In the area of aircraft maintenance, it is vital to be able to predict airplane component or equipment failures and maintenance needs in order to reduce costly downtime, avoid unplanned out of service times, and to optimize service crew schedules. With over 1,000 airplanes to be maintained, Lufthansa had hundreds of thousands of log entries, sensor data, error messages, and maintenance reports that needed to be evaluated in order to accurately predict and prevent failures.
Lufthansa uses the RapidMiner Data Science Platform to offer predictive analytics services to their customers. Using RapidMiner’s real-time analytics of time series data, feature extraction, machine learning for regression, classification, and frequent item set mining, on the available airplane and service data, they were able to develop accurate models for predicting when maintenance should be performed.
