Water content in output crude oil is hard to measure precisely because of wide range of dielectric coefficient of crude oil caused by injected dehydrating and demulsifying agents. The method to reduce measurement error of water content in crude oil proposed in this paper is based on switching measuring ranges of on-line water content analyzer automatically. Measuring precision on data collected from oil field and analyzed by in-field operators can be impressively improved by using back propogation (BP) neural network to predict water content in output crude oil. Application results show that the difficulty in accurately measuring water-oil content ratio can be solved effectively through this combination of on-line measuring range automatic switching and real time prediction, as this method has been tested repeatedly on-site in oil fields with satisfactory prediction results.