与机理杂交的支持向量机为发酵过程建模

针对生物发酵过程机理复杂、高度非线性的特点,采用基于结构风险最小的支持向量机为发酵过程建模,其算法规范,建模复杂度低于神经网络方法,所建模型的预测效果更好.还将生化过程的动力学机理与支持向量机相结合,采用串联和串并联结构,提出与机理杂交的支持向量机建模方法,并为间歇式酒精发酵过程中酵母菌体浓度变化建立了预测模型.原理分析与试验结果表明与机理杂交的支持向量机建模方法,相比于单一近似的动力学模型、单一的支持向量机模型,以及机理杂交的神经网络模型,它的预测精度高,泛化能力强,性能更为优越.     

丁二酸发酵过程软测量模型的参数优化研究

针对生物转化法制备丁二酸发酵过程机理复杂、高度非线性、生物参数难以实时在线测量等特点,采用基于结构风险最小化的支持向量机对发酵过程建模.与神经网络方法相比,所建模型的预测效果更好.同时采用粒子群算法对支持向量机模型中     

基于最小二乘支持向量机的MIMO线性参数变化模型辨识及预测控制

将现有的面向单输入单输出系统的基于最小二乘支持向量机的参数变化模型辨识算法(SISO-LSSVM-LPV), 推广到多输入多输出系统, 实现了面向多输入多输出系统的基于最小二乘支持向量机的参数变化模型辨识算法(MIMO-LSSVM-LPV), 进一步结合基于遗传算法的预测控制算法(GA-MPC), 提出并实现了MIMO-LSSVM-LPV+ GA-MPC的建模控制一体化新架构。仿真结果表明, 该辨识算法可逼近复杂非线性MIMO系统, 辨识精度高, 并且保留了线性回归低计算量的优点, 结合了GA的MPC可实现最优控制量的在线实时寻优, 并取得了良好控制效果。     

基于改进支持向量机的化学镀Ni-P/ZrO2复合镀层显微硬度预测模型的建立

选取对化学镀Ni-P/ZrO_2复合镀层的显微硬度具有代表性的影响因素作为输入变量,以正交试验获得的有限试验数据为样本,先建立基于传统支持向量机的预测模型,再采用遗传算法对传统支持向量机中的惩罚因子与核函数参数进行优化,最终建立基于改进支持向量机的预测模型。通过遗传算法进化迭代,提高改进支持向量机模型的预测精度。选取神经网络模型和传统支持向量机模型作为对比模型。结果表明:改进支持向量机模型的预测精度较高,可以利用该模型对化学镀Ni-P/ZrO_2复合镀层的显微硬度进行预测。     

基于近似最小一乘准则的Hammerstein-Wiener模型随机梯度辨识

基于最小一乘准则和随机梯度算法原理,针对受尖峰噪声影响的非线性Hammerstein-Wiener模型,提出基于最小一乘准则的随机梯度算法。为解决最小一乘准则函数不可微的问题,该算法引入确定性可导函数近似代替残差绝对值。仿真实验表明:基于最小一乘准则的随机梯度算法对于非线性Hammerstein-Wiener模型可以有效地辨识出模型参数,同时抑制尖峰噪声对辨识结果的影响,具有更高的辨识精度、更快的收敛速度和良好的鲁棒性。     

芳烃异构化过程的多模型建模

针对芳烃异构化过程的非线性、复杂性,提出利用仿射传播聚类和最小二乘支持向量机对芳烃异构化过程进行多模型建模,以此来弥补单一模型建模的不足。首先仿射传播聚类对异构化数据聚类,利用最小二乘支持向量机对聚类之后的各个类分别建立子模型,通过计算欧氏距离来判断测试样本的所属类,将测试样本送入所属类的模型进行预测,以此来实现异构化过程的多模型预测。实验证明,与单模型以及基于k均值聚类的神经网络模型相比,本文提出的基于仿射传播聚类的最小二乘支持向量机模型更能准确地预测输出。     

一种人工情感神经网络及其应用

为了提高神经网络的学习速度和神经网络小样本的学习性能,提出了一种人工情感神经网络（artificial affective neural network,AANN）,在普通神经网络中加入了非全连接的情感神经元,使用与传统神经元不同的非线性激励函数,利用"紧张"与"自信"两个情感因子模拟人类学习的情感变化,可以提高神经网络对于对象的认知能力,进而提高学习速度。为了验证模型的有效性,分别采用数值实例和锅炉过热蒸汽温度预测控制进行了实例研究,结果表明,与BP神经网络以及支持向量机（SVM）相比,AANN对于小样本对象具有更好的辨识能力。     

