Fault diagnosis of wind turbine structures using decision tree learning algorithms with big data

• Published in: Safety and Reliability - Safe Societies in a Changing World pp. 3053 - 3061
• Main Authors: Abdallah, I., Dertimanis, V., Mylonas, H., Tatsis, K., Chatzi, E., Dervili, N., Worden, K., Maguire, E.
• Format: Book Chapter
• Language: English
• Published: CRC Press 2018
• Edition: 1
• Subjects: Fault Diagnostics; CHAID; Cyber Physical Systems; BN; Cart Algorithm; Decision Tree Algorithms; SHM; Leaf Nodes; Sequential Trace; Diagnostics Framework; SCADA Data; Decision Tree Learning; Split Criterion; Fact; Impurity Index; Bagged Decision Tree; Gini Impurity; Minimal Cut Sets; Decision Tree Learning Algorithm; Dt; Reliability Blocks Diagrams; WTs; Sprint; Decision Tree Classifiers; Maximum Generator Speed
• ISBN: 0815386826; 9780815386827
• DOI: 10.1201/9781351174664-382

In the context of Operation and Maintenance of wind energy infrastructure, it is important to develop decision support tools, able to guide engineers in the management of these assets. This task is particularly challenging given the multiplicity of uncertainties involved, from the point of view of the aggregated data, the available knowledge with respect to the wind turbine structures, as well as the varying operational and environmental loads. We propose to propagate wind turbine telemetry through a decision tree learning algorithm to detect faults, damage, and abnormal operations. The use of decision trees is motivated by the fact that they tend to be easier to implement and interpret than other quantitative data-driven methods. Furthermore, the telemetry consists of data from condition and structural health monitoring systems, which lends itself nicely in the field of Big Data as large amounts are continuously sampled at high rate from thousands of wind turbines. In this paper, we review several decision tree algorithms, we then train an ensemble Bagged decision tree classifier on a dataset from an offshore wind farm comprising 48 wind turbines, and use it to automatically extract paths linking excessive vibrations faults to their possible root causes. We finally give an outlook of a cloud computing based architecture to implement decision tree learning involving Apache Hadoop and Spark. This chapter proposes to perform automated fault diagnostics and root cause analysis of faults on wind turbines (WTs) on the basis of decision tree classifiers. It revisits the decision tree learning theory and trains an ensemble of bagged decision tree classifiers with the standard CART algorithm on a condition monitoring data set from the Lillgrund offshore wind farm comprising 48 wind turbines and use it to perform a diagnostics to elucidate the root cause of excessive vibrations. The chapter shows how decision tree learning can be expanded to big data based applications for monitoring and diagnostics for wind turbines using the object-oriented based decision tree concept cite. It highlights the need for cloud based storage and computing, and an innovative approach based on object-oriented decision tree learning that extends the traditional decision tree classifier concept. In the future, more concrete implementations and results of the proposed framework will be disseminated.