木糖醇发酵过程的软测量研究

针对木糖醇发酵过程中木糖醇浓度不能在线测量和影响发酵过程控制的情况,使用软测量技术来估算木糖醇的浓度和底物浓度,使用动态BP网络作为软测量模型,并确定了10个隐含层节点的网络拓扑结构,使用LM算法训练网络。用未经训练的数据检验软测量模型,取得了满意的逼近效果。实现了木糖醇发酵过程木糖醇浓度和底物浓度的间接实时测量。     

SMB色谱分离过程组分纯度软测量技术

针对SMB色谱分离过程中组分纯度的实时测量存在困难的现状,建立了两组分(葡萄糖、果糖)纯度的在线软测量模型。软测量模型采用NNARMAX模型作为模型辨识类;采用BP神经网络对模型进行逼近,为加快网络收敛速度,采用Levenberg—Marquardt算法对网络进行训练。在Matlab工作平台上进行了大量的仿真,对该模型进行验证,仿真结果证明了该方法的有效性。     

双弯管法煤粉质量流量检测

双弯管法是一种基于弯管单相流测量原理的气固两相流固相质量流量测量方法,其测量结果与输入参数间非线性关系非常复杂,直接影响其测量精度.在双弯管法固相质量流量测量原理基础上,利用人工神经网络优良的非线性映射能力,建立了一种带有附加动量项的BP神经网络软测量模型,并在气固两相流测量实验平台上进行了实验研究.以实验数据为样本对双弯管法软测量模型进行训练,仿真结果与实验数据一致性较好,测量误差小于6％,为煤粉质量流量实时在线测量提供了一种行之有效的方法.     

基于神经网络的污水处理软测量系统的研究

针对污水处理质量指标无法在线检测的问题,提出了基于人工神经网络的软测量方法。构造了污水处理质量软测量的神经网络结构,运用实际工业污水处理过程测量数据对BP神经网络进行了训练和仿真。结果表明,实能准确地进行污水处理质量的实时估计,实现污水处理质量的实时控制。     

基于文化算法的神经网络及其在建模中的应用

在深入研究文化算法和神经网络相关文献基础上,针对神经网络建模的特点提出了一种训练神经网络的文化算法流程构造文化神经网络,并将该网络用于乙烯精馏塔产品质量软测量建模.通过训练与泛化能力的比较分析,结果表明基于文化神经网络的软测量模型具有良好的性能和较好的应用前景.     

基于改进模糊神经网络的软测量建模方法

提出了一种改进的模糊神经网络软测量建模方法，采用规则化的平均输出隶属度函数作为模糊基函数进行反模糊化运算；在训练网络时,部分参数采用Levenberg-Marquardt算法来训练，另一部分采用一阶梯度下降法．最后用该建模方法建立了聚合反应中熔融指数的软测量模型，并与一般的模糊神经网络软测量模型进行比较．结果表明改进的模糊神经网络对初始值的选择不敏感,具有很好的收敛性，同时还能达到指定的预测精度，很适合工程应用．     

基于支持向量机的软测量建模方法

提出了一种基于支持向量机的软测量方法，并建立了青霉素发酵过程中菌丝浓度的软测量模型，通过实验分析了参数调整和核函数选择对支持向量机建模的影响．利用现场数据建立各种软测量模型可以发现，与其他软测量方法相比，支持向量机方法在理论上优于人工神经网络等其他建模方法．     

基于BP网络的水文预报模型

在BP人工神经网络基础上建立水文预报模型,讨论了模型的学习样本、网络参数和训练方式对预报精度的影响,选出最佳网络参数配置.     

丁二烯精馏塔的推断控制方案与软测量模型

研究了某厂丁二烯精馏塔塔底控制回路目前存在的问题，提出了基于软测量的推断控制方案。利用DCS采集的现场数据进行相关性分析后，分别建立了非线性回归模型和人工神经网络模型。选用较为简单的回归模型构成了软测量仪表。     

人工神经网络技术在系统流量异常检测模块中的应用

介绍人工神经网络技术,建立了人工神经网络的典型模型.应用BP算法的泛化功能,将输入输出样本进行训练,不断学习调整网络权值,使网络实现给定的输入输出映射关系,以达到检测流量异常的目的.     

Artificial neural networks for job shop simulation

This paper explores the use of artificial neural networks (ANNs) as a valid alternative to the traditional job-shop simulation approach. Feed forward, multi-layered neural network metamodels were trained through the back-error-propagation (BEP) learning algorithm to provide a versatile job-shop scheduling analysis framework. The constructed neural network architectures were capable of satisfactorily estimating the manufacturing lead times (MLT) for orders simultaneously processed in a four-machine job shop. The MLTs produced by the developed ANN models turned out to be as valid as the data generated from three well-known simulation packages, i.e. Arena, SIMAN, and ProModel. The ANN outputs proved not to be substantially different from the results provided by other valid models such as SIMAN and ProModel when compared against the adopted baseline, Arena. The ANN-based simulations were able to fairly capture the underlying relationship between jobs' machine sequences and their resulting average flowtimes, which proves that ANNs are a viable tool for stochastic simulation metamodeling.     

