To improve the prediction accuracy of water quality indexes such as BOD (Biochemical Oxygen Demand) in wastewater treatment process, a novel soft sensor modeling method based on support vector machine (SVM) is designed. The Gaussian kernel function is configured for the proposed method, and the grid search method is combined with K-fold cross-validation to search the optimal values of Gamma and C parameters, thereby improving the prediction accuracy of the proposed model. Finally, the method is tested by using the production data of wastewater treatment. The experimental results show that the proposed model has high prediction accuracy, which provides an effective method for guiding practical production.
{"title":"Research on Soft Sensor Modeling of Support Vector Machine for Wastewater Treatment","authors":"Mingzhu Li, Hongchao Cheng, Xiaojuan Wang, Jiaxian Qin","doi":"10.1109/CACRE58689.2023.10208469","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208469","url":null,"abstract":"To improve the prediction accuracy of water quality indexes such as BOD (Biochemical Oxygen Demand) in wastewater treatment process, a novel soft sensor modeling method based on support vector machine (SVM) is designed. The Gaussian kernel function is configured for the proposed method, and the grid search method is combined with K-fold cross-validation to search the optimal values of Gamma and C parameters, thereby improving the prediction accuracy of the proposed model. Finally, the method is tested by using the production data of wastewater treatment. The experimental results show that the proposed model has high prediction accuracy, which provides an effective method for guiding practical production.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115931657","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 paper proposes a finite-time prescribed performance containment control method for multiple autonomous underwater vehicles (AUVs) with uncertainty and disturbance. The control law is designed based on the conversion error derived from the prescribed performance control (PPC) framework. A new finite-time performance function, instead of exponential decay function, is used for error transformation, which enables the containment error converges in a finite time. The model uncertainty is approximated using the radial basis function neural networks (RBFNN), and the external disturbance is compensated with the unknow boundary being estimated using the adaptive approach. The simulation results confirm the validity of the proposed control protocol.
{"title":"Finite-time Containment Control for Autonomous Underwater Vehicles with Prescribed Performance","authors":"Zilong Song, Zheyuan Wu, Qing Wang, Miao Xie, Haocai Huang","doi":"10.1109/CACRE58689.2023.10208674","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208674","url":null,"abstract":"This paper proposes a finite-time prescribed performance containment control method for multiple autonomous underwater vehicles (AUVs) with uncertainty and disturbance. The control law is designed based on the conversion error derived from the prescribed performance control (PPC) framework. A new finite-time performance function, instead of exponential decay function, is used for error transformation, which enables the containment error converges in a finite time. The model uncertainty is approximated using the radial basis function neural networks (RBFNN), and the external disturbance is compensated with the unknow boundary being estimated using the adaptive approach. The simulation results confirm the validity of the proposed control protocol.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134286184","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}
A phase modulation method for remote guidance faults in autonomous and quick rendezvous and docking is proposed. According to position and attitude navigation information, ground fault judgment instructions, various fault modes corresponding to different autonomous quick rendezvous and docking fault conditions are given. The chaser spacecraft is guided to the frozen orbit behind the target spacecraft by using the two impulses orbit change strategy for typical fault modes. After the fault is removed, new rendezvous and docking can be achieved by guidance from ground for one or two days according to the current phase angle.
