Home List of Titles Improving the generalization ability of an artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process
Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/219702
|Download PDF (Published version) (Adobe Acrobat PDF, 773 KB)|
- Improving the generalization ability of an artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process
- Choudhury, T. A.; Hosseinzadeh, N.; Berndt, C. C.
- This paper presents the application of the artificial neural network into an atmospheric plasma spray process for predicting the in-flight particle characteristics, which have significant influence on the in-service coating properties. One of the major problems for such function-approximating neural network is over-fitting, which reduces the generalization capability of a trained network and its ability to work with sufficient accuracy under a new environment. Two methods are used to analyze the improvement in the network's generalization ability: (i) cross-validation and early stopping, and (ii) Bayesian regularization. Simulations are performed both on the original and expanded database with different training conditions to obtain the variations in performance of the trained networks under various environments. The study further illustrates the design and optimization procedures and analyzes the predicted values, with respect to the experimental ones, to evaluate the performance and generalization ability of the network. The simulation results show that the performance of the trained networks with regularization is improved over that with cross-validation and early stopping and, furthermore, the generalization capability of the networks is improved; thus preventing any phenomenon associated with over-fitting.
- Publication type
- Journal article
- Research centre
- Swinburne University of Technology. Faculty of Engineering and Industrial Sciences
- Research centre
- Swinburne University of Technology. Faculty of Engineering and Industrial Sciences. Industrial Research Institute Swinburne
- Journal of Thermal Spray Technology, Vol. 21, no. 5 (Sep 2012), pp. 935-949
- Publication year
- FOR Code(s)
- 0912 Materials Engineering; 0913 Mechanical Engineering
- Artificial neural network; Atmospheric plasma spray; Bayesian regularization; Cross-validation; Early stopping; In-flight particle characteristics; Kernel regression
- Publisher URL
- Copyright © ASM International. The published version is reproduced in accordance with the copyright policy of the journal.
- Full text
- Peer reviewed