Pub Date : 2014-12-18DOI: 10.1109/ICCAS.2014.6987757
Sung Jin Yoo, J. H. Kim, J. M. Lee
Microalgae have received considerable attention as a source of biodiesel since they contain large amounts of lipid. However, microalgal biodiesel is not economically competitive compared to other sources of biodiesel or petrodiesel. To improve the productivity of lipid and biomass in photobioreactor systems, real-time monitoring and control are prerequisite. However, measurement of lipid in microalgae itself is very difficult and time consuming task, and it is not easy to know the lipid concentration in real-time. In this study, estimation of lipid concentration using other online measurements from biomass or glucose sensor was studied. Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF) were compared in various cases for their applicability to photobioreactor systems. Furthermore, simulation studies to find appropriate types of sensors for estimating lipid have also been performed. This study suggests what filters and what type of sensors are suitable for estimating lipid concentration on-line.
{"title":"Soft sensor design with state estimator for lipid estimation of microalgal photobioreactor system","authors":"Sung Jin Yoo, J. H. Kim, J. M. Lee","doi":"10.1109/ICCAS.2014.6987757","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987757","url":null,"abstract":"Microalgae have received considerable attention as a source of biodiesel since they contain large amounts of lipid. However, microalgal biodiesel is not economically competitive compared to other sources of biodiesel or petrodiesel. To improve the productivity of lipid and biomass in photobioreactor systems, real-time monitoring and control are prerequisite. However, measurement of lipid in microalgae itself is very difficult and time consuming task, and it is not easy to know the lipid concentration in real-time. In this study, estimation of lipid concentration using other online measurements from biomass or glucose sensor was studied. Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF) were compared in various cases for their applicability to photobioreactor systems. Furthermore, simulation studies to find appropriate types of sensors for estimating lipid have also been performed. This study suggests what filters and what type of sensors are suitable for estimating lipid concentration on-line.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"121 1","pages":"1299-1304"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86724311","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987758
Boeun Kim, Hong Jang, Moon-Ho Eom, Jay H. Lee
Biobutanol is considered to be a promising choice for renewable fuel due to its high energy content, low volatility, and low water solubility. However, the production of biobutanol through fermentation is complicated by the fact that butanol inhibits the microorganism's cell growth and therefore the butanol production when its concentration in the fermentation broth reaches a certain critical level. In order to raise the volumetric productivity to a commercially acceptable level, produced biobutanol needs to be separated out as the fermentation is on-going. In this study, a continuous extractive fermentation process integrated with an ex-situ adsorption recovery process is studied to overcome this limitation. Switching of the adsorption column upon the saturation yields a continuous process with a cyclic steady state behavior. A dynamic model for the integrated process is developed and an optimization is performed based on the cyclic steady state analysis in order to design an optimal operation strategy that satisfies given requirements.
{"title":"Optimal design and operation of an extractive fermentation process for continuous biobutanol production","authors":"Boeun Kim, Hong Jang, Moon-Ho Eom, Jay H. Lee","doi":"10.1109/ICCAS.2014.6987758","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987758","url":null,"abstract":"Biobutanol is considered to be a promising choice for renewable fuel due to its high energy content, low volatility, and low water solubility. However, the production of biobutanol through fermentation is complicated by the fact that butanol inhibits the microorganism's cell growth and therefore the butanol production when its concentration in the fermentation broth reaches a certain critical level. In order to raise the volumetric productivity to a commercially acceptable level, produced biobutanol needs to be separated out as the fermentation is on-going. In this study, a continuous extractive fermentation process integrated with an ex-situ adsorption recovery process is studied to overcome this limitation. Switching of the adsorption column upon the saturation yields a continuous process with a cyclic steady state behavior. A dynamic model for the integrated process is developed and an optimization is performed based on the cyclic steady state analysis in order to design an optimal operation strategy that satisfies given requirements.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"30 1 1","pages":"1305-1310"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90067649","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987756
Young Kook Kim, Jongwon Park, Byungho Yoon, Kyung-Soo Kim, Soohyun Kim
In terms of the speed performance in feline galloping, relative spinal motion is observed as a key role to increase the locomotion speed. In order to prove this, a domestic cat was observed to investigate galloping gait patterns of the feline. Based on the measurement of the dynamic behavior of a domestic cat, we observed a significant increase in speed through correlated angular rate changes of spinal segments. To support the motion into a quadruped system, the hindlimb stance phase was analyzed using a 2 dimensional planar dynamic model to verify that the external torque generated by spinal motion plays an important role in increasing the ground reaction force in the direction of movement. To verify the analysis, the dynamic simulation demonstrating the hindlimb stance was applied with 3 parameter variations: time, phase and the amplitude of the fitted relative angular velocity profile.
