A Legendre Neural Network-Based Approach to Multiparameter Identification of Traffic Loads Across the Full Spatiotemporal Domain
Abstract
:1. Introduction
2. Methodology
3. Training of the Legendre Neural Networks and Hyperparameter Optimizations
4. Verification of the Traffic Load Identification Method
4.1. Numerical Verification
4.2. Experimental Verification
5. Discussions
6. Conclusions
- (1)
- An LNN model is proposed to establish the relationship between bridge strains and traffic load. With the well-trained LNN model, the explicit expression of the moving load could be obtained based on Legendre polynomial combinations. The explicit expressions of the loading may help to reveal the influence of strain response on the moving load and are applicable in a variety of bridges with the same type.
- (2)
- To improve the performance of the LNN, a series of training and optimization of the learning rates and training sample quantities was conducted to determine the optimal values of these hyperparameters. Due to the optimization of hyperparameters of the LNN model, the MPAE of the validation samples with the LNN model achieved lower than 2%, and the training time of the LNN was less than 0.5 h. The outcomes prove the high training efficiency and precision of the method in identification ability.
- (3)
- With the well-trained LNN, the precision of the proposed method was validated through simulations and experiments with a continuous beam. Both the magnitude and moving speed of the loading could be accurately identified at the same time.
- (4)
- The processes of loading identification with the LNN proved to be insensitive to noise and rely on the placement scheme of sensors. When the method was applied in the identification of loading of beam bridges with different lengths and the same other physical parameters, the precisions of identified loading with the LNN were all very high, which confirms its wide applicability.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Tang, Q.; Xin, J.; Jiang, Y.; Zhou, J.; Li, S.; Chen, Z. Novel identification technique of moving loads using the random response power spectral density and deep transfer learning. Measurement 2022, 195, 111120. [Google Scholar] [CrossRef]
- Chen, Z.; Chan, T.H.T.; Nguyen, A.; Yu, L. Identification of vehicle axle loads from bridge responses using preconditioned least square QR-factorization algorithm. Mech. Syst. Signal Process. 2019, 128, 479–496. [Google Scholar] [CrossRef]
- Pan, C.-D.; Yu, L.; Liu, H.-L.; Chen, Z.-P.; Luo, W.-F. Moving force identification based on redundant concatenated dictionary and weighted l1-norm regularization. Mech. Syst. Signal Process. 2018, 98, 32–49. [Google Scholar] [CrossRef]
- Xiang, T.; Huang, K.; Zhang, H.; Zhang, Y.; Zhang, Y.; Zhou, Y. Detection of Moving Load on Pavement Using Piezoelectric Sensors. Sensors 2020, 20, 2366. [Google Scholar] [CrossRef] [PubMed]
- Dan, D.; Ge, L.; Yan, X. Identification of moving loads based on the information fusion of weigh-in-motion system and multiple camera machine vision. Measurement 2019, 144, 155–166. [Google Scholar] [CrossRef]
- Zhang, H.; Xie, X.; Jiang, J.; Yamashita, M. Assessment on transient sound radiation of a vibrating steel bridge due to traffic loading. J. Sound Vib. 2015, 336, 132–149. [Google Scholar] [CrossRef]
- Xie, X.; Wu, D.; Zhang, H.; Shen, Y.; Mikio, Y. Low-frequency noise radiation from traffic-induced vibration of steel double-box girder bridge. J. Vib. Control 2012, 18, 373–384. [Google Scholar] [CrossRef]
- Zhang, H.; Shen, M.; Zhang, Y.; Chen, Y.; Lü, C. Identification of Static Loading Conditions Using Piezoelectric Sensor Arrays. J. Appl. Mech. 2018, 85, 011008. [Google Scholar] [CrossRef]
- Sujon, M.; Dai, F. Application of Weigh-in-Motion Technologies for Pavement and Bridge Response Monitoring: State-of-the-Art Review. Autom. Constr. 2021, 130, 103844. [Google Scholar] [CrossRef]
- Zhang, H.; Zhu, J.; Zhou, Y.; Shen, Z. Non-Contact Weigh-in-Motion Approach with an Improved Multi-Region of Interest Method. Mech. Syst. Signal Process. 2024, 212, 111323. [Google Scholar] [CrossRef]
