基于PLS和GAs的径基函数网络构造策略

鉴于传统径基函数网络(radial basis function network,简称RBFN)构造策略的不足,提出了基于偏最小二乘法(partial least squares,简称PLS)和遗传算法(genetic algorithms,简称GAs)的RBFN构造策略和一种更有效的径基宽度取值方法.在这个集成构造策略中,PLS克服了K-Means算法求取径基易陷入局部最优的弊病,并使合成径基比由正交算法获取的径基更具代表性;而所提出的径基宽度取值方法和GAs则为网络性能和结构的实质性改善与优化提供了保障.实验证实了基于PLS和GAs的RBFN构造策略及所提出的径基宽度取值方法的优越性、可靠性和有效性.

洛阳PTA装置基于径基函数网络的4-CBA软测量

采用一种具有强非线性表达能力的径基函数网络方法建立洛阳PTA装置4-CBA含量软测量模型。在实际应用中,4-CBA含量软测量模型具有良好的预测精度,相对误差仅为4.3%。基于该软测量模型系统分析主要工艺操作参数对TA产品中4-CBA含量的影响,为生产操作条件的优化提供指导。

基于径向基函数模型的工程工料消耗的估算方法

将径向基函数网络方法应用于工程工料消耗估算 ,讨论了网络结构的设计、学习算法等问题 ;建立了基于径向基函数网络的工程工料消耗估算模型 ,计算实例表明 ,借助该模型可实现工程工料消耗的快速估算 .

前向神经网络设计问题的回顾与探索

本文评述了近十几年来国内外对前向神经网络设计问题的研究情况，在分析各种已有设计方法优缺点的基础上，提出另一种新的解决前向神经网络设计问题的方法，并给出几个非常典型的设计（模拟）例子，以说明本文所提出方法的有效性和潜力。

RBF-based cluster-head selection for wireless sensor networks

The radial basis function （RBF）, a kind of neural networks algorithm, is adopted to select clusterheads. It has many advantages such as simple parallel distributed computation, distributed storage, and fast learning. Four factors related to a node becoming a cluster-head are drawn by analysis, which are energy （ energy available in each node）, number （the number of neighboring nodes）, centrality （ a value to classify the nodes based on the proximity how central the node is to the cluster）, and location （the distance between the base station and the node）. The factors are as input variables of neural networks and the output variable is suitability that is the degree of a node becoming a cluster head. A group of cluster-heads are selected according to the size of network. Then the base station broadcasts a message containing the list of cluster-heads＇ IDs to all nodes. After that, each cluster-head announces its new status to all its neighbors and sets up a new cluster. If a node around it receives the message, it registers itself to be a member of the cluster. After identifying all the members, the cluster-head manages them and carries out data aggregation in each cluster. Thus data flowing in the network decreases and energy consumption of nodes decreases accordingly. Experimental results show that, compared with other algorithms, the proposed algorithm can significantly increase the lifetime of the sensor network.

Application of Radial Basis Function Network in Sensor Failure Detection

Aim To detect sensor failure in control system using a single sensor signal. Methods A neural predictor was designed based on a radial basis function network(RBFN), and the neural predictor learned the sensor signal on line with a hybrid algorithm composed of n means clustering and Kalman filter and then gave the estimation of the sensor signal at the next step. If the difference between the estimation and the actural values of the sensor signal exceeded a threshold, the sensor could be declared to have a failure. The choice of the failure detection threshold depends on the noise variance and the possible prediction error of neural predictor. Results and Conclusion\ The computer simulation results show the proposed method can detect sensor failure correctly for a gyro in an automotive engine.

Generalization Capabilities of Feedforward Neural Networks for Pattern Recognition

This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.

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.

Improving Land Resource Evaluation Using Fuzzy Neural Network Ensembles

Land evaluation factors often contain continuous-, discrete- and nominal-valued attributes. In traditional land evaluation, these different attributes are usually graded into categorical indexes by land resource experts, and the evaluation results rely heavily on experts＇ experiences. In order to overcome the shortcoming, we presented a fuzzy neural network ensemble method that did not require grading the evaluation factors into categorical indexes and could evaluate land resources by using the three kinds of attribute values directly. A fuzzy back propagation neural network （BPNN）, a fuzzy radial basis function neural network （RBFNN）, a fuzzy BPNN ensemble, and a fuzzy RBFNN ensemble were used to evaluate the land resources in Guangdong Province. The evaluation results by using the fuzzy BPNN ensemble and the fuzzy RBFNN ensemble were much better than those by using the single fuzzy BPNN and the single fuzzy RBFNN, and the error rate of the single fuzzy RBFNN or fuzzy RBFNN ensemble was lower than that of the single fuzzy BPNN or fuzzy BPNN ensemble, respectively. By using the fuzzy neural network ensembles, the validity of land resource evaluation was improved and reliance on land evaluators＇ experiences was considerably reduced.

