Abstract
We propose to combine a physics-based finite element (FE) track model and a data-driven Gaussian process regression (GPR) model to directly infer railpad and ballast stiffness from measured frequency response functions (FRF) by field hammer tests. Conventionally, only the rail resonance and full track resonance are used as the FRF features to identify track stiffness. In this paper, eleven features, including sleeper resonances, from a single FRF curve are selected as the predictors of the GPR. To deal with incomplete measurements and uncertainties in the FRF features, we train multiple candidate GPR models with different features, kernels and training sets. Predictions by the candidate models are fused using a weighted Product of Experts method that automatically filters out unreliable predictions. We compare the performance of the proposed method with a model updating method using the particle swam optimization (PSO) on two synthesis datasets in a wide range of scenarios. The results show that the enriched features and the proposed fusion strategy can effectively reduce prediction errors. In the worst-case scenario with only three features and 5% injected noise, the average prediction errors for the railpad and ballast stiffness are approximately 12% and 6%, outperforming the PSO by about 6% and 3%, respectively. Moreover, the method enables fast predictions for large datasets. The predictions for 400 samples takes only approximately 10 s compared with 40 min using the PSO. Finally, a field application example shows that the proposed method is capable of extracting the stiffness values using a simple setup, i.e., with only one accelerometer and one impact location.
Highlights
The stiffness of the ballasted railway track is primarily provided by resilient components such as railpads and ballast
We propose a non-iterative method to directly infer the stiffness of railpad and ballast from measured frequency response functions (FRF) features based on the Gaussian process regression (GPR)
We propose a new method to directly infer railpad and ballast stiffness from a single FRF using the GPR
Summary
The stiffness of the ballasted railway track is primarily provided by resilient components such as railpads and ballast. The fitting process can be achieved by solving an optimization problem, where objective functions defining the difference between modelled and measured FRFs are minimized iteratively. Compared with conventional parametric regression models, the GPR has more expressive power in the sense that it can handle complex datasets (e.g., high-dimensions) with more flexibility [36] Another practical motivation to use the GPR is that it can provide both predictions and confidence intervals, as opposed to other kernel based non-parametric regression methods, such as the support vector machine (SVM) and artificial neural network (ANN), which only offer point estimates. We propose a non-iterative method to directly infer the stiffness of railpad and ballast from measured FRF features based on the GPR.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have