Pub Date : 2017-05-01DOI: 10.1109/DDCLS.2017.8068113
Guotao Zhuang, Chunliang Zhao, X. Yue, Zongjie Du, Shulin Sui
It is important to cut down the erection time and the operation guidance by studying the shield machine tool failure. In this paper, an ACO-BP algorithm based tool failure prediction model is established by utilizing the nonlinear mapping characteristics of neural network and mining data characteristics from the subway. According to the practical problems, the dependent variables and the independent variable are systematically selected and compared. The wear and life are chosen as the independent variables in the light of the effect of the cutting tool failure. The factors under different targets combined with the actual situation are selected as the independent variables by applying the principle component analysis and gray correlation. After that, the ant colony algorithm is used to reduce the problem of low efficiency because of ant colony large-scale iterations. The final weights, threshold, and the number of hidden layer nodes by properly adjusting the feedback link. Finally, the analysis results show that the ACO-BP prediction model is effective and accurate. In addition, the control strategy for the abnormal damage is given.
{"title":"Prediction of shield machine tool failure and control strategy design based on ant colony optimization and neural network","authors":"Guotao Zhuang, Chunliang Zhao, X. Yue, Zongjie Du, Shulin Sui","doi":"10.1109/DDCLS.2017.8068113","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068113","url":null,"abstract":"It is important to cut down the erection time and the operation guidance by studying the shield machine tool failure. In this paper, an ACO-BP algorithm based tool failure prediction model is established by utilizing the nonlinear mapping characteristics of neural network and mining data characteristics from the subway. According to the practical problems, the dependent variables and the independent variable are systematically selected and compared. The wear and life are chosen as the independent variables in the light of the effect of the cutting tool failure. The factors under different targets combined with the actual situation are selected as the independent variables by applying the principle component analysis and gray correlation. After that, the ant colony algorithm is used to reduce the problem of low efficiency because of ant colony large-scale iterations. The final weights, threshold, and the number of hidden layer nodes by properly adjusting the feedback link. Finally, the analysis results show that the ACO-BP prediction model is effective and accurate. In addition, the control strategy for the abnormal damage is given.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130874951","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/DDCLS.2017.8068049
Qun Zhu, Hong-Fei Gong, Yuan Xu, Yanlin He
Though in the era of big data, it remains a challenge to be tackled that the forecasting model with high accuracy and robustness needs to be built using small size samples. One effective tool of addressing this problem is the virtual sample generation (VSG), which can generate a mass of new virtual samples on the basis of small sample sets. The bootstrap method is adopted to feasibly resample the virtual samples in this paper. The effectiveness of the proposed bootstrap virtual sample generation (BVSG) is evaluated over one real case. The experimental results show that the proposed approach achieves better performance with the aid of virtual samples.
{"title":"A bootstrap based virtual sample generation method for improving the accuracy of modeling complex chemical processes using small datasets","authors":"Qun Zhu, Hong-Fei Gong, Yuan Xu, Yanlin He","doi":"10.1109/DDCLS.2017.8068049","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068049","url":null,"abstract":"Though in the era of big data, it remains a challenge to be tackled that the forecasting model with high accuracy and robustness needs to be built using small size samples. One effective tool of addressing this problem is the virtual sample generation (VSG), which can generate a mass of new virtual samples on the basis of small sample sets. The bootstrap method is adopted to feasibly resample the virtual samples in this paper. The effectiveness of the proposed bootstrap virtual sample generation (BVSG) is evaluated over one real case. The experimental results show that the proposed approach achieves better performance with the aid of virtual samples.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132124931","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/DDCLS.2017.8068086
H. Yan, Weidong Yang, Hong Zhang, Bo Tao, Ying Zheng
Multi-phase is one of the characteristics of the batch process. In this paper, Density Peaks Clustering (DPC) algorithm is applied to identify the different sub-phases and transition phase of batch processes. First, the three-dimensional training data is unfolded into K time-slice two-dimensional matrices. Then, the DPC algorithm is used to find out the cluster centers and divide the process into multiple sub-phases. In DPC algorithm, the local density and the minimum distance between the data points are calculated to find the most suitable cluster centers. Finally, Multi PCA models are built for each sub-phase, and T2 and SPE statistics are computed to monitor the process online. The proposed method has the following advantages: firstly, it can identify the different sub-phases including transition phases; secondly, there is no need to specify the cluster numbers and initialize cluster centers; finally, it does not require a prior knowledge, and has low computational complexity. This method is applied on penicillin fermentation simulation system. The results verify the effectiveness of the proposed method.
