Pub Date : 2004-06-21DOI: 10.1109/ICIA.2004.1373308
Xueliang Zhang, S. Wen, Meixian Wu
In this paper, firstly the influencing factors of contact stiffness of machine joint interfaces and their description method are introduced and discussed. Then a weight smoothing BP algorithm is introduced briefly. It has better generalization performance. Basing on this algorithm, the intelligent modeling method of contact stiffness of machine joint interfaces under multijoint conditions is proposed for the first time. This method is proved feasible by the given modeling example.
{"title":"Intelligent modeling of contact stiffness of machine joint interfaces","authors":"Xueliang Zhang, S. Wen, Meixian Wu","doi":"10.1109/ICIA.2004.1373308","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373308","url":null,"abstract":"In this paper, firstly the influencing factors of contact stiffness of machine joint interfaces and their description method are introduced and discussed. Then a weight smoothing BP algorithm is introduced briefly. It has better generalization performance. Basing on this algorithm, the intelligent modeling method of contact stiffness of machine joint interfaces under multijoint conditions is proposed for the first time. This method is proved feasible by the given modeling example.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115546643","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373411
Runjing Zhou, Yupei Du
We analyze the transmitting process of ultrasonic in two types of medium that are made of different material in detailed, present several general methods for echo analysis. Aiming at the particularity of the ultrasonic echo in the sheet metal (thickness is from 1 mm to 10 mm) we propose concrete design scheme and method for quantitative measurement.
{"title":"Felting quality recognition of interface of metal and nonmetal material utilizing ultrasonic method","authors":"Runjing Zhou, Yupei Du","doi":"10.1109/ICIA.2004.1373411","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373411","url":null,"abstract":"We analyze the transmitting process of ultrasonic in two types of medium that are made of different material in detailed, present several general methods for echo analysis. Aiming at the particularity of the ultrasonic echo in the sheet metal (thickness is from 1 mm to 10 mm) we propose concrete design scheme and method for quantitative measurement.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121156511","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373416
Wushan Cheng, M. Fei
This paper presents the genetic-neural network for sinter's burning through point since BTP control is the most important, which is tightly coupled with sinter ore quality. In offline, advanced genetic algorithm (GA) is used to optimize the original connection weights and thresholds, and during online, hybrid neural network (HNN) inherited from the principle of backpropagation is used to train the map parameters and improve the system precision in each sampling period. The results obtained from the actual process demonstrate that the performance and capability of the proposed system are superior.
{"title":"A building of the genetic-neural network for sinter's burning through point","authors":"Wushan Cheng, M. Fei","doi":"10.1109/ICIA.2004.1373416","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373416","url":null,"abstract":"This paper presents the genetic-neural network for sinter's burning through point since BTP control is the most important, which is tightly coupled with sinter ore quality. In offline, advanced genetic algorithm (GA) is used to optimize the original connection weights and thresholds, and during online, hybrid neural network (HNN) inherited from the principle of backpropagation is used to train the map parameters and improve the system precision in each sampling period. The results obtained from the actual process demonstrate that the performance and capability of the proposed system are superior.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123789792","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373309
W. Tao
In this paper, a kind of fuzzy neural network based on hybrid genetic algorithms is proposed. Hybrid genetic algorithm is presented to train the fuzzy neural network. The hybrid genetic algorithm improved normal genetic algorithm. The BP algorithm is added to genetic algorithm. In particularly, the global convergent characteristic of the genetic algorithm is used to find the possible universal optimum, and the great feature of the BP algorithm, that is, error descend in the direction of grads, is used to fast search about the optimum. Thus, the fast learning capability and an accurate approximation ability are obtained. The fuzzy neural network is used to the control problem of truck backer-upper. The simulation results show that it achieves better control effect.
