Pub Date : 2017-05-01DOI: 10.1109/CCDC.2017.7979177
Qu Xing-yu, Zeng Peng, Fu Dong-dong, Xu Chengcheng
At present, most fault diagnosis for grinding system is based on artificial judgments, which is inefficient, low accurate, high cost and easy to cause casualties. The traditional neural network has an unsatisfying performance to predict on high dimensional dataset, and is hard to extract crucial features, which brings about terrible classification results. To solve the above problems, the paper present a deep learning based on autoencoder to realize the intelligent diagnosis for grinding system. The algorithm applies autoencoder to extract features from fault dataset, and transit the non-linearized features to Softmax classification to recognize the fault category. This paper compares autoencoder-based deep learning networks and the traditional BP neural networks in experiments, and it is concluded that the autoencoder-based deep learning outperforms BP networks in the unbalanced classification. The classification precision is up to 92.4% by using the proposed method.
{"title":"Autoencoder-based fault diagnosis for grinding system","authors":"Qu Xing-yu, Zeng Peng, Fu Dong-dong, Xu Chengcheng","doi":"10.1109/CCDC.2017.7979177","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979177","url":null,"abstract":"At present, most fault diagnosis for grinding system is based on artificial judgments, which is inefficient, low accurate, high cost and easy to cause casualties. The traditional neural network has an unsatisfying performance to predict on high dimensional dataset, and is hard to extract crucial features, which brings about terrible classification results. To solve the above problems, the paper present a deep learning based on autoencoder to realize the intelligent diagnosis for grinding system. The algorithm applies autoencoder to extract features from fault dataset, and transit the non-linearized features to Softmax classification to recognize the fault category. This paper compares autoencoder-based deep learning networks and the traditional BP neural networks in experiments, and it is concluded that the autoencoder-based deep learning outperforms BP networks in the unbalanced classification. The classification precision is up to 92.4% by using the proposed method.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"21 1","pages":"3867-3872"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78704409","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979418
Xiao Qian, Xiao Yu, Chen Fa
In view of the traditional transportation passenger flow statistics methods are rough statistics on passenger flow, and it can't get statistical data of passenger flow in a certain period of time immediately, so the passenger flow counting method of subway video based on image processing is proposed. Firstly take the characters obtained by the background subtraction method in the video as the statistical target, and then extract of the human figure outline and do the morphology processing, finally use the method of the connected domain to achieve the statistical effect of the intelligent number. Experimental results show that, the number of statistics is very accurate.
{"title":"The passenger flow counting research of subway video based on image processing","authors":"Xiao Qian, Xiao Yu, Chen Fa","doi":"10.1109/CCDC.2017.7979418","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979418","url":null,"abstract":"In view of the traditional transportation passenger flow statistics methods are rough statistics on passenger flow, and it can't get statistical data of passenger flow in a certain period of time immediately, so the passenger flow counting method of subway video based on image processing is proposed. Firstly take the characters obtained by the background subtraction method in the video as the statistical target, and then extract of the human figure outline and do the morphology processing, finally use the method of the connected domain to achieve the statistical effect of the intelligent number. Experimental results show that, the number of statistics is very accurate.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"153 1","pages":"5195-5198"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78209438","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979155
Zhenning Yu, S. Wong
The growing number of elder people is a huge problem in Macau, China, especially, the elder people who loss living ability. In medical area, the complicating disease, such as press sore is one of the most dangerous reason to cause disabled people death. Therefore, some relative research projects are still developing. This paper address the problem of driving a smart wheelchair with independent active suspension system to follow a desired path. Based on a practical wheelchair, Krama KM5000.2, the suspension was a nonlinear system. The solution consists of a Lyapunov-based trajectory tracking control law and an active force for correcting vehicle running attitude. When the wheelchair is working, active suspension generates an active force to against vehicle attitude error. In detail, the paper demonstrates how Lyapunov based techniques yield a control structure includes i) active force against vehicle attitude error, i) saturation on position error and iii) nonlinear damping disturbance.
