检索结果-内蒙古大学图书馆

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Wang, Diandian Xiong, Shuangshuang Cao, Shuang School of Automation Beijing Information Science and Technology University Beijing100192 China

ISBN: (纸本)9798350361674

A control scheme based on model-free adaptive control (MFAC) is presented for the input-constrained problem in this paper. Firstly, an equivalent linear system is established using the dynamic linearisation method. A novel dynamic compensator is applied in the controller design to overcome the input-constrained saturation problem. Then on this basis, the relationship between the input constrainted before and after is also introduced to simplify the operation. Furthermore, the tracking error signal is shown to converge asymptotically in the stability analysis section. At last, the system is simulated to verify the effectiveness of the control algorithm. © 2024 ieee.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Tool wear state identification based on frequency domain denoising and frequencies-separation attention networks 12

Tool wear state identification based on frequency domain den...

引用

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

作者： Lai, Xuwei Zhang, Kai Li, Zhixuan Zheng, Qing Ding, Guofu Southwest Jiaotong Univ Sch Mech Engn Chengdu 610031 Peoples R China Southwest Jiaotong Univ Technol & Equipment Rail Transit Operat & Mainten Chengdu 610031 Peoples R China

ISBN: (纸本)9798350321050

Real-time and accurate monitoring of tool wear is an important link to realizing intelligent manufacturing, which has an important impact on product quality and production cost. Due to its convenience and strong nonlinear mapping capability, deep learning has attracted extensive attention in the field of tool wear monitoring. However, the monitoring signal in the machining process will inevitably be interfered with by the noise from the machine tool, which will affect the models' reliability and optimization. In this work, the effectiveness of monitoring signals is analyzed, and a machine tool inherent characteristic frequency interception method and a time-frequency domain decoupling technique based on wavelet transform with tunable Q-factor are introduced to perform targeted noise removal during machining. The method is naturally interpretable. Meanwhile, a frequency-separation attention mechanism is proposed to weigh the frequency at different stages adaptively. The validity of the proposed method is verified by using real machining data. And the interpretability of the model is briefly analyzed.

关键词： tool wear state recognition interpretable deep learning attention mechanism frequency analysis

来源：评论

学校读者我要写书评

暂无评论

data-driven control Design With LMIs and Dynamic Programming

引用

ieee ACCESS 2023年 11卷 14309-14321页

作者： Lee, Donghwan Kim, Do Wan Korea Adv Inst Sci & Technol Dept Elect Engn Daejeon South Korea Hanbat Natl Univ Dept Elect Engn Daejeon South Korea

The goal of this paper is to study model-free data-driven control evaluation and design strategies for discrete-time linear time-invariant systems, where the system model is unknown. In particular, our main contribution is twofold: 1) new state-input exploration and data collection schemes from experiences;2) new data-driven linear matrix inequalities and dynamic programming methods for stabilization and optimal control problems. The proposed exploration and data collection schemes theoretically guarantee to acquire sufficient information from the system's state-input trajectories that can solve the underlying control design problems. We prove that under mild assumptions, as more and more data is accumulated, the collected data can solve the problems with higher probability along with the proposed algorithms.

关键词： data collection Symmetric matrices Linear systems control design Optimal control Mathematical models Dynamic programming data-driven design reinforcement learning optimal control linear matrix inequality (LMI) dynamic programming linear time-invariant (LTI) system

来源：评论

学校读者我要写书评

暂无评论

Prediction of matte grade in the oxygen-rich top blown smelting based on WD-SSA-SVM algorithm 12

Prediction of matte grade in the oxygen-rich top blown smelt...

引用

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

作者： Li, Xincai Yang, Chunxi Zhang, Xiufeng Li, Gengen Kunming Univ Sci & Technol Fac Mech & Elect Engn Kunming 650504 Yunnan Peoples R China Yunnan Int Joint Lab Intelligent Control & Applic Kunming Yunnan Peoples R China

ISBN: (纸本)9798350321050

In view of the defects of noise in the industrial data of the oxygen-rich top blown smelting and time lag in off-line detection of matte grade, it is difficult to accurately establish the prediction model of process parameters. A process parameter prediction model based on wavelet denoising sparrow search algorithm optimized support vector machine (WD-SSA-SVM) was proposed. Firstly, wavelet denoising is used to improve the quality of the data. Secondly, the sparrow search algorithm was used to optimize the support vector machine to establish the nonlinear relationship model between the melting process and the process index, and the model parameters were identified by the sample data after denoising, so as to effectively predict the process index of frosted sand grade in the process of the oxygen-rich top blown smelting. The experimental results on the actual production data of a smelter show that the WD-SSA-SVM model proposed in this paper has high accuracy, meets the accuracy requirements in the actual industrial production, and can effectively guide the optimization and adjustment of the operating parameters of the oxygen-rich top blown smelting process.

