Tolerance allocation for an electronic system using neural network/Monte Carlo approach

Mohammed Al-Mohammed; Daniel Esteve; Jaque Boucher

doi:10.1117/12.450689

12 December 2001 Tolerance allocation for an electronic system using neural network/Monte Carlo approach

Mohammed Al-Mohammed, Daniel Esteve, Jaque Boucher

Proceedings Volume 4540, Sensors, Systems, and Next-Generation Satellites V; (2001) https://doi.org/10.1117/12.450689
Event: International Symposium on Remote Sensing, 2001, Toulouse, France

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.

Citation Download Citation

Mohammed Al-Mohammed, Daniel Esteve, and 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); https://doi.org/10.1117/12.450689

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available