检索结果-内蒙古大学图书馆

Support vector regression based on multi-scale wavelet kernel for propylene concentration estimation and application

引用

Huagong Xuebao/CIESC Journal 2010年第6期61卷 1486-1494页

作者： Yu, Yanfang Du, Wenli Qian, Feng Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai 200237 China

Support vector regression based on multi-scale wavelet kernel has strong robustness and good generalization ability, but it is critical for it to choose appropriate model parameters. Obviously, the multi-scale kernel method has more difficulty in model selection than the single kernel approach. This paper proposed an approach about how to develop support vector regression based on multi-scale wavelet kernel. It applied quantum clustering to data partition in order to determine the scale parameter of the multi-scale kernel, resorted to the support vector data description algorithm to calculate the kernel width of the corresponding data points, and then used cultural algorithms to optimize the kernel width and the remaining parameters. The results showed that the multi-scale kernel method outperformed the single wavelet approach and the Gaussian method. The experiments about three regression data sets-Boston housing, Bodyfat and Santa demonstrated that in contrast with the Gaussian approach, the present multi-scale wavelet support vector regression made the mean squared error of test sets decrease by 6.8%, 62.0% and 91.3%, respectively. Meanwhile, the proposed approach exhibited good generalization ability for propylene concentration estimation in the bottom byproduct of propylene fractionation tower. It not only enabled the model output of training set for propylene concentration to show little difference with the actual output, but also made the relative error of test set down to 0.211. Compared with other methods, it had the minimal prediction error. © All Rights Reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Sufficient and Necessary Condition of Admissibility for Fractional-order Singular System

引用

自动化学报 2013年第12期39卷 2160-2164页

作者： YU Yao JIAO Zhuang SUN Chang-Yin School of Automation Electrical Engineering University of Science and Technology Beijing Beijing 100083 China Key Laboratory of Advanced Control of Iron and Steel Process Ministry of Education Beijing 100083 China Beijing Institute of Elec- tronic System Engineering Beijing 100854 China

这份报纸与顺序为部分顺序的单个系统集中于考虑条件吗？(0， 1 ) 。整齐的定义，没有推动并且考虑被给第一，然后，为部分顺序的单个系统的考虑的一个足够、必要的条件被建立。一个数字例子被包括说明建议条件。

关键词：奇异系统分数阶充要条件可容许充分必要条件

来源：评论

学校读者我要写书评

暂无评论

A Memory-Greedy Policy With Guaranteed Convergence for Accelerating Reinforcement Learning

引用

Journal of Autonomous Vehicles and Systems 2021年第1期1卷 011005页

作者： Yu, Xinglin Wu, Yuhu Sun, Xi-Ming Zhou, Wenya Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Control Science and Engineering Dalian University of Technology Dalian116024 China Liaoning Provincial Key Laboratory of Aerospace Advanced Technology School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China

Balancing the exploration and exploitation in reinforcement learning is a commonly dilemma and time-wasting work. In this paper, a novel exploration policy used in Q-Learning, called Memory-greedy policy, is proposed to accelerate learning. By memory storage and playback, the probability of random action selecting can be effectively dealt with or reduced, which hence speeds up learning. The principle of this policy is analyzed by maze scene, and the theoretical convergence is given according to dynamic programming. Copyright © 2021 by ASME.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrating field images and microclimate data to realize multi-day ahead forecasting of maize crop coverage using CNN-LSTM

引用

International Journal of Agricultural and Biological Engineering 2023年第2期16卷 199-206页

作者： Xin Wang Yu Yang Xin Zhao Min Huang Qibing Zhu Key Laboratory of Advanced Process Control for Light Industry Ministry of EducationJiangnan UniversityWuxi 214122JiangsuChina School of Physics and Electronic Electrical Engineering Huaiyin Normal UniversityHuai’an223300JiangsuChina