{"title":"A Fault Handling Scheme for Remote Guidance of Autonomous Quick Rendezvous and Docking","authors":"Changqing Cheng, Yongchun Xie, Zhang Qiang, Zhang Hao","doi":"10.1109/CACRE58689.2023.10208304","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208304","url":null,"abstract":"A phase modulation method for remote guidance faults in autonomous and quick rendezvous and docking is proposed. According to position and attitude navigation information, ground fault judgment instructions, various fault modes corresponding to different autonomous quick rendezvous and docking fault conditions are given. The chaser spacecraft is guided to the frozen orbit behind the target spacecraft by using the two impulses orbit change strategy for typical fault modes. After the fault is removed, new rendezvous and docking can be achieved by guidance from ground for one or two days according to the current phase angle.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130839695","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 : 2023-07-01DOI: 10.1109/CACRE58689.2023.10208829
Ziyuan Ma, Huajun Gong, Xinhua Wang
Unmanned Aerial Vehicles (UAVs) represent a typical example of underactuated and strongly coupled nonlinear systems, renowned for their high speed, maneuverability, and endurance, making them a prominent research focus in the fields of national defense and air defense. However, controlling a fixed-wing UAV poses challenges due to its susceptibility to external interference and the inherent complexity of the flight environment. To address these challenges, this study adopts a novel approach based on the gated cyclic convolutional neural network (GCCNN) architecture. By leveraging the unique structure of GCCNN, this research successfully solves the four control input signals of a fixed-wing UAV and employs the gated convolutional neural network for trajectory control and prediction. The utilization of cyclic convolution offers distinct advantages, enhancing the accuracy of UAV trajectory prediction and improving the overall trajectory prediction effectiveness.
{"title":"Trajectory Tracking Prediction of Multiple-UAVs Formation Based on Gated Cyclic Convolution Neural Network","authors":"Ziyuan Ma, Huajun Gong, Xinhua Wang","doi":"10.1109/CACRE58689.2023.10208829","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208829","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) represent a typical example of underactuated and strongly coupled nonlinear systems, renowned for their high speed, maneuverability, and endurance, making them a prominent research focus in the fields of national defense and air defense. However, controlling a fixed-wing UAV poses challenges due to its susceptibility to external interference and the inherent complexity of the flight environment. To address these challenges, this study adopts a novel approach based on the gated cyclic convolutional neural network (GCCNN) architecture. By leveraging the unique structure of GCCNN, this research successfully solves the four control input signals of a fixed-wing UAV and employs the gated convolutional neural network for trajectory control and prediction. The utilization of cyclic convolution offers distinct advantages, enhancing the accuracy of UAV trajectory prediction and improving the overall trajectory prediction effectiveness.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126221119","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 : 2023-07-01DOI: 10.1109/CACRE58689.2023.10208534
Balamurugan Ramachandran, Scott Mayberry, Fumin Zhang
Underwater robots, despite their wide applications, struggle with localization and navigation in GPS-free environments, a problem potentially solvable by acoustic sensor modules. However, to counteract sensor bias caused by varying factors, the Particle filter algorithm, which employs measurement and motion models for location determination, can be applied and real-time tested for model weight adjustments.In our work, we have developed a Particle Filter Algorithm that takes in the time of arrival of beacon pings as input and uses it to calculate the current position of the robot through a time of arrival particle filter method. We successfully tested the particle filter in a simulated environment by creating an observation model using beacon pings.Our resulting Particle filter algorithm can successfully track a simulated robot with high levels of accuracy within a reasonable run time. In the future, we aim to test the filtering method in real-life scenarios to prove the efficacy of this method in open-water arenas.
{"title":"Acoustic Localization of Underwater Robots: A Time of Arrival-Based Particle Filter Approach Using Asynchronous Beacon Pinging","authors":"Balamurugan Ramachandran, Scott Mayberry, Fumin Zhang","doi":"10.1109/CACRE58689.2023.10208534","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208534","url":null,"abstract":"Underwater robots, despite their wide applications, struggle with localization and navigation in GPS-free environments, a problem potentially solvable by acoustic sensor modules. However, to counteract sensor bias caused by varying factors, the Particle filter algorithm, which employs measurement and motion models for location determination, can be applied and real-time tested for model weight adjustments.In our work, we have developed a Particle Filter Algorithm that takes in the time of arrival of beacon pings as input and uses it to calculate the current position of the robot through a time of arrival particle filter method. We successfully tested the particle filter in a simulated environment by creating an observation model using beacon pings.Our resulting Particle filter algorithm can successfully track a simulated robot with high levels of accuracy within a reasonable run time. In the future, we aim to test the filtering method in real-life scenarios to prove the efficacy of this method in open-water arenas.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126349522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The unmanned aerial vehicle (UAV) requires the control system with fast response speed, high accuracy and strong robustness. Due to the strong coupling and nonlinearity of UAV system, it is difficult to build the accurate system model, which makes it difficult for traditional linear control methods to achieve accurate and stable control effects. This paper proposes an intelligent attitude control method for high-speed UAV. Firstly, the nonlinear attitude motion model of UAV is established and a new intelligent attitude controller structure is built based on the Deep Deterministic Policy Gradient (DDPG) algorithm. Secondly, the DDPG attitude controller is trained by the simulation training system. The control simulation results show that the proposed intelligent control system and controller can meet the requirements of attitude adjustment and attitude stabilization, the control accuracy error is less than 0.02 degree. Finally, considering fixed mutation interference, Gaussian noise and 50% deviation of aerodynamic parameters disturbance, the control accuracy error is still less than 0.1 degree during the interference test. The stability analysis shows that the intelligent controller has strong robustness and generalization ability.
