基于果蝇优化算法的LSSVR干燥速率建模

回转干燥窑由于干燥速率难以在线测量,其干燥速率模型的建立一直是一大难题.在分析干燥速率建模的基础上,提出将最小二乘支持向量机运用到干燥速率建模,及其基于免疫-果蝇优化算法的最小二乘支持向量机回归参数优化方法( IAFOALSSVR).首先利用预处理的干燥过程数据进行模型的训练,利用免疫-果蝇算法对模型参数进行寻优,然后获得最优参数并建立最优模型,通过使用该改进方法建立干燥速率模型与其他算法优化的模型进行对比,结果表明该优化方式在干燥速率建模精度上与其它智能算法相当,在计算效率上要优于其它算法.     

基于混沌混合优化的回转干燥窑出料含水量软测量

回转干燥窑由于出料含水量难以在线测量,其过程控制一直是一大难题.本文在分析回转干燥窑干燥过程的基础上,提出了基于分布式RBF网络的出料含水量软测量模型及其优化学习算法,首先根据先验知识和聚类将输入空间划分成多个子空间,对于每个子空间的RBF网络,由FCM算法和分区校验熵确定隐含节点数,中心向量的学习采用混沌优化与FCM相结合的混合算法.设计了获取样本数据的实验,得到了出料含水量软测量模型,此模型已成功应用于干燥窑的推断控制中.     

一种带过程变量时滞估计的在线软测量建模方法

为了有效地将时滞信息引入到软测量建模过程中,同时实时跟踪过程动态,本文提出一种基于模糊曲线分析（FCA）估计过程时滞参数的新方法,用离线条件下得到的时滞参数集对软测量建模的数据进行重构;对于新的输入数据,基于一定时刻之前采集的历史变量值,采用时间差—高斯过程回归（TDGPR）模型对当前时刻主导变量值进行在线预测．通过对脱丁烷塔过程的仿真研究,验证了所提方法的有效性和精度.     

The Hybrid Fuzzy Least-Squares Regression Approach to Modeling Manufacturing Processes

Uncertainty in manufacturing processes is caused both by randomness, as in material properties, and by fuzziness, as in the inexact knowledge. Previous research has seldom considered these two types of uncertainty when modeling manufacturing processes. In this paper, a hybrid fuzzy least-squares regression (HFLSR) approach to modeling manufacturing processes, which does take into consideration these two types of uncertainty, is proposed and described, and a new form of weighted fuzzy arithmetic is introduced to develop the hybrid fuzzy least-squares regression method. The proposed HFLSR approach not only features the capability of dealing with the two types of uncertainty, but also addresses the consideration of replication of responses in experiments. To investigate the effectiveness of the proposed approach to process modeling, it was applied to the modeling solder paste dispensing process. Modeling results were compared with those based on statistical regression and fuzzy linear regression. It was found that the accuracy of prediction based on the HFLSR is slightly better than that based on statistical regression and much better than that based on the Peters fuzzy regression.     

稀土萃取过程组分含量的神经网络软测量方法

Throught fusion of the mechanism modeling and the neural networks modeling, a component content soft-sensor, which is composed of the equilibrium calculation model for multi-component rare earth extraction and the error compensation model of fuzzy system, is proposed to solve the problem that the component content in countercurrent rare-earth extraction process is hardly measured on-line. An industry experiment in the extraction Y process by HAB using this hybrid soft-sensor proves its effectiveness.     

基于自适应模糊聚类的神经网络软测量建模方法

提出一种基于模糊聚类的神经网络软测量建模方法．该方法采用数据分组训练、自动确定模糊分类数、在线测量时分类中心自适应修正，降低了计算量，提高了建模精度．将该算法用于步进式加热炉钢坯温度预报的仿真结果表明，它能够解决钢坯温度难以在线测量的问题。     

A new model-free adaptive sliding controller for active suspension system

Active suspension systems are designed to provide better ride comfort and handling capability in the automotive industry. Since the active suspension system has nonlinear and time-varying characteristics, it is difficult to establish an accurate dynamic model for designing a model-based controller. Here, a functional approximation (FA) based adaptive sliding controller with fuzzy compensation is proposed for an active suspension system. The FA technique is employed to represent the unknown functions, which releases the model-based requirement of the sliding mode control. In addition, a fuzzy control scheme with online learning ability is employed to compensate for the modeling error of the FA with finite number of terms for reducing the implementation difficulty. To guarantee the control system stability, the update laws of the coefficients in the approximation function and the fuzzy tuning parameters are derived from the Lyapunov theorem. The proposed controller is employed on a quarter-car active suspension system. The simulation results and experimental results show that the proposed controller can suppress the oscillation amplitude of the sprung mass effectively. To evaluate the performance improvement of inducing a fuzzy compensator in this FA adaptive controller, the dynamic responses of the proposed hybrid controller are compared with those of FA-based adaptive sliding controller only.     

