Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619325
Zhao Yinxiang, H. Yuqing
In this paper, the formation control problem is considered for two-wheeled agents, and both the control input constraint problem and the rollover problem due to two-wheel driving are considered. We design the distributed distance-based control law under an undirected and a directed perceptual topology graph, respectively. Our proposed control method does not require a global coordinate system, and each agent only needs to use its local coordinate system. Finally, we provide some simulation results to verify the effectiveness of the formation control method proposed in this paper.
{"title":"A Formation Control Approach Considering Rollover Avoidance for Two-wheeled Mobile Agents","authors":"Zhao Yinxiang, H. Yuqing","doi":"10.1109/IAI53119.2021.9619325","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619325","url":null,"abstract":"In this paper, the formation control problem is considered for two-wheeled agents, and both the control input constraint problem and the rollover problem due to two-wheel driving are considered. We design the distributed distance-based control law under an undirected and a directed perceptual topology graph, respectively. Our proposed control method does not require a global coordinate system, and each agent only needs to use its local coordinate system. Finally, we provide some simulation results to verify the effectiveness of the formation control method proposed in this paper.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122973307","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619450
Tao Zhang, Honglin Li, Xu-Yen Tu, Huizhen Pang, Yu Huang
Aiming at the parameter optimization problem of the state of charge (SOC) PID adjustment method of the soild oxide fuel cell (SOFC), in the analysis of the SOFC adjustment system characteristics and PID parameter optimization fitness function based on the improved firefly algorithm, a fractional PID parameter optimization model of SOC control is established. For the 6.6% voltage disturbance simulation test without external load and the 25% external load current disturbance test, the optimal solutions of fractional PID and conventional PID under the improved Firefly algorithm and the standard Firefly algorithm are obtained. The research shows that the optimal solution of fractional PID parameters obtained by the improved Firefly algorithm not only has a smaller overshoot under disturbance, but also a shorter transition process time, which is more conducive to SOC control.
{"title":"Optimization of SOC fractional PID control parameters for solid oxide battery based on improved firefly algorithm","authors":"Tao Zhang, Honglin Li, Xu-Yen Tu, Huizhen Pang, Yu Huang","doi":"10.1109/IAI53119.2021.9619450","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619450","url":null,"abstract":"Aiming at the parameter optimization problem of the state of charge (SOC) PID adjustment method of the soild oxide fuel cell (SOFC), in the analysis of the SOFC adjustment system characteristics and PID parameter optimization fitness function based on the improved firefly algorithm, a fractional PID parameter optimization model of SOC control is established. For the 6.6% voltage disturbance simulation test without external load and the 25% external load current disturbance test, the optimal solutions of fractional PID and conventional PID under the improved Firefly algorithm and the standard Firefly algorithm are obtained. The research shows that the optimal solution of fractional PID parameters obtained by the improved Firefly algorithm not only has a smaller overshoot under disturbance, but also a shorter transition process time, which is more conducive to SOC control.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"338 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122750041","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619230
Yu-quan Zhang, Chengxin Xian, Yu Zhao
This paper focuses on solving distributed optimization problems with local nonlinear inequality constraints in a specified-time over undirected graph. Here, we present a distributed optimization algorithm with specified-time. It can be used for the multi-agent network to minimize the sum of local objective functions. The establishment of specified-time in the proposed algorithm is independent of initial conditions and algorithm parameters. This is a completely distributed algorithm, which only needs information interaction between adjacent agents to complete the specified-time optimization problem. The effectiveness of the proposed theory is demonstrated by an example of resource allocation.
