Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks

Structural health monitoring (SHM) is crucial for ensuring the safety and longevity of military training aircraft, which face demanding conditions such as high maneuverability, variable loads, and extreme environments, leading to structural fatigue. Traditional methods, such as modal analysis, often...

Full description

Saved in:
Bibliographic Details
Main Author: Tarek Berghout
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/13/3/179
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342418417090560
author Tarek Berghout
author_facet Tarek Berghout
author_sort Tarek Berghout
collection DOAJ
description Structural health monitoring (SHM) is crucial for ensuring the safety and longevity of military training aircraft, which face demanding conditions such as high maneuverability, variable loads, and extreme environments, leading to structural fatigue. Traditional methods, such as modal analysis, often struggle to handle the multivariate complexity of operational conditions and data variability. Recently, deep learning has emerged as a promising alternative to overcome these limitations. However, deep learning models typically operate in a unidirectional manner, where feedback to the inputs is often neglected. In contrast, biological neurons utilize feedback mechanisms to refine and adapt their responses in natural ecosystems, enabling adaptive learning and error correction. In this context, this study proposes an innovative Convolutional Neural Network with Reversed Mapping (CNN-RM) approach to SHM, which incorporates feedback loops and self-correcting mechanisms. Before feeding the data into CNN-RM, the dataset complexity is reduced through time-series-to-images Continuous Wavelet Transform (CWT), followed by a denoising CNN (DnCNN) to mitigate complex behavior under various conditions. For application, this study utilizes a massive dataset collected from multivariate sensors installed on a decommissioned military training aircraft previously used by the British Royal Air Force and now housed in a laboratory environment. The results revealed that the overall mean of classification metrics for the CNN is 0.9673 (training) and 0.9422 (testing), while for CNN-MR, it is 0.9764 (training) and 0.9515 (testing), showing an improvement of 0.94% in training and 1.00% in testing. These results highlight significant advancements in SHM, recommending the consideration of such learning mechanisms in neural learning models.
format Article
id doaj-art-ff52c45c6c7e43fda32b1859389a4abc
institution Kabale University
issn 2075-1702
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-ff52c45c6c7e43fda32b1859389a4abc2025-08-20T03:43:22ZengMDPI AGMachines2075-17022025-02-0113317910.3390/machines13030179Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural NetworksTarek Berghout0Laboratory of Automation and Manufacturing Engineering, Batna 2 University, Batna 05000, AlgeriaStructural health monitoring (SHM) is crucial for ensuring the safety and longevity of military training aircraft, which face demanding conditions such as high maneuverability, variable loads, and extreme environments, leading to structural fatigue. Traditional methods, such as modal analysis, often struggle to handle the multivariate complexity of operational conditions and data variability. Recently, deep learning has emerged as a promising alternative to overcome these limitations. However, deep learning models typically operate in a unidirectional manner, where feedback to the inputs is often neglected. In contrast, biological neurons utilize feedback mechanisms to refine and adapt their responses in natural ecosystems, enabling adaptive learning and error correction. In this context, this study proposes an innovative Convolutional Neural Network with Reversed Mapping (CNN-RM) approach to SHM, which incorporates feedback loops and self-correcting mechanisms. Before feeding the data into CNN-RM, the dataset complexity is reduced through time-series-to-images Continuous Wavelet Transform (CWT), followed by a denoising CNN (DnCNN) to mitigate complex behavior under various conditions. For application, this study utilizes a massive dataset collected from multivariate sensors installed on a decommissioned military training aircraft previously used by the British Royal Air Force and now housed in a laboratory environment. The results revealed that the overall mean of classification metrics for the CNN is 0.9673 (training) and 0.9422 (testing), while for CNN-MR, it is 0.9764 (training) and 0.9515 (testing), showing an improvement of 0.94% in training and 1.00% in testing. These results highlight significant advancements in SHM, recommending the consideration of such learning mechanisms in neural learning models.https://www.mdpi.com/2075-1702/13/3/179convolutional neural networksdeep learningfeedback correction mechanismmilitary training aircraftneural networksstructural health monitoring
spellingShingle Tarek Berghout
Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
Machines
convolutional neural networks
deep learning
feedback correction mechanism
military training aircraft
neural networks
structural health monitoring
title Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
title_full Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
title_fullStr Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
title_full_unstemmed Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
title_short Military Training Aircraft Structural Health Monitoring Leveraging an Innovative Biologically Inspired Feedback Mechanism for Neural Networks
title_sort military training aircraft structural health monitoring leveraging an innovative biologically inspired feedback mechanism for neural networks
topic convolutional neural networks
deep learning
feedback correction mechanism
military training aircraft
neural networks
structural health monitoring
url https://www.mdpi.com/2075-1702/13/3/179
work_keys_str_mv AT tarekberghout militarytrainingaircraftstructuralhealthmonitoringleveraginganinnovativebiologicallyinspiredfeedbackmechanismforneuralnetworks