{"title":"Dynamic analysis of the spinal-pelvic motion match during feline galloping for speed increase into quadruped robotic system","authors":"Young Kook Kim, Jongwon Park, Byungho Yoon, Kyung-Soo Kim, Soohyun Kim","doi":"10.1109/ICCAS.2014.6987756","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987756","url":null,"abstract":"In terms of the speed performance in feline galloping, relative spinal motion is observed as a key role to increase the locomotion speed. In order to prove this, a domestic cat was observed to investigate galloping gait patterns of the feline. Based on the measurement of the dynamic behavior of a domestic cat, we observed a significant increase in speed through correlated angular rate changes of spinal segments. To support the motion into a quadruped system, the hindlimb stance phase was analyzed using a 2 dimensional planar dynamic model to verify that the external torque generated by spinal motion plays an important role in increasing the ground reaction force in the direction of movement. To verify the analysis, the dynamic simulation demonstrating the hindlimb stance was applied with 3 parameter variations: time, phase and the amplitude of the fitted relative angular velocity profile.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"27 12 1","pages":"1294-1298"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83531703","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987974
Sun-Ho Kim, Jungho Kim, Youngbae Hwang, Byoung-Tae Choi, J. Yoon
In this paper, we present a new object tracking algorithm which integrates color-based mean-shift and feature-based optical flow methods. To utilize two approaches in the complimentary manner, we iteratively compute the mean-shift vector based on color histograms and tracked features by KLT. In the experiments, we show the improved performance for partial occlusion and severe appearance changes in the representative benchmark sequences.
{"title":"Object tracking using KLT aided mean-shift object tracker (ICCAS 2014)","authors":"Sun-Ho Kim, Jungho Kim, Youngbae Hwang, Byoung-Tae Choi, J. Yoon","doi":"10.1109/ICCAS.2014.6987974","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987974","url":null,"abstract":"In this paper, we present a new object tracking algorithm which integrates color-based mean-shift and feature-based optical flow methods. To utilize two approaches in the complimentary manner, we iteratively compute the mean-shift vector based on color histograms and tracked features by KLT. In the experiments, we show the improved performance for partial occlusion and severe appearance changes in the representative benchmark sequences.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"65 1","pages":"140-145"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89319478","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987822
Jun-beom Park, S. Bae, B. Koo, Jung-ha Kim
Method of improving the safety of autonomous vehicles are diverse. In particular, Path Tracking phase which is the last step and important to operate an autonomous vehicle. Method of Path tacking are diverse. Kinematic and dynamic methods is typically methods. In this study, Among Kinematic method, Pure pursuit is used by using the path tracking. Commonly pure pursuit is used to path tracking of mobile robots. Pure pursuit is selected target point and is path traced When selecting the tracking target point, the traveling speed is low or, in certain cases, to extract the following target point at a fixed distance. However, the speed and the path of autonomous vehicle is continually changing. Therefore, the selection method of tracking a target point of the fixed distance, can inhibit the behavioral stability of the vehicle. Also affect the path tracking performance. Therefore, changing of the tracking target point is advantageous.
{"title":"When path tracking using look-ahead distance about the lateral error method and the velocity change method tracking comparison","authors":"Jun-beom Park, S. Bae, B. Koo, Jung-ha Kim","doi":"10.1109/ICCAS.2014.6987822","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987822","url":null,"abstract":"Method of improving the safety of autonomous vehicles are diverse. In particular, Path Tracking phase which is the last step and important to operate an autonomous vehicle. Method of Path tacking are diverse. Kinematic and dynamic methods is typically methods. In this study, Among Kinematic method, Pure pursuit is used by using the path tracking. Commonly pure pursuit is used to path tracking of mobile robots. Pure pursuit is selected target point and is path traced When selecting the tracking target point, the traveling speed is low or, in certain cases, to extract the following target point at a fixed distance. However, the speed and the path of autonomous vehicle is continually changing. Therefore, the selection method of tracking a target point of the fixed distance, can inhibit the behavioral stability of the vehicle. Also affect the path tracking performance. Therefore, changing of the tracking target point is advantageous.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"25 1","pages":"1643-1647"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84796690","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987989
Denys Makarets, G. Noh, Keri Kim, Deukhee Lee
Continuum robots, new class of dexterous and thin robots, can be applied in great variety of minimal invasive surgical operations. These robots consist of two parts: manipulator, also called active cannula, and control unit. Manipulators, which are composed of concentric precurved tubes(usually 2-3), commonly made from nitinol, can enter human body through small incisions or natural orifices and, after reconfiguration into more complex structure, guide surgical instruments to the target regions avoiding obstacles. In this paper, we propose to use plastic as the material for innermost tube. Variations in the shape of lab-made concentric precurved plastic tube prototypes after numerous extension-retractions are investigated. We also use kinematic model, based on beam mechanics, for capturing the end-effector tip position and the shape of the two manipulators (I - manipulator is composed of one nitinol tube and one plastic tube prototype; II - manipulator is composed of two nitinol tubes and one plastic tube prototype). The model predictions are compared with the experimental results. Preliminary results show that plastic tubes may have small radii of precurvature, and sustain extension-retraction without self-damage thus potentially can be used as a component of continuum robots.
