检索结果-内蒙古大学图书馆

2024 International conference on Intelligent Robots and systems

作者： Yoshimitsu, Yuhei Osa, Takayuki Ben Amor, Heni Ikemoto, Shuhei Kyushu Inst Technol Grad Sch Life Sci & Syst Engn 2-4 Hibikino Kitakyushu Fukuoka Japan Univ Tokyo Grad Sch Informat Sci & Technol 7-3-1 Hongo Tokyo Japan Arizona State Univ Ira A Fulton Sch Engn 699 S Mill Ave 119 Tempe AZ 85281 USA

ISBN: (纸本)9798350377712;9798350377705

In flexible redundantly-driven multi-DOF systems, like living beings, the representation of redundant kinematics including the diversity of solutions, is crucial for leveraging its distinctive characteristics. This paper proposes an active learning framework for forward and inverse modeling of complex kinematics that improves expressions of control space, task space, and null space. It consists of a Variational Auto Encoder (VAE)-type network that internally holds expressions of control space, task space, and null space, and an algorithm for selecting new data using the cross-entropy method. The validity of the proposed system was verified using a tensegrity manipulator driven by 40 pneumatic cylinders. As a result, it was confirmed that active learning contributed to achieving the entire range of motion covered and a well-organized representation of the null space.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Offline data-driven Adaptive Critic Design With Variational Inference for Wastewater Treatment Process control

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2024年第4期21卷 4987-4998页

作者： Qiao, Junfei Yang, Ruyue Wang, Ding Beijing Univ Technol Fac Informat Technol Beijing Key Lab Computat Intelligence & Intelligen Beijing Lab Smart Environm Protect Beijing 100124 Peoples R China Beijing Univ Technol Beijing Inst Artificial Intelligence Beijing 100124 Peoples R China

Wastewater treatment is indispensable to the functioning of urban society, and its optimal control has enormous social benefits. However, precise modelling of the unstable and complex treatment process is challenging yet crucial to the adaptive dynamic programming method. In this article, an adaptive critic algorithm with variational inference is designed to address the optimal control problem of nonlinear discrete-time systems, along with the convergence analysis. Based on the recorded system trajectory, the variational autoencoder is utilized to approximate the behavior policy of the offline dataset without system modelling and online interaction. Through policy iteration learning, the actor-critic structure can amend the policy generated by the variational autoencoder to achieve the optimal control objective. Simulations on a nonlinear system and the wastewater treatment process have verified that the proposed approach outperformed the behavior policy. driven by the wastewater treatment process data derived from the incremental proportional-integral-derivative controller, the proposed approach can produce an optimal control policy of less tracking error and cost. Note to Practitioners-When dealing with an unknown system with complex dynamics, it is more feasible to improve the acceptable performance of the existing control policy based on the system's trajectory than to obtain an excelling policy. Motivated by batch reinforcement learning, learning from offline data can avoid the online interaction between the system and the adaptive dynamic programming algorithm, which could lead to exploratory errors during online learning. Specifically, using a model-free adaptive dynamic programming algorithm, the parameters of the controller are instantly updated based on the experience replay buffer sampled from the online trajectory data. However, online exploration determines the update, and there is no guarantee that the system will converge every time. As a specific typ

关键词： Adaptive dynamic programming offline reinforcement learning data-driven control variational autoencoder wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Gaussian Mixture Model and Double-Weighted Deep Neural Networks for data Augmentation Soft Sensing 12

Gaussian Mixture Model and Double-Weighted Deep Neural Netwo...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Jiang, Xiaoyu Yao, Le Yang, Zeyu Song, Zhihuan Shen, Bingbing Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China Hangzhou Normal Univ Sch Math Hangzhou 311121 Peoples R China Huzhou Univ Sch Engn Huzhou Key Lab Intelligent Sensing & Optimal Cont Huzhou 313000 Peoples R China

ISBN: (纸本)9798350321050

In practice, data-driven soft sensors often face data shortages in modeling. data augmentation technology has offered a feasible solution for this problem in recent years. However, how to better use virtual data for data augmentation is still an open topic. In this paper, a novel data augmentation soft sensing method is proposed. It uses Gaussian mixture models (GMM) to generate virtual data for the training dataset, and developed a double-weighted neural network (dwDNN) for weighted regression modeling. On top of that, the Bayesian optimization algorithm is applied to the weight selection of dwDNN to further enhance the efficiency and effectiveness of GMM-dwDNN on virtual data. In the end, a real industrial case is used to illustrate the superiority of the proposed approach in soft sensing.