椭球定界算法在混合建模中的应用研究

并行结构混合建模主要由机理模型与误差补偿模型组成.一般地,误差补偿模型不宜过于复杂,且模型应具有校正功能,以免精度随时间不断下降.针对这个问题,本文选择单层神经网络作为误差补偿模型,并将椭球定界算法应用于单层神经网络的参数更新,不仅能够保证建模误差稳定有界,同时能够提高网络的收敛速度.将提出的方法应用于氧化铝生产过程,改进了原有的苛性碱和氧化铝组 分浓度软测量方法.实验研究结果表明,椭球定界算法的应用提高了模型的精度和网络的收敛速度.除此之外,在存在噪声干扰下,改进 的方法比原有方法更稳定,进一步证明了方法的有效性和优越性.     

基于递阶分解聚类的非线性系统递推模糊辨识

提出一种基于递阶分解聚类的递推模糊辨识方法．采用半模糊化方法对论域内的样本进行归类,根据各子集“线性化”程度评判模糊聚类的有效性,通过对性能最差的子集进行分解并辨识新增子模型的参数,逐步完成整个样本空间的模糊划分和模型辨识过程．在线辨识时采用递推最小二乘算法对模糊规则进行修正,同时可根据建模精度的要求删除性能最差的规则,并确立新模糊规则．仿真研究表明了该方法的有效性．     

基于模糊T-S模型的批过程建模与最优控制

基于模糊T-S模型,提出一种具有自学习能力的模糊方法用于批过程建模和最优控制.通过引入与均方误差相关的动态误差传递因子,使用改进的梯度下降法,本方法能够辨识模糊T-S预测模型.对于批过程的受限非线性最优控制,基于所辨识的预测模型,运用庞特里亚金最小值原理和平行分布补偿算法,本方法能够把一个复杂非线性系统最优控制设计问题转化为一些基于复杂T-S预测模型的局部线性系统的最优问题,从而给出一种有效和简单的模糊最优控制策略.所提方法用于一个半连续式反应器的建模和最优控制,仿真结果表明新方法是有效和准确的.     

Online fuzzy modeling with structure and parameter learning

This paper describes a novel nonlinear modeling approach with fuzzy rules and support vector machines. Structure identification is realized by an online clustering method and fuzzy support vector machines, the fuzzy rules are generated automatically. Time-varying learning rates are applied for updating the membership functions of the fuzzy rules. The modeling errors are proven to be robustly stable with bounded uncertainties by a Lyapunov method and an input-to-state stability technique. Comparisons with other related works are made through an application of gas furnace process. The results demonstrate that our approach has good accuracy, and this method is suitable for online fuzzy modeling.     

基于误差补偿的复杂场景下背景建模方法

在基于子空间学习的背景建模方法中,利用背景信息对前景误差进行补偿有助于建立准确的背景模型.然而,当动态背景（摇曳的树枝、波动的水面等）和复杂前景等干扰因素存在时,补偿过程的准确性和稳定性会受到一定的影响.针对这些问题,本文提出了一种基于误差补偿的增量子空间背景建模方法.该方法可以实现复杂场景下的背景建模.首先,本文在误差补偿的过程中考虑了前景的空间连续性约束,在补偿前景信息的同时减少了动态背景的干扰,提高了背景建模的准确性.其次,本文将误差估计过程归结为一个凸优化问题,并根据不同的应用场合设计了相应的精确求解算法和快速求解方法.再次,本文设计了一种基于Alpha通道的误差补偿策略,提高了算法对复杂前景的抗干扰能力.最后,本文构建了不依赖于子空间模型的背景模板,减少了由前景信息反馈引起的背景更新失效,提高了算法的鲁棒性.多项对比实验表明,本文算法在干扰因素存在的情况下仍然可以实现对背景的准确建模,表现出较强的抗扰性和鲁棒性.     

