Structural health monitoring (SHM) based on artificial neural networks (ANN) has received a lot of attention in recent decades, especially the Bayesian neural network (BNN) approach, which is more robust to noise for training and generalization. Since building a high-quality BNN architecture suitable for a specific task depends highly on user experience, the existing literature generally studies BNNs with simple single-hidden-layer architectures designed by empirical formulas or very few tailor-made algorithms. Multiple hidden layer BNN (MBNN) has a more complex architecture than single hidden layer BNN (SBNN) and is expected to achieve better generalization performance for complex problems. But the corresponding architectural design problem is much more complex, and there is no previous experience in the literature. To achieve this for MBNN, this paper proposes two feasible algorithms to optimize the number of neurons in each hidden layer simultaneously, where a logarithmic evidence metric is introduced to quantitatively characterize the performance of MBNN for a given multi-hidden-layer architecture. The feasibility and effectiveness of the proposed method are verified by the finite element (FE) model updating of both a planar truss model and a real-life pedestrian bridge. The verification results show that the second algorithm is much more computationally efficient for the optimal design of the MBNN architecture and has the potential for practical application.
AlkayemNFCaoMZhangY, et al. (2018) Structural damage detection using finite element model updating with evolutionary algorithms: a survey. Neural Computing & Applications30: 389–411.
2.
ArangioSBeckJ (2012) Bayesian neural networks for bridge integrity assessment. Structural Control and Health Monitoring19(1): 3–21.
3.
AvciOAbdeljaberOKiranyazS, et al. (2021) A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mechanical Systems and Signal Processing147: 107077.
4.
BartilsonDTJangJSmythAW (2019) Finite element model updating using objective-consistent sensitivity-based parameter clustering and Bayesian regularization. Mechanical Systems and Signal Processing114: 328–345.
5.
BengioY (2000) Gradient-based optimization of hyperparameters. Neural Computation12(8): 1889–1900.
6.
BishopCMNasrabadiNM (2006) Pattern Recognition and Machine Learning. Springer.
7.
DomkeJ (2012) Generic methods for optimization-based modeling. Artificial Intelligence and Statistics1: 318–326. PMLR.
8.
dos SantosJASoaresCM (2000) A damage identification numerical model based on the sensitivity of orthogonality conditions and least squares techniques. Computers & Structures78(1-3): 283–291.
9.
FarhatCHemezFM (1993) Updating finite element dynamic models using an element-by-element sensitivity methodology. AIAA Journal31(9): 1702–1711.
10.
FeiQGXuYLNgCL, et al. (2007) Structural health monitoring oriented finite element model of Tsing Ma bridge tower. International Journal of Structural Stability and Dynamics07(04): 647–668.
ForeseeFDHaganMT (1997) Gauss-Newton approximation to Bayesian learning. In: Proceedings of International Conference on Neural Networks (ICNN'97). IEEE, 1930–1935.
13.
FranceschiLDoniniMFrasconiP, et al. (2017) Forward and reverse gradient-based hyperparameter optimization. In: International Conference on Machine Learning. PMLR, 1165–1173.
14.
FritzenC-PJenneweinDKieferT (1998) Damage detection based on model updating methods. Mechanical Systems and Signal Processing12(1): 163–186.
15.
GeifmanYEl-YanivR (2019) Deep active learning with a neural architecture search. Advances in Neural Information Processing Systems32: 16.
16.
GoanEFookesC (2020) Bayesian neural networks: an introduction and survey. Case Studies in Applied Bayesian Data Science: CIRM Jean-Morlet Chair, Fall 2018: 45–87.
17.
HaganMTMenhajMB (1994) Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks5(6): 989–993.
18.
HeXZhaoKChuX (2021) AutoML: a survey of the state-of-the-art. Knowledge-Based Systems212: 106622.
19.
HundtAJainVHagerGD (2019) sharpdarts: Faster and more accurate differentiable architecture search. arXiv preprint arXiv:1903.09900.
20.
ImregunMVisserW (1991) Technical Article: practical articles in shock and vibration technology. The Shock and Vibration Digest23(1): 9–20.
21.
JangJSmythA (2017) Bayesian model updating of a full‐scale finite element model with sensitivity‐based clustering. Structural Control and Health Monitoring24(11): e2004.
22.
KavehAJavadiSManiatM (2014) Damage assessment via modal data with a mixed particle swarm strategy, ray optimizer, and harmony search.
23.
LamHFNgCT (2008) The selection of pattern features for structural damage detection using an extended Bayesian ANN algorithm. Engineering Structures30(10): 2762–2770.
24.
LamHKoJWongC (1998) Localization of damaged structural connections based on experimental modal and sensitivity analysis. Journal of Sound and Vibration210(1): 91–115.
25.
LamHFYuenKVBeckJL (2006) Structural health monitoring via measured Ritz vectors utilizing artificial neural networks. Computer-Aided Civil and Infrastructure Engineering21(4): 232–241.