关键词： Soft sensor data augmentation Gaussian mixture models Double-weighted neural networks

来源：评论

学校读者我要写书评

暂无评论

Fixed-time synchronization of nonlinear non-affine system 12

Fixed-time synchronization of nonlinear non-affine system

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Liu, Dandan Lv, Hui Zhao, Fuyu Han, Andong Du, Mingjun Qilu Univ Technol Sch Informat Sci & Automat Shandong Acad Sci Jinan 250353 Peoples R China

ISBN: (纸本)9798350321050

This paper concerns with the fixed-time control problem of nonlinear non-affine system. First, based on a Taylor series expansion, the nonlinear non-affine system is transformed into an affine system. Second, by using norm-normalized sign functions and providing sufficient Lyapunov conditions, it is shown that the nonlinear non-affine system can be achieved synchronization in a fixed time, regardless of its initial value. In addition, the settling time is calculated by using an enhanced estimation method. Third, compared with the classical calculate method, a switching sliding-mode control technique is adopted to deal with the possible singularity problem.

关键词： non-affine system Taylor series expansion fixed-time-synchronized enhanced estimation sliding-mode control

来源：评论

学校读者我要写书评

暂无评论

A cyber-security framework for ST-MPC of state and input constrained CPS under false data injection attacks 12

A cyber-security framework for ST-MPC of state and input con...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： He, Ning Li, Yuxiang Ma, Kai Xian Univ Architecture & Technol Sch Mech & Elect Engn Xian Peoples R China

ISBN: (纸本)9798350321050

Self-triggered model predictive control (ST-MPC) is widely applied in various aspects currently, however, the ST-MPC mechanisms that have seldom been developed consider the possible malicious false data injection (FDI) attacks in the cyber-physical system (CPS). Therefore, in this paper, a novel resilient ST-MPC strategy based on input reconstruction (IR) against FDI attacks is proposed for a nonlinear input-affine discrete-time system with state and input constraints, which combines both cyber security and resource consumption. More specifically, when faced with FDI attacks in controller-to-actuator (C-A) channels at the triggering instants, on the actuator side, two key control data are selected to reconstruct input control signals for application into the system, otherwise, the optimal input control signals will be applied into the controlled system. Furthermore, a resilient ST-MPC algorithm with a dual-mode control strategy is proposed, and its closed-loop stability is also analyzed, in which the state constraint is elaborated. Finally, a simulation and its resultant comparisons illustrate the effectiveness of the proposed method.

关键词： Self-triggered model predictive control nonlinear discrete time systems false data injection input reconstruction strategy state constraint

来源：评论

学校读者我要写书评

暂无评论

Speed Tracking control of PMSM Using Adaptive Extended Harmonic State Observer 12

Speed Tracking Control of PMSM Using Adaptive Extended Harmo...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Wang, Xianyu Pang, Zhonghua Guo, Haibin Gao, Shengnan North China Univ Technol Key Lab Fieldbus Technol & Automat Beijing Beijing 100144 Peoples R China Beijing Inst Technol State Key Lab Autonomous Intelligent Unmanned Sys Beijing 100081 Peoples R China

ISBN: (纸本)9798350321050

This paper investigates the speed tracking control issue of a permanent magnet synchronous motor (PMSM). A speed tracking controller based on an adaptive extended harmonic state observer and an extended state observer is proposed under the PMSM non-cascaded structure to suppress multiple disturbances and improve the speed tracking performance. Specifically, an adaptive extended harmonic state observer is designed to estimate mismatched periodic and mismatched aperiodic disturbances with uncertain frequencies, and another extended state observer is developed to estimate matched disturbances. Based on the disturbance estimates, a linear feedback controller is designed to solve the PMSM speed tracking problem under matched and mismatched disturbances. Finally, the effectiveness of the proposed control scheme is verified by the simulation study.

关键词： Permanent magnet synchronous motor (PMSM) adaptive extended harmonic state observer mismatched disturbance periodic disturbances

来源：评论

学校读者我要写书评

暂无评论

data-driven Containment control for Unknown MIMO Nonlinear MASs Under Aperiodic DoS Attacks

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 7762-7772页

作者： Tan, Wen Hou, Zhongsheng Li, Yuan-Xin Qingdao Univ Coll Automat Qingdao 266071 Peoples R China Liaoning Univ Technol Coll Sci Jinzhou 121001 Peoples R China