关键词： Wavelet denoising Sparrow optimization Support vector machine Oxygen-rich top blown

来源：评论

学校读者我要写书评

暂无评论

Sludge bulking prediction method for Sewage treatment plant based on GWO-CPSO algorithm 12

Sludge bulking prediction method for Sewage treatment plant ...

引用

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

作者： Xue, Tonglai Gao, Yutao Zhou, Meng Han, Fei Liu, Chun North China Univ Technol Sch Elect & Control Engn Beijing 100144 Peoples R China Hebei Univ Sci & Technol Sch Environm Sci & Engn Shijiazhuang 050018 Hebei Peoples R China

ISBN: (纸本)9798350321050

Various biological and abiotic factors influence the process of sludge bulking, showing a high degree of nonlinearity. Various inducing factors interact with each other and have strong coupling. In theory, the artificial neural network can approximate any nonlinear system with any precision, so it is determined to use a neural network algorithm for prediction. The Middle BP algorithm is the most common and effective method. This paper proposes a prediction method based on the BP neural network optimized by the grey wolf optimization algorithm and chaotic particle swarm optimization algorithm to predict the trend of sludge bulking, in which the grey wolf algorithm and messy particle swarm optimization method are used to optimize the neural network algorithm. This algorithm can solve the problems of the BP neural network in the early stage, such as convergence, easy falling into the local minimum value, too dependent on the early weight, and effectively improve the neural network's calculation speed and prediction accuracy.

关键词： Sewage treatment plant GWO-CPSO algorithm BP neural network Sludge swelling

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal control of Unknown Nonlinear systems via Homotopy-Based Policy Iteration

引用

ieee TRANSACTIONS ON AUTOMATIC control 2024年第5期69卷 3396-3403页

作者： Chen, Ci Lewis, Frank L. Xie, Kan Xie, Shengli Guangdong Univ Technol Sch Automat Guangdong Key Lab IoT Informat Technol Guangzhou 510006 Peoples R China Minist Educ Key Lab Intelligent Informat Proc & Syst Integrat Guangzhou 510006 Peoples R China Univ Texas Arlington UTA Res Inst Ft Worth TX 76118 USA Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China 111 Ctr Intelligent Batch Mfg Based IoT Technol Guangzhou 510006 Peoples R China Guangdong Univ Technol Sch Automat Key Lab Intelligent Detect & Internet Things Mfg Guangzhou 510006 Peoples R China Guangdong Hong Kong Macao Joint Lab oratory Smart Guangzhou Peoples R China

As one efficient technique in reinforcement learning, policy iteration (PI) requires an initial admissible (or stabilizing for linear systems) control policy that renders the existing PI-based results to be model dependent. To attain a completely data-driven adaptive optimal control, this article suggests integrating a homotopic design with PI for unknown continuous-time nonlinear systems. Technically, we leverage a homotopic constant to construct an artificially stable system that allows zero control to initialize PI. Utilizing a homotopic strategy, we recursively update the artificial system and then enforce it to gradually recover the original system. This ultimately allows us to obtain an admissible control policy in a finite number of iterations without carrying out a model-based initialization. Once the admissible control is obtained, the proposed homotopic PI inherits fast convergence from the traditional PI technique and ensures learning the optimal control solution from the data measured from unknown nonlinear systems.

关键词： Adaptive optimal control homotopic initial admissible control policy iteration (PI) reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

learning Model Predictive control with Error Dynamics Regression for Autonomous Racing

Learning Model Predictive Control with Error Dynamics Regres...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Xue, Haoru Zhu, Edward L. Dolan, John M. Borrelli, Francesco Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA Univ Calif Berkeley Dept Mech Engn Berkeley CA 94720 USA

ISBN: (纸本)9798350384581;9798350384574

This work presents a novel learning Model Predictive control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/10th scale hardware, and deployed the proposed LMPC on a full-scale autonomous race car used in the Indy Autonomous Challenge (IAC) with closed loop experiments at the Putnam Park Road Course in Indiana, USA. The results show that the proposed control policy exhibits improved robustness to parameter tuning and data scarcity. Incremental and safety-aware exploration toward the limit of handling and iterative learning of the vehicle dynamics in high-speed domains is observed both in simulations and experiments.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Robust fixed-time sliding mode control of underactuated Furuta pendulum system 12

Robust fixed-time sliding mode control of underactuated Furu...

