Pub Date : 2018-05-18DOI: 10.1109/YAC.2018.8406538
Jinbo Liu, Zhiyi Su, Jinlei Chen
Brushless DC machine (BLDCM) has found wide applications in many fields. How to brake electrically with regeneration capability for BLDCM is a new subject of great concern. This paper compares two emergent hybrid electric braking schemes recently. One is a “plugging+ regenerative” braking scheme, which blends plugging with regenerative braking method. The other is “dynamic+ regenerative” braking scheme, which combines dynamic braking with regenerative braking method. All of the problems involved in these two hybrid braking schemes such as switching laws of inverter, close-loop system implementation and their four-quadrant operation are investigated in detail. Effectiveness and validity of the proposed strategies are justified through simulation. Many important conclusions are drawn.
{"title":"Comparison of two electric braking methods with regenerative capability of brushless DC machine and their four-quadrant operation","authors":"Jinbo Liu, Zhiyi Su, Jinlei Chen","doi":"10.1109/YAC.2018.8406538","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406538","url":null,"abstract":"Brushless DC machine (BLDCM) has found wide applications in many fields. How to brake electrically with regeneration capability for BLDCM is a new subject of great concern. This paper compares two emergent hybrid electric braking schemes recently. One is a “plugging+ regenerative” braking scheme, which blends plugging with regenerative braking method. The other is “dynamic+ regenerative” braking scheme, which combines dynamic braking with regenerative braking method. All of the problems involved in these two hybrid braking schemes such as switching laws of inverter, close-loop system implementation and their four-quadrant operation are investigated in detail. Effectiveness and validity of the proposed strategies are justified through simulation. Many important conclusions are drawn.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134415519","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406346
Yonghao Ma, Zhijia Zhao, Xuejing Lan, Xiuyu He, Wei He
In this paper, we address the vibration control and angle positioning problem of a distributed parameter flexible Timoshenko arm system in the presence of input saturation constraint. The smooth hyperbolic tangent function is adopted to develop boundary controls for regulating the vibration and shear deformation, achieving the angle tracking and restricting the control input in the specified area. The proposed controls are able to make sure that the robotic manipulator is placed in the desired angular. Finally, simulation results are demonstrated for control performance verification.
{"title":"Boundary constrained control of a flexible Timoshenko arm","authors":"Yonghao Ma, Zhijia Zhao, Xuejing Lan, Xiuyu He, Wei He","doi":"10.1109/YAC.2018.8406346","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406346","url":null,"abstract":"In this paper, we address the vibration control and angle positioning problem of a distributed parameter flexible Timoshenko arm system in the presence of input saturation constraint. The smooth hyperbolic tangent function is adopted to develop boundary controls for regulating the vibration and shear deformation, achieving the angle tracking and restricting the control input in the specified area. The proposed controls are able to make sure that the robotic manipulator is placed in the desired angular. Finally, simulation results are demonstrated for control performance verification.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125298331","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}
Sparse auto encoder(SAE) can reduces information loss and extract the meaningful feature by learning the deep structure of complex data. This paper presents a novel SAE based semi-supervised feature learning method for fault diagnosis of batch process which includes two stages, namely, unsupervised pre-training stage and supervised tuning stage. At the unsupervised pre-training stage, denoising SAE(DSAE) is utilized by introducing denoising auto encoder into SAE to improve the robustness of network. At the supervised tuning stage, the pretrained DSAE netwrok is optimized using back propagation algorithm to improve the accuracy of classification. The proposed method is validated on penicillin fermentation simulation experiment and Escherichia coli fermentation experiment. Experimental results show that the proposed approach achieves good fault diagnostic performance and is superirior to the traditional fault diagnosis method.
