Neural network principal components preprocessing and diffraction tomography

The use of principal component analysis in preprocessing neural network input data is explored. Four preprocessing schemes are compared in an example problem, and the theoretical basis for the results are discussed. A preconditioning method for the principal components is introduced here, combining normalisation and improved conditioning. The techniques are applied to an object location problem in diffraction tomography. The spectral analysed scattered field from an irradiated object form the input to a Multilayer Perceptron neural network, trained by backpropagation to calculate the coordinates of the object's centre in 2D.Aspects of this work were presented at the NCAF Symposium, King's College London, 9 January 1992.     

Neural network compensation control for mechanical systems with disturbances

Two novel compensation schemes based on accelerometer measurements to attenuate the effect of external vibrations on mechanical systems are proposed in this paper. The first compensation algorithm exploits the neural network as the feedback-feedforward compensator whereas the second is the neural network feedforward compensator. Each compensation strategy includes a feedback controller and a neural network compensator with the help of a sensor to detect external vibrations. The feedback controller is employed to guarantee the stability of the mechanical systems, while the neural network is used to provide the required compensation input for trajectory tracking. Dynamics knowledge of the plant, disturbances and the sensor is not required. The stability of the proposed schemes is analyzed by the Lyapunov criterion. Simulation results show that the proposed controllers perform well for a hard disk drive system and a two-link manipulator.     

基于自适应评价的非线性系统神经网络控制

针对一类非线性系统,提出了一种自适应评价方法．该方法可以控制系统输出对参考信号进行跟踪,其评价函数可直接解析求出．该方法只需一个动作网络用于产生控制动作,并且方法中的网络权值初始化可随机选取．使用Lyapunov方法对整个系统的动态性能进行分析,证明了在一定条件下此方法能保证闭环误差及网络权值一致最终有界．仿真结果与理论分析相一致,证明了所提出方法的有效性．     

Neural network evaluation of steel beam patch load capacity

This work presents a neural network modelling to forecast steel beam patch load resistance. In preceding studies, the results of a neural network system composed of four neural networks, have been compared and calibrated with experimental data and existing design formulae, showing a good agreement. Despite these results, the adopted system did not properly consider the differences in behaviour of slender, intermediate and compact beams. This paper introduces a new strategy based on a single neural network, which is trained with a different normalisation parameter. The neural network presented a maximum error value lower than 30%, while existing formulas presented errors greater than 40%.     

Neural network ensembles: evaluation of aggregation algorithms

Ensembles of artificial neural networks show improved generalization capabilities that outperform those of single networks. However, for aggregation to be effective, the individual networks must be as accurate and diverse as possible. An important problem is, then, how to tune the aggregate members in order to have an optimal compromise between these two conflicting conditions. We present here an extensive evaluation of several algorithms for ensemble construction, including new proposals and comparing them with standard methods in the literature. We also discuss a potential problem with sequential aggregation algorithms: the non-frequent but damaging selection through their heuristics of particularly bad ensemble members. We introduce modified algorithms that cope with this problem by allowing individual weighting of aggregate members. Our algorithms and their weighted modifications are favorably tested against other methods in the literature, producing a sensible improvement in performance on most of the standard statistical databases used as benchmarks.     

混沌系统的神经网络预测控制

提出一种基于预测控制的神经网络控制方法，将模型未知时的混沌运动控制到不稳定的不动点（UFP）处，该控制系统不需要UFP的位置及其局性态等知识，它包括观测器、带反馈校正的神经网络在预测器和在线训练的神经网络控制器，其方法简便，收敛速度比现有同类方法快得多，同时还分析了控制系统的稳定性，并证明了神经网络控制器的收敛性，理论推导和仿真结果都表明了该方法的有效性。     

基于神经网络的拒绝服务攻击预测

基于神经网络的拒绝服务攻击的预测能对相应主机是否受到服务攻击的检测,而通过类神经网络的构建实现了网络安全环境的创建和营造,拒绝服务攻击针对的是桌一网络的服务,从而向相应的主机发送大量的网络信息,从而用信息的攻势致使服务器处于忙碌的状态,阻碍了其他网络的正常服务和信息的传输。互联网上的主机应建立正常运转下的训练。从而建立神经网络的拒绝服务攻击的预测系统,保证系统的安全和运行的稳定。     

Neural network recognition of electronic malfunctions

Neural network software can be applied to manufacturing process control as a tool for diagnosing the state of an electronic circuit board. The neural network approach significantly reduces the amount of time required to build a diagnostic system. This time reduction occurs because the ordinary combinatorial explosion in rules for identifying faulted components can be avoided. Neural networks circumvent the combinatorial explosion by taking advantage of the fact that the fault characteristics of multiple simultaneous faults frequently correlate to the fault characteristics of the individual faulted components. This article clearly demonstrates that state-of-the-art neural networks can be used in automatic test equipment for iterative diagnosis of electronic circuit board malfunctions.     

