Artificial neural network approach to predict the engine performance of fish oil biodiesel with diethyl ether using back propagation algorithm

An artificial neural network (ANN) model is developed to predict the engine performance of fish oil biodiesel blended with diethyl ether. Engine performance and emission characteristics such as brake thermal efficiency, hydrocarbon, exhaust gas temperature, oxides of nitrogen (NO_x), carbon monoxide (CO), smoke and carbon dioxide (CO₂) were considered. Experimental investigations on single-cylinder, constant speed, direct injection diesel engine are carried out under variable load conditions. The performance and emission characteristics are measured using an exhaust gas analyser, smoke metre, piezoelectric pressure transducer and crank angle encoder for different fuel blends and engine load conditions. In this model, a back propagation algorithm is used to predict the performance. Computational results clearly demonstrated that the developed ANN models produced less deviations and exhibited higher predictive accuracy with acceptable determination correlation coefficients of 0.97–1 and mean relative error of 0–3.061% with experimental values. The root mean square errors were found to be low. The developed model produces the idealised results and it has been found to be useful for predicting the engine performance and emission characteristics with limited number of available data.     

Predicting a water infrastructure leakage index via machine learning

In this study, the infrastructure leakage index (ILI) indicator that is preferred frequently by the water utilities with sufficient data to determine the performances of water distribution systems is modeled for the first time through the three different methodologies using different input data. In addition to the variables in the literature used for the classical ILI calculations, the age parameter is also included in the models. In the first step, the ILI values have been estimated via multiple linear regression (MLR) using water supply quantity, water accrual quantity, network length, service connection length, number of service connections, and pressure variables. Secondly, the Artificial Neural Network (ANN) approach has been applied with raw data to improve the ILI prediction performance. Finally, the data set has been standardized with the Z-Score method for increasing the learning power of the ANN models, and then the ANN predictions have been made by converting the data through the principal component analysis (PCA) method to minimize complexity by reducing the data set size. The model predictions have been evaluated via mean square error, G-value, mean absolute error, mean bias error, and adjusted-R² model performance scale. When the model outputs obtained at the end of the study are evaluated together with the classical ILI calculations, it is seen that the successful ILI predictions with three and four variables, including the age parameter, rather than six variables, have been made through the PC-ANN method. Water utilities with insufficient physical and operational data for ILI indicator calculation can make network performance evaluations by predicting the ILI through the models suggested in this study with high accuracy in a reliable way.     

Artificial neural network,ANN-PSO and ANN-ICA for modelling the Stirling engine

Nowadays, shortage of fossil fuels resources, especially oil, and also global attention to environmental hazards produced by the internal combustion process have caused extensive researches on the development of renewable energy engine technology. Among all kinds of renewable resources, solar energy Stirling engines have their own special situation for energy generation with lower pollutants and sustainable sources. The Stirling engine is an external combustion engine that uses any external heat source to generate mechanical power. Various parameters affect the performance of the Stirling engine. In this study, artificial neural network (ANN) was applied to estimate the power and torque values obtained from a Stirling heat engine (Philips M102C engine). It employs the Levenberg–Marquardt algorithm for training ANN with back propagation network for estimating the power and torque of the Stirling heat engine. The performances of the imperialist competitive algorithm (ICA)-ANN and ANN-particle swarm optimisation (PSO) are compared with the performance of the ANN based on mean square error (MSE) and correlation coefficient. PSO and ICAs are applied to determine the initial weights of the neural network. The obtained results indicate that ANN-PSO has a better performance than ICA-ANN and ANN alone; also the MSE for the ANN-PSO is lower as well. Considering the results obtained from this study, there is very good agreement between the output of the testing phase of the ANN-PSO model with experimental data and they are very close to each other.     

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.     

