Modeling and estimation of the reliability of electrical components for autonomous driving

Abstract

AbstractFrom automated to autonomous cars, a higher and higher reliability of the electrical components is required, while on the other hand the number of electrical components is continuously increasing in modern cars. Therefore for these components the estimation of a mean‐time‐to‐failure (MTTF) and a failure rate, a so‐called failure‐in‐time (FIT) rate, and the quantification of the corresponding uncertainties is crucial. The verification of the required FIT rates of less than one failure in one billion hours of lifetime is a challenge.Risk estimates have to be determined before and within the development process of future automated/autonomous cars. However, tests in real time take too long and are too expensive. As the next step, the uncertainty quantification of networks of components as in the vehicle electric system or a battery (with cells and management systems) are to be considered as well.This paper discusses several options for the determination of these failure rates. Following an overview we focus on the approach of experimental overstress tests and the combination of overstresses varying in time. Mathematically, the latter means a switching between different probability distributions in time. We state how to combine probability distributions that are typical for MTTF. Results for step functions in time as well as continuous changes in time of the probability distribution are presented. The main result is that the order of the temporal stresses is essential. This calls into question whether the common practice using temperature collectives is applicable here.