高斯过程集成算法的发酵过程软测量建模

针对谷氨酸发酵过程一些关键参数不能在线测量而导致的建模精度不高的问题,Bagging和高斯过程回归算法相结合,提出一种基于Bagging算法集成高斯过程的软测量建模方法。该算法使用Bagging技术从训练样本集中选取若干子训练样本集,利用该若干子集形成许多高斯过程模型,并通过平均组合方式进行集成,得到最终的模型输出。将该集成算法应用到谷氨酸发酵过程的软测量建模中,实现了对谷氨酸浓度的准确预测,相对于单一高斯过程模型,具有更高的预测精度和鲁棒性。     

基于微粒群优化算法的非线性系统PWA多模型建模

针对复杂非线性系统,将微粒群优化(PSO)算法与多模型建模相结合,设计了一种基于PSO算法的非线性系统分段仿射(PWA)多模型建模算法。该算法将PWA多模型建模问题转化为混合整数二次规划（MIQP）问题,并基于PSO算法对其进行优化求解。在求解的过程中,采用分层优化求解方法,有效降低优化问题的维数,减小了陷入局部最优的概率,并通过仿真验证了该算法的有效性。     

一种基于过程神经网络的动态系统控制信号求解模型和算法

针对非线性动态系统控制问题,提出了一种基于过程神经网络的控制信号求解模型和算法。利用过程神经网络对动态系统时变输入/输出信号的非线性映射机制和对系统过程模态特征的自适应提取能力,建立基于过程神经网络的辨识模型;然后根据所建立的辨识模型、系统控制结构和状态参数之间的关系,构建可满足系统信息传递约束关系的控制信号求解模型。分析了过程神经网络控制模型的信息处理机制,给出了基于GA与LMS相结合的优化求解算法,实验结果验证了模型和算法的有效性。     

发酵过程的多模型融合建模算法

提出了利用多模型融合技术进行发酵过程建模的新方法， 该方法能够将在线参数和离线参数同时用于建模中． 首先给出了多模型融合建模算法框架， 并描述了基于自适应模糊神经网络和模糊推理技术两个参与融合的子模型的建立方法. 采用三个非线性函数分别运用GMDH-PTSV算法、傅里叶神经网络和多模型融合建模算法进行建模精度比较. 最后给出了多模型融合建模算法在青霉素发酵过程中应用的结果．     

基于PSO-MKSVM发酵过程建模与补料优化控制

针对动态非线性、时变发酵过程,采用混合核支持向量机的智能模型建模方法,通过建立混合核支持向量机的状态预估模型,实现对发酵产物浓度的预估,解决了缺乏生物传感器的问题.在此基础上,再利用粒子群优化算法求取补料速率优化曲线,最终使得发酵终止时产物产量最高.实验结果表明,该方法取得了良好的效果.     

基于不定期决策过程的最短路径搜索算法

不定期决策过程具有广泛的应用领域。该文针对基于不定期决策过程的段数不定线路网,在动态规划的基础上,提出了SPUCN算法(ShortestPathProblemofUncertainColumnNetwork),该算法通过对UCN模型进行分析转换,建立起能够以动态规划基本方程进行分析求解的理想模型,然后对该模型进行动态规划的后向分析求解,文章给出了算法的正确性和理论性证明,最后通过实例验证了算法的有效性。     

基于混沌和SVM的青霉素发酵过程混合建模

就青霉素发酵过程难以建立理想模型,提出一种基于混沌支持向量机和动力学模型相结合的混合建模新方法.首先分析青霉素发酵过程动力学模型的特点,选择合适的状态变量,然后利用混沌算法优化支持向量机的参数,建立动态时变的混合模型.该模型不但能自动选择支持向量机的参数,而且能够预报一些不能在线测量的生化状态变量.通过实用,证明了此方法有效.     

