带滤波器的新型网络无限时间最优控制

针对网络控制系统中的无限时间最优方法,设计了一种基于输入变化率的新型滤波器算法。改进后的算法在保证系统快速性的情况下,使得控制更加平稳。考虑到半实物仿真实验平台不能保证实验条件的一致性,开发出NCS数字仿真实验平台。仿真结果说明了所采用方法的有效性。     

Mixed Constrained Infinite Horizon Linear Quadratic Optimal Control

For a given initial state, a constrained infinite horizon linear quadratic optimal control problem can be reduced to a finite dimensional problem [12]. To find a conservative estimate of the size of the reduced problem, the existing algorithms require the on‐line solutions of quadratic programs [10] or a linear program [2]. In this paper, we first show based on the Lyapunov theorem that the closed‐loop system with a mixed constrained infinite horizon linear quadratic optimal control is exponentially stable on proper sets. Then the exponentially converging envelop of the closed‐loop trajectory that can be computed off‐line is employed to obtain a finite dimensional quadratic program equivalent to the mixed constrained infinite horizon linear quadratic optimal control problem without any on‐line optimization. The example considered in [2] showed that the proposed algorithm identifies less conservative size estimate of the reduced problem with much less computation.     

离散时间不定号随机线性二次型最优控制:无限时区情形

应用渐近分析方法讨论了无限时区离散时间不定号随机线性二次型最优控制问题. 所进行的研究是建立在这一问题有限时区情形结果和系统均方能镇定假设基础之上的. 广义代数Riccati方程(GARE)解的一些性质也得到了考虑. 最后提供了两个例子来说明所推出的结果是有效的.     

A Recurrent Neural Network for N-Stage Optimal Control Problems

A recurrent neural network is introduced for the N-stage optimal control problem. The new neural network is based on a reformulation of the original optimal control problem and the gradient method. The simulation results on two examples indicate that the new neural network is quite effective.     

一种基于前馈网络的分组密码体制

研究了分组密码体制及前馈神经网络的特征,构造了一种分组密码体制的数学模型,并基于二层前馈网络具体实现了该分组密码体制。在此基础上进行了仿真,结果表明该分组密码体制是可行的;针对其安全性进行了大量的实验,说明此分组密码体制具有较高的安全性,具有很好的混乱特征和扩散特征,可以用于信息安全领域的加/解密过程。     

一种基于前馈网络的分组密码体制

研究了分组密码体制及前馈神经网络的特征，构造了一种分组密码体制的数学模型，并基于二层前馈网络具体实现了该分组密码体制。在此基础上进行了仿真，结果表明该分组密码体制是可行的；针对其安全性进行了大量的实验，说明此分组密码体制具有较高的安全性，具有很好的混乱特征和扩散特征，可以用于信息安全领域的加／解密过程。     

On the Infinite Horizon Performance of Receding Horizon Controllers

Receding horizon control is a well established approach for control of systems with constraints and nonlinearities. Optimization over an infinite time-horizon, which is often computationally intractable, is therein replaced by a sequence of finite horizon problems. This paper provides a method to quantify the performance degradation that comes with this approximation. Results are provided for problems both with and without terminal costs and constraints and for both exactly and practically asymptotically stabilizable systems.     

前馈神经网络凸优化算法及其仿真应用

该文利用凸函数共轭性质中的Young不等式构造前馈神经网络优化目标函数。这个优化目标函数若固定权值,对隐层输出来说为凸函数;若固定隐层输出,对权值来说为凸函数。因此,此目标函数不存在局部最小。此目标函数的优化速度快,大大提高了前馈神经网络的学习效率。仿真试验表明,与传统算法如误差反向传播算法或BP算法和含势态因子(Momentum factor)的BP算法及现有的分层优化算法相比,新算法能加快收敛速度,并降低学习误差。利用这种快速算法对矿体进行仿真预测,取得了良好效果。     

A Neural Network Approach for Solving Optimal Control Problems with Inequality Constraints and Some Applications

In this paper, a class of nonlinear optimal control problems with inequality constraints is considered. Based on Karush–Kuhn–Tucker optimality conditions of nonlinear optimization problems and by constructing an error function, we define an unconstrained minimization problem. In the minimization problem, we use trial solutions for the state, Lagrange multipliers, and control functions where these trial solutions are constructed by using two-layered perceptron. We then minimize the error function using a dynamic optimization method where weights and biases associated with all neurons are unknown. The stability and convergence analysis of the dynamic optimization scheme is also studied. Substituting the optimal values of the weights and biases in the trial solutions, we obtain the optimal solution of the original problem. Several examples are given to show the efficiency of the method. We also provide two applicable examples in robotic engineering.     

