RBF neural networks-based robust adaptive tracking control for switched uncertain nonlinear systems

In this paper, a robust adaptive H∞ control scheme is presented for a class of switched uncertain nonlinear systems. Radical basis function neural networks (RBF NNs) are employed to approximate unknown nonlinear functions and uncertain terms. A robust H∞ controller is designed to enhance robustness due to the existence of the compound disturbance which consists of approximation errors of the neural networks and external disturbance. Adaptive neural updated laws and switching signals are deducted from multiple Lyapunov function approach. It is proved that with the proposed control scheme, the resulting closed-loop switched system is robustly stable and uniformly ultimately bounded (UUB) such that good capabilities of tracking performance is attained and H∞ tracking error performance index is achieved. A practical example shows the effectiveness of the proposed control scheme.     

A neural networks-based negative selection algorithm in fault diagnosis

Inspired by the self/nonself discrimination theory of the natural immune system, the negative selection algorithm (NSA) is an emerging computational intelligence method. Generally, detectors in the original NSA are first generated in a random manner. However, those detectors matching the self samples are eliminated thereafter. The remaining detectors can therefore be employed to detect any anomaly. Unfortunately, conventional NSA detectors are not adaptive for dealing with time-varying circumstances. In the present paper, a novel neural networks-based NSA is proposed. The principle and structure of this NSA are discussed, and its training algorithm is derived. Taking advantage of efficient neural networks training, it has the distinguishing capability of adaptation, which is well suited for handling dynamical problems. A fault diagnosis scheme using the new NSA is also introduced. Two illustrative simulation examples of anomaly detection in chaotic time series and inner raceway fault diagnosis of motor bearings demonstrate the efficiency of the proposed neural networks-based NSA.     

A neural networks-based approach for strategic planning

We establish a systematic approach that incorporates neural networks in conjunction with portfolio matrices to assist managers in evaluating and forming strategic plans. Based on the principle of dispersing risks, we also provide a linear integer programming model, which helps in allocating the annual budget optimally among proposed strategies. The approach has been successfully implemented for a major food industry leader in Taiwan for its annual strategic planning. Although a particular portfolio matrix model was adopted in our approach, the framework proposed here can be modified to incorporate other strategy-evaluation measures.     

Fuzzy neural networks-based quality prediction system for sinteringprocess

A hybrid fuzzy neural networks and genetic algorithm (GA) system is proposed to solve the difficult and challenging problem of constructing a system model from the given input and output data to predict the quality of chemical components of the finished sintering mineral. A bidirectional fuzzy neural network (BFNN) is proposed to represent the fuzzy model and realize the fuzzy inference. The learning process of BFNN is divided into off-line and online learning. In off-line learning, the GA is used to train the BFNN and construct a system model based on the training data. During online operation, the algorithm inherited from the principle of backpropagation is used to adjust the network parameters and improve the system precision in each sampling period. The process of constructing a system model is introduced in details. The results obtained from the actual prediction demonstrate that the performance and capability of the proposed system are superior     

RBF networks-based adaptive approximate model controller for steam valving control

This paper proposes a novel steam valving controller using radial basis function (RBF) networks-based approximate model method. Approximate model method is a kind of direct linearization approach that is derived based on the approximation of the plant’s input–output model via Taylor expansion. RBF networks are used to identify the plant to implement the approximate model control law. In order to improve the performance of the approximate model controller, RBF networks weights are adjusted online using BP algorithms with an adaptive learning rate. Several simulations results demonstrate the effectiveness of the proposed controller for team valving control.     

Neural networks-based adaptive control for a class of nonlinear bioprocesses

The paper studies the design and analysis of a neural adaptive control strategy for a class of square nonlinear bioprocesses with incompletely known and time-varying dynamics. In fact, an adaptive controller based on a dynamical neural network used as a model of the unknown plant is developed. The neural controller design is achieved by using an input–output feedback linearization technique. The adaptation laws of neural network weights are derived from a Lyapunov stability property of the closed-loop system. The convergence of the system tracking error to zero is guaranteed without the need of network weights convergence. The resulted control method is applied in a depollution control problem in the case of a wastewater treatment bioprocess, belonging to the square nonlinear class, for which kinetic dynamics are strongly nonlinear, time varying and not exactly known.     

自适应前馈神经网络结构优化设计

针对多数前馈神经网络结构设计算法采取贪婪搜索策略而易陷入局部最优结构的问题,提出一种自适应前馈神经网络结构设计算法.该算法在网络训练过程中采取自适应寻优策略合并和分裂隐节点,达到设计最优神经网络结构的目的.在合并操作中,以互信息为准则对输出线性相关的隐节点进行合并;在分裂操作中,引入变异系数,有助于跳出局部最优网络结构.算法将合并和分裂操作之后的权值调整与网络对样本的学习过程结合,减少了网络对样本的学习次数,提高了网络的学习速度,增强了网络的泛化性能.非线性函数逼近结果表明,所提算法能得到更小的检测误差,最终网络结构紧凑.     

