基于AP聚类算法的跳汰机床层松散度软测量建模

松散度是跳汰分选过程的重要影响因素,针对其难以用仪器在线检测的问题,提出采用最小二乘支持向量机(LS-SVM)的软测量建模方法。在充分考虑分选过程高度非线性及强耦合性的基础上,为避免单模型建模回归精度差和泛化能力弱的问题,提出采用基于仿射传播(AP)聚类的LS-SVM多模型建模算法进行床层松散度软测量建模。首先采用AP算法对样本数据进行聚类划分,再用LS-SVM的方法对子类样本分别建立子模型,最后通过子模型切换策略得到系统输出。仿真实验表明,基于AP聚类算法的LS-SVM软测量建模算法能够更好地预测跳汰机床层松散度。     

基于支持向量机的软测量建模方法的应用

利用基于最小二乘支持向量机(LS-SVM)的软测量建模方法,通过工业现场数据来对丁二烯精馏装置建立软测量模型.对于该软测量模型,支持向量机方法比BP神经网络方法具有更好的泛化能力.研究结果表明,基于最小二乘的支持向量机建模方法是一种有效的软测量建模方法.     

一种基于时序误差补偿的动态软测量建模方法

针对目前静态软测量建模方法无法反映工业过程动态信息,造成预测模型精度低、鲁棒性差等问题,提出了一种基于最小二乘支持向量机(LS-SVM)和自回归-滑动平均模型(ARMA)的软测量建模方法。首先,建立了基于LS-SVM的软测量模型,利用ARMA模型对预测误差的动态估计,通过增加动态校正环节,实现了对静态模型的动态校正以改善系统动态响应特性。最后将上述方法用于乙烯精馏过程中乙烷浓度的软测量建模,仿真结果表明:与单一使用LSSVM模型相比,该方法具有跟踪性能好、泛化能力强等优点,是一种有效的软测量建模方法。     

基于GMM核的LS-SVM真核启动子模型

由于真核启动子DNA序列结构复杂、数据量巨大,启动子序列辨识一直是一个难点。首先对真核启动子序列寡核苷酸位置分布特征进行高斯混合模型建模,能够将出现频率少但重要的基序提取出来。并将高斯混合模型作为真核启动子最小二乘支持向量机分类器中的核函数,将最小二乘支持向量机模型简化为最小二乘模型,计算量减少。辨识结果表明,该算法的辨识精度优于贝叶斯辨识算法,和RBF核LS-SVM相比,辨识精度基本相同,建模时间略有缩短。     

基于人工蜂群算法优化LSSVM的蒸汽干度软测量

为了提高蒸汽干度测量的精确性,提出了基人工蜂群优化最小二乘支持向量机的干度软测量模型。首先利用人工蜂群算法对最小二乘支持向量机的核参数进行参数优化,然后利用优化后的最小二乘支持向量机干度测量模型对干度进行软测量,软测量结果表明基于人工蜂群优化的最小二乘支持向量机的测量效果满足了精度要求。最后运用最小二乘支持向量机和BP神经网络模型对干度进行了软测量,结果表明:基于人工蜂群优化的最小二乘支持向量机软测量模型具有测量精度高,测量稳定性好的优点。     

基于局部重构融合流形聚类的多模型软测量建模

针对单模型描述复杂非线性对象时估计精度低、泛化能力差的问题,提出了一种基于局部重构融合流形聚类的多模型软测量建模方法。该方法将样本集拆分为多个互不相交的样本子簇,克服异常样本点对聚类结果的影响;以各样本子簇重构线性流形面,将属于同一流形面且相距较近的样本子簇进行融合;采用支持向量机为各个子类建立回归子模型,得到一个基于多个子模型的软测量组合模型。在双酚A生产过程质量指标的软测量建模仿真中验证了该方法的有效性。     

基于ICA和ES-SVM的油气两相流空隙率测量

基于12电极电容层析成像系统(ECT),提出了一种油气两相流空隙率测量的新方法.实际测量时,以ECT电容传感器获得的66个电容测量值作为输入,利用空隙率测量模型计算空隙率.建模过程中,首先采用独立分量分析(ICA),对66个电容测量值进行特征提取.然后以特征参数作为输入,空隙率作为输出,用最小二乘支持向量机(LS-SVM)建立回归函数,并运用进化策略(ES)寻找最优LS-SVM参数.实验结果验证了本文方法的有效性,测量精度和实时性满足工业应用的要求.     

