检索结果-内蒙古大学图书馆

Deep Reinforcement Learning With Curriculum Design for Quantum State Classification

IEEE Transactions on Emerging Topics in Computing 2024年

作者： Yu, Haixu Zhao, Xudong Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian116024 China

In quantum information science, one of the ambitious goals is to look for an efficient technique for classifying multiple quantum states. To solve the binary classification problem for multiple quantum states characterized by parameters, we propose a deep reinforcement learning with curriculum design (DRL-CD) method. In DRL-CD, a series of tasks are created, using state parameter intervals and fidelity thresholds, to form a curriculum. Then, a quantum state binary classifier can be obtained by utilizing deep reinforcement learning (DRL) to solve each task in the designed curriculum. In particular, we construct a training set by sampling the state parameter interval corresponding to each task, and each task is accomplished by learning the control strategies capable of steering the sampled quantum states to the target state. In addition, a knowledge review method is proposed to prevent DRL from forgetting the learned classification knowledge. Some state classification problems of the spin-1/2 quantum system and λ-type atomic system are solved by the proposed DRL-CD method, and comparison experiments with deep Q-network (DQN) and stochastic gradient descent (SGD) show the better classification performance of DRL-CD. © 2013 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-anion electrolyte modulates the interactions in solvation structure to construct robust lithium metal batteries

引用

Journal of Energy Chemistry 2025年第5期104卷 36-43页

作者： Ke-Feng Ren Yun-Fei Du Jia-Xin Guo Zhen-Hui Luo Xin Sun Wen-Bo Tang Tian-Qi Li Cong Guo Weizhai Bao Feng Yu He Liu Xin-Bing Cheng Jingfa Li Jiangsu Key Laboratory of New Energy Devices&Interface Science School of Chemistry and Materials ScienceNanjing University of Information Science and TechnologyNanjing 210044JiangsuChina Z Energy Storage Center Key Laboratory of Energy Thermal Conversion and Control of Ministry of EducationSchool of Energy and EnvironmentSoutheast UniversityNanjing 211189JiangsuChina Tianmu Lake Institute of Advanced Energy Storage Technologies Liyang 213300JiangsuChina

Designing anion-dominated weak solvation structures is often achieved by elevating the concentration of Li ***,this is accompanied by the increase in the ***,a medium concentration electrolyte (1 M) with weak solvation structures is established by the multi-anion *** anions in the electrolyte strengthen the anion-solvent interactions through stronger ion–dipole *** reduces the quantity of free solvent and improves the reduction resistance of *** addition,the Li ion–solvent interaction is weakened,facilitating the anions to enter the solvation sheaths of Li *** multi-anion-dominated weak solvation structures boost Li ion diffusion in the electrolyte,accelerate the desolvation process of Li ions,and induce inorganic-rich solid electrolyte interphase and uniform Li *** average Coulombic efficiency of 99.1%for repeated Li plating/stripping can be ***||LiNi_(0.5)Co_(0.2)Mn_(0.3)O_(2) cells with a high cathode loading of 3.0 m A h cm^(-2) can maintain a capacity retention as high as 95% after 150 *** finding provides novel standpoints to modulate the interaction of solvation structures and extend the lifespan of high-energy–density Li metal batteries.

关键词： Lithium metal battery Multi-anion electrolyte Weak solvation structure Desolvation Solid electrolyte interphase

来源：评论

学校读者我要写书评

暂无评论

Recent Patents for control Devices of Fluid Pressure

引用

Recent Patents on Engineering 2022年第3期16卷 43-53页

作者： Xie, Baocheng Wang, Yi Li, Chaoxiang Zhang, Hanyang Zhang, Yongxing Su, Haobin Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin150080 China Beijing Institute of Control Engineering Beijing200085 China

Fluid pressure, an important parameter of fluid flow, affects the control accuracy and stability of fluid transmission. The control devices of fluid pressure are widely applied to the mechanical transmission control, which is the main means to change the fluid pressure and improve control accuracy and stability in the mechanical transmission system. To control the accuracy and stability of the fluid transmission, the pressure control device is divided into pressure reduction devices, pressurization devices, and stabilizing pressure devices. The characteristics of pressure control devices with different functions are analyzed from the structure of the device. Thus, more and more attention has been paid to the control devices of fluid pressure. To meet the increasing requirement of control accuracy and stability of fluid transmission, the control devices of fluid pressure, such as pressure reduction devices, pressurization devices, and stabilizing pressure devices, are being improved continuously. This paper reviews various current representative patents related to pressure reduction devices, pressurization devices, and stabilizing pressure devices of fluid pressure. By investigating various patents on the control devices of fluid pressure, the main current existing problems of the pressure control devices, such as low control accuracy and poor stability, are summarized and analyzed. Furthermore, the development trend of the control devices of fluid pressure has also been discussed. The optimization of the structure and function of the control devices of fluid pressure is conducive to improve the control accuracy and stability of transmission of the fluid. More relevant patents will be invented in the future. © 2022 Bentham Science Publishers.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Optimal denial-of-service attack scheduling for remote state estimation via sequential observations 43

Optimal denial-of-service attack scheduling for remote state...

