Prediction of abrasive waterjet machining of sheet metals using artificial neural network
High pressure waterjet technology has received a wider acceptance for various applications involving machining, cleaning, surface treatment and material cutting. Machining of soft and thin materials with acceptable cutting quality requires a relatively low waterjet pump capacity typically below 150...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English English |
Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
Subjects: | |
Online Access: | http://umpir.ump.edu.my/id/eprint/42304/1/Prediction%20of%20abrasive%20waterjet%20machining%20of%20sheet%20metals.pdf http://umpir.ump.edu.my/id/eprint/42304/2/Prediction%20of%20abrasive%20waterjet%20machining%20of%20sheet%20metals%20using%20artificial%20neural%20network_ABS.pdf http://umpir.ump.edu.my/id/eprint/42304/ https://doi.org/10.1007/978-981-19-2095-0_5 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaysia Pahang Al-Sultan Abdullah |
Language: | English English |
Summary: | High pressure waterjet technology has received a wider acceptance for various applications involving machining, cleaning, surface treatment and material cutting. Machining of soft and thin materials with acceptable cutting quality requires a relatively low waterjet pump capacity typically below 150 MPa. The present study attempts to predict the surface roughness during the waterjet machining process for a successful cutting of sheet metals using low pressure. Artificial neural network model was used as the method for prediction. Taguchi method with L36 orthogonal array was employed to develop the experimental design. A back-propagation algorithm used in the ANN model has successfully predicted the surface roughness with the mean squared error to be below 10%. This summarizes that ANN model can sufficiently estimate surface roughness in the abrasive waterjet machining of sheet metals with a reasonable error range. |
---|