Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the hierarchical Bayesian modelling of frequency response functions (2307.06263v2)

Published 12 Jul 2023 in cs.LG, cs.SY, and eess.SY

Abstract: For situations that may benefit from information sharing among datasets, e.g., population-based SHM of similar structures, the hierarchical Bayesian approach provides a useful modelling structure. Hierarchical Bayesian models learn statistical distributions at the population (or parent) and the domain levels simultaneously, to bolster statistical strength among the parameters. As a result, variance is reduced among the parameter estimates, particularly when data are limited. In this paper, a combined probabilistic FRF model is developed for a small population of nominally-identical helicopter blades, using a hierarchical Bayesian structure, to support information transfer in the context of sparse data. The modelling approach is also demonstrated in a traditional SHM context, for a single helicopter blade exposed to varying temperatures, to show how the inclusion of physics-based knowledge can improve generalisation beyond the training data, in the context of scarce data. These models address critical challenges in SHM, by accommodating benign variations that present as differences in the underlying dynamics, while also considering (and utilising), the similarities among the domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Natural frequency measurements for production quality control of fibre composites, Composites 16 (1985) 23–27.
  2. W.D. Zhu, K. He, Detection of damage in space frame structures with L-shaped beams and bolted joints using changes in natural frequencies, J. Vib. Acoust. 135 (2013).
  3. M. Colakoglu, Effect of temperature on frequency and damping properties of polymer matrix composites, Adv. Compos. Mater. 17 (2008) 111–124.
  4. Elastic and damping properties from room temperature to 673 K in an AZ31 magnesium alloy, Scr. Mater. 51 (2004) 291–295.
  5. Experimental and simulation investigation of temperature effects on modal characteristics of composite honeycomb structure, Compos. Struct. 201 (2018) 816–827.
  6. Novelty detection in a changing environment: Regression and interpolation approaches, J. Sound Vib. 258 (2002) 741–761.
  7. H. Sohn, Effects of environmental and operational variability on structural health monitoring, Philos. Trans. A: Math. Phys. Eng. Sci. 365 (2007) 539–560.
  8. S. Alampalli, Influence of in-service environment on modal parameters, in: Proceedings of the 16th International Modal Analysis Conference (IMAC), Society for Experimental Mechanics, Santa Barbara, CA, USA, 1998.
  9. P. Cawley, Long range inspection of structures using low frequency ultrasound, in: Proceedings of the International Conference on Damage Assessment of Structures (DAMAS 97), Sheffield, UK, Sheffield Academic Press, June 30 - July 2, 1997, p. 1–17.
  10. Structural damage identification using damping: A compendium of uses and features, Smart Mater. Struct. 26 (2017) 043001.
  11. Critical design parameters and operating conditions of wireless sensor units for structural health monitoring, in: Proceedings of the 23rd International Modal Analysis Conference (IMAC), 2005.
  12. Wireless sensor networks for long-term structural health monitoring, Smart Struct. Syst. 6 (2010).
  13. Compressive sampling–based data loss recovery for wireless sensor networks used in civil structural health monitoring, Struct. Health Monit. 12 (2013) 78–95.
  14. Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights, Struct. Health Monit. 21 (2022) 1906–1955.
  15. J. Lynch, K. Loh, A summary review of wireless sensors and sensor networks for structural health monitoring, Shock Vibr. Dig. 38 (2006) 91–128.
  16. Issues in structural health monitoring employing smart sensors, Smart Struct. Syst. 3 (2007) 299–320.
  17. Foundations of population-based SHM, Part II: Heterogeneous populations–graphs, networks, and communities, Mech. Syst. Signal Process. 148 (2021) 107144.
  18. Foundations of population-based SHM, Part III: Heterogeneous populations–mapping and transfer, Mech. Syst. Signal Process. 149 (2021) 107142.
  19. Foundations of population-based SHM, Part I: Homogeneous populations and forms, Mech. Syst. Signal Process. 148 (2021) 107141.
  20. Overlapping mixtures of Gaussian processes for the data association problem, Pattern Recognit. 45 (2012) 1386–1395.
  21. Bayesian modelling of multivalued power curves from an operational wind farm, Mech. Syst. Signal Process. (2021) 108530.
  22. Modelling variability in vibration-based PBSHM via a generalised population form, J. Sound Vib. 538 (2022) 117227.
  23. Population-level modelling for truck fleet survival analysis, in: Proceedings of the 10th European Workshop on Structural Health Monitoring (EWSHM), Palermo, Italy, Springer, July 4-7, 2022.
