Abstract
In this work, the sensor data from a gas turbine system is analyzed with the objective of failure modeling and prediction. Several maintenance incidents were recorded by the sensor system in two separate vehicles. Two approaches to selecting training data were used in the analysis. The first followed a traditional method of randomly selecting a certain percentage of data points to include in training. The second data selection strategy was to select certain incidents to include in training, with the remaining incidents unseen for testing. Using classifier and anomaly detection techniques, models of the system using 76 predictor variables were trained to distinguish between healthy and failed system states in a two-class problem. Significant differences in performance results were noted depending on the selection of data included in training. A rule-based classifier model was then applied to leverage the predictions from both the classifier and anomaly detection models yielding promising results. The construction of an ensemble model was an effective way to mitigate the challenges presented in the training strategies, where a single individual model would not succeed in both scenarios. The simplification of the system into two states could be regarded as restrictive when the `healthiness' of a system is nuanced; however, despite this simplification, good performance and accurate predictions could still be achieved.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have