Neural network control of nonlinear dynamic systems using hybrid algorithm

In this paper, a hybrid method is proposed to control a nonlinear dynamic system using feedforward neural network. This learning procedure uses different learning algorithm separately. The weights connecting the input and hidden layers are firstly adjusted by a self organized learning procedure, whereas the weights between hidden and output layers are trained by supervised learning algorithm, such as a gradient descent method. A comparison with backpropagation (BP) shows that the new algorithm can considerably reduce network training time.     

基于 BP 神经网络的铁路互联网售票系统信息安全评估方法

互联网售票逐步取代了传统售票方式,在铁路运输生产中发挥至关重要的作用,但由于其向互联网提供服务,面临多个层面的安全风险和威胁,受外部攻击、病毒感染等安全威胁日益增大,一旦遭受攻击或其他因素导致系统宕机或终止服务,产生社会负面影响巨大。针对上述威胁,需要安全维护人员运用科学的方法和手段,系统地分析系统所面临的威胁及其存在的脆弱性,评估安全事件一旦发生可能造成的危害程度,提出有针对性的抵御威胁的防护对策和整改措施,将风险控制在可接受的水平,最大限度地保障信息系统安全。人工神经网络具有常规方法所不具备的智能特性,具有自主获取和学习知识的功能,可以较好地处理不确定性和非线性的问题,目前基于人工神经网络的信息安全风险评估在多个行业中已经开展了研究并得到了应用。相对其他人工神经网络模型,BP 神经网络模型具有较强的非线性映射能力和自学习、自适应能力。首先,采用3层的神经网络能够以任意精度逼近任何非线性连续函数,使其适合于求解内部机制复杂的问题;其次,训练时能够通过学习自动提取输出、输出数据间的“合理规则”,并自适应的将学习内容记忆于网络的权值中。因此,文章根据铁路互联网售票系统复杂网络体系结构,采用具有3层结构的 BP 反向传播人工神经网络模型与之对应,准确反映互联网售票系统面临的各类安全威胁,并利用 BP 神经网络良好的自适应性和容错能力,以互联网售票系统面临的安全风险威胁等级值为训练样本,采用已训练的 BP 网络对互联网售票系统进行安全风险评估,设计了基于 BP 神经网络的风险评估模型,仿真结果表明,设计的模型具有很好的自适应性和容错能力,适用于复杂的互联网售票系统网络,实验数?     

BP算法收敛性分析及改进

在标准BP神经网络的训练中,将误差函数作为权值调整的依据,使用固定学习率计算权值,这样的结果往往使网络的学习速度过慢甚至无法收敛。对此,从网络收敛的稳定性和速度的角度出发,分析了误差函数和权值修改函数,对算法中学习率的作用进行了具体的讨论,提出了一种根据误差变化对学习率进行动态调整的方法。该方法简单实用,能有效防止网络训练时出现发散,提高网络的收敛速度和稳定性。     

改进BP网络及其在传感器非线性校正中的应用

针对传统BP网络收敛速度慢、容易陷入局部最小点等问题,采用附加动量因子和自适应学习速率进行了改进,并将其用于对传感器的非线性误差进行补偿.用MATLAB语言编制相应的训练程序,仿真结果表明,在相同的条件下,改进后算法节省了大量的训练时间,同时提高了数据拟合的精度.     

BP神经网络的联合优化算法

针对BP神经网络存在收敛速度慢、易陷入局部极小等缺陷,提出了一种自适应调节学习率和动态调整S型激励函数相结合的改进BP算法。该算法将学习率与误差函数相关联,再对每个隐单元和输出单元的激励函数的斜率进行自动调整。通过实例仿真,将改进算法与标准BP算法、加动量项法和自适应学习率法进行比较,来验证所提出方法的有效性。实验结果表明,联合优化的BP算法能有效加快网络的收敛过程,并具有较强的泛化能力。     

A neuron model with trainable activation function (TAF) and its MFNN supervised learning

This paper addresses a new kind of neuron model, which has trainable activation function (TAF) in addition to only trainable weights in the conventional M-P model. The final neuron activation function can be derived from a primitive neuron activation function by training. The BP like learning al-gorithm has been presented for MFNN constructed by neurons of TAP model. Several simulation ex-amples are given to show the network capacity and performance advantages of the new MFNN in com-parison with that of conventional sigmoid MFNN.     

When Does Online BP Training Converge?