Artificial neural network-based techniques for the retrieval of SWE and snow depth from SSM/I data

The retrieval of snow water equivalent (SWE) and snow depth is performed by inverting Special Sensor Microwave Imager (SSM/I) brightness temperatures at 19 and 37 GHz using artificial neural network ANN-based techniques. The SSM/I used data, which consist of Pathfinder Daily EASE-Grid brightness temperatures, were supplied by the National Snow and Ice Data Centre (NSIDC). They were gathered during the period of time included between the beginning of 1996 and the end of 1999 all over Finland. A ground snow data set based on observations of the Finnish Environment Institute (SYKE) and the Finnish Meteorological Institute (FMI) was used to estimate the performances of the technique. The ANN results were confronted with those obtained using the spectral polarization difference (SPD) algorithm, the HUT model-based iterative inversion and the Chang algorithm, by comparing the RMSE, the R², and the regression coefficients. In general, it was observed that the results obtained through ANN-based technique are better than, or comparable to, those obtained through other approaches, when trained with simulated data. Performances were very good when the ANN were trained with experimental data.     

Design of artificial neural networks for distribution feeder loss analysis

To enhance the efficiency for power loss analysis of voluminous distribution feeders, ANN-based simplified power loss models with the Levenberg–Marquardt (LM) algorithm have been developed for overhead feeders and underground feeders, respectively. The three-phase load flow analysis is executed to obtain the sensitivity of feeder loss with variations in power loading, conductor length, and total capacity of distribution transformers. Through this, the data set for neural network training is prepared to derive the ANN-based simplified power loss models. The power loss of each distribution feeder can be easily derived from the key factors of hourly loading, feeder length, and transformer capacity. By integrating the power loss of all feeders, the power loss of the entire distribution system can thus be obtained to estimate the operation efficiency of the Taipower system.     

Applying machine learning to software fault-proneness prediction

The importance of software testing to quality assurance cannot be overemphasized. The estimation of a module’s fault-proneness is important for minimizing cost and improving the effectiveness of the software testing process. Unfortunately, no general technique for estimating software fault-proneness is available. The observed correlation between some software metrics and fault-proneness has resulted in a variety of predictive models based on multiple metrics. Much work has concentrated on how to select the software metrics that are most likely to indicate fault-proneness. In this paper, we propose the use of machine learning for this purpose. Specifically, given historical data on software metric values and number of reported errors, an Artificial Neural Network (ANN) is trained. Then, in order to determine the importance of each software metric in predicting fault-proneness, a sensitivity analysis is performed on the trained ANN. The software metrics that are deemed to be the most critical are then used as the basis of an ANN-based predictive model of a continuous measure of fault-proneness. We also view fault-proneness prediction as a binary classification task (i.e., a module can either contain errors or be error-free) and use Support Vector Machines (SVM) as a state-of-the-art classification method. We perform a comparative experimental study of the effectiveness of ANNs and SVMs on a data set obtained from NASA’s Metrics Data Program data repository.     

Artificial neural network model for ground vibration amplitudes prediction due to light railway traffic in urban areas

The growth of density and circulation speed of railway transportation systems in urban areas increases the importance of the research issues of the produced environmental impacts. This study presents a field data analysis, obtained during monitoring campaigns of ground vibration, due to light railway traffic in urban areas, based on the artificial neural network (ANN) approach, using quantitative and qualitative predictors. Different ANN-based models, using those predictors, were evaluated/trained and validated. Using several criteria, including those that measures the possibility of ANN overfitting (RR²) and complexity (AIC), the best ANN model was successfully obtained for Lisbon area. This model, with 16 input elements (quantitative and qualitative predictors), 2 neurons on the hidden layer with a hyperbolic tangent sigmoid transfer function, and 1 neuron on the output layer considering a linear transfer function, has 0.9720 for the coefficient of determination and 0.5293 for the sum squared error.

     

Robust radar target classifier using artificial neural networks

In this paper an artificial neural network (ANN) based radar target classifier is presented, and its performance is compared with that of a conventional minimum distance classifier. Radar returns from realistic aircraft are synthesized using a thin wire time domain electromagnetic code. The time varying backscattered electric field from each target is processed using both a conventional scheme and an ANN-based scheme for classification purposes. It is found that a multilayer feedforward ANN, trained using a backpropagation learning algorithm, provides a higher percentage of successful classification than the conventional scheme. The performance of the ANN is found to be particularly attractive in an environment of low signal-to-noise ratio. The performance of both methods are also compared when a preemphasis filter is used to enhance the contributions from the high frequency poles in the target response.     

