Pub Date : 2011-10-13DOI: 10.1109/CCA.2011.6044515
R. Ahmed, M. E. Sayed, S. Gadsden, S. Habibi
A multilayered neural network is a multi-input, multi-output (MIMO) nonlinear system in which training can be regarded as a nonlinear parameter estimation problem by estimating the network weights. In this paper, the relatively new smooth variable structure filter (SVSF) is used for the training of a nonlinear multilayered feed forward network. The SVSF is a recursive sliding mode parameter and state estimator that has a predictor-corrector form. Using a switching gain, a corrective term is calculated to force the network weights to converge to within a neighbourhood of the optimal weight values. SVSF-based trained neural networks are used to classify engine faults on the basis of vibration data. Two faults are induced in a four-stroke, eight-cylinder engine. Furthermore, a comparative study between the popular back propagation method, the extended Kalman filter (EKF), and the SVSF is presented. Experimental results indicate that the SVSF is comparable with the EKF, and both methods outperform back propagation.
{"title":"Fault detection of an engine using a neural network trained by the smooth variable structure filter","authors":"R. Ahmed, M. E. Sayed, S. Gadsden, S. Habibi","doi":"10.1109/CCA.2011.6044515","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044515","url":null,"abstract":"A multilayered neural network is a multi-input, multi-output (MIMO) nonlinear system in which training can be regarded as a nonlinear parameter estimation problem by estimating the network weights. In this paper, the relatively new smooth variable structure filter (SVSF) is used for the training of a nonlinear multilayered feed forward network. The SVSF is a recursive sliding mode parameter and state estimator that has a predictor-corrector form. Using a switching gain, a corrective term is calculated to force the network weights to converge to within a neighbourhood of the optimal weight values. SVSF-based trained neural networks are used to classify engine faults on the basis of vibration data. Two faults are induced in a four-stroke, eight-cylinder engine. Furthermore, a comparative study between the popular back propagation method, the extended Kalman filter (EKF), and the SVSF is presented. Experimental results indicate that the SVSF is comparable with the EKF, and both methods outperform back propagation.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122954617","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044384
Yohei Watanabe, K. Nonaka
In this paper, we propose a velocity control method for leg/wheel type robots by using tire side slip angle and tire slip ratio. Side slip angle and slip ratio is measured by caster type odometers which are comprised of directional sensors and travel distance sensors. The odometer system has redundant four encoders to measure three dimensional velocities: planar two dimensional and rotational movements. We reduce the error between target velocity and actual velocity by feedback control based on both tire slip angle and slip ratio. This method can improve stability and accuracy of movement of vehicles. The experimental vehicle is an omnidirectional vehicle which has legs comprised of three joints. Experimental results of circular trajectory running show effectiveness of the proposed control method.
{"title":"Slip measurement and vehicle control for leg/wheel mobile robots using caster type odometers","authors":"Yohei Watanabe, K. Nonaka","doi":"10.1109/CCA.2011.6044384","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044384","url":null,"abstract":"In this paper, we propose a velocity control method for leg/wheel type robots by using tire side slip angle and tire slip ratio. Side slip angle and slip ratio is measured by caster type odometers which are comprised of directional sensors and travel distance sensors. The odometer system has redundant four encoders to measure three dimensional velocities: planar two dimensional and rotational movements. We reduce the error between target velocity and actual velocity by feedback control based on both tire slip angle and slip ratio. This method can improve stability and accuracy of movement of vehicles. The experimental vehicle is an omnidirectional vehicle which has legs comprised of three joints. Experimental results of circular trajectory running show effectiveness of the proposed control method.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114358759","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044436
H. Igarashi
This paper addresses a human skill evaluation technique with characteristics of input command decision during operation tasks of a mobile object. The characteristics is how long past of tracking error information is utilized to decide the operation command. This evaluation is achieved by a novel human model with multiple neural networks which have different time series of input signals. Then, by the prediction errors from the neural networks, which time series is dominant to decide operation command can be estimated. In this paper, target tracking tasks in 2D CG environment are experimented. A main goal of the task is to operate the mobile target by joystick operation to keep approaching a reference target behaving randomly. Furthermore, effects of subliminal input filtering by predicted operation input are discussed. Finally, by analysis for distribution the neural networks prediction errors, the operator's skill is evaluated and verify the technique with conventional average of tracking errors during the task.
