Guaranteed Cost Iterative Learning Control for Multi-Phase Batch Processes

Batch process is a typical multi-phase process. Due to the interaction between the phases of the batch process, high precision control in a single phase cannot guarantee high precision control of the whole batch process. In order to solve this problem, the guaranteed cost iterative learning control (ILC) of multi-phase batch processes is studied in this paper. Firstly, through introducing the output error, the state error and the extended information, the multi-phase batch process is transformed into an equivalent 2D switched system which has different dimensions. In addition, under the measurable condition, the guaranteed cost iterative learning control law with extended information is designed. The proposed control law ensures not only the stability of the system but also the optimal control performance. Next, in order to study the stability of the system and the minimum running time under the condition of stable running, the multi-Lyapunov function method is used. By means of the average dwell time method, the sufficient conditions ensuring system to be exponentially stable are given in the form of linear matrix inequality (LMI). Finally, the injection molding process is taken as an example to make simulation, which shows the feasibility and effectiveness of the proposed method.     

航路飞行冲突解脱策略的滚动时域优化

针对固定航路上2架航空器的冲突解脱问题, 在基于航向角和地速调整的静态单一最优解脱策略的基础上, 考虑航空器飞行过程中可能存在的速度扰动等不确定因素, 给出了一种基于滚动时域优化的动态混合最优解脱策略, 采用极大似然估计和牛顿-拉夫逊迭代算法对风矢量进行辨识, 对无扰动下的静态优化、航空器地速变化条件下的滚动时域优化以及风矢量变化条件下的滚动时域优化3种策略进行对比。分析结果表明: 调整航向角的最短解脱时间为195s, 调整地速的最短解脱时间为285s;第1架航空器减速、匀速、加速时, 解脱时间分别为240、215、150s;风矢量横向、纵向分量估计值的平均绝对误差分别为0.049、-0.067km·h^-1, 相对误差分别为0.173%、-0.205%;对风矢量进行辨识后解脱时间从215s减少为160s。可见, 基于风矢量辨识与滚动时域优化的动态混合最优解脱策略能够及时应对风矢量、航空器地速突然变化的情况, 具有较好的动态适应性。     

铁路风屏障防风效果代理模型优化

为确定铁路风屏障的最优参数,基于代理模型方法对风屏障防风效果进行了优化.首先,改进了网格搜索法以优化支持向量机回归模型的参数,并通过算例进行了验证.其次,以设置风屏障时的车辆气动特性为目标函数,建立了风屏障防风效果的优化模型.最后,利用风屏障的风洞试验结果,采用支持向量机回归建立了目标函数的代理模型,对风屏障的高度和透风率进行了优化.研究结果表明:改进的网格搜索法提高了支持向量机模型参数选择的准确性,当风屏障高度为1.91~2.90 m时,最优的风屏障透风率为0.00~0.17;当风屏障高度超过2.50 m后,增加风屏障的高度对防风效果的提高较为有限.      

Uncertainty Quantification for Structural Optimal Design Based on Evidence Theory

Uncertainty design can take account of aleatory and epistemic uncertainty in optimal processes.Aleatory uncertainty and epistemic uncertainty can be expressed as evidence theory uniformly, and evidence theory is used to describe the uncertainty. Transferring and response with evidence theory for structural optimal design are introduced. The principle of response evaluation is also set up. Finally, the cantilever beam in a test system is optimized in the introduced optimization process, and the results are estimated by the evaluation principle. The optimal process is validated after the optimization of beam.     

Stability Analysis for Stochastic Optimization Problems

Stochastic optimization offers a means of considering the objectives and constrains with stochastic parameters. However, it is generally difficult to solve the stochastic optimization problem by employing conventional methods for nonlinear programming when the number of random variables involved is very large. Neural network models and algorithms were applied to solve the stochastic optimization problem on the basis of the stability theory. Stability for stochastic programs was discussed. If random vector sequence converges to the random vector in the original problem in distribution, the optimal value of the corresponding approximation problems converges to the optimal value of the original stochastic optimization problem.     

