神经网络-模糊推理数据融合技术应用研究

近几年来,神经网络与模糊推理技术相辅相成构成了比较完备的智能信息系统框架.本文以神经网络-模糊推理数据融合技术为主线,重点介绍模糊神经多传感器数据融合系统的建模与分析;针对C3I数据融合系统中,传感器受外界复杂环境的影响使得其探测到的传感器信息具有不确定性,通过将模糊技术、神经网络理论与 Petri网相结合,讨论了模糊神经多传感器数据融合系统的建模方法,这对于提高系统学习能力和对外界环境的自适应能力具有实际意义.     

机器人系统中操作环境动力学模型研究

研究了机器人操作环境的动力学模型,提出了一种基于径向基函数(RBF)神经网络的机器人系统中环境非线性动力学模型新的建立方法,阐述了其建模机理和算法.结果表明,采用RBF神经网络对机器人系统中的操作环境建模比用BP神经网络有更高的精度,其网络训练速度也大大快于BP神经网络.     

电液伺服系统的神经网络建模方法研究

针对电液伺服系统固有的流量-压力特性等非线性因素使得采用传递函数等传统方法难以获得电液伺服系统的精确模型的问题,详细研究了电液伺服系统的神经网络建模方法.研究了两种最常见的神经网络,即多层感知器神经网络和径向基函数神经网络,采用5种典型学习算法构造了3种多层感知器神经网络和2种径向基函数神经网络,并结合自动定深电液伺服系统的工程实例,详细分析了这5种神经网络在电液伺服系统中的建模性能.研究结果表明,采用正交最小二乘算法的径向基函数神经网络最适合电液伺服系统的建模.     

基于先进信息处理技术的软测量应用探讨

软测量技术是通过间接方法实现对不易直接测量的过程变量进行估计.介绍了软测量技术的研究及应用现状,分析了软测量机理建模和非机理建模及其在不同场合的应用,探讨了软测量未来的发展方向.举例说明了软测量技术在不同领域的应用.融合神经网络、统计学习理论等多种先进信息处理技术是解决软测量中的在线自校正和实时性问题等难题的有效方法.     

基于BP网络的光纤陀螺刻度因子建模研究

针对光纤陀螺(FOG)随温度呈非线性变化的特性,提出了采用BP神经网络对刻度因子的温度误差建模的方法,以减小光纤陀螺输出误差;用BP网络对其建模的结果和传统的建模结果进行了比较,结果表明采用BP神经网络对刻度因子的建模是非常有效的.     

基于神经网络的复杂系统杂交建模研究

利用先验知识和神经网络黑箱建模相结合,对一类复杂滞后非线性系统进行了杂交建模研究.先验知识建模确定滞后系统模型的形式及主体部分,神经网络估计滞后系统恢复力的未确定部分,所建模型不仅能够进行系统响应预测分析,而且能够获得系统的主体结构特征,对结构设计修改具有指导作用.     

神经网络技术在供应链管理中的应用

神经网络技术已被成功地应用在许多商业领域,包括供应链管理。本文首次系统地总结了神经网络技术在供应链管理中的应用。首先介绍了神经网络的本质和特性,接着详细介绍了神经网络技术在供应链管理中的５个方面的应用：优化、预测、决策支持、建模和仿真和全局化管理;然后运用ＢＰ型神经网络对上海市场自行车的需求量进行了预测;最后指出阻碍神经网络技术发展的两个障碍以及神经网络技术发展的方向。     

基于RBF神经网络的诺西肽发酵过程菌体质量浓度软测量

针对诺西肽发酵过程中菌体质量浓度的估计问题,提出了一种基于RBF神经网络的软测量建模方法.在诺西肽发酵过程非结构模型的基础上,根据隐函数存在定理确定出辅助变量,从而使其选择有严格的理论依据;根据每批样本数据对被预测对象的预估能力,自适应地为各个批次的训练样本分配权值,并进而实施加权RBF神经网络建模.实际应用表明,所提出的软测量建模方法是有效的.     