This paper considers the problem of containment control for multi-input multi-output (MIMO) nonlinear multi-agent systems (MASs) with output saturation and aperiodic denial-of-service (DoS) attacks. By applying the dynamic linearization method, the nonlinear systems are modified to an equivalent linear data model. Based on the inputs and saturated outputs data, a new data-driven containment control algorithm in the presence of aperiodic DoS attacks is developed, which mainly includes the following perspectives: 1) based on the historical information of the MASs, a switched error system is designed to decrease the impact of aperiodic DoS attacks, where the time duration was constrained due to the limitation of attackers' energy;2) the relation between measured error and tracking error is constructed to deal with the difficulties of incomplete data suffered from output saturation;3) with the help of contraction mapping method and mathematical induction approach, the boundedness of containment error is guaranteed by the convergence of the control strategy in such an insecure environment. Numerical simulations are given to validate the effectiveness of the framework. Note to Practitioners-This paper studies the containment control problem for MIMO nonlinear MASs, which has application value in robotic systems, intelligent transportation, multiple spacecraft systems, and other fields. Note that these systems are notably susceptible to network attacks and saturation nonlinearity, which may decrease the system performance or even cause instability. Since the agent dynamics generally are not accurate even unavailable, the existing model-based technologies are inappropriate for MIMO nonlinear MASs. Therefore, in light of the challenge aroused by aperiodic DoS attacks and output saturation, a novel switched error system-based model-free adaptive containment control approach is developed to preserve data integrity while the stability of containment error is guaranteed. Numeric

关键词： Denial-of-service attack data models Adaptation models Switches Nonlinear dynamical systems Mathematical models Iterative learning control Topology Security Protocols Containment control nonlinear MASs model-free adaptive control aperiodic DoS attacks

来源：评论

学校读者我要写书评

暂无评论

Two-stage Anaerobic Digestion Process Optimal control Study based on Extremum-seeking control and Self-optimizing control 12

Two-stage Anaerobic Digestion Process Optimal Control Study ...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Li, Hongxuan Tian, Yang Wang, Haoping Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China

ISBN: (纸本)9798350321050

In this paper, a new dynamic nonlinear gradient observer-based extremum-seeking control algorithm (DNGO-based ESC) and a dynamic Jacobian matrices estimator-based self-optimizing control algorithm (DJE-based SOC) are designed for the control of two-stage anaerobic digestion (TSAD). None of two algorithms requires priori knowledge about the system model. The proposed algorithms are compared with the classical extremum-seeking control algorithm and the Kalman Filter based Newton extremum-seeking control algorithm. The simulation results show that in the presence of disturbance both of proposed control algorithms can maintain the system at the optimal operating point and drive the hydrogen and methane yields to the extreme point. Future work is to validate the designed control algorithm in an actual two-stage anaerobic digestion process.

关键词： anaerobic digestion extremum-seeking control self-optimizing control model-free control

来源：评论

学校读者我要写书评

暂无评论

Hidden Markov model based finite-time H∞ guaranteed cost control for singular discrete-time Markov jump delay systems 12

Hidden Markov model based finite-time H∞ guaranteed cost co...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Chen, Zhiwen Li, Bo Zhao, Junjie Li, Feng Du, Youwu Jiangsu Univ Technol Sch Elect & Informat Engn Changzhou 213001 Jiangsu Peoples R China

ISBN: (纸本)9798350321050

Considering partially known transition rates and saturating actuators, the finite-time H-infinity control problem for a class of singular discrete-time Markovian jump delayed systems is studied in this article. First, by employing local sector conditions and an appropriate Lyapunov function, a hidden Markov model based state feedback controller is designed to guarantee that the resulted closed-loop constrained system is mean-square locally finite-time stabilizable, and the closed-loop cost function value is not more than a specified upper bound. Furthermore, some sufficient conditions for the solution to this problem are derived in terms of linear matrix inequalities. Finally, a numerical example is provided to demonstrate the effectiveness of proposed method.

关键词： Finite-time control guaranteed cost control input saturation partially known transition rates time-varying delay

来源：评论

学校读者我要写书评

暂无评论

Safety Predefined-Time Tracking control of Second-Order Nonlinear systems 12

Safety Predefined-Time Tracking Control of Second-Order Nonl...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Xu, Yang Sun, Yuan Chen, Yiyang Tao, Hongfeng Soochow Univ Sch Mech & Elect Engn Suzhou 215137 Peoples R China Jiangnan Univ Key Lab Adv Proc Control Light Ind Minist Educ Wuxi 214122 Jiangsu Peoples R China

ISBN: (纸本)9798350321050

This paper examines a category of second-order nonlinear systems' predefined-time tracking control issue restricted by the state and input from the control. The safety predefined-time control framework proposed by this work aims at tracking a desired trajectory in a predefined time while maintaining safe system outputs and control inputs. The safety predefined-time controller is specifically created by a safety filter utilizing the control barrier function approach and a predefined-time controller on the basis of the backstepping technique. The predefined-time controller establishes an explicit relation between the controller parameters and the convergence time constraint. Moreover, the safety filter enforces the state and control input constraints by constructing a quadratic programming problem. In an effort to demonstrate the feasibility of the safety predefined-time controller, a second-order practical system is simulated.

关键词： Predefined-time control Backstepping control Safety controller control barrier function

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：