Neural network applications in business: A review and analysis of the literature (1988–1995)

A survey of journal articles on neural network business applications published between 1988 and 1995 indicates that an increasing amount of neural network research is being conducted for a diverse range of business activities. The classification of literature by (1) year of publication, (2) application area, (3) problem domain, (4) decision process phase, (5) level of management, (6) level of task interdependence, (7) means of development, (8) corporate/academic interaction in development, (9) technology integration, (10) comparative study, (11) major contribution, and (12) journal provides some insights into the trends in neural networks research. The implications for neural networks developers/researchers and suggestions on future research areas are discussed.     

Neural network modelling of continuous microbial cultivation accounting for the memory effects

Three approaches to the problem of Neural Network (NN) modelling of chemostat microbial culture accounting for the memory effects are considered and, based on the results they are compared. The first approach uses feedforward NNs with time delay feedback connections from and to the output neurons, for the entire process modelling. The second and third approach relay on Hybrid NN modelling. The second one applies feedforward NNs with time delayed inputs for the specific growth rate approximation within the framework of the classical unstructured model. In this case the specific consumption rate is assumed to be proportional to the specific growth rate. The yield factor is assumed to be constant or polynomial function of the substrate concentration. The third approach is also based on a classical unstructured model, but different feedforward NNs with delay elements for both specific growth rate and specific consumption rate approximation are adopted. On the example of the growth of a strain Saccharomyces cerevisiae on a glucose limited medium different NN topologies are studied and a suitable model is figured out.     

Minimum entropy control of nonlinear ARMA systems over a communication network

In this paper, the entropy concept has been utilized to characterize the uncertainty of the tracking error for nonlinear ARMA stochastic systems over a communication network, where time delays in the communication channels are of random nature. A recursive optimization solution has been developed. In addition, an alternative algorithm is also proposed based on the probability density function of the tracking error, which is estimated by a neural network. Finally, a simulation example is given to illustrate the efficiency and feasibility of the proposed approach.     

Neural network based detection of local textile defects

A new approach for the segmentation of local textile defects using feed-forward neural network is presented. Every fabric defect alters the gray-level arrangement of neighboring pixels, and this change is used to segment the defects. The feature vector for every pixel is extracted from the gray-level arrangement of its neighboring pixels. Principal component analysis using singular value decomposition is used to reduce the dimension of feature vectors. Experimental results using this approach illustrate a high degree of robustness for the detection of a variety of fabric defects. The acceptance of a visual inspection system depends on economical aspects as well. Therefore, a new low-cost solution for the fast web inspection using linear neural network is also presented. The experimental results obtained from the real fabric defects, for the two approaches proposed in this paper, have confirmed their usefulness.     

A neural network solution for fixed-final time optimal control of nonlinear systems

In this paper, fixed-final time optimal control laws using neural networks and HJB equations for general affine in the input nonlinear systems are proposed. The method utilizes Kronecker matrix methods along with neural network approximation over a compact set to solve a time-varying HJB equation. The result is a neural network feedback controller that has time-varying coefficients found by a priori offline tuning. Convergence results are shown. The results of this paper are demonstrated on an example.     

Neural network controller for a multivariable model of submarine dynamics

Recently, there have been many attempts to use neural networks as a feedback controller. However, most of the reported cases seek to control Single-Input Single-Output (SISO) systems using some sort of adaptive strategy. In this paper, we demonstrate that neural networks can be used for the control of complex multivariable, rather than simply SISO, systems. A modified direct control scheme using a neural network architecture is used with backpropagation as the adaptive algorithm. The proposed algorithm is designed for Multi-Input Multi-Output (MIMO) systems, and is similar to that proposed by Saerens and Soquet [1] and Goldenthal and Farrell [2] for (SISO) systems, and differs only in the form of the gradient approximation. As an example of the application of this approach, we investigate the control of the dynamics of a submarine vehicle with four inputs and four outputs, in which the differential stern, bow and rudder control surfaces are dynamically coordinated to cause the submarine to follow commanded changes in roll, yaw rate, depth rate and pitch attitude. Results obtained using this scheme are compared with those obtained using optimal linear quadratic control.     