{"title":"Adaptive nonlinear control of wheelchair with independent active suspension system","authors":"Zhenning Yu, S. Wong","doi":"10.1109/CCDC.2017.7979155","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979155","url":null,"abstract":"The growing number of elder people is a huge problem in Macau, China, especially, the elder people who loss living ability. In medical area, the complicating disease, such as press sore is one of the most dangerous reason to cause disabled people death. Therefore, some relative research projects are still developing. This paper address the problem of driving a smart wheelchair with independent active suspension system to follow a desired path. Based on a practical wheelchair, Krama KM5000.2, the suspension was a nonlinear system. The solution consists of a Lyapunov-based trajectory tracking control law and an active force for correcting vehicle running attitude. When the wheelchair is working, active suspension generates an active force to against vehicle attitude error. In detail, the paper demonstrates how Lyapunov based techniques yield a control structure includes i) active force against vehicle attitude error, i) saturation on position error and iii) nonlinear damping disturbance.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"64 1","pages":"3741-3746"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78399168","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7978987
Fuzheng Chen, Junguo Lu, Yubin Miao
In this paper, the decentralized H∞ control problem for the fractional order interconnected systems with element-bounded uncertainties is investigated. A sufficient condition for designing the decentralized state feedback controllers, which guarantees that the fractional order closed loop interconnected systems are asymptotically stable and satisfy a prescribed H∞ performance, is derived and transformed into the solvability problem of linear matrix inequalities. Furthermore, the gains of the decentralized state feedback controllers are optimized as low as possible by solving the convex optimization problem with linear matrix inequality constraints. A simulation example is given to demonstrate the validity of the proposed approach.
{"title":"Decentralized robust H∞ controller design for fractional order interconnected systems with element-bounded uncertainties","authors":"Fuzheng Chen, Junguo Lu, Yubin Miao","doi":"10.1109/CCDC.2017.7978987","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7978987","url":null,"abstract":"In this paper, the decentralized H∞ control problem for the fractional order interconnected systems with element-bounded uncertainties is investigated. A sufficient condition for designing the decentralized state feedback controllers, which guarantees that the fractional order closed loop interconnected systems are asymptotically stable and satisfy a prescribed H∞ performance, is derived and transformed into the solvability problem of linear matrix inequalities. Furthermore, the gains of the decentralized state feedback controllers are optimized as low as possible by solving the convex optimization problem with linear matrix inequality constraints. A simulation example is given to demonstrate the validity of the proposed approach.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"35 1","pages":"2790-2795"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78442427","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7978421
Li Linlin, Zhao Xu, Zhujinsheng, Xing Jing, Xing Shuntao
The key factor which restricts the Lithium battery packs using widely is the capacity issue. By analyzing the functional requirements of Lithium battery management system, we will design a battery management system with dynamic equalization to realize maximize of the whole set lithium batteries after charging. This devise can extend the service life of lithium batteries.
{"title":"Research on dynamic equalization for lithium battery management system","authors":"Li Linlin, Zhao Xu, Zhujinsheng, Xing Jing, Xing Shuntao","doi":"10.1109/CCDC.2017.7978421","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7978421","url":null,"abstract":"The key factor which restricts the Lithium battery packs using widely is the capacity issue. By analyzing the functional requirements of Lithium battery management system, we will design a battery management system with dynamic equalization to realize maximize of the whole set lithium batteries after charging. This devise can extend the service life of lithium batteries.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"20 1","pages":"6884-6888"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78443401","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979058
Jie Yu, Tao Shen, Yanjun Li, Yan Zhang
This paper describes a new power flow solution based on graph theory for solving distribution systems. The method proposed to deal with both radial and meshed networks is a kind of forward/backward sweep method, which is used to solve radial networks only. We fully depict the topological characteristic of a radial or meshed structure by a node-branch incidence matrix. Without breaking meshes or loop-analysis like previous studies, our method can directly solve meshed structure by finding the basis of the null space of the incidence matrix. In addition, we also give a convergence analysis by using of the Banach fixed-point theorem.
