Sharif Digital Repository

Two artificial neural networks (ANNs) are constructed, trained, and tested to map inputs of a complex trunk finite element (FE) model to its outputs for spinal loads and muscle forces. Five input variables (thorax flexion angle, load magnitude, its anterior and lateral positions, load handling technique, i.e., one- or two-handed static lifting) and four model outputs (L4-L5 and L5-S1 disc compression and anterior-posterior shear forces) for spinal loads and 76 model outputs (forces in individual trunk muscles) are considered. Moreover, full quadratic regression equations mapping input-outputs of the model developed here for muscle forces and previously for spine loads are used to compare the... 

The authors studied the efficiency and accuracy of neural network model for prediction of permeability as a key parameter in reservoir characterization. So, some multilayer perceptron (MLP) neural network models with different learning algorithms of Levenberg-Margnardt, back propagation, improved back propagation (IBP), and quick propagation with three layers and different node numbers (3, 4, 5, 6, 7) in the middle layer have been presented. These models have been obtained by 630 permeability data from one of offshore reservoirs located in Saudi Arabia. The accuracy of models was studied by comparing the obtained results of each model with experimental data. So, the neural network with IBP... 

An artificial neural network (ANN) model was used to predict the weight loss of MgO-C composites at different temperatures and graphite contents. The general idea of ANN modeling was presented and after that the empirical weight loss data were used for both model verification and assessment of the oxidation rate predictions. The model was proved to have an astounding power in predicting kinetic parameters of the oxidation process. Graphite oxidation was, for example, found to be controlled by alternative diffusion steps. Plotting the Arrhenius law curves for graphite oxidation indicated a distinguishable slope change at a critical temperature which is related to the graphite content. This... 

Analytical Jacobian, nonlinear least square and three layer artificial neural network models are employed to predict deformation of mouse embryos under needle injection, based on experimental data captured from literature. The Maximum Absolute Error (MAE), coefficient of determination ( R2), Relative Error of Prediction (REP), Root Mean Square Error of Prediction (RMSEP), NashSutcliffe coefficient of efficiency ( Ef) and accuracy factor ( Af) are used as the basis for comparison of these three models. Analytical Jacobian, nonlinear least square and ANN models have yielded the correlation coefficient of 0.9985, 0.9964 and 0.9998, respectively. The REP between the models predicted values and... 

Biological cell injection is a sensitive and important work which is implemented in injection of foreign materials into individual cells. Microinjection is significantly developed in the field of drug discovery and genetics so predicting the behavior of cell in microinjection is remarkably important because a tiny excessive manipulation force can destroy the tissue of the biological cell. There are a few analytical methods available to simulate the cell injection, hence the numerical methods such as FEM are suitable to be used to model the microinjection. In this study, a new spherical super element is presented to model the biological cells and deformation of a specific cell under an... 

In this work, the modified Flory-Huggins coupled with the free-volume concept and the artificial neural network models were used to obtain the osmotic pressure of aqueous poly(ethylene glycol) solutions. In the artificial neural network, the osmotic pressure of aqueous poly(ethylene glycol) solutions depends on temperature, molecular weight and the mole fractions of poly(ethylene glycol) in aqueous solution. The network topology is optimized and the (3-1-1) architecture is found using optimization of an objective function with batch back propagation (BBP) method for 134 experimental data points. The results obtained from the neural network in obtaining of the osmotic pressure of aqueous... 

An Artificial Neural Network (ANN) model has been designed for predicting the effects of alloying elements (Fe, Si, Al, Mn) on the recrystallization behavior and microstructural changes of 70/30 brass. The model introduced here considers the content of alloying elements, temperature, and time of recrystallization as inputs while percent of recrystallization is presented as output. It is shown that the designed model is able to predict the effect of alloying elements well. It is also shown that all alloying elements strongly affect the recrytallization kinetics, and all slow down the recrystallization process. The effect of alloying elements on the activation energy for recrystallization has... 

Metal matrix composites (MMCs) have received considerable attention due to their excellent engineering properties, but their poor machinability has been the main deterrent to their substitution for metal parts. Optimization of machining parameters such as cutting speed, feed rate and depth of cut will improve the machinability of this material. This paper represents application of artificial neural network (ANN) model and genetic algorithm to study the machinability aspects of Al/SiC-15% produced by powder metallurgy process and to obtain optimum machining conditions. A multilayer feed forward ANN has been employed to study the effect of machining parameters on three aspects of machinablity,... 

In this work, an artificial neural network model was used to obtain the partition coefficients of biomolecules in polymer-polymer aqueous two-phase systems. In the artificial neural network, the partition coefficient of a biomolecule depends on the difference between concentrations of poly (ethylene glycol), dextran in the top and bottom phases, temperature and molecular weights of poly (ethylene glycol), dextran, and the biomolecule. The network topology is optimized and the (6-1-1) architecture is found using optimization of an objective function with sequential quadratic programming (SQP) method for 450 experimental data points. The results obtained from the neural network of the... 

River water quality monitoring using traditional water sampling and laboratory analyses is expensive and time-consuming. The application of artificial neural network (ANN) models to simulate water quality parameters is cost-effective, quick, and reliable. This study provides two methods of mathematical and ANN modeling to simulate and forecast five important river water quality indicators (DO, TDS, SAR, BOD5, HCO3) correlated with variables such as EC, temperature, and pH which can be measured easily and almost with no cost. The mathematical method is based on polynomial fitting with least square method and the neural network model was developed using a feed-forward algorithm. The 35 years’... 

