Toggle Main Menu Toggle Search

Open Access padlockePrints

Prediction of depth removal in leather surface grit blasting using neural networks and Box-Behnken design of experiments

Lookup NU author(s): Dr Zhongxu Hu, Dr Bob Bicker, Christopher Marshall


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


In this work, leather material is for the first time prepared by grit blasting process in order to improve peel strength when bonding. Peel tests show that it is the surface depth of removal rather than surface roughness that dominates the bonding performance. Therefore, measurement of surface removal is critical for surface preparation of using a grit blasting process. Indirect measurement of preparation performance is essential due to the hazardous conditions for conventional sensing equipment in the blasting chamber. A neural network modelling approach is proposed for the prediction of surface removal of leather materials, and the neural network model also characterizes the process, which is very useful for machine design and optimum control. The data used for the training of the artificial neural network is collected through screening experiments, which was efficiently planned using the Box-Behnken design method. © Springer-Verlag London Limited 2007.

Publication metadata

Author(s): Hu Z, Bicker R, Marshall C

Publication type: Article

Publication status: Published

Journal: International Journal of Advanced Manufacturing Technology

Year: 2007

Volume: 32

Issue: 7-8

Pages: 732-738

ISSN (print): 0268-3768

ISSN (electronic): 1433-3015

Publisher: Springer UK


DOI: 10.1007/s00170-005-0381-6


Altmetrics provided by Altmetric