{"title":"An Intelligent Attitude Control Method for UAV Based on DDPG Algorithm","authors":"Y.X. Xian, Peng Wang, Hongbo Xin, Yujie Wang, Qing-yang Chen, Z. Hou","doi":"10.1109/CACRE58689.2023.10208439","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208439","url":null,"abstract":"The unmanned aerial vehicle (UAV) requires the control system with fast response speed, high accuracy and strong robustness. Due to the strong coupling and nonlinearity of UAV system, it is difficult to build the accurate system model, which makes it difficult for traditional linear control methods to achieve accurate and stable control effects. This paper proposes an intelligent attitude control method for high-speed UAV. Firstly, the nonlinear attitude motion model of UAV is established and a new intelligent attitude controller structure is built based on the Deep Deterministic Policy Gradient (DDPG) algorithm. Secondly, the DDPG attitude controller is trained by the simulation training system. The control simulation results show that the proposed intelligent control system and controller can meet the requirements of attitude adjustment and attitude stabilization, the control accuracy error is less than 0.02 degree. Finally, considering fixed mutation interference, Gaussian noise and 50% deviation of aerodynamic parameters disturbance, the control accuracy error is still less than 0.1 degree during the interference test. The stability analysis shows that the intelligent controller has strong robustness and generalization ability.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"2019 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121411717","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 : 2023-07-01DOI: 10.1109/CACRE58689.2023.10208497
Yalu Zhu, Shi Lian, WenTao Zhong, Wei Meng
In this paper, a model-free reinforcement learning(RL) method of training a nonlinear attitude controller of a quadrotor is proposed. For the problem that the attitude controller is uncontrolled when trained by RL directly, the proposed method utilizes an expert to provide the prior information, i.e. the action’s judgement and suggestion, to guide the updating process. For the problem that the policy falls in local optima by the limitation of the expert, the proposed method maximize the entropy of the strategy to increase the exploratory behavior of the nonlinear attitude controller approximator. Furthermore, We employ the Proximal policy optimization algorithm (PPO) as the RL model and PID algorithm as the expert model to approach an exact attitude controller of a quadrotor based on the proposed method. Finally, the simulations experiments has been conducted to verify that our proposed method can train a true nonlinear attitude controller which has a better performance than the expert.