{"title":"Fault diagnosis of batch process based on denoising sparse auto encoder","authors":"Xuejin Gao, Hao Wang, Huihui Gao, Xichang Wang, Zidong Xu","doi":"10.1109/YAC.2018.8406474","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406474","url":null,"abstract":"Sparse auto encoder(SAE) can reduces information loss and extract the meaningful feature by learning the deep structure of complex data. This paper presents a novel SAE based semi-supervised feature learning method for fault diagnosis of batch process which includes two stages, namely, unsupervised pre-training stage and supervised tuning stage. At the unsupervised pre-training stage, denoising SAE(DSAE) is utilized by introducing denoising auto encoder into SAE to improve the robustness of network. At the supervised tuning stage, the pretrained DSAE netwrok is optimized using back propagation algorithm to improve the accuracy of classification. The proposed method is validated on penicillin fermentation simulation experiment and Escherichia coli fermentation experiment. Experimental results show that the proposed approach achieves good fault diagnostic performance and is superirior to the traditional fault diagnosis method.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"475 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129606080","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406416
Hao Lei, Liang Xu, Boyi Chen, Yuping Lu, Mingmin Sun
This paper deals with the model reduction methods for very flexible aircraft (VFA). Such aircraft is characterized by strong coupling between rigid motion and flexible motion, resulting in a very high order system for controll design. Recently released high-fidelity Vulture model of 707 order is chosen to be a typical example of VFA and is regarded as the reference model. Then three model reduction methods: balanced truncation method, balanced residual method and optimal hankel norm approximation are presented. Finally, numerical simulation is used to illustrate the characteristic of VFA and determine the best method for model reduction of VFA. In addition, the relationship between model error and model order is given. Both frequency domain and time domain analysis verify the reduced model of order 80 using balanced singular perturbation method is sufficient to maintain the accuracy of the full model.
{"title":"Comparison of model reduction methods for very flexible aircraft","authors":"Hao Lei, Liang Xu, Boyi Chen, Yuping Lu, Mingmin Sun","doi":"10.1109/YAC.2018.8406416","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406416","url":null,"abstract":"This paper deals with the model reduction methods for very flexible aircraft (VFA). Such aircraft is characterized by strong coupling between rigid motion and flexible motion, resulting in a very high order system for controll design. Recently released high-fidelity Vulture model of 707 order is chosen to be a typical example of VFA and is regarded as the reference model. Then three model reduction methods: balanced truncation method, balanced residual method and optimal hankel norm approximation are presented. Finally, numerical simulation is used to illustrate the characteristic of VFA and determine the best method for model reduction of VFA. In addition, the relationship between model error and model order is given. Both frequency domain and time domain analysis verify the reduced model of order 80 using balanced singular perturbation method is sufficient to maintain the accuracy of the full model.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125916388","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406498
Jiaxi Lin, Xinde Li, Hong Pan
Object recognition is one of the fundamental issues in the field of computer vision. In traditional methods, invariant features are extracted from segmented targets for recognition. However, there is no common method for segmentation of aircraft targets so far due to the complex backgrounds, illuminations, noise and other practical factors. Therefore, in this paper, we propose a method for aircraft identification in remote sensing images based on HOG and deep learning features. We train two classifiers, one is the SVM classifier based on HOG feature, and the other is a classifier based on deep convolutional neural network VGGNet. First, we use the SVM classifier to identify the aircraft in the picture roughly, then we use the deep learning classifier to exclude misidentified targets. In this way, this coarse to fine framework can significantly improve the speed and accuracy of aircraft recognition in remote sensing images. At the same time, our method has a better generalization capability than the traditional methods. Experimental results demonstrate the robustness of our method.
