Predictive Maintenance (PdM) aims to estimate the optimal moment when the maintenance of an industrial asset should be performed according to its actual health status. The goal is to minimize the costs, by finding the optimal point where the sum of the prevention and repair cost is at the lowest. Data-driven model may predict whether an asset is close to a real breakdown, therefore helping to build more cost-efficient maintenance strategies. This paper focuses on survival analysis based predictive maintenance applied to the operation of Battery Electric Trucks (BET). Cox Proportional Hazards and Random Survival Forests methods are adopted for modelling time-to-failure and the associated survival functions. Detailed telematics data from BET vehicles in real operations are used for modelling and analysis. The model performance is further improved by the feature selection and hyperparameter tuning processes.