Application of the ANN with swarm optimization algorithm in layer property backcalculation for asphalt pavement
Source abstract
Abstract
State-of-the-art techniques for pavement performance evaluation have attracted considerable attention in recent years. Artificial Neural Networks (ANNs) can simulate the human brain to discover hidden patterns within datasets, thereby enhancing the accuracy of performance evaluations in civil engineering. Routine backcalculation of layer properties from Falling Weight Deflectometer (FWD) deflection time histories provide critical information for asphalt pavement performance assessment. This study proposes a general framework that integrates the ANN with swarm optimization algorithms for asphalt pavement layer property backcalculation at the project level. The proposed procedure employed the spectral element method (SEM) to calculate the deflection time histories, explicitly accounting for the dynamic effect of FWD loading and the viscoelastic property of asphalt concrete (AC). The geometrical characteristic of the load time history and the load-deflection hysteresis curve were extracted to construct the training dataset for the ANN model. Three swarm optimization algorithms were utilized to determine the initial weights and biases of the ANN. Subsequently, the parameters of the Williams-Landel-Ferry (WLF) function were optimized using the field temperatures and the backcalculated layer property to characterize the temperature-dependent behaviour of AC. A well agreement between the backcalculated and measured deflection time histories, together with the consistency of the backcalculated layer properties within reasonable ranges, demonstrated the feasibility of the proposed procedure. In contrast to conventional backpropagation neural networks (BPNNs), whose built-in optimization schemes tend to become trapped in local optima and may yield unreasonable layer properties, swarm optimization algorithms expand the candidate solution space and facilitate global optimization. The standard deviation (STD) and coefficient of variation (COV) obtained from ANNs enhanced with swarm optimization are significantly lower than those from BPNNs; the maximum reduction in COV for ANN + HPO (Hunter–Prey optimization) relative to BPNN exceeds 50%. The ANN + MA (Mayfly Algorithm) and ANN + HPO exhibit superior performance and greater computational efficiency for layer property backcalculation compared with a conventional ANN model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Asphalt Pavement Performance Evaluation · Infrastructure Maintenance and Monitoring · Transport Systems and Technology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Infrastructure Engineering, Dalian University of Technology
Shanxi Provincial Transportation Construction Engineering Quality Inspection Center (Co., Ltd.)
Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology
Department of Statistics and Data Science, The University of Texas
References (44)
Show source-provided references
1. Simplified closed-form procedure for network-level determination of pavement layer moduli from falling weight deflectometer data10.1061/JPEODX.0000080 ↗
2. Artificial neural networks based optimization techniques: a review10.3390/electronics10212689 ↗
3. Spectral element technique for efficient parameter identification of layered media. I. Forward calculation10.1016/S0020-7683(00)00112-8 ↗
4. Spectral element technique for efficient parameter identification of layered media: part II: inverse calculation10.1016/S0020-7683(01)00109-3 ↗
5. Spectral element technique for efficient parameter identification of layered media. Part III: viscoelastic aspects10.1016/S0020-7683(02)00079-3 ↗
6. Development of statistical temperature prediction models for a test road in Edmonton, Alberta, Canada10.1016/j.ijprt.2017.05.004 ↗
7. Temperature correction factors for backcalculated asphalt modulus and HWD deflections of airfield pavements
8. Comparisons of asphalt pavement responses computed using layer properties backcalculated from dynamic and static approaches10.1080/14680629.2018.1436467 ↗
9. Effectiveness of static and dynamic backcalculation approaches for asphalt pavement10.1139/cjce-2019-0052 ↗
10. An efficient dynamic backcalculation procedure for flexible pavement at a network level10.1080/14680629.2025.2499234 ↗