{"title":"Aircraft recognition in remote sensing images based on deep learning","authors":"Jiaxi Lin, Xinde Li, Hong Pan","doi":"10.1109/YAC.2018.8406498","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406498","url":null,"abstract":"Object recognition is one of the fundamental issues in the field of computer vision. In traditional methods, invariant features are extracted from segmented targets for recognition. However, there is no common method for segmentation of aircraft targets so far due to the complex backgrounds, illuminations, noise and other practical factors. Therefore, in this paper, we propose a method for aircraft identification in remote sensing images based on HOG and deep learning features. We train two classifiers, one is the SVM classifier based on HOG feature, and the other is a classifier based on deep convolutional neural network VGGNet. First, we use the SVM classifier to identify the aircraft in the picture roughly, then we use the deep learning classifier to exclude misidentified targets. In this way, this coarse to fine framework can significantly improve the speed and accuracy of aircraft recognition in remote sensing images. At the same time, our method has a better generalization capability than the traditional methods. Experimental results demonstrate the robustness of our method.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132818476","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406531
Jing Tang, Jun Yu Li, Xiangping Xu
The morphology of glands is the main basis of colon cancer diagnosis and accurate segmentation of glands from histology images is a prerequisite for correct clinical diagnosis. A gland segmentation method based on Segnet is proposed in this paper. First, the Warwick-QU dataset is used and augmented for training Segnet. Second, the network parameters are optimized according to the training results. Finally, the trained Segnet is used to perform segmentation test on both Parts A and B of Warwick-QU. The results show that the presented method achieves segmentation accuracy of 0.882 on Part A and 0.8636 on Part B, and shape similarity 106.6471 on Part A and 102.5729 on Part B, respectively. Compared with the existing methods with respect to the same dataset, our method reaches the highest accuracy on whole.
{"title":"Segnet-based gland segmentation from colon cancer histology images","authors":"Jing Tang, Jun Yu Li, Xiangping Xu","doi":"10.1109/YAC.2018.8406531","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406531","url":null,"abstract":"The morphology of glands is the main basis of colon cancer diagnosis and accurate segmentation of glands from histology images is a prerequisite for correct clinical diagnosis. A gland segmentation method based on Segnet is proposed in this paper. First, the Warwick-QU dataset is used and augmented for training Segnet. Second, the network parameters are optimized according to the training results. Finally, the trained Segnet is used to perform segmentation test on both Parts A and B of Warwick-QU. The results show that the presented method achieves segmentation accuracy of 0.882 on Part A and 0.8636 on Part B, and shape similarity 106.6471 on Part A and 102.5729 on Part B, respectively. Compared with the existing methods with respect to the same dataset, our method reaches the highest accuracy on whole.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"403 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133540352","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406349
Shizhou Fu, Shaosheng Zhou
This paper is concerned with the tracking control problem for the closed single spin-1/2 quantum ensembles. Based on the Liouville-von Neumann equation, mathematical model of dynamics for single spin-1/2 quantum ensembles are formulated as a bilinear form with states evolving on Bloch sphere. An associated matrix Lie group equation describing transfers from the initial state being an identity matrix is naturally introduced. The tracking problem for the system in question is transformed to a stabilization problem such that the control techniques are able to be used. In order to deal with the tracking problem, the Lyapunov-based feedback design method is employed to obtain the control such that the dynamics of system can converge to the reference trajectory.
{"title":"Tracking control of single spin-1/2 quantum ensembles","authors":"Shizhou Fu, Shaosheng Zhou","doi":"10.1109/YAC.2018.8406349","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406349","url":null,"abstract":"This paper is concerned with the tracking control problem for the closed single spin-1/2 quantum ensembles. Based on the Liouville-von Neumann equation, mathematical model of dynamics for single spin-1/2 quantum ensembles are formulated as a bilinear form with states evolving on Bloch sphere. An associated matrix Lie group equation describing transfers from the initial state being an identity matrix is naturally introduced. The tracking problem for the system in question is transformed to a stabilization problem such that the control techniques are able to be used. In order to deal with the tracking problem, the Lyapunov-based feedback design method is employed to obtain the control such that the dynamics of system can converge to the reference trajectory.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133627407","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406367
Shi Li, Z. Xiang
This paper considers the problem of adaptive output feedback prescribed performance control for a class of switched nonlinear systems with time-varying delays. The radial basis function neural networks are employed to approximate the unknown nonlinear functions. In order to estimate the unmeasured system states, an observer is designed. It is shown that all signals of the closed-loop system are bounded and the tracking error satisfies the prescribed performance. Finally, an example is presented to demonstrate the effectiveness of the proposed method.