{"title":"Preliminary study of utilizing plastic tubes as a component of continuum robots","authors":"Denys Makarets, G. Noh, Keri Kim, Deukhee Lee","doi":"10.1109/ICCAS.2014.6987989","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987989","url":null,"abstract":"Continuum robots, new class of dexterous and thin robots, can be applied in great variety of minimal invasive surgical operations. These robots consist of two parts: manipulator, also called active cannula, and control unit. Manipulators, which are composed of concentric precurved tubes(usually 2-3), commonly made from nitinol, can enter human body through small incisions or natural orifices and, after reconfiguration into more complex structure, guide surgical instruments to the target regions avoiding obstacles. In this paper, we propose to use plastic as the material for innermost tube. Variations in the shape of lab-made concentric precurved plastic tube prototypes after numerous extension-retractions are investigated. We also use kinematic model, based on beam mechanics, for capturing the end-effector tip position and the shape of the two manipulators (I - manipulator is composed of one nitinol tube and one plastic tube prototype; II - manipulator is composed of two nitinol tubes and one plastic tube prototype). The model predictions are compared with the experimental results. Preliminary results show that plastic tubes may have small radii of precurvature, and sustain extension-retraction without self-damage thus potentially can be used as a component of continuum robots.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"7 1","pages":"217-220"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83649534","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6988013
D. Park, Chanhun Park, Hyunmin Do, Taeyong Choi, J. Kyung
A dual arm robot is one of the most popular issue on the robotic field. Because a dual arm robot has two arms like humans, it can conduct the complex handling task and the jigless assembly task which cannot be performed by a single arm robot. Also, it is expected to substitute for humans and do better performance than humans in the industrial manufacturing. In the paper, we proposed a dual arm robot system with a mobile platform for the automatic assembly of electrical devices and it was developed through kinematic and dynamic analysis. Kinematic analysis was performed for the workspace and dynamic analysis was carried out for the robot specification.
{"title":"Development of dual arm robot platform for automatic assembly","authors":"D. Park, Chanhun Park, Hyunmin Do, Taeyong Choi, J. Kyung","doi":"10.1109/ICCAS.2014.6988013","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6988013","url":null,"abstract":"A dual arm robot is one of the most popular issue on the robotic field. Because a dual arm robot has two arms like humans, it can conduct the complex handling task and the jigless assembly task which cannot be performed by a single arm robot. Also, it is expected to substitute for humans and do better performance than humans in the industrial manufacturing. In the paper, we proposed a dual arm robot system with a mobile platform for the automatic assembly of electrical devices and it was developed through kinematic and dynamic analysis. Kinematic analysis was performed for the workspace and dynamic analysis was carried out for the robot specification.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"68 1","pages":"319-321"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90460042","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987929
Yuri Shimanuki, K. Hidaka
This paper presents a recognition of obstacle and objects for an industrial a mobile robot, e.g., an automated guided vehicle (AGV), by using monocular camera. The mobile robot moves for transporting same parts in a factory where the robot has to pass a production line. An accurate recognition of object on the production line is required for moving the robot automatically. In addition, the robustness to luminance changes is required. During the past decades, some robust features, such as Scale Invariant Feature Transform(SIFT), Speeded Up Robust Features(SURF), Histograms of Oriented Gradients(HOG), or Extended HOG(EHOG), have been proposed in computer vision and machine learning. In this paper, we focus on the robustness of EHOG and we propose a decision algorithm of objects on a path by using the machine learning based on EHOG.We show that experimental results are provided and the usefulness of the proposed algorithm is introduced by these results.