{"title":"Human skill evaluation by operation input characteristics with multiple neural networks","authors":"H. Igarashi","doi":"10.1109/CCA.2011.6044436","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044436","url":null,"abstract":"This paper addresses a human skill evaluation technique with characteristics of input command decision during operation tasks of a mobile object. The characteristics is how long past of tracking error information is utilized to decide the operation command. This evaluation is achieved by a novel human model with multiple neural networks which have different time series of input signals. Then, by the prediction errors from the neural networks, which time series is dominant to decide operation command can be estimated. In this paper, target tracking tasks in 2D CG environment are experimented. A main goal of the task is to operate the mobile target by joystick operation to keep approaching a reference target behaving randomly. Furthermore, effects of subliminal input filtering by predicted operation input are discussed. Finally, by analysis for distribution the neural networks prediction errors, the operator's skill is evaluated and verify the technique with conventional average of tracking errors during the task.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"11 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120870594","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044414
C. Spelta, I. Boniolo, G. Alli, S. Savaresi, Massimo Vanzulli
This paper focuses on a new electric and compact vehicle with a differential steering and a sensitive plantar as driving command. The mechanical, electronic and software architecture are presented. A special focus is given to the sensitive surface of the vehicle chassis which allows the user to drive the vehicle by unbalancing his or her center-of-gravity (COG). The design of the plantar is herein outlined: the electronic system is described and the algorithm to estimate the COG position is proposed. Some experimental results about the sensitive plantar are reported.
{"title":"A planar electric vehicle with differential steering and a plantar command","authors":"C. Spelta, I. Boniolo, G. Alli, S. Savaresi, Massimo Vanzulli","doi":"10.1109/CCA.2011.6044414","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044414","url":null,"abstract":"This paper focuses on a new electric and compact vehicle with a differential steering and a sensitive plantar as driving command. The mechanical, electronic and software architecture are presented. A special focus is given to the sensitive surface of the vehicle chassis which allows the user to drive the vehicle by unbalancing his or her center-of-gravity (COG). The design of the plantar is herein outlined: the electronic system is described and the algorithm to estimate the COG position is proposed. Some experimental results about the sensitive plantar are reported.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122584005","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044514
Eloy García, G. Vitaioli, P. Antsaklis
This paper presents a control design approach for the reference input tracking problem over networks. Plant uncertainties are considered and the Model-Based Networked Control Systems (MB-NCS) framework is used in order to obtain an estimate of the state of the plant between sensor sampling intervals. The results in this paper not only provide a bound on the tracking error but they also allow the networked system to operate in open-loop mode for longer intervals compared to typical approaches that use only a zero-order-hold (ZOH) in the controller/actuator node. This mode of operation reduces time delays and packet dropouts and releases the network to be used for other tasks.
{"title":"Model-based tracking control over networks","authors":"Eloy García, G. Vitaioli, P. Antsaklis","doi":"10.1109/CCA.2011.6044514","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044514","url":null,"abstract":"This paper presents a control design approach for the reference input tracking problem over networks. Plant uncertainties are considered and the Model-Based Networked Control Systems (MB-NCS) framework is used in order to obtain an estimate of the state of the plant between sensor sampling intervals. The results in this paper not only provide a bound on the tracking error but they also allow the networked system to operate in open-loop mode for longer intervals compared to typical approaches that use only a zero-order-hold (ZOH) in the controller/actuator node. This mode of operation reduces time delays and packet dropouts and releases the network to be used for other tasks.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115961033","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044448
P. Giani, F. Todeschini, Stefano Corbetta, M. Tanelli, S. Savaresi, L. Fabbri
This paper addresses the analysis of the gear shifting maneuver for motorcycles and it constitutes, to our best knowledge, the first contribute to study this aspect in two-wheeled vehicles. Specifically, a comparison between automatic and manual gear shifting is discussed, based on which some cost functions are proposed to quantitatively evaluate the maneuver quality from measured data. Based on such cost functions, we are able to automatically classify the performed maneuver and label it with a quality attribute matching that assigned by the rider.