{"title":"Adaptive neural network prescribed performance control of switched nonlinear time-varying delay systems","authors":"Shi Li, Z. Xiang","doi":"10.1109/YAC.2018.8406367","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406367","url":null,"abstract":"This paper considers the problem of adaptive output feedback prescribed performance control for a class of switched nonlinear systems with time-varying delays. The radial basis function neural networks are employed to approximate the unknown nonlinear functions. In order to estimate the unmeasured system states, an observer is designed. It is shown that all signals of the closed-loop system are bounded and the tracking error satisfies the prescribed performance. Finally, an example is presented to demonstrate the effectiveness of the proposed method.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133679052","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}
The outputs of adjacent wind farms have some correlation characteristics because of similar resource conditions, which has certain influences on transmission network expansion planning. In this paper, the influences of multi-wind power output correlations on transmission network expansion planning are considered. Firstly, the correlations between the outputs of adjacent wind farms are studied by Copula theory, and the method of generating wind farm samples with correlation is presented. Secondly, a transmission network expansion planning model is constructed based on the minimum cost method. In this model, Monte Carlo simulation technology is utilized to analyze uncertain characteristics of power flows resulted from multi-wind farms that are integrated into electric power grids simultaneously. At last, the simulation results based on the improved Garver 6 system verify the feasibility and rationality of the proposed model and algorithm. The results also show that the correlations of wind power outputs among multi-wind farm have a significant effect on the transmission network planning results, which should be taken into account in the planning.
{"title":"Transmission network expansion planning considering multi-wind power output correlations","authors":"Shuxiu Cao, Hui Zhou, Xinsong Zhang, Juping Gu, Liang Hua, Jiale Wang","doi":"10.1109/YAC.2018.8406482","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406482","url":null,"abstract":"The outputs of adjacent wind farms have some correlation characteristics because of similar resource conditions, which has certain influences on transmission network expansion planning. In this paper, the influences of multi-wind power output correlations on transmission network expansion planning are considered. Firstly, the correlations between the outputs of adjacent wind farms are studied by Copula theory, and the method of generating wind farm samples with correlation is presented. Secondly, a transmission network expansion planning model is constructed based on the minimum cost method. In this model, Monte Carlo simulation technology is utilized to analyze uncertain characteristics of power flows resulted from multi-wind farms that are integrated into electric power grids simultaneously. At last, the simulation results based on the improved Garver 6 system verify the feasibility and rationality of the proposed model and algorithm. The results also show that the correlations of wind power outputs among multi-wind farm have a significant effect on the transmission network planning results, which should be taken into account in the planning.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122988677","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 : 2018-05-18DOI: 10.1109/YAC.2018.8406523
N. Xie, Xinle Li, Yao Yu
Position estimation based on vision system is essential for a UAV in the GPS-deny situation to realize the position control. However, in the practice, the hardware and software are not ideal for the UAV to carry when flying. Thus, this study is aiming at the problem of position estimation and control for a quadrotor UAV based on vision. Firstly, a position estimation algorithm based on vision is proposed, in which optical flow is used combining with FAST corner detection to ensure the real-time performance of the estimation in condition with limited loader. Meanwhile, a robust controller with nonlinear compensating input has been designed in this paper to deal with the position control for the quadrotor. A simulation is presented in this paper to verify the performance of the controller. Moreover, an experiment is also utilized in this paper to show that the method is practical and with high performance.
{"title":"A position estimation and control system for the quadrotor in GPS-deny situation based on FAST detection and optical flow","authors":"N. Xie, Xinle Li, Yao Yu","doi":"10.1109/YAC.2018.8406523","DOIUrl":"https://doi.org/10.1109/YAC.2018.8406523","url":null,"abstract":"Position estimation based on vision system is essential for a UAV in the GPS-deny situation to realize the position control. However, in the practice, the hardware and software are not ideal for the UAV to carry when flying. Thus, this study is aiming at the problem of position estimation and control for a quadrotor UAV based on vision. Firstly, a position estimation algorithm based on vision is proposed, in which optical flow is used combining with FAST corner detection to ensure the real-time performance of the estimation in condition with limited loader. Meanwhile, a robust controller with nonlinear compensating input has been designed in this paper to deal with the position control for the quadrotor. A simulation is presented in this paper to verify the performance of the controller. Moreover, an experiment is also utilized in this paper to show that the method is practical and with high performance.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"269 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122200504","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：