Structural Health Monitoring & Machine Learning, Vol. 12

Front Cover	1
Conference Proceedings of the Society for Experimental Mechanics Series	2
Preface	6
Contents	8
Theoretical Foundations and Practical Applications of Damage Detection Using Autocovariance Functions	10
Introduction	10
Autocovariance Functions for Damage Detection	11
Damage Detection Algorithm	12
Numerical Experiment	13
Conclusion	17
On the Real Time Tightness Measurement of Complex Shaped Flanges	20
Introduction	20
Brief Outline of the Theory	21
Numerical Example	21
Results	23
Comments on the Measurability of the Strains	24
Comments on the Sensitivity to Noisy Data	24
Comments on the Real-Time Capability	24
Conclusion	24
Parameter Rejection in Sensitivity-based Model Updating using Output Feedback Eigenstructure Assignment	26
Introduction	26
Background Theory and Problem Statement	27
Eigenstructure Assignment for Parameter Rejection	27
Implementation of the Scheme	29
Numerical Example	29
Closing Remarks	30
Structural Health Monitoring of a Ferry Quay: Instrumentation and Impact of Tidal Levels on Modal Parameters	32
Introduction	32
The Magerholm Research Quay	33
Analysis of the Time Histories	35
Tital Level Variations and Modal Analysis	36
Correlation between Tidal Levels and Natural Frequency	37
Conclusions	39
Outcomes from Field Measurements on the Magerholm Ferry Quay: System Identification, Finite Element Model Updating and Sensitivity Analysis	42
Introduction	42
Field measurement	43
Magerholm Ferry Dock	43
Field Measurement Setup	44
System Identification	44
Modal Analysis	44
Finite Element Model Updating	45
Finite Element Model	45
Model Updating Methodology	46
Updating Parameters	47
Results	48
Sensitivity Analysis of Lifting Towers	49
A Robust Data-Driven Algorithm for Early Damage Detection in Structural Health Monitoring	52
Introduction	52
Background	53
Principal Component Analysis	53
Independent Component Analysis	54
Overview and Description of the Technique	55
Analysis	56
Case Study: A Randomly Excited Cylindrical Pipe	56
Results and Discussion	57
Conclusion	58
Real-Time Structural Health Assessment of a Tension Rod Assembly Using Machine Learning	60
Introduction	60
Methodology	61
CNN Architecture	62
Test Structure	62
Training Procedure	62
Structural Health Estimation	63
Results and discussions	64
Conclusions	65
Multi-Bridge Indirect Structural Health Monitoring: Leveraging Big Data and Drive-By Crowdsensing Techniques	68
Introduction	68
Numerical Simulations	69
Analysis	69
Signal-Level comparison and correlation coefficient calculation	69
System-wide cross-comparison and separation factor calculation	70
Relative damage index and threshold calculation	70
Results and Discussions	70
Percentage difference matrices	70
RDI and TRDI results	72
Conclusion	74
A Comparative Study of Feature Selection Methods for Wind Turbine Gearbox Bearing Fault Prognosis	76
Introduction	76
Methodology	77
Data preprocessing	77
Normal Behavior Model Development	78
Testing the NBMs and Gearbox Bearing Fault Prognosis	78
Results and Discussion	78
Conclusions	80
Damage Identification on Gear Drivetrains Using Neural Networks Trained by High-Fidelity Multibody Simulation Data	82
Introduction	82
Background	83
Analysis	86
Conclusion	91
Advanced Condition Monitoring framework for CFRP Gear Drivetrains Using Machine Learning and Multibody Dynamics Simulations	94
Introduction	94
Background	95
Analysis	98
Conclusion	102
On the use of Statistical Learning Theory for model selection in Structural Health Monitoring	104
Introduction	104
The Model-Selection Problem	104
Managing Complexity and Minimisation of Structural Risk	106
Case Study: Model Selection for Modelling a Sdof Impulse Response	107
Predictors for the Regression Problem	108
Model Selection Strategy	108
Results and Discussion	109
Conclusion	111
Full-field Measurements for Anomaly Detection of Mechanical Systems using Convolutional Neural Networks and LSTM Networks	114
Introduction	114
Background	115
Experimental Setup	116
Analysis and Results	118
Conclusion	119
A Generative Modeling Approach for the Translation of Operational Variables to Short-term Vibrations	122
Introduction	122
Methodology	123
Conclusions	130
Effective Structural Health Monitoring of Rotating Propellers using Asynchronous Neuromorphic Tracking	132
Introduction	132
Methodology	133
Analysis	135
Data acquisition and processing	136
Analysis of results	137
Conclusion	137
Estimating Damage Detection of an Aircraft Component with Machine Learning Models	140
Introduction	140
Methodology	141
Experimental Setup	141
Experimental Results	142
Non-Destructive Cases	142
Destructive Cases	143
Limitations	144
Conclusion	144
Physics-Informed Machine Learning for Advanced Structural Damage Detection and Localization	146
Introduction	146
Methodology	147
Numerical Study: ASCE Benchmark Models	147
Experimental Study: ASCE Benchmark Structure	149
Conclusion	150
Damage Detection Strategy Based on PCA/Mode-Shapes Developed on a Laboratory Truss Girder Subjected to Environmental Variations	152
Introduction	152
Benchmark and Experimental Setup	153
Feature Extraction	153
Damage Index Evaluation and Results	155
Conclusion	156

RkJQdWJsaXNoZXIy MTMzNzEzMQ==