����SVM�����ݲ��ԴITS�����ںϷ�����̽

在阐明ITS数据融合的意义及层次性的基础上，分析了数据层多源ITS数据融合及支持向量机的特点，根据支持向量机（SVM）的原理设计了利用支持向量机进行多源ITS数据融合的思路，并从支持向量机训练、训练结果评价以及支持向量机测试三个方面提出了该思路的实现步骤。在对日本阪神公路上堺入口的二源交通流数据进行支持向量机融合后，比较融合前后的数据，证明所提出的基于支持向量机技术的数据层多源ITS数据融合方法能够有效地进行数据质量控制，提高数据的精确度。     

基于手机运动传感器数据的交通流拥挤识别

准确的交通流状态识别是智能交通管理与控制的基础.通过所开发的手机端软件从手机中提取车辆的加速度与角加速度数据,在研究了其统计特征后,发现该数据可反应周围车辆对目标车辆运行环境的影响,从而与交通流状态的变化有着密切关系.利用支持向量机学习算法,以加速度与角加速度统计参数作为输入变量识别断面交通流状态.实验结果识别精度最高达到92%,表明加速度和角加速度指标可作为交通流状态的表征参数.该研究采用Lasso模型和最小角回归算法对输入参数进行变量选择,在降低计算成本的同时保证了良好的识别效果.      

复杂生产过程的小故障检测与分类方法

为监测复杂生产过程的状态,根据多元统计过程控制方法和支持向量机理论,将累积和控制图原理扩展为多变量的形式对过程数据进行预处理,并通过主元分析方法提取复杂生产过程的关键信息,得到有效的小故障数据,进而构建计算正常数据的统计量阀值及故障数据的Hotelling T平方统计值（T2）和平方预测误差值,实现了复杂生产过程的小故障模式检测,并采用支持向量机多分类方法将检测到的故障进行了分类.沥青混合料生产过程的仿真研究表明:在集料均值发生小波动、周期性上升和下降3种小故障模式下,故障检测识别率均达到95%,与主元分析方法相比平均提高了75%;分类准确率达到92.5%,与BP神经网络方法相比提高了19.3%.      

基于人工智能算法的隧道锚承载能力评价

针对隧道锚承载能力评价合理的解析计算公式缺乏、模型试验测试方法耗时费力、数值模拟可靠性不佳的问题,提出了一种人工智能化隧道锚承载能力预测方法.从隧道锚受力传力过程出发,分析了影响承载能力的因子,确定了承载能力评价指标体系;基于最小二乘支持向量机(least squares support vector machines...     

基于驾驶员偏好的最优路径选择

现实生活中,驾驶员往往依据自身偏好来选择路径,对不同的路径属性有不同的要求,且对其属性值存在一个可接受范围,而不是一个精确值. 本文对存在驾驶员偏好的最优路径选择问题进行了研究,提出了一种能够综合反映驾驶员偏好的最优路径选择方法. 首先基于可能度和区间数相离度的多属性决策方法,建立驾驶员偏好与路径属性总偏差最小的优化模型,并解出路径属性权重;其次算出各路径的综合属性值,建立路径间的可能度矩阵及其排序向量,据此选出最优路径;最后以算例进行验证,结果表明本文给出的路径选择方法具有很好的可行性和适用性.     