{"title":"Solving specified-time distributed optimization problem with local inequality constraint based on penalty method","authors":"Yu-quan Zhang, Chengxin Xian, Yu Zhao","doi":"10.1109/IAI53119.2021.9619230","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619230","url":null,"abstract":"This paper focuses on solving distributed optimization problems with local nonlinear inequality constraints in a specified-time over undirected graph. Here, we present a distributed optimization algorithm with specified-time. It can be used for the multi-agent network to minimize the sum of local objective functions. The establishment of specified-time in the proposed algorithm is independent of initial conditions and algorithm parameters. This is a completely distributed algorithm, which only needs information interaction between adjacent agents to complete the specified-time optimization problem. The effectiveness of the proposed theory is demonstrated by an example of resource allocation.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171307","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619356
J. Viola, Y. Chen
Industry 4.0 requires introducing smart capabilities into the classic process control that makes the system aware of its current health status, modifying its closed-loop controller parameters or references to ensure the optimal performance of a system under acceptable conditions. This paper presents a Self Optimizing Control (SOC) framework using a Real-Time Globalized Constrain Nelder Mead optimization algorithm supported by the system closed-loop performance specification to control a thermal system. A simulation benchmark is designed to assess the SOC controller performance using a normalized First Order Plus Dead Time model of the thermal system. Obtained results show that the SOC controller can reach the desired closed-loop performance after multiple periodic reference executions of the system.
{"title":"A Self Optimizing Control Framework and A Benchmark for Smart Process Control","authors":"J. Viola, Y. Chen","doi":"10.1109/IAI53119.2021.9619356","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619356","url":null,"abstract":"Industry 4.0 requires introducing smart capabilities into the classic process control that makes the system aware of its current health status, modifying its closed-loop controller parameters or references to ensure the optimal performance of a system under acceptable conditions. This paper presents a Self Optimizing Control (SOC) framework using a Real-Time Globalized Constrain Nelder Mead optimization algorithm supported by the system closed-loop performance specification to control a thermal system. A simulation benchmark is designed to assess the SOC controller performance using a normalized First Order Plus Dead Time model of the thermal system. Obtained results show that the SOC controller can reach the desired closed-loop performance after multiple periodic reference executions of the system.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115495733","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619235
Yutong Liu, Ning Chen, Chuang Yang, Haocong Ji
With growing traffic needs, it has become an inevitable trend to apply information, communication, and control to the field of transportation. In real-time communication process, the coordination between satellites and logistics trucks requires precise position information for phased array antenna alignment. However, in mountain areas and forests with weak GPS signals, the information provided by GPS often has coordinate deviations caused by environmental and measurement noise. Therefore, it is difficult to provide accurate location information for phased array antenna alignment. Considering the above problems, this paper firstly compares the mean square error of the Kalman filter algorithm under the constant acceleration(CA) motion model and the Singer motion model, and analyze their respective adaptation environments. Then a Kalman filter is applied to a phased-array antenna alignment. This method mainly uses the latitude and longitude coordinate information to predict trajectory, and analyzes the off-axis angle error and the phase error in the antenna alignment. The results show that the coordinate error fluctuation amplitude of this algorithm is low, and the converge time is short. After being applied to the antenna alignment, it effectively reduces the off-axis angle error and the phase error. It is indicated that the application of Kalman filter algorithm can control these two kinds of errors within a range, which has little impact on the selection of the antenna array.
{"title":"Error Analysis of Kalman Filter Applied to Phased Array Antenna Alignment","authors":"Yutong Liu, Ning Chen, Chuang Yang, Haocong Ji","doi":"10.1109/IAI53119.2021.9619235","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619235","url":null,"abstract":"With growing traffic needs, it has become an inevitable trend to apply information, communication, and control to the field of transportation. In real-time communication process, the coordination between satellites and logistics trucks requires precise position information for phased array antenna alignment. However, in mountain areas and forests with weak GPS signals, the information provided by GPS often has coordinate deviations caused by environmental and measurement noise. Therefore, it is difficult to provide accurate location information for phased array antenna alignment. Considering the above problems, this paper firstly compares the mean square error of the Kalman filter algorithm under the constant acceleration(CA) motion model and the Singer motion model, and analyze their respective adaptation environments. Then a Kalman filter is applied to a phased-array antenna alignment. This method mainly uses the latitude and longitude coordinate information to predict trajectory, and analyzes the off-axis angle error and the phase error in the antenna alignment. The results show that the coordinate error fluctuation amplitude of this algorithm is low, and the converge time is short. After being applied to the antenna alignment, it effectively reduces the off-axis angle error and the phase error. It is indicated that the application of Kalman filter algorithm can control these two kinds of errors within a range, which has little impact on the selection of the antenna array.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115820953","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619200
Tsung-Hsi Tsai, Qing Li
In this paper, we propose a mapless autonomous navigation planner which plans a collision-free trajectory for quadrotor without any manual operations. Deep Reinforcement Learning (DRL) can optimize the policy by trial and error without knowing the prior information of the environment. The designed reward function has better convergence which compares to the benchmark method. The learned policy makes a real time collision free trajectory which can cope with the dynamic obstacles under different scenarios. The evaluation result shows that the trained model can be applied directly to the unknown environment without retraining the agent.