{"title":"A Reinforcement Learning Method for Quadrotor Attitude Control Based on Expert Information","authors":"Yalu Zhu, Shi Lian, WenTao Zhong, Wei Meng","doi":"10.1109/CACRE58689.2023.10208497","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208497","url":null,"abstract":"In this paper, a model-free reinforcement learning(RL) method of training a nonlinear attitude controller of a quadrotor is proposed. For the problem that the attitude controller is uncontrolled when trained by RL directly, the proposed method utilizes an expert to provide the prior information, i.e. the action’s judgement and suggestion, to guide the updating process. For the problem that the policy falls in local optima by the limitation of the expert, the proposed method maximize the entropy of the strategy to increase the exploratory behavior of the nonlinear attitude controller approximator. Furthermore, We employ the Proximal policy optimization algorithm (PPO) as the RL model and PID algorithm as the expert model to approach an exact attitude controller of a quadrotor based on the proposed method. Finally, the simulations experiments has been conducted to verify that our proposed method can train a true nonlinear attitude controller which has a better performance than the expert.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116197101","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 : 2023-07-01DOI: 10.1109/cacre58689.2023.10209045
{"title":"Sponsors","authors":"","doi":"10.1109/cacre58689.2023.10209045","DOIUrl":"https://doi.org/10.1109/cacre58689.2023.10209045","url":null,"abstract":"","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116778266","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 : 2023-07-01DOI: 10.1109/CACRE58689.2023.10209036
Ding Yan, Jiajian He, Shuchen He, Yang Chen
This paper deals with the assignment problem of multiple robot with the rectangular spaying tasks. Without pointing to the starting points of each task, the upper left vertex, the upper right vertex, the lower left vertex and the lower right vertex are selected by the genetic algorithm. The ergodic-based genetic algorithm is designed to achieve the shortest time and the lowest path cost. The improved mutation operator is set to accelerate the convergence process and improve the practicability of the proposed algorithm. Compared with the strategy of market-based algorithm, the genetic algorithm reduces the average time cost by 16.98% and distance costs by 9.05%, respectively.
{"title":"Rectangular Spraying Task Assignment Via a Genetic Algorithm","authors":"Ding Yan, Jiajian He, Shuchen He, Yang Chen","doi":"10.1109/CACRE58689.2023.10209036","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10209036","url":null,"abstract":"This paper deals with the assignment problem of multiple robot with the rectangular spaying tasks. Without pointing to the starting points of each task, the upper left vertex, the upper right vertex, the lower left vertex and the lower right vertex are selected by the genetic algorithm. The ergodic-based genetic algorithm is designed to achieve the shortest time and the lowest path cost. The improved mutation operator is set to accelerate the convergence process and improve the practicability of the proposed algorithm. Compared with the strategy of market-based algorithm, the genetic algorithm reduces the average time cost by 16.98% and distance costs by 9.05%, respectively.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125652439","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 : 2023-07-01DOI: 10.1109/CACRE58689.2023.10208583
Lei Ju, Zhiwei Wang, Anqing Wang, Xiaotong Zhou
This paper focuses on exploring the problem of achieving leader-follower consensus in uncertain Euler-Lagrange multi-agent systems, which are subjected to disturbance, and operate on switched digraph. To be more precise, the system dynamics are characterized by uncertainties that can be linearly parameterized, and the disturbances that are considered are those originating from the leader system. A novel adaptive distributed control strategy is proposed to overcome the difficulties of suppressing disturbances and achieving consistency under the condition of joint connectivity of switched digraphs. By using Lyapunov stability theory and the generalized Barbalat's lemma, it is proved that the uncertain Euler-Lagrange multi-agent systems achieves state consensus asymptotically with the proposed distributed adaptive control protocol. The efficacy of the adaptive distributed control strategy proposed in the paper is validated by presenting a case study involving a system composed of four double-link manipulators.
{"title":"Consensus of Uncertain Euler-Lagrange Multi-agent Systems under Switching Digraphs and Disturbances","authors":"Lei Ju, Zhiwei Wang, Anqing Wang, Xiaotong Zhou","doi":"10.1109/CACRE58689.2023.10208583","DOIUrl":"https://doi.org/10.1109/CACRE58689.2023.10208583","url":null,"abstract":"This paper focuses on exploring the problem of achieving leader-follower consensus in uncertain Euler-Lagrange multi-agent systems, which are subjected to disturbance, and operate on switched digraph. To be more precise, the system dynamics are characterized by uncertainties that can be linearly parameterized, and the disturbances that are considered are those originating from the leader system. A novel adaptive distributed control strategy is proposed to overcome the difficulties of suppressing disturbances and achieving consistency under the condition of joint connectivity of switched digraphs. By using Lyapunov stability theory and the generalized Barbalat's lemma, it is proved that the uncertain Euler-Lagrange multi-agent systems achieves state consensus asymptotically with the proposed distributed adaptive control protocol. The efficacy of the adaptive distributed control strategy proposed in the paper is validated by presenting a case study involving a system composed of four double-link manipulators.","PeriodicalId":447007,"journal":{"name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115268958","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：