Abstract

This paper investigates how to improve the performance of a classifier of tightening torque in bolted joints by applying transfer learning. The procedure uses vibration measurements to extract features and to train a classifier using a Gaussian mixture model (GMM). The key to enhancing the surrogate model for torque loss detection is considering the bolted joint structures with more qualitative and quantitative knowledge as the source domain, where labels are known and the classifier is trained. After applying a domain adaptation method, it is possible to reuse this trained classifier for a target domain, i.e., a set of different limited data of bolted joint structures with unknown labels. Four different bolted joint structures are analyzed. The new experimental tests adopt a wide range of torque in the bolts to extract the features with the respective labels under safe or unsafe tightening torque. All combinations of possible source or target domains are considered in the application to demonstrate whether the method can aid the detection of the loss of tightening torque, reducing the learning steps and the training sample. A guidance list is discussed based on this population-based structural health monitoring (SHM) of bolted joint structures.

References

1.
Kim
,
J.
,
Yoon
,
J.-C.
, and
Kang
,
B.-S.
,
2007
, “
Finite Element Analysis and Modeling of Structure With Bolted Joints
,”
Appl. Math. Modell.
,
31
(
5
), pp.
895
911
.10.1016/j.apm.2006.03.020
2.
Lacayo
,
R.
,
Pesaresi
,
L.
,
Gro
,
J.
,
Fochler
,
D.
,
Armand
,
J.
,
Salles
,
L.
,
Schwingshackl
,
C.
,
Allen
,
M.
, and
Brake
,
M.
,
2019
, “
Nonlinear Modeling of Structures With Bolted Joints: A Comparison of Two Approaches Based on a Time-Domain and Frequency-Domain Solver
,”
Mech. Syst. Signal Process.
,
114
, pp.
413
438
.10.1016/j.ymssp.2018.05.033
3.
Huang
,
J.
,
Liu
,
J.
,
Gong
,
H.
, and
Deng
,
X.
,
2022
, “
A Comprehensive Review of Loosening Detection Methods for Threaded Fasteners
,”
Mech. Syst. Signal Process.
,
168
, p.
108652
.10.1016/j.ymssp.2021.108652
4.
Kim
,
Y.-S.
, and
Na
,
W. S.
,
2022
, “
Development of a Portable Damage Detection System Based on Electromechanical Impedance Technique for Monitoring of Bolted Joint Structures
,”
J. Intell. Mater. Syst. Struct.
,
33
(
20
), pp.
2507
2519
.10.1177/1045389X221093331
5.
Ziaja
,
D.
, and
Nazarko
,
P.
,
2021
, “
SHM System for Anomaly Detection of Bolted Joints in Engineering Structures
,”
Structures
,
33
, pp.
3877
3884
.10.1016/j.istruc.2021.06.086
6.
Pal
,
J.
,
Sikdar
,
S.
, and
Banerjee
,
S.
,
2022
, “
A Deep-Learning Approach for Health Monitoring of a Steel Frame Structure With Bolted Connections
,”
Struct. Control Health Monit.
,
29
(
2
), p.
e2873
.10.1002/stc.2873
7.
Miguel
,
L. P.
,
Teloli
,
R. O.
,
da Silva
,
S.
, and
Chevallier
,
G.
,
2022
, “
Probabilistic Machine Learning for Detection of Tightening Torque in Bolted Joints
,”
Struct. Health Monit.
,
21
(
5
), pp.
2136
2151
.10.1177/14759217211054150
8.
Teloli
,
R. O.
,
Butaud
,
P.
,
Chevallier
,
G.
, and
da Silva
,
S.
,
2022
, “
Good Practices for Designing and Experimental Testing of Dynamically Excited Jointed Structures: The Orion Beam
,”
Mech. Syst. Signal Process.
,
163
, p.
108172
.10.1016/j.ymssp.2021.108172
9.
Gardner
,
P.
,
Liu
,
X.
, and
Worden
,
K.
,
2020
, “
On the Application of Domain Adaptation in Structural Health Monitoring
,”
Mech. Syst. Signal Process.
,
138
, p.
106550
.10.1016/j.ymssp.2019.106550
10.
Pan
,
S.
,
Tsang
,
I.
,
Kwok
,
J.
, and
Yang
,
Q.
,
2011
, “
Domain Adaptation Via Transfer Component Analysis
,”
IEEE Trans. Neural Networks
,
22
(
2
), pp.
199
210
.10.1109/TNN.2010.2091281
11.
Silva
,
S. D.
,
Yano
,
M. O.
, and
Gonsalez-Bueno
,
C. G.
,
2021
, “
Transfer Component Analysis for Compensation of Temperature Effects on the Impedance-Based Structural Health Monitoring
,”
J. Nondestr. Eval.
,
40
(
3
), p.
64
.10.1007/s10921-021-00794-6
12.
Figueiredo
,
E.
,
Omori
,
M.
,
da Silva
,
S.
,
Moldovan
,
I.
, and
Bud
,
M. A.
,
2023
, “
Transfer Learning to Enhance the Damage Detection Performance in Bridges When Using Numerical Models