{"title":"A power flow solution for meshed network by incidence matrix","authors":"Jie Yu, Tao Shen, Yanjun Li, Yan Zhang","doi":"10.1109/CCDC.2017.7979058","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979058","url":null,"abstract":"This paper describes a new power flow solution based on graph theory for solving distribution systems. The method proposed to deal with both radial and meshed networks is a kind of forward/backward sweep method, which is used to solve radial networks only. We fully depict the topological characteristic of a radial or meshed structure by a node-branch incidence matrix. Without breaking meshes or loop-analysis like previous studies, our method can directly solve meshed structure by finding the basis of the null space of the incidence matrix. In addition, we also give a convergence analysis by using of the Banach fixed-point theorem.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"44 1","pages":"3201-3206"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77264038","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}
This paper considers the problem of proportional-integral-derivative (PID) controller design for a closed-loop feedback system with time delay according some desired performance indexes. In this study, the characteristic equation of the closed-loop system is considered as that of a neutral type system with time delay. Besides, it is expected that the step response of the closed-loop systems has no overshoot. To achieve the objective of control, combining with Smith Predictor, we propose a new approach on the PID controller design for a neutral type delay system via dominant eigenvalue assignment. Such a method can make the performance of the system very close to the desired performance indexes for a standard first-order system. A numerical example is given to illustrate the effectiveness of the proposed approach.
{"title":"PID controller tuning for neutral type systems with time delay via dominant eigenvalue assignment","authors":"Honghai Wang, Jianchang Liu, Xia Yu, Shubin Tan, Yu Zhang","doi":"10.1109/CCDC.2017.7978162","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7978162","url":null,"abstract":"This paper considers the problem of proportional-integral-derivative (PID) controller design for a closed-loop feedback system with time delay according some desired performance indexes. In this study, the characteristic equation of the closed-loop system is considered as that of a neutral type system with time delay. Besides, it is expected that the step response of the closed-loop systems has no overshoot. To achieve the objective of control, combining with Smith Predictor, we propose a new approach on the PID controller design for a neutral type delay system via dominant eigenvalue assignment. Such a method can make the performance of the system very close to the desired performance indexes for a standard first-order system. A numerical example is given to illustrate the effectiveness of the proposed approach.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"20 1","pages":"5592-5597"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75034673","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979211
Zhu Meng, P. Feng, Pan Chao, Li Weixing, Gao Qi
In order to ensure the smoothness of joint motion and the accurateness of the target position estimate, B-spline has been widely used in joint trajectory planning for mechanical arms. In this paper, the base functions of the third order, fifth order, and seventh order of uniform B-splines are given. Comparison between piecewise polynomial and B-splines on trajectory planning is presented to show the differences in computational complexity. The trajectories planned in using three different order B-splines are shown and discussed. Detailed analysis of the planning with virtual points is described in this paper.
