Pub Date : 1998-08-31DOI: 10.1109/IECON.1998.723931
O. Kaynak, I. Rudas
This tutorial discusses how some "intelligence" can be incorporated in sliding mode controllers by the use of computational intelligence methodologies in order to alleviate the well known problems met in practical implementations of sliding mode controllers. The paper presents an overview of the research and applications reported in the literature in this respect. Parallels are drawn between fuzzy control and VSS (variable structure systems) with a sliding mode.
{"title":"The fusion of computational intelligence methodologies in sliding mode control","authors":"O. Kaynak, I. Rudas","doi":"10.1109/IECON.1998.723931","DOIUrl":"https://doi.org/10.1109/IECON.1998.723931","url":null,"abstract":"This tutorial discusses how some \"intelligence\" can be incorporated in sliding mode controllers by the use of computational intelligence methodologies in order to alleviate the well known problems met in practical implementations of sliding mode controllers. The paper presents an overview of the research and applications reported in the literature in this respect. Parallels are drawn between fuzzy control and VSS (variable structure systems) with a sliding mode.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"01 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127205333","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 : 1998-08-31DOI: 10.1109/IECON.1998.723941
Y. Kikuchi, H. Murakoshi, N. Funakubo
We propose an execution system for a logic programming language using neural networks. We transform the style like logic programming language into a Hopfield-type neural network and attempt to execute the logic programming language using the ability of the neural network as an optimization machine. Although we have proposed such a system, previous works have not implemented "list processing". Therefore we propose an improved transformation algorithm for "list processing". The performance of the new transformation algorithm is evaluated by comparing it with a previous algorithm, without handling list structure, for a logic programming language. The result shows that the proposed algorithm generates an especially smaller network scale than a conventional algorithm, and reduces iteration times.
{"title":"An execution system of logic programming language using neural networks-an improvement of the transformation algorithm","authors":"Y. Kikuchi, H. Murakoshi, N. Funakubo","doi":"10.1109/IECON.1998.723941","DOIUrl":"https://doi.org/10.1109/IECON.1998.723941","url":null,"abstract":"We propose an execution system for a logic programming language using neural networks. We transform the style like logic programming language into a Hopfield-type neural network and attempt to execute the logic programming language using the ability of the neural network as an optimization machine. Although we have proposed such a system, previous works have not implemented \"list processing\". Therefore we propose an improved transformation algorithm for \"list processing\". The performance of the new transformation algorithm is evaluated by comparing it with a previous algorithm, without handling list structure, for a logic programming language. The result shows that the proposed algorithm generates an especially smaller network scale than a conventional algorithm, and reduces iteration times.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127267430","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 : 1998-08-31DOI: 10.1109/IECON.1998.724232
Shyh-Shing Perng, Y. Lai, Chang-Huan Liu
A sensorless vector controller for induction motor drives based on the theory of model reference adaptive system (MRAS) has been presented in previous papers, which identifies synchronous speed of motor drives using the error of reactive power as the reference input of adaptation mechanism. Moreover, as shown by the authors in a previous paper (see Proc. European Power Electronics Conf., vol.4, p.480-5, 1997) the MRAS-based synchronous speed identification scheme requires neither rotor time constant nor stator resistance in both adjustable and reference models. However, rotor resistance is still used for the estimation of shaft speed. In this paper, a stator resistance identification scheme based upon MRAS using the error of active power as the reference input of adaptation mechanism and details about the stability of the identification scheme is presented. Moreover, the rotor resistance is adjusted using the variation rate of stator resistance. Simulation and experimental results are presented to confirm the theoretical analysis.