{"title":"Control-oriented analysis and quality assessment of gear shifting in motorcycles","authors":"P. Giani, F. Todeschini, Stefano Corbetta, M. Tanelli, S. Savaresi, L. Fabbri","doi":"10.1109/CCA.2011.6044448","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044448","url":null,"abstract":"This paper addresses the analysis of the gear shifting maneuver for motorcycles and it constitutes, to our best knowledge, the first contribute to study this aspect in two-wheeled vehicles. Specifically, a comparison between automatic and manual gear shifting is discussed, based on which some cost functions are proposed to quantitatively evaluate the maneuver quality from measured data. Based on such cost functions, we are able to automatically classify the performed maneuver and label it with a quality attribute matching that assigned by the rider.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117034273","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044419
R. Filali, C. A. Badea, S. Tebbani, D. Dumur, D. Pareau, F. Lopes
Microalgae present a very promising alternative for carbon dioxide mitigation strategies. These unicellular photosynthetic microorganisms fix carbon dioxide efficiently, converting it into biomass and high-value compounds. One of the control system challenges is to maximize carbon dioxide consumption by maintaining the cellular concentration to an optimal value in the exponential phase. In this paper, we propose a software sensor for the biomass concentration of Chlorella vulgaris culture in a continuous photobioreactor with uncertain model parameters. From Total Inorganic Carbon measurements, the interval observer can provide a guaranteed upper and lower bound for the cellular concentration using the available interval of the uncertain initial condition, model parameters and measurements. Numerical simulations and experimental validation are included to illustrate the performance of the proposed estimation strategy.
{"title":"Interval observer for Chlorella vulgaris culture in a photobioreactor","authors":"R. Filali, C. A. Badea, S. Tebbani, D. Dumur, D. Pareau, F. Lopes","doi":"10.1109/CCA.2011.6044419","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044419","url":null,"abstract":"Microalgae present a very promising alternative for carbon dioxide mitigation strategies. These unicellular photosynthetic microorganisms fix carbon dioxide efficiently, converting it into biomass and high-value compounds. One of the control system challenges is to maximize carbon dioxide consumption by maintaining the cellular concentration to an optimal value in the exponential phase. In this paper, we propose a software sensor for the biomass concentration of Chlorella vulgaris culture in a continuous photobioreactor with uncertain model parameters. From Total Inorganic Carbon measurements, the interval observer can provide a guaranteed upper and lower bound for the cellular concentration using the available interval of the uncertain initial condition, model parameters and measurements. Numerical simulations and experimental validation are included to illustrate the performance of the proposed estimation strategy.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114099154","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044426
David Tick, Jinglin Shen, Yinghua Zhang, N. Gans
This paper presents a sensor fusion implementation to improve the accuracy of robot localization by combining multiple visual odometry approaches with wheel and IMU odometry. Discrete and continuous Homography Matrices are used to recover robot pose and velocity from image sequences of tracked feature points. The camera's limited field of view is addressed by chaining vision-based motion estimates. As feature points leave the field of view, new features are acquired and tracked. When a new set of points is needed, the motion estimate is reinitialized and chained to the previous state estimate. An extended Kalman filter fuses measurements from the robot's wheel encoders with those from visual and inertial measurement systems. Time varying matrices in the extended Kalman filter compensate for known changes in sensor accuracy, including periods when visual features cannot be reliably tracked. Experiments are performed to validate the approach.
