检索结果-内蒙古大学图书馆

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

作者： Song, Wanping Zheng, Chen Chen, Zengqiang Sun, Mingwei Sun, Qinglin Nankai Univ Coll Artificial Intelligence Tianjin 300350 Peoples R China Beijing Inst Astronaut Syst Engn Beijing 100076 Peoples R China Key Lab Intelligent Robot Tianjin Tianjin 300350 Peoples R China

ISBN: (纸本)9798350321050

Extended state observer (ESO) has been used to estimate the unknown nonlinear function of the system using input and output data. Recently, a new observer, the compensation function observer (CFO), has a significant improvement over ESO in estimating accuracy. This paper refers to the theory of CFO of fully using the available information and the innovation of the new definition of disturbance, designs a new observer, and verifies the availability of the new observer on the depth control simulation of the autonomous underwater vehicle (AUV). The simulation results demonstrate that the new observer is capable of estimating the unknown nonlinear function more quickly and accurately.

关键词： Autonomous underwater vehicle (AUV) Position control Compensation function observer (CFO) Extended state observer (ESO)

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Maneuvering Decision in Close Air Combat Based on Deep Q Network 12

Research on Intelligent Maneuvering Decision in Close Air Co...

引用

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

作者： Zhangl, Tingyu Zheng, Chen Sun, Mingwei Wang, Yongshuai Chen, Zengqiang Nankai Univ Coll Artificial Intelligence Tianjin 300350 Peoples R China Beijing Inst Astronaut Syst Engn Beijing 100076 Peoples R China

ISBN: (纸本)9798350321050

For the Unmanned Combat Aerial Vehicle(UCAV)maneuvering decision in close air combat, the design of reinforcement learning(RL) reward function and the selection of hyperparameters are studied based on the deep Q network algorithm. Considering the angle, range, altitude, and speed factors, an auxiliary reward function is proposed to solve the sparse reward problem of RL. Meanwhile, aiming at the issue of hyperparameter selection in RL, the influence of learning rate, the number of network nodes, and layers on the decision-making system is explored, and a suitable range of parameters is given, which provides a reference for the subsequent research on parameter selection. In addition, the simulation results show that the trained agent can obtain the optimal maneuver strategy in different air combat situations, but it is sensitive to RL hyperparameters.

关键词： air combat autonomous maneuvering decision deep reinforcement learning DQN reward function

来源：评论

学校读者我要写书评

暂无评论

Position control of X-Y Precision Planar Motion Stage Based on Iterative learning and Cross-coupling 12

Position Control of X-Y Precision Planar Motion Stage Based ...

引用

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

作者： Fang, Jingzhe Zhang, Tao Chen, Xiyou Qi, Chen Zhang, Guopeng Zhang, Hualiang Yan, Hongyu Shenyang Univ Technol Sch Elect Engn Shenyang 110020 Peoples R China Dalian Univ Technol Sch Elect Engn Dalian 116024 Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang 110016 Peoples R China Chinese Acad Sci Key Lab Networked Control Syst Shenyang 110016 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110169 Peoples R China

ISBN: (纸本)9798350321050

In some precision machining applications, not only should we pay attention to the tracking accuracy of the X-Y precision plane motion table, but the more important criterion is the contour accuracy. This paper proposes an adaptive iterative learning control that adjusts in real time with the system's working state for the X-Y precision plane motion stage control system. Then on the basis of adaptive iterative learning control, the relationship between the two axes is established by cross-coupling control, the contour error of the system is calculated in real time, and the stability of the system is improved. The final experimental results show that the improved algorithm has smaller contour error and better robustness.

关键词： iterative learning cross coupling X-Y precision plane motion conference

来源：评论

学校读者我要写书评

暂无评论

data-driven Iterative learning control for Continuous-Time systems 62

Data-driven Iterative Learning Control for Continuous-Time S...