基于模型参考自适应系统(MRAS)理论，提出了一种异步电机驱动的无传感器矢量控制器，该控制器以无功功率误差作为自适应机制的参考输入来识别电机驱动的同步速度。此外，正如作者在之前的论文中所示(见Proc. European Power Electronics Conf.， vol.4, p.480- 5,1997)，基于mras的同步速度识别方案在可调和参考模型中既不需要转子时间常数，也不需要定子电阻。然而，转子电阻仍然用于估计轴转速。本文提出了一种基于MRAS的定子电阻辨识方案，该方案以有功功率误差作为自适应机制的参考输入，并详细介绍了辨识方案的稳定性。利用定子电阻的变化率来调节转子电阻。仿真和实验结果验证了理论分析的正确性。
{"title":"Sensorless vector controller for induction motor drives with parameter identification","authors":"Shyh-Shing Perng, Y. Lai, Chang-Huan Liu","doi":"10.1109/IECON.1998.724232","DOIUrl":"https://doi.org/10.1109/IECON.1998.724232","url":null,"abstract":"A sensorless vector controller for induction motor drives based on the theory of model reference adaptive system (MRAS) has been presented in previous papers, which identifies synchronous speed of motor drives using the error of reactive power as the reference input of adaptation mechanism. Moreover, as shown by the authors in a previous paper (see Proc. European Power Electronics Conf., vol.4, p.480-5, 1997) the MRAS-based synchronous speed identification scheme requires neither rotor time constant nor stator resistance in both adjustable and reference models. However, rotor resistance is still used for the estimation of shaft speed. In this paper, a stator resistance identification scheme based upon MRAS using the error of active power as the reference input of adaptation mechanism and details about the stability of the identification scheme is presented. Moreover, the rotor resistance is adjusted using the variation rate of stator resistance. Simulation and experimental results are presented to confirm the theoretical analysis.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127345817","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 : 1998-08-31DOI: 10.1109/IECON.1998.723946
Wang Limei, Wang Yan, Guo Qingding, Luo Ruifu
This paper describes a DSP-based neural network controller of a high-performance brushless DC servomotor system. It has a multi-layer feedforward structure and adopts a DSP (TMS320C30) as its operation element. Its learning scheme and design method are discussed. Simulation and experiment results are presented and the performance of such neural network controllers is studied.
{"title":"Neural network based brushless DC motor servo system","authors":"Wang Limei, Wang Yan, Guo Qingding, Luo Ruifu","doi":"10.1109/IECON.1998.723946","DOIUrl":"https://doi.org/10.1109/IECON.1998.723946","url":null,"abstract":"This paper describes a DSP-based neural network controller of a high-performance brushless DC servomotor system. It has a multi-layer feedforward structure and adopts a DSP (TMS320C30) as its operation element. Its learning scheme and design method are discussed. Simulation and experiment results are presented and the performance of such neural network controllers is studied.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124778231","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 : 1998-08-31DOI: 10.1109/IECON.1998.724152
P. Hernandez, F. Monterde, J. Burdío, J.R. Garcia
One of the main problems in induction cooking appliances is the relatively high temperature the inductor reaches. Self-heating is not the only issue, the heat transferred from the pot is also a concern, which elevates the inductor temperature beyond 200/spl deg/C. A copper foil coil in the inductor is considered a good solution for this application. This paper deals with how current distributes in this type of coil, and which are the proper foil section dimensions in order to obtain lower power losses (low temperature rise), with minimum volume of copper (low cost).
{"title":"Power loss optimisation of foil coils for induction cooking","authors":"P. Hernandez, F. Monterde, J. Burdío, J.R. Garcia","doi":"10.1109/IECON.1998.724152","DOIUrl":"https://doi.org/10.1109/IECON.1998.724152","url":null,"abstract":"One of the main problems in induction cooking appliances is the relatively high temperature the inductor reaches. Self-heating is not the only issue, the heat transferred from the pot is also a concern, which elevates the inductor temperature beyond 200/spl deg/C. A copper foil coil in the inductor is considered a good solution for this application. This paper deals with how current distributes in this type of coil, and which are the proper foil section dimensions in order to obtain lower power losses (low temperature rise), with minimum volume of copper (low cost).","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124981526","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 : 1998-08-31DOI: 10.1109/IECON.1998.724065
E. Freund, D. Rokossa
This paper presents a new approach to an automatic trajectory generation in multi-joint robot systems. The developed method consists of two parts. During the off-line part a 3D-trajectory-net inside the robot's workspace is generated under consideration of the fixed obstacles of the environment. By testing the robot's motion along this net a set of trajectory segments defining safe TCP locations is computed. The second part, the on-line part, derives a trajectory-graph from these off-line generated segments. Considering the current position of the robot in its environment and the state of possible nonfixed obstacles a sequence of trajectory segments is computed to realize a desired task. By using this method for the generation of necessary trajectories the time for the teach-in programming is drastically reduced.