{"title":"Chained fusion of discrete and continuous epipolar geometry with odometry for long-term localization of mobile robots","authors":"David Tick, Jinglin Shen, Yinghua Zhang, N. Gans","doi":"10.1109/CCA.2011.6044426","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044426","url":null,"abstract":"This paper presents a sensor fusion implementation to improve the accuracy of robot localization by combining multiple visual odometry approaches with wheel and IMU odometry. Discrete and continuous Homography Matrices are used to recover robot pose and velocity from image sequences of tracked feature points. The camera's limited field of view is addressed by chaining vision-based motion estimates. As feature points leave the field of view, new features are acquired and tracked. When a new set of points is needed, the motion estimate is reinitialized and chained to the previous state estimate. An extended Kalman filter fuses measurements from the robot's wheel encoders with those from visual and inertial measurement systems. Time varying matrices in the extended Kalman filter compensate for known changes in sensor accuracy, including periods when visual features cannot be reliably tracked. Experiments are performed to validate the approach.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126835975","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044388
Kevin McDonough, I. Kolmanovsky, Dimitar Filev, D. Yanakiev, Steven Szwabowski, J. Michelini, M. Abou-nasr
This paper considers modeling of vehicle driving conditions using transition probability models (TPMs) for applications of dynamic optimization. The properties of transition probabilities for vehicle speed, vehicle acceleration, and road grade are discussed based on the analysis and experimental vehicle data. The KL-divergence is shown to provide an effective metric that can differentiate similar driving conditions from dissimilar ones.
{"title":"Modeling of vehicle driving conditions using transition probability models","authors":"Kevin McDonough, I. Kolmanovsky, Dimitar Filev, D. Yanakiev, Steven Szwabowski, J. Michelini, M. Abou-nasr","doi":"10.1109/CCA.2011.6044388","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044388","url":null,"abstract":"This paper considers modeling of vehicle driving conditions using transition probability models (TPMs) for applications of dynamic optimization. The properties of transition probabilities for vehicle speed, vehicle acceleration, and road grade are discussed based on the analysis and experimental vehicle data. The KL-divergence is shown to provide an effective metric that can differentiate similar driving conditions from dissimilar ones.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126179949","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 : 2011-10-13DOI: 10.1109/CCA.2011.6044469
Lun-Hui Lee, Pei-Hsiang Huang, Yu-Cheng Shih, Sung-Chih Ku, Cheng-Yuan Chang
Using visual tracking technology by CCD sensor instead of high speed computational resources to measure the fast dynamic systems is not easy. This paper proposes a simple and effective method to do the image processing, catching this dynamic movement in real-time and controlling the overhead crane. Visual tracking based on color histograms will compare the color in a model image with the color in image sequences to track the dynamic object. Once it tracked, the sensing data will be sent to the adaptive fuzzy sliding mode controller (AFSMC) to control the overhead cranes. The merits of it include the robustness and model free properties of the sliding mode and fuzzy logic controllers; adaptable slopes of the sliding surface are also presented to enhance the control results.
{"title":"Adaptive fuzzy sliding mode control to overhead crane by CCD sensor","authors":"Lun-Hui Lee, Pei-Hsiang Huang, Yu-Cheng Shih, Sung-Chih Ku, Cheng-Yuan Chang","doi":"10.1109/CCA.2011.6044469","DOIUrl":"https://doi.org/10.1109/CCA.2011.6044469","url":null,"abstract":"Using visual tracking technology by CCD sensor instead of high speed computational resources to measure the fast dynamic systems is not easy. This paper proposes a simple and effective method to do the image processing, catching this dynamic movement in real-time and controlling the overhead crane. Visual tracking based on color histograms will compare the color in a model image with the color in image sequences to track the dynamic object. Once it tracked, the sensing data will be sent to the adaptive fuzzy sliding mode controller (AFSMC) to control the overhead cranes. The merits of it include the robustness and model free properties of the sliding mode and fuzzy logic controllers; adaptable slopes of the sliding surface are also presented to enhance the control results.","PeriodicalId":208713,"journal":{"name":"2011 IEEE International Conference on Control Applications (CCA)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126200082","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：