引用

62nd ieee conference on Decision and control (CDC)

作者： Chu, Bing Rapisarda, Paolo Univ Southampton Sch Elect & Comp Sci Southampton England

ISBN: (纸本)9798350301243

We develop a data-driven iterative learning control design framework for continuous-time systems that does not require explicit or implicit identification of a system model. Using Chebyshev polynomial orthogonal bases, we show that all system trajectories can be characterised from sufficiently rich input/output data. Using this crucial result we develop a data-driven version of the model-based norm-optimal iterative learning control algorithm, and provide a computationally efficient implementation thereof. We rigorously analyse the convergence properties of the resulting design and also present a numerical example to illustrate its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Aeration Quantity of Biochemical Tank Based on Ensemble learning Algorithm 12

Prediction of Aeration Quantity of Biochemical Tank Based on...

引用

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

作者： Tao, Yu-Xin Yang, Bin Pang, Zhong-Hua Fan, Lan-Zhi North China Univ Technol Key Lab Fieldbus Technol & Automat Beijing Beijing 100144 Peoples R China Beijing KingTrol Data Technol Co Ltd Beijing 100160 Peoples R China

ISBN: (纸本)9798350321050

This paper presents an intelligent prediction method for aeration capacity of biochemical tank for sewage treatment. Firstly, the data collected in the field is processed from the actual sewage treatment plant and the data set is obtained through correlation analysis. Secondly, after optimizing the model parameters, RF, GBDT, LGB and LR models are established respectively to obtain the forecasting capabilities of each model. Furthermore, the fusion of the Stacking model is introduced by using RF, GBDT and LGB as the first layer and LR as the second layer. Experimental results show that the optimized model can better predict the aeration required by the biochemical tank according to the real-time incoming and outbound water quality and quantity data, so as to ensure that the urban sewage treatment plant can save energy and reduce consumption to a certain extent and maintain the sustainable development of carbon neutrality.

关键词： Wastewater Treatment Machine learning Aeration Integrated learning Prediction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Finite-Time Heading control of Intelligent Ship with Asymmetric Output Constraints 12

Adaptive Finite-Time Heading Control of Intelligent Ship wit...

引用

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

作者： Liu, Yanli Sun, Yihua Hao, Li-Ying Dalian Maritime Univ Sch Marine Elect Engn Dalian 116026 Liaoning Peoples R China

ISBN: (纸本)9798350321050

A command filter based finite-time heading control scheme of intelligent ship with asymmetric output constraints is developed. Firstly, asymmetric output constraints are handled via the nonlinear state-dependent function. Then, the finite-time command filters are utilized to filter the immediate control function. This method can solve the issue of calculating burden with good effect. Subsequently, the finite-time error compensate signals are established to make up for the filtering error. Under the constructed tactic, system output does not violate the constraint conditions. Additionally, by analysis of the Lyapunov function and immediate control function, all closed-loop signals are bounded, the heading tracking error can converge to zero in finite time. And the validity of the tactic is confirmed on the simulations in the end.

关键词： Asymmetric output constraints Intelligent ship Finite-time control Backstepping Heading tracking

来源：评论

学校读者我要写书评

暂无评论

Position-Dependent Motion Feedforward via Gaussian Processes: Applied to Snap and Force Ripple in Semiconductor Equipment

引用

ieee TRANSACTIONS ON control systems TECHNOLOGY 2024年第6期32卷 1968-1982页

作者： Poot, Maurice van Haren, Max Kostic, Dragan Portegies, Jim Oomen, Tom Eindhoven Univ Technol Dept Mech Engn NL-5612 AZ Eindhoven Netherlands Ctr Competency ASMPT NL-6641 TL Beuningen Netherlands Eindhoven Univ Technol Dept Math & Comp Sci NL-5612 AZ Eindhoven Netherlands Delft Univ Technol Delft Ctr Syst & Control NL-2628 CD Delft Netherlands

The requirements for high accuracy and throughput in next-generation data-intensive motion systems lead to situations where position-dependent feedforward is essential. This article aims to develop a framework for interpretable and task-flexible position-dependent feedforward through systematic learning with automated experimental design. A data-driven and interpretable framework is developed by employing Gaussian process (GP) regression, enabling accurate modeling of feedforward parameters as a continuous function of position. The data is efficiently collected and illustrated through an iterative learning control (ILC) algorithm. Moreover, a framework for experimental design in the sense of automatically determining the training positions is presented by exploiting the uncertainty estimates of the GP and the specified first-principles knowledge. Two relevant case studies show the importance and significant performance improvement of the approach for position-dependent snap feedforward for a simplified 1-D wafer stage simulation and experimental application to position-dependent motor force constant compensation in an industrial wirebonder.

