Pub Date : 2018-06-01DOI: 10.1109/ICSSE.2018.8520044
Kolitha Warnakulasooriya, C. Premachandra, B. Sudantha, S. Sumathipala
Gesture recognition could be effectively used in most instruments targeting the life support of differently abled people. Therefore, an enhanced development was carried out targeting the miscellaneous requirements of the said kind of people. The Kinect capturing device was used to extract the 3-D information and processing could be carried out using a single board PC and the low power blue tooth module was used to get the connectivity between external devices enabling IoT features of the system. Different gestures were carefully identified and unique command set was generated covering each gesture identified. Once the system is configured identifying the relevant conditions of a particular person's hearing conditions, it could be used to address his different hearing requirements.
{"title":"IoT Empowered Gesture Recognition System for Life Style Enhancement of Differently Abled People","authors":"Kolitha Warnakulasooriya, C. Premachandra, B. Sudantha, S. Sumathipala","doi":"10.1109/ICSSE.2018.8520044","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520044","url":null,"abstract":"Gesture recognition could be effectively used in most instruments targeting the life support of differently abled people. Therefore, an enhanced development was carried out targeting the miscellaneous requirements of the said kind of people. The Kinect capturing device was used to extract the 3-D information and processing could be carried out using a single board PC and the low power blue tooth module was used to get the connectivity between external devices enabling IoT features of the system. Different gestures were carefully identified and unique command set was generated covering each gesture identified. Once the system is configured identifying the relevant conditions of a particular person's hearing conditions, it could be used to address his different hearing requirements.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131979334","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520064
N. T. Long, Nguyen Van Huong, Dao Phuong Nam, Mai Xuan Sinh, Nguyen Thu Ha
This work presents an adaptive optimal control algorithm based integral sliding mode control law for a class of continuous-time systems with input disturbance or uncertain and unknown parameters. The main objective is to find a general form of integral sliding mode control law can assure that the system states are forced to reach a sliding surface in the initial finite time. Then, an adaptive optimal control based on the approximate dynamic programming method is responsible for the robust stability of the closed-loop system. Finally, the theoretical analysis and simulation results demonstrate the performance of the proposed algorithm for a wheel inverted pendulum system.
{"title":"A Simple Approximate Dynamic Programing Based on Integral Sliding Mode Control for Unknown Linear Systems with Input Disturbance","authors":"N. T. Long, Nguyen Van Huong, Dao Phuong Nam, Mai Xuan Sinh, Nguyen Thu Ha","doi":"10.1109/ICSSE.2018.8520064","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520064","url":null,"abstract":"This work presents an adaptive optimal control algorithm based integral sliding mode control law for a class of continuous-time systems with input disturbance or uncertain and unknown parameters. The main objective is to find a general form of integral sliding mode control law can assure that the system states are forced to reach a sliding surface in the initial finite time. Then, an adaptive optimal control based on the approximate dynamic programming method is responsible for the robust stability of the closed-loop system. Finally, the theoretical analysis and simulation results demonstrate the performance of the proposed algorithm for a wheel inverted pendulum system.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131816589","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520209
Mu-Yen Chen, Hsin-Te Wu, Wen-Yu Chiu
Ever since the Internet of Things was developed, countries around the world have been applying the technology to solve current issues in agriculture, such as combating climate change and reducing labor costs. In the moment, intelligent agriculture has focused mainly on greenhouse cultivation; however, it takes significant amount of material and labor resources to build greenhouses, and their products are mostly high-valued cash crops. This study employs an outdoor farm as the field of experimentation and uses self-made model vehicles that patrols regularly to obtain information on the farm's crops. The study first establishes deep learning in intelligent agriculture to understand the farmer's farming skills so that such information may in turn help in further establishing an Internet of Things system that realizes automated farming systems. This study utilizes small, self-made model vehicles to gather crop information every day. The vehicles' designed functions include the following: (1) automated patrol along preprogrammed routes, (2) automatic photographing of each area, (3) prevention of collision between the small, self-made model vehicles, and (4) data collection of each area's temperature and humidity conditions. In this study, deep learning is employed mainly towards training and prediction of conditions based on the crop's temperature and humidity data as well as weather information. Deep learning is established first, followed by the Internet of Things, in order to achieve intelligent agriculture. The study must first acquire the farmers' cultivation skills; since such knowledge is passed on through experience and without any recordings, it can only be retrieved by means of the small model vehicles. In addition, the study also conducted simulation through hands-on experiments. The proposed scheme first collects all environment-related factors and conducts training on related coefficients, then utilizes the automatic irrigation system to allow the same kind of crops to grow in the most ideal environment. The system focuses on outdoor farms; it establishes an intelligent agriculture using minimal costs, resolving issues such as number of sensors needed, farm network accessibility, and electrical wiring.
