Application of artificial neural network for performance evaluation of vertical axis wind turbine rotor

In the present paper, artificial neural network (ANN) modelling has been performed for evaluating power coefficient (C_p) and torque coefficient (C_t) of a combined three-bucket-Savonius and three-bladed-Darrieus vertical axis wind turbine rotor, which has got potential for power generation in a small-scale manner, especially in low wind speed conditions. However, detailed experimental work on the rotor for evaluating its performance parameters is either scarce or too costly and time consuming to carry out. In this work, a new ANN modelling method is adopted to map the input–output parameters using very small training data sets, selected from past experimental results of the rotor. The trained ANN models are used to predict the performance data, which are obtained within acceptable error limits. Furthermore, to evaluate the fit values and estimate the variance of the predicted data by the ANN models, linear regression equations are fitted to the experimental and predicted results, which shows that R-squared (R²) values are obtained close to unity meaning good fitting of the data. Moreover, the results of ANN modelling are also compared with that of radial basis function (RBF) networks, which also show a good agreement between ANN predicted data and RBF network data. The present ANN models can be exploited to extract more performance data within a given range of input data.     

Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods

In order to determine the appropriate model for predicting the maximum surface settlement caused by EPB shield tunneling, three artificial neural network (ANN) methods, back-propagation (BP) neural network, the radial basis function (RBF) neural network, and the general regression neural network (GRNN), were employed and the results were compared. The nonlinear relationship between maximum ground surface settlements and geometry, geological conditions, and shield operation parameters were considered in the ANN models. A total number of 200 data sets obtained from the Changsha metro line 4 project were used to train and validate the ANN models. A modified index that defines the physical significance of the input parameters was proposed to quantify the geological parameters, which improves the prediction accuracy of ANN models. Based on the analysis, the GRNN model was found to outperform the BP and RBF neural networks in terms of accuracy and computational time. Analysis results also indicated that strong correlations were established between the predicted and measured settlements in GRNN model with MAE = 1.10, and RMSE = 1.35, respectively. Error analysis revealed that it is necessary to update datasets during EPB shield tunneling, though the database is huge.     

基于ANN的岩土体热阻系数预测模型研究

为准确预测土体热阻系数,通过室内热探针测试与数据分析,简要分析了含水量、干密度、矿物成分和颗粒形态等因素对土体热传导特性的影响,利用人工神经网络(ANN)技术,建立了计算土体热阻系数的预测模型,并与传统经验关系模型进行对比,明确所提计算模型的可靠性与优越性.结果表明:土体传热性能受众多因素影响,其热阻系数难以准确估算,基于ANN的计算模型可以较好地解决这一问题;以含水量和干密度为输入参数的单个模型适用于特定类型土体,而4个输入参数(含水量、干密度、黏粒含量和石英含量)的广义模型不受此限制,增加相关输入参数可有效保证模型计算结果的精确度;单个模型和广义模型的计算结果与实测结果吻合良好,预测能力均显著优于传统经验关系模型;对于工程性质差异显著、沉积环境复杂的不同类型土体,建议优先选用广义模型来估算其热阻系数.     

Prediction of roadheader performance by artificial neural network

Performance prediction of the roadheaders is one of the main subjects in determining the economics of the underground excavation projects. During the last decades, researchers have focused on developing performance prediction models for roadheaders. In the first stage of this study, the performance of a roadheader used in Kucuksu sewage tunnel (Istanbul) was recorded in detail and the instantaneous cutting rate (ICR) of the machine was determined. The uniaxial compressive strength (UCS) and rock quality designation (RQD) are used as input parameters in previously developed empirical models in order to point out the efficiency of these models, and the relationships between measured and predicted ICR for different encountered formations. In the second stage of the study, Artificial Neural Network (ANN) technique is used for predicting of the ICR of the roadheader. A data set including UCS, RQD, and measured ICR are established. It is traced that a neural network with two inputs (RQD and UCS) and one hidden layer can be sufficient for the estimation of ICR. In addition, it is determined that increase in number of neurons in hidden layer has positive optimizing on the performance of the ANN and a hidden layer larger than 10 neurons does not have a significant effect on optimizing the performance of the neural network. Furthermore, probability of memorizing is being recognized in this situation. Based on this study, it is concluded that the prediction capacity of ANN is better than the empirical models developed previously.     