Comparison between design and actual energy performance of a HVAC-ground coupled heat pump system in cooling and heating operation

This work compares the experimental results obtained for the energy performance study of a ground coupled heat pump system with the design values predicted by means of standard methodology. The system energy performance of a monitored ground coupled heat pump system is calculated using the instantaneous measurements of temperature, flow and power consumption and these values are compared with the numerical predictions. These predictions are performed with the TRNSYS software tool following standard procedures taking the experimental thermal loads as input values. The main result of this work is that simulation results solely based on nominal heat pump capacities and performances overestimate the measured overall energy performance by a percentage between 15% and 20%. A sensitivity analysis of the simulation results to changes in percentage of its input parameters showed that the heat pump nominal coefficient of performance is the parameter that mostly affects the energy performance predictions. This analysis supports the idea that the discrepancies between experimental results and simulation outputs for this ground coupled system are mainly due to heat pump performance degradation for being used at partial load. An estimation of the impact of this effect in energy performance predictions reduces the discrepancies to values around 5%.     

Artificial neural network optimized by differential evolution for predicting diameters of jet grouted columns

A novel and effective artificial neural network (ANN) optimized using differential evolution (DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters. The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters (i.e. the epoch size, the number of neurons in a hidden layer, the number of hidden layers, and the regularization parameter) that govern the neural network efficacy. This approach is further enhanced by a stochastic gradient optimization algorithm to allow ‘expensive’ computation efforts. The ANN-DE is first trained using a prepared jet grouting dataset, then verified and compared with the prevalent machine learning tools, i.e. neural networks and support vector machine (SVM). The results show that, the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance. Specifically, the ANN-DE achieved root mean square error (RMSE) values of 0.90603 and 0.92813 for the training and testing phases, respectively. The corresponding values were 0.8905 and 0.9006 for the optimized ANN, then, 0.87569 and 0.89968 for the optimized SVM, respectively. The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.     

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.     

基于神经网络的供热计量系统热负荷短期预测

针对实行热计量后热负荷变化的特点，采用神经网络中应用最广泛的BP网络对热负荷进行预测，利用MATLAB仿真程序对所建立的人工神经网络负荷预测模型进行验证，仿真误差为6．93％，满足工程需要。     

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.     

Application of several optimization techniques for estimating TBM advance rate in granitic rocks

This study aims to develop several optimization techniques for predicting advance rate of tunnel boring machine(TBM)in different weathered zones of granite.For this purpose,extensive field and laboratory studies have been conducted along the 12,649 m of the Pahang-Selangor raw water transfer tunnel in Malaysia.Rock properties consisting of uniaxial compressive strength(UCS),Brazilian tensile strength(BTS),rock mass rating(RMR),rock quality designation(RQD),quartz content(q)and weathered zone as well as machine specifications including thrust force and revolution per minute(RPM)were measured to establish comprehensive datasets for optimization.Accordingly,to estimate the advance rate of TBM,two new hybrid optimization techniques,i.e.an artificial neural network(ANN)combined with both imperialist competitive algorithm(ICA)and particle swarm optimization(PSO),were developed for mechanical tunneling in granitic rocks.Further,the new hybrid optimization techniques were compared and the best one was chosen among them to be used for practice.To evaluate the accuracy of the proposed models for both testing and training datasets,various statistical indices including coefficient of determination(R~2),root mean square error(RMSE)and variance account for(VAF)were utilized herein.The values of R~2,RMSE,and VAF ranged in 0.939-0.961,0.022-0.036,and 93.899-96.145,respectively,with the PSO-ANN hybrid technique demonstrating the best performance.It is concluded that both the optimization techniques,i.e.PSO-ANN and ICA-ANN,could be utilized for predicting the advance rate of TBMs;however,the PSO-ANN technique is superior.     