一种基于PSO的自适应神经网络预测控制

针对非线性系统,提出了一种基于微粒群优化（PSO）的自适应神经网络预测控制方法。采用对角递归网络（DRNN）对非线性系统进行建模,并利用扩展卡尔曼滤波（EKF）递推估计算法在线计算网络模型参数的Jacobian矩阵以实现模型参数的自适应。利用PSO算法在线优化求解非线性系统的预测控制律,以克服传统基于梯度法的非线性规划方法求解预测控制律时对初始条件非常敏感的缺点。生化发酵过程的仿真结果表明,所提出的控制方法具有良好的跟踪能力和抗干扰能力。     

一种基于PSO的自适应神经网络预测控制

针对非线性系统,提出了一种基于微粒群优化(PSO)的自适应神经网络预测控制方法.采用对角递归网络(DRNN)对非线性系统进行建模,并利用扩展卡尔曼滤波(EKF)递推估计算法在线计算网络模型参数的Jacobian矩阵以实现模型参数的自适应.利用PSO算法在线优化求解非线性系统的预测控制律,以克服传统基于梯度法的非线性规划方法求解预测控制律时对初始条件非常敏感的缺点.生化发酵过程的仿真结果表明,所提出的控制方法具有良好的跟踪能力和抗干扰能力.     

最优Box-Cox变换模型的反向动态规划求解

本文通过构造Box—Cox变换模型加权最优目标函数，综合考虑回归系数t统计量对应P阀值，Theil系数U2及其误差分解，修正回归拟合优度，Durbin—Watson检验量，回归残差。利用Excel矩阵向量数组函数三维动态建模，通过Excel基于稳健GRG2算法的规划求解，“反向”动态求解整体最优Box—Cox变换模型估计参数。实例给出了建模过程，显示反求建模可较有效地克服变换模型的异方差，多重共线性和序列相关性。     

Training feedforward networks with the Marquardt algorithm

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights.     

基于Levenberg-Marquardt算法和最小二乘方法的小波网络混合学习算法

本文针对小波网络现有学习算法的不足,把Levenberg-Marquardt算法(简称LM算法)和最小二乘算法有机地结合在一起,提出了一种新的小波网络混合学习算法.在该混合算法中LM算法用来训练小波网络的非线性参数,而最小二乘算法用来训练线性参数.最后以辩识一个混沌系统为例进行了数值仿真,并与改进的BP算法和单纯LM算法进行了比较,结果说明了所提算法具有很好的收敛性能和收敛速度.     

Optimal design of neural networks for control in robotic arc welding

Robotic gas metal arc (GMA) welding is a manufacturing process which is used to produce high quality joints and has to a capability to be utilized in automation systems to enhance productivity. Despite its widespread use in the various manufacturing industries, the full automation of the robotic GMA welding has not yet been achieved partly because mathematical models for the process parameters for a given welding tasks are not fully understood and quantified. In this research, an attempt has been made to develop a neural network model to predict the weld bead width as a function of key process parameters in robotic GMA welding. The neural network model is developed using two different training algorithms; the error back-propagation algorithm and the Levenberg–Marquardt approximation algorithm. The accuracy of the neural network models developed in this study has been tested by comparing the simulated data obtained from the neural network model with that obtained from the actual robotic welding experiments. The result shows that the Levenberg–Marquardt approximation algorithm is the preferred method, as this algorithm reduces the root of the mean sum of squared (RMS) error to a significantly small value.     

回声状态网络LM算法及混沌时间序列预测

回声状态网络（ESN）学习算法中可能存在解的奇异问题,在时间序列预测时易导致病态解问题,且伴随着具有较大幅值的输出权值,尤其是当训练样本个数小于输出权值维数时,ESN的解必为奇异的.鉴于此,考虑使用LM（Levenberg Marquardt）算法代替常用的线性回归方法,自适应选择LM参数,从而有效地控制输出权值的幅值,提高ESN的预测性能.通过Lorenz混沌时间序列进行预测研究,对大连月平均气温实际数据进行仿真研究,取得了较好的预测效果.     

Neural network based model predictive control for a steel pickling process

A multi-layer feedforward neural network model based predictive control scheme is developed for a multivariable nonlinear steel pickling process in this paper. In the acid baths three variables under controlled are the hydrochloric acid concentrations. The baths exhibit the normal features of an industrial system such as nonlinear dynamics and multi-effects among variables. In the modeling, multiple input, single-output recurrent neural network subsystem models are developed using input–output data sets obtaining from mathematical model simulation. The Levenberg–Marquardt algorithm is used to train the process models. In the control (MPC) algorithm, the feedforward neural network models are used to predict the state variables over a prediction horizon within the model predictive control algorithm for searching the optimal control actions via sequential quadratic programming. The proposed algorithm is tested for control of a steel pickling process in several cases in simulation such as for set point tracking, disturbance, model mismatch and presence of noise. The results for the neural network model predictive control (NNMPC) overall show better performance in the control of the system over the conventional PI controller in all cases.     