{"title":"Fuzzy neural network control of truck backer-upper using hybrid genetic algorithms","authors":"W. Tao","doi":"10.1109/ICIA.2004.1373309","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373309","url":null,"abstract":"In this paper, a kind of fuzzy neural network based on hybrid genetic algorithms is proposed. Hybrid genetic algorithm is presented to train the fuzzy neural network. The hybrid genetic algorithm improved normal genetic algorithm. The BP algorithm is added to genetic algorithm. In particularly, the global convergent characteristic of the genetic algorithm is used to find the possible universal optimum, and the great feature of the BP algorithm, that is, error descend in the direction of grads, is used to fast search about the optimum. Thus, the fast learning capability and an accurate approximation ability are obtained. The fuzzy neural network is used to the control problem of truck backer-upper. The simulation results show that it achieves better control effect.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124167263","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373419
Xiujun Wang, Y. Ge, B. Xiao, Yong Yu
Considering the deficiency of present robotic force control algorithm, we introduce artificial intelligent method in this paper. We attempt to combine fuzzy control theory with impedance control strategy, and attempt to control the external force on the robotic end-effector by this quomodo. The structure of the system is presented and the force controller is designed. Finally we show the results based on the practical experiments. It is a more effective strategy to solve the robotic force control problem.
{"title":"Application study of robotic control system based on force information","authors":"Xiujun Wang, Y. Ge, B. Xiao, Yong Yu","doi":"10.1109/ICIA.2004.1373419","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373419","url":null,"abstract":"Considering the deficiency of present robotic force control algorithm, we introduce artificial intelligent method in this paper. We attempt to combine fuzzy control theory with impedance control strategy, and attempt to control the external force on the robotic end-effector by this quomodo. The structure of the system is presented and the force controller is designed. Finally we show the results based on the practical experiments. It is a more effective strategy to solve the robotic force control problem.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130702965","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373371
Jinmao Wei, Wei-Guo Yi, Ming-Yang Wang, Shuqin Wang
It is comprehensible that to find as much interesting knowledge as possible is the initial and main aim to mine data, no matter which pattern (parallel or sequential) is utilized in data mining, though parallelism is practically important as well. We present a principle, called DFDP, for partitioning large dataset-the first step for parallelization. Data subsets after partitioning are treated tendentiously for possible parallel or distributed processing. One feasible logical structure for parallel processing is recommended in the paper. Also experimental comparisons are reported in the paper, which shows that weighted data mining will find more interesting rules from data.
{"title":"Data feature oriented data partition and weighted data mining","authors":"Jinmao Wei, Wei-Guo Yi, Ming-Yang Wang, Shuqin Wang","doi":"10.1109/ICIA.2004.1373371","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373371","url":null,"abstract":"It is comprehensible that to find as much interesting knowledge as possible is the initial and main aim to mine data, no matter which pattern (parallel or sequential) is utilized in data mining, though parallelism is practically important as well. We present a principle, called DFDP, for partitioning large dataset-the first step for parallelization. Data subsets after partitioning are treated tendentiously for possible parallel or distributed processing. One feasible logical structure for parallel processing is recommended in the paper. Also experimental comparisons are reported in the paper, which shows that weighted data mining will find more interesting rules from data.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124408945","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373338
Rui Qiao, Bo Chen
This paper puts forward a method of bringing neural network to bear intrusion detection. When the average error can't decrease any longer, the hereditary algorithm will be used to continuatively train the network in the interest of acquiring optimized join parameter. The network structure and network joining parameter will evolve at the same time by the neural network and hereditary algorithm. The convergence effect is good and the adaptivity is strong, suitable for real-time processing.
{"title":"Intrusion detection method research based on optimized self-buildup clustering neural network","authors":"Rui Qiao, Bo Chen","doi":"10.1109/ICIA.2004.1373338","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373338","url":null,"abstract":"This paper puts forward a method of bringing neural network to bear intrusion detection. When the average error can't decrease any longer, the hereditary algorithm will be used to continuatively train the network in the interest of acquiring optimized join parameter. The network structure and network joining parameter will evolve at the same time by the neural network and hereditary algorithm. The convergence effect is good and the adaptivity is strong, suitable for real-time processing.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128449850","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373357
Deyong Chen, D. Cui
Operation and measurement of an electro-thermally excited resonant pressure sensor are described. An open-loop measuring system with lock-in amplification technology is established to assess the characteristics of the beam resonator and in order to solve the problem of detecting dynamic relationships between various sensors' output frequency and their applied conditions, a close-loop data-acquisition system is developed and the gage factor, temperature sensitivity and frequency stability are measured with the system.