A neural network model for the prediction of compression ignition engine performance at different injection timings

Rapid depletion of fossil fuel and continuous increase in gasoline prices have stimulated the search of alternative fuels. This paper deals with the prediction of engine performance, emission and combustion characteristics of compression ignition engine fuelled with fish oil biodiesel using artificial neural network (ANN). Experimental investigations are carried out in a single cylinder constant speed direct injection diesel engine under variable load conditions at different injection timings?21⁰, 24⁰ and 27⁰ bTDC. The performance, combustion and emission characteristics are measured using an exhaust gas analyser, smoke meter, piezoelectric pressure transducer and crank angle encoder for different fuel blends and engine load conditions. For training the neural network, feed-forward back propagation algorithm is used. The developed ANN model predicts the performance, combustions and exhaust emissions with a correlation coefficients (R) of 0.97–0.99 and a mean relative error of 0.62–4.826%. The root mean square errors are found to be low. The developed model has found to predict accurately the engine performance, combustion and emission parameters at different injection timings.     

Predicting pile dynamic capacity via application of an evolutionary algorithm

This study presents the development of a new model obtained from the correlation of dynamic input and SPT data with pile capacity. An evolutionary algorithm, gene expression programming (GEP), was used for modelling the correlation. The data used for model development comprised 24 cases obtained from existing literature. The modelling was carried out by dividing the data into two sets: a training set for model calibration and a validation set for verifying the generalization capability of the model. The performance of the model was evaluated by comparing its predictions of pile capacity with experimental data and with predictions of pile capacity by two commonly used traditional methods and the artificial neural networks (ANNs) model. It was found that the model performs well with a coefficient of determination, mean, standard deviation and probability density at 50% equivalent to 0.94, 1.08, 0.14, and 1.05, respectively, for the training set, and 0.96, 0.95, 0.13, and 0.93, respectively, for the validation set. The low values of the calculated mean squared error and mean absolute error indicated that the model is accurate in predicting pile capacity. The results of comparison also showed that the model predicted pile capacity more accurately than traditional methods including the ANNs model.     

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.     

Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural network models for an open office

In this study, a linear parametric autoregressive model with external inputs (ARX) and a neural network-based nonlinear autoregressive model with external inputs (NNARX) are developed to predict the thermal behaviour of an open office in a modern building. External and internal climate data recorded over three months were used to build and validate models for predicting dry bulb temperature and relative humidity for different time-scales (30 min to 3 h ahead). In order to compare the accuracy for different step-ahead predictions, different performance measures, such as goodness of fit, mean squared error, mean absolute error and coefficient of determination between predicted model output and real measurements, were calculated. For the NNARX model, the optimal network structure after training, is subsequently determined by pruning the fully connected network using the optimal brain surgeon strategy. The results demonstrate that both models provide reasonably good predictions but the nonlinear NNARX model outperforms the linear ARX model. These models can both potentially be used for improving indoor air quality by focusing on building intelligence into the controller in HVAC plants, in particular, adaptive control systems.     

Artificial neural network based modelling of desiccant wheel

In this article, the concept of artificial neural network and goal oriented design have been used to propose a computer design tool that can help designers to evaluate performance of desiccant cooling system and behaviour of the desiccant wheel. Based on the experimental observations on desiccant wheel, a neural network model has been developed using a neural network toolbox of MATLAB^® with feed forward back propagation method. The model has been validated against experimental data sets. A number of training algorithms with feed forward back propagation method have been used for the modelling of desiccant wheel to identify a training algorithm with least mean square error (MSE). The performance of all training algorithms has been analyzed and training algorithm trainlm (Levenberg-Marquardt back propagation) is found most suitable for the prediction of outputs which have least mean square error of 0.064462 and 0.007575 for specific humidity and temperatures respectively. The proposed model can predict the specific humidity and temperature at the outlet of desiccant wheel within the range of experimental values.     