光纤陀螺刻度因子的建模方法

针对低精度光纤陀螺(FOG)刻度因子线性度较差的问题,提出了采用径向基函数(RBF)神经网络对刻度因子进行建模的方法,以减小光纤陀螺输出误差。通过测量数据对 RBF 神经网络进行训练,获得神经网络参数,根据神经网络结构和参数可以得到非线性刻度因子的解析表达式,将其作为刻度因子的模型,来提高 FOG 的精度。同时将 RBF 神经网络对刻度因子进行建模的结果与传统的建模结果进行了比较,验证了采用 RBF 神经网络对低精度刻度因子建模是非常有效的。     

于GA-BP模糊神经网络的商业银行信用风险评估

研究了商业银行信用风险评估的现状,针对单独应用BP神经网络评估信用风险时存在的缺陷,提出了基于遗传算法优化模糊BP神经网络的信用风险评估新模型.通过遗传算法训练模糊BP神经网络,克服网络建模中产生的局部极小的缺点,提高了风险评估的准确性.最后,利用Matlab软件对样本数据进行训练和测试,仿真结果表明所构造的评估模型预测误差非常小.     

Prediction of Drug Content and Hardness of Intact Tablets Using Artificial Neural Network and Near-Infrared Spectroscopy

The purpose of this study was to predict drug content and hardness of intact tablets using artificial neural networks (ANN) and near-infrared spectroscopy (NIRS). Tablets for the drug content study were compressed from mixtures of Avicel® PH-101, 0.5% magnesium stearate, and varying concentrations (0%, 1%, 2%, 5%, 10%, 20%, and 40% w/w) of theophylline. Tablets for the hardness study were compressed from mixtures of Avicel PH-101 and 0.5% magnesium stearate at varying compression forces ranging from 0.4 to 1 ton. An Intact Analyzer™ was used to obtain near infrared spectra from the tablets with varying drug contents, whereas a Rapid Content Analyzer™ (RCA) was used to obtain spectral data from the tablets with varying hardness. Two sets of tablets from each batch (i.e., tablets with varying drug content and hardness) were randomly selected. One set of tablets was used to generate appropriate calibration models, while the other set was used as the unknown (test) set. A total of 10 ANN calibration models (5 each with 10 and 160 inputs at appropriate wavelengths) and five separate 4-factor partial least squares (PLS) calibration models were generated to predict drug contents of the test tablets from the spectral data. For the prediction of tablet hardness, two ANN calibration models (one each with 10 and 160 inputs) and two 4-factor PLS calibration models were generated and used to predict the hardness of test tablets. The PLS calibration models were generated using Vision® software. Prediction of drug contents of test tablets using the ANN calibration models generated with 10 inputs was significantly better than the prediction obtained with the ANN calibration models with 160 inputs. For tablets with low drug concentrations (less than or equal to 2%w/w), prediction of drug content was better with either of the two ANN calibration models than with the PLS calibration models. However, prediction of drug contents of tablets with greater than or equal to 5% w/w drug was better with the PLS calibration models than with the ANN calibration models. Prediction of tablet hardness was better with the ANN calibration models generated with either 10 or 160 inputs than with the PLS calibration models. This work demonstrated that a well-trained ANN model is a powerful alternative technique for analysis of NIRS data. Moreover, the technique could be used in instances when the conventional modeling of data does not work adequately.     

Artificial neural networks as alternative tool for minimizing error predictions in manufacturing ultradeformable nanoliposome formulations

This work was aimed at determining the feasibility of artificial neural networks (ANN) by implementing backpropagation algorithms with default settings to generate better predictive models than multiple linear regression (MLR) analysis. The study was hypothesized on timolol-loaded liposomes. As tutorial data for ANN, causal factors were used, which were fed into the computer program. The number of training cycles has been identified in order to optimize the performance of the ANN. The optimization was performed by minimizing the error between the predicted and real response values in the training step. The results showed that training was stopped at 10?000 training cycles with 80% of the pattern values, because at this point the ANN generalizes better. Minimum validation error was achieved at 12 hidden neurons in a single layer. MLR has great prediction ability, with errors between predicted and real values lower than 1% in some of the parameters evaluated. Thus, the performance of this model was compared to that of the MLR using a factorial design. Optimal formulations were identified by minimizing the distance among measured and theoretical parameters, by estimating the prediction errors. Results indicate that the ANN shows much better predictive ability than the MLR model. These findings demonstrate the increased efficiency of the combination of ANN and design of experiments, compared to the conventional MLR modeling techniques.     

