Cargando…

Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data

Renewable energy sources are a growing branch of industry. One such source is wind farms, which have significantly increased their number over recent years. Alongside the increased number of turbines, maintenance problems are growing. There is a need for newer and less intrusive predictive maintenan...

Descripción completa

Detalles Bibliográficos
Autores principales: Knap, Paweł, Lalik, Krzysztof, Bałazy, Patryk
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181244/
https://www.ncbi.nlm.nih.gov/pubmed/37177504
http://dx.doi.org/10.3390/s23094295
_version_ 1785041528155013120
author Knap, Paweł
Lalik, Krzysztof
Bałazy, Patryk
author_facet Knap, Paweł
Lalik, Krzysztof
Bałazy, Patryk
author_sort Knap, Paweł
collection PubMed
description Renewable energy sources are a growing branch of industry. One such source is wind farms, which have significantly increased their number over recent years. Alongside the increased number of turbines, maintenance problems are growing. There is a need for newer and less intrusive predictive maintenance methods. About 40% of all turbine failures are due to bearing failure. This paper presents a modified neural direct classifier method using raw accelerometer measurements as input. This proprietary platform allows for better damage prediction results than convolutional networks in vibration spectrum image analysis. It operates in real time and without signal processing methods converting the signal to a time–frequency spectrogram. Image processing methods can extract features from a set of preset features and based on their importance. The proposed method is not based on feature extraction from image data but on automatically finding a set of features from raw tabular data. This fact significantly reduces the computational cost of detection and improves the failure detection accuracy compared to the classical methods. The model achieved a precision of 99.32% on the validation set, and 96.3% during bench testing. These results were an improvement over the method that classifies time–frequency spectrograms of 97.76% for the validation set and 90.8% for the real-world tests, respectively.
format Online
Article
Text
id pubmed-10181244
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101812442023-05-13 Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data Knap, Paweł Lalik, Krzysztof Bałazy, Patryk Sensors (Basel) Article Renewable energy sources are a growing branch of industry. One such source is wind farms, which have significantly increased their number over recent years. Alongside the increased number of turbines, maintenance problems are growing. There is a need for newer and less intrusive predictive maintenance methods. About 40% of all turbine failures are due to bearing failure. This paper presents a modified neural direct classifier method using raw accelerometer measurements as input. This proprietary platform allows for better damage prediction results than convolutional networks in vibration spectrum image analysis. It operates in real time and without signal processing methods converting the signal to a time–frequency spectrogram. Image processing methods can extract features from a set of preset features and based on their importance. The proposed method is not based on feature extraction from image data but on automatically finding a set of features from raw tabular data. This fact significantly reduces the computational cost of detection and improves the failure detection accuracy compared to the classical methods. The model achieved a precision of 99.32% on the validation set, and 96.3% during bench testing. These results were an improvement over the method that classifies time–frequency spectrograms of 97.76% for the validation set and 90.8% for the real-world tests, respectively. MDPI 2023-04-26 /pmc/articles/PMC10181244/ /pubmed/37177504 http://dx.doi.org/10.3390/s23094295 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Knap, Paweł
Lalik, Krzysztof
Bałazy, Patryk
Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title_full Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title_fullStr Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title_full_unstemmed Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title_short Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data
title_sort boosted convolutional neural network algorithm for the classification of the bearing fault form 1-d raw sensor data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181244/
https://www.ncbi.nlm.nih.gov/pubmed/37177504
http://dx.doi.org/10.3390/s23094295
work_keys_str_mv AT knappaweł boostedconvolutionalneuralnetworkalgorithmfortheclassificationofthebearingfaultform1drawsensordata
AT lalikkrzysztof boostedconvolutionalneuralnetworkalgorithmfortheclassificationofthebearingfaultform1drawsensordata
AT bałazypatryk boostedconvolutionalneuralnetworkalgorithmfortheclassificationofthebearingfaultform1drawsensordata