Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Archives of Civil and Mechanical Engineering

1 2019

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Prediction of average surface roughness and formability in single point incremental forming using artificial neural network

Mulay Amrut, Ben B. Satish, Ismail Syed, Kocanda Andrzej

Archives of Civil and Mechanical Engineering

2019

Vol. 19, no. 4

1135--1149

Single point incremental forming (SPIF) is a flexible, innovative, and cheap process for rapidmanufacturing of complex sheet metal parts. It is a crucial task for engineers to predict aprocess when many independent parameters are affecting simultaneously its performance.An artificial neural network (ANN) based prediction model was developed to evaluateaverage surface roughness (Ra) and maximum forming angle (Ømax) while SPIF forming ofAA5052-H32 material. A feedforward backpropagation network with Levenberg–Marquardtalgorithm was employed to build ANN model. The ANNs (4-n-1, 4-n-2) were generated byintroducing different combinations of transfer functions and a number of neurons. Theconfirmation runs were performed to verify the agreement between the ANN predicted andthe experimental results. The developed ANN model (4-n-1) was capable of predicting theprocess response with an excellent accuracy and resulted in overall R-value, MSE, and MAPEof 0.99807, 0.0209, and 5.96% for Ra0.99913, 0.0281, and 0.003 for Ømax. The optimum 4-n-2model was built with overall R-value, MSE of 0.99999 and 0.057194, respectively. Hence, itwas found that the engineering efforts may be reduced in the SPIF process with successfulANN model implementation.