  24. Hierarchical Bayesian modeling for knowledge transfer across engineering fleets via multitask learning, Comput.-Aided Civ. Inf. 38 (2023a) 821–848.
  25. Encoding domain expertise into multilevel models for source location, arXiv preprint arXiv:2305.08657 (2023b).
  26. Constraining Gaussian processes for physics-informed acoustic emission mapping, Mech. Syst. Signal Process. 188 (2023) 109984.
  27. Pruning deep convolutional neural networks for efficient edge computing in condition assessment of infrastructures, Comput.-Aided Civ. Inf. 34 (2019) 774–789.
  28. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete, Constr. Build. Mater. 186 (2018) 1031–1045.
  29. Y. Gao, K.M. Mosalam, Deep transfer learning for image-based structural damage recognition, Comput.-Aided Civ. Inf. 33 (2018) 748–768.
  30. Deep learning–based autonomous concrete crack evaluation through hybrid image scanning, Struct. Health Monit. 18 (2019) 1722–1737.
  31. Deep learning for detecting building defects using convolutional neural networks, Sensors 19 (2019).
  32. G. Michau, O. Fink, Domain adaptation for one-class classification: Monitoring the health of critical systems under limited information, Int. J. Progn. Health Manag. 10 (2019) 4.
  33. A. Ozdagli, X. Koutsoukos, Domain adaptation for structural health monitoring, in: Annual Conference of the PHM Society, volume 12, 2020, p. 9.
  34. Vector-valued control variates, arXiv preprint arXiv:2109.08944 (2021).
  35. H-P. Wan, Y-Q. Ni, Bayesian multi-task learning methodology for reconstruction of structural health monitoring data, Struct. Health Monit. 18 (2019) 1282–1309.
  36. A missing sensor measurement data reconstruction framework powered by multi-task Gaussian process regression for dam structural health monitoring systems, Measurement 186 (2021) 110085.
  37. Bayesian assessments of aeroengine performance with transfer learning, Data-Centric Eng. 3 (2022) e29.
  38. Bayesian hierarchical models for uncertainty quantification in structural dynamics, in: Vulnerability, Uncertainty, and Risk: Quantification, Mitigation, and Management, 2014, pp. 1615–1624.
  39. Hierarchical Bayesian model updating for structural identification, Mech. Syst. Signal Process. 64 (2015) 360–376.
  40. Y. Huang, J.L. Beck, Hierarchical sparse Bayesian learning for structural health monitoring with incomplete modal data, Int. J. Uncertain. Quantif. 5 (2015).
  41. Multitask sparse Bayesian learning with applications in structural health monitoring, Comput.-Aided Civ. Inf. 34 (2019) 732–754.
  42. Hierarchical Bayesian approach for model parameter updating in piezoelectric energy harvesters, Mech. Syst. Signal Process. 172 (2022) 108942.
  43. Decision-theoretic inspection planning using imperfect and incomplete data, Data-Centric Eng. 2 (2021).
  44. N. Papadimas, T. Dodwell, A hierarchical Bayesian approach for calibration of stochastic material models, Data-Centric Eng. 2 (2021).
  45. Anomaly detection in a fleet of industrial assets with hierarchical statistical modeling, Data-Centric Eng. 1 (2020) e21.
  46. On the integration of physics-based machine learning with hierarchical Bayesian modeling techniques, arXiv preprint arXiv:2303.00187 (2023).
  47. Dynamic analysis of modified composite helicopter blade, FME Transactions 40 (2012) 63–68.
  48. Investigating the effects of temperature variation in vibration-based SHM, in: Proceedings of the 30th International Conference on Noise and Vibration Engineering (ISMA), Leuven, Belgium, Springer, Sept. 12-14, 2022.
  49. M.D. Hoffman, A. Gelman, The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo., J. Mach. Learn. Res. 15 (2014) 1593–1623.
  50. M. Betancourt, M. Girolami, Hamiltonian Monte Carlo for hierarchical models, Current Trends in Bayesian Methodology with Applications 79 (2015) 2–4.
  51. A. Gelman, Prior distributions for variance parameters in hierarchical models 1 (2006) 515–533.
  52. Rank-normalization, folding, and localization: An improved R̂ for assessing convergence of MCMC (with discussion), Bayesian Analysis 16 (2021) 667–718.
  53. Exact post-selection inference, with application to the lasso, The Annals of Statistics 44 (2016) 907–927.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now