Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study
Structural health monitoring (SHM) is a promising technique for in-service inspection of technical structures in a broad field of applications in order to reduce maintenance efforts as well as the overall structural weight. SHM is basically an inverse problem deriving physical properties such as dam...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/10/3/34 |
| _version_ | 1797540918477193216 |
|---|---|
| author | Stefan Bosse Dennis Weiss Daniel Schmidt |
| author_facet | Stefan Bosse Dennis Weiss Daniel Schmidt |
| author_sort | Stefan Bosse |
| collection | DOAJ |
| description | Structural health monitoring (SHM) is a promising technique for in-service inspection of technical structures in a broad field of applications in order to reduce maintenance efforts as well as the overall structural weight. SHM is basically an inverse problem deriving physical properties such as damages or material inhomogeneity (target features) from sensor data. Often models defining the relationship between predictable features and sensors are required but not available. The main objective of this work is the investigation of model-free distributed machine learning (DML) for damage diagnostics under resource and failure constraints by using multi-instance ensemble and model fusion strategies and featuring improved scaling and stability compared with centralised single-instance approaches. The diagnostic system delivers two features: A binary damage classification (damaged or non-damaged) and an estimation of the spatial damage position in case of a damaged structure. The proposed damage diagnostics architecture should be able to be used in low-resource sensor networks with soft real-time capabilities. Two different machine learning methodologies and architectures are evaluated and compared posing low- and high-resolution sensor processing for low- and high-resolution damage diagnostics, i.e., a dedicated supervised trained low-resource and an unsupervised trained high-resource deep learning approach, respectively. In both architectures state-based recurrent artificial neural networks are used that process spatially and time-resolved sensor data from experimental ultrasonic guided wave measurements of a hybrid material (carbon fibre laminate) plate with pseudo defects. Finally, both architectures can be fused to a hybrid architecture with improved damage detection accuracy and reliability. An extensive evaluation of the damage prediction by both systems shows high reliability and accuracy of damage detection and localisation, even by the distributed multi-instance architecture with a resolution in the order of the sensor distance. |
| first_indexed | 2024-03-10T13:07:54Z |
| format | Article |
| id | doaj.art-9106567ef46f4e52bd50889a5dace4ba |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T13:07:54Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-9106567ef46f4e52bd50889a5dace4ba2023-11-21T10:58:12ZengMDPI AGComputers2073-431X2021-03-011033410.3390/computers10030034Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison StudyStefan Bosse0Dennis Weiss1Daniel Schmidt2Department Mathematics & Computer Science, University of Bremen, 28359 Bremen, GermanyDepartment Mathematics & Computer Science, University of Bremen, 28359 Bremen, GermanyGerman Aerospace Center (DLR e. V.), Institute of Composite Structures and Adaptive Systems, 38108 Braunschweig, GermanyStructural health monitoring (SHM) is a promising technique for in-service inspection of technical structures in a broad field of applications in order to reduce maintenance efforts as well as the overall structural weight. SHM is basically an inverse problem deriving physical properties such as damages or material inhomogeneity (target features) from sensor data. Often models defining the relationship between predictable features and sensors are required but not available. The main objective of this work is the investigation of model-free distributed machine learning (DML) for damage diagnostics under resource and failure constraints by using multi-instance ensemble and model fusion strategies and featuring improved scaling and stability compared with centralised single-instance approaches. The diagnostic system delivers two features: A binary damage classification (damaged or non-damaged) and an estimation of the spatial damage position in case of a damaged structure. The proposed damage diagnostics architecture should be able to be used in low-resource sensor networks with soft real-time capabilities. Two different machine learning methodologies and architectures are evaluated and compared posing low- and high-resolution sensor processing for low- and high-resolution damage diagnostics, i.e., a dedicated supervised trained low-resource and an unsupervised trained high-resource deep learning approach, respectively. In both architectures state-based recurrent artificial neural networks are used that process spatially and time-resolved sensor data from experimental ultrasonic guided wave measurements of a hybrid material (carbon fibre laminate) plate with pseudo defects. Finally, both architectures can be fused to a hybrid architecture with improved damage detection accuracy and reliability. An extensive evaluation of the damage prediction by both systems shows high reliability and accuracy of damage detection and localisation, even by the distributed multi-instance architecture with a resolution in the order of the sensor distance.https://www.mdpi.com/2073-431X/10/3/34structural health monitoringdistributed sensor networksdistributed machine learningmodel fusionautoencoder learning |
| spellingShingle | Stefan Bosse Dennis Weiss Daniel Schmidt Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study Computers structural health monitoring distributed sensor networks distributed machine learning model fusion autoencoder learning |
| title | Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study |
| title_full | Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study |
| title_fullStr | Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study |
| title_full_unstemmed | Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study |
| title_short | Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study |
| title_sort | supervised distributed multi instance and unsupervised single instance autoencoder machine learning for damage diagnostics with high dimensional data a hybrid approach and comparison study |
| topic | structural health monitoring distributed sensor networks distributed machine learning model fusion autoencoder learning |
| url | https://www.mdpi.com/2073-431X/10/3/34 |
| work_keys_str_mv | AT stefanbosse superviseddistributedmultiinstanceandunsupervisedsingleinstanceautoencodermachinelearningfordamagediagnosticswithhighdimensionaldataahybridapproachandcomparisonstudy AT dennisweiss superviseddistributedmultiinstanceandunsupervisedsingleinstanceautoencodermachinelearningfordamagediagnosticswithhighdimensionaldataahybridapproachandcomparisonstudy AT danielschmidt superviseddistributedmultiinstanceandunsupervisedsingleinstanceautoencodermachinelearningfordamagediagnosticswithhighdimensionaldataahybridapproachandcomparisonstudy |