Saturation Magnetic Induction Prediction for Amorphous Magnetic Alloys by Using Support Vector Regression

This paper illustrates an application of support vector regression (SVR) approach in forecasting the saturation magnetic induction (B _s ) of amorphous magnetic alloys. SVR was trained and tested with an experimental data set comprised of five input variables, comprising the average number of valence electrons of amorphous magnetic alloys, mixed entropy, ratio of radii, difference of electron density, and difference of work function. The prediction performance of SVR was compared with that of artificial neural networks’ (ANN) model. The results demonstrate that the prediction ability of SVR is superior to that of ANN. This investigation indicates that SVR-based modeling is a practically useful tool in prediction of the saturation magnetic induction of amorphous alloys. This study provides a novel methodology to foresee the saturation magnetic induction in sintering/development of novel amorphous magnetic alloys possessing high saturation magnetic induction.     

Prediction of mechanical properties of extra deep drawn steel in blue brittle region using Artificial Neural Network

Blue brittle region also known as dynamic strain ageing (DSA) regime is very important in the materials because in this region material properties behave in very unpredictable ways. In this work, Artificial Neural Network (ANN) models are developed for the prediction of mechanical properties such as yield strength (YS), ultimate tensile strength (UTS), % elongation, strength coefficient (K) and strain hardening exponent (n) for the extra deep drawn (EDD) quality steel in blue brittle region. To calculate the mechanical properties at elevated temperatures, experiments were conducted at the interval of 25 °C from room temperature till 700 °C in three rolling directions. Based on the experimental results, the blue brittle region for EDD steel is identified between 350 °C and 450 °C and ANN model is trained in all the three rolling directions. Trained up ANN model is tested with the experimental results at two different temperatures with in blue brittle region. Experimental and modeling errors in the prediction of mechanical properties are found within the permissible range.     

Predicting the Fatigue Life of Different Composite Materials Using Artificial Neural Networks

Artificial Neural Networks (ANN) have been recently used in modeling the mechanical behavior of fiber-reinforced composite materials including fatigue behavior. The use of ANN in predicting fatigue failure in composites would be of great value if one could predict the failure of materials other than those used for training the network. This would allow developers of new materials to estimate in advance the fatigue properties of their material. In this work, experimental fatigue data obtained for certain fiber-reinforced composite materials is used to predict the cyclic behavior of a composite made of a different material. The effect of the neural network architecture and the training function used were also investigated. In general, ANN provided accurate fatigue life prediction for materials not used in training the network when compared to experimentally measured results.     

Prediction of the heat transfer rate of a single layer wire-on-tube type heat exchanger using ANFIS

In this paper, we applied an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for prediction of the heat transfer rate of the wire-on-tube type heat exchanger. Limited experimental data was used for training and testing ANFIS configuration with the help of hybrid learning algorithm consisting of backpropagation and least-squares estimation. The predicted values are found to be in good agreement with the actual values from the experiments with mean relative error less than 2.55%. Also, we compared the proposed ANFIS model to an ANN approach. Results show that the ANFIS model has more accuracy in comparison to ANN approach. Therefore, we can use ANFIS model to predict the performances of thermal systems in engineering applications, such as modeling heat exchangers for heat transfer analysis.     

