In order to meet the mounting social and economic demands, railway operators and manufacturers are striving for a longer availability and a better reliability of railway transportation systems. Commercial trains are equipped with state-of-the-art onboard intelligent sensors monitoring various subsystems all over the train such as tilt, traction, signalling, pantograph, doors, etc. These sensors provide real-time flow of data, called floating train data, consisting of georeferenced events, along with their spatial and temporal coordinates. Once ordered with respect to time, these events can be considered as long temporal sequences which can be mined for valuable information. The aim is to implement these information into an on-line analysis process of the incoming event stream in order to predict the occurrence of infrequent target events, i.e. severe failures requiring immediate corrective maintenance actions. In this article, we tackle the above mentioned data mining task. We propose a methodology based on pattern recognition methods in order to predict rare tilt and traction failures in sequences using past events that are less critical. The results obtained on real datasets collected from a fleet of trains highlight the effectiveness of the proposed methodology.