检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 722-733页

作者： Li, Dong Liu, Yiqi Huang, Daoping Xu, Chong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering Guangzhou510640 China Technical University of Denmark Process and Systems Engineering Center Department of Chemical and Biochemical Engineering Lyngby2800 Denmark South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Gannan Normal University School of Physics and Electronic Information Ganzhou341000 China

To monitor industrial processes properly, soft-sensors are widely used to predict significant but difficult-to-measure quality variables. However, the prediction performances of traditional data-driven soft-sensors are usually unacceptable once suffering from high-nonlinear, high-dimension, and imblance data issues. Therefore, a semisupervised soft-sensor, which is learned by a just-in-time method with structure entropy clustering (SS-JITL-SEC), is proposed aiming to improve prediction performance with a simpler way. Inspired by a divide and conquer strategy, a novel SEC method is proposed to achieve several clusters and then to translate the highly complex and nonlinear modeling problems into simple and linear ones. Moreover, the training dataset is extended through a mixed SS labeling approach. Finally, dissimilarity-based JITL works together with the resulting clustering subdatasets to formulate a local adaptive prediction model. Two datasets from different types of wastewater treatment plants are used to verify the effectiveness of the proposed soft-sensor. The results show that the SS-JITL-SEC soft-sensor can achieve better prediction performance than other standard counterparts, and even for effective process monitoring with the resulted residuals. © 2020 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Design and Characteristics of Shape Memory Alloy Bidirectional Torsional Actuator 9

Design and Characteristics of Shape Memory Alloy Bidirection...

引用

2023 9th international conference on Applied Materials and Manufacturing Technology, ICAMMT 2023

作者： Shen, Chuanliang Zhan, Jincheng Deng, Yifei Gao, Yaohui State Key Laboratory of Automotive Simulation and Control Jilin University Changchun China College of Automotive Engineering Jilin University Changchun China

To overcome the problems of the low power/weight ratio of traditional servo motors, complex transmission systems, and large space occupied by hydraulic drive systems, this paper designs a bidirectional torsional actuator using the shape memory effect of Ti-Ni shape memory alloy (SMA) wire, which aims to realize the folding and unfolding of the wings of flying cars. The model of the designed actuator was established and the theoretical calculation was analyzed, based on which the experimental verification was carried out. It is found that when the heating current is 1.6 A, the mechanism can take into account the economy under the premise of meeting a certain folding speed. When the pre-stretching amount of SMA wire is 3%, the residual strain corresponding to the wire is small, about 0.577%, and it can provide driving torque and torsion angle to meet the design requirements of the actuator. This verifies the feasibility of the actuator and obtains the driving characteristics of the actuator. Finally, the shortcomings and improvement measures of the actuator are analyzed briefly. © Published under licence by IOP Publishing Ltd.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Robots in Agriculture 15

Artificial Intelligence and Robots in Agriculture

引用

15th international conference Management of Large-Scale System Development, MLSD 2022

作者： Raikov, Alexander Abrosimov, Vyacheslav Institute of Control Sciences Russian Academy of Sciences Laboratory of Modular Data Processing and Control Systems Moscow Russia Main Research and Test Interspecific Center for Advanced Weapons of the Ministry of Defense of Russia Moscow Russia

ISBN: (数字)9781665497015

ISBN: (纸本)9781665497015

The article addresses the generalization of modern challenges to agricultural production from robotization and artificial intelligence (AI). The classification of agricultural robots is given for the identification of development trends. It is shown the possibilities of using agricultural robots and AI systems to improve the efficiency of agriculture in the field of crop and livestock production. Approaches to the construction and use of information resources for solving problems of precision farming and animal husbandry are described. The justification is given that agriculture robots are successfully used for solving the problems of complex agrochemical soil survey, recognition of plant diseases, weed, and pest control, cattle feeding, milking, etc. General approaches to the use of agriculture robots in the context of using the Internet are described. Methods and means of AI are considered mainly on examples from the field of animal husbandry, where they are used to diagnose behavior, proactively detect diseases in animals and birds, etc. © 2022 IEEE.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

DEVELOPING HEURISTICS FOR RESOURCE ALLOCATION AND UTILIZATION IN systems DESIGN: A HIERARCHICAL REINFORCEMENT LEARNING APPROACH

DEVELOPING HEURISTICS FOR RESOURCE ALLOCATION AND UTILIZATIO...