A New Strategy of Integrated Control and On-line Optimization on High-purity Distillation Process

For high-purity distillation processes,it is difficult to achieve a good direct product quality control using traditional proportional-integral-differential(PID)control or multivariable predictive control technique due to some difficulties,such as long response time,many un-measurable disturbances,and the reliability and precision issues of product quality soft-sensors.In this paper,based on the first principle analysis and dynamic simulation of a distillation process,a new predictive control scheme is proposed by using the split ratio of distillate flow rate to that of bottoms as an essential controlled variable.Correspondingly,a new strategy with integrated control and on-line optimization is developed,which consists of model predictive control of the split ratio,surrogate model based on radial basis function neural network for optimization,and modified differential evolution optimization algorithm. With the strategy,the process achieves its steady state quickly,so more profit can be obtained.The proposed strategy has been successfully applied to a gas separation plant for more than three years,which shows that the strategy is feasible and effective.

Splicing System Based Genetic Algorithms for Developing RBF Net-works Models

A splicing system based genetic algorithm is proposed to optimize dynamical radial basis function(RBF)neural network,which is used to extract valuable process information from input output data.The novel RBF net-work training technique includes the network structure into the set of function centers by compromising between the conflicting requirements of reducing prediction error and simultaneously decreasing model complexity.The ef-fectiveness of the proposed method is illustrated through the development of dynamic models as a benchmark discrete example and a continuous stirred tank reactor by comparing with several different RBF network training methods.

A fault diagnosis method of reciprocating compressor based on sensitive feature evaluation and artificial neural network

A method combining information entropy and radial basis function network is proposed for fault automatic diagnosis of reciprocating compressors.Aiming at the current situation that the accuracy rate of reciprocating compressor fault diagnosis which depends on manual work in engineering is very low,we apply information entropy evaluation to select the sensitive features and make clear the corresponding relationship of characteristic parameters and failures.This method could reduce the feature dimension.Then,a complete fault diagnosis architecture has been built combining with radial basis function network which has the fast and efficient characteristics.According to the test results using experimental and engineering data,it is observed that the proposed fault diagnosis method improves the accuracy of fault automatic diagnosis effectively and it could improve the practicability of the monitoring system.

Estimation of vegetation biophysical parameters by remote sensing using radial basis function neural network

Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD, mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980’s. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used. Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.

Intelligent prediction on air intake flow of spark ignition engine by a chaos radial basis function neural network

To ensure the control of the precision of air-fuel ratio(AFR)of port fuel injection(PFI)spark ignition(SI)engines,a chaos radial basis function(RBF)neural network is used to predict the air intake flow of the engine.The data of air intake flow is proved to be multidimensionally nonlinear and chaotic.The RBF neural network is used to train the reconstructed phase space of the data.The chaos algorithm is employed to optimize the weights of output layer connection and the radial basis center of Gaussian function in hidden layer.The simulation results obtained from Matlab/Simulink illustrate that the model has higher accuracy compared to the conventional RBF model.The mean absolute error and the mean relative error of the chaos RBF model can reach 0.0017 and 0.48,respectively.

Comparison Between Radial Basis Function Neural Network and Regression Model for Estimation of Rice Biophysical Parameters Using Remote Sensing

The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. Hyperspectral reflectance （350 to 2500 nm） data were recorded at two different rice sites in two experiment fields with two cultivars, three nitrogen treatments and one plant density （45 plants m^-2）. Stepwise multivariable regression model （SMR） and RBF were used to compare their predictability for the leaf area index （LAI） and green leaf chlorophyll density （GLCD） of rice based on reflectance （R） and its three different transformations, the first derivative reflectance （D1）, the second derivative reflectance （D2） and the log-transformed reflectance （LOG）. GRNN based on D1 was the best model for the prediction of rice LAI and CLCD. The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed. Owing to its strong capacity for nonlinear mapping and good robustness, GRNN could maximize the sensitivity to chlorophyll content using D1. It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.