Crop coverage(CC)is an important parameter to represent crop growth characteristics,and the ahead forecasting of CC is helpful to track crop growth trends and guide agricultural management *** this study,a novel CNN-LSTM model that combined the advantages of convolutional neural network(CNN)in feature extraction and long short-term memory(LSTM)in time series processing was proposed for multi-day ahead forecasting of maize *** the influence of climate change on maize growth,five microclimatic factors were combined with historical maize CC estimated from field images as the input variables of the forecasting *** field experimental data of four observation points for more than three years were used to evaluate the performance of CNN-LSTM at the forecasting horizon of three to seven days ahead and compared the forecasting results to CNN and *** results demonstrated that CNN-LSTM obtained the lowest RMSE and the highest R2 at all forecasting ***,the performance of CNN-LSTM under univariate(historical maize CC)and multivariate(historical maize CC+microclimatic factors)input was compared,and the results indicated that additional microclimatic factors were effective in improving the forecasting ***,the 3-day ahead forecasting results of CNN-LSTM in different growth stages of maize were also analyzed,and the results showed that the highest forecasting accuracy was obtained in the seven leaves ***,CNN-LSTM can be considered a useful tool to forecast maize CC.

关键词： maize crop coverage multi-day ahead forecasting CNN-LSTM field images microclimatic factors

来源：评论

学校读者我要写书评

暂无评论

Evolutionary algorithm based on the evolution of Pareto archive and individual migration

Evolutionary algorithm based on the evolution of Pareto arch...

引用

作者： Qi, Rongbin Ma, Tianyi Sun, Fan Qian, Feng Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai China Shanghai Business School Shanghai China

An evolutionary algorithm based on the parallel evolution of multiple single objective populations and Pareto archive population is proposed, which is not only suitable for solving multi-objective optimization, but also effective for multimodal function. For each single objective population, single objective evolutionary algorithm is applied to optimize separately each of multi-objective functions, where individuals generated by tournament selection from the union of single objective and Pareto Archive population form the single objective population of next generation. Especially, individuals in Pareto archive population also join evolutionary operations. Simulations manifest that the proposed method can realize the search from multiple directions to obtain the non-dominated solutions scattered more uniformly over the Pareto frontier with better convergence metric compared to well-known NSGA-II algorithm. Individual migration from Pareto archive population by tournament selection is also proved to have the advantage in improving the converging speed and converging precision. Moreover, for multimodal single objective function, simulations also show that ideal optimizing solution can be obtained by properly separating single objective function into multi-objective function and applying the above method. © 2011 Zhejiang University.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Influence of flue gas radiative properties, burner geometry and shadow effects in steam cracking furnace simulations

Influence of flue gas radiative properties, burner geometry ...

引用

Computing and Systems Technology Division 2014 - Core Programming Area at the 2014 AIChE Annual Meeting

作者： Zhang, Yu Schietekat, Carl M. Van Geem, Kevin M. Qian, Feng Marin, Guy B. Laboratory for Chemical Technology Department of Chemical Engineering Ghent University Technologiepark 918 Zwijnaarde Belgium Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology 130 Meilong Road Shanghai China

来源：评论

学校读者我要写书评

暂无评论

Gross Error Detection and Data Reconciliation using Historical Data

引用

Procedia Engineering 2011年 15卷 55-59页

作者： Shaochao Sun Dao Huang Yanxue Gong Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education Ecust shanghai 20037 China

With the information technology applied widely to process industry, a large amount of historical data which could be used for obtaining the prior probabilities of gross error occurrence is stored in database. To use the historical data to enhance the efficiency of gross error detection and data reconciliation, a new strategy which includes two steps is proposed. The first step is that mixed integer program technique is incorporated to use the prior information to detect gross errors. The second step is to estimate all detected gross errors and adjust process data with material, energy, and other balance constrains. In this step an improved method is proposed to achieve the same effect with traditional method through adjusting the covariance matrix. Novel prior information criteria are described and performance of this new strategy is compared and discussed by applying the strategy for a challenging test problem.

