结合稳态模型的非线性动态建模方法及应用

考虑到热工对象的动态特性大多从阶跃响应获得,非线性的存在使此种线性动态模型只能在相应稳态点附近有良好的性能,文中采用了基于非线性稳态模型来实现动态模型自适应的策略,该策略用较为精确的非线性稳态模型得到当前输入下的稳态参数,然后由此修正线性动态模型中与稳态相关的参数,实现了动态模型的自适应,进而有效提高了大范围下的动态预测性能。通过对某电厂360 MW"W型"火焰强制循环固态排渣煤粉炉的稳态和动态试验,建立了NOx的神经网络稳态模型和线性动态模型,用两个不同工况下的实际数据,验证了结合稳态模型的非线性自适应动态模型比线性动态模型具有更好的NOx排放预测性能。     

基于神经网络的双闭环伺服系统自适应控制

针对双闭环伺服系统中传统自抗扰控制（ADRC）控制器待整定的参数较多且整定过程较复杂的问题,设计了一种基于径向基函数神经网络的ADRC控制器。考虑到组合控制律的独立性,设计线性状态误差反馈进一步降低参数整定复杂性。径向基函数神经网络将扩张状态观测器中的非线性误差增益作为其权值系数,在线辨识出被控对象的Jacobian信息,利用神经网络的自学习功能实现了ADRC的参数在线自整定。以永磁同步电机(PMSM)作为被控对象,通过MATLAB进行仿真。仿真结果证明,此控制策略有效地优化了伺服系统的静态性能和动态品质,实现了控制系统的高动态和高精度。     

基于神经网络的自主水下机器人动态反馈控制

针对自主水下机器人数学模型的强非线性及所受海流干扰无法确定等特点,设计了基于神经网络补偿器的动态反馈控制算法.通过对自主水下机器人系统数学模型研究,将系统分解为近似线性部分与非线性不确定部分.通过动态反馈控制实现对分解出的近似线性部分进行初步控制,利用神经网络所具有的自适应控制实现对不确定模型与干扰项进行补偿控制,提高...     

基于降阶状态观测器的压水堆功率自抗扰控制

压水堆是高度非线性、参数时变,并存在较大不确定性的被控对象,工程应用要求其控制器鲁棒性好,抗扰能力强,结构简单,参数整定方便。根据上述需求,文中给出了一种基于线性自抗扰控制的压水堆功率控制器设计方法。首先基于压水堆非线性模型推导出了用于控制器设计的相对功率的二阶非线性模型。然后设计了两种基于降阶扩张状态观测器的压水堆功率线性自抗扰控制策略,即没有模型信息和利用模型信息的情况。并运用变量代换方法避免了观测器要求输入功率的导数项,使其工程实现更容易。仿真结果表明,所设计的两种控制器均具有良好的跟踪性能和抗干扰能力。在模型引入参数时变、参数摄动、未建模动态情况下,均能取得较好的控制品质。但充分利用模型信息时控制性能和性能鲁棒性更佳。     

感应电机调速系统模糊神经网络逆鲁棒控制

以多变量、非线性、强耦合的感应电机调速系统为研究对象,采用模糊神经网络逆鲁棒控制策略,通过模糊神经网络加积分器来构造感应电机调速系统的动态逆系统,将二者串联重构成伪线性复合系统,基于内模控制,根据复合系统的特性设计鲁棒控制器,实现了感应电机转速的高精度鲁棒控制.仿真和实验结果表明系统具有优良的静态及动态性能,对负载扰动、参数摄动和未建模动态等具有很强的鲁棒性.     

基于GA-RBF神经网络逆的两电机同步控制

以多变量、非线性、强耦合的两电机同步控制系统为研究对象,提出了基于遗传算法的径向基函数(GA-RBF)神经网络逆的两电机同步控制方法。根据给定的性能指标,采用遗传算法对RBF神经中心进行优化,在此基础上串联RBF神经网络逆与两电机系统,构建复合伪线性系统。这一复杂控制对象即可解耦成转速与张力两个线性子系统,进而通过设计线性闭环调节器实现了解耦控制。实验结果表明,采用GA-RBF神经网络逆的两电机系统,对速度和张力实现了较好的解耦控制,且具有较强的抗干扰能力。     

