层流冷却过程混合智能参数辨识

热轧层流冷却过程带钢温度难以连续检测,其换热系数具有随工况频繁变化而变化、动态特性具有时变、强非线性等综合复杂特性.正确辨识热轧层流冷却过程带钢温度的离散动态模型中的换热系数是提高模型精度的关键.本文将案例推理技术和神经网络技术相结合,提出了混合智能参数辨识方法.采用某钢铁公司热轧层流冷却过程实际运行数据对所提出的方法进行实验研究.结果表明本文提出的混合智能参数辨识方法大大提高了层流冷却过程带钢温度预报精度.     

规则与数据驱动的层流冷却过程带钢卷取温度模型

针对现有层流冷却过程带钢温度模型缺乏换热系数、带钢定位、带钢卷取温度计算的有效方法这一问题,提出了由冷却单元阀门开闭状态模型、带钢冷却单元定位模型、不同换热方式下的带钢温度模型组成的带钢卷取温度动态模型,将案例推理、规则推理、 神经网络等相结合,提出了规则与数据驱动的模型参数智能辨识方法.采用某钢厂实际生产运行数据对所提出的带钢卷取温度动态模型进行了实验研究,实验结果表明本文提出的方法能够有效提高带钢卷取温度模型的精度.     

案例推理及迭代学习在层流冷却控制中的应用

现有的卷取温度预报补偿模型和带钢批次间补偿模型中,由于案例推理(Case-based reasoning, CBR)系统中检索特征权重系数采用人工凑试的方法,难以获得满意的补偿作用,且由于缺乏迭代学习的初始工况条件的匹配算法,难以进行准确匹配和有效迭代.因此,本文针对这两个问题, 提出了基于神经网络技术的案例推理系统检索特征权重系数自动学习算法及迭代学习技术初始工况匹配算法,改进了卷取温度预报补偿模 型和带钢批次间补偿模型,并采用国内某大型钢厂的现场实际数据进行实验研究.实验结果表明,与原有方法相比,带钢卷取温度的控制偏差减小了1.63℃,卷取温度精度控制在±10℃以内的命中率提高了14.5%.     

冷连轧动态过程混合智能建模方法

针对具有非线性、多变量、强耦合、参数不确定等综合复杂特性的多机架冷连轧动态过程，在工作点附近建立基于轧制过程动态机理方程的线性状态空间模型，提出基于RBF 的轧机出口带钢速度模型以及机架间厚度延时估计方法，采用案例推理技术实现线性化多模型选择算法，研制了冷连轧动态过程的混合智能模型.使用某钢厂五机架四辊冷连轧机系统的实际生产过程数据进行仿真实验，在实际板厚控制系统的设定和轧件的扰动下，本文提出模型的各机架轧制力、冷轧板厚度和张力仿真结果与实际值的变化趋势相同，最大误差小于20%.     

Hot-rolled strip laminar cooling process plant-wide temperature monitoring and control

The hot-rolled strip laminar cooling (HSLC) process is important to the production quality in hot-rolled strip product line. How to monitor the strip's transient temperature and accurately control the coiling temperature (CT) are the problems in HSLC since the strip temperature can hardly be measured inside the cooling section. In this paper, a modified EKF with trade-off feed-back coefficient is implemented to reconstruct the spatial distribution of strip temperature. It has the advantages of simple designation, having reasonable convergence rate and stability. Then a novel control strategy based on the designed EKF and model predictive control (MPC) is proposed for HSLC to improve the precision of CT. In MPC, a predictor is employed to predict the future temperature sequence at the inlet of fine cooling zone to further improve the performance of MPC. Finally, the reliability and performance of the proposed monitoring and control method were demonstrated by the experimentations in one HSLC manufactory.     

Distributed model predictive control for plant-wide hot-rolled strip laminar cooling process

Since hot-rolled strip laminar cooling (HSLC) process is a large-scale, nonlinear system, a distributed model predictive control (DMPC) framework is proposed for computational reason and enhancing the precision and flexibility of control system. The overall system is divided into several interconnected subsystems and each subsystem is controlled by local model predictive control (MPC). These local MPCs cooperate with its neighbours through the scheme of neighbourhood optimization for the improvement of global performance. The state space representation of each subsystem’s prediction model is designed by finite volume method firstly, and then is linearized around the current operating point at each step to overcome the computational obstacle of nonlinear model. Moreover, since the strip temperature is measurable only at a few positions in water cooling section due to the difficult ambient conditions, an Extended Kalman Filter (EKF) is used to estimate the transient temperature of strip. Both simulation and experiment results prove the efficiency of the proposed method.     

层流冷却过程喷水系统的智能设定方法

针对热轧层流冷却过程具有强非线性、分布参数和时变等综合复杂特性,提出了基于案例推理技术的层流冷却过程喷水系统的智能设定方法.层流冷却过程的典型工况及喷水系统设定值以案例的形式存于案例库,对于待冷却的带钢,根据当前的工况描述特征在案例库中检索匹配的历史案例,经推理完成当前工况下喷水控制系统的设定.采用某钢铁公司热轧层流冷却生产过程的实际数据进行仿真实验,结果表明所提出的智能设定方法在工况变化时是有效的.     