- Ventura, R.; Barabino, B.; Vetturi, D.; Maternini, G. Monitoring Vehicles with Permits and That Are Illegally Overweight on Bridges Using Weigh-In-Motion (WIM) Devices: A Case Study from Brescia. Case Stud. Transp. Policy 2023, 13, 101023. [Google Scholar] [CrossRef]
- Ventura, R.; Maternini, G.; Barabino, B. Traffic Hazards on Main Road’s Bridges: Real-Time Estimating and Managing the Overload Risk. IEEE Trans. Intell. Transp. Syst. 2024, 25, 12239–12255. [Google Scholar] [CrossRef]
- Fiorillo, G.; Ghosn, M. Risk-Based Importance Factors for Bridge Networks under Highway Traffic Loads. Struct. Infrastruct. Eng. 2019, 15, 113–126. [Google Scholar] [CrossRef]
- Fiorillo, G.; Ghosn, M. Risk-Based Life-Cycle Analysis of Highway Bridge Networks under Budget Constraints. Struct. Infrastruct. Eng. 2022, 18, 1457–1471. [Google Scholar] [CrossRef]
- Yannis, G.; Antoniou, C. Integration Of Weigh-In-Motion Technologies In Road Infrastructure Management. ITE J. 2005, 75, 39–43. [Google Scholar]
- Zhang, H.; Zhu, J.; Xie, W.; Huang, K.; Wu, M.; Lu, C.; Shen, Z. Fusion of Computer Vision and Piezoelectric Tactility Approach to Measuring Moving Vehicle Loads. Measurement 2025, 240, 115616. [Google Scholar] [CrossRef]
- Zhang, H.; Huang, K.; Zhou, Y.; Sun, L.; Zhang, Z.; Luo, J. A Real-Time Sensing System Based on Triboelectric Nanogenerator for Dynamic Response of Bridges. Sci. China Technol. Sci. 2022, 65, 2723–2733. [Google Scholar] [CrossRef]
- Law, S.S.; Chan, T.H.T.; Zeng, Q.H. Moving Force Identification: A Time Domain Method. J. Sound Vib. 1997, 201, 1–22. [Google Scholar] [CrossRef]
- Law, S.S.; Chan, T.H.T.; Zeng, Q.H. Moving Force Identification—A Frequency and Time Domains Analysis. J. Dyn. Syst. Meas. Control 1999, 121, 394–401. [Google Scholar] [CrossRef]
- Law, S.S.; Bu, J.Q.; Zhu, X.Q.; Chan, S.L. Moving load identification on a simply supported orthotropic plate. Int. J. Mech. Sci. 2007, 49, 1262–1275. [Google Scholar] [CrossRef]
- Zhang, H.; Zhou, Y.; Quan, L. Identification of a moving mass on a beam bridge using piezoelectric sensor arrays. J. Sound Vib. 2021, 491, 115754. [Google Scholar] [CrossRef]
- Xiao, F.; Mao, Y.; Sun, H.; Chen, G.S.; Tian, G. Stiffness Separation Method for Reducing Calculation Time of Truss Structure Damage Identification. Struct. Control Health Monit. 2024, 2024, 5171542. [Google Scholar] [CrossRef]
- Yang, H.; Yan, W.; He, H. Parameters Identification of Moving Load Using ANN and Dynamic Strain. Shock Vib. 2016, 2016, 8249851. [Google Scholar] [CrossRef]
- O’Connor, C.; Chan, T.H.T. Dynamic Wheel Loads From Bridge Strains. J. Struct. Eng. 1988, 114, 1703–1723. [Google Scholar] [CrossRef]
- Law, S.S.; Fang, Y.L. Moving Force Identification: Optimal State Estimation Approach. J. Sound Vib. 2001, 239, 233–254. [Google Scholar] [CrossRef]
- Pinkaew, T.; Asnachinda, P. Experimental study on the identification of dynamic axle loads of moving vehicles from the bending moments of bridges. Eng. Struct. 2007, 29, 2282–2293. [Google Scholar] [CrossRef]
- Pinkaew, T. Identification of vehicle axle loads from bridge responses using updated static component technique. Eng. Struct. 2006, 28, 1599–1608. [Google Scholar] [CrossRef]
- Chen, Z.; Chan, T.H.T.; Yu, L. Comparison of regularization methods for moving force identification with ill-posed problems. J. Sound Vib. 2020, 478, 115349. [Google Scholar] [CrossRef]
- Pan, C.; Ye, X.; Zhou, J.; Sun, Z. Matrix regularization-based method for large-scale inverse problem of force identification. Mech. Syst. Signal Process. 2020, 140, 106698. [Google Scholar] [CrossRef]
- Chen, Z.; Chan, T.H.T. A truncated generalized singular value decomposition algorithm for moving force identification with ill-posed problems. J. Sound Vib. 2017, 401, 297–310. [Google Scholar] [CrossRef]
- Qiao, B.; Zhang, X.; Wang, C.; Zhang, H.; Chen, X. Sparse regularization for force identification using dictionaries. J. Sound Vib. 2016, 368, 71–86. [Google Scholar] [CrossRef]