Batch culture of Azohydromonas lata was investigated for the production of intracellular poly-b-hydroxybutyrate (PHB). In order to determine the C:N value of the culture media for maximizing the microbial productivity of PHB, different concentrations of glucose and ammonium chloride were used as carbon and nitrogen sources, respectively. The optimal temperature and shaking rate was obtained at 30_C and 180 rpm, respectively. The maximum intracellular PHB concentration obtained was 5.09 g/l, which was 20% (w/w) of the cell dry weight (CDW) after 72 h. Also, the synthesis of PHB was growth associated with the C:N ratio of 153.71. The maximum calculated Yp/s was 0.212 (gr/gr) and the specific... 

Use of computational modeling with a few experiments is considered useful to obtain the best possible result for a final product, without performing expensive and time-consuming experiments. Proton exchange membrane fuel cells (PEMFCs) can produce clean electricity, but still require further study. An oxygen reduction reaction (ORR) takes place at the cathode, and carbon-supported platinum (Pt/C) is commonly used as an electrocatalyst. The harsh conditions during PEMFC operation result in Pt/C degradation. Observation of changes in the Pt/C layer under operating conditions provides a tool to study the lifetime of PEMFCs and overcome durability issues. Recently, artificial neural networks... 

In this study, the self-adaptive evolutionary (SaE) agent is employed to structure the contributing elements to process the management of extreme learning machine (ELM) architecture based on a logical procedure. In fact, the SaE algorithm is utilized for possibility of enhancing the performance of the ELM to estimate daily soil temperature (ST) at 6 different depths of 5, 10, 20, 30, 50 and 100 cm. In the developed SaE-ELM model, the network hidden node parameters of the ELM are optimized using SaE algorithm. The precision of the SaE-ELM is then compared with the ELM model. Daily weather data sets including minimum, maximum and average air temperatures (Tmin, Tmax and Tavg), atmospheric... 

In the present study, the main purpose is investigation of the coatings thickness effect on the fatigue life of AISI 1045 steel. Herein, two different coatings of warm galvanization and hardened chromium have been used on the specimens. Fatigue tests were performed on specimens with different coating thicknesses of 13 and 19 µm. In the high-cycle level, S–N curves are extracted with 13 points for each sample. The results show that the galvanized coating is the most appropriate coating with low thickness, but with significant increasing of coating thickness, the best choice is hardened chromium coating. However, artificial neural network (ANN) has been used as an efficient approach instead of... 

An accurate examination of deformability of rock samples in response to any change in stresses is deeply dependent on the reliable determination of properties of the rock as analysis inputs. Although Young’s modulus (E) can provide valuable characteristics of the rock material deformation, the direct determination of E is considered a time-consuming and complicated analysis. The present study is aimed to introduce a new hybrid intelligent model to predict the E of granitic rock samples. Hence, a series of granitic block samples were collected from the face of a water transfer tunnel excavated in Malaysia and transferred to laboratory to conduct rock index tests for E prediction. Rock index... 

The activity coefficient at infinite dilution is a representative of the limiting non-ideality of a solute in a mixture. Various methods for the prediction of infinite dilution activity coefficients (IDACs) have been developed. Artificial neural networks are powerful mapping tools for nonlinear function approximations. Accordingly, an artificial neural network model is proposed for the prediction of the IDACs of binary systems where the properties of the individual components are used as inputs to the network. The input parameters of the neural network are the mixture temperature, critical temperature, critical pressure, critical volume, molecular weight, dipole moment and the acentric... 

In this work, microstructural evolutions and mechanical properties of AISI 304L stainless steel were studied after rolling operations at elevated temperatures. Rolling experiments were conducted under warm and hot rolling conditions in the range of 600-1000 °C employing different reductions. Then, the developed microstructures and the mechanical properties of the steel were evaluated by means of uniaxial tensile testing, metallographic observations, and x-ray diffraction method. Besides, two-dimensional finite element analysis coupled with artificial neural network modeling was developed to assess thermo-mechanical behavior of the steel during and after rolling. The results show that... 

The application of artificial neural network to compressor performance map prediction is investigated. Different types of artificial neural networks such as general regression neural network, rotated general regression neural network proposed by the authors, radial basis function network, and multilayer perceptron network are considered. Two different models are utilized in simulating the performance map. The results indicate that while the rotated general regression neural network has the least mean error and best agreement to the experimental data; it is however, limited to interpolation application. On the other hand, if one considers a tool for interpolation as well as extrapolation... 

Severe shot peening (SSP) process is widely used for surface nanocrysallization of a bulk material that demonstrates excellent mechanical properties compared with its coarse-grained equivalents. In this study, a plastically deformed surface was produced with nanostructured grains on different materials of AISI 1045, 1050, and 1060 carbon steels by means of SSP. Shot peening was applied with a wide range of Almen intensities and coverages. Optical microscopy, scanning electron microscopy, field emission scanning electron microscopy, high resolution transmission electron microscope observations, and X-ray diffraction analysis were employed to analyze the mechanism of grain refinement... 

Statistical bias correction methods are inferred relationships between inputs and outputs. The constructed functions are based on available observations, which are limited in time and space. This study investigates the ability of regression models (linear and nonlinear) to regionalize a domain by defining a minimum number of training pixels necessary to achieve a good level of bias correction performance. Linear regression is used to divide northern South America into five regions. To correct the biases of temperature and precipitation, an artificial neural network (ANN) model was trained with selected pixels within each region and then used to reproduce bias-corrected temperature and...