检索结果-南通市图书馆

A Novel Interacting Multiple-Model Method and Its Application to Moisture Content Prediction of ASP Flooding

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2018年第1期114卷 95-116页

作者： Shurong Li yulei ge Renlin Zang Automation School Beijing University of Posts and TelecommunicationsBeijingChina College of Information and Control Engineering China University of Petroleum(East China)QingdaoChina

In this paper,an interacting multiple-model(IMM)method based on datadriven identification model is proposed for the prediction of nonlinear dynamic ***,two basic models are selected as combination components due to their proved *** is Gaussian process(GP)model,which can provide the predictive variance of the predicted output and only has several optimizing *** other is regularized extreme learning machine(RELM)model,which can improve the overfitting problem resulted by empirical risk minimization principle and enhances the overall generalization *** both of the models are updated continually using meaningful new data selected by data selection ***,recursive methods are employed in the two models to reduce the computational burden caused by continuous ***,the two models are combined in IMM algorithm to realize the hybrid prediction,which can avoid the error accumulation in the single-model *** order to verify the performance,the proposed method is applied to the prediction of moisture content of alkali-surfactant-polymer(ASP)*** simulation results show that the proposed model can match the process very *** IMM algorithm can outperform its components and provide a nice improvement in accuracy and robustness.

关键词： Interacting multiple model regularized extreme learning machine gaussian process moisture content of ASP flooding

A Possibilistic Programming Approach Based on Trapezoidal Possibility Distribution and Its Application in Oil Field Exploitation 36

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Possibilistic Programming Approach Based on Trapezoidal Po...

Numerical Computation of a Mixed-Integer Optimal Control Problem Based on Quantum Annealing

第36届中国控制会议

作者： Zhe Liu Shurong Li yulei ge College of Information and Control Engineering China University of Petroleum（East China）

ISBN: (纸本)9781538629185

Against a low accuracy for people to solve fuzzy assignment problem by using possibilistic programming approach,an improved algorithm based on trapezoidal possibility distribution is given in this *** possibility distribution has comparative complex membership function,so we can process actual decision information better and reflect decision maker’s subjectivity much *** the improved possibilistic programming approach is used to solve a fuzzy multi-objective assignment problem in oil field exploitation,which contains imprecise objective functions and fuzzy relation ***,we obtain a regular conclusion in which the decision maker can acquire different appropriate schemes by changing aspiration *** acquired optimal assignment schemes in oil field exploitation verify the feasibility and effectiveness of the improved algorithm.

关键词： trapezoidal fuzzy numbers oil field exploitation fuzzy mathematical programming

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2020年第5期25卷 623-629页

作者： LIU Zhe LI Shurong ge yulei Automation School Beijing University of Posts and TelecommunicationsBeijing 100876China Qingdao Topscomm Communication Co. Ltd..Qingdao 266024ShandongChina

It is extremely challenging to solve the mixed-integer optimal control problems(MIOCPs)due to the complex computation in solving the integer decision *** paper presents a new method based on quantum annealing(QA)to solve *** QA is a metaheuristic which applies quantum tunneling in the annealing *** has a faster convergence speed in optimal-searching and is less likely to run into local ***,QA is applied to deal with this kind of optimization ***,MIOCP is transformed into a mixed-integer nonlinear programming(MINLP).Then,a method based on QA is adopted to solve the MINLP and acquire the optimal *** last,two benchmark examples including Lotka-Volterra type fishing problem and distillation column are presented and *** effectiveness of the metliodology is verified by the acquired optimal schemes.

关键词： mixed-integer optimal control quantum annealing distillation column

A Switch Control based Dynamic Optimization of Polymer Flooding

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Switch Control based Dynamic Optimization of Polymer Flood...

A New Wavelet Neural Network with Boundary Value Constraints

第37届中国控制会议

作者： Shurong Li Zhe Liu yulei ge College of Automation Beijing University of Posts and Telecommunications College of Information and Control Engineering China University of Petroleum (East China)

Polymer flooding for oil field reservoir is one of the most important technologies to enhance oil recovery and increase profits. Against the issue of uncertainty and fluctuation of crude oil price, a fuzzy multi-objective optimization model will be established and solved by an improved possibilistic programming algorithm based on Gaussian probability distribution in this paper. A switch control variable with respect to concentration of injected polymer will be also introduced and solved to reduce exploitation cost and increase the net present value. Additionally, we will obtain an actual optimal exploitation scheme by using genetic algorithm and the acquired optimal exploitation scheme in oil field exploitation verifies the feasibility and effectiveness of the improved algorithm based on switch control.

关键词： dynamic programming switch control polymer flooding Gaussian probability distribution

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A New Wavelet Neural Network with Boundary Value Constraints

基于RBF神经网络的油藏相对渗透率曲线计算

第37届中国控制会议

作者： Lu Han Shurong Li yulei ge College of Information and Control Engineering China University of Petroleum (East China) College of Automation Beijing University of Posts and Telecommunications

A new wavelet neural network（WNN） with boundary value constraints（BVC） is proposed in this paper. The network has a novel topology, which is able to satisfy a series of BVC automatically. The difference of the proposed network with conventional WNN is that the proposed BVC-WNN considers not only the prior knowledge, but also the observation data. Here the prior knowledge means the BVC. The orthogonal least squares algorithm（OLS） is applied to identify the BVC-WNN. And the ability of satisfying BVC is discussed in this paper. By comparing the simulation result for a numerical example using BVC-WNN and conventional WNN, the experimental result proves that the BVC-WNN has better accuracy.