基于混合SVR-PLS方法的丙烯腈收率软测量建模

为了更有效地处理过程非线性、多输入和数据共线性等复杂特性,提高模型的推广能力和精度,提出了混合支持向量回归机-偏最小二乘法(SVR—PLS)方法．该方法兼具SVR和PLS的优点．用PLS进行特征提取．用SVR建立PLS的内部模型．对工业丙烯腈生产过程丙烯腈收率软测量建模的应用表明．采用该方法建立的软测量模型．在模型精度、推广能力等方面明显优于一些传统软测量建模方法．满足工业应用要求．     

Error compensation and accuracy improvements in 5-axis machine tools using the global offset method

To enhance the machine tool accuracy, the Global offset method is developed for compensating the five-axis machine tool errors based on the measurement results of one or more identical machined parts. The machined features of a part are measured in a CMM and evaluated by a compensation processor, based on which the Global offset parameters, representing the machine tool errors, are estimated. The methodology is capable of compensating the overall effect of all position-dependent and position-independent systematic errors which contribute to particular workpiece accuracy. The developed technique and software are based on the Global offset method which interprets the computed deviations between the measured and nominal dimensions of the part through the analysis, synthesis and modeling of a fixture and rotary tables errors. The proposed model-based error compensation method is simple enough to be implemented in five-axis CNC machine tools. Production results exhibit effective compensation and remarkable improvement in the workpiece accuracy of the five-axis machine tools.     

基于模糊规则与CBR的磨矿专家控制方法

为了解决磨矿过程这一典型的复杂工业过程的优化控制问题,基于某选矿厂的两段全闭路磨矿流程展开研究,提出了基于模糊规则和案例推理相结合的磨矿专家系统控制方法,解决了实际应用中案例检索相似度较低,无法求解的问题.同时,为了进一步提高模型的准确性,解决由于检索到的案例与当前工况之间的差异导致的案例解之间存在差别的问题,采用RB...     

基于模糊建模的冷凝器污脏软测量

提出了一种基于模糊建模的冷凝器污脏软测量方法.该方法选取传热端差作为研究对象,应用模糊建模技术分离出冷凝器污脏对端差的影响.在模糊建模中,采用T-S模型描述变工况传热端差,研究了一种相似度判别法则以确定最优模型结构,并采用实数编码的遗传算法同时优化模型前、后件参数,从而获得了规则简化、精度较高的模糊模型.根据此方法,设计了试验系统,并进行了现场试验.试验结果表明:该方法能有效地在线监测冷凝器污脏,并在冷凝器出现堵管或空气漏入量较大时,取得比热阻法、传热系数法更可靠的测量结果.     

电熔镁砂产品单吨能耗混合预报模型

产品的单吨能耗是反映电熔镁砂熔炼过程产品产量和能耗的综合生产指标. 通过分析炉内电热转换关系,利用能量守恒原理建立了产品单吨能耗模型. 针对模型的未知非线性和参数时变等综合复杂性提出了由基于机理分析的单吨能耗主模型和 基于神经网络的补偿模型组成的产品单吨能耗混合预报模型. 其中神经网络补偿模型用于补偿模型的未知非线性和参数不确定性对于预报模型准确性的影响. 采用某电熔镁砂熔炼过程实测数据验证了所建立的混合预报模型是有效的.     

离焦图像多视角模糊特征自动补偿仿真研究

传统离焦图像多视角模糊特征自动补偿方法存在着图像信息丢失率大、图像补偿完整度低的弊端,为了解决上述问题,提出离焦图像多视角模糊特征自动补偿方法研究。为了得到更好的模糊特征补偿效果,对离焦图像形成过程进行分析,以此为基础,对离焦图像多视角模糊模型进行构建,以构建的离焦图像多视角模糊模型为工具,采用聚类算法对离焦图像模糊特征进行相应的提取,以提取的离焦图像多视角模糊特征为基础,采用补偿算法对离焦图像多视角模糊特征进行处理,实现了离焦图像多视角模糊特征的自动补偿。通过仿真对比实验得到,与现有的三种离焦图像多视角模糊特征自动补偿方法相比较,提出的离焦图像多视角模糊特征自动补偿方法极大的降低了图像信息丢失率,提升了图像补偿完整度,充分说明提出的离焦图像多视角模糊特征自动补偿方法具备更好的补偿性能。     

基于模糊相似测量和模糊映射改进的模糊支持向量机对不确定性信息处理

针对传统模糊支持向量机(FSVM)对于不确定性信息处理的局限性,提出一种基于模糊相似测量和高维空间模糊映射的改进模糊支持向量机方法。首先,构建不确定信息集的模糊相似测量函数, 从不确定性信息本质出发,利用Gregson相似度,构建具有模糊特征的相似测量函数;然后,根据空间映射理论,将模糊相似测量函数应用于FSVM,构建满足Mercer理论的FSVM相似内核;最后,利用该方法对旋转超声加工中材料切屑率(MRR)中的不确信性信息进行建模。对比具有传统内核的FSVM,所提方法能够利用较少的运算步骤完成较好的不确定性信息处理,有效提高不确定信息处理的准确性,且计算复杂度低。