,”
J. Bridge Eng.
,
28
(
1
), p.
04022134
.10.1061/(ASCE)BE.1943-5592.0001979
13.
Poole
,
J.
,
Gardner
,
P.
,
Dervilis
,
N.
,
Bull
,
L.
, and
Worden
,
K.
,
2023
, “
On Statistic Alignment for Domain Adaptation in Structural Health Monitoring
,”
Struct. Health Monit.
,
22
(
3
), pp.
1581
1600
.10.1177/14759217221110441
14.
Bull
,
L.
,
Gardner
,
P.
,
Dervilis
,
N.
,
Papatheou
,
E.
,
Haywood-Alexander
,
M.
,
Mills
,
R.
, and
Worden
,
K.
,
2021
, “
On the Transfer of Damage Detectors Between Structures: An Experimental Case Study
,”
J. Sound Vib.
,
501
, p.
116072
.10.1016/j.jsv.2021.116072
15.
Yano
,
M. O.
,
da Silva
,
S.
,
Figueiredo
,
E.
, and
Villani
,
L. G. G.
,
2022
, “
Damage Quantification Using Transfer Component Analysis Combined With Gaussian Process Regression
,”
Struct. Health Monit.
,
22
(
2
), pp.
1290
1307
.10.1177/14759217221094500
16.
Ritto
,
T.
,
Worden
,
K.
,
Wagg
,
D.
,
Rochinha
,
F.
, and
Gardner
,
P.
,
2022
, “
A Transfer Learning-Based Digital Twin for Detecting Localised Torsional Friction in Deviated Wells
,”
Mech. Syst. Signal Process.
,
173
, p.
109000
.10.1016/j.ymssp.2022.109000
17.
Grieves
,
M.
,
2014
, “
Digital Twin: Manufacturing Excellence Through Virtual Factory Replication
,”
White Paper
,
2014
, pp.
1
7
.https://scholar.google.com/citations?view_op=view_citation&hl=en&user=0gGMvgkAAAAJ&citation_for_view=0gGMvgkAAAAJ:KlAtU1dfN6UC
18.
Grieves
,
M.
, and
Vickers
,
J.
,
2017
, “
Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems
,”
Transdisciplinary Perspectives on Complex Systems
,
Springer
,
Cham, Switzerland
, pp.
85
113
.
19.
Ritto
,
T. G.
, and
Rochinha
,
F. A.
,
2021
, “
Digital Twin, Physics-Based Model, and Machine Learning Applied to Damage Detection in Structures
,”
Mech. Syst. Signal Process.
,
155
, p.
107614
.10.1016/j.ymssp.2021.107614
20.
Wagg
,
D.
,
Worden
,
K.
,
Barthorpe
,
R.
, and
Gardner
,
P.
,
2020
, “
Digital Twins: State-of-the-Art and Future Directions for Modelling and Simulation in Engineering Dynamics Applications
,”
ASME
Paper No. RISK-19-1039. 10.1115/RISK-19-1039
21.
Hughes
,
A.
,
Bull
,
L.
,
Gardner
,
P.
,
Dervilis
,
N.
, and
Worden
,
K.
,
2022
, “
On Robust Risk-Based Active-Learning Algorithms for Enhanced Decision Support
,”
Mech. Syst. Signal Process.
,
181
, p.
109502
.10.1016/j.ymssp.2022.109502
22.
Rojas-Mercedes
,
N.
,
Erazo
,
K.
, and
Di Sarno
,
L.
,
2022
, “
Seismic Fragility Curves for a Concrete Bridge Using Structural Health Monitoring and Digital Twins
,”
Earthquakes Struct.
,
22
(
5
), pp.
503
515
.
23.
Longman
,
R.
,
Xu
,
Y.
,
Sun
,
Q.
,
Turkan
,
Y.
, and
Riggio
,
M.
,
2023
, “
Digital Twin for Monitoring In-Service Performance of Post-Tensioned Self-Centering Cross-Laminated Timber Shear Walls
,”
J. Comput. Civ. Eng.
,
37
(
2
), p.
04022055
.10.1061/(ASCE)CP.1943-5487.0001050
24.
Teng
,
S.
,
Chen
,
X.
,
Chen
,
G.
, and
Cheng
,
L.
,
2023
, “
Structural Damage Detection Based on Transfer Learning Strategy Using Digital Twins of Bridges
,”
Mech. Syst. Signal Process.
,
191
, p.
110160
.10.1016/j.ymssp.2023.110160
25.
Gardner
,
P.
,
Bull
,
L.
,
Gosliga
,
J.
,
Dervilis
,
N.
, and
Worden
,
K.
,
2021
, “
Foundations of Population-Based SHM, Part III: Heterogeneous Populations—Mapping and Transfer
,”
Mech. Syst. Signal Process.
,
149
, p.
107142
.10.1016/j.ymssp.2020.107142
26.
Teloli
,
R. O.
,
Butaud
,
P.
,
Chevallier
,
G.
, and
da Silva
,
S.
,
2021
, “
Dataset of Experimental Measurements for the Orion Beam Structure
,”
Data Brief
,
39
, p.
107627
.10.1016/j.dib.2021.107627
27.
Ramasso
,
E.
,
Denœux
,
T.
, and
Chevallier
,
G.
,
2022
, “
Clustering Acoustic Emission Data Streams With Sequentially Appearing Clusters Using Mixture Models
,”
Mech. Syst. Signal Process.
,
181
, p.
109504
.10.1016/j.ymssp.2022.109504
28.
Yano
,
M. O.
,
Figueiredo
,
E.
,
da Silva
,
S.
, and
Cury
,
A.
,
2023
, “
Foundations of Transfer Learning for Structural Health Monitoring of Bridges
,”
Mech. Syst. Signal Process.
,
204
, p.
110766
.10.1016/j.ymssp.2023.110766
You do not currently have access to this content.