{"title":"Density peaks clustering based sub-phase partition and monitoring for batch process","authors":"H. Yan, Weidong Yang, Hong Zhang, Bo Tao, Ying Zheng","doi":"10.1109/DDCLS.2017.8068086","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068086","url":null,"abstract":"Multi-phase is one of the characteristics of the batch process. In this paper, Density Peaks Clustering (DPC) algorithm is applied to identify the different sub-phases and transition phase of batch processes. First, the three-dimensional training data is unfolded into K time-slice two-dimensional matrices. Then, the DPC algorithm is used to find out the cluster centers and divide the process into multiple sub-phases. In DPC algorithm, the local density and the minimum distance between the data points are calculated to find the most suitable cluster centers. Finally, Multi PCA models are built for each sub-phase, and T2 and SPE statistics are computed to monitor the process online. The proposed method has the following advantages: firstly, it can identify the different sub-phases including transition phases; secondly, there is no need to specify the cluster numbers and initialize cluster centers; finally, it does not require a prior knowledge, and has low computational complexity. This method is applied on penicillin fermentation simulation system. The results verify the effectiveness of the proposed method.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134009508","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/DDCLS.2017.8068089
Xinli Zhang
A kind of nonlinear equation with dissipative term ∊x + x = ∊F(ōt, x), with ō ∊ Rd and d ∊ N, is considered in this paper. Here function F is real analytic. Based on the Renormalizaion Group techniques and Multiscale techniques, the existence of quasi-periodic solutions have been proved for the above-mentioned equation. This generalizes the known results in the existing literatures.
{"title":"The existence of response solution for strongly dissipative nonlinear differential equations","authors":"Xinli Zhang","doi":"10.1109/DDCLS.2017.8068089","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068089","url":null,"abstract":"A kind of nonlinear equation with dissipative term ∊x + x = ∊F(ōt, x), with ō ∊ R<sup>d</sup> and d ∊ N, is considered in this paper. Here function F is real analytic. Based on the Renormalizaion Group techniques and Multiscale techniques, the existence of quasi-periodic solutions have been proved for the above-mentioned equation. This generalizes the known results in the existing literatures.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129334973","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/DDCLS.2017.8068108
Yao-bin Yue, Ruikun Zhang, Bing Wu, Wei Shao
Permanent magnet synchronous motor (PMSM) is a strongly coupled nonlinear system. In this paper, the speed control of PMSM with the direct torque control (DTC) scheme and SVPWM is studied, where the fractional order calculus theory is used to design the fractional order PIλDμ controller. Simulation results show that the proposed fractional order PID control system has better dynamic performance and capacity of resisting disturbance than the integer order PID controller. In addition, the results provide a theoretical basis and foundation for the development and application of fractional order PIλDμ controller in the PMSM speed control system.