{"title":"An Intelligent Agriculture Application Based on Deep Learning","authors":"Mu-Yen Chen, Hsin-Te Wu, Wen-Yu Chiu","doi":"10.1109/ICSSE.2018.8520209","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520209","url":null,"abstract":"Ever since the Internet of Things was developed, countries around the world have been applying the technology to solve current issues in agriculture, such as combating climate change and reducing labor costs. In the moment, intelligent agriculture has focused mainly on greenhouse cultivation; however, it takes significant amount of material and labor resources to build greenhouses, and their products are mostly high-valued cash crops. This study employs an outdoor farm as the field of experimentation and uses self-made model vehicles that patrols regularly to obtain information on the farm's crops. The study first establishes deep learning in intelligent agriculture to understand the farmer's farming skills so that such information may in turn help in further establishing an Internet of Things system that realizes automated farming systems. This study utilizes small, self-made model vehicles to gather crop information every day. The vehicles' designed functions include the following: (1) automated patrol along preprogrammed routes, (2) automatic photographing of each area, (3) prevention of collision between the small, self-made model vehicles, and (4) data collection of each area's temperature and humidity conditions. In this study, deep learning is employed mainly towards training and prediction of conditions based on the crop's temperature and humidity data as well as weather information. Deep learning is established first, followed by the Internet of Things, in order to achieve intelligent agriculture. The study must first acquire the farmers' cultivation skills; since such knowledge is passed on through experience and without any recordings, it can only be retrieved by means of the small model vehicles. In addition, the study also conducted simulation through hands-on experiments. The proposed scheme first collects all environment-related factors and conducts training on related coefficients, then utilizes the automatic irrigation system to allow the same kind of crops to grow in the most ideal environment. The system focuses on outdoor farms; it establishes an intelligent agriculture using minimal costs, resolving issues such as number of sensors needed, farm network accessibility, and electrical wiring.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133788152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study applies socket for connecting Ethernet control automation technology (EtherCAT) master program and OpenPLC. EtherCAT is a new potential protocol that might be the next generation of industrial communication. To make it fully functional, combining EtherCAT with programmable logic controller (PLC) become our first target. With Socket, a reliable API, we can implement PLC on EtherCATstructure by connecting EtherCAT master program and OpenPLC
{"title":"Applying Socket on Connecting EtherCAT and OpenPLC","authors":"Hong-Yu Lin, I-Wen Cheng, Yu-Hsuan Huang, Hung-Chun Liu, Yu-Hsin Lin, Chan-Yun Yang, Hooman Saman, Ying-Jen Chen","doi":"10.1109/ICSSE.2018.8520168","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520168","url":null,"abstract":"This study applies socket for connecting Ethernet control automation technology (EtherCAT) master program and OpenPLC. EtherCAT is a new potential protocol that might be the next generation of industrial communication. To make it fully functional, combining EtherCAT with programmable logic controller (PLC) become our first target. With Socket, a reliable API, we can implement PLC on EtherCATstructure by connecting EtherCAT master program and OpenPLC","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116254684","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520247
W. Huang, Wen Kai Yang, T. Chiang, Jyh-Homg Chou
This study investigated the application of ultrasonic atomization lubrication system with Nanofluid additive implemented in micro-milling process on SKD11 die steel. The graphene nanoparticles are employed as the additive of Nanofluid. Ultrasonic atomization system not only can effectively improve the agglomeration phenomena of Nanoparticles in Nanofluids but also provide the benefit of particle lubrication. For this experiment, Taguchi method was adopted and L934 orthogonal array was used to explore the optimal parameters. Targeting micro-milling force evaluation as the only focus, the control parameters included the average thickness and weight percentage concentration of Nano-graphene, the amount of ultrasonic atomization, and the angle of nozzle are analyzed. Based on the analysis, the optimal combination of Nano-graphene with ultrasonic atomization micro-lubrication was found, and then compared to the case of MWCNTs with ultrasonic atomization micro-lubrication and the other case of basal liquid with ultrasonic atomization micro-lubrication. According to the experiment results, the Nanofluid with Nano-graphene added can further reduce the micro-milling force of micro-milling process that suppress the burr generated by the processing. It can achieve the goal of tool life improvement and high workpiece quality. The micro-milling force using Nano-graphene with ultrasonic atomization micro-lubrication is reduced by 7.8% and 12.9% compared to the other two lubricating fluids, respectively.
