Cargando…

Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of...

Descripción completa

Detalles Bibliográficos
Autores principales: Rengasamy, Divish, Jafari, Mina, Rothwell, Benjamin, Chen, Xin, Figueredo, Grazziela P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7038523/
https://www.ncbi.nlm.nih.gov/pubmed/32012944
http://dx.doi.org/10.3390/s20030723
_version_ 1783500660053901312
author Rengasamy, Divish
Jafari, Mina
Rothwell, Benjamin
Chen, Xin
Figueredo, Grazziela P.
author_facet Rengasamy, Divish
Jafari, Mina
Rothwell, Benjamin
Chen, Xin
Figueredo, Grazziela P.
author_sort Rengasamy, Divish
collection PubMed
description Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.
format Online
Article
Text
id pubmed-7038523
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-70385232020-03-09 Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management Rengasamy, Divish Jafari, Mina Rothwell, Benjamin Chen, Xin Figueredo, Grazziela P. Sensors (Basel) Article Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions. MDPI 2020-01-28 /pmc/articles/PMC7038523/ /pubmed/32012944 http://dx.doi.org/10.3390/s20030723 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Rengasamy, Divish
Jafari, Mina
Rothwell, Benjamin
Chen, Xin
Figueredo, Grazziela P.
Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title_full Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title_fullStr Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title_full_unstemmed Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title_short Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management
title_sort deep learning with dynamically weighted loss function for sensor-based prognostics and health management
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7038523/
https://www.ncbi.nlm.nih.gov/pubmed/32012944
http://dx.doi.org/10.3390/s20030723
work_keys_str_mv AT rengasamydivish deeplearningwithdynamicallyweightedlossfunctionforsensorbasedprognosticsandhealthmanagement
AT jafarimina deeplearningwithdynamicallyweightedlossfunctionforsensorbasedprognosticsandhealthmanagement
AT rothwellbenjamin deeplearningwithdynamicallyweightedlossfunctionforsensorbasedprognosticsandhealthmanagement
AT chenxin deeplearningwithdynamicallyweightedlossfunctionforsensorbasedprognosticsandhealthmanagement
AT figueredograzzielap deeplearningwithdynamicallyweightedlossfunctionforsensorbasedprognosticsandhealthmanagement