{"title":"Quadrotor Mapless Navigation in Static and Dynamic Environments based on Deep Reinforcement Learning","authors":"Tsung-Hsi Tsai, Qing Li","doi":"10.1109/IAI53119.2021.9619200","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619200","url":null,"abstract":"In this paper, we propose a mapless autonomous navigation planner which plans a collision-free trajectory for quadrotor without any manual operations. Deep Reinforcement Learning (DRL) can optimize the policy by trial and error without knowing the prior information of the environment. The designed reward function has better convergence which compares to the benchmark method. The learned policy makes a real time collision free trajectory which can cope with the dynamic obstacles under different scenarios. The evaluation result shows that the trained model can be applied directly to the unknown environment without retraining the agent.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130637009","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619406
Shenyu Su, Daofu Guo, An Chen, Jiaqi Yun, Yichuan Wang, Zhigang Ren
By remarkably reducing real fitness evaluations, surrogate-assisted evolutionary algorithms (SAEAs) have been successfully applied to expensive optimization problems. However, existing SAEAs generally ignore the widespread simulation evaluation noise when constructing surrogate models, which severely limits their robustness and applications. To alleviate this issue, this study proposes a robust SAEA based on maximum correntropy criterion (MCC). MCC can robustly measure the similarity between two random variables by weakening the negative influence of outlier data. With it as the loss function, the trained surrogate model thus could have a good tolerance of the simulation evaluation noise. Taking the radial basis function (RBF) as the basic surrogate model and the differential evolution (DE) algorithm as the optimizer, this study then develops a specific SAEA named MCC-RBF-DE. Comprehensive experimental results on various benchmark functions with evaluation noise show that the introduction of MCC can effectively suppress the influence of noise. Moreover, MCC-RBF-DE shows stronger robustness compared to traditional SAEAs.
{"title":"A Robust Surrogate-assisted Evolutionary Algorithm based on Maximum Correntropy Criterion⋆","authors":"Shenyu Su, Daofu Guo, An Chen, Jiaqi Yun, Yichuan Wang, Zhigang Ren","doi":"10.1109/IAI53119.2021.9619406","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619406","url":null,"abstract":"By remarkably reducing real fitness evaluations, surrogate-assisted evolutionary algorithms (SAEAs) have been successfully applied to expensive optimization problems. However, existing SAEAs generally ignore the widespread simulation evaluation noise when constructing surrogate models, which severely limits their robustness and applications. To alleviate this issue, this study proposes a robust SAEA based on maximum correntropy criterion (MCC). MCC can robustly measure the similarity between two random variables by weakening the negative influence of outlier data. With it as the loss function, the trained surrogate model thus could have a good tolerance of the simulation evaluation noise. Taking the radial basis function (RBF) as the basic surrogate model and the differential evolution (DE) algorithm as the optimizer, this study then develops a specific SAEA named MCC-RBF-DE. Comprehensive experimental results on various benchmark functions with evaluation noise show that the introduction of MCC can effectively suppress the influence of noise. Moreover, MCC-RBF-DE shows stronger robustness compared to traditional SAEAs.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128900719","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619415
Yongwei Zhang, Shunchao Zhang, Bo Zhao, Qiuye Wu, Derong Liu
This paper investigates zero-sum game problems of nonlinear multi-player systems by using adaptive dynamic programming-based event-triggered control method. To begin with, a cost function which contains all the control inputs and the disturbance is designed. For the purpose of reducing the computation and communication burdens, a novel triggering condition which is suitable to multiple controllers is derived by using Lyapunov’s direct method. It is noticed that the control laws and the disturbance laws are updated when the triggering condition is violated only to save computational resources. Theoretical analysis shows that the developed triggering condition guarantees the uniform ultimate boundedness of the closed-loop system. Finally, simulation example is provided to validate the effectiveness of the developed method.