Batch-to-batch control of fed-batch processes using control-affine feedforward neural network

A control strategy for fed-batch processes is proposed based on control affine feed-forward neural network (CAFNN). Many fed-batch processes can be considered as a class of control affine nonlinear systems. CAFNN is constructed by a special structure to fit the control affine system. It is similar to a multi-layer feed-forward neural network, but it has its own particular feature to model the fed-batch process. CAFNN can be trained by a modified Levenberg–Marquardt (LM) algorithm. However, due to model-plant mismatches and unknown disturbances, the optimal control policy calculated based on the CAFNN model may not be optimal when applied to the fed-batch process. In terms of the repetitive nature of fed-batch processes, iterative learning control (ILC) can be used to improve the process performance from batch to batch. Due to the special structure of CAFNN, the gradient information of CAFNN can be computed analytically and applied to the batch-to-batch ILC. Under the ILC strategy from batch to batch, endpoint product qualities of fed-batch processes can be improved gradually. The proposed control scheme is illustrated on a simulated fed-batch ethanol fermentation process.     

Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process

Monitoring and control of multiple process quality characteristics (responses) in grinding plays a critical role in precision parts manufacturing industries. Precise and accurate mathematical modelling of multiple response process behaviour holds the key for a better quality product with minimum variability in the process. Artificial neural network (ANN)-based nonlinear grinding process model using backpropagation weight adjustment algorithm (BPNN) is used extensively by researchers and practitioners. However, suitability and systematic approach to implement Levenberg-Marquardt (L-M) and Boyden, Fletcher, Goldfarb and Shanno (BFGS) update Quasi-Newton (Q-N) algorithm for modelling and control of grinding process is seldom explored. This paper provides L-M and BFGS algorithm-based BPNN models for grinding process, and verified their effectiveness by using a real life industrial situation. Based on the real life data, the performance of L-M and BFGS update Q-N are compared with an adaptive learning (A-L) and gradient descent algorithm-based BPNN model. The results clearly indicate that L-M and BFGS-based networks converge faster and can predict the nonlinear behaviour of multiple response grinding process with same level of accuracy as A-L based network.     

基于LM算法的神经网络语音识别

由于语音识别中朵用标准BP算法存在的训练速度慢、容易陷入局部极小等问题，提出一种基于稳定、快速的Levenberg-Marquardt算法的神经网络语音识别方法，主要包括语音信号预处理、特征提取、网络结构优化设计、网络学习训练和语音识别等过程。其中网络隐含层节点数的选取采用黄金分割优选法。试验仿真表明，LM算法明显提高了网络训练速度，减少了训练时间，其效果优越于标准BP算法。     

基于遗传算法的非线性模型预测控制方法

介绍了非线性模型预调控制算法结构，提出了基于遗传算法的非线性模型预测控制方法，将遗传算法作为优化技术用于受限非线性模型预测控制器的设计。算法采用双模控制策略，将保证预测控制算法稳定性的终点等式约束转化为终点不等式约束，以利于遗传算法的实施。基于不变集理论，给出了非线性模型预测控制算法的稳定性定理。仿真结果表明了所提出控制算法的可行性和有效性。     

人工神经网络在汽液相平衡常数预测中的应用

汽液相平衡常数的计算在化工分离过程中至关重要 ,传统方法参数众多 ,计算过程复杂 ,耗用机时多。本文在文献数据的基础上 ,首先利用过程模拟软件DesignⅡ对汽液相平衡常数进行了计算 ,然后使用三层BP神经网络及L -M算法对汽液相平衡常数进行预测 ,并以其他多种算法作为对比。结果表明 ,预测数据与实验数据吻合相当好 ,L -M算法运算速度明显快于其他算法 ,总耗机时大大缩短