一种基于自适应遗传算法的神经网络学习算法

结合遗传算法与梯度下降法优点,提出了一种训练神经网络权值的混合优化算法,同时能够优化网络的结构.首先利用全局搜索能力可靠的遗传算法,采用递阶编码方案和自适应变异概率,同时优化网络的权值和结构,在进化结束时,能够寻到全局最优点附近的点.在遗传算法搜索结果的基础上,利用局部寻优能力较强的梯度下降法,从此点出发,进行局部搜索,最终达到网络的训练目标.与单一的遗传算法或者梯度下降法比较而言,混合优化算法的收敛速度明显提高.     

基于PSO-BP神经网络的煤矿井下自适应定位算法

提出了一种基于PSO-BP神经网络的煤矿井下自适应定位算法。针对传统的基于测距模型的定位算法易受煤矿井下环境干扰、测距误差大的问题,选择指纹匹配定位模型。针对煤矿井下环境强时变性,易增大实时采集的指纹信息与离线阶段建立的静态指纹数据库信息的匹配误差问题,将信标节点作为参考点的校准节点,以更好地反映参考点随环境变化的情况,避免增加额外的校准节点;在不增加硬件成本的同时,通过动态补偿法实时修正目标节点指纹数据,解决了指纹匹配定位模型自适应差的问题。匹配定位阶段采用PSO优化BP神经网络权值,以加速BP神经网络收敛,提高学习速度。实验结果表明,该算法更加适应随时间变化的煤矿井下环境,满足井下自适应定位要求。     

基于SAPSO-BP神经网络的井下自适应定位算法

针对基于传统BP神经网络的井下定位算法存在收敛速度慢、易形成局部极值、在煤矿井下强时变性电磁环境中定位误差大等问题,提出了一种基于模拟退火思想的粒子群优化算法加BP神经网络(SAPSO-BP)的井下自适应定位算法。采用SAPSO算法优化BP神经网络的初始权值和阈值,以加快训练收敛速度,使之到达全局最优;通过安装在井下巷道中的无线校准器采集目标点接收信号强度指示(RSSI)值,采用自适应动态校准方法对RSSI值进行实时校准,以减小强时变性电磁环境对定位精度的影响;最后利用SAPSO-BP神经网络估算出目标点位置坐标。实验结果表明,该算法的定位误差在2m内的置信概率为77.54%,平均误差为1.53m,定位性能优于未校准SAPSO-BP神经网络算法、PSO-BP神经网络算法、BP神经网络算法。     

Neural networks-based adaptive bidding with the contract net protocol in multi-robot systems

This paper investigates the effectiveness of using the Contract Net Protocol, an auction type system, for controlling task allocation among a group of robots, and presents and evaluates a strategy of using Artificial Neural Networks to formulate adaptive bids within the framework of the Contract Net Protocol. The robots were used in a foraging environment and showed that excellent communication among robots leads to a need for a social control mechanism for managing the robots, such as the Contract Net Protocol. The experiments also confirmed that a moderate benefit can be gained by using adaptive bidding within the framework of the Contract Net Protocol.     

Supervised adaptive clustering: A hybrid neural network clustering algorithm

A neural network architecture is introduced which implements a supervised clustering algorithm for the classification of feature vectors. The network is selforganising, and is able to adapt to the shape of the underlying pattern distribution as well as detect novel input vectors during training. It is also capable of determining the relative importance of the feature components for classification. The architecture is a hybrid of supervised and unsupervised networks, and combines the strengths of three wellknown architectures: learning vector quantisation, backpro-pagation and adaptive resonance theory. Network performance is compared to that of learning vector quantisation, back-propagation and cascade-correlation. It is found that performance is generally as good as or better than the performance of these other architectures, while training time is considerably shorter. However, the main advantage of the hybrid architecture is its ability to gain insight into the feature pattern space.Nomenclature O _j The output value of thejth unit - I _i Theith component of the input pattern - W _ij The weight of the cluster connection between theith input and thejth unit - B _ij The weight of the shape connection between theith input and thejth unit - N The dimension of the input patterns - v _j The vigilance parameter of thejth unit - v _init The initial vigilance parameter value - v _rate The change in the vigilance parameter value - X _i Theith direction in anN-dimensional coordinate system - T _k The classification tag of thekth unit - C The classification tag of the current input vector - (p) The learning rate at thepth epoch for the cluster weights - p The current epoch - P The total number of epochs - E _k The error associated with thekth unit - The constant learning rate for the shape weights - a _j The age in epochs of thejth unit     

Evaluation of neural networks-based controllers in batch polymerisation of methyl methacrylate

The importance of batch reactors in today's process industries cannot be overstated. Thus said, it is important to optimise their operation in order to consistently achieve products of high quality while minimising the production of undesirables. In processes like polymerisation, these reactors are responsible for a greater number of products than other reactor types and the need for optimal operation is therefore greater.

An approach based on an offline dynamic optimisation and online control strategy is used in this work to generate optimal set point profiles for the batch polymerisation of methyl methacrylate. Dynamic optimisation is carried out from which controller set points to attain desired polymer molecular end point characteristics are achieved. Temperature is the main variable to be controlled, and this is done over finite discrete intervals of time.