基于改进粒子群优化LSSVM的水泥熟料fCaO软测量

针对水泥熟料fCaO含量难以在线实时测量,提出了一种基于最小二乘支持向量机的软测量建模方法。针对最小二乘支持向量机模型的2个难点进行了改进:首先利用样本间的马氏距离来衡量样本的相似程度,删除样本中部分相似样本,提高最小二乘支持向量机模型的稀疏性,从而减小了模型的运算量。然后利用改进的粒子群优化算法对最小二乘支持向量机模型的2个重要参数进行迭代寻优,克服了常规交叉验证法或网格搜索法等参数选择方法的盲目性。最后将基于粒子群最小二乘支持向量机软测量模型用于熟料fCaO含量的实例仿真。结果表明,该方法具有收敛性好、预测精度高、泛化能力强等优点。     

基于改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量

针对氧化铝蒸发过程铝酸钠溶液浓度难以在线检测问题,提出了改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量建模方法。首先基于灰色关联分析和核主成分分析确定模型的输入变量,再用改进差分进化算法的最小二乘支持向量机构建软测量模型。并与DE-LSSVM软测量模型进行比较;最后应用蒸发过程生产数据进行验证,结果表明,新模型具有更好的学习能力和泛化性能且预测精度更高,可为蒸发过程操作优化提供必要的指导。     

基于最小二乘支持向量机的复合肥装置养分含量的软测量建模

针对复合肥装置养分含量无法用常规的传感器在线测量的问题,提出了基于最小二乘支持向量机(LS-SVM)的软测量方法来在线估计养分含量.LS-SVM用等式约束代替传统的标准支持向量机中的不等式约束,求解过程从解二次规划问题变成解线性方程组,求解速度相对加快.工业实例表明LS-SVM所建模型的预测精度较高,能满足实际工业应用的需求.     

Soft-sensor for copper extraction process in cobalt hydrometallurgy based on adaptive hybrid model

In the process of copper extraction in cobalt hydrometallurgy, the copper concentration of raffinate solution needs to be monitored and controlled simultaneously. It is difficult to measure such concentration online by existing instruments and sensors. Soft sensor technique has been became an online supplement measurement for process monitoring and control. In this paper, an adaptive hybrid modeling method for copper extraction process is proposed. The proposed model is composed of simplified first principle model and block-wise recursive PLS model. The former based on material balancing calculation with some assumptions is used to describe the extraction process in general; and the latter is constructed to compensate the unmodeled characteristic and deal with the time-variant feature. A model rectification strategy is also employed to correct the final output and increase the prediction accuracy. The proposed model has been used in a cobalt hydrometallurgy pilot plant, and the prediction results indicate that the adaptive hybrid model is more precise and efficient than the other conventional models.     

钢铁企业蒸汽产生量预测模型研究

提出一种基于小波变换-最小二乘支持向量机的钢铁企业蒸汽产生量预测方法。先对数据进行小波变换以提取数据的特征;然后建立LS-SVM模型,对各分量进行预测以提高预测精度。实验结果表明:小波变换-最小二乘支持向量机预测方法预测精度高、性能好,具有良好的实用性,为蒸汽生产优化调度提供了科学的依据。     

Dynamic synergistic modelling for cobalt removal process in zinc hydrometallurgy and the research of parameter estimation based on unscented Kalman filter

The cobalt removal process with arsenic salt of zinc hydrometallurgy has serious non-linearity, uncertainty, and mutual coupling. Its accurate dynamic modelling has always been a challenging problem. On the basis of in-depth analysis of cobalt removal process and reaction mechanism, considering the cascade relationship between the reactors, a dynamic synergistic continuously stirred tank reactor (SCSTR) mechanism model of the cobalt removal process was constructed. Aiming at the unknown parameters in the SCSTR model, the idea of the Kalman filter was introduced, and the unknown parameters were characterized as unknown states; a method of estimating the unknown model parameters was developed using the augmented state equation and the unscented Kalman filter (UKF) algorithm. Simulation results with industrial data of a zinc smeltery showed that the parameter estimation model has high accuracy, and the estimated parameters can be used in the SCSTR model. An intensive simulation analysis of the dynamic characteristics of the complete SCSTR model was carried out to verify the influence of different input disturbances on the output ion concentration of each reactor, which demonstrated the excellent dynamic performance and potential of the model. Ultimately, according to the industrial calculation analysis, the SCSTR model has a guiding effect on the addition of zinc powder in the reactors, overcomes the blindness in the production process, and provides a momentous basis for the optimization control of the cobalt removal process.     