{"title":"Automatic trajectory generation for multi-joint robot system","authors":"E. Freund, D. Rokossa","doi":"10.1109/IECON.1998.724065","DOIUrl":"https://doi.org/10.1109/IECON.1998.724065","url":null,"abstract":"This paper presents a new approach to an automatic trajectory generation in multi-joint robot systems. The developed method consists of two parts. During the off-line part a 3D-trajectory-net inside the robot's workspace is generated under consideration of the fixed obstacles of the environment. By testing the robot's motion along this net a set of trajectory segments defining safe TCP locations is computed. The second part, the on-line part, derives a trajectory-graph from these off-line generated segments. Considering the current position of the robot in its environment and the state of possible nonfixed obstacles a sequence of trajectory segments is computed to realize a desired task. By using this method for the generation of necessary trajectories the time for the teach-in programming is drastically reduced.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125068504","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 : 1998-08-31DOI: 10.1109/IECON.1998.724108
J. M. Lange, H. Voigt, S. Burkhardt, R. Gobel
An intelligent inspection engine (IIE) for the classification of nonregular shaped objects from images is described and evaluated using real-world data from a waste package sorting application. The entire system is self-organizing. Principal component analysis and additional a priori knowledge on color properties are used for feature extraction. As classifiers, growing neural networks provide robustness and minimize the number of runs for parameter tuning. The authors propose a method to encompass feature extraction and classification within a bootstrap procedure. This method reduces the immense memory requirement for the computation of principal components if the number and size of training images are huge without too much loss of recognition quality.
{"title":"The intelligent inspection engine-a real-time real-world visual classifier system","authors":"J. M. Lange, H. Voigt, S. Burkhardt, R. Gobel","doi":"10.1109/IECON.1998.724108","DOIUrl":"https://doi.org/10.1109/IECON.1998.724108","url":null,"abstract":"An intelligent inspection engine (IIE) for the classification of nonregular shaped objects from images is described and evaluated using real-world data from a waste package sorting application. The entire system is self-organizing. Principal component analysis and additional a priori knowledge on color properties are used for feature extraction. As classifiers, growing neural networks provide robustness and minimize the number of runs for parameter tuning. The authors propose a method to encompass feature extraction and classification within a bootstrap procedure. This method reduces the immense memory requirement for the computation of principal components if the number and size of training images are huge without too much loss of recognition quality.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126835","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 : 1998-08-31DOI: 10.1109/IECON.1998.722847
Jianming Yang, Y. Suematsu, S. Shimizu
In their laboratory, the authors have conducted research into a special super wide angle with high distortion lens (WAHD lens) which is designed to be functionally similar to the human eye. By using this lens, they optically obtain foveated information (distorted image). Color information and neural networks are used to make a computer recognize the traffic marks from the distorted image. This paper describes a color characteristic compensation method for the image obtained by WAHD lens, and a feature generation method based on discrete cosine transformation (DCT). The features are used in backpropagation trained neural networks. They conclude that this approach can be used in robots provided with wide angle vision sensors with high distortion lens to recognize traffic markings effectively.