For on-line control, we evaluate the performance of neural networks in two controllers used to track the derived optimal set points for the system. The controllers are generic model control (GMC), ([P.L. Lee, G.R. Sullivan, Generic model control, Comput. Chem. Eng. 12(6) (1998) 573–580]) and the neural network-based inverse model-based control (IMBC), ([M.A. Hussain, L.S. Kershenbaum, Implementation of an inverse model based control strategy using neural networks on a partially simulated exothermic reactor, Trans. IchemE 78(A) (2000) 299–311]). Although the GMC is a model-based controller, neural networks are used to estimate the heat release within its framework for on-line control. Despite the application of these two controllers to general batch reactors, no published work exists on their application to batch polymerisation in the literature. In this work, the performance of the neural networks within each controller's algorithm for tracking and setpoint regulation of the optimal trajectory and in robustness tests on the system is evaluated.     

基于自适应线性神经元网络的谐波检测算法

为了克服基于傅里叶变换(FFT)谐波检测算法运算量大、实时性不强、易受噪声影响的缺点,提出了基于自适应线性神经元网络(ADALINE)的谐波检测算法,建立了基于最小二乘法(LMS)的最优解求解过程的数学模型,根据LMS误差与各次谐波傅里叶系数之间的三维流形的几何形状选择算法的步长因子。采用时域迭代的方法准确地提取基波有功、无功和各次谐波分量,为实现APF可选择性谐波补偿奠定了基础。     

Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks

The major drawbacks of backpropagation algorithm are local minima and slow convergence. This paper presents an efficient technique ANMBP for training single hidden layer neural network to improve convergence speed and to escape from local minima. The algorithm is based on modified backpropagation algorithm in neighborhood based neural network by replacing fixed learning parameters with adaptive learning parameters. The developed learning algorithm is applied to several problems. In all the problems, the proposed algorithm outperform well.     

基于自适应递阶遗传算法的神经网络优化策略

基于递阶结构的遗传算法可以同时对多层前向神经网络进行结构优化和权重求解。与基本的遗传算法相比，这种算法不仅在权重训练方面更加快速稳定，而且能在学习过程中确定网络的拓扑结构，具有较高的学习效率，而在遗传过程中采用自适应的交叉和变异概率能有效加快遗传速度和避免早熟现象的出现。     

Blind source separation with dynamic source number using adaptive neural algorithm

A difficult blind source separation (BSS) issue dealing with an unknown and dynamic number of sources is tackled in this study. In the past, the majority of BSS algorithms familiarize themselves with situations where the numbers of sources are given, because the settings for the dimensions of the algorithm are dependent on this information. However, such an assumption could not be held in many advanced applications. Thus, this paper proposes the adaptive neural algorithm (ANA) which designs and associates several auto-adjust mechanisms to challenge these advanced BSS problems. The first implementation is the on-line estimator of source numbers improved from the cross-validation technique. The second is the adaptive structure neural network that combines feed-forward architecture and the self-organized criterion. The last is the learning rate adjustment in order to enhance efficiency of learning. The validity and performance of the proposed algorithm are demonstrated by computer simulations, and are compared to algorithms with state of the art. From the simulation results, these have been confirmed that the proposed ANA performed better separation than others in static BSS cases and is feasible for dynamic BSS cases.     

On realizability of neural networks-based input-output models in the classical state-space form

This paper proves that the typical neural network-based input/output model does not have a state-space realization and suggests the Additive Nonlinear Auto-Regressive with eXogenous input (ANARX) structure as an excellent choice for neural-network-based input-output models. The advantage of the ANARX model is that the time-steps in the argument are pair-wise decomposed, which allows the ANARX model to be realized in state space, and to be linearized via dynamic output feedback. Moreover, accessibility of the state-space realization has been proved.     

Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks

This paper presents a novel multi-objective genetic algorithm (MOGA) based on the NSGA-II algorithm, which uses metamodels to determine optimal sampling locations for installing pressure loggers in a water distribution system (WDS) when parameter uncertainty is considered. The new algorithm combines the multi-objective genetic algorithm with adaptive neural networks (MOGA–ANN) to locate pressure loggers. The purpose of pressure logger installation is to collect data for hydraulic model calibration. Sampling design is formulated as a two-objective optimization problem in this study. The objectives are to maximize the calibrated model accuracy and to minimize the number of sampling devices as a surrogate of sampling design cost. Calibrated model accuracy is defined as the average of normalized traces of model prediction covariance matrices, each of which is constructed from a randomly generated sampling set of calibration parameter values. This method of calculating model accuracy is called the ‘full’ fitness model. Within the genetic algorithm search process, the full fitness model is progressively replaced with the periodically (re)trained adaptive neural network metamodel where (re)training is done using the data collected by calling the full model. The methodology was first tested on a hypothetical (benchmark) problem to configure the setting requirement. Then the model was applied to a real case study. The results show that significant computational savings can be achieved by using the MOGA–ANN when compared to the approach where MOGA is linked to the full fitness model. When applied to the real case study, optimal solutions identified by MOGA–ANN are obtained 25 times faster than those identified by the full model without significant decrease in the accuracy of the final solution.