Calculation method of ship collision force on bridge using artificial neural network

Ship collision on bridge is a dynamic process featured by high nonlinearity and instantaneity. Calculating ship-bridge collision force typically involves either the use of design-specification-stipulated equivalent static load, or the use of finite element method （FEM） which is more time-consuming and requires supercomputing resources. In this paper, we proposed an alternative approach that combines FEM with artificial neural network （ANN）. The radial basis function neural network （RBFNN） employed for calculating the impact force in consideration of ship-bridge collision mechanics. With ship velocity and mass as the input vectors and ship collision force as the output vector, the neural networks for different network parameters are trained by the learning samples obtained from finite element simulation results. The error analyses of the learning and testing samples show that the proposed RBFNN is accurate enough to calculate ship-bridge collision force. The input-output relationship obtained by the RBFNN is essentially consistent with the typical empirical formulae. Finally, a special toolbox is developed for calculation effi- ciency in application using MATLAB software.     

两自由度闭链机器人的神经网络自适应控制

A closed-chain robot has several advantages over an open-chain robot, such as high mechanical rigidity, high payload, high precision. Accurate trajectory control of a robot is essential in practical use. This paper presents an adaptive proportional integral differential (PID) control algorithm based on radial basis function (RBF) neural network for trajectory tracking of a two-degree-of-freedom (2-DOF) closed-chain robot. In this scheme, an RBF neural network is used to approximate the unknown nonlinear dynamics of the robot, at the same time, the PID parameters can be adjusted online and the high precision can be obtained. Simulation results show that the control algorithm accurately tracks a 2-DOF closed-chain robot trajectories. The results also indicate that the system robustness and tracking performance are superior to the classic PID method.     

Parameters optimization and nonlinearity analysis of grating eddy current displacement sensor using neural network and genetic algorithm

A grating eddy current displacement sensor （GECDS） can be used in a watertight electronic transducer to realize long range displacement or position measurement with high accuracy in difficult industry conditions. The parameters optimization of the sensor is essential for economic and efficient production. This paper proposes a method to combine an artificial neural network （ANN） and a genetic algorithm （GA） for the sensor parameters optimization. A neural network model is developed to map the complex relationship between design parameters and the nonlinearity error of the GECDS, and then a GA is used in the optimization process to determine the design parameter values, resulting in a desired minimal nonlinearity error of about 0.11%. The calculated nonlinearity error is 0.25%. These results show that the proposed method performs well for the parameters optimization of the GECDS.     

基于人工神经网络的等离子熔积层形貌试验研究

1IntroductionPlasma deposition manufacturing(PDM)is a newlydeveloped direct metal fabrication process based onplasma transferred arc surfacing[1],as shown in Fig.1.Unlike most existing rapid prototyping techn-ologies,this technique is characterized by sup…     

Nonlinear modelling of a SOFC stack by improved neural networks identification

The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far,most existing models are based on conversion laws,which are too complicated to be applied to design a control system. To facilitate a valid control strategy design,this paper tries to avoid the internal complexities and presents a modelling study of SOFC per-formance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of mod-elling,the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations,whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore,it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model.     

Rice yield estimation using remote sensing and simulation model

Remote sensing techniques have the potential to provide information on agricultural crops quantitatively, instantaneously and above all nondestructively over large areas. Crop simulation models describe the relationship between physiological processes in plants and environmental growing conditions. The integration between remote sensing data and crop growth simulation model is an important trend for yield estimation and prediction, since remote sensing can provide information on the actual status of the agricultural crop. In this study, a new model (Rice-SRS) was developed based mainly on ORYZA1 model and modified to accept remote sensing data as input from different sources. The model can accept three kinds of NDVI data: NOAA AVHRR(LAC)-NDVI, NOAA AVHRR(GAC)-NDVI and radiometric measurements-NDVI. The integration between NOAA AVHRR (LAC) data and simulation model as applied to Rice-SRS resulted in accurate estimates for rice yield in the Shaoxing area, reduced the estimating error to 1.027%, 0.794% and (−0.787%) for early, single, and late season respectively. Utilizing NDVI data derived from NOAA AVHRR (GAC) as input in Rice-SRS can yield good estimation for rice yield with the average error (−7.43%). Testing the new model for radiometric measurements showed that the average estimation error for 10 varieties under early rice conditions was less than 1%. Project supported by the National Defense Scientific and Technological Committee of China(No. Y97#14-6-2)     

A maximum power point tracker for photovoltaic energy systems based on fuzzy neural networks

To extract the maximum power from a photovoltaic （PV） energy system, the real-time maximum power point （MPP） of the PV array must be tracked closely. The non-linear and time-variant characteristics of the PV array and the non-linear and non-minimum phase characteristics of a boost converter make it difficult to track the MPP for traditional control strategies. We propose a fuzzy neural network controller （FNNC）, which combines the reasoning capability of fuzzy logical systems and the learning capability of neural networks, to track the MPP. With a derived learning algorithm, the parameters of the FNNC are updated adaptively. A gradient estimator based on a radial basis function neural network is developed to provide the reference information to the FNNC. Simulation results show that the proposed control algorithm provides much better tracking performance compared with the filzzy logic control algorithm.     