{"title":"Direct torque control method of PMSM based on fractional order PID controller","authors":"Yao-bin Yue, Ruikun Zhang, Bing Wu, Wei Shao","doi":"10.1109/DDCLS.2017.8068108","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068108","url":null,"abstract":"Permanent magnet synchronous motor (PMSM) is a strongly coupled nonlinear system. In this paper, the speed control of PMSM with the direct torque control (DTC) scheme and SVPWM is studied, where the fractional order calculus theory is used to design the fractional order PIλDμ controller. Simulation results show that the proposed fractional order PID control system has better dynamic performance and capacity of resisting disturbance than the integer order PID controller. In addition, the results provide a theoretical basis and foundation for the development and application of fractional order PIλDμ controller in the PMSM speed control system.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130988824","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/DDCLS.2017.8068070
Qiuxia Qu, Huaguang Zhang, Rui Yu, Geyang Xiao
In this paper, a novel constrained composite sliding mode controller is studied for uncertain nonlinear systems with input saturation. Based on integral sliding mode and approximate dynamic programming theory, the proposed sliding mode control consists of discontinuous control used for completely compensating matched uncertainties and continuous control that results in an optimal sliding mode dynamics. Without using linearization techniques, the constrained optimal control law for nominal nonlinear systems is approximated by using an online approximate learning algorithm with actor-critic NN framework. Lyapunov techniques are used to demonstrate the uniform ultimate bounded convergence condition for closed-loop nominal system and the weight errors.
{"title":"Constrained robust optimal sliding mode control for uncertain nonlinear systems using ADP approach","authors":"Qiuxia Qu, Huaguang Zhang, Rui Yu, Geyang Xiao","doi":"10.1109/DDCLS.2017.8068070","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068070","url":null,"abstract":"In this paper, a novel constrained composite sliding mode controller is studied for uncertain nonlinear systems with input saturation. Based on integral sliding mode and approximate dynamic programming theory, the proposed sliding mode control consists of discontinuous control used for completely compensating matched uncertainties and continuous control that results in an optimal sliding mode dynamics. Without using linearization techniques, the constrained optimal control law for nominal nonlinear systems is approximated by using an online approximate learning algorithm with actor-critic NN framework. Lyapunov techniques are used to demonstrate the uniform ultimate bounded convergence condition for closed-loop nominal system and the weight errors.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115863636","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/DDCLS.2017.8068111
Jingyao Zhang, De-yuan Meng, W. Feng
In this paper, we address robust iterative learning control (ILC) problem for nonrepetitive systems subject to iteration-varying desired references generated by high-order internal models (HOIM). A modified high-order ILC algorithm is proposed by incorporating HOIM into the ILC algorithm design. We give one condition to guarantee the bounded system trajectories and tracking errors under the assumption that all system matrices, initial states, learning gain coefficients and iteration-varying reference trajectories are bounded. Furthermore, if the variations of all system matrices between two successive iterations converge to zeros and the initial state at each iteration satisfies the HOIM progressively, we give one additional condition together with the former one to guarantee the perfect zero-error tracking.
{"title":"Robust iterative learning control with high-order internal models for SISO nonrepetitive systems","authors":"Jingyao Zhang, De-yuan Meng, W. Feng","doi":"10.1109/DDCLS.2017.8068111","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068111","url":null,"abstract":"In this paper, we address robust iterative learning control (ILC) problem for nonrepetitive systems subject to iteration-varying desired references generated by high-order internal models (HOIM). A modified high-order ILC algorithm is proposed by incorporating HOIM into the ILC algorithm design. We give one condition to guarantee the bounded system trajectories and tracking errors under the assumption that all system matrices, initial states, learning gain coefficients and iteration-varying reference trajectories are bounded. Furthermore, if the variations of all system matrices between two successive iterations converge to zeros and the initial state at each iteration satisfies the HOIM progressively, we give one additional condition together with the former one to guarantee the perfect zero-error tracking.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115147991","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/DDCLS.2017.8068062
Wei Wang, H. Shen, Shen Yin
The sound field distribution is different for disc type permanent magnet motor with different structures and parameters. The effect of structures and parameters on the electromagnetic noise had been discussed in this paper, such as ratio of axial length to diameter, effective pole arc coefficient, length of magnetization direction, width of stator slot, and length of air-gap. In this paper, how to choose noise measuring point and determine the noise distribution characteristic for disc type motor with different shapes are also discussed.