引用

ASME 2024 international Design Engineering Technical conferences and Computers and Information in Engineering conference, IDETC-CIE 2024

作者： Gadi, Vikranth S. Szajnfarber, Zoe Panchal, Jitesh H. School of Mechanical Engineering Purdue University West LafayetteIN47907 United States Engineering Management and Systems Engineering The George Washington University WashingtonDC20052 United States

ISBN: (纸本)9780791888377

This paper presents an approach that integrates systems engineering principles with reinforcement learning (RL) to solve complex design problems under resource constraints. Product design processes often involve decomposing a large system into interconnected subsystems, with resources allocated across teams responsible for optimizing each subsystem. We formulate this process as a hierarchical multi-armed bandit (MAB) problem, where decisions are made at both the system level (allocating budget across subsystems) and subsystem level (selecting heuristics for sequential information acquisition). We employ Thompson Sampling, a Bayesian RL technique, to concurrently learn effective decision-making policies at each level. This hierarchical RL agent aims to maximize the overall system performance while adhering to fixed budgets for design evaluations. To demonstrate the approach, we present an illustrative example of a race car optimization in The Open Racing Car Simulator (TORCS) environment. Results show that the RL agent can learn to allocate resources strategically, prioritize the most impactful subsystems, and identify effective information acquisition heuristics for each subsystem team. The results also indicate that our method converges to high-performing car configurations with greater efficiency when compared to Bayesian Optimization. Copyright © 2024 by ASME.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Study of Approaches to Preprocessing Datasets and Initializationof Embeddings in Low-Dimensional Space when Implementing the PacMAP Algorithm

Study of Approaches to Preprocessing Datasets and Initializa...

引用

international conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Elena Andrianova Nikolai Demidov Institute of Information Technologies MIREA – Russian Technological University Moscow Russia

ISBN: (数字)9798331532178

ISBN: (纸本)9798331532185

The paper considers approaches to solving problems of preprocessing of datasets and initialization of embeddings in lowdimensional space when implementing the PacMAP algorithm. In the basic version of the PacMAP algorithm., the PCA algorithm is used to solve these problems. The proposed study examines the prospects for using 11 dimensionality reduction algorithms (DRA) in PacMAP algorithm in terms of minimizing the value of the loss function (LF) with acceptable time costs. The results of experimental studies have been presented and recommendations on the feasibility of using certain DRAs have been ascertained.

关键词： Dimensionality reduction Analytical models Costs Automation control systems Mathematical models Energy efficiency Optimization Python Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Sequence Impedance modeling and Stability Analysis of Grid-Connected LCL-type Voltage Source Converter Considering control Delay and the Frequency Coupling Effect of the SPWM Modulator

Sequence Impedance Modeling and Stability Analysis of Grid-C...

引用

2022 international conference on Power Energy systems and Applications, ICoPESA 2022

作者： Shi, Jinzhu Yang, Lihui Xi'an Jiaotong University School of Electrical Engineering Xi'an China

ISBN: (纸本)9781665410977

In the modern power system, the penetration level of the LCL-type voltage source converter (VSC) is increasing. Various complicated harmonic oscillation and instability problems are caused by its multi-timescale dynamic characteristic, which is a challenge for the safe and stable operation of the power system. The impedance model based on the traditional state-space average method, which ignores the frequency coupling effect of the SPWM modulator, can only accurately analyze the low-frequency instability. Therefore, to study the wide frequency range oscillation of such system, the frequency coupled impedance model of the LCL-type VSC is established considering control delay and the frequency coupling effect of the SPWM modulator in this paper. And an equivalent decoupled sequence impedance model is derived by the diagonalization method to simplify the stability analysis. On this basis, the grid-connected VSC system stability is investigated. The accuracy of the derived impedance model and the stability analysis results are verified by the time-domain simulation in MATLAB/Simulink. © 2022 IEEE.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

Computer Simulation of the Path and control of an Intelligent Mobile Robot in Python

Computer Simulation of the Path and Control of an Intelligen...

引用

2022 international conference on Smart Information systems and Technologies, SIST 2022

作者： Khuralay, Moldamurat Serikovna, Brimzhanova Saule Baizhumanova, Bibianar Ivanovna, Bizhanova Olga Telektesovich, Akhmetov Kayrat Moldamuratovich, Moldamurat Aibek L.N. Gumilyov Eurasian National University Nur-Sultan city Kazakhstan Nplc A. Baitursynov KRU Kostanay Academy Of The Mia Of The Rk Named After Sh. Kabylbaev Kostanay Kazakhstan L.N. Gumilyov Eurasian National University Nur-Sultan Kazakhstan Nplc «a. Baitursynov Kru» Kostanay Kazakhstan

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

Artificial intelligence has long been a scientific study. Mathematicians, physicists, neurobiologists, psychologists, programmers, philosophers, engineers have concentrated their efforts on their development. In the words of the famous French mathematician Jules Henri Poincare «Science is a graveyard of hypotheses». The article covers in detail current issues on artificial intelligence systems, mobile robot control systems, virtual 3D modeling. Intelligent control systems significantly expand the capabilities of robots to master increasingly complex operations. Using a methodology, the authors have developed methods for modeling the motion of an intelligently controlled mobile robot in three different computer programs. The authors conducted the study in the Python computer environment, and the C++ programming language was also used. In the work, the coordinates of motion x, y, z and distance were calculated. This distance was calculated by the total number of steps, and the optimal trajectory was realized by selecting the movement. Using a laser remote sensor (rangefinder) of the mobile robot, a virtual 3D model was modeled in a computer navigation control program environment based on the algorithm of an intelligently controlled mobile robot. In addition, the material discusses the relevance of using a microcontroller control system for the intelligent robot. The topic under consideration will be of interest to specialists in science, engineering, and other fields. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Inverse Problem Regularization of Parametric Identification of the Particle Temperature Distribution of Gas-Thermal Flow with Optimization of Its Solution 12th

Inverse Problem Regularization of Parametric Identification ...

