12 December 2001 Tolerance allocation for an electronic system using neural network/Monte Carlo approach
Author Affiliations +
Abstract
The intense global competition to produce quality products at a low cost has led many industrial nations to consider tolerances as a key factor to bring about cost as well as to remain competitive. In actually, Tolerance allocation stays widely applied on the Mechanic System. It is known that to study the tolerances in an electronic domain, Monte-Carlo method well be used. But the later method spends a long time. This paper reviews several methods (Worst-case, Statistical Method, Least Cost Allocation by Optimization methods) that can be used for treating the tolerancing problem for an Electronic System and explains their advantages and their limitations. Then, it proposes an efficient method based on the Neural Networks associated with Monte-Carlo method as basis data. The network is trained using the Error Back Propagation Algorithm to predict the individual part tolerances, minimizing the total cost of the system by a method of optimization. This proposed approach has been applied on Small-Signal Amplifier Circuit as an example. This method can be easily extended to a complex system of n-components.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mohammed Al-Mohammed, Daniel Esteve, Jaque Boucher, "Tolerance allocation for an electronic system using neural network/Monte Carlo approach", Proc. SPIE 4540, Sensors, Systems, and Next-Generation Satellites V, (12 December 2001); doi: 10.1117/12.450689; https://doi.org/10.1117/12.450689
PROCEEDINGS
12 PAGES


SHARE
Back to Top