The application of a hybrid inverse boundary element problem engine for the solution of potential problems

This source preferred by John Vinney, Siamak Noroozi and Philip Sewell

Authors: Noroozi, S., Sewell, P. and Vinney, J.

Journal: Computer Modelling in Engineering and Sciences

Volume: 14

Pages: 171-180

ISSN: 1526-1492

A method that combines a modified back propagation Artificial Neural Network (ANN) and Boundary Element Analysis (BEA) was introduced and discussed in the author's previous papers. This paper discusses the development of an automated inverse boundary element problem engine. This inverse problem engine can be applied to both potential and elastostatic problems. \\ In this study, BEA solutions of a two-dimensional potential problem is utilised to test the system and to train a back propagation Artificial Neural Network (ANN). Once training is completed and the transfer function is created, the solution to any subsequent or new problems can be obtained quickly and in real-time without any further modelling or processing time with a high degree of accuracy. This provides substantial savings on computational time and provides instant solutions to a given problem with infinite combinations of alternative boundary conditions. This approach is particularly useful when parametric optimisation of an existing component is required, which may typically involve several iterations in order to obtain valid results. In this paper the inverse problem engine will be explained in detail. \\ The logic behind its Graphical User Interface (GUI) will be explained and results will be discussed. Using this technique we can for example identify the temperature at the cutting tool tip or on the external surface due to cutting force, from accurate internal temperatures.

This data was imported from Scopus:

Authors: Noroozi, S., Sewell, P. and Vinney, J.

Journal: CMES - Computer Modeling in Engineering and Sciences

Volume: 14

Issue: 3

Pages: 171-180

ISSN: 1526-1492

A method that combines a modified back propagation Artificial Neural Network (ANN) and Boundary Element Analysis (BEA) was introduced and discussed in the author's previous papers. This paper discusses the development of an automated inverse boundary element problem engine. This inverse problem engine can be applied to both potential and elastostatic problems. In this study, BEA solutions of a two-dimensional potential problem is utilised to test the system and to train a back propagation Artificial Neural Network (ANN). Once training is completed and the transfer function is created, the solution to any subsequent or new problems can be obtained quickly and in real-time without any further modelling or processing time with a high degree of accuracy. This provides substantial savings on computational time and provides instant solutions to a given problem with infinite combinations of alternative boundary conditions. This approach is particularly useful when parametric optimisation of an existing component is required, which may typically involve several iterations in order to obtain valid results. In this paper the inverse problem engine will be explained in detail. The logic behind its Graphical User Interface (GUI) will be explained and results will be discussed. Using this technique we can for example identify the temperature at the cutting tool tip or on the external surface due to cutting force, from accurate internal temperatures. Copyright © 2006 Tech Science Press.

This data was imported from Web of Science (Lite):

Authors: Noroozi, S., Sewell, P. and Vinney, J.

Journal: CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES

Volume: 14

Issue: 3

Pages: 171-180

ISSN: 1526-1492

The data on this page was last updated at 10:28 on April 24, 2019.