两电机调速系统的神经网络逆无模型自适应鲁棒解耦控制

为了解决非线性强耦合的多输入/输出的两电机调速系统存在较大负载扰动的问题,提出一种基于神经网络逆(neural network inverse,NNI)的鲁棒解耦控制策略。首先,根据逆系统理论,分析系统的可逆性,利用神经网络逼近原系统逆模型,将强耦合的两电机非线性系统线性化解耦为一伪线性复合系统。其次,针对两电机调速系统中负载扰动的问题,根据动态线性化理论,设计无模型自适应(model-freeadaptive,MFA)补偿控制器;将MFA补偿控制器与伪线性化复合系统相结合,以提高神经网络逆控制的两电机调速系统在负载扰动下的抗扰性能。基于Matlab/Simulink和PLC实验平台进行仿真和实验。实验结果表明:基于神经网络逆系统的MFA鲁棒控制策略不仅能很好地实现两电机转速与张力的解耦,还对负载扰动具有很强的抗扰性能。     

基于粒子群优化神经网络观测器感应电机定子电阻辨识

针对感应电机模型参数时变性突出的问题,提出一种基于粒子群优化神经网络观测器感应电机定子电阻辨识方法。该方法首先通过构建一个含待辨识参数的非线性函数,然后根据神经网络的一致逼近任意非线性连续函数的性质,利用RBF神经网络逼近这个非线性函数,并在此基础上构造自适应观测器。采用伪降阶观测器结构,减少了参数辨识的计算时间;用粒子群优化算法对神经网络参数进行优化,提高了神经网络的收敛速度和逼近精确度。仿真和实验结果验证该方法鲁棒性强,动态性能好,具有较好的辨识效果。     

基于改进型BP神经网络的瓦斯传感器的非线性校正

提出了一种基于改进型BP神经网络的瓦斯传感器的非线性校正方法,利用神经网络良好的非线性映射能力,逼近反非线性函数完成非线性校正.仿真实验结果表明:与分段线性校正和传统BP算法相比,改进型的BP神经网络收敛速度快、逼近精度高,准确度由原来分段线性校正的±5.02%提高到现在的±0.130%,且易于动态调校.     

多层前馈神经网络及其在开关变换器中的应用

多层前馈神经网络具有多层结构、可鉴别神经元特性函数和误差反传算法等三个要素.本文从多层前馈神经网络的结构和原理出发,分析了多层前馈神经网络的非线性函数映射能力,以此为基础,从而可以实现其在系统辨识和非线性控制上的作用.另外,以Boost变换器的神经网络辨识器和控制器的设计为例,探讨了开关变换器的数学建模方法和多层前馈神经网络在其中的应用,使得各种线性和非线性控制方法均可以利用多层前馈神经网络来实现,并具有统一的设计和训练措施.     

Elman神经网络在非线性模拟电路故障诊断中的应用

Elman神经网络把隐层输出反馈回输入层,是一种动态递归神经网络,改进的Elman网络能逼近任意动态非线性系统。本文研究了Elman网络的结构和学习算法,并把改进的Elman网络应用于非线性模拟电路故障诊断激励信号参数优化中,以提高故障正确诊断率。首先用改进的Elman神经网络建立故障电路和无故障电路系统模型,然后用遗传算法搜索电路故障诊断的最佳激励信号参数。     

Neural networks with quantum architecture and quantum learning

A method is proposed for solving the two key problems facing quantum neural networks: introduction of nonlinearity in the neuron operation and efficient use of quantum superposition in the learning algorithm. The former is indirectly solved by using suitable Boolean functions. The latter is based on the use of a suitable nonlinear quantum circuit. The resulting learning procedure does not apply any optimization method. The optimal neural network is obtained by applying an exhaustive search among all the possible solutions. The exhaustive search is carried out by the proposed quantum circuit composed of both linear and nonlinear components. Copyright © 2009 John Wiley & Sons, Ltd.     

Perceptron-how this neural network model lets you evaluate Booleanfunctions

The author explores aspects of just what a neural network can do, by building a simple model that evaluates Boolean functions. The neural network model for the system that the author is building is one of the earliest: the perceptron, developed by Rosenblatt in the 1960s. The goal of the present work is to build a perceptron that can evaluate Boolean functions by learning the input patterns and the associated output. A major part of the process of building a neural net, the training of the network, is discussed. A wide variety of training algorithms have been developed. An analysis of the system is given, and limitations of the perceptron are described     

Programmable analogue vlsi cnn chip with local digital logic

A new integrated circuit cellular neural network implementation with digitally or continuously selectable template coefficients is presented. Local logic and memory are added into each cell, providing a simple dual (analogue and digital) computing structure. Variable gain OTAs are used as the voltage-controlled current sources to programme the template element values. the cells have local switched feedback (both analogue and digital) to feed from the output to the input or state capacitor. Therefore this analogue array processor can be applied to solve problems with a sequence of different templates. A 4 × 4 CNN circuit is realized using the 2 μm analogue CMOS process.     

