Artificial neural network application for modeling the rail rolling process

Altınkaya, Hüseyin; Orak, İlhami Muharrem; Esen, İsmail

doi:10.1016/j.eswa.2014.06.014

Cited by 29 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the net output, denoted by a is obtained by applying transfer function to n. These three steps are called weight function, net input function and transfer function [10,17]. There are various transfer functions used in neuron structure in literature [18].…”

Section: N=wp+b (2)mentioning

confidence: 99%

The Performance Analysis of Artificial Neural Network Based Shimizu-Morioka Chaotic System with Respect to Sample Numbers

Alçın¹,

Pehlivan²,

Koyuncu³

2015

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

In this paper, Shimizu-Morioka Chaotic System (SMCS) is modelled using Feed Forward Artificial Neural Network. In the realized network model, Log-Sigmoid and Purelin transfer functions have been used for hidden and output layer, respectively. 3-10-3 network structure is created using MATLAB. The model inputs are the state variables of SMCS. Outputs represent not only the outputs of SMCS but also iterative versions of these inputs. For the equations' numeric solutions of describing SMCS, Runge Kutta 5 Butcher (RK-5-B) algorithm which is one of the differential equation solution methods, is used. Samples in the structure of described network, the created different numbers of samples using RK-5-B have been used as input data and performance analysis have been performed for these data. As a result, the paper shows that when the sample data numbers increase, network modeling performance gives more successful results.

show abstract

Section: N=wp+b (2)mentioning

confidence: 99%

The Performance Analysis of Artificial Neural Network Based Shimizu-Morioka Chaotic System with Respect to Sample Numbers

Alçın¹,

Pehlivan²,

Koyuncu³

2015

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…New generation computers allow full 3D modelling of rail rolling and there are several papers published showing this solution, the examples may be seen in [10][11][12], but it is still computationally expensive. Therefore, when only forces were to be calculated simplified models or artificial intelligence methods were used [13]. Over the last years much more attention, however, has been paid to the cooling process, what is because the final microstructure and properties of rails are determined in this process.…”

Section: Introductionmentioning

confidence: 99%

Numerical simulation of manufacturing process chain for pearlitic and bainitic steel rails

Milenin

Zalecki

Pernach

et al. 2020

Archiv.Civ.Mech.Eng

View full text Add to dashboard Cite

Computer system for the design of technology of the manufacturing of pearlitic and bainitic rails was presented in this paper. The system consists of the FEM simulation module of thermal–mechanical phenomena and microstructure evolution during hot rolling integrated with the module of phase transformation occurring during cooling. Model parameters were identified based on dilatometric tests. Physical simulations, including Gleeble tests, were used for validation and verification of the models. In the case of pearlitic steels, the process of subsequent immersions of the rail head in the polymer solution was numerically simulated. The objective function in the optimization procedure was composed of minimum interlamellar spacing and maximum hardness. Cooling in the air at a cooling bed was simulated for the bainitic steel rails and mechanical properties were predicted. The obtained results allowed us to formulate technological guidelines for the process of accelerated cooling of rails.

show abstract

“…An ANN model was designed to obtain optimum parameters values for rail rolling process by Altinkaya et al. 15 Their studies presented that instead of using complex techniques and analytical equations, ANNs can be used to control factor values required for product design in the rail rolling process. Furthermore, Gudur and Dixit 16 utilized neural network technique to estimate the roll force and torque in the process.…”

Section: Introductionmentioning

confidence: 99%

Application of artificial neural network and genetic algorithm to predict and optimize load and torque in T-section profile ring rolling

Parvizi

Raftar

2019

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Artificial neural network is implemented to predict the required load and torque in T-section profile ring rolling process for the first time in this study. Moreover, an optimal condition of T-section profile ring rolling process for specific limit of input factor is acquired using genetic algorithm technique. Various three-dimensional finite element simulations are carried out for different collections of process variables to obtain initial data for training and validation of the neural network. Besides, the finite element model is verified via comparison with the experimental results of the other investigators. The back-propagation algorithm is utilized to develop Levenberg–Marquardt feed-forward network and the optimum architecture is achieved by estimating the performance considering different number of hidden layers and neurons. It is concluded that results of artificial neural network predictions have an appropriate conformity with those ones from simulation and experiments. Moreover, a reasonable accuracy is obtained from the implemented model by which the prediction of ring rolling load and torque in different conditions can be achieved.

show abstract

Artificial neural network application for modeling the rail rolling process

Cited by 29 publications

References 12 publications

The Performance Analysis of Artificial Neural Network Based Shimizu-Morioka Chaotic System with Respect to Sample Numbers

The Performance Analysis of Artificial Neural Network Based Shimizu-Morioka Chaotic System with Respect to Sample Numbers

Numerical simulation of manufacturing process chain for pearlitic and bainitic steel rails

Application of artificial neural network and genetic algorithm to predict and optimize load and torque in T-section profile ring rolling

Contact Info

Product

Resources

About