58916 - Prediction of Gas Turbine Trip: A Novel Methodology Based on Random Forest Models 

Gas turbine trip is an unplanned shutdown, of which the most relevant consequences are business interruption and a reduction of equipment remaining useful life. Thus, understanding the underlying causes of gas turbine trip would allow predicting its occurrence in order to maximize profitability and improve availability of the gas turbine.

In the ever competitive Oil & Gas sector, data mining and machine learning are increasingly being employed to support a deeper insight and improved operation of gas turbines. Among the various machine learning tools, Random Forests are an ensemble learning method consisting of an aggregation of decision tree classifiers that address the scope of predicting gas turbine trip based on information gathered during a timeframe of historical data acquired from multiple sensors.

This paper presents a novel methodology aimed at exploiting information embedded in the data and develops Random Forest models. The novel approach exploits time series segmentation in order to increase the amount of training data, thus reducing overfitting.

First, data are transformed according to a feature engineering methodology developed in a previous work by the authors. Then, Random Forest models are trained and tested on unseen observations to demonstrate the benefits of the novel approach. The superiority of the novel approach is proved by considering two real-word case-studies, involving filed data taken during three years of operation on two fleets of Siemens gas turbines located in different regions.

The novel methodology allows values of Precision, Recall and Accuracy in the range 75 - 85 %, thus demonstrating the industrial feasibility of the predictive methodology.