基于多级神经元的神经网络及其在分类中的应用

为了提高前向神经网络的分类能力,该文将多级神经元扩展使用到多层感知器的输出层和隐含层中,并提出了量子神经网络的学习算法。通过一个实际的分类问题实验验证了该方法的有效性。实验表明,无论输出层或隐含采用多级神经元,都可以带来分类能力的提高。而当输出层采用多级神经元时,还可以导致连接的减少和训练速度的加快。     

基于传感器阵列与前馈神经网络的气体辨识系统

将气体传感器阵列与前馈神经网络模式识别技术相结合形成气体辨识技术相结合形成气体辨识系统,通过实验比较了不同的传感器信号预处理方法、前馈神经网络的结构和参数对气体辨识系统性能的影响,研究结果具有一定的工程应用价值。     

利用人工神经网络SNC进行最优励磁控制

BP神经网络是一种多层结构的映射网络。由于它计算简单、存储量小,并具有分布并行处理特性,所以是目前应用最广的一种模型。本文设计了一种BP神经网络的监督学习控制器（SNC）,在线性最优励磁控制的基础上,利用3层BP神经网络对柴油发电机的控制过程进行监督学习。通过对网络的训练,使其能达到实时控制的目的。仿真结果表明,所设计的SNC在系统运行方式较大的变化范围内,都能提供很好的控制性能。     

基于神经网络近似的自适应优化控制

为了解决初始和终端确定的一类离散时间非线性系统有限时间优化控制,利用动态规划原理求解过程中遇到维数灾的问题,提出了基于神经网络的自适应动态规划近似优化控制.在分析动态规划求解遇到维数灾的基础上,进而给出了迭代ADP算法,并采用神经网络近似代价函数和控制律来实现迭代ADP算法,设计近似优化控制器.通过mat lab实验仿真结果表明,采用迭代ADP算法能够避免求解中遇到的维数灾,从而有效地实现了一类离散时间非线性系统的有限时间近似优化控制.     

一种鲁棒神经网络自适应控制策略及其应用

针对具有外部干扰等不确定因素的离散未知非线性受控对象,提出了一种鲁棒神经网络自适应控制策略.该策略运用自适应预测及带遗忘因子的递推最小二乘参数估计的思想,对神经网络的预报输出进行修正,利用鲁棒反馈控制器保证系统稳定性,并对控制信号的增量进行限幅以抑制突变大幅值干扰信号对系统的影响.将提出的控制方法应用于实验室级液面系统的仿真中,结果表明了该控制策略的有效性.     

基于BP神经网络的自适应补偿控制方法

研究工业过程控制系统补偿问题,对于一类模型未知的SISO非线性系统,传统的控制方法不能获得被控系统的精确数学模型,因而在系统稳定性和鲁棒性上存在缺馅,控制效果不佳。为了提高被控非线性系统的稳定性和鲁棒性,提出了一种基于BP神经网络的自适应补偿控制方法。首先,通过逆系统理推导了被控系统输出和伪控制量之间的误差,然后误差进行在线自适应BP神经网络补偿,从而实现对被控系统的BP神经网络自适应补偿控制,且采用Lyapunov理论证明BP神经而网络的收敛性和闭环系统的稳定性。计算机仿真表明所提方法明显提高了非线性系统的鲁棒控制性能。     

一种基于神经网络的非线性飞行控制系统设计方案研究

在全状态反馈的前提下,设计了一种基于在线神经网络和反馈线性化的非线性直接自适应控制器。本文首先利用多重尺度摄动与动态逆技术结合,设计了无人驾驶飞机的解析动态逆控制器;然后引入一个单隐层在线神经网络来修正各种因素引起的状态误差,并证明了控制器的稳定性。最后对在线网络的实现做了详细描述。仿真分析表明,该方案具有很强的鲁棒性和对故障状态的适应性。     

On the Approximation of Infinite Dimensional Optimal Stopping Problems with Application to Mathematical Finance

We consider the approximation of the optimal stopping problem for infinite dimensional processes by variational methods. To this end, we employ a Fourier-Legendre representation for the state space and exhaust an indexed family of regularized Hamilton-Jacobi characterizations. We implement our results utilizing penalization and a method-of-lines semi-implicit finite element method; application to term-structure valuation problems from mathematical finance demonstrate the applicability of the approach. This research was supported by the U.S. National Science Foundation, award number DMI-0422985.     

基于神经网络的迭代优化预测控制

针对时变的非线性系统,提出一种基于神经网络的迭代优化预测控制。它将传统的预测控制策略与神经网络逼近任息非线性函数的能力结合,预测系统未来输出,然后用迭代学习方法优化预测控制器,即通过一阶泰勒展开的方法,把非线性优化问题转化为线性优化问题。不仅简化计算,同时避免用神经网络优化控制器时,由于调节参数过多、涮前速度慢而导致系统闭环稳定性和鲁棒性差的问题。仿真结果表明,该控制方案具有良好的控制品质,并适应对象参数的变化,具有较强的鲁棒性和自适应性。     

Neural Network Structures for Optimal Control of LPCVD Reactors

In this paper, a new approach of LPCVD reactor modelling and control is presented, based on the use of neural networks. We first present the development of a hybrid networks model of the reactor. The objective is to provide a simulation model which can be used to compute online the film thickness on each wafer. In the second section, the thermal control of a LPCVD reactor is studied. The objective is to develop a multivariable controller to control a space- and time-varying temperature profile inside the reactor. A neural network is designed using a methodology based on process inverse dynamics modelling. Good control results have been obtained when tracking space-time temperature profiles inside the LPCVD reactor pilot plant. Finally, global software is elaborated to achieve film thickness control in an experimental LPCVD reactor pilot plant, in order to get a defined and uniform deposition thickness on the wafers all along the reactor. Experimental results are presented which confirm the efficiency of the optimal control strategy.     

前馈神经网络的一种快速学习算法

提出的算法是利用凸函数共轭性质中的Young不等式构造优化目标函数,这个优化目标函数对于权值和隐层输出来说为凸函数,不存在局部最小。首先把隐层输出作为变量进行优化更新,然后快速计算出隐层前后的权值。数值实验表明：此算法简单,收敛速度快,泛化能力强,并大大降低了学习误差。