Artificial neural network modeling in competitive adsorption of phenol and resorcinol from water environment using some carbonaceous adsorbents

This paper illustrates the application of artificial neural network (ANN) for prediction of performances in competitive adsorption of phenol and resorcinol from aqueous solution by conventional and low cost carbonaceous adsorbent materials, such as activated carbon (AC), wood charcoal (WC) and rice husk ash (RHA). The three layer's feed forward neural network with back propagation algorithm in MATLAB environment was used for estimation of removal efficiencies of phenol and resorcinol in bi-solute water environment based on 29 sets of laboratory batch study results. The input parameters used for training of the neural network include amount of adsorbent (g/L), initial concentrations of phenol (mg/L) and resorcinol (mg/L), contact time (h), and pH. The removal efficiencies of phenol and resorcinol were considered as an output of the neural network. The performances of the developed ANN models were also measured using statistical parameters, such as mean error, mean square error, root mean square error, and linear regression. The comparison of the removal efficiencies of pollutants using ANN model and experimental results showed that ANN modeling in competitive adsorption of phenolic compounds reasonably corroborated with the experimental results.     

用人工神经网络研究合金元素对NdFeB永磁体磁性能的影响

为了系统研究合金元素对Nd-Fe-Co-Zr-B系永磁合金磁性能的影响，采用均匀设计方法设计了Nd、Co、Zr和B的4因素6水平U18（6^4）试验方案，根据试验结果，建立了合金成分与磁性能之间的人工神经网络（ANN）预测模型。利用该预测模型获得的成分-性能的二维曲线、三维曲面及等高线图，研究了单个合金元素以及多元素间的交互作用对NdFeB磁体磁性能的影响规律。结果表明：预测结果与实测结果吻合良好，预测精度高；Nd、Zr为提高矫顽力Hcj而降低剩磁Br的元素；Co、B则对提高Br有利而对提高Hcj不利；合金元素对Hcj与Br的影响呈相反的趋势；元素间交互作用对磁性能影响显著。     

Linear and nonlinear modeling for simultaneous prediction of dissolved oxygen and biochemical oxygen demand of the surface water — A case study

The paper describes linear and nonlinear modeling for simultaneous prediction of the dissolved oxygen (DO) and biochemical oxygen demand (BOD) levels in the river water using the set of independent measured variables. Partial least squares (PLS2) regression and feed forward back propagation artificial neural networks (FFBP ANNs) modeling methods were applied to predict the DO and BOD levels using eleven input variables measured monthly in the river water at eight different sites over a period of ten years. The performance of the models was assessed through the root mean squared error (RMSE), the bias, the standard error of prediction (SEP), the coefficient of determination (R²), the Nash-Sutcliffe coefficient of efficiency (E_f), and the accuracy factor (A_f), computed from the measured and model-predicted values of the dependent variables (DO, BOD). Goodness of the model fit to the data was also evaluated through the relationship between the residuals and the model predicted values of DO and BOD, respectively. Although, the model predicted values of DO and BOD by both the linear (PLS2) and nonlinear (ANN) models were in good agreement with their respective measured values in the river water, the nonlinear model (ANN) performed relatively better than the linear one. Relative importance and contribution of the input variables to the identified ANN model was evaluated through the partitioning approach. The developed models can be used as tool for the water quality prediction.     

Performance prediction of a specific wear rate in epoxy nanocomposites with various composition content of polytetrafluoroethylen (PTFE), graphite,short carbon fibers (CF) and nano-TiO2 using adaptive neuro-fuzzy inference system (ANFIS)

Specific wear rate of composite materials plays a significant role in industry. The processes to measure it are both time and cost consuming. It is essential to suggest a modeling method to predict and analyze the effectiveness of parameters of specific wear rate. Nowadays, computational methods such as Artificial Neural Network (ANN), Fuzzy Inference System (FIS) and adaptive neuro-fuzzy inference system (ANFIS) are mainly considered as applicable tools from modeling point of view. ANFIS present integrate performance of neural network (NN) and fuzzy system (FS). Present paper investigates performance prediction of a specific wear rate of epoxy composites with various composition using ANFIS. The obtained results showed that ANFIS is a powerful tool in modeling specific wear rate. The obtained mean of squared error (MSE) for testing sets in present paper obtained 0.0071.