{"title":"Measurement of resonant microbeam pressure sensors","authors":"Deyong Chen, D. Cui","doi":"10.1109/ICIA.2004.1373357","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373357","url":null,"abstract":"Operation and measurement of an electro-thermally excited resonant pressure sensor are described. An open-loop measuring system with lock-in amplification technology is established to assess the characteristics of the beam resonator and in order to solve the problem of detecting dynamic relationships between various sensors' output frequency and their applied conditions, a close-loop data-acquisition system is developed and the gage factor, temperature sensitivity and frequency stability are measured with the system.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114081577","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373365
X. Dai, Dongchuan Yu, Yuhan Ding, Wancheng Wang
This paper presents a novel soft-sensing approach based on artificial neural network (ANN) inversion to estimate some crucial biochemical parameters in erythromycin fermentation, which usually can not be directly measurable by commercial sensors. Such direct-unmeasurable variables as mycelia concentration, sugar concentration and chemical potency, can be derived from other direct-measurable variables such as dissolved oxygen concentration, pH, and volume by using the proposed ANN inversion. The ANN inversion consists of a static ANN and several differentiators and acts as a soft-sensor. Experimental results show that the soft-sensing values are almost identical with the actual ones and the proposed method would be helpful for the real-time control of the biochemical fermentation.
{"title":"ANN inversion based soft-sensing of biochemical parameters in erythromycin fermentation","authors":"X. Dai, Dongchuan Yu, Yuhan Ding, Wancheng Wang","doi":"10.1109/ICIA.2004.1373365","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373365","url":null,"abstract":"This paper presents a novel soft-sensing approach based on artificial neural network (ANN) inversion to estimate some crucial biochemical parameters in erythromycin fermentation, which usually can not be directly measurable by commercial sensors. Such direct-unmeasurable variables as mycelia concentration, sugar concentration and chemical potency, can be derived from other direct-measurable variables such as dissolved oxygen concentration, pH, and volume by using the proposed ANN inversion. The ANN inversion consists of a static ANN and several differentiators and acts as a soft-sensor. Experimental results show that the soft-sensing values are almost identical with the actual ones and the proposed method would be helpful for the real-time control of the biochemical fermentation.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131401817","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373405
Xiaojun Zhao, Qiang Huang, Peng Du, Dongming Wen, Kejie Li
The captured data must be adapted for the humanoid because its kinematics and dynamic differ from those of the human actor. The kinematics constraints such as ground contact conditions are crucial for humanoid locomotion. Furthermore, it is desirable that the humanoid motion have of high similarity with those of the human actor. In this paper, first the similarity function of the humanoid motion is proposed. Then, the kinematics constrains including ground contact conditions are formulated, and the algorithm to derive the humanoid motion with a high similarity and satisfying kinematics constraints is present. Finally, the effectiveness is confirmed by the experiment of Chinese Kongfu "Taiji" using our developed 33 DOF humanoid robot.
{"title":"Humanoid kinematics mapping and similarity evaluation based on human motion capture","authors":"Xiaojun Zhao, Qiang Huang, Peng Du, Dongming Wen, Kejie Li","doi":"10.1109/ICIA.2004.1373405","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373405","url":null,"abstract":"The captured data must be adapted for the humanoid because its kinematics and dynamic differ from those of the human actor. The kinematics constraints such as ground contact conditions are crucial for humanoid locomotion. Furthermore, it is desirable that the humanoid motion have of high similarity with those of the human actor. In this paper, first the similarity function of the humanoid motion is proposed. Then, the kinematics constrains including ground contact conditions are formulated, and the algorithm to derive the humanoid motion with a high similarity and satisfying kinematics constraints is present. Finally, the effectiveness is confirmed by the experiment of Chinese Kongfu \"Taiji\" using our developed 33 DOF humanoid robot.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133101723","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：