Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling.

In this paper, an Artificial Neural Network (ANN) is used to investigate the influence of rolling parameters such as thickness reduction, inter-strand tension, rolling speed and friction on the rolling force, rolling power, and slip of tandem cold rolling. For this reason, the rolling power was derived for 195 various experiments through a series of observation tests. The network is trained and tested using real data collected from a practical tandem rolling line. The best topology of the ANN is determined by Broyden-Fletcher-Goldfarb-Shanno (BFGS) training algorithm and error, and nine neurons in the hidden layer had the best performance. The average of the training, testing, and validating correlation coefficients data sets are mentioned 0.947, 0.924, and 0.943, respectively. The obtained results show MSE value 4.2 × 10-4 for predicting slip. In addition, the effect of friction and angular velocity condition on the cold rolling critical slip phenomena are investigated. The results show that ANNs can accurately predict the cold rolling parameters considered in this study.

Pareto multi-objective optimization of tandem cold rolling settings for reductions and inter stand tensions using NSGA-II.

In this paper, multi-objective optimization of tandem cold rolling settings for reductions and inter-stand tensions using NSGA-II and Pareto-optimal front are investigated. In this multi-objective optimization, the total power consumption and uniform power distribution are suggested as objective functions, and reduction thicknesses in each stand and inter stand tensions were selected as problem decision variables. Analytical formulations are introduced to determine the rolling forces and power based on the Stone approach. Then, the main variables of the optimization problem, objective functions, linear and nonlinear constraints, are defined. Moreover, some empirical constraints are introduced regarding the practical limitations of cold rolling equipment and the mechanical properties of the material. At first, considering the conditions of a practical tandem rolling line, single-objective optimization is performed separately, and finally, NSGA-II was used for multi-objective optimization. Compared to the initial setting of the rolling line, the obtained single objective schedules have better performance. Moreover, the multi-objective results based on the Pareto-optimal front are investigated, and an optimized setting for rolling schedule has been suggested. Using this proposed schedule the total power consumption is reduced by more than 11% comparing to the initial setting and more uniform power distribution has been obtained in rolling stands. The normalized reductions calculated from this investigation are compared with numerical and experimental results found in the literature and the similarity was observed in the pattern of thickness reduction distribution.

A well-trained artificial neural network for predicting the rheological behavior of MWCNT-Al2O3 (30-70%)/oil SAE40 hybrid nanofluid.

In this study, the influence of different volume fractions ([Formula: see text]) of nanoparticles and temperatures on the dynamic viscosity ([Formula: see text]) of MWCNT-Al2O3 (30-70%)/oil SAE40 hybrid nanofluid was examined by ANN. For this reason, the [Formula: see text] was derived for 203 various experiments through a series of experimental tests, including a combination of 7 different [Formula: see text], 6 various temperatures, and 5 shear rates. These data were then used to train an artificial neural network (ANN) to generalize results in the predefined ranges for two input parameters. For this reason, a feed-forward perceptron ANN with two inputs (T and [Formula: see text]) and one output ([Formula: see text]) was used. The best topology of the ANN was determined by trial and error, and a two-layer with 10 neurons in the hidden layer with the tansig function had the best performance. A well-trained ANN is created using the trainbr algorithm and showed an MSE value of 4.3e-3 along 0.999 as a correlation coefficient for predicting [Formula: see text]. The results show that an increase [Formula: see text] has a significant effect on [Formula: see text] value. As [Formula: see text] increases, the viscosity of this nanofluid increases at all temperatures. On the other hand, with increasing temperature, the viscosity of this nanofluid decreases. Based on all of the diagrams presented for the trained ANNs, we can conclude that a well-trained ANN can be used as an approximating function for predicting the [Formula: see text].

Investigation of vibrational manner of carbon nanotubes in the vicinity of ultrasonic argon flow using molecular dynamics simulation.

Among various types of nanostructures, carbon nanotube (CNT) is one of the most important nanostructures. These nanostructures have been considered due to their mechanical, thermal, and vibrational properties. In this research, this nanostructure's vibrational behavior in the vicinity of argon flow in the vicinity of ultrasonic velocity was investigated. The effect of factors such as the stability of atomic structures, the atomic manner of carbon nanotubes in the presence of ultrasonic fluid, the influence of carbon nanotubes' length, and the chirality of carbon nanotubes on vibrational behavior was studied by molecular dynamics simulation. The MD simulations display an enhance in amplitude and a decrease in the oscillation frequency. Physically, these simulations' results indicated the appropriate mechanical strength of carbon nanotubes in the presence of argon fluid. Numerically, the simulated carbon nanotubes' minimum oscillation amplitude and frequency were equal to 2.02 nm and 10.14 ps-1. On the other hand, the maximum physical quantities were expressed as 4.03 nm and 13.01 ps-1.