{"title":"The Application of Nanofluid (Nano-Graphene)/Ultrasonic Atomization Micro-Lubrication in Micro-Milling Process on SKD11 Die Steel","authors":"W. Huang, Wen Kai Yang, T. Chiang, Jyh-Homg Chou","doi":"10.1109/ICSSE.2018.8520247","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520247","url":null,"abstract":"This study investigated the application of ultrasonic atomization lubrication system with Nanofluid additive implemented in micro-milling process on SKD11 die steel. The graphene nanoparticles are employed as the additive of Nanofluid. Ultrasonic atomization system not only can effectively improve the agglomeration phenomena of Nanoparticles in Nanofluids but also provide the benefit of particle lubrication. For this experiment, Taguchi method was adopted and L934 orthogonal array was used to explore the optimal parameters. Targeting micro-milling force evaluation as the only focus, the control parameters included the average thickness and weight percentage concentration of Nano-graphene, the amount of ultrasonic atomization, and the angle of nozzle are analyzed. Based on the analysis, the optimal combination of Nano-graphene with ultrasonic atomization micro-lubrication was found, and then compared to the case of MWCNTs with ultrasonic atomization micro-lubrication and the other case of basal liquid with ultrasonic atomization micro-lubrication. According to the experiment results, the Nanofluid with Nano-graphene added can further reduce the micro-milling force of micro-milling process that suppress the burr generated by the processing. It can achieve the goal of tool life improvement and high workpiece quality. The micro-milling force using Nano-graphene with ultrasonic atomization micro-lubrication is reduced by 7.8% and 12.9% compared to the other two lubricating fluids, respectively.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131049219","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520032
Sheng-Yang Chiu, Jui-Chien Hsieh, Chi-I Hsu, C. Chiu
Among various kinds of falling prevention measures, bed exit alarm mechanism has raised serious attention recently. In particular, the recent inflow of innovative ICT advancement from Internet of Things, wearable technology, and artificial intelligence have shed on more possibility in realizing effective bed exit alarm systems. This research proposes a deep learning algorithm to construct the bed exit detection model using monitored behavior information collected from the infrared array sensor. Based on the preliminary experiment results, the bed-exit events can be recognized with 92% accuracy, 99% for precision and 97% for recall rate. This approach also has its advantages in low device costs, less data storage needed, less spacial resolution without privacy and legal concerns, and unaffected performance in various lighting conditions.
{"title":"A Convolutional Neural Networks Approach with Infrared Array Sensor for Bed-Exit Detection","authors":"Sheng-Yang Chiu, Jui-Chien Hsieh, Chi-I Hsu, C. Chiu","doi":"10.1109/ICSSE.2018.8520032","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520032","url":null,"abstract":"Among various kinds of falling prevention measures, bed exit alarm mechanism has raised serious attention recently. In particular, the recent inflow of innovative ICT advancement from Internet of Things, wearable technology, and artificial intelligence have shed on more possibility in realizing effective bed exit alarm systems. This research proposes a deep learning algorithm to construct the bed exit detection model using monitored behavior information collected from the infrared array sensor. Based on the preliminary experiment results, the bed-exit events can be recognized with 92% accuracy, 99% for precision and 97% for recall rate. This approach also has its advantages in low device costs, less data storage needed, less spacial resolution without privacy and legal concerns, and unaffected performance in various lighting conditions.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125567170","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520258
Li Ning, Rong Zhou, Yong Zhang, D. Yu, Francis C. M. Lau
Existing collision avoidance approaches for multiagent navigation often cause excessive detouring as a side effect. In this work, we propose an approach that navigates the agents with much less deviation from the ideal route, while efficiently avoiding potential collisions.
{"title":"Taking Less Detour when Avoiding the Collisions","authors":"Li Ning, Rong Zhou, Yong Zhang, D. Yu, Francis C. M. Lau","doi":"10.1109/ICSSE.2018.8520258","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520258","url":null,"abstract":"Existing collision avoidance approaches for multiagent navigation often cause excessive detouring as a side effect. In this work, we propose an approach that navigates the agents with much less deviation from the ideal route, while efficiently avoiding potential collisions.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122488823","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520136
Ping‐Jui Hsieh, Guan-Yan Chen, I-Chieh Chiang, J. Perng
In recent years, brand new vehicles equipped with muti-driving assist systems have been more and more popular. As a result, we propose a path planning design for muti-vehicle driving assist systems that enable vehicle adjust speed and traveling direction according to different road sections by itself. The overall system can be divided into two layers, one is decision layer and the other is control layer. In decision layer, reference route which built by high accuracy real time kinematic differential positioning system is necessary. Then, reference route would be separated into bending and straight sections. After that, desired speed and steering angle can be obtained by kinematics equations and position node of reference route. In control layer, actuators, such as throttle, braking paddle, and steering wheel, are driven by fuzzy logic controller to reach desired speed and steering angle from decision layer. The overall system is implemented on an electric golf car which as a testing platform. The experimental results show that the proposed system integrates kinematic and human experience to fulfill above functions.