一种净化过程钻离子浓度的混合智能预测方法

针对锌湿法冶炼净化过程的复杂性,提出了一种结合粒子群算法和案例推理方法的净化过程Ⅱ段出口钴离子浓度混杂预测模型.考虑到不同时期案例所起的作用不一样,提出了一种综合加权相似函数.针对案例推理方法中属性权重选择和近邻个数的选取问题,提出了带有变异的惯性权重自适应粒子群算法优化方法,优化最近邻算法中特征权重矢量和近邻数,提高案例的检索精度.以净化过程生产数据进行实验验证和对比分析,计算结果表明改进的案例推理模型精度优于神经网络模型,模型预测结果可以作为过程信息用于净化过程的优化控制.     

Parameter calibration framework for environmental emergency models

Simulation systems that predict the propagation of environmental emergencies have to satisfy hard real-time constraints to prevent tragedy. To obtain more reliable forecasts, input parameter calibration mechanisms should be integrated because it is often impossible to measure highly dynamic input parameters in a correct and timely manner. Evolutionary optimisation methods showed promising calibration potential but involve numerous expensive fitness evaluations. This makes their application to time-restricted real-world problems impractical, especially when only limited computing resources are available. We therefore propose a framework for efficient parameter calibration based on evolutionary intelligent systems. A genetic algorithm is joined with a case-based reasoner to form a hybrid calibration approach. The suggested framework allows the user to select the configuration of the calibration process according to emergency and prediction characteristics and available computing resources. The possibility to generate quick calibration estimates thus minimising the additional computational effort caused by the introduction of parameter calibration is highlighted. The framework was tested in the area of forest fire spread prediction. A case base was generated from real historical and synthetical forest fires. Experiments show that case-based reasoning generates results comparable to pure evolutionary optimisation approaches, clearly outperforming the latter in runtime.     

基于人机一体的混合智能创新设计

如何应用智能技术进行创新设计是制造领域的研究热点。该文在分析和总结当前智能设计方法的基础上,将进化思想引入创新设计过程,以人类设计师为主导,将改进遗传算法与基于实例推理的产品设计方法结合起来,集成人机智能进行产品设计,实现了基于人机一体的混合智能创新设计。     

基于混合智能的航天器故障诊断系统

面向航天器测控管理,研究了一种基于专家系统（ES）、案例推理（CBR）以及故障树（FT）的混合智 能诊断技术．文中,故障树双向混合推理机制被用于实现航天器故障定位和预测．同时案例推理的k 最近邻检索 策略（KNN）采用了简单实用、易收敛特性的多感官群集算法（MSA）．基于案例推理和故障树的航天器专家系 统（SESCF）采用了2 种融合模式．案例推理和故障树采用独立运行模式,专家系统与案例推理和故障树之间则采 用了松耦合运行模式．出于改善推理效率的目的,文中提出了一种将遥测信息转化为语义信息的结合特定推理方法 的非线性转换方法．某卫星供配电分系统的测试证实了SESCF 系统诊断的有效性．测试结果表明,相对于专家系 统,SESCF 系统具有更高的诊断准确度和可靠性．SESCF 系统采用的非线性转换方法在航天器故障诊断过程中简 单实用且容错性较好．     

磁选管回收率智能混合预报方法

针对衡量竖炉焙烧过程焙烧矿质量好坏的关键工艺指标磁选管回收率难以在线测量、化验结果滞后的难题，采用神经网络、案例推理和专家系统技术，提出了由神经网络预报模型、案例推理预报模型、自校正模型组成的磁选管回收率智能混合预报模型，讨论了模型的结构、主要功能和实现算法，并成功应用于赤铁矿选矿厂竖炉焙烧过程．应用效果表明，在工况正常与异常两种情况下，所提出的方法均能准确预报磁选管回收率．将磁选管回收率预报模型应用于竖炉焙烧过程的优化控制，使磁选管回收率保持在最优工艺指标范围之内，取得了明显的成效．     

基于案例推理的层流冷却过程建模

针对具有非线性,参数时变,分布参数等综合复杂特性的热轧层流冷却过程,将机理建模方法与案例推理技术相结合,通过使用层流冷却过程中带钢的运行工况构造案例,在案例库中检索与其匹配的历史案例,利用实际工况的特征与匹配工况的特征经过推理给出当前工况的模型参数,从而确定层流冷却过程的动态模型.利用这一模型可以预测整个冷却过程中带钢的温度变化过程.通过某钢铁公司热轧层流冷却过程实际数据的实验比较表明所提出的建模方法是有效的.     