基于粒子群优化SVM的高速公路交通事件检测

为了更加准确地检测出高速公路上的偶发性交通事件,采用一种粒子群优化SVM参数的高速公路交通事件检测算法,提升事件检测效果。文中运用高速公路实测数据集（L880）,对支持向量机算法进行分类性能测试,并且采用改进的粒子群优化算法对支持向量机的参数进行优化,进而利用测试集数据对该模型进行验证比较,获得满意的检测效果。     

基于粒子群优化的高速公路网集成优化控制模型(英文)

应用非线性最优控制方法, 研究了高速公路网的匝道控制和路径诱导的集成问题, 构造了集成控制的最优控制模型。在模型中, 以路网总耗时最小为优化目标, 以METANET模型为网络交通流模型, 考虑了控制变量的更新周期约束, 采用粒子群优化技术求解优化模型。仿真结果表明: 无控制时, 路网总耗时为3376 veh·h; 仅实施匝道控制时, 路网总耗时为3005 veh·h; 仅实施路径诱导时, 路网总耗时为2768 veh·h; 集成控制时, 路网总耗时为2464 veh·h。可见, 集成控制效果最优。     

Structural Optimization of Hatch Cover Based on Bi-directional Evolutionary Structure Optimization and Surrogate Model Method

Weight reduction has attracted much attention among ship designers and ship owners. In the present work, based on an improved bi-directional evolutionary structural optimization (BESO) method and surrogate model method, we propose a hybrid optimization method for the structural design optimization of beam-plate structures, which covers three optimization levels: dimension optimization, topology optimization and section optimization. The objective of the proposed optimization method is to minimize the weight of design object under a group of constraints. The kernel optimization procedure (KOP) uses BESO to obtain the optimal topology from a ground structure. To deal with beam-plate structures, the traditional BESO method is improved by using cubic box as the unit cell instead of solid unit to construct periodic lattice structure. In the first optimization level, a series of ground structures are generated based on different dimensional parameter combinations, the KOP is performed to all the ground structures, the response surface model of optimal objective values and dimension parameters is created, and then the optimal dimension parameters can be obtained. In the second optimization level, the optimal topology is obtained by using the KOP according to the optimal dimension parameters. In the third optimization level, response surface method (RSM) is used to determine the section parameters. The proposed method is applied to a hatch cover structure design. The locations and shapes of all the structural members are determined from an oversized ground structure. The results show that the proposed method leads to a greater weight saving, compared with the original design and genetic algorithm (GA) based optimization results.     

Multi-Step Model Predictive Control Based on Online Support Vector Regression Optimized by Multi-Agent Particle Swarm Optimization Algorithm

As optimization of parameters affects prediction accuracy and generalization ability of support vector regression (SVR) greatly and the predictive model often mismatches nonlinear system model predictive control, a multi-step model predictive control based on online SVR (OSVR) optimized by multi-agent particle swarm optimization algorithm (MAPSO) is put forward. By integrating the online learning ability of OSVR, the predictive model can self-correct and adapt to the dynamic changes in nonlinear process well.     

智能三维位移反分析法在浅埋偏压隧道中的应用

支持向量机（Support Vector Machines,SVM）算法具有小样本、全局优化和泛化性能好的优点,且不存在过拟合的弊病.结合张石高速北口隧道浅埋偏压段的施工,将一种改进的支持向量机算法引入隧道工程位移反分析,并采用遗传算法在样本训练阶段自动搜索训练效果最优的SVM参数,建立起围岩力学和初始地应力参数与洞周位移的非线性SVM映射;然后,以遗传算法在围岩力学和初始地应力参数范围内,自动搜索能使SVM计算位移与实测位移最接近的参数组合,完成围岩力学和初始地应力参数的智能辨识.应用结果表明,这种新型的智能位移反分析法能在监测数据有限的情况下,高精度地反演辨识围岩力学与初始地应力场参数,为围岩变形超前预报提供计算参数以指导施工,并为类似工程提供借鉴.     