A novel artificial neural network fire model for prediction of thermal interface location in single compartment fire

Thermal interface is the boundary between the hot and cold gases layers in a compartment fire. The height of the interface depends predominantly on the mass of air entrained into the fire plume. However, the analytical determination of the air mass flow rate is complicated since it is highly nonlinear in nature. Currently, computer models including zone models and field models can be applied to predict fire phenomena effectively. In the zone model computation, the compartment on fire is commonly divided into two layers to which conservation equations are applied to evaluate the fire behaviour. However, the locations of the fire bed and the openings are ignored in the computation. Computational fluid dynamics techniques may be employed, but a major shortcoming is the requirement for extensive computational resources and lengthy computational time. A unique, new and novel artificial neural network (ANN) model, denoted as GRNNFA, is developed for predicting parameters in compartment fires and is an extremely fast alternative approach. The GRNNFA model is capable of capturing the nonlinear system behaviour by training the network using relevant historical data. Since noise is usually embedded in most of the collected fire data, traditional ANN models (e.g. feed-forward multi-layer-perceptron, general regression neural network, radial basis function, etc.) are unable to separate the embedded noise from the genuine characteristics of the system during the course of network training. The GRNNFA has been developed particularly for processing noisy fire data. The model was applied to predict the location of the thermal interface in a single compartment fire and compared with the experiments conducted by Steckler et al. (Flow induced by fire in a compartment, NBSIR 82-2520, National Bureau of Standards, Washington, DC, 1982). The results show that the GRNNFA fire model can predict the location of the thermal interface with up to 94.5% accuracy and minimum computational times and resources. The trained GRNNFA model was also applied to rapidly determine the height of the thermal interface with different locations of fire on the compartment floor and different widths of the opening against field model predictions. Among the five test cases, four of them were predicted well within the minimum error range of the experiment results. It also demonstrated that the prediction accuracy is related to the amount of knowledge provided for network training.     

Predicting the capacity of perfobond rib shear connector using an ANN model and GSA method

Due to recent advances in the field of artificial neural networks (ANN) and the global sensitivity analysis (GSA) method, the application of these techniques in structural analysis has become feasible. A connector is an important part of a composite beam, and its shear strength can have a significant impact on structural design. In this paper, the shear performance of perfobond rib shear connectors (PRSCs) is predicted based on the back propagation (BP) ANN model, the Genetic Algorithm (GA) method and GSA method. A database was created using push-out test test and related references, where the input variables were based on different empirical formulas and the output variables were the corresponding shear strengths. The results predicted by the ANN models and empirical equations were compared, and the factors affecting shear strength were examined by the GSA method. The results show that the use of ANN model optimization by GA method has fewer errors compared to the empirical equations. Furthermore, penetrating reinforcement has the greatest sensitivity to shear performance, while the bonding force between steel plate and concrete has the least sensitivity to shear strength.     

Statistical and neural network assessment of the compression index of clay-bearing soils

The compression index is used to estimate the consolidation settlement of clay-bearing soils. As the determination of compression index from oedometer tests is relatively time-consuming, empirical equations based on index properties can be useful. In this study the performance of widely used single and multi-variable empirical equations was evaluated using a database consisting of 135 test data. New empirical equations were developed utilizing least square regression analysis. In addition, an artificial neural network (ANN) with eight input variables was also developed to estimate the compression index. It was concluded that ANN provides the best results.      

Prediction of thermal conductivity of rock through physico-mechanical properties

The transfer of energy between two adjacent parts of rock mainly depends on its thermal conductivity. Present study supports the use of artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) in the study of thermal conductivity along with other intrinsic properties of rock due to its increasing importance in many areas of rock engineering, agronomy and geo environmental engineering field. In recent years, considerable effort has been made to develop techniques to determine these properties. Comparative analysis is made to analyze the capabilities among six different models of ANN and ANFIS. ANN models are based on feedforward backpropagation network with training functions resilient backpropagation (RP), one step secant (OSS) and Powell–Beale restarts (CGB) and radial basis with training functions generalized regression neural network (GRNN) and more efficient design radial basis network (NEWRB). A data set of 136 has been used for training different models and 15 were used for testing purposes. A statistical analysis is made to show the consistency among them. ANFIS is proved to be the best among all the networks tried in this case with average absolute percentage error of 0.03% and regression coefficient of 1, whereas best performance shown by the FFBP (RP) with average absolute error of 2.26%. Thermal conductivity is predicted using P-wave velocity, porosity, bulk density, uniaxial compressive strength of rock as input parameters.     

Developing a simple-to-use predictive model for prediction of hydrate formation temperature

Hydrate formation may be a common occurrence during oil and gas drilling and production operation when temperature of these solid crystalline compounds that formed in the presence of free water decreases at elevated pressure. Also, they have often been found responsible for operating difficulties at wellheads, pipelines and other processing equipment. Nowadays, because of the importance of predicting hydrate formation condition, different accurate methods have been used. Besides the experiential correlations that are common for predicting, the developments in the field of modelling led to the use of different methods in a thermodynamic way. In fact, because of the risk of experimental uncertainties and to remove the need for intricate analytic equations and empirical correlations, the computational intelligence model, which result in the lowest error and based on experimental data, is strongly proposed, in attempts to solve complex industrial problems. In this article, in order to predict gas hydrate formation condition, two smart techniques are established based on feed-forward neural network (artificial neural network (ANN)) which is optimised by imperialist competitive algorithm (ICA). The ICA-ANN model is conducted utilising the empirical data released in the literature and finally the performance of ICA-ANN model is compared with the conventional ANN model. Furthermore, they have been compared with an accurate thermodynamic model at different operating conditions. The outcomes, contrary to expectations, establish that the ICA-ANN model has poor performance when compared with the ANN.     

