PREDICTION OF ABRASIVE WATER JET CUTTING PARAMETERS USING ARTIFICIAL NEURAL NETWORK | ||||
The International Conference on Applied Mechanics and Mechanical Engineering | ||||
Article 68, Volume 18, 18th International Conference on Applied Mechanics and Mechanical Engineering., April 2018, Page 1-14 PDF (1.44 MB) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/amme.2018.35013 | ||||
View on SCiNiTO | ||||
Authors | ||||
Y. M. Elattar1; M. A. Mahdy2; H. A. Sonbol3 | ||||
1Assistant Lecturer, Modern Academy for Engineering and Tech., Cairo, Egypt. | ||||
2Dean of Higher Institute for Engineering and Modern Technology Marg, Cairo, Egypt. | ||||
3Professor, Design and Prod. Eng. Dept., Faculty of Engineering, Ain Shams University, Cairo, Egypt. | ||||
Abstract | ||||
ABSTRACT This work presents a new predictive model of abrasive water-jet (AWJ) machining of ARMOX shielding steel plate of 7.6 mm thick. The model was developed to predict some interesting process parameters from process variables. As AWJ is a complicated multi input multi output machining process. The model is developed using artificial neural network (ANN). A feed forward neural network based on back propagation was made up of 4 input neurons, 1 hidden layer with 10 hidden neurons and 2 output neurons. The ANN training set was generated by extensive experimental work. The tests considered four process variables. The studied AWJ process variables are traverse speed (T), waterjet pressure (P), standoff distance (s), and abrasive flow rate (ma). The considered process parameters are surface roughness (Ra) and material removal rate (MRR). The ANN model was trained and tested. The ANN succeeded to model the AWJ process by extracting the process parameters from process variables with a regression factor above 90%. This paper is a step forward to model and control the AWJ machining process. | ||||
Keywords | ||||
Abrasive water jet (AWJ); Armox; Artificial Neural network (ANN); surface roughness (Ra); Material Removal Rate (MRR) | ||||
Statistics Article View: 175 PDF Download: 430 |
||||