The backpropogation (BP) neural networks have been widely applied in scientific research and engineering. The success of the application, however, relies upon the convergence of the training procedure involved in the neural network learning. We settle down the convergence analysis issue through proving two fundamental theorems on the convergence of the online BP training procedure. One theorem claims that under mild conditions, the gradient sequence of the error function will converge to zero (the weak convergence), and another theorem concludes the convergence of the weight sequence defined by the procedure to a fixed value at which the error function attains its minimum (the strong convergence). The weak convergence theorem sharpens and generalizes the existing convergence analysis conducted before, while the strong convergence theorem provides new analysis results on convergence of the online BP training procedure. The results obtained reveal that with any analytic sigmoid activation function, the online BP training procedure is always convergent, which then underlies successful application of the BP neural networks.     

多层前传神经网的广义误差反传训练与模式分类

本文以天然留兰香的组分构成与其品质的关系为例，讨论人工神经元方法用于复杂信息模式分类的问题，提出一种广义的误差反传训练策略，将网络的训练范围从联接权扩大到神经元模型，这种新的训练方法（ＧＢＰ）能提高多层前传网络的学习效率，加快收敛的速率。实际运行的结果表明，所需训练时间仅为普通误差反传（ＢＰ）训练方法的１／１５，并能达到较高的预报精度。     

Performance of fuzzy logic-based slope tuning of neural equaliser for digital communication channel

Adaptive equalisation in digital communication systems is a process of compensating the disruptive effects caused mainly by intersymbol interference in a band-limited channel and plays a vital role for enabling higher data rate in modern digital communication system. Designing efficient equalisers having low structural complexity and faster learning algorithms is also an area of much research interest in the present scenario. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP)-based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique provides faster learning with less training samples and significant performance gain. This research work also proposes adaptive channel equalisation techniques on recurrent neural network framework. Exhaustive simulation studies carried out prove that by replacing the conventional sigmoid activation functions in each of the processing nodes of recurrent neural network with multilevel sigmoid activation functions, the bit error rate performance has significantly improved. Further slopes of different levels of the multilevel sigmoid have been adapted using fuzzy logic control concept. Simulation results considering standard channel models show faster learning with less number of training samples and performance level comparable to the their conventional counterparts. Also, there is scope for parallel implementation of slope adaptation technique in real-time implementation, which saves the computational time.     

二进制神经网络分类问题的几何学习算法

分类问题在前向神经网络研究中占有重要位置.本文利用几何方法给出一个二进制神经网络K（≥2）分类问题的新学习算法.算法通过训练点的几何位置与类别分析，建立一个四层前向神经网络，实现网络输入向量分类.本文算法的优点在于:保证学习收敛且收敛速度快于BP算法及已有的其他一些前向网络学习算法;算法可以确定神经网络的结构且能实现精确的向量分类.另外，算法所建神经网络由线性阀值单元组成，神经元突触权值和阀值均为整数，特别适合于集成电路实现.     

Exponential Continuous Non-Parametric Neural Identifier With Predefined Convergence Velocity

This paper addresses the design of an exponential function-based learning law for artificial neural networks (ANNs) with continuous dynamics. The ANN structure is used to obtain a non-parametric model of systems with uncertainties, which are described by a set of nonlinear ordinary differential equations. Two novel adaptive algorithms with predefined exponential convergence rate adjust the weights of the ANN. The first algorithm includes an adaptive gain depending on the identification error which accelerated the convergence of the weights and promotes a faster convergence between the states of the uncertain system and the trajectories of the neural identifier. The second approach uses a time-dependent sigmoidal gain that forces the convergence of the identification error to an invariant set characterized by an ellipsoid. The generalized volume of this ellipsoid depends on the upper bounds of uncertainties, perturbations and modeling errors. The application of the invariant ellipsoid method yields to obtain an algorithm to reduce the volume of the convergence region for the identification error. Both adaptive algorithms are derived from the application of a non-standard exponential dependent function and an associated controlled Lyapunov function. Numerical examples demonstrate the improvements enforced by the algorithms introduced in this study by comparing the convergence settings concerning classical schemes with non-exponential continuous learning methods. The proposed identifiers overcome the results of the classical identifier achieving a faster convergence to an invariant set of smaller dimensions.      

神经网络建模在热膨胀螺栓形变测量中的应用

基于神经网络建立热膨胀螺栓形变的非线性数学模型。神经网络的辨识采用变尺度二阶快速学习算法,利用二阶插值法来优化搜索学习速率。新方法具有很快的收敛速度和良好的收敛精度,克服了BP算法在神经网络的权值训练中收敛速度过慢的缺点。热膨胀螺栓的受热形变测量结果表明,该学习算法适用于非线性系统的建模与辨识。     

量子门Elman神经网络及其梯度扩展的量子反向传播学习算法

针对Elman神经网络的学习速度和泛化性能, 提出一种具有量子门结构的新型Elman神经网络模型及其梯度扩展反向传播(Back-propagation)学习算法, 新模型由量子比特神经元和经典神经元构成. 新网络结构采用量子映射层以确保来自上下文单元的局部反馈与隐藏层输入之间的模式一致; 通过量子比特神经元输出与相关量子门参数的修正互补关系以提高网络更新动力. 新学习算法采用搜索然后收敛的策略自适应地调整学习率参数以提高网络学习速度; 通过将上下文单元的权值扩展到隐藏层的权值矩阵, 使其在与隐藏层权值同步更新过程中获取时间序列的额外信息, 从而提高网络上下文单元输出与隐藏层输入之间的匹配程度. 以峰值检波为例的数值实验结果显示, 在量子反向传播学习过程中, 量子门Elman神经网络具有较快的学习速度和良好的泛化性能.     

