In view of the current situation that Weibull distribution is widely used in the life prediction of intelligent electric energy meters, this paper introduces an important failure model in probabilistic physics method: B-S fatigue life distribution and its reliability analysis, and deduces the maximum likelihood estimation value and approximate interval of two parameter B-S distribution. B-S distribution is suitable for describing the life law of failed products. It is mainly used in the analysis and research of fatigue failure and performance degradation failure of electronic products. In this paper, the two parameter B-S distribution is introduced into the life prediction of intelligent electric energy meter for the first time. The parameters of the two parameter B-S distribution are estimated by using the maximum likelihood method and the least square method, and the life prediction method based on the B-S distribution is established. The practicability of the B-S distribution life prediction method is verified by a practical example. The research content of this paper provides a new method for the life prediction and rotation cycle of electric energy meter, and provides a new idea for the reliability evaluation of electric energy meter.