基于灰色自适应粒子群LSSVM的铁路货运量预测

为了提高铁路货运量的预测精度及建模速度,将灰色预测模型(GM(1,1))、最小二乘支持向量机(LSSVM)和自适应粒子群优化(APSO)算法相融合,建立了灰色自适应粒子群最小二乘支持向量机(GM-APSO-LSSVM)预测模型.通过灰色预测模型中的灰色序列算子,弱化原始数列随机性,挖掘数列中蕴含的规律,利用最小二乘支持向量机计算简便、求解速度快、非线性映射能力强的特点进行预测,并采用自适应粒子群算法优化选择LSSVM参数.对我国铁路货运量的实例分析表明:用该模型得到的评价指标RMSE、MAE、MPE和Theil不等系数分别为0.062 8、0.052 3、0.016 2和0.010 7,均小于其它模型,预测性能好;用APSO算法搜索LSSVM最优参数的时间为55.656 s,比传统交叉验证法减少了10.462 s;2006~2009年的预测相对误差分别为0.39%、-1.67%、1.44%和4.75%,适用于铁路货运量的短期预测.      

On-line Batch Process Monitoring and Diagnosing Based on Fisher Discriminant Analysis

Introduction Nowadays, it has been paying more attentionto the batch or semi-batch process which producedthe high added value and high quality products inchemical industry, such as polymer, pharmaceuti-cal and semiconductor industry.The aim of the batch process monitoring is tokeep the product quality uniform and consistentunder batch-to-batch process and meet specifica-tion limits. The direct approach is to monitor cru-cial product quality variables in batch process.However, quality variables…     

非稳态多模物流企业信息系统关键技术

转型期物流企业业务多模式且复杂多变的特点.构建此类物流企业的信息系统应从流程整合和系统结构优化入手,以保证系统的可调整和可拓展性.提出了包括业务活动标准化、子流程规范化和可配置化的核心流程的优化方法,以及以SOA技术、EDI技术和合理的结构层次划分为特征的系统结构方案.用案例验证了提出的方法和方案.     

基于3DCNN-DNN 的高空视频交通状态预测

为使用高空视频识别和预测道路交通状态，提出基于三维卷积神经网络-深度神经网络(3DCNN-DNN)的交通状态预测方法. 将道路切分为D 个路段，每个路段视频片段时长 m s，基于典型3DCNN结构C3D识别路段视频片段交通状态；建立道路? 个历史时段、D 个路段的交通状态矩阵Φ ，将道路交通状态预测问题转化为以Φ 为输入，有限交通状态为输出的分类问题，构建基于DNN的短时交通状态预测模型原型；建立交通视频数据集，对DNN预测模型原型的隐藏层数量、神经元数量及训练批大小进行测试优化，提出有4 隐藏层，各层神经元数量为64/128/128/64，训练批大小为64 的优化模型DNN*.测试结果表明：C3D视频交通态识别平均F1 值为95.71%，DNN*道路交通状态预测准确率为91.18%，比DNN线性分类、KMeans 、KNN、SVM和线性分类分别高6.86%、57.85%、62.26%、26.47%、43.14%；C3D能提供准确的交通状态矩阵，3DCNN-DNN可有效识别和预测道路视频交通状态.     

自供电路侧单元能量-时延均衡分组调度策略

考虑了自供电路侧单元在分组传输过程中能量收集、车辆到达与车速的随机性, 基于受限马尔科夫决策模型建立分组调度系统模型, 研究了分组平均传输时延与能量消耗; 分析了在能量队列约束下最小分组平均传输时延的优化问题, 提出了自供电路侧单元能量-时延均衡分组调度策略, 通过仿真试验分析了最优分组调度策略性能, 并与贪婪中继方案和Q-learning算法进行对比。仿真结果表明: 该分组调度策略具有双门限结构, 系统通过自供电路侧单元的能量队列状态以及到达车辆的车速状态确定决策变量, 使系统可以在考虑能量利用效率的前提下降低监测数据分组的平均传输时延, 保证自供电路侧单元在能量存储不溢出不耗尽的同时, 最小化系统分组平均传输时延; 在单分组发送模型中, 提出的分组调度策略的平均传输时延相比贪婪中继方案降低了15.7%, 相比Q-learning算法降低了13.5%;在批量分组发送模型中, 其分组平均传输时延相比贪婪中继方案降低了20.4%, 相比Q-learning算法降低了11.5%。