Neural network model for rapid forecasting of freeway link travel time

Estimation of freeway travel time with reasonable accuracy is essential for successful implementation of an advanced traveler information system (ATIS) for use in an intelligent transportation system (ITS). An ATIS consists of a route guiding system that recommends the most suitable route based on the traveler's requirements using the information gathered from various sources such as loop detectors and probe vehicles. This information can be disseminated through mass media or on on-board satellite-based navigational system. Based on the estimated travel times for various routes, the traveler can make a route choice. In this article, a neural network model is presented for forecasting the freeway link travel time using the counter propagation neural (CPN) network. The performance of the model is compared with a recently reported freeway link travel forecasting model using the backpropagation (BP) neural network algorithm. It is shown that the new model based on the CPN network, and the learning coefficients proposed by Adeli and Park, is nearly two orders of magnitude faster than the BP network. As such, the proposed freeway link travel-forecasting model is particularly suitable for real-time advanced travel information and management systems.     

Neural network-based robust adaptive control of nonlinear systems with unmodeled dynamics

A neural network-based robust adaptive control design scheme is developed for a class of nonlinear systems represented by input–output models with an unknown nonlinear function and unmodeled dynamics. By on-line approximating the unknown nonlinear functions and unmodeled dynamics by radial basis function (RBF) networks, the proposed approach does not require the unknown parameters to satisfy the linear dependence condition. It is proved that with the proposed control law, the closed-loop system is stable and the tracking error converges to zero in the presence of unmodeled dynamics and unknown nonlinearity. A simulation example is presented to demonstrate the method.     

纯反馈非线性离散系统的自适应神经网络控制

针对一类未知的纯反馈非线性离散系统,提出了基于反步法设计的自适应神经网络控制方法.为避免反步法设计中可能出现的因果矛盾问题,首先将系统进行等价变换,然后利用隐函数定理证实了理想虚拟控制输入和实际控制输入的存在性.利用高阶神经网络估计这些控制量,并基于反步法设计自适应神经网络控制系统,证明了闭环系统半全局一致最终有界.仿真结果验证了所提出方法的有效性.     

Neural network modeling of the cellgap process for liquid crystal display fabricated on plastic substrates

In this paper, a neural network model is presented to characterize the thickness and the uniformity of the cellgap process for flexible liquid crystal display (LCD). Input factors are explored via a D-optimal design with 15 runs and used as training data in the neural network. In order to verify the fitness of the model, three more runs are added as test data. Latin hypercube sampling and error back-propagation algorithm are used to build the model. Latin hypercube sampling is used to generate initial weights and biases of the network. The thickness of cellgap is measured at five points: one at the center and four at the edges. The average thickness is used as cellgap thickness, and the uniformity is obtained by comparing the thickness at the center and edge points.     

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.     

Improving neural network models of physical systems through dimensional analysis

The paper presents a technique for generating concise neural network models of physical systems. The neural network models are generated through a two-stage process. The first stage uses information embedded in the dimensions or units in which the data is represented. Dimensional analysis techniques are used initially to make this information explicit, and a limited search in the neural network architecture space is then conducted to determine dimensionless representations of variables/parameters that perform well for a given model complexity. The second stage uses information available in the numerical values of the data to search for high-level dimensionless variables/parameters, generated from simple combinations of dimensionless quantities generated in the first stage and which result in concise neural network models with improved performance characteristics. The search for these high-level dimensionless variables/parameters is conducted in an enhanced representation space using functional link networks with flat or near flat architectures. The use and effectiveness of the technique is demonstrated for three applications. The first is the design and analysis of reinforced concrete beams, which is representative of the class of problems associated with the design and analysis of composites. The second is the classical elastica problem, for predicting non-linear post-buckled behaviour of columns and the third, the analysis of a bent bar under a specified combination of loads.