{"title":"Path Planning Design for Vehicle Driving Assist Systems","authors":"Ping‐Jui Hsieh, Guan-Yan Chen, I-Chieh Chiang, J. Perng","doi":"10.1109/ICSSE.2018.8520136","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520136","url":null,"abstract":"In recent years, brand new vehicles equipped with muti-driving assist systems have been more and more popular. As a result, we propose a path planning design for muti-vehicle driving assist systems that enable vehicle adjust speed and traveling direction according to different road sections by itself. The overall system can be divided into two layers, one is decision layer and the other is control layer. In decision layer, reference route which built by high accuracy real time kinematic differential positioning system is necessary. Then, reference route would be separated into bending and straight sections. After that, desired speed and steering angle can be obtained by kinematics equations and position node of reference route. In control layer, actuators, such as throttle, braking paddle, and steering wheel, are driven by fuzzy logic controller to reach desired speed and steering angle from decision layer. The overall system is implemented on an electric golf car which as a testing platform. The experimental results show that the proposed system integrates kinematic and human experience to fulfill above functions.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121505579","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520249
Yu-Kun Lin, Bing-Fei Wu, Chia-Meng Chen
The properties of grinding wheel condition for the hard and brittle material thinning equipment (Vertical Wheel Grinder) can be estimated based on the analysis of acoustic emission (AE) signals during grinding process. In this paper, a study on the frequency content of the raw AE signals is carried out to determine the features of frequency bands from three grinding wheels with different grades. The signal characteristics of the surface condition change affected by different wheel grades are obtained from the root mean square (RMS) and ratio of power (ROP) statistics at frequency bands selected from AE spectra. The analyze results indicate that the proposed methodology can distinguish different grades of grinding wheel condition from each raw AE signals segment using the ROP statistics. Thus, based on AE spectra analysis, the raw AE signals contain most of grinding information at the frequency bands of 600~900 kHz. Discrete wavelet transform and RMS statistics are able to describe the change of grinding-wheel-surface condition during grinding process. The findings of this paper proves that this research can be applied to the intelligent grinding monitoring systems in the future [1].
{"title":"Characterization of Grinding Wheel Condition by Acoustic Emission Signals","authors":"Yu-Kun Lin, Bing-Fei Wu, Chia-Meng Chen","doi":"10.1109/ICSSE.2018.8520249","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520249","url":null,"abstract":"The properties of grinding wheel condition for the hard and brittle material thinning equipment (Vertical Wheel Grinder) can be estimated based on the analysis of acoustic emission (AE) signals during grinding process. In this paper, a study on the frequency content of the raw AE signals is carried out to determine the features of frequency bands from three grinding wheels with different grades. The signal characteristics of the surface condition change affected by different wheel grades are obtained from the root mean square (RMS) and ratio of power (ROP) statistics at frequency bands selected from AE spectra. The analyze results indicate that the proposed methodology can distinguish different grades of grinding wheel condition from each raw AE signals segment using the ROP statistics. Thus, based on AE spectra analysis, the raw AE signals contain most of grinding information at the frequency bands of 600~900 kHz. Discrete wavelet transform and RMS statistics are able to describe the change of grinding-wheel-surface condition during grinding process. The findings of this paper proves that this research can be applied to the intelligent grinding monitoring systems in the future [1].","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116831463","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520162
Le Viet Anh, Lê Xuân Hải, Vu Duc Thuan, Pham Van Trieu, L. Tuan, Hoang Manh Cuong
This paper proposes an adaptive control system for uncertain overhead cranes on the basis of hierarchical sliding mode approach combined with radial basis function (RBF) neural network. A sliding surface is defined by linearly combining two sub-manifolds. A RBF neural network is adopted to approximate the unknown dynamic model. The control law is designed to ensure the stability of sliding surfaces while an adaptation mechanism for updating weight matrices of neural network is derived from a candidate of Lyapunov function. Simulation results show the effectiveness of the proposed control scheme.
{"title":"Designing an Adaptive Controller for 3D Overhead Cranes Using Hierarchical Sliding Mode and Neural Network","authors":"Le Viet Anh, Lê Xuân Hải, Vu Duc Thuan, Pham Van Trieu, L. Tuan, Hoang Manh Cuong","doi":"10.1109/ICSSE.2018.8520162","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520162","url":null,"abstract":"This paper proposes an adaptive control system for uncertain overhead cranes on the basis of hierarchical sliding mode approach combined with radial basis function (RBF) neural network. A sliding surface is defined by linearly combining two sub-manifolds. A RBF neural network is adopted to approximate the unknown dynamic model. The control law is designed to ensure the stability of sliding surfaces while an adaptation mechanism for updating weight matrices of neural network is derived from a candidate of Lyapunov function. Simulation results show the effectiveness of the proposed control scheme.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116699591","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：