引用

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

作者： Wang, Zhujun Zhou, Xinhao Zhang, Ancai Liang, Xiao Pan, Guangyuan Linyi Univ Sch Automat & Elect Engn Linyi 276005 Shandong Peoples R China Linyi Univ Key Lab Complex Syst & Intelligent Comp Univ Shan Linyi 276005 Shandong Peoples R China

ISBN: (纸本)9798350321050

A Furuta pendulum is a typical underactuated mechanical system with two degrees of freedom (DOF) and only one input. We address the robust stabilization control problem for this 2-DOF underactuated system with a matched external disturbance. A fixed-time sliding mode control method is presented. First, the dynamic motion model of the system is established using the Euler-Lagrange modeling method. And then, we get the approximate linearization model of the system around the origin equilibrium point and construct a homeomorphic coordinate transformation for this model. After that, a sliding mode surface and a fixed-time robust controller are designed for the transformed system. The developed controller ensures the system's state variables to reach the sliding mode surface in a fixed time. This guarantees the fixed-time robust stabilization control objective to be achieved. Finally, two numerical examples demonstrate the validity of our presented control strategy.

关键词： Furuta pendulum fixed-time stable sliding mode control robust stabilization

来源：评论

学校读者我要写书评

暂无评论

Scenario-Optimization-Based Velocity Planning of Autonomous Vehicles for Interacting With Pedestrians

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2025年第4期26卷 5382-5395页

作者： Jekl, Bence Dabcevic, Zvonimir Nemeth, Balazs Skugor, Branimir Gaspar, Peter Hungarian Res Network HUN REN Inst Comp Sci & Control SZTAK H-1111 Budapest Hungary Univ Zagreb Fac Mech Engn & Naval Architecture Zagreb 10000 Croatia HUN REN SZTAKI H-1111 Budapest Hungary Budapest Univ Technol & Econ Fac Transportat Engn & Vehicle Engn Dept Control Transportat & Vehicle Syst H-1111 Budapest Hungary

This paper presents a velocity planning method for autonomous vehicles (AVs) to guarantee safe interactions with pedestrians at unsignalized crosswalks and with surrounding vehicles on the AV's route. The method is structured within a hierarchical framework that includes robust control, a learning-based component, and a supervisory element. The learning-based component is trained using reinforcement learning techniques to reduce traveling time, minimize control interventions, and set the priority ratio between the AV and pedestrians. The supervisory element employs scenario optimization, using statistical data on pedestrian motions to ensure collision avoidance. A complex game-theory-based pedestrian model is formulated and analyzed in order to evaluate the effectiveness of the proposed velocity planning method. Extensive simulations are performed using the high-precision traffic simulator software SUMO. These simulations evaluate various aspects of the velocity planner, including computation time, traveling time, control interventions, and parameter settings. The results demonstrate the method's ability to achieve real-time implementation while maintaining safety and performance objectives.

关键词： Pedestrians Planning Computational modeling Safety data models Real-time systems Predictive models Autonomous vehicles Adaptation models Vehicle dynamics pedestrian modeling velocity planning scenario approach data-driven control

来源：评论

学校读者我要写书评

暂无评论

A Fault Diagnosis Method Based on Wavelet Denoising and 2DCNN under Background Noise 12

A Fault Diagnosis Method Based on Wavelet Denoising and 2DCN...

引用

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

作者： Liu, Kexin Li, Zhe He, Wenbin Peng, Jia Wang, Xudong Wang, Yaonan Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China State Grid Hunan Elect Power Co Ltd Changsha 410029 Peoples R China Hunan Univ Sch Robot Changsha 410082 Peoples R China Natl Engn Res Ctr Robot Visual Sensing Control Te Changsha 410082 Peoples R China

ISBN: (纸本)9798350321050

This paper develops a novel method named wavelet denoising convolutional neural network (WDECNN) for fault diagnosis with background noise. The continuous wavelet transform (CWT) is first applied to transform the measured raw vibration data into time-frequency images which serve as the inputs of WDECNN. Then, a light-weight two-dimensional CNN (2DCNN) model is incorporated in WDECNN to simplify the network architecture, while a wavelet denoising module is also applied in it to achieve high accuracy of fault identification in the noisy environment. Particularly, the wavelet denoising module which consists of wavelet decomposition and denoising is parallel to the 2DCNN model, and the denoising results are integrated into pooling layers in the 2DCNN model. Thus, the denoised information is added to the 2DCNN model to improve its feature learning ability. Finally, the effectiveness of the developed method is validated on Paderborn bearing dataset, which illustrates its fault diagnosis capability under background noise.

关键词： Fault Diagnosis Background Noise Wavelet Denoising Convolutional Neural Network (CNN) data-driven

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：