Abstract

It's becoming more and more difficult to get enough failure data sample during life test of modern integrated circuit(IC). However traditional reliability assessment methods need a large number of failure data sets. In order to resolve this contradiction, this paper proposed a life prediction method of IC with small sample based on least squares support vector machine (LSSVM). This method can predict the lifetime of IC with small sample when the failure distribution is assumed to lognormal distribution. In addition, this paper demonstrated the effectiveness of LSSVM approach by Monte Carlo simulation. Error back propagation (BP) neural network was also compared with it. The simulation results show that LSSVM method has better generalization and higher accuracy of life prediction than BP neural network when dealing with small data samples from lognormal distribution.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call