{"title":"Research on mechanical arms trajectory-planning using different order B-splines","authors":"Zhu Meng, P. Feng, Pan Chao, Li Weixing, Gao Qi","doi":"10.1109/CCDC.2017.7979211","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979211","url":null,"abstract":"In order to ensure the smoothness of joint motion and the accurateness of the target position estimate, B-spline has been widely used in joint trajectory planning for mechanical arms. In this paper, the base functions of the third order, fifth order, and seventh order of uniform B-splines are given. Comparison between piecewise polynomial and B-splines on trajectory planning is presented to show the differences in computational complexity. The trajectories planned in using three different order B-splines are shown and discussed. Detailed analysis of the planning with virtual points is described in this paper.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"80 1","pages":"4061-4066"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72652573","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979080
Liu Fuchun, C. Yifeng, Li Yunze
LIDAR and odometer are used as the main sensors in this paper, with the two-wheeled self-balancing robot as the research and experiment platform, this topic has researched the way to SLAM when the robot is in unfamiliar environment with uncertain position and orientation. On the issue of setting the dynamic threshold value to zone the LIDAR scanning points in the process of constructing the geometry map, with the consideration of the character of RPLIDAR which is used in our research, this paper has analyzed and proposed the specific dynamic threshold values, which make the zoning of LIDAR scanning points more reasonable. In order to improve the robustness of SLAM, we have used regular particle filter (RPF) as the location algorithm. In order to solve the problem of unable to add auxiliary information under the traditional MCL framework, we have taken full use of the high accuracy character of the geometry matching and locating, and have used the result of it to improve the importance density function of RPF. Based on the idea of Rao-Blackwellization, the improved RBPF-SLAM has been proposed. The validity and feasibility of the improved RBPF-SLAM have been proved with simulations and experiments.
{"title":"Research on indoor robot SLAM of RBPF improved with geometrical characteristic localization","authors":"Liu Fuchun, C. Yifeng, Li Yunze","doi":"10.1109/CCDC.2017.7979080","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979080","url":null,"abstract":"LIDAR and odometer are used as the main sensors in this paper, with the two-wheeled self-balancing robot as the research and experiment platform, this topic has researched the way to SLAM when the robot is in unfamiliar environment with uncertain position and orientation. On the issue of setting the dynamic threshold value to zone the LIDAR scanning points in the process of constructing the geometry map, with the consideration of the character of RPLIDAR which is used in our research, this paper has analyzed and proposed the specific dynamic threshold values, which make the zoning of LIDAR scanning points more reasonable. In order to improve the robustness of SLAM, we have used regular particle filter (RPF) as the location algorithm. In order to solve the problem of unable to add auxiliary information under the traditional MCL framework, we have taken full use of the high accuracy character of the geometry matching and locating, and have used the result of it to improve the importance density function of RPF. Based on the idea of Rao-Blackwellization, the improved RBPF-SLAM has been proposed. The validity and feasibility of the improved RBPF-SLAM have been proved with simulations and experiments.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"40 1","pages":"3325-3330"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74963443","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 : 2017-05-01DOI: 10.1109/CCDC.2017.7979131
Zeng De-liang, Deng Zhi-guang, Jian Yifan, Sun Yue
AVS-P10 is the first national standard for mobile audio codec with completely independent intellectual property rights. In view of the current situation of the explosive growth of network audio data, According to the principle of AVS-P10 coding and based on AVS-P10 core encoder to make the algorithm compile. And the algorithm is optimized by the self search cycle optimization scheme. Finally, the third National Graduate smart city technology and creative design contest organized by the audio data to do the experiment. And the experimental results show that the algorithm has achieved some results. At the same time, the compression ratio of the optimized algorithm increases with the same code rate.
{"title":"Audio data compression based on AVS-P10","authors":"Zeng De-liang, Deng Zhi-guang, Jian Yifan, Sun Yue","doi":"10.1109/CCDC.2017.7979131","DOIUrl":"https://doi.org/10.1109/CCDC.2017.7979131","url":null,"abstract":"AVS-P10 is the first national standard for mobile audio codec with completely independent intellectual property rights. In view of the current situation of the explosive growth of network audio data, According to the principle of AVS-P10 coding and based on AVS-P10 core encoder to make the algorithm compile. And the algorithm is optimized by the self search cycle optimization scheme. Finally, the third National Graduate smart city technology and creative design contest organized by the audio data to do the experiment. And the experimental results show that the algorithm has achieved some results. At the same time, the compression ratio of the optimized algorithm increases with the same code rate.","PeriodicalId":6588,"journal":{"name":"2017 29th Chinese Control And Decision Conference (CCDC)","volume":"44 1","pages":"3608-3612"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77380456","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：