引用

12th international conference on High-Performance Computing systems and Technologies in Scientific Research, Automation of control and Production, HPCST 2022

作者： Jordan, Vladimir Kobelev, Denis Altai State University Lenin Avenue 61 Barnaul656049 Russia Khristianovich Institute of Theoretical and Applied Mechanics SB RAS Institutskaya Street 4/1 Novosibirsk630090 Russia Joint-Stock Company "Radiy TN" Krupskaya Street 99a Barnaul656031 Russia

ISBN: (纸本)9783031237430

The inverse problem of parametric identification of the model function of the temperature distribution density of heterogeneous flow particles, which form functional powder coatings on the surface of technical products in the process of their thermal spraying, is considered. The regularization of this ill-posed inverse problem consists in choosing a physically adequate parameterized model function of the density of the particle temperature distribution using the registered spectrum of the particle thermal radiation. Structural diagrams of the complex for recording the spectrum of particle thermal radiation and the complex for its calibration are given. As the objective function of parametric optimization, the criterion function of the least squares method (LSM) is used. This function is defined as the sum of the squared deviations of the experimental readings of the thermal radiation spectrum of particles from the calculated values of its model spectrum corresponding to these readings. The model spectrum of the thermal radiation of particles is determined by the integral Fredholm operator of the first kind with the kernel of the operator based on the Planck function and the model parametrized function of the density of the particle temperature distribution. The Planck function depends on the temperature and wavelength of the thermal radiation of particles. Computational experiments were carried out to analyze the accuracy and numerical stability of the parameters being optimized when solving the inverse problem. The influence of the error aperture in the registered spectrum of the thermal radiation of particles on the estimate of the "shift" of the optimized parameters of the model density function of the particle temperature distribution is studied. Numerical modeling and experimental verification have shown that the accuracy and numerical stability of the regularized solution to measurement errors of the recorded spectrum of particle thermal radiation can be impro

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control with Recursive Multi-step Input Convex Lipschitz Neural Networks: an Application to Smart Buildings

Model Predictive Control with Recursive Multi-step Input Con...

引用

IEEE international conference on systems, Man and Cybernetics

作者： Paolo Scarabaggio Nicola Mignoni Jan Jantzen Raffaele Carli Mariagrazia Dotoli Department of Electrical and Information Engineering Polytechnic of Bari Italy Department of Financial and Management Engineering Samso Energy Academy Samso Denmark University of the Aegean Chios Greece

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Model Predictive control (MPC) is an optimal control technique that employs a dynamic model of the controlled process and an optimization algorithm to determine the control strategy. Nevertheless, the cost and effort required to create and maintain dynamical models are often high, and solving the resulting optimal control problem can be computationally complex. In recent years, data-driven modeling has become an attractive alternative to approximate the behavior of dynamical systems, with the aim of alleviating these issues. However, using such models for model-based control can be challenging due to their typically nonlinear and nonconvex nature. To address these issues, we propose a recursive multi-step learning-based dynamical modeling framework to capture the temporal behavior of dynamic systems. We take advantage of Input Convex Lipschitz Neural Networks, which are explicitly designed to be convex and continuous with respect to their in-puts. We further show that these mathematical proprieties hold in a multi-step dynamical modeling framework. The proposed approach is evaluated in a real-life MPC experiment conducted in a smart building in the Samso Marina, Denmark. We show that the proposed approach keeps the internal temperature within comfort constraints while minimizing heating/cooling energy consumption.

关键词： Smart buildings Uncertainty Computational modeling Heuristic algorithms Neural networks Optimal control Predictive models Mathematical models Dynamical systems Predictive control

来源：评论

学校读者我要写书评

暂无评论

Choice of Investment Decisions by Generating Companies, Taking into Account Payments for CO2 Emissions

Choice of Investment Decisions by Generating Companies, Taki...

引用

international conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Valery Akinfiev Laboratory of Management of Large-Scale System Development V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

Planning for the development of electricity generation is a complex decision-making problem, especially in an oligopolistic market in which several generation companies compete with each other. The paper considers some tasks of choosing the strategic behavior of generating companies in the conditions of energy transition, in particular, considering the influence of mechanisms to stimulate the reduction of CO2 emissions. The approach used is based on the reduction of interrelated optimization problems of various agents of the electric power market to complementarity models that allow searching for a solution based on market equilibrium. The results of formalization and solution of the problem for a distributed heterogeneous generation network are presented. The problem considers three agents - generating companies, a grid company, and electricity consumers. Considering a heterogeneous generation network makes it possible to simulate various effects associated with a change in the agents’ behavior depending on the price of permits for CO2 emissions. To solve the problem, we use the method of reducing it to solve the mixed complementarity problem (MCP), for which there are effective packages.

关键词：

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：