26.
LiYSuXZhangQHuangYJiaZ (2024) Model Updating Method for Jacket Platform Considering Different Component Degradation Based on Deep Learning. Int J Str Stab Dyn24: 2450070. doi: 10.1142/S0219455424500706.
27.
LiLTalwalkarA (2020) Random search and reproducibility for neural architecture search. In: Uncertainty in Artificial Intelligence. PMLR, 367–377.
28.
LiSLiHLiuY, et al. (2014) SMC structural health monitoring benchmark problem using monitored data from an actual cable‐stayed bridge. Structural Control and Health Monitoring21(2): 156–172.
MaclaurinDDuvenaudDAdamsR (2015) Gradient-based hyperparameter optimization through reversible learning. In: International Conference on Machine Learning. PMLR, 2113–2122.
31.
MarwalaT (2002) Finite element model updating using wavelet data and genetic algorithm. Journal of Aircraft39(4): 709–711.
32.
MarwalaT (2010) Finite-element-model updating using particle-swarm optimization. In: Finite-element-model Updating Using Computional Intelligence Techniques: Applications to Structural Dynamics, 67–84.
33.
MordiniASavovKWenzelH (2008) Damage detection on stay cables using an open source-based framework for finite element model updating. Structural Health Monitoring7(2): 91–102.
34.
PedregosaF (2016) Hyperparameter optimization with approximate gradient. In: International Conference on Machine Learning. PMLR, 737–746.
35.
Rezaiee‐PajandMEntezamiASarmadiH (2020) A sensitivity‐based finite element model updating based on unconstrained optimization problem and regularized solution methods. Structural Control and Health Monitoring27(5): e2481.
36.
ShahriariBSwerskyKWangZ, et al. (2015) Taking the human out of the loop: a review of Bayesian optimization. Proceedings of the IEEE104(1): 148–175.
37.
SiowPYOngZCKhooSY, et al. (2021) Damage sensitive PCA-FRF feature in unsupervised machine learning for damage detection of plate-like structures. International Journal of Structural Stability and Dynamics21(02): 2150028.
38.
SongMRensonLNoëlJP, et al. (2018) Bayesian model updating of nonlinear systems using nonlinear normal modes. Structural Control and Health Monitoring25(12): e2258.
39.
VegaMAToddMD (2022) A variational Bayesian neural network for structural health monitoring and cost-informed decision-making in miter gates. Structural Health Monitoring21(1): 4–18.
40.
WanH-PDongG-SLuoY, et al. (2022) An improved complex multi-task Bayesian compressive sensing approach for compression and reconstruction of SHM data. Mechanical Systems and Signal Processing167: 108531.
41.
WangY-QZongLShiY-J, et al. (2015) Damage detection and rehabilitation on a curvilinear steel box girder bridge by multistage model updating. Structure and Infrastructure Engineering11(11): 1420–1431.
42.
XiangCGuJSunC, et al. (2023) Vibration-based structural damage identification using P-CNN and time-frequency Hybrid Index under the conditions of uncertainties and incomplete measurements. International Journal of Structural Stability and Dynamics23: 2350183.
43.
YeXJinTYunC (2019) A review on deep learning-based structural health monitoring of civil infrastructures. Smart Structures and Systems24(5): 567–585.
44.
YinT (2022) A practical Bayesian framework for structural model updating and prediction. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering8(1): 04021073.
45.
YinTZhuH (2018) Probabilistic damage detection of a steel truss bridge model by optimally designed Bayesian neural network. Sensors18(10): 3371.
46.
YinTZhuHP (2020) An efficient algorithm for architecture design of Bayesian neural network in structural model updating. Computer-Aided Civil and Infrastructure Engineering35(4): 354–372.
47.
YuenK-VLamH-F (2006) On the complexity of artificial neural networks for smart structures monitoring. Engineering Structures28(7): 977–984.
48.
YuenKVBeckJLKatafygiotisLS (2006) Efficient model updating and health monitoring methodology using incomplete modal data without mode matching. Structural Control and Health Monitoring: The Official Journal of the International Association for Structural Control and Monitoring and of the European Association for the Control of Structures13(1): 91–107.
49.
ZhangYMWangHMaoJX (2022) A Bayesian neural network approach for probabilistic model updating using incomplete modal data. Structural Control and Health Monitoring29(10): e3030.
50.
ZhaoRYanRChenZ, et al. (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing115: 213–237.
51.
ZhengZLuZChenW, et al. (2015) Structural damage identification based on power spectral density sensitivity analysis of dynamic responses. Computers & Structures146: 176–184.
52.
ZhuTTianWWengS, et al. (2018) Sensitivity-based finite element model updating using dynamic condensation approach. International Journal of Structural Stability and Dynamics18(08): 1840004.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
