# Wind turbine database for intelligent operation and maintenance strategies

## TL;DR

This paper introduces a 3-year database from five wind turbines to help develop smart maintenance strategies by analyzing sensor data and detecting malfunctions.

## Contribution

The paper presents a freely accessible, multi-year wind turbine database with sensor data and tools for intelligent maintenance analysis.

## Key findings

- The database includes 312 sensor variables with statistical summaries and alarm events.
- A normality modeling approach using gearbox variables can detect rotor malfunctions.
- Functions for downloading subsets of the database are available in multiple programming languages.

## Abstract

With the aim of helping researchers to develop intelligent operation and maintenance strategies, in this manuscript, an extensive 3-years Supervisory Control and Data Acquisition database of five Fuhrländer FL2500 2.5 MW wind turbines is presented. The database contains 312 analogous variables recorded at 5-minute intervals, from 78 different sensors. The reported values for each sensor are minimum, maximum, mean, and standard deviation. The database also contains the alarm events, indicating the system and subsystem and a small description. Finally, a set of functions to download specific subsets of the whole database is freely available in Matlab, R, and Python. To demonstrate the usefulness of this database, an illustrative example is given. In this example, different gearbox variables are selected to estimate a target variable to detect whether or not the estimate differs from the actual value provided for the sensor. By using this normality modelling approach, it is possible to detect rotor malfunction when the estimate differs from the actual measured value.