关键词： Feedforward systems Dynamics Task analysis Force Systematics Actuators Wires Gaussian processes (GPs) iterative learning control (ILC) mutual information

来源：评论

学校读者我要写书评

暂无评论

Security Versus Accuracy: Trade-Off data Modeling to Safe Fault Classification systems

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2024年第9期35卷 12095-12106页

作者： Zhuo, Yue Song, Zhihuan Ge, Zhiqiang Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

While the data-driven fault classification systems have achieved great success and been widely deployed, machine-learning-based models have recently been shown to be unsafe and vulnerable to tiny perturbations, i.e., adversarial attack. For the safety-critical industrial scenarios, the adversarial security (i.e., adversarial robustness) of the fault system should be taken into serious consideration. However, security and accuracy are intrinsically conflicting, which is a trade-off issue. In this article, we first study this new trade-off issue in the design of fault classification models and solve it from a brand new view, hyperparameter optimization (HPO). Meanwhile, to reduce the computational expense of HPO, we propose a new multiobjective (MO), multifidelity (MF) Bayesian optimization (BO) algorithm, MMTPE. The proposed algorithm is evaluated on safety-critical industrial datasets with the mainstream machine learning (ML) models. The results show that the following hold: 1) MMTPE is superior to other advanced optimization algorithms in both efficiency and performance and 2) fault classification models with optimized hyperparameters are competitive with advanced adversarially defensive methods. Moreover, insights into the model security are given, including the model intrinsic security properties and the correlations between hyperparameters and security.

关键词： Adversarial attack Bayesian hyperparameter optimization (HPO) fault classification multifidelity (MF) mul-tiobjective (MO) safe data-driven modeling

来源：评论

学校读者我要写书评

暂无评论

Generalized Predictive control of Converter Inlet Temperature in the Process of Acid Production with Flue Gas 12

Generalized Predictive Control of Converter Inlet Temperatur...

引用

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

作者： Liu, Minghua Li, Xiaoli Wang, Kang Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing 100124 Peoples R China Minist Educ Engn Res Ctr Digital Community Beijing 100124 Peoples R China

ISBN: (纸本)9798350321050

The effective control of converter inlet temperature in the process of acid production with flue gas is an effective means to improve the conversion rate of sulfur dioxide and reduce environmental pollution. According to the characteristics of the process of acid production with flue gas, the control process of converter inlet temperature is studied in this paper. Firstly, the CARIMA (controlled auto-regressive integrated moving average, CARIMA) model of converter inlet temperature is established. Then, a generalized predictive controller based on CARIMA model is designed. Finally, the proposed method is verified by experiment and compared with PID controller. Experimental results show that the proposed method has a better tracking effect and smaller error. The effectiveness of the proposed method is verified.

关键词： CARIMA model generalized predictive control acid production tracking control

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-Based Fault Tolerant control Design for Aero-Engines With Multiple Types of Faults

引用

ieee TRANSACTIONS ON CIRCUITS AND systems I-REGULAR PAPERS 2024年第12期71卷 5770-5779页

作者： Qian, Moshu Jiang, Bin Sun, Chenglin Shi, Jiantao Bo, Cuimei Nanjing Tech Univ Coll Elect Engn & Control Sci Nanjing 211816 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 210016 Peoples R China

In this paper, a reinforcement learning (RL) based fault tolerant control (FTC) strategy is investigated for the bleed air temperature control system (BATCS) of an aero-engine with time delays, parameter uncertainties and multiple types of faults. By the design of offline training networks, the deep deterministic policy gradient (DDPG) algorithm is employed to update the parameters of training networks. Then a data driven FTC input combined with exponential weighted moving average (EWMA) filter can be obtained to achieve the fault tolerant tracking control of BATCS. Finally, a comparison simulation between PID and RL based FTC scheme is demonstrated to verify the feasibility of the research.

关键词： Aircraft propulsion Engines Valves Heating systems Atmospheric modeling Mathematical models Aerodynamics Reinforcement learning (RL) fault tolerant control (FTC) PID aero-engine multiple types of faults

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：