引用

43rd Chinese control Conference, CCC 2024

作者： Yang, Xinxin Ni, Yuqing Chen, Xiaomeng Chen, Shan Liu, Fei Jiangnan University The Key Laboratory of Advanced Process Control for Light Industry Ministry of Education School of Internet of Things Engineering Wuxi214122 China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong999077 Hong Kong

ISBN: (纸本)9789887581581

This study investigates the optimal allocation problem of attack energy in multi-system remote state estimation for Cyber-Physical Systems (CPSs). We consider a scenario where there are M independent systems, each equipped with a remote sensor monitoring system. The local estimates from these systems are sent to a remote estimator through a packet loss channel. The objective of the attacker is to degrade the communication channel between the sensors and the remote estimator. Due to capacity limitations, the attacker is restricted to attacking at most one out of M channels. We incorporate interference from other sensors or interference sources into the communication model based on the SINR (Signal-to-Interference-plus-Noise Ratio) model. It should be noted that the same attack power can lead to different packet loss rates in different network environments. From the attacker's perspective, the goal is to find the optimal attack strategy that maximizes the average estimation error of the remote estimator. Given the uncertainties of wireless network environments, we employ the sequentially-observed Markov decision process (SOMDP) framework to solve the problem. By observing the wireless channels, we gather additional information and incorporate it into the decision-making policy, resulting in better performance than using a standard Markov decision process (MDP). The simulation results support our theoretical findings. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Health Parameters Estimation of Turbofan Engine Based on Improved UKF Method 41

Health Parameters Estimation of Turbofan Engine Based on Imp...

引用

第41届中国控制会议

作者： Yu Zhang Si-Xin Wen Kun-Zhi Liu Chongyi Sun Xi-Ming Sun School of Control Science and Engineering Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology DUT Artificial Intelligence Institute

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In view of the shortcomings of the standard Unscented Kalman Filter(UKF),such as slow convergence speed,low precision and easy divergence,the state estimation problem is transformed into an unconstrained optimization problem,and an iterative Unscented Kalman Filter based on the optimization method is *** Levenberg-Marquart nonlinear optimization method is used to improve the measurement update equation of the filtering ***,the numerical simulation of health parameters estimation on a certain turbofan engine is carried *** results show that the established parameters estimation model can accurately estimate the changes of health parameters in different performance degradation modes,and the convergence speed and stability are obviously better than the standard UKF *** addition,the improved algorithm was successfully deployed on the NVIDIA Jetson Xavier embedded platform to complete the online estimation,which indicates that the proposed method has good real-time performance.

关键词： Turbofan engine Kalman filter Unconstrained optimization Online estimation

来源：评论

学校读者我要写书评

暂无评论

An ensemble multivariate detection method for steady-state drift in process industries

引用

Science China(Information Sciences) 2025年

作者： Wenshuo SONG Weihua CAO Yan YUAN Wenkai HU School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

In process industries, it is crucial to maintain operational parameters within a designated steady-state operating point to ensure product quality and operational efficiency. However,steady-state drift(a gradual shift in key parameters occurs over time even when the system is intended to be under stable conditions) can lead to significant production losses,safety risks, and increased operational costs. Therefore, accurately detecting steady-state drift is essential for maintaining stable, safe, and optimized operating conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on active disturbance rejection control scheme of auxiliary power unit 41

Research on active disturbance rejection control scheme of a...

引用

第41届中国控制会议

作者： Jijun Li Jianyi Zhang Si-Xin Wen Kun-Zhi Liu Xi-Ming Sun School of Control Science and Engineering Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology DUT Artificial Intelligence Institute

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

As an important secondary power source of the aircraft,the control performance of the Auxiliary Power Unit(APU)will directly affect the working efficiency of the aero-engines and the aircraft ***,APU has complex nonlinear characteristics and faces the influence of various inevitable and uncertain ***,the design of its highperformance control system is extremely challenging,and the traditional gain-scheduling PI control method cannot meet this *** resolve this problem,we design an Active Disturbance Rejection control(ADRC) scheme for APU *** the same time,the parametric design method of the proposed ADRC is given,so that the corresponding control parameters can be set according to the linearized model in engineering ***,a numerical comparison simulation is carried out on a certain auxiliary power unit model to verify the effectiveness and superiority of the proposed method.