Prediction of bed load sediments using different artificial neural network models

Modeling and prediction of bed loads is an important but difficult issue in river engineering. The introduced empirical equations due to restricted applicability even in similar conditions provide different accuracies with each other and measured data. In this paper, three different artificial neural networks (ANNs) including multilayer percepterons, radial based function (RBF), and generalized feed forward neural network using five dominant parameters of bed load transport formulas for the Main Fork Red River in Idaho-USA were developed. The optimum models were found through 102 data sets of flow discharge, flow velocity, water surface slopes, flow depth, and mean grain size. The deficiency of empirical equations for this river by conducted comparison between measured and predicted values was approved where the ANN models presented more consistence and closer estimation to observed data. The coefficient of determination between measured and predicted values for empirical equations varied from 0.10 to 0.21 against the 0.93 to 0.98 in ANN models. The accuracy performance of all models was evaluated and interpreted using different statistical error criteria, analytical graphs and confusion matrixes. Although the ANN models predicted compatible outputs but the RBF with 79% correct classification rate corresponding to 0.191 network error was outperform than others.     

Prediction of pressure coefficients on roofs of low buildings using artificial neural networks

This paper describes an artificial neural network (ANN) approach for the prediction of mean and root-mean-square (rms) pressure coefficients on the gable roofs of low buildings. The ANN models, which employ a backpropagation training algorithm, are capable of generalizing the complex, nonlinear functional relationships between the pressure coefficients and eave height, wind direction and spatial location on the roof. The performance of the ANN is demonstrated by the prediction of the pressure coefficients for roof tap locations in a corner bay. The mean bay uplift can be predicted accurately with an average error less than 2% for three cornering wind directions not seen by the ANN during training. The mean-square errors of all of the individual pressure taps in the corner bay were 12% and 9% for the mean and rms coefficients, respectively. This approach could be used to expand aerodynamic databases to a larger variety of geometries and increase its practical feasibility.     

Predicting Spill Plumes with the Fire Risk Zone Model B-RISK

Recent experimental research on spill plume entrainment has developed a range of empirically-based formulae for smoke management design. These formulae form the spill plume entrainment model in B-RISK, a new fire risk zone model. This article describes the performance of B-RISK in predicting spill plume entrainment. Selected experimental data from the series of reduced-scale experiments used to form the new design formulae have been used for model validation, along with other full-scale experimental data from ‘hot smoke tests’ conducted to assess the performance of installed smoke management systems. B-RISK provides predictions of the plume clear-layer height that generally agree with experimental results within the range of experimental error. This gives confidence in its use to predict spill plume entrainment for smoke management design purposes.     

An applied artificial intelligence approach towards assessing building performance simulation tools

With the development of modern computer technology, a large amount of building energy simulation tools is available in the market. When choosing which simulation tool to use in a project, the user must consider the tool's accuracy and reliability, considering the building information they have at hand, which will serve as input for the tool. This paper presents an approach towards assessing building performance simulation results to actual measurements, using artificial neural networks (ANN) for predicting building energy performance. Training and testing of the ANN were carried out with energy consumption data acquired for 1 week in the case building called the Solar House. The predicted results show a good fitness with the mathematical model with a mean absolute error of 0.9%. Moreover, four building simulation tools were selected in this study in order to compare their results with the ANN predicted energy consumption: Energy_10, Green Building Studio web tool, eQuest and EnergyPlus. The results showed that the more detailed simulation tools have the best simulation performance in terms of heating and cooling electricity consumption within 3% of mean absolute error.     

An experimental study of naturally driven heated air flow in a vertical pipe

Specifications of warm air flow within a vertical pipe which is induced by the buoyancy effect were investigated in this study. Air from surroundings was directed into a heating chamber connected to a vertical pipe to establish a flow within the pipe. The temperature and the velocity were measured at different points within the stable flow and the mean values of these parameters were computed. Mass flow rate of air was evaluated using ideal gas assumption. In order to investigate the effect of the thermal boundary condition of the pipe, two tests were conducted; once for the pipe exposed to the surroundings and then for the pipe with a thermal insulation. A model for predicting the induced flow rate of warm air was developed and the predictions of the model were compared with the experimental data over the tested range of the parameters.