关键词： wavelet neural network(WNN) boundary value constraints(BVC) priority knowledge orthogonal least squares algorithm(OLS)

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

化工学报 2013年第12期64卷 4571-4577页

作者：葛玉磊李树荣中国石油大学(华东)信息与控制工程学院山东青岛266580

提出了一种基于改进的RBF神经网络的相对渗透率曲线计算方法。利用骨干粒子群的位置更新操作更新RNA遗传算法的变异算子得到混合RNA遗传算法(HRGA),针对RBF神经网络中隐含层径向基中心值的确定,利用HRGA算法对其进行优化,并用于相对渗... 详细信息

提出了一种基于改进的RBF神经网络的相对渗透率曲线计算方法。利用骨干粒子群的位置更新操作更新RNA遗传算法的变异算子得到混合RNA遗传算法(HRGA),针对RBF神经网络中隐含层径向基中心值的确定,利用HRGA算法对其进行优化,并用于相对渗透率曲线的计算。将HRGA优化的RBF神经网络和标准RBF神经网络计算的相对渗透率曲线与真实值误差对比分析,实验结果表明HRGA优化的RBF神经网络明显提高了计算精度。

关键词： RBF神经网络混合RNA遗传算法骨干粒子群径向基中心值相对渗透率

在线全文

学校读者我要写书评

暂无评论

开式逆流能源塔传热传质特性分析

太阳能学报 2018年第6期39卷 1581-1587页

作者：葛宇磊张欢由世俊郑万冬天津大学环境科学与工程学院

以开式逆流能源塔为研究对象,建立开式逆流能源塔传热传质数学模型,并运用Matlab软件对数学模型进行求解。通过对开式逆流能源塔热泵实际冬季工况的测试,对数学模型的正确性进行验证。并运用所建立的数学模型对能源塔冬季传热传质的特... 详细信息

以开式逆流能源塔为研究对象,建立开式逆流能源塔传热传质数学模型,并运用Matlab软件对数学模型进行求解。通过对开式逆流能源塔热泵实际冬季工况的测试,对数学模型的正确性进行验证。并运用所建立的数学模型对能源塔冬季传热传质的特性进行分析,得出提高能源塔空气进口干球温度和含湿量,降低载冷剂进口温度,能够增加能源塔换热量的结论。

关键词：能源塔开式逆流数值模拟传热传质

一种求解化工动态优化问题的改进磷虾觅食优化算法

在线全文

学校读者我要写书评

暂无评论

系统科学与数学 2016年第7期36卷 961-972页

作者：臧人霖李树荣葛玉磊常鹏中国石油大学(华东)信息与控制工程学院青岛266580

智能算法原理简单、容易实现,且具有良好的全局收敛能力,近年来被广泛应用于化工过程的动态优化问题.提出一种改进的磷虾觅食优化算法求解化工动态优化问题.该算法通过跟踪磷虾种群的变化来更新速度因子,提高收敛速度;引入自适应柯西变... 详细信息

智能算法原理简单、容易实现,且具有良好的全局收敛能力,近年来被广泛应用于化工过程的动态优化问题.提出一种改进的磷虾觅食优化算法求解化工动态优化问题.该算法通过跟踪磷虾种群的变化来更新速度因子,提高收敛速度;引入自适应柯西变异,增强了算法跳出局部最优值的能力.针对化工动态优化问题,首先通过控制向量参数化方法将其转化为非线性规划问题,并引入变时间区间分布法来优化区间划分,然后利用改进算法进行求解.最后,将改进算法应用于多个化工动态优化问题中,仿真结果表明,该算法具有良好的可行性.

关键词：磷虾觅食优化算法动态优化控制向量参数化变时间区间分布法

在线全文

学校读者我要写书评

暂无评论

迭代步进值自适应调整的果蝇优化算法

计算机工程与应用 2016年第3期52卷 32-36页

作者：常鹏李树荣葛玉磊卢松林中国石油大学(华东)信息与控制工程学院山东青岛257061

针对传统果蝇优化算法(FOA)收敛精度不高和易陷入局部最优的缺点,提出了一种迭代步进值自适应调整的果蝇优化算法(FOAMR)。在该算法中,引入了果蝇群体速度进化因子和聚集度因子,并将迭代步进值表示为以上2个参数的函数同时定义自适应调... 详细信息

针对传统果蝇优化算法(FOA)收敛精度不高和易陷入局部最优的缺点,提出了一种迭代步进值自适应调整的果蝇优化算法(FOAMR)。在该算法中,引入了果蝇群体速度进化因子和聚集度因子,并将迭代步进值表示为以上2个参数的函数同时定义自适应调整因子。在每次迭代时,算法根据当前果蝇群体速度进化因子和聚集度因子动态调整步进值的大小并通过自适应调整因子动态调整搜索距离的大小。对典型函数的测试结果表明,FOAMR比FOA具有更好的全局搜索能力,同时收敛速度、收敛精度明显提高。

关键词：果蝇优化算法迭代步进值速度进化因子聚集度因子