关键词： Auxiliary power unit(APU) Aero-engine Active disturbance rejection control(ADRC) Extended state observer(ESO)

来源：评论

学校读者我要写书评

暂无评论

Conjugate gradient based Cholesky CMA-ES estimation algorithms for Hammerstein systems 41

Conjugate gradient based Cholesky CMA-ES estimation algorith...

引用

第41届中国控制会议

作者： Yawen Mao Chen Xu School of Science Jiangnan University Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) School of Internet of Things EngineeringJiangnan University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper studies the parameter estimation problems of nonlinear systems with colored noise using the covariance matrix adaptation evolution strategy(CMA-ES),which is one of the most competitive evolutionary algorithms available and has been applied in the area of reinforcement learning and process ***,a major limit ationthatimpedes the application of the CMA-ES is the high computational complexity caused by matrix *** alleviate this problem,an efficient Cholesky CMA-ES is proposed,which uses the Cholesky factor instead of the covariance matrix to reduce the computational complexity,and updates the search direction and distribution mean based on the conjugate gradient method to further improve the search *** virtue of the auxiliary model identification idea,the Cholesky CMA-ES can be applied to the parameter estimation problems of the Hammerstein nonlinear systems with colored noise.A simulation example is provided to demonstrate its effectiveness.

关键词： Nonlinear system Evolution strategy Cholesky factor Conjugate gradient method Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Energy storage resources management:Planning,operation,and business model

引用

Frontiers of Engineering Management 2022年第3期9卷 373-391页

作者： Kaile ZHOU Zenghui ZHANG Lu LIU Shanlin YANG School of Management Hefei University of TechnologyHefei 230009China Key Laboratory of Process Optimization and Intelligent Decision-making of Ministry of Education Hefei University of TechnologyHefei 230009China

With the acceleration of supply-side renewable energy penetration rate and the increasingly diversified and complex demand-side loads,how to maintain the stable,reliable,and efficient operation of the power system has become a challenging issue requiring *** of the feasible solutions is deploying the energy storage system(ESS)to integrate with the energy system to stabilize ***,considering the costs and the input/output characteristics of ESS,both theinitial configuration process and the actual operation process require efficient *** study presents a comprehensive reviewof managing ESs from the perspectives of planning,operation,and business *** of all,in terms of planning and configuration,it is investigated from capacity planning,location planning,as well as capacity and location combined *** process is generally the first step in deploying ***,it explores operation management of ESS from the perspectives of state assessment and operation *** so-called state assessment refers to the assessment of three aspects:The state of charge(SOC),the state of health(SOH),and the remaining useful life(RUL).The operation optimization includes ESS operation strategy optimization and joint operation ***,it discusses the business models of *** business models involve ancillary services and load transfer,while emerging business models include electric vehicle(EV)as energy storage and shared energy storage.

关键词： energy storage system energy storage resources management planning configuration operational management business model

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Multiobjective Gene Selection for Cell Classification From Large-Scale Single-Cell RNA Sequencing Data

引用

IEEE Transactions on Evolutionary Computation 2025年第3期29卷 601-615页

作者： Lin, Jianqing He, Cheng Jiang, Hanjing Huang, Yabing Jin, Yaochu Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology State Key Laboratory of Advanced Electromagnetic Technology School of Electrical and Electronic Engineering Wuhan430074 China Renmin Hospital of Wuhan University Department of Pathology Wuhan430060 China Westlake University Trustworth and General Artificial Intelligence Laboratory School of Engineering Hangzhou310030 China

Accurate cell classification is crucial but expensive for large-scale single-cell RNA sequencing (scRNA-seq) analysis. Gene selection (GS) emerges as a pivotal technique in identifying gene subsets of scRNA-seq for classification accuracy improvement and gene scale reduction. Nevertheless, the rising scale of scRNA-seq data presents challenges to existing GS methods regarding performance and computational time. Thus, we propose a surrogate-assisted evolutionary algorithm for multiobjective GS to address these deficiencies. An innovative two-phase initialization method is proposed to select sparse solutions to provide preliminary insights into gene contributions. Then, a binary competitive swarm optimizer is proposed for effective global search, where a local search method is embedded to eliminate irrelevant genes for efficiency consideration. Additionally, a surrogate model is adopted to forecast classification accuracy efficiently and substitutes part of the computationally expensive classification process. Experiments are conducted on eight large-scale scRNA-seq datasets with more than 20 000 genes. The effectiveness of the proposed GS method for scRNA-seq cell classification compared with eight state-of-the-art methods is validated. Gene expression analysis results of selected genes further validated the significance of the genes selected by the proposed method in the classification of scRNA-seq data. © 1997-2012 IEEE.

关键词： Gene expression

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：