Many tribological problems are expensive to solve due to the requirement of heavy and iterative computation. In this study, a direct mapping between design variables and merits is obtained using a neural network. Data from limited numerical simulations of the behaviors of fluid film of a slider in the thermohydrodynamic regime were used to train the network, which replaces further lengthy simulations. A balance between the modeling accuracy and generalization capability of the network is achieved by optimizing the network size using an efficient optimization scheme, DIviding RECTangles (DIRECT). Performance comparison of the optimization method is based on a hybrid learning strategy that combines the steepest descent and Levenberg-Marquardt method.
Skip Nav Destination
Sign In or Register for Account
World Tribology Congress III
September 12–16, 2005
Washington, D.C., USA
Conference Sponsors:
- Tribology Division
ISBN:
0-7918-4201-0
PROCEEDINGS PAPER
Tribological Performance Prediction Using an Artificial Neural Network Optimized by the DIRECT Algorithm
Yau-Zen Chang
,
Yau-Zen Chang
Chang Gung University, Tao-Yuan, Taiwan
Search for other works by this author on:
Nenzi Wang
Nenzi Wang
Chang Gung University, Tao-Yuan, Taiwan
Search for other works by this author on:
Yau-Zen Chang
Chang Gung University, Tao-Yuan, Taiwan
Nenzi Wang
Chang Gung University, Tao-Yuan, Taiwan
Paper No:
WTC2005-63413, pp. 911-912; 2 pages
Published Online:
November 17, 2008
Citation
Chang, Y, & Wang, N. "Tribological Performance Prediction Using an Artificial Neural Network Optimized by the DIRECT Algorithm." Proceedings of the World Tribology Congress III. World Tribology Congress III, Volume 1. Washington, D.C., USA. September 12–16, 2005. pp. 911-912. ASME. https://doi.org/10.1115/WTC2005-63413
Download citation file:
Sign In
2
Views
0
Citations
Related Articles
Simulation of Static Performance of Air Foil Bearings Using Coupled Finite Element and Computational Fluid Dynamics Techniques
J. Eng. Gas Turbines Power (February,2014)
A Thermohydrodynamic Analysis of Dry Gas Seals for High-Temperature Gas-Cooled Reactor
J. Tribol (April,2013)
Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures
J. Mech. Des (February,2020)
Related Chapters
A Novel Approach for LFC and AVR of an Autonomous Power Generating System
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)
Modeling and Simulation of Coal Gas Concentration Prediction Based on the BP Neural Network
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)
Hybrid Cryptographic Scheme for Data Communication
International Conference on Advanced Computer Theory and Engineering (ICACTE 2009)