Application of principal component-radial basis function neural networks (PC-RBFNN) for the detection of water-adulterated bayberry juice by near-infrared spectroscopy

Near-infrared (NIR) spectroscopy combined with chemometrics techniques was used to classify the pure bayberry juice and the one adulterated with 10% (w/w) and 20% (w/w) water. Principal component analysis (PCA) was applied to reduce the dimensions of spectral data, give information regarding a potential capability of separation of objects, and provide principal component (PC) scores for radial basis function neural networks (RBFNN). RBFNN was used to detect bayberry juice adulterant. Multiplicative scatter correction (MSC) and standard normal variate (SNV) transformation were used to preprocess spectra. The results demonstrate that PC-RBFNN with optimum parameters can separate pure bayberry juice samples from water-adulterated bayberry at a recognition rate of 97.62%, but cannot clearly detect water levels in the adulterated bayberry juice. We conclude that NIR technology can be successfully applied to detect water-adulterated bayberry juice.     

An artificial neural network approach for prediction of long-term strength properties of steel fiber reinforced concrete containing fly ash

In this study, an artificial neural network （ANN） model for studying the strength properties of steel fiber reinforced concrete （SFRC） containing fly ash was devised. The mixtures were prepared with 0 wt%, 15 wt%, and 30 wt% of fly ash, at 0 vol.%, 0.5 vol.%, 1.0 vol.% and 1.5 vol.% of fiber, respectively. After being cured under the standard conditions for 7, 28, 90 and 365 d, the specimens of each mixture were tested to determine the corresponding compressive and flexural strengths. The pa- rameters such as the amounts of cement, fly ash replacement, sand, gravel, steel fiber, and the age of samples were selected as input variables, while the compressive and flexural strengths of the concrete were chosen as the output variables. The back propagation learning algorithm with three different variants, namely the Levenberg-Marquardt （LM）, scaled conjugate gradient （SCG） and Fletcher-Powell conjugate gradient （CGF） algorithms were used in the network so that the best approach can be found. The results obtained from the model and the experiments were compared, and it was found that the suitable algorithm is the LM algorithm. Furthermore, the analysis of variance （ANOVA） method was used to determine how importantly the experimental parameters affect the strength of these mixtures.     

基于人工神经网络的时间序列交通事故预测

分析了人工神经网络和时间序列的优越性和适用性，提出了基于神经网络基础之上的时间序列预测方法，从而实现了从线性预测到非线性预测的转变。     

Application of BP NN and RBF NN in Modeling Activated Sludge System

Based on the operation data from a certain wastewater treatment plant(WWTP) in northeast China,the models of back propagation neural network ( BP NN ) and radial basis function neural network ( RBF NN ) have been designed respectively and the ability of convergence and generalization has been analyzed separately.As for BP NN, the effects of numbers of layers and nodes have been studied ; as for RBF NN, the influences of the number of nodes and the RBF‘s width have been studied. It is concluded that BP NN has converged much slowly in comparison with RBF NN. The conclusion that the RBF NN is suitable for modeling activated sludge system has been drawn. An automatically optimum design program for RBF NN has been developed, through which the RBF NN model of traditional activated sludge system has been established.     

Study of CNG/diesel dual fuel engine's emissions by means of RBF neural network

Great efforts have been made to resolve the serious environmental pollution and inevitable declining of energy resources. A review of Chinese fuel reserves and engine technology showed that compressed natural gas (CNG)/diesel dual fuel engine (DFE) was one of the best solutions for the above problems at present. In order to study and improve the emission performance of CNG/diesel DFE, an emission model for DFE based on radial basis function (RBF) neural network was developed which was a black-box input-output training data model not require priori knowledge. The RBF centers and the connected weights could be selected automatically according to the distribution of the training data in input-output space and the given approximating error. Studies showed that the predicted results accorded well with the experimental data over a large range of operating conditions from low load to high load. The developed emissions model based on the RBF neural network could be used to successfully predict and optimize the emissions performance of DFE. And the effect of the DFE main performance parameters, such as rotation speed, load, pilot quantity and injection timing, were also predicted by means of this model. In resume, an emission prediction model for CNG/diesel DFE based on RBF neural network was built for analyzing the effect of the main performance parameters on the CO, NOx emissions of DFE. The predicted results agreed quite well with the traditional emissions model, which indicated that the model had certain application value, although it still has some limitations, because of its high dependence on the quantity of the experimental sample data.     

