journal article·2023-04-06Open access

Framework for Identification and Prediction of Corrosion Degradation in a Steel Column through Machine Learning and Bayesian Updating

Simone Castelli, Andrea Belleri

Applied Sciences· Volume 13· Issue 7

Abstract

In recent years, structural health monitoring, starting from accelerometric data, is a method which has become widely adopted. Among the available techniques, machine learning is one of the most innovative and promising, supported by the continuously increasing computational capacity of current computers. The present work investigates the potential benefits of a framework based on supervised learning suitable for quantifying the corroded thickness of a structural system, herein uniformly applied to a reference steel column. The envisaged framework follows a hybrid approach where the training data are generated from a parametric and stochastic finite element model. The learning activity is performed by a support vector machine with Bayesian optimization of the hyperparameters, in which a penalty matrix is introduced to minimize the probability of missed alarms. Then, the estimated structural health conditions are used to update an exponential degradation model with random coefficients suitable for providing a prediction of the remaining useful life of the simulated corroded column. The results obtained show the potentiality of the proposed framework and its possible future extension for different types of damage and structural types.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Concrete Corrosion and Durability · Structural Health Monitoring Techniques · Infrastructure Maintenance and Monitoring

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Engineering and Applied Sciences, University of Bergamo, Viale Marconi 5, 24044 Dalmine, Italy

References (49)

Show source-provided references
1. Farrar, C., and Worden, K. (2012). Structural Health Monitoring: A Machine Learning Perspective, John Wiley & Sons.10.1002/9781118443118 ↗
2. Damage detection using outlier analysis10.1006/jsvi.1999.2514 ↗
3. Machine Learning algoritms for damage detection under operational and environmental variability10.1177/1475921710388971 ↗
4. A machine learning framework for assessing post–earthquake structural safety10.1016/j.strusafe.2017.12.001 ↗
5. Real–time vibration based structural damage detection using one–dimensional convolution neurla network10.1016/j.jsv.2016.10.043 ↗
6. Damage detection method using support vector machine and first three natural frequencies for shear structures
7. Quantitative damage diagnosis of shear structures using support vector machine
8. Data–driven support vector machine with optimization techniques for structural health monitoring and damage detection
9. Nonlinear multiclass support vector machine–based health monitoring system for buildings employing magnetorheological dampers10.1177/1045389X13507343 ↗
10. Structural health monitoring with autoregressive support vector machine10.1115/1.3025827 ↗
11. Wavelet–based AR–SVM for health monitoring of smart structures10.1088/0964-1726/22/1/015003 ↗
12. A data framework for near reall–time and robust damage diagnosis of building structures
13. Momeni, M., Bedon, C., Hadianfard, M.A., and Baghalani, A. (2021). An Efficient Reliability–Based Approch for Evaluation Safe Scaled Distance of Steel Columns under Dynamic Blast Loads. Buildings, 11.10.3390/buildings11120606 ↗
14. Damage evaluation of H–section steel columns under impulsive blast loads via gene expression programming10.1016/j.engstruct.2020.110909 ↗
15. Vibration–based Structural Damage Identification under Varying Temperature Effects10.1061/(ASCE)AS.1943-5525.0000829 ↗
16. Damage identificaiton of Bridge Structures Considering Temperature Variations–Based SVM and MFO10.1061/(ASCE)AS.1943-5525.0001225 ↗
17. Bayesian damage identification based on autoregressive model and MH–PSO hybrid MCMC sampling method10.1007/s13349-021-00541-5 ↗
18. A Novel Method for Damage Identification Based on Tuning–Free Strategy and Simple Population Metropolis–Hasting Algorithm10.1142/S0219455423500438 ↗
19. Value of information from vibration–based structural health monitoring extracted via Bayesian model updating10.1016/j.ymssp.2021.108465 ↗
20. Fusing damage–sensitive features and domain adaptation towards robust damage classification in real buildings10.1016/j.soildyn.2022.107739 ↗
21. A transfer learning SHM strategy for bridges enriched by the use of speaker recognition x–vectors10.1007/s13349-022-00591-3 ↗
22. Structural damage detection and localization using decision tree ensemble and vibration data10.1111/mice.12633 ↗
23. Structural damage assessment through a new generalized autoencoder with features in the quefrency domain10.1016/j.ymssp.2022.109713 ↗
24. Castelli, S., Belleri, A., and Riva, P. (July, January 30). Machine Learning technique for the diagnosis of environmental degradation in a steel structure. Proceedings of the SHMII 2021: 10th International Conference on Structural Health Monitoring of Intelligent Infrastructure, Porto, Portugal.
25. Mathworks (2020). Mathworks.
26. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Element of Statistical Learning: Data Minimg, Inference, and Prediction, Springer.10.1007/978-0-387-84858-7 ↗
27. Crisitanini, N., and Shawe–Taylor, J. (2000). An Introduction to Support Vector Machines and Other Kernel–Based Learning Methods, Cambridge University Press.10.1017/CBO9780511801389 ↗
28. Working set selection using second order information for training support vector machines
29. A reflective newton method for minimizing a quadratic function subject to bounds on some of the variables10.1137/S1052623494240456 ↗
30. Gill, P.E., Murray, W., and Wright, M.H. (2019). Pratical Optimisation, SIAM.10.1137/1.9781611975604 ↗
31. Kecman, V., Huang, T.M., and Vogt, M. (2005). Support Vector Machines: Theory and Applications, Springer.10.1007/10984697_1 ↗
32. Preprocessing for quadratic programming10.1007/s10107-003-0487-2 ↗
33. OpenSees: A Framework for Earthquake Engineering Simulation10.1109/MCSE.2011.66 ↗
34. Modal identification of output–only systems using frequency domain decomposition10.1088/0964-1726/10/3/303 ↗
35. Gelbart, M.A., Snoek, J., and Adams, P. (2014). Bayesian optimization with unknown constraints. arXiv.
36. Gaussian processes in machine learning
37. Nocedal, J., and Wright, S. (2006). Numerical optimization., Springer Science & Business Media.
38. Convergence properties of the nelder–mead simplex method in low dimensions10.1137/S1052623496303470 ↗
39. Snock, J., Larochelle, H., and Adams, R.P. (2012). Advances in Neural Information Processing Systems, MIT Press.
40. Convergence rates of efficient global optimization algorithms
41. Residual–life estimation for components with non–symmetric priors10.1080/07408170802369409 ↗
42. Residual–life distributions from component degradation signals: A bayesian approach10.1080/07408170590929018 ↗
43. Using degradation measures to estimate a time–to–failure distribution10.1080/00401706.1993.10485038 ↗
44. A model to determine the optimal critical level and the monitoring intervals in condition–based maintenance10.1080/002075400188933 ↗
45. Nelson, W. (1990). Accelerated Testing Statistical Models, Test Plans and Data Anlysis, Wiley.10.1002/9780470316795 ↗
46. Prognosis of remaining bearing life using neural networks
47. Bernstein reliability model: Derivation and estimation of parameters10.1016/0143-8174(84)90020-9 ↗
48. Sensory–updated residual life distributions for components with exponential degradation patterns10.1109/TASE.2006.876609 ↗
49. Pedeferri, P. (2010). Corrosione e Protezione Dei Materiali Metallici, Polipress. (In Italian).