Wind turbine multi-fault detection based on SCADA data via an AutoEncoder
| Autor: | Ángel Encalada-Dávila, Christian Tutivén Gálvez, Bryan Puruncajas Maza, Yolanda Vidal Seguí |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió, Universitat Politècnica de Catalunya. Departament de Matemàtiques, Universitat Politècnica de Catalunya. CoDAlab - Control, Modelització, Identificació i Aplicacions |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Energia eòlica
AutoEncoder Renewable Energy Sustainability and the Environment Computer science Multi-Fault Detection Real-time computing Energy Engineering and Power Technology Normality Model Autoencoder Turbine Fault detection and isolation Aerogeneradors SCADA SCADA Data Wind Turbine Wind turbines Wind power Electrical and Electronic Engineering Enginyeria mecànica::Mecatrònica [Àrees temàtiques de la UPC] |
| Zdroj: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| Popis: | Nowadays, wind turbine fault detection strategies are settled as a meaningful pipeline to achieve required levels of efficiency, availability, and reliability, considering there is an increasing installation of this kind of machinery, both in onshore and offshore configuration. In this work, it has been applied a strategy that makes use of SCADA data with an increased sampling rate. The employed wind turbine in this study is based on an advanced benchmark, established by the National Renewable Energy Laboratory (NREL) of USA. Different types of faults on several actuators and sensed by certain installed sensors have been studied. The proposed strategy is based on a normality model by means of an autoencoder. As of this, faulty data are used for testing from which prediction errors were computed to detect if those raise a fault alert according to a defined metric which establishes a threshold on which a wind turbine works securely. The obtained results determine that the proposed strategy is successful since the model detects the considered three types of faults. Finally, even when prediction errors are small, the model is able to detect the faults without problems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|