Today, many industrial companies must face challenges raised by maintenance. In particular, the anomaly detection problem is probably one of the most investigated. In this paper we address anomaly detection in new train data by comparing them to a source of normal train behavior knowledge, expressed as sequential patterns. To this end, fuzzy logic allows our approach to be both finer and easier to interpret for experts. In order to show the quality of our approach, experiments have been conducted on real and simulated anomalies.