11. Temperature adjustment for light weight deflectometer application of evaluating asphalt pavement structural bearing capacity10.3141/2641-10 ↗
12. A review of back-calculation techniques and their potential to inform mitigation strategies with application to non-transmissible acute infectious diseases10.1098/rsif.2015.0096 ↗
13. Development of FWD based hybrid back-analysis technique for railway track condition assessment10.1016/j.trgeo.2022.100894 ↗
14. Determination of effective frequency range excited by falling weight deflectometer loading history for asphalt pavement10.1016/j.conbuildmat.2019.117792 ↗
15. Particle swarm optimization10.1109/ICNN.1995.488968 ↗
16. Temperature correction of deflections and backcalculated asphalt concrete moduli10.3141/1570-13 ↗
17. Development and validation of a temperature correction model for FWD backcalculated moduli10.1080/14488353.2022.2083045 ↗
18. Viscowave–a new solution for viscoelastic wave propagation of layered structures subjected to an impact load10.1080/10298436.2013.782401 ↗
19. Verification of a backcalculation of pavement moduli
20. Prediction of asphalt pavement responses from FWD surface deflections using soft computing methods10.1061/JPEODX.0000044 ↗
21. Development of ANN-GA program for backcalculation of pavement moduli under FWD testing with viscoelastic and nonlinear parameters10.1080/10298436.2017.1309197 ↗
22. Automated decision making in highway pavement preventive maintenance based on deep learning10.1016/j.autcon.2021.104111 ↗
23. Machine learning approach for pavement performance prediction10.1080/10298436.2019.1609673 ↗
24. Intelligent optimization: literature review and state-of-the-art algorithms (1965–2022)10.1016/j.engappai.2023.106959 ↗
25. A new methodology to improve backcalculation of flexible pavements with stabilized foundations10.1016/j.conbuildmat.2023.130405 ↗
26. Hunter–prey optimization: algorithm and applications10.1007/s00500-021-06401-0 ↗
27. Effective layer temperature prediction model and temperature correction via falling weight deflectometer deflections10.3141/1764-11 ↗
28. Fractional viscoelastic models for asphalt concrete: from parameter identification to pavement mechanics analysis10.1061/(ASCE)EM.1943-7889.0002116 ↗
29. Artificial neural networks based backcalculation of the structural properties of a typical flexible pavement10.1007/s00521-012-1131-y ↗
30. Stubstad · 2006
31. Viscoelastic nonlinear multilayered model for asphalt pavements10.1061/(ASCE)EM.1943-7889.0001095 ↗
32. Bird swarm algorithms with chaotic mapping10.1007/s10462-019-09704-9 ↗
33. Predicting bedrock depth under asphalt pavement through a data-driven method based on particle swarm optimization-back propagation neural network10.1016/j.conbuildmat.2022.129165 ↗
34. Optical fiber sensing technology for full-scale condition monitoring of pavement layers10.1080/14680629.2018.1547656 ↗
35. Backcalculation of asphalt concrete modulus master curve from field-measured falling weight deflectometer data: using a new time domain viscoelastic dynamic solution and genetic algorithm10.3141/2457-09 ↗
36. A mayfly optimization algorithm10.1016/j.cie.2020.106559 ↗
37. High-speed railway seismic response prediction using CNN-LSTM hybrid neural network10.1007/s13349-023-00758-6 ↗
38. Bending strain progression and damage of asphalt beams based on distributed fibre optic sensors10.1080/10298436.2025.2479645 ↗
39. A distributed fiber optic sensor-based approach for crack asphalt structure under freeze-thaw cycling tests10.1016/j.conbuildmat.2025.141262 ↗
40. Prediction of freeze-thaw damage of asphalt concrete based on distributed fiber optic sensors and KAN-Transformer fusion model10.1016/j.yofte.2025.104304 ↗
41. Distributed fiber optic sensing and Informer-LSTM prediction for damage evolution of asphalt concrete under freeze–thaw cycling10.1617/s11527-025-02758-y ↗
42. Characterization of linear viscoelastic behavior of asphalt concrete using complex modulus model10.1061/(ASCE)MT.1943-5533.0000688 ↗
43. Dynamic backcalculation of asphalt pavement layer properties using spectral element method10.1080/14680629.2015.1056214 ↗
44. Correlation between pavement temperature and deflection basin form factors of asphalt pavement10.1080/10298436.2017.1356172 ↗