Analysis of Wind Speed Characteristics Along a High-Speed Railway
Source abstract
Abstract
The safe operation of high-speed railways (HSRs) is significantly challenged by strong winds. Accurate wind speed prediction along HSRs is crucial for ensuring the safety of train operations. However, existing research primarily focuses on designing and improving data-driven models, with limited attention given to the characteristics of wind speed specific to HSR environments. To address this gap, this study analyzes the wind speed characteristics of weather stations (WSs) and railway stations (RSs) along an HSR. These characteristics are explored from multiple perspectives, including wind speed variability, amplitude, correlation, wind speed distribution, and turbulence across different time scales. Additionally, the normalized cumulative periodogram (NCP) and Bartlett’s test are employed to quantify wind speed predictability. A wind speed prediction model is then developed based on predictability analysis. The findings reveal that RS wind speeds differ significantly from WS wind speeds, exhibiting higher volatility. The predictability of wind speed is influenced by the sampling interval: as the sampling time increases, the predictability and length of the predictable historical wind speed period decrease. By establishing a prediction model grounded in wind speed predictability analysis, irrelevant historical wind speed data can be excluded, improving the model’s prediction accuracy. Predictability analysis thus provides a robust foundation for forecasting strong winds along HSRs, ultimately enhancing train operation safety.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Aerodynamics and Fluid Dynamics Research · Railway Systems and Energy Efficiency · Railway Engineering and Dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
Funding
National Natural Science Foundation of China · China Postdoctoral Science Foundation
References (46)
Show source-provided references
1. Impact of high-speed railway on urban resilience in China: Does urban innovation matter?10.1016/j.seps.2023.101607 ↗
2. WindTrans: Transformer-Based Wind Speed Forecasting Method for High-Speed Railway10.1109/TITS.2023.3337150 ↗
3. A short-term strong wind prediction model for railway application: Design and verification10.1016/S0167-6105(02)00226-X ↗
4. Delaunay, D., Cléon, L.M., Sacré, C., Sourget, F., and Gautier, P.E. (2003, January 2–5). Designing a wind alarm system for the TGV-Méditerranée. Proceedings of the 11th International Conference on Wind Engineering, Lubbock, TX, USA.
5. Wind-Induced Accidents of Train/Vehicles and Their Measures in Japan10.2219/rtriqr.40.50 ↗
6. Data processing strategies in wind energy forecasting models and applications: A comprehensive review10.1016/j.apenergy.2019.04.188 ↗
7. A deep learning-based evolutionary model for short-term wind speed forecasting: A case study of the Lillgrund offshore wind farm10.1016/j.enconman.2021.114002 ↗
8. Two-stage decomposition and temporal fusion transformers for interpretable wind speed forecasting10.1016/j.energy.2023.129728 ↗
9. An attention-based multi-input LSTM with sliding window-based two-stage decomposition for wind speed forecasting10.1016/j.apenergy.2024.124057 ↗
10. Short-term prediction of the power production from wind farms10.1016/S0167-6105(98)00192-5 ↗
11. Wind power prediction based on numerical and statistical models10.1016/j.jweia.2012.09.004 ↗
12. Wang, Z., Wang, C., and Wu, J. (2016). Wind energy potential assessment and forecasting research based on the data pre-processing technique and swarm intelligent optimization algorithms. Sustainability, 8.10.3390/su8111191 ↗
13. On comparing three artificial neural networks for wind speed forecasting10.1016/j.apenergy.2009.12.013 ↗
14. ARMA based approaches for forecasting the tuple of wind speed and direction10.1016/j.apenergy.2010.10.031 ↗
