methods is an important aspect of this application, several styles of knowledge presentation methods are incorporated in the developed system. Inference mechanism of the expert system is also briefly described in this paper. Finally, preliminary test results are presented and compared with judgment of experienced operators
{"title":"Research on expert system for dredging producation optimization","authors":"Qingfeng Wang, Jian-Zhong Tang","doi":"10.1109/WCICA.2006.1712817","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1712817","url":null,"abstract":"Dredging operation is characterized by considerably high cost. For manually control dredging process is of low production and poor efficiency, in order to raise production and reduce unit cost, automatically controlled dredging equipment is urgently required. Expert system based production optimization and control system proposed in this paper is an initial attempt to tackle these problems with artificial technology in this area. To cope with the complicated control and optimization task, a multi-layer multi-agent scheme is introduced in the structure of the expert system. For the variety of knowledge obtained and its considerably large amount, design of knowledge presentation methods is an important aspect of this application, several styles of knowledge presentation methods are incorporated in the developed system. Inference mechanism of the expert system is also briefly described in this paper. Finally, preliminary test results are presented and compared with judgment of experienced operators","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114632525","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1713590
Li Zhang, Jinyan Song, Ji-Yan Zou
A new type storage energy element, hybrid super-capacitor, is introduced, which can be used for pulse source system. The hybrid super-capacitor is composed of anodes of electrolytic capacitor and cathodes of electrochemical capacitor, so it has the characteristics of high working voltage and low inner resistance. When the hybrid super-capacitors are connected in proper series and parallel to form storage energy device, the device has the perfect performances of high energy density and fast charging and discharging, and can meet the needs of pulse power technology. A power source was designed for electric vehicle, which is based on the hybrid super-capacitors and batteries in parallel connection. The simulation and experiment results show that it can export high peak power and peak current, achieve the optimal matching of output energy, attain the best ratio of performance and price
{"title":"Performance Investigations on the Power Source of Electric Vehicle Based on Hybrid Super-capacitors","authors":"Li Zhang, Jinyan Song, Ji-Yan Zou","doi":"10.1109/WCICA.2006.1713590","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1713590","url":null,"abstract":"A new type storage energy element, hybrid super-capacitor, is introduced, which can be used for pulse source system. The hybrid super-capacitor is composed of anodes of electrolytic capacitor and cathodes of electrochemical capacitor, so it has the characteristics of high working voltage and low inner resistance. When the hybrid super-capacitors are connected in proper series and parallel to form storage energy device, the device has the perfect performances of high energy density and fast charging and discharging, and can meet the needs of pulse power technology. A power source was designed for electric vehicle, which is based on the hybrid super-capacitors and batteries in parallel connection. The simulation and experiment results show that it can export high peak power and peak current, achieve the optimal matching of output energy, attain the best ratio of performance and price","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116299910","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 : 2006-10-23DOI: 10.1109/WCICA.2006.1713552
C. Xia, Zi-Ying Chen, M. Xue
The switched reluctance motor drive (SRD) has obtained great attention as an AC stepless speed control system due to its large regulating scope, low cost and ruggedness. However, its strong nonlinearity and multivariable characteristic make it difficult to control. To solve the problem, this paper presents an approach of adaptive PWM speed control for switched reluctance motors (SRM) based on RBF neural network. This method builds up a speed controller based on RBF neural network which has powerful approximating ability and fast convergence property. The controller is trained off-line in advance, and then with the motor's operation, the on-line training of it makes its parameters vary with the environment in order to improve the control performance. In addition, another RBF network is constructed to offer gradient parameters, which is needed by the on-line training, via on-line identification. The results of experiments prove that the approach has lots of advantages in response speed, control accuracy and adaptability
{"title":"Adaptive PWM Speed Control for Switched Reluctance Motors Based on RBF Neural Network","authors":"C. Xia, Zi-Ying Chen, M. Xue","doi":"10.1109/WCICA.2006.1713552","DOIUrl":"https://doi.org/10.1109/WCICA.2006.1713552","url":null,"abstract":"The switched reluctance motor drive (SRD) has obtained great attention as an AC stepless speed control system due to its large regulating scope, low cost and ruggedness. However, its strong nonlinearity and multivariable characteristic make it difficult to control. To solve the problem, this paper presents an approach of adaptive PWM speed control for switched reluctance motors (SRM) based on RBF neural network. This method builds up a speed controller based on RBF neural network which has powerful approximating ability and fast convergence property. The controller is trained off-line in advance, and then with the motor's operation, the on-line training of it makes its parameters vary with the environment in order to improve the control performance. In addition, another RBF network is constructed to offer gradient parameters, which is needed by the on-line training, via on-line identification. The results of experiments prove that the approach has lots of advantages in response speed, control accuracy and adaptability","PeriodicalId":375135,"journal":{"name":"2006 6th World Congress on Intelligent Control and Automation","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116314443","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：