IMMUNE RBF NETWORK AND ITS APPLICATION IN THE MODULATION-STYLE RECOGNITION OF RADAR SIGNALS

Based on Immune Programming(IP), a novel Radial Basis Function (RBF) networkdesigning method is proposed. Through extracting the preliminary knowledge about the widthof the basis function as the vaccine to form the immune operator, the algorithm reduces thesearching space of canonical algorithm and improves the convergence speed. The application ofthe RBF network trained with the algorithm in the modulation-style recognition of radar signalsdemonstrates that the network has a fast convergence speed with good performances.

Soft measurement model of ring's dimensions for vertical hot ring rolling process using neural networks optimized by genetic algorithm

Vertical hot ring rolling(VHRR) process has the characteristics of nonlinearity,time-variation and being susceptible to disturbance.Furthermore,the ring's growth is quite fast within a short time,and the rolled ring's position is asymmetrical.All of these cause that the ring's dimensions cannot be measured directly.Through analyzing the relationships among the dimensions of ring blanks,the positions of rolls and the ring's inner and outer diameter,the soft measurement model of ring's dimensions is established based on the radial basis function neural network(RBFNN).A mass of data samples are obtained from VHRR finite element(FE) simulations to train and test the soft measurement NN model,and the model's structure parameters are deduced and optimized by genetic algorithm(GA).Finally,the soft measurement system of ring's dimensions is established and validated by the VHRR experiments.The ring's dimensions were measured artificially and calculated by the soft measurement NN model.The results show that the calculation values of GA-RBFNN model are close to the artificial measurement data.In addition,the calculation accuracy of GA-RBFNN model is higher than that of RBFNN model.The research results suggest that the soft measurement NN model has high precision and flexibility.The research can provide practical methods and theoretical guidance for the accurate measurement of VHRR process.

Catalytic Cracking and PSO-RBF Neural Network Model of FCC Cycle Oil

Catalytic cracking experiments of FCC cycle oil were carried out in a fixed fluidized bed reactor. Effects of reac- tion conditions, such as temperature, catalyst to oil ratio and weight hourly space velocity, were investigated. Hydrocarbon composition of gasoline was analyzed by gas chromatograph. Experimental results showed that conversion of cycle oil was low on account of its poor crackability performance, and the effect of reaction conditions on gasoline yield was obvi- ous. The paraffin content was very high in gasoline. Based on the experimental yields under different reaction conditions, a model for prediction of gasoline and diesel yields was established by radial basis function neural network （RBFNN）. In the model, the product yield was viewed as function of reaction conditions. Particle swarm optimization （PSO） algorithm with global search capability was used to obtain optimal conditions for a highest yield of light oil. The results showed that the yield of gasoline and diesel predicted by RBF neural network agreed well with the experimental values. The optimized reac- tion conditions were obtained at a reaction temperature of around 520 ~C, a catalyst to oil ratio of 7.4 and a space velocity of 8 h~. The predicted total yield of gasoline and diesel reached 42.2% under optimized conditions.

Fault Detection and Diagnosis of a Gearbox in Marine Propulsion Systems Using Bispectrum Analysis and Artificial Neural Networks

A marine propulsion system is a very complicated system composed of many mechanical components.As a result,the vibration signal of a gearbox in the system is strongly coupled with the vibration signatures of other components including a diesel engine and main shaft.It is therefore imperative to assess the coupling effect on diagnostic reliability in the process of gear fault diagnosis.For this reason,a fault detection and diagnosis method based on bispectrum analysis and artificial neural networks (ANNs) was proposed for the gearbox with consideration given to the impact of the other components in marine propulsion systems.To monitor the gear conditions,the bispectrum analysis was first employed to detect gear faults.The amplitude-frequency plots containing gear characteristic signals were then attained based on the bispectrum technique,which could be regarded as an index actualizing forepart gear faults diagnosis.Both the back propagation neural network (BPNN) and the radial-basis function neural network (RBFNN) were applied to identify the states of the gearbox.The numeric and experimental test results show the bispectral patterns of varying gear fault severities are different so that distinct fault features of the vibrant signal of a marine gearbox can be extracted effectively using the bispectrum,and the ANN classification method has achieved high detection accuracy.Hence,the proposed diagnostic techniques have the capability of diagnosing marine gear faults in the earlier phases,and thus have application importance.

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.