基于遗传算法和案例推理的软件费用估算方法

为了提高类比法的估算精度,减少人工检索案例的工作量和难度,提出了一种基于遗传算法和案例推理的软件费用估算方法。给出了案例推理过程的估算步骤,构造了案例的相似性度量函数;设计了用于案例推理问题的遗传算法,利用该算法在历史数据库中搜索与目标案例最相似的项目,并对软件项目的特征权重进行优化;借助Albrecht和Desharnais数据库,对提出的方法进行分析。实验结果表明,该方法可以在软件生命周期的早期显著提高软件费用的估算精度,与类比估算和线性回归方法相比,具有更小的平均误差率,其估算性能符合相关行业软件的估算需求。     

铅锌烧结配料过程的智能集成建模与综合优化方法

以铅锌烧结配料过程为背景, 针对传统配料方法中存在的成本高和准确率低的问题, 提出一种智能集成建模与综合优化方法. 首先, 在建立过程神经网络模型和改进灰色系统预测模型的基础上, 利用信息论中熵值的概念, 提出一种既可保证预测精度又能满足配料计算对数据完备性要求的烧结块成分集成预测模型; 其次, 以成本最小为目标建立烧结配料优化模型, 采用基于专家推理策略和改进免疫遗传算法的定性定量综合集成方法, 实现烧结配料的优化. 仿真结果验证了该方法的有效性.     

基于遗传算法的层流冷却系统优化控制策略

为进一步提高层流冷却系统的控制精度, 不仅要满足对卷取温度的要求, 还要满足控制冷却对冷却速率的要求. 本文以热连轧层流冷却系统的粗调区为研究对象. 综合考虑层流冷却控制系统的两个控制目标: 目标卷取温度与目标冷却速率, 直接将粗调区集管的开闭模式作为染色体的编码, 应用遗传算法搜索粗调区集管开闭的最佳模式. 最后对整个冷却控制系统进行了仿真, 结果表明采用该控制策略明显优于简单的前端密集冷却模式.     

支持向量机与神经网络相结合的板带凸度预测

为提高热轧生产过程中板带凸度的预测精度,提出了一种将粒子群优化算法(particle swarm optimization, PSO)、支持向量回归(support vector regression, SVR)和BP神经网络(back propagation neural network, BPNN)相结合的板带凸度预测模型。采用PSO算法优化SVR模型的参数,建立了PSO-SVR板带凸度预测模型,提出采用BPNN建立板带凸度偏差模型与PSO-SVR板带凸度模型相结合的方法对板带凸度进行预测。采用现场数据对模型的预测精度进行验证,并采用统计指标评价模型的综合性能。仿真结果表明,与PSO-SVR、SVR、BPNN和GA-SVR模型进行比较,PSO-SVR+BPNN模型具有较高的学习能力和泛化能力,并且比GA-SVR模型运算时间短。     

热轧带钢层流冷却控制方法

针对热轧带钢层流冷却终冷温度范围的扩大以及控制精度提高的要求,通过分析影响层流冷却过程的关键性因素如,速度、厚度、喷水量对终轧温度的影响,以及各因素之间相互的作用关系,合理制定出层流冷却的初始值,并建立起层流冷却温度控制的数学模型。运用前馈控制、速度补偿控制的思想以及针对层流冷却特点的线性叠加控制对层流冷却过程进行实时控制。所提出的方法成功运用于某层流冷却生产模型中,实现了终冷温度范围扩大以及控制精度提高的目标。     

FSfRT: FORECASTING SYSTEM FOR RED TIDES. A HYBRID AUTONOMOUS AI MODEL

A hybrid neuro-symbolic problem-solving model is presented in which the aim is to forecast parameters of a complex and dynamic environment in an unsupervised way. In situations in which the rules that determine a system are unknown, the prediction of the parameter values that determine the characteristic behavior of the system can be a problematic task. In such a situation, it has been found that a hybrid case-based reasoning system can provide a more effective means of performing such predictions than other connectionist or symbolic techniques. The system employs a case-based reasoning model that incorporates a growing cell structures network, a radial basis function network, and a set of Sugeno fuzzy models to provide an accurate prediction. Each of these techniques is used at a different stage of the reasoning cycle of the case-based reasoning system to retrieve historical data, to adapt it to the present problem, and to review the proposed solution. This system has been used to predict the red tides that appear in the coastal waters of the north west of the Iberian Peninsula. The results obtained from experiments, in which the system operated in a real environment, are presented.     

A case-based reasoning system with the two-dimensional reduction technique for customer classification

Many studies have tried to optimize parameters of case-based reasoning (CBR) systems. Among them, selection of appropriate features to measure similarity between the input and stored cases more precisely, and selection of appropriate instances to eliminate noises which distort prediction have been popular. However, these approaches have been applied independently although their simultaneous optimization may improve the prediction performance synergetically. This study proposes a case-based reasoning system with the two-dimensional reduction technique. In this study, vertical and horizontal dimensions of the research data are reduced through our research model, the hybrid feature and instance selection process using genetic algorithms. We apply the proposed model to a case involving real-world customer classification which predicts customers’ buying behavior for a specific product using their demographic characteristics. Experimental results show that the proposed technique may improve the classification accuracy and outperform various optimized models of the typical CBR system.