- Kawamura, K.; Miyamoto, A.; Frangopol, D.M.; Kimura, R. Performance evaluation of concrete slabs of existing bridges using neural networks. Eng. Struct. 2003, 25, 1455–1477. [Google Scholar] [CrossRef]
- Yeung, W.T.; Smith, J.W. Damage detection in bridges using neural networks for pattern recognition of vibration signatures. Eng. Struct. 2005, 27, 685–698. [Google Scholar] [CrossRef]
- Lee, J.J.; Yun, C.B. Damage diagnosis of steel girder bridges using ambient vibration data. Eng. Struct. 2006, 28, 912–925. [Google Scholar] [CrossRef]
- Mehrjoo, M.; Khaji, N.; Moharrami, H.; Bahreininejad, A. Damage detection of truss bridge joints using Artificial Neural Networks. Expert Syst. Appl. 2008, 35, 1122–1131. [Google Scholar] [CrossRef]
- Zhou, Y.; Pei, Y.; Li, Z.; Fang, L.; Zhao, Y.; Yi, W. Vehicle weight identification system for spatiotemporal load distribution on bridges based on non-contact machine vision technology and deep learning algorithms. Measurement 2020, 159, 107801. [Google Scholar] [CrossRef]
- Zhou, J.; Dong, L.; Guan, W.; Yan, J. Impact load identification of nonlinear structures using deep Recurrent Neural Network. Mech. Syst. Signal Process. 2019, 133, 106292. [Google Scholar] [CrossRef]
- Mall, S.; Chakraverty, S. Application of Legendre Neural Network for solving ordinary differential equations. Appl. Soft Comput. 2016, 43, 347–356. [Google Scholar] [CrossRef]
- Yang, Y.; Hou, M.; Luo, J. A novel improved extreme learning machine algorithm in solving ordinary differential equations by Legendre neural network methods. Adv. Differ. Equ. 2018, 2018, 469. [Google Scholar] [CrossRef]
- Zhang, H.; Wang, L.; Zhang, C.; Shu, J.; Huang, K.; Song, Y. A General Modification of the V-Q-x Relationship of the Contact-Separation Mode Triboelectric Nanogenerator. Nano Energy 2023, 115, 108716. [Google Scholar] [CrossRef]
- Chen, Y.; Zhang, H.; Quan, L.; Zhang, Z.; Lü, C. Theoretical Assessment on Piezoelectric Energy Harvesting in Smart Self-Powered Asphalt Pavements. J. Vib. Eng. Technol. 2018, 6, 1–10. [Google Scholar] [CrossRef]
- Zhang, Y.; Zhang, H.; Lü, C.; Chen, Y.; Wang, J. Piezoelectric Energy Harvesting from Roadway Deformation under Various Traffic Flow Conditions. J. Intell. Mater. Syst. Struct. 2020, 31, 1751–1762. [Google Scholar] [CrossRef]
- Huang, K.; Zhang, H.; Jiang, J.; Zhang, Y.; Zhou, Y.; Sun, L.; Zhang, Y. The Optimal Design of a Piezoelectric Energy Harvester for Smart Pavements. Int. J. Mech. Sci. 2022, 232, 107609. [Google Scholar] [CrossRef]
Basic Parameters | Value |
---|---|
Length (l = 3 × ls) | 4.5 m = 1.5 m × 3 |
Young’s modulus (Es) | 200 Gpa |
Cross-section (bs × hs) | 50 mm × 26 mm |
Simulation Dataset | Experimental Dataset | |
---|---|---|
Speed (v) | [0, 2] m/s | 0.375, 0.5 m/s |
Magnitude (F) | [10, 50] N | 10, 17 N |
Sample quantities | 800 group | 24 group |
Method | MAE | MAPE | RMSE | |||
---|---|---|---|---|---|---|
Speed (m/s) | Magnitude (N) | Speed | Magnitude | Speed (m/s) | Magnitude (N) | |
LNN | 0.002 | 0.078 | 1.43% | 1.52% | 0.003 | 0.207 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, H.; Shen, R.; Zhou, Y.; Zhang, C.; Zhang, Z. A Legendre Neural Network-Based Approach to Multiparameter Identification of Traffic Loads Across the Full Spatiotemporal Domain. Sensors 2024, 24, 7785. https://doi.org/10.3390/s24237785
Zhang H, Shen R, Zhou Y, Zhang C, Zhang Z. A Legendre Neural Network-Based Approach to Multiparameter Identification of Traffic Loads Across the Full Spatiotemporal Domain. Sensors. 2024; 24(23):7785. https://doi.org/10.3390/s24237785
Chicago/Turabian StyleZhang, He, Ruihong Shen, Yuhui Zhou, Cun Zhang, and Zhicheng Zhang. 2024. "A Legendre Neural Network-Based Approach to Multiparameter Identification of Traffic Loads Across the Full Spatiotemporal Domain" Sensors 24, no. 23: 7785. https://doi.org/10.3390/s24237785
APA StyleZhang, H., Shen, R., Zhou, Y., Zhang, C., & Zhang, Z. (2024). A Legendre Neural Network-Based Approach to Multiparameter Identification of Traffic Loads Across the Full Spatiotemporal Domain. Sensors, 24(23), 7785. https://doi.org/10.3390/s24237785