Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Matteo Cardoni, Danilo Pietro Pau, Laura Falaschetti, Claudio Turchetti, Marco Lattuada
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	anomaly detection binary quantization block-based processing echo state networks micro-controller online learning Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/752c8b673a104a1db2ba206ae45870f9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:752c8b673a104a1db2ba206ae45870f9
record_format	dspace
spelling	oai:doaj.org-article:752c8b673a104a1db2ba206ae45870f92021-11-25T17:25:13ZOnline Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir10.3390/electronics102228362079-9292https://doaj.org/article/752c8b673a104a1db2ba206ae45870f92021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2836https://doaj.org/toc/2079-9292The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimentation has been conducted using a STM32H743ZI2 MCU running at 480 MHz and the results achieved show an accurate identification of anomalies, with a reduced computational cost per image and memory occupancy. Based on the obtained results, we conclude that BBS-ESN is feasible on off-the-shelf 32 bit MCUs. Moreover, the solution is also scalable in the number of image cameras to be deployed and to achieve accurate and fast oil leak detections from different viewpoints.Matteo CardoniDanilo Pietro PauLaura FalaschettiClaudio TurchettiMarco LattuadaMDPI AGarticleanomaly detectionbinary quantizationblock-based processingecho state networksmicro-controlleronline learningElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2836, p 2836 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	anomaly detection binary quantization block-based processing echo state networks micro-controller online learning Electronics TK7800-8360
spellingShingle	anomaly detection binary quantization block-based processing echo state networks micro-controller online learning Electronics TK7800-8360 Matteo Cardoni Danilo Pietro Pau Laura Falaschetti Claudio Turchetti Marco Lattuada Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
description	The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimentation has been conducted using a STM32H743ZI2 MCU running at 480 MHz and the results achieved show an accurate identification of anomalies, with a reduced computational cost per image and memory occupancy. Based on the obtained results, we conclude that BBS-ESN is feasible on off-the-shelf 32 bit MCUs. Moreover, the solution is also scalable in the number of image cameras to be deployed and to achieve accurate and fast oil leak detections from different viewpoints.
format	article
author	Matteo Cardoni Danilo Pietro Pau Laura Falaschetti Claudio Turchetti Marco Lattuada
author_facet	Matteo Cardoni Danilo Pietro Pau Laura Falaschetti Claudio Turchetti Marco Lattuada
author_sort	Matteo Cardoni
title	Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
title_short	Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
title_full	Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
title_fullStr	Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
title_full_unstemmed	Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir
title_sort	online learning of oil leak anomalies in wind turbines with block-based binary reservoir
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/752c8b673a104a1db2ba206ae45870f9
work_keys_str_mv	AT matteocardoni onlinelearningofoilleakanomaliesinwindturbineswithblockbasedbinaryreservoir AT danilopietropau onlinelearningofoilleakanomaliesinwindturbineswithblockbasedbinaryreservoir AT laurafalaschetti onlinelearningofoilleakanomaliesinwindturbineswithblockbasedbinaryreservoir AT claudioturchetti onlinelearningofoilleakanomaliesinwindturbineswithblockbasedbinaryreservoir AT marcolattuada onlinelearningofoilleakanomaliesinwindturbineswithblockbasedbinaryreservoir
_version_	1718412357033525248

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

Ejemplares similares