Artificial neural networks as a basis for new generation of rock failure criteria

Conventional methods for prediction of rock strength are based on using classical failure criteria. In this study, artificial neural networks were regarded as new tools for considering the strength of intact rock in a wide range of loading condition from uniaxial tension to triaxial compression. A comprehensive data set of the values of major and minor principal stresses at failure from 1638 laboratory tests on seven rock types was collected. For each rock type, data were randomly divided into two subsets, training and test sets. Neural networks were trained using training sets to predict the value of major principal stress at failure from uniaxial compressive stress and minor principal stress. Small architecture and regularization method were adopted to avoid over-fitting problems. The same training sets were used in determining the constants of two popular empirical failure criteria, namely Bieniawski–Yudhbir and Hoek–Brown. Then, the test sets were used to examine the accuracy and generalization of the models in predicting the strength in new situations. Comparison of the results of the neural network models with those of the empirical criteria showed that the former approach always lead to less root mean squared error and higher coefficient of determination. On average, for different rock types, using ANN models led to about 30% decrease in prediction error relative to best empirical models. These models also showed better flexibility in the prediction of major principal stress at failure in both brittle and ductile failure regimes.     

Wavelet and ANN combination model for prediction of daily suspended sediment load in rivers

In this research, a new wavelet artificial neural network (WANN) model was proposed for daily suspended sediment load (SSL) prediction in rivers. In the developed model, wavelet analysis was linked to an artificial neural network (ANN). For this purpose, daily observed time series of river discharge (Q) and SSL in Yadkin River at Yadkin College, NC station in the USA were decomposed to some sub-time series at different levels by wavelet analysis. Then, these sub-time series were imposed to the ANN technique for SSL time series modeling. To evaluate the model accuracy, the proposed model was compared with ANN, multi linear regression (MLR), and conventional sediment rating curve (SRC) models. The comparison of prediction accuracy of the models illustrated that the WANN was the most accurate model in SSL prediction. Results presented that the WANN model could satisfactorily simulate hysteresis phenomenon, acceptably estimate cumulative SSL, and reasonably predict high SSL values.     

Backfilling missing microbial concentrations in a riverine database using artificial neural networks

Predicting peak pathogen loadings can provide a basis for watershed and water treatment plant management decisions that can minimize microbial risk to the public from contact or ingestion. Artificial neural network models (ANN) have been successfully applied to the complex problem of predicting peak pathogen loadings in surface waters. However, these data-driven models require substantial, multiparameter databases upon which to train, and missing input values for pathogen indicators must often be estimated. In this study, ANN models were evaluated for backfilling values for individual observations of indicator bacterial concentrations in a river from 44 other related physical, chemical, and bacteriological data contained in a multi-year database. The ANN modeling approach provided slightly superior predictions of actual microbial concentrations when compared to conventional imputation and multiple linear regression models. The ANN model provided excellent classification of 300 randomly selected, individual data observations into two defined ranges for fecal coliform concentrations with 97% overall accuracy. The application of the relative strength effect (RSE) concept for selection of input variables for ANN modeling and an approach for identifying anomalous data observations utilizing cross validation with ANN model are also presented.     

Artificial neural network-based prediction of performance and emission characteristics of CI engine using polanga as a biodiesel

The present work predicts the performance parameters, namely brake specific fuel consumption (BSFC), brake thermal efficiency (BTE), peak pressure, exhaust gas temperature and exhaust emissions of a single cylinder four-stroke diesel engine at different injection timings and engine load using blended mixture of polanga biodiesel by artificial neural network (ANN). The properties of biodiesel produced from polanga were measured based on ASTM standards. Using some of the experimental data for training, an ANN model was developed based on standard back-propagation algorithm for the engine. Multi-layer perception network was used for non-linear mapping between input and output parameters. Different activation functions and several rules were used to assess the percentage error between the desired and the predicted values. It was observed that the developed ANN model can predict the engine performance and exhaust emissions quite well with correlation coefficient (R) 0.99946, 0.99968, 0.99988, 0.99967, 0.99899, 0.99941 and 0.99991 for the BSFC, BTE, peak pressure, exhaust gas temperature, NO_x, smoke and unburned hydrocarbon emissions, respectively. The experimental results revealed that the blended fuel provides better engine performance and improved emission characteristics.     

