A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples

Deep learning-based impact load identification technology for the next generation of large aircraft structures has garnered significant attention and has become one of the focal points in aircraft structural health monitoring. However, this technology relies on a large number of training samples and...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengbao Bai, Ji Yao, Chenhui Huang, Yuan Tian, Zhigang Xiong, Gang Chen, Hu Sun
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/10/3169
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126177381908480
author Shengbao Bai
Ji Yao
Chenhui Huang
Yuan Tian
Zhigang Xiong
Gang Chen
Hu Sun
author_facet Shengbao Bai
Ji Yao
Chenhui Huang
Yuan Tian
Zhigang Xiong
Gang Chen
Hu Sun
author_sort Shengbao Bai
collection DOAJ
description Deep learning-based impact load identification technology for the next generation of large aircraft structures has garnered significant attention and has become one of the focal points in aircraft structural health monitoring. However, this technology relies on a large number of training samples and exhibits poor scalability. One of the current challenges in system-level multi-structure monitoring is how to construct deep learning models with a small number or even zero impact training samples, and improve the models’ ability to migrate between different structures. To address this challenge, a novel method for impact load identification using only a small number of samples, based on a supervised scene adaptive model, is proposed. The performance of the model is validated on real aircraft structures. For large and complex structures, the model can be applied to other similar structural areas or different structural areas by using samples from the baseline area for training. Then, a very small number of calibration samples from the migrated area can be used for calibration. The results demonstrate that the proposed model, calibrated with just a single sample, achieves 97.22% accuracy in impact location identification and 99.44% accuracy in energy identification under similar regional structural conditions. Under different structural region conditions, the location identification accuracy of the proposed model is 87.65%, while the energy identification accuracy remains at 98.85%. The position identification accuracy of the model is 91.98% under different impact energy level conditions, and the identification accuracy remains at 87.04% even under varying impact energy levels and structural region conditions.
format Article
id doaj-art-d90d3352819f47549bbf5ef5f84de1ae
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-d90d3352819f47549bbf5ef5f84de1ae2025-08-20T02:33:58ZengMDPI AGSensors1424-82202025-05-012510316910.3390/s25103169A Supervised Scene Adaptive Model for Identifying Impact Load with Few SamplesShengbao Bai0Ji Yao1Chenhui Huang2Yuan Tian3Zhigang Xiong4Gang Chen5Hu Sun6National Key Laboratory of Structural Integrity, Aircraft Strength Research Institute of China, Xi’an 710065, ChinaNational Key Laboratory of Ship Structural Safety, China Ship Scientific Research Center, Wuxi 214082, ChinaSchool of Aerospace Engineering, Xiamen University, Xiamen 361005, ChinaNational Key Laboratory of Structural Integrity, Aircraft Strength Research Institute of China, Xi’an 710065, ChinaSchool of Aerospace Engineering, Xiamen University, Xiamen 361005, ChinaSchool of Aerospace Engineering, Xiamen University, Xiamen 361005, ChinaSchool of Aerospace Engineering, Xiamen University, Xiamen 361005, ChinaDeep learning-based impact load identification technology for the next generation of large aircraft structures has garnered significant attention and has become one of the focal points in aircraft structural health monitoring. However, this technology relies on a large number of training samples and exhibits poor scalability. One of the current challenges in system-level multi-structure monitoring is how to construct deep learning models with a small number or even zero impact training samples, and improve the models’ ability to migrate between different structures. To address this challenge, a novel method for impact load identification using only a small number of samples, based on a supervised scene adaptive model, is proposed. The performance of the model is validated on real aircraft structures. For large and complex structures, the model can be applied to other similar structural areas or different structural areas by using samples from the baseline area for training. Then, a very small number of calibration samples from the migrated area can be used for calibration. The results demonstrate that the proposed model, calibrated with just a single sample, achieves 97.22% accuracy in impact location identification and 99.44% accuracy in energy identification under similar regional structural conditions. Under different structural region conditions, the location identification accuracy of the proposed model is 87.65%, while the energy identification accuracy remains at 98.85%. The position identification accuracy of the model is 91.98% under different impact energy level conditions, and the identification accuracy remains at 87.04% even under varying impact energy levels and structural region conditions.https://www.mdpi.com/1424-8220/25/10/3169structural health monitoringimpact load detectiontransfer learningscene adaptivedeep learning
spellingShingle Shengbao Bai
Ji Yao
Chenhui Huang
Yuan Tian
Zhigang Xiong
Gang Chen
Hu Sun
A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
Sensors
structural health monitoring
impact load detection
transfer learning
scene adaptive
deep learning
title A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
title_full A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
title_fullStr A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
title_full_unstemmed A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
title_short A Supervised Scene Adaptive Model for Identifying Impact Load with Few Samples
title_sort supervised scene adaptive model for identifying impact load with few samples
topic structural health monitoring
impact load detection
transfer learning
scene adaptive
deep learning
url https://www.mdpi.com/1424-8220/25/10/3169
work_keys_str_mv AT shengbaobai asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT jiyao asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT chenhuihuang asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT yuantian asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT zhigangxiong asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT gangchen asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT husun asupervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT shengbaobai supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT jiyao supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT chenhuihuang supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT yuantian supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT zhigangxiong supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT gangchen supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples
AT husun supervisedsceneadaptivemodelforidentifyingimpactloadwithfewsamples