{"title":"Recognition of object by extended Histograms of Oriented Gradients (EHOG) on route for a mobile robot","authors":"Yuri Shimanuki, K. Hidaka","doi":"10.1109/ICCAS.2014.6987929","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987929","url":null,"abstract":"This paper presents a recognition of obstacle and objects for an industrial a mobile robot, e.g., an automated guided vehicle (AGV), by using monocular camera. The mobile robot moves for transporting same parts in a factory where the robot has to pass a production line. An accurate recognition of object on the production line is required for moving the robot automatically. In addition, the robustness to luminance changes is required. During the past decades, some robust features, such as Scale Invariant Feature Transform(SIFT), Speeded Up Robust Features(SURF), Histograms of Oriented Gradients(HOG), or Extended HOG(EHOG), have been proposed in computer vision and machine learning. In this paper, we focus on the robustness of EHOG and we propose a decision algorithm of objects on a path by using the machine learning based on EHOG.We show that experimental results are provided and the usefulness of the proposed algorithm is introduced by these results.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"15 1","pages":"986-991"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90473071","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6988042
Tae-Shin Kim, Young-Ho Lee, Jong-Koo Park, Tae-Yong Kuc, S. Ji, Sang-Moo Lee, Y. Moon
This paper considers a design problem for time synchronized coverage control of cooperative mobile robots. The derived algorithm provides a coverage control which not only considers the mobility characteristic of each mobile robot for task allocation but generates robot velocity profile for synchronized coverage completion within the constrained time. Since the environment for robot coverage work is modeled as a set of locations to visit by robots, the derived coverage algorithm and its control method are equally well suited to an unstructured working environment as to the structured work space. In determining the number of locations for each robot to visit during coverage operation, a time index derived from the minimum time velocity profile is used for the comparison of robot performance. Once the set of locations has been determined for each robot, the corresponding path tree and velocity profile are generated for synchronized execution of coverage work. The completeness of synchronized group coverage within the constrained time is proven through simulation for a group of mobile robots with different motor characteristics. An additional consideration by the derived coverage controller is collision avoidance of mobile robots in a crowded environment with the aid of finite potential function approach.
{"title":"A time synchronized multi-robot coverage algorithm for unstructured environment","authors":"Tae-Shin Kim, Young-Ho Lee, Jong-Koo Park, Tae-Yong Kuc, S. Ji, Sang-Moo Lee, Y. Moon","doi":"10.1109/ICCAS.2014.6988042","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6988042","url":null,"abstract":"This paper considers a design problem for time synchronized coverage control of cooperative mobile robots. The derived algorithm provides a coverage control which not only considers the mobility characteristic of each mobile robot for task allocation but generates robot velocity profile for synchronized coverage completion within the constrained time. Since the environment for robot coverage work is modeled as a set of locations to visit by robots, the derived coverage algorithm and its control method are equally well suited to an unstructured working environment as to the structured work space. In determining the number of locations for each robot to visit during coverage operation, a time index derived from the minimum time velocity profile is used for the comparison of robot performance. Once the set of locations has been determined for each robot, the corresponding path tree and velocity profile are generated for synchronized execution of coverage work. The completeness of synchronized group coverage within the constrained time is proven through simulation for a group of mobile robots with different motor characteristics. An additional consideration by the derived coverage controller is collision avoidance of mobile robots in a crowded environment with the aid of finite potential function approach.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"126 1","pages":"503-508"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78546440","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 : 2014-12-18DOI: 10.1109/ICCAS.2014.6987543
Asim Zaheer, M. Salman
In this work, black-box model identification and output prediction for unknown sampled-data minimum phase system has been achieved. Feedforward neural network (multilayer perceptron) is used for system identification. Unscented Kalman Filter (UKF) online determine weights of neural network and predicts output in open-loop sampled-data configuration. Magnetic levitation and DC motor model has been identified in computer simulations using the presented black-box identification and prediction scheme.
{"title":"Online black-box model identification and output prediction for sampled-data systems","authors":"Asim Zaheer, M. Salman","doi":"10.1109/ICCAS.2014.6987543","DOIUrl":"https://doi.org/10.1109/ICCAS.2014.6987543","url":null,"abstract":"In this work, black-box model identification and output prediction for unknown sampled-data minimum phase system has been achieved. Feedforward neural network (multilayer perceptron) is used for system identification. Unscented Kalman Filter (UKF) online determine weights of neural network and predicts output in open-loop sampled-data configuration. Magnetic levitation and DC motor model has been identified in computer simulations using the presented black-box identification and prediction scheme.","PeriodicalId":6525,"journal":{"name":"2014 14th International Conference on Control, Automation and Systems (ICCAS 2014)","volume":"14 1","pages":"1095-1100"},"PeriodicalIF":0.0,"publicationDate":"2014-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75433730","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：