基于倒立摆系统前馈型神经网络实验的开发

介绍一个基于MATLAB/SIMULINK和直线一级倒立摆系统的前馈型人工神经网络的实验方案。设计了一级倒立摆系统BP神经网络控制器,并完成了仿真和实物控制实验。实验结果有利于对前馈型人工神经网络的本质认识。     

Maximum power point tracking of a photovoltaic energy system using neural fuzzy techniques

In order to improve the output efficiency of a photovoltaic (PV) energy system, the real-time maximum power point (MPP) of the PV array should be tracked closely. The non-linear and time-variant characteristics of the photovoltaic array and the non-linear and non-minimum phase characteristics of a boost converter make it difficult to track the MPP as in traditional control strategies. A neural fuzzy controller (NFC) in conjunction with the reasoning capability of fuzzy logical systems and the learning capability of neural networks is proposed to track the MPP in this paper. A gradient estimator based on a radial basis function neural network is developed to provide the reference information to the NFC. With a derived learning algorithm, the parameters of the NFC are updated adaptively. Experimental results show that, compared with the fuzzy logic control algorithm, the proposed control algorithm provides much better tracking performance.     

Rectification of magnetic force tracker using neural network inaugmented reality system

1IntroductionAugmented reality(AR)is a newtechnique based onvirtual reality,which has attracted much attention inrecent years.AR is used to describe a system thatenhances the real world by superi mposing computer-generated information on top of it.It supp…     

增强现实系统中基于神经网络的磁力跟踪器校正

Nonlinear errors always exist in data obtained from tracker in augmented reality （AR）, which badly influence the effect of AR. This paper proposes to rectify the errors using BP neural network. As BP neural network is prone to getting into local extrema and convergence is slow, genetic algorithm is employed to optimize the initial weights and threshold of neural network. This paper discusses how to set the crucial parameters in the algorithm. Experimental results show that the method ensures that the neural network achieves global convergence quickly and correctly. Tracking precision of AR system is improved after the tracker is rectified, and the third dimension of AR system is enhanced.     

Feature Mapping and Recuperation by Using Elliptical Basis Function Networks for Robust Speaker Verification

The performance of speaker verification systems is often compromised under real-world environments.For example,variations in handset characteristics could cause severe performance degradation.This paper presents a novel method to overcome this problem by using a non-linear handset mapper.Under this method,a mapper is constructed by training an elliptical basis function network using distorted speech features as inputs and the corresponding clean features as the desired outputs.During feature recuperation,clean features are recovered by feeding the distorted features to the feature mapper.The recovered features are then presented to a speaker model as if they were derived from clean speech.Experimental evaluation based on 258 speakers of the TIMIT and NTIMIT corpuses suggest that the feature mappers improve the verification performance remarkably.     

Application of least squares vector machines in modelling water vapor and carbon dioxide fluxes over a cropland

INTRODUCTION Modelling the variation in surface-atmosphericexchange of water vapor and carbon dioxide fluxesand how they are influenced by a complex combina-tion of environment variables and plant physiology iscrucial for assessing the annual water and carbonbudget for cropland. Biophysical or process-basedmodels such as soil-vegetation-atmosphere transfer(SVAT) (Franks et al., 1997; Franks and Beven, 1999Mo and Beven, 2004), Simultaneous Heat and Water(SHAW) (Flerchinger et al., 1…     

基于RBF神经网络辨识的直接甲醇燃料电池电堆非成性建模与自适应模糊控制

1 Introduction Direct methanol fuel cell ( DMFC) is desirable toserve as the power systemfor portable devices such ascellular phones , portable computers ,etc. due to thetheoretically high energy density and the liquid fuelused that can be stored and tran…     

Neural network and principal component regression in non-destructive soluble solids content assessment: a comparison

Visible and near infrared spectroscopy is a non-destructive, green, and rapid technology that can be utilized to estimate the components of interest without conditioning it, as compared with classical analytical methods. The objective of this paper is to compare the performance of artificial neural network (ANN) (a nonlinear model) and principal component regression (PCR) (a linear model) based on visible and shortwave near infrared (VIS-SWNIR) (400–1000 nm) spectra in the non-destructive soluble solids content measurement of an apple. First, we used multiplicative scattering correction to pre-process the spectral data. Second, PCR was applied to estimate the optimal number of input variables. Third, the input variables with an optimal amount were used as the inputs of both multiple linear regression and ANN models. The initial weights and the number of hidden neurons were adjusted to optimize the performance of ANN. Findings suggest that the predictive performance of ANN with two hidden neurons outperforms that of PCR.