Dynamic modelling and predictive control for the sequential collaborative reactors of cobalt removal process under time‐varying conditions

The accuracy of the process model directly affects the performance of the model‐based controller. In zinc hydrometallurgy, the overall dynamics of the cobalt removal process can hardly be described by a fixed model since there are a series of interconnected reactors working together under time‐varying inlet and reaction conditions. In this study, an interacting continuously stirred tank reactors (ICSTR) model is developed to describe the cooperative relationship of these cascaded reactors. Considering the time‐varying inlet and reaction conditions, the reaction surface conversion coefficient is defined and incorporated into the ICSTR model, and the kernel partial least squares (KPLS) is employed to update the dynamic model online. The effectiveness of the time‐varying ICSTR model is validated using industrial data. Based on the proposed time‐varying ICSTR model, a predictive controller is designed to realize the optimal operation of the cobalt removal process. Simulation results indicate that compared with conventional predictive control and manual manipulation, the time‐varying ICSTR model‐based predictive control method can not only maintain the outlet cobalt ion concentration but also reduce the zinc dust dosage.     

基于混合粒子群优化的异类多模型软测量方法研究与应用

基于异类组合预测模型可提高模型的预测精度及鲁棒性的思想,提出一种基于混合粒子群优化的异类多模型非线性组合软测量建模的新方法。即先分别用混合粒子群优化的径向基函数神经网络、最小二乘支持向量机及部分最小二乘算法对训练集训练得出子模型,然后将具有性能互补性的三个子模型的输出作为反向传播网络的输入得到最后结果。用混合粒子群优化的方法来选取径向基函数神经网络和最小二乘支持向量机的模型参数,该方法克服了常用的交叉验证法耗时与盲目性问题。三层反向传播网络具有无限逼近特性,使得整个组合预测模型具有更好的泛化能力和预报精度。将其应用于汽油调合系统中研究法辛烷值的预测,仿真结果表明,该方法是可行且有效的。     

Deep Purification of Zinc Ammoniacal Leaching Solution

Deep purification of zinc ammoniacal leaching solution by cementation using zinc dust was studied. The effects of relative amount of metallic impurities, dosage of zinc dust, purification time, temperature, pH value and total ammonia concentration in the solution on the purification of the solution were investigated. The results indicate that total ammonia concentration in the solution had no effect on the purification, but relative amount of metallic impurities, dosage of zinc dust, purification time, temperature and pH value of the solution were the main factors influencing the purification. Keeping appropriate molar ratio of copper to cadmium or nickel to cadmium was beneficial to the cementation of cadmium. Nevertheless, the presence of cobalt went against the cementation of cadmium and cobalt. All metallic impurities could be decreased to acceptable levels under the optimized conditions of 2 g/L of zinc dust dosage, 1 h of purification time, 35℃, pH value 9.03 of zinc ammoniacal leaching solution. The deeply purified zinc ammoniacal solution obtained by one-stage purification meets the requirements of zinc electrowinning.     

Deep Purification of Zinc Ammoniacal Leaching Solution by Cementation with Zinc Dust

Deep purification of zinc ammoniacal leaching solution by cementation using zinc dust was studied.The effects of relative amount of metallic impurities,dosage of zinc dust,purification time,temperature,pH value and total ammonia concentration in the solution on the purification of the solution were investigated.The results indicate that total ammonia concentration in the solution had no effect on the purification,but relative amount of metallic impurities,dosage of zinc dust,purification time,temperature and pH value of the solution were the main factors influencing the purification.Keeping appropriate molar ratio of copper to cadmium or nickel to cadmium was beneficial to the cementation of cadmium.Nevertheless,the presence of cobalt went against the cementation of cadmium and cobalt.All metallic impurities could be decreased to acceptable levels under the optimized conditions of 2 g/L of zinc dust dosage,1 h of purification time,35℃,pH value 9.03 of zinc ammoniacal leaching solution.The deeply purified zinc ammoniacal solution obtained by one-stage purification meets the requirements of zinc electrowinning.     

基于改进即时学习算法的湿法冶金浸出过程建模

针对湿法冶金浸出过程中存在的多变量、非线性和多工况等问题,采用基于即时学习算法的最小二乘支持向量机建立浸出率的预测模型。将时间有序性引入到即时学习算法学习集的选取规则中以确定系统当前工作点的建模邻域,从而提高模型精度;引入累计相似因子以提高所建模型的实时性,并利用自适应相似度阈值来判定是否需要重新建立当前工作点的局部模型。将改进的建模方法应用到湿法冶金浸出过程浸出率的预测中,仿真结果表明,所建模型具有较高的精度和实时性,可用于湿法冶金工业生产过程。