关键词： data rectification gross error detection mixed integer program projection matrix historical data

来源：评论

学校读者我要写书评

暂无评论

Investigation of the trigger voltage walk-in effect in LDMOS for high-voltage ESD protection

引用

Journal of Semiconductors 2014年第9期35卷 56-59页

作者：梁海莲董树荣顾晓峰钟雷吴健于宗光 Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Department of Electronic Engineering Jiangnan University ESD Laboratory Department of Information Science and Electronic Engineering Zhejiang University China Electronic Technology Group Corporation No.58 Research Institute

The trigger voltage walkin effect has been investigated by designing two different laterally diffused metal-oxide-semiconductor （LDMOS） transistors with an embedded silicon controlled rectifier （SCR）. By inserting a P＋ implant region along the outer and the inner boundary of the N＋ region at the drain side of a conventional LDMOS transistor, we fabricate the LDMOS-SCR and the SCR-LDMOS devices with a different triggering order in a 0.5/zm bipolar-CMOS-DMOS process, respectively. First, we perform transmission line pulse （TLP） and DC-voltage degradation tests on the LDMOS-SCR. Results show that the trigger voltage walk-in effect can be attributed to the gate oxide trap generation and charge trapping. Then, we perform TLP tests on the SCR-LDMOS. Results indicate that the trigger voltage walk-in effect is remarkably reduced. In the SCR-LDMOS, the embedded SCR is triggered earlier than the LDMOS, and the ESD current is mainly discharged by the parasitic SCR structure. The electric potential between the drain and the gate decreases significantly after snapback, leading to decreased impact ionization rates and thus reduced trap generation and charge trapping. Finally, the above explanation of the different trigger voltage walk-in behavior in LDMOS-SCR and SCR-LDMOS devices is confirmed by TCAD simulation.

关键词： electrostatic discharge laterally diffused metal-oxide-semiconductor silicon control rectifier triggervoltage walk-in effect

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control for Continuous-time Markov Jump Linear Systems

Model Predictive Control for Continuous-time Markov Jump Lin...

引用

第27届中国控制与决策会议

作者： Gu Xinxin Wen Jiwei Peng Li Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) School of Internet of Things EngineeringJiangnan University

ISBN: (纸本)9781479970186

This paper mainly studies the continuous-time Markov Jump Linear Systems(MJLSs) problem based on model predictive control(MPC).Sufficient conditions of the optimization problem,which could guarantee the mean square stability of the close-loop MJLS,are given at every sample *** the MPC strategy is aggregated into continuous-time MJLSs,a discrete-time controller is employed to deal with a continuous-time plant and the adopted cost function not only refers to the knowledge of system state but also considers the sampling *** addition,the feasibility of MPC scheme and the mean square stability of the MJLS are deeply discussed by using the invariant ***,the main results are verified by a numerical example.

关键词： Continuous-time Markov jump linear systems,Model predictive control,Invariant ellipsoid

来源：评论

学校读者我要写书评

暂无评论

Computing reachable sets for linear discrete systems with bounded input 29

Computing reachable sets for linear discrete systems with bo...

引用

第29届中国控制与决策会议

作者： Chao Wang Lizhen Shao Guangda Hu Yadong Xu Key Laboratory of Advanced Control of Iron and Steel Process(Ministry of Education ) School of Automation and Electrical EngineeringUniversity of Science and Technology Beijing Department of mathematics Shanghai University

ISBN: (纸本)9781509046584

In this paper,an approximation method of reachable sets for linear discrete systems with bounded input is *** method finds boundary points of reachable sets by solving finite convex optimization *** not only constructs an inner approximation bounding but also an outer approximation *** numerical examples are used to demonstrate the validity of the *** to a recent Lyapunov-Krasovskii functional based approach,our method obtains much tighter bounding sets.

关键词： approximation of reachable sets optimization supporting points normal directions

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：