{"title":"Recognition of traffic marks in the images of WAHD lens by using color information and neural networks","authors":"Jianming Yang, Y. Suematsu, S. Shimizu","doi":"10.1109/IECON.1998.722847","DOIUrl":"https://doi.org/10.1109/IECON.1998.722847","url":null,"abstract":"In their laboratory, the authors have conducted research into a special super wide angle with high distortion lens (WAHD lens) which is designed to be functionally similar to the human eye. By using this lens, they optically obtain foveated information (distorted image). Color information and neural networks are used to make a computer recognize the traffic marks from the distorted image. This paper describes a color characteristic compensation method for the image obtained by WAHD lens, and a feature generation method based on discrete cosine transformation (DCT). The features are used in backpropagation trained neural networks. They conclude that this approach can be used in robots provided with wide angle vision sensors with high distortion lens to recognize traffic markings effectively.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125413920","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 : 1998-08-31DOI: 10.1109/IECON.1998.724157
H. Watanabe, N. Kasa
In a sensorless vector control system of the induction motor, it is difficult to estimate rotor speed accurately in the lower speed region because the dead times of the switching devices in a inverter distort the waveforms of the voltages and currents, and these distorted currents affect on the estimated speed as a fluctuation. The motor torque thus has ripples whose frequency are 1 and 6 times those of the primary frequency. In this paper, the authors propose an accurate speed controller in the lower speed region for a speed sensorless vector control system. In the system, the load torque is estimated by a disturbance observer and in order to extract the ripple of torque, they adopt the wavelet transform technique to the estimated torque. From experimental results obtained using this system, sensorless vector controlled induction motors can be driven accurately in the lower speed region.
{"title":"A torque ripples compensating technique based on disturbance observer with wavelet transform for sensorless induction motor drives","authors":"H. Watanabe, N. Kasa","doi":"10.1109/IECON.1998.724157","DOIUrl":"https://doi.org/10.1109/IECON.1998.724157","url":null,"abstract":"In a sensorless vector control system of the induction motor, it is difficult to estimate rotor speed accurately in the lower speed region because the dead times of the switching devices in a inverter distort the waveforms of the voltages and currents, and these distorted currents affect on the estimated speed as a fluctuation. The motor torque thus has ripples whose frequency are 1 and 6 times those of the primary frequency. In this paper, the authors propose an accurate speed controller in the lower speed region for a speed sensorless vector control system. In the system, the load torque is estimated by a disturbance observer and in order to extract the ripple of torque, they adopt the wavelet transform technique to the estimated torque. From experimental results obtained using this system, sensorless vector controlled induction motors can be driven accurately in the lower speed region.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126608117","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 : 1998-08-31DOI: 10.1109/IECON.1998.724248
K. Furst, Z. Tamasi
Powerful high-bandwidth components with built-in, high-speed processing are available on the market. The currently used techniques to connect such devices to a main-unit which controls the device and processes the data (e.g. an industrial camera with a PC) are no longer satisfactory. In this paper, a new approach of modules is used. These modules consist of nodes which are linked together with a high-speed serial bus to build a functional entity. The multimedia-bus IEEE 1394 is proposed as this bus because it has the properties which are needed for building flexible modules. Finally, the new approach is verified with a prototype system.
{"title":"IDBC: a module-architecture for the integration of distributed high-bandwidth-components","authors":"K. Furst, Z. Tamasi","doi":"10.1109/IECON.1998.724248","DOIUrl":"https://doi.org/10.1109/IECON.1998.724248","url":null,"abstract":"Powerful high-bandwidth components with built-in, high-speed processing are available on the market. The currently used techniques to connect such devices to a main-unit which controls the device and processes the data (e.g. an industrial camera with a PC) are no longer satisfactory. In this paper, a new approach of modules is used. These modules consist of nodes which are linked together with a high-speed serial bus to build a functional entity. The multimedia-bus IEEE 1394 is proposed as this bus because it has the properties which are needed for building flexible modules. Finally, the new approach is verified with a prototype system.","PeriodicalId":377136,"journal":{"name":"IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115534301","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：