Optimal design of experiments for sensor calibration
- 9 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A framework for the design of experiments for sensor calibration is presented. The theoretical ideas, which are based on the mathematical theory of optimal design of experiments, are demonstrated using a new software program, I-OPT. This program has been used to find I-optimal designs for both a silicon capacitive absolute-pressure sensor and a silicon piezoresistive pressure sensor. It is noted that I-optimal designs are particularly attractive if the model variance is relatively small or if it is desired to keep the number of experiments to a minimum, although in this last case comparisons should be made with designs based on other criteria.Keywords
This publication has 7 references indexed in Scilit:
- Digital compensation of high-performance silicon pressure transducersSensors and Actuators A: Physical, 1990
- Constructing Exact D-Optimal Experimental Designs by Simulated AnnealingAmerican Journal of Mathematical and Management Sciences, 1988
- The Application of the Annealing Algorithm to the Construction of Exact Optimal Designs for Linear-Regression ModelsTechnometrics, 1987
- Computer-Aided Design of Experiments for Response EstimationTechnometrics, 1984
- Optimization by Simulated AnnealingScience, 1983
- A mean squared error criterion for the design of experimentsBiometrika, 1983
- A Basis for the Selection of a Response Surface DesignJournal of the American Statistical Association, 1959