神经网络反馈分析方法预测土体热阻系数研究

为研究不同土体的热传导特性,通过文献数据归纳整理,简要分析了土体热阻系数与主要影响因素的相关关系。利用神经网络反馈分析方法,提出土体热阻系数的预测模型,并对所提模型的有效性与优越性进行了对比验证。结果表明:反馈神经网络能够简便、有效的预测土体热阻系数,所建模型以干密度、饱和度和石英含量为输入参数,较为全面、合理地反映了影响土体热传导性质的主要因素;预测模型具有较高的精度,预测值与实测值的相关系数R~2大于0.93,均方根误差RMSE低于28 K?cm/W,方差比VAF大于94%;与传统经验关系式相比,反馈分析模型在新环境中的预测结果上具有显著的优越性。     

应用RBF神经网络的预应力混凝土碳化深度预测研究

在现有混凝土碳化研究成果基础上,建立了预应力混凝土碳化预测模型。随后,运用径向基函数神经网络的基本原理,通过对影响预应力混凝土碳化深度因素的分析,建立了预测碳化深度的RBF和GRNN网络模型。通过实例进行了分析计算和预测,预测结果具有较高的精度。可以说,人工神经网络预测方法是一种可同时考虑各种影响因素组合、行之有效的混凝土碳化预测分析方法。     

Application of artificial neural network for the prediction of jaggery mass during drying inside the natural convection greenhouse dryer

In this paper, an attempt is made to predict the hourly mass of jaggery during the process of drying inside greenhouse dryer under the natural convection mode. Jaggery was dried until the constant variation in the mass of jaggery. Artificial neural network (ANN) is used to predict the mass of the dried jaggery on hourly basis. Solar radiation, ambient temperature and relative humidity are input parameters for the prediction of jaggery mass in each hour in the ANN modelling. The results of the ANN model are also validated with experimental drying data of jaggery mass. The statistical parameters such as root mean square error and correlation coefficient (R²) are used to measure the difference between values predicted by the ANN model and the values actually observed from the experimental study. It was found that the results of the ANN model and experimental are shown fairly good agreement.     

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore mine,Iran简

Blast-induced ground vibration is one of the inevitable outcomes of blasting in mining projects and may cause substantial damage to rock mass as well as nearby structures and human beings. In this paper, an attempt has been made to present an application of artificial neural network (ANN) to predict the blast-induced ground vibration of the Gol-E-Gohar (GEG) iron mine, Iran. A four-layer feed-forward back propagation multi-layer perceptron (MLP) was used and trained with Levenberg–Marquardt algorithm. To construct ANN models, the maximum charge per delay, distance from blasting face to monitoring point, stemming and hole depth were taken as inputs, whereas peak particle velocity (PPV) was considered as an output parameter. A database consisting of 69 data sets recorded at strategic and vulnerable locations of GEG iron mine was used to train and test the generalization capability of ANN models. Coefficient of determination (R²) and mean square error (MSE) were chosen as the indicators of the performance of the networks. A network with architecture 4-11-5-1 and R² of 0.957 and MSE of 0.000722 was found to be optimum. To demonstrate the supremacy of ANN approach, the same 69 data sets were used for the prediction of PPV with four common empirical models as well as multiple linear regression (MLR) analysis. The results revealed that the proposed ANN approach performs better than empirical and MLR models.     

Prediction of wind speed for the estimation of wind turbine power output from site climatological data using artificial neural network

In this paper, the wind speeds of Noupoort in the Western Cape region of South Africa are forecasted from the site climatological data using feed forward artificial neural network (ANN) with the back propagation training method. Different architectural designs are tested with different combinations of climatological data to obtain the most suitable ANN for predicting the wind speed of the site. The predicted wind speeds are compared with the actual measured wind speeds and the results are evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE) and correlation coefficient (R). Some of the key results show that combination of temperature, wind direction and time of the day (TEM?+?WD?+?T) could effectively predict wind speed of Noupoort. The forecasted wind speed shows a strong agreement with the measured wind speed with R, RMSE, MAPE and MAE of 0.96, 0.56, 6.64% and 0.44, respectively.     

CAST工艺的BP和RBF人工神经网络仿真模型

将误差反向传播前馈(BP)神经网络模型和径向基函数(RBF)神经网络模型应用到CAST工艺中,并采用多输入、双输出神经网络模拟处理过程中各变量之间的关系和预测出水水质.误差分析结果表明,训练阶段RBF神经网络模型的拟合精度比BP神经网络模型的高,但两者的预测精度相差不大;测试阶段BP神经网络模型和RBF神经网络模型预测出水COD的平均相对误差分别为6.35%、6.80%,预测出水TN的平均相对误差分别为7.19%、5.49%,均在8%以下,这说明两种神经网络模型均可用于模拟CAST污水处理工艺各变量之间的关系和预测出水水质,为污水厂的运行管理提供了理论依据.