基于小波能量与神经网络的断路器振动信号识别方法

高压断路器出现机械故障不仅会引起振动冲击事件的时间漂移,还会引起时域波形中一些波峰幅值的变化。依据同一类型断路器振动信号相似的特点,在对高压断路器故障振动信号进行特征分析的基础上,提出了一种识别高压断路器振动信号的新方法:将小波包提取算法和径向基神经网络模式识别功能相结合,利用小波包分解与重构原理将断路器合闸振动信号分解到不同频段中,提取每个频带能量作为断路器状态监测的特征向量,作为径向基神经网络的输入向量;基于径向基神经网络的故障诊断方法在系统参数未知的情况下自动建立动态模型,对于线性系统和非线性系统都有很好的跟踪能力,通过实验室断路器典型合闸振动信号的监测及识别分析验证了该方法的有效性。     

A small‐gain approach for adaptive output‐feedback NN control of switched pure‐feedback nonlinear systems

This paper investigates the problem of adaptive output‐feedback neural network (NN) control for a class of switched pure‐feedback uncertain nonlinear systems. A switched observer is first constructed to estimate the unmeasurable states. Next, with the help of an NN to approximate the unknown nonlinear terms, a switched small‐gain technique‐based adaptive output‐feedback NN control scheme is developed by exploiting the backstepping recursive design scheme, input‐to‐state stability analysis, the common Lyapunov function method, and the average dwell time (ADT) method. In the recursive design, the difficulty of constructing an overall Lyapunov function for the switched closed‐loop system is dealt with by decomposing the switched closed‐loop system into two interconnected switched systems and constructing two Lyapunov functions for two interconnected switched systems, respectively. The proposed controllers for individual subsystems guarantee that all signals in the closed‐loop system are semiglobally, uniformly, and ultimately bounded under a class of switching signals with ADT, and finally, two examples illustrate the effectiveness of theoretical results, which include a switched RLC circuit system.     

Adaptive fuzzy backstepping dynamic surface control for a class of MIMO nonlinear systems with input delays and state time‐varying delays

In this paper, an adaptive fuzzy backstepping dynamic surface control (DSC) approach is developed for a class of MIMO nonlinear systems with input delays and state time‐varying delays. The unknown continuous nonlinear functions are expressed as the linearly parameterized form by using the fuzzy logic systems, and then, by combining the backstepping technique, the appropriate Lyapunov–Krasovskii functionals, and the ‘minimal learning parameters’ algorithms with the DSC approach, the adaptive fuzzy tracking controller is designed. Our development is able to eliminate the problem of ‘explosion of complexity’ inherent in the existing backstepping‐based methods. It is proven that the proposed design method can guarantee that all the signals in the closed‐loop system are bounded and the tracking error is smaller than a prescribed error bound. Finally, simulation results are provided to show the effectiveness of the proposed approach. Copyright © 2014 John Wiley & Sons, Ltd.     

基于MATLAB的BPNN在变压器故障诊断中的仿真参数研究

首先简要介绍了基于油中溶解气体DGA( Dissolved Gas - in - oil Analysis)的变压器故障诊断机理,然后介绍了反向传播神经网络BPNN( Back - propagation Neural Network)的网络结构、学习算法和训练流程,并结合变压器故障实际特点,分析了输入输出模式的确定、隐含层设计、传递函数和训练函数的选择对于整个网络设计的重要性,通过在MATLAB中神经网络工具箱平台上的仿真比较找出合理的参数,从而建立基于BPNN的变压器故障诊断模型,最后通过对验证样本的仿真诊断结果对比,说明了该模型在实际应用中的有效性.     

Cellular neural network with trapezoidal activation function

This paper presents a cellular neural network (CNN) scheme employing a new non‐linear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly non‐separable data points and realize Boolean operations (including eXclusive OR) by using only a single‐layer CNN. In order to simplify the stability analysis, a feedback matrix W is defined as a function of the feedback template A and 2D equations are converted to 1D equations. The stability conditions of CNN with TAF are investigated and a sufficient condition for the existence of a unique equilibrium and global asymptotic stability is derived. By processing several examples of synthetic images, the analytically derived stability condition is also confirmed. Copyright © 2005 John Wiley & Sons, Ltd.     

基于模糊神经网络的交流伺服系统

提出了一种基于神经网络的模糊控制交流伺服系统,将神经网络与模糊逻辑结合起来,输入信号先模糊化,然后通过构建的神经网络,在线调整其权值和变化的控制参数,使系统的输出具有更好的动、静态性能,提高了系统的鲁棒性。仿真实验证明了这种基于神经网络模糊控制方法在交流伺服系统中应用的可行性和可靠性。