{"title":"Event-Triggered Control of Multi-Player Zero-Sum Games via Adaptive Dynamic Programming","authors":"Yongwei Zhang, Shunchao Zhang, Bo Zhao, Qiuye Wu, Derong Liu","doi":"10.1109/IAI53119.2021.9619415","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619415","url":null,"abstract":"This paper investigates zero-sum game problems of nonlinear multi-player systems by using adaptive dynamic programming-based event-triggered control method. To begin with, a cost function which contains all the control inputs and the disturbance is designed. For the purpose of reducing the computation and communication burdens, a novel triggering condition which is suitable to multiple controllers is derived by using Lyapunov’s direct method. It is noticed that the control laws and the disturbance laws are updated when the triggering condition is violated only to save computational resources. Theoretical analysis shows that the developed triggering condition guarantees the uniform ultimate boundedness of the closed-loop system. Finally, simulation example is provided to validate the effectiveness of the developed method.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121066630","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619251
Li Kang, Yang Cui-li, Qiao Jun-fei
Aiming at the characteristics of high coupling degree, strong nonlinearity, and serious time delay in the measurement of ammonia nitrogen concentration in wastewater treatment process (WWTP), a prediction model of ammonia nitrogen concentration based on gray relational analysis (GRA) and time convolution network (TCN) was proposed. Firstly, based on the relevant water quality parameters collected in WWTP, the grey correlation analysis method was used to find out other characteristic variables highly related to the ammonia nitrogen concentration. Then, a new group of multivariate time series data was constructed by using the sliding window method. Finally, based on the advantages of the time convolution network in processing time series data, such as simple, flexible, and easy to parallel, the constructed time series data were modeled to predict the concentration of effluent ammonia-nitrogen. To verify the validity of the model, the predicted results were compared with the other four models. The experimental results show that the ammonia-nitrogen concentration prediction model based on GRA and TCN has good prediction performance, which is helpful to realize the accurate prediction of effluent ammonia-nitrogen concentration. At the same time, it can also provide timely and effective guidance for the control and optimization of the wastewater treatment process.
{"title":"Research on Forecasting Method for Effluent Ammonia Nitrogen Concentration Based on GRA-TCN","authors":"Li Kang, Yang Cui-li, Qiao Jun-fei","doi":"10.1109/IAI53119.2021.9619251","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619251","url":null,"abstract":"Aiming at the characteristics of high coupling degree, strong nonlinearity, and serious time delay in the measurement of ammonia nitrogen concentration in wastewater treatment process (WWTP), a prediction model of ammonia nitrogen concentration based on gray relational analysis (GRA) and time convolution network (TCN) was proposed. Firstly, based on the relevant water quality parameters collected in WWTP, the grey correlation analysis method was used to find out other characteristic variables highly related to the ammonia nitrogen concentration. Then, a new group of multivariate time series data was constructed by using the sliding window method. Finally, based on the advantages of the time convolution network in processing time series data, such as simple, flexible, and easy to parallel, the constructed time series data were modeled to predict the concentration of effluent ammonia-nitrogen. To verify the validity of the model, the predicted results were compared with the other four models. The experimental results show that the ammonia-nitrogen concentration prediction model based on GRA and TCN has good prediction performance, which is helpful to realize the accurate prediction of effluent ammonia-nitrogen concentration. At the same time, it can also provide timely and effective guidance for the control and optimization of the wastewater treatment process.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203449","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：