基于BtW的和声搜索算法在BP网络优化中的应用

针对和声搜索算法参数影响其优化BP神经网络的性能问题,提出了一种可有效提高BP神经网络收敛速度和准确度的基于BtW参数动态变化的改进和声算法,同时用于BP网络优化。算法根据和声搜索参数的特点,采用以BtW为自变量的非线性函数变换方法,对微调概率PAR和微调幅度BW进行动态调整,利用改进的和声搜索算法对BP神经网络的连接权和偏置值进行优化。实验结果表明,该算法有效改善了和声搜索算法在BP神经网络优化中的性能,提高了BP网络的训练速度和预测的准确度。     

BP算法参数选取及应用

本文对ｓｉｇｍｏｉｄ函数的陡度、学习速率、动量因子等的选取探讨，分析它们对收敛速度的影响，提出一些选取时应考虑的问题，在模糊控制规则生成和智能控制应用中证明本文提出的ＢＰ算法参数选取方法能有效地缩短训练时间。     

Multiplicative neuron model artificial neural network based on Gaussian activation function

Multiplicative neuron model-based artificial neural networks are one of the artificial neural network types which have been proposed recently and have produced successful forecasting results. Sigmoid activation function was used in multiplicative neuron model-based artificial neural networks in the previous studies. Although artificial neural networks which involve the use of radial basis activation function produce more successful forecasting results, Gaussian activation function has not been used for multiplicative neuron model yet. In this study, rather than using a sigmoid activation function, Gaussian activation function was used in multiplicative neuron model artificial neural network. The weights of artificial neural network and parameters of activation functions were optimized by guaranteed convergence particle swarm optimization. Two major contributions of this study are as follows: the use of Gaussian activation function in multiplicative neuron model for the first time and the optimizing of central and propagation parameters of activation function with the weights of artificial neural network in a single optimization process. The superior forecasting performance of the proposed Gaussian activation function-based multiplicative neuron model artificial neural network was proved by applying it to real-life time series.     

局部式反传网络的改进BP算法及应用

针对标准BP算法收敛速度慢的缺点,分析了其产生的主要原因,提出了一种改进BP算法。在传统BP算法基础上通过对其激励函数增加陡度因子并在误差反传权值修正时增加协调器,通过对网络灵敏度的分析将全反传式网络变成局部式反传网络,从而达到提高网络学习速率及精度的目的。改进的BP算法应用于导向钻井稳定平台系统的辨识,仿真结果表明该算法收敛速度快,精度高。     

基于PID神经网络的非线性动态系统控制

基于PID神经网络的控制器可以完成变量的单输入-单输出非线性系统的任务.该控制器采用BP(误差反向传播)算法来修正连接权重值,通过在线训练和学习,使目标函数到达最优值.充分利用了BP神经网络算法逼近任意连续有界非线性函数的能力,显示了神经网络在解决非线性系统方面的潜能.为了达到控制的目的,和其他非线性建模技术相比较,PID神经网络有几个明确的优点和它独特的用法相一致.仿真结果表明,在对非线性动态系统控制时,基于PID神经网络的控制系统具有很强的灵活和高效性,能取得良好的控制效果.     

Legender神经网络建模及股票预测

基于多项式逼近理论,将一组Legender正交多项式做为隐含层神经元的传递函数,再以其加权和函数做为神经网络输出,从而构成一种新型的三层多输入Legender神经网络模型;采用BP学习算法,通过对历史观测样本数据的训练,调整该神经网络的权值,建立非线性时间序列辨识模型,以此预测股票价格的变化.仿真实验表明,Legender神经网络具有优良的逼近任意非线性系统的特性,且学习收敛速度很快;深发展A股预测结果为：训练次数200,最大相对误差5.41%;深证成指预测结果为：训练次数120,最大相对误差4.17%.     

人工神经网络BP算法的改进及其在无损检测中的应用

采用多层感知器（MLP）与误差反向传播算法（er-ror back-propagation algorithm)构造与监督训练人工祖辈 经网络,采用了改进的非线性激励函数与学习率的误差反向传播算法,超声无损检测的计算机模拟与实验结果表明,改进的BP算法收敛速度较之BP算法明显加快。