{"title":"Analysis of control technology on electromagnetic noise of permanent magnet synchronous motor","authors":"Wei Wang, H. Shen, Shen Yin","doi":"10.1109/DDCLS.2017.8068062","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068062","url":null,"abstract":"The sound field distribution is different for disc type permanent magnet motor with different structures and parameters. The effect of structures and parameters on the electromagnetic noise had been discussed in this paper, such as ratio of axial length to diameter, effective pole arc coefficient, length of magnetization direction, width of stator slot, and length of air-gap. In this paper, how to choose noise measuring point and determine the noise distribution characteristic for disc type motor with different shapes are also discussed.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115621430","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/DDCLS.2017.8068146
Mingxuan Sun, Jianyong Chen, He Li
This paper presents a finite-time control strategy for uncertain systems with unknown time-invariant parameters. The finite-time adaptive robust controller is designed via Lyapunov approach, where projection-type integral and incremental adaptation laws are applied in estimation of the time-invariant parametric uncertainties, respectively. The terminal attractor is suggested in the adaptive robust controller, and with the proposed control schemes, the finite time convergence can be realized. The bounded error convergence result is obtained in the presence of disturbances. Otherwise, the zero-error convergence can be achieved. The numerical results demonstrate the effectiveness of the proposed control schemes.
{"title":"Finite-time adaptive robust control","authors":"Mingxuan Sun, Jianyong Chen, He Li","doi":"10.1109/DDCLS.2017.8068146","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068146","url":null,"abstract":"This paper presents a finite-time control strategy for uncertain systems with unknown time-invariant parameters. The finite-time adaptive robust controller is designed via Lyapunov approach, where projection-type integral and incremental adaptation laws are applied in estimation of the time-invariant parametric uncertainties, respectively. The terminal attractor is suggested in the adaptive robust controller, and with the proposed control schemes, the finite time convergence can be realized. The bounded error convergence result is obtained in the presence of disturbances. Otherwise, the zero-error convergence can be achieved. The numerical results demonstrate the effectiveness of the proposed control schemes.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126786134","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/DDCLS.2017.8068055
Jun-Zhou Yue, Qiao Zhu
This work is focused on the active vibration control of piezoelectric cantilever beam, where an adaptive feeedforward controller (AFC) is utilized to reject the vibration with unknown multiple frequencies. First, the experiment setup and its mathematical model are introduced. Because the channel between the disturbance and the vibration output is unknown in practice, a concept of equivalent input disturbance (EID) is used to put a equivalent disturbance into the input channel. In this situation, the vibration control can be realized by setting the control input be the identified EID. Then, for the disturbance with known frequencies, the AFC is introduced to reject the disturbance but is sensitive to the frequencies. In order to accurately identify the unknown frequencies of disturbance in presence of the random disturbances and un-modeled nonlinear dynamics, the time-frequency-analysis method is adopted to precisely identify the unknown frequencies of the disturbance. Finally, experiments results demonstrate the efficiency of the AFC algorithm.
{"title":"Active vibration control of piezoelectricity cantilever beam using an adaptive feedforward control method","authors":"Jun-Zhou Yue, Qiao Zhu","doi":"10.1109/DDCLS.2017.8068055","DOIUrl":"https://doi.org/10.1109/DDCLS.2017.8068055","url":null,"abstract":"This work is focused on the active vibration control of piezoelectric cantilever beam, where an adaptive feeedforward controller (AFC) is utilized to reject the vibration with unknown multiple frequencies. First, the experiment setup and its mathematical model are introduced. Because the channel between the disturbance and the vibration output is unknown in practice, a concept of equivalent input disturbance (EID) is used to put a equivalent disturbance into the input channel. In this situation, the vibration control can be realized by setting the control input be the identified EID. Then, for the disturbance with known frequencies, the AFC is introduced to reject the disturbance but is sensitive to the frequencies. In order to accurately identify the unknown frequencies of disturbance in presence of the random disturbances and un-modeled nonlinear dynamics, the time-frequency-analysis method is adopted to precisely identify the unknown frequencies of the disturbance. Finally, experiments results demonstrate the efficiency of the AFC algorithm.","PeriodicalId":419114,"journal":{"name":"2017 6th Data Driven Control and Learning Systems (DDCLS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126332239","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：