一种人工情感神经网络及其应用

为了提高神经网络的学习速度和神经网络小样本的学习性能,提出了一种人工情感神经网络(artificial affective neural network,AANN),在普通神经网络中加入了非全连接的情感神经元,使用与传统神经元不同的非线性激励函数,利用"紧张"与"自信"两个情感因子模拟人类学习的情感变化,可以提高神经网络对于对象的认知能力,进而提高学习速度。为了验证模型的有效性,分别采用数值实例和锅炉过热蒸汽温度预测控制进行了实例研究,结果表明,与BP神经网络以及支持向量机(SVM)相比,AANN对于小样本对象具有更好的辨识能力。     

混沌最小二乘支持向量机及其在发酵过程建模中的应用

针对青霉素发酵过程的参数检测存在不确定因素,提出一种基于混沌最小二乘支持向量机的青霉素浓度预测方案。采用混沌优化算法对最小二乘支持向量机参数进行寻优,建立了一种混沌最小二乘支持向量机模型。首先,利用该模型对两种常规非线性函数曲线进行了仿真回归,结果表明,算法具有良好的建模精度;其次,基于Pensim仿真平台,运用文中方法预测青霉素发酵过程的产物量,实验仿真表明混沌优化算法具有良好的全局优化性能,在参数选择中可以有效避免陷入局部最小值,基于混沌优化的最小二乘支持向量机具有较高的建模精度。     

基于动态多核相关向量机的软测量建模研究

针对污水处理过程中存在的多变量耦合、强非线性以及参数时变等问题，提出基于多核学习相关向量机的软测量建模方法，并采用粒子群算法对多核权重以及核参数进行优化。同时，引入时间差分(time difference)方法改进多核相关向量机的动态特性。为了验证所提模型的有效性，通过一仿真案例与单核相关向量机、多层前馈神经网络和基于遗传算法的支持向量机进行对比研究。结果表明，所提模型具有更好的预测效果。最后，对模型的鲁棒性在数据漂移和异常的场景下进行了讨论。     

基于2次核SVM的单步非线性模型预测控制

A support vector machine (SVM) with quadratic polynomial kernel function based nonlinear model one-step-ahead predictive controller is presented. The SVM based predictive model is established with black-box identification method. By solving a cubic equation in the feature space, an explicit predictive control law is obtained through the predictive control mechanism. The effect of controller is demonstrated on a recognized benchmark problem and on the control of continuous-stirred tank reactor (CSTR). Simulation results show that SVM with quadratic polynomial kernel function based predictive controller can be well applied to nonlinear systems, with good performance in following reference trajectory as well as in disturbance-rejection.     

利用输出反馈方法实现聚合物分子量分布的控制

利用正交多项式组合神经网络对聚合反应分子量分布(MWD)进行建模,MWD被解构为若干矩值组成的矩向量函数,由此二元MWD控制问题可被转换为一元分布矩控制问题。以矩向量为直接被控对象,通过对矩的控制实现MWD的跟踪。为便于求解这类非仿射非线性多变量系统的控制策略,提出了改进型非线性自回归正交多项式网络结构,建立模型输出与U(k)之间的线性映射关系;针对高维被控矩向量,证明了矩向量中独立变量与分布函数参变量间的数量对等关系,给出了矩向量降维准则,将高维输出控制转化为低维问题。基于改进的神经网络模型,利用输出反馈方法对MWD矩向量进行控制,实现了对MWD的形状跟踪,仿真实验证明了方法的有效性。所提出的方法为非线性多变量系统的建模控制问题提供了新思路。     

基于多核支持向量机的非线性模型预测控制

Multi-kernel-based support vector machine （SVM） model structure of nonlinear systems and its specific identification method is proposed, which is composed of a SVM with linear kernel function followed in series by a SVM with spline kernel function. With the help of this model, nonlinear model predictive control can be transformed to linear model predictive control, and consequently a unified analytical solution of optimal input of multi-step-ahead predictive control is possible to derive. This algorithm does not require online iterative optimization in order to be suitable for real-time control with less calculation. The simulation results of pH neutralization process and CSTR reactor show the effectiveness and advantages of the presented algorithm.     