15. Elsaraiti, M., and Merabet, A. (2021). A comparative analysis of the arima and lstm predictive models and their effectiveness for predicting wind speed. Energies, 14.10.3390/en14206782 ↗
16. Day-ahead wind speed forecasting using f-ARIMA models10.1016/j.renene.2008.09.006 ↗
17. Wind speed modeling using a vector autoregressive process with a time-dependent intercept term10.1016/j.ijepes.2015.11.027 ↗
18. Wind speed forecasting based on multi-objective grey wolf optimisation algorithm, weighted information criterion, and wind energy conversion system: A case study in Eastern China10.1016/j.enconman.2021.114402 ↗
19. Wind speed estimation using multilayer perceptron10.1016/j.enconman.2014.02.017 ↗
20. A hybrid ultra-short-term and short-term wind speed forecasting method based on CEEMDAN and GA-BPNN
21. Statistical wind speed forecasting models for small sample datasets: Problems, Improvements, and prospects10.1016/j.enconman.2022.115658 ↗
22. Wind speed forecasting approach based on Singular Spectrum Analysis and Adaptive Neuro Fuzzy Inference System10.1016/j.renene.2017.11.089 ↗
23. A wind speed forecasting system for the construction of a smart grid with two-stage data processing based on improved ELM and deep learning strategies10.1016/j.eswa.2023.122487 ↗
24. One dimensional convolutional neural network architectures for wind prediction10.1016/j.enconman.2019.05.007 ↗
25. Hybrid bidirectional LSTM model for short-term wind speed interval prediction10.1109/ACCESS.2020.3027977 ↗
26. A transformer-based deep neural network with wavelet transform for forecasting wind speed and wind energy10.1016/j.energy.2023.127678 ↗
27. Two novel hybrid linear and nonlinear models for wind speed forecasting10.1016/j.enconman.2021.114162 ↗
28. A data-driven multi-model methodology with deep feature selection for short-term wind forecasting10.1016/j.apenergy.2017.01.043 ↗
29. A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecasting10.1016/j.apenergy.2022.120601 ↗
30. Robustified extreme learning machine regression with applications in outlier-blended wind-speed forecasting10.1016/j.asoc.2022.108814 ↗
31. An EMD-recursive ARIMA method to predict wind speed for railway strong wind warning system10.1016/j.jweia.2015.02.004 ↗
32. Review of the use of numerical weather prediction (NWP) models for wind energy assessment10.1016/j.rser.2010.07.001 ↗
33. Field measurement analysis of wind parameters and nonstationary characteristics in mountainous terrain: Focusing on cooling windstorms10.1016/j.jweia.2022.105175 ↗
34. Probabilistic wind spectrum model based on correlation of wind parameters in mountainous areas: Focusing on von Karman spectrum10.1016/j.jweia.2023.105337 ↗
35. Analysis of some flexible families of distributions for estimation of wind speed distributions10.1016/j.apenergy.2011.07.045 ↗
36. Improving probabilistic wind speed forecasting using M-Rice distribution and spatial data integration10.1016/j.apenergy.2024.122840 ↗
37. Use of Birnbaum-Saunders distribution for estimating wind speed and wind power probability distributions: A review10.1016/j.enconman.2017.03.083 ↗
38. Probability distributions of wind speed in the UAE10.1016/j.enconman.2015.01.036 ↗
39. Time series modelling of water resources and environmental systems
40. White noise testing using wavelets10.1002/sta4.69 ↗
41. Temporal convolutional networks interval prediction model for wind speed forecasting10.1016/j.epsr.2020.106865 ↗
42. A new short-term wind speed forecasting method based on fine-tuned LSTM neural network and optimal input sets10.1016/j.enconman.2020.112824 ↗
43. A novel approach to ultra-short-term wind power prediction based on feature engineering and informer10.1016/j.egyr.2022.12.062 ↗
44. MRIformer: A multi-resolution interactive transformer for wind speed multi-step prediction10.1016/j.ins.2024.120150 ↗
45. Leveraging data from nearby stations to improve short-term wind speed forecasts10.1016/j.energy.2022.125644 ↗
46. Characterizing forecastability of wind sites in the United States10.1016/j.renene.2018.08.085 ↗