Development of a virtual curve tracer for estimation of transducer characteristics under the influence of a disturbing variable

This paper presents an artificial neural network (ANN)-based novel virtual curve tracer (VCT) for estimation of transducer response characteristics under the influence of a disturbing variable for computer-based measurement systems. The disturbing variable effect on transducer output response is a typical problem that affects the accuracy of such systems. Especially, change in transducer excitation causes its response characteristics to be highly nonlinear and complex signal processing is required to obtain its accurate direct model. The proposed VCT used a multilayer feed-forward back-propagation artificial neural network (MLFFBP-ANN)-based two-dimensional (2D) model for accurate fitting of transducer characteristics to measured data under the influence of a disturbing variable. The proposed model is trained with Levenberg–Marquardt learning algorithm for achieving an extremely fast convergence speed as compared to the existing ANN-based techniques.     

Learning-based multi-pass adaptive scheduling for a dynamic manufacturing cell environment

Because the essential attributes are uncertain in a dynamic manufacturing cell environment, to select a near-optimal subset of manufacturing attributes to enhance the generalization ability of knowledge bases remains a critical, unresolved issue for classical artificial neural network-based (ANN-based) multi-pass adaptive scheduling (MPAS). To resolve this problem, this study develops a hybrid genetic /artificial neural network (GA/ANN) approach for ANN-based MPAS systems. The hybrid GA/ANN approach is used to evolve an optimal subset of system attributes from a large set of candidate manufacturing system attributes and, simultaneously, to determine configuration and learning parameters of the ANN according to various performance measures. In the GA/ANN-based MPAS approach, for a given feature subset and the corresponding topology and learning parameters of an ANN decoded by a GA, an ANN was applied to evaluate the fitness in the GA process and to generate the MPAS knowledge base used for adaptive scheduling control mechanisms. The results demonstrate that the proposed GA/ANN-based MPAS approach has, according to various performance criteria, a better system performance over a long period of time than those obtained with classical machine learning-based MPAS approaches and the heuristic individual dispatching rules.     

Top-of-atmosphere flux retrievals from CERES using artificial neural networks

The Clouds and the Earth's Radiant Energy System (CERES) instruments on the Terra spacecraft provide accurate shortwave (SW), longwave (LW) and window (WN) region top-of-atmosphere (TOA) radiance measurements from which TOA radiative flux values are obtained by applying Angular Distribution Models (ADMs). These models are developed empirically as functions of the surface and cloud properties provided by coincident high-resolution imager measurements over CERES field-of-view. However, approximately 5.6% of the CERES/Terra footprints lack sufficient imager information for a reliable scene identification. To avoid any systematic biases in regional mean radiative fluxes, it is important to provide TOA fluxes for these footprints. For this purpose, we apply a feedforward error-backpropagation Artificial Neural Network (ANN) technique to reproduce CERES/Terra ADMs relying only on CERES measurements. All-sky ANN-based angular distribution models are developed for 10 surface types separately for shortwave, longwave and window TOA flux retrievals. To optimize the ANN performance, we use a partially connected first hidden neuron layer and compact training sets with reduced data noise. We demonstrate the performance of the ANN-based ADMs by comparing TOA fluxes inferred from ANN and CERES anisotropic factors. The global annual average bias in ANN-derived fluxes relative to CERES is less than 0.5% for all ANN scene types. The maximum bias occurs over sea ice and permanent snow surfaces. For all surface types, instantaneous ANN-derived TOA fluxes are self-consistent in viewing zenith angle to within 9% for shortwave, 3.5% and 3% longwave daytime and nighttime, respectively.     

Line flow contingency selection and ranking using cascade neural network

Line flow or real-power contingency selection and ranking is performed to choose the contingencies that cause the worst overloading problems. In this paper, a cascade neural network-based approach is proposed for fast line flow contingency selection and ranking. The developed cascade neural network is a combination of a filter module and a ranking module. All the contingency cases are applied to the filter module, which is trained to classify them either in critical contingency class or in non-critical contingency class using a modified BP algorithm. The screened critical contingencies are passed to the ranking module (four-layered feed-forward artificial neural network (ANN)) for their further ranking. Effectiveness of the proposed ANN-based method is demonstrated by applying it for contingency screening and ranking at different loading conditions for IEEE 14-bus system. Once trained, the cascade neural network gives fast and accurate screening and ranking for unknown patterns and is found to be suitable for on-line applications at energy management centre.