ROBUST NONLINEAR PREDICTIVE CONTROL USING A DISTURBANCE ESTIMATOR

A robust nonlinear predictive control strategy using a disturbance estimator is presented. The disturbance estimator is comprised of two parts: one is the disturbance model parameter adaptation and the other is future disturbance prediction. A linear discrete model is proposed as a disturbance model which is formulated by using process inputs and available process measurements. The recursive least square (RLS) method with exponential forgetting is used to determine the uncertain disturbance model parameters and for the future disturbance prediction, future disturbances projected by the future process inputs are used. Two illustrative examples: a jacketed CSTR as a SISO system: an adiabatic CSTR as a MIMO system, and experimental results of the distillation column control are presented. The results indicate that a substantial improvement in nonlinear predictive control performance is possible using the disturbance estimator.     

利用离散正交多项式组合神经网络建立聚合物分子量分布灰箱模型

聚合物分子量分布（MWD）是反映产品性能最重要的指标之一,它是典型的二元建模对象,聚合物分子量分布（MWD）是反映产品性能最重要的指标之一,它是典型的二元建模对象,采用组合神经网络对MWD的空间和时间变量进行分解建模。首先利用离散正交多项式神经网络在链长空间上建立分布与链长的模型,然后将MWD与时间变量的关系转换为网络权向量与输入变量之间的函数,利用递归神经网络建立两者之间的模型,最后组合两个网络达到建模目标。分布函数的模型表达式可写成状态方程形式,为进一步设计控制策略提供了基础。在链长空间上建立模型时,实现了神经网络的权向量与MWD相应阶次矩值之间的等价关系,网络权向量由单纯的拟合数据转变为有意义的物理量,实现了神经网络模型的灰箱化,为精确预测网络隐层节点数问题提供了解决途径。提出的方法应用于实验室规模的苯乙烯聚合过程,证明了建模方法的可行性,同时网络权值与矩值的等价关系也得到验证。     

ADAPTIVE NEURAL-NETWORK PREDICTIVE CONTROL FOR NONMINIMUM-PHASE NONLINEAR PROCESSES

An adaptive neural-network predictive control strategy for a class of nonlinear processes, which exhibit input multiplicities and change in the sign of steady-state gains, is presented. According to the graphic-based determination associated with prescribed input/output patterns, the feed-forward neural network (FNN) is attributed to reconstruct dynamic and steady-state characteristics of minimum-phase modes with specified operating ranges. The flexible predictive control strategy using on-line neuro-based adaptation is developed for enhancing the predictive capability of neural network. Finally, the proposed FNN-based implementation is illustrated on simulations of both isothermal and adiabatic CSTR systems.     

基于最小二乘支持向量机回归的单桩竖向极限承载力预测

基于单桩载荷试验数据,采用最小二乘支持向量机(LSSVM)回归的方法,建立了单桩竖向极限承载力的预测模型.利用文献中桩的载荷试验数据来训练LSSVM模型,并确定了模型参数.研究结果表明,同常用的BP网络相比,LSSVM预测模型具有学习速度快、预测性能较好、选择参数少等优点,是一种有效的预测单桩极限承载力的方法.     

一种基于速率线性化的非线性预测控制算法

提出了一种基于速率线性化方法的非线性预测控制算法。该算法采用速率线性化方法得到与原系统非线性模型相对应的线性变参数模型,这类变参数模型在结构上是线性的,而模型参数将随工作条件的变化而变化,在系统的整个工作区间内都能很好地逼近原非线性模型。在此模型的基础上设计了预测控制器,并利用基于置信域的Levenberg-Marquardt算法在线求得预测控制率。最后对连续搅拌反应釜进行了仿真研究,仿真结果表明了该算法的可行性和有效性。     

Neural‐Networks‐Based Feedback Linearization versus Model Predictive Control of Continuous Alcoholic Fermentation Process

In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.     

Neural network-based predictive control for multivariable processes

In this paper, the systematic derivations of setting up a nonlinear model predictive control based on the neural network are presented. This extends our previous work (Chen, 1998) into a multivariable system to explore the characteristics of the design. There are two stages for the development of nonlinear neural network predictive control: a neural network model and a control design. In the neural network model design, a parallel multiple-input, single-output neural network autoregressive with a model of exogenous inputs (NNARX) is proposed for multistep ahead predictions. In control design, the controller with extended control horizon is developed. The Levenberg-Marquardt algorithm is applied to training the NNARX model. Also, the sequential quadratic programming is used to search for the optimal manipulated inputs. The gradient of the objective function and constraints that require computation of Jacobian matrices are completely derived for optimization calculation. To demonstrate the control ability of MIMO cases, the proposed method is applied through two nonlinear simulation problems.