A decision support methodology for process in the loop optimisation

Gladwin, Dan and Stewart, Paul and Stewart, Jill and Chen, Rui and Winward, Edward (2008) A decision support methodology for process in the loop optimisation. In: CS/IEEE International Workshop on Modelling and Applied Simulation 2008, September 17-19, 2008, Calabria, Italy.

Documents
A decision support methodology for process in the loop optimisation
Experimental optimisation with hardware-in-the-loop is a common procedure in engineering, particularly in cases where accurate modelling is not possible. A common methodology to support experimental search is to use one of the many gradient descent methods. However, even sophisticated and proven methodologies such as Simulated Annealing (SA) can be significantly challenged in the presence of significant noise. This paper introduces a decision support methodology based upon Response Surfaces (RS), which supplements experimental management based on variable neighbourhood search, and is shown to be highly effective in directing experiments in the presence of significant signal to noise (S-N) ratio and complex combinatorial functions. The methodology is developed on a 3-dimensional surface with multiple local-minima and large basin of attraction, and high S-N ratio. Finally, the method is applied to a real-life automotive experimental application.
[img]
[Download]
[img]
Preview
PDF
MAS2008.pdf - Whole Document

1MB

Abstract

Experimental optimisation with hardware-in-the-loop is a common procedure in engineering, particularly in cases where accurate modelling is not possible. A common methodology to support experimental search is to use one of the many gradient descent methods. However, even sophisticated and proven methodologies such as Simulated Annealing (SA) can be significantly challenged in the presence of significant noise. This paper introduces a decision support methodology based upon Response Surfaces (RS), which supplements experimental management based on variable neighbourhood search, and is shown to be highly effective in directing experiments in the presence of significant signal to noise (S-N) ratio and complex combinatorial functions. The methodology is developed on a 3-dimensional surface with multiple local-minima and large basin of attraction, and high S-N ratio. Finally, the method is applied to a real-life automotive experimental application.

Item Type:Conference or Workshop Item (Presentation)
Keywords:Experimental decision support, Simulated annealing, Multiobjective Optimisation
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
H Engineering > H100 General Engineering
Divisions:College of Science > School of Engineering
ID Code:2264
Deposited By:INVALID USER
Deposited On:31 Mar 2010 14:06
Last Modified:17 Jul 2014 11:13

Repository Staff Only: item control page