Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/103987
| Title: | Intelligent power-supply-free ballastless track slab arch deformation state monitoring method | Other Title: | 一种智能免供电无砟轨道板上拱变形状态监测方法 | Authors: | Wang, YW Ni, Y He, J Liang, Y Xu, J |
Issue Date: | 14-Apr-2023 | Source: | 中国专利 ZL 202211603122.0 | Abstract: | The invention discloses an intelligent power-supply-free ballastless track slab arch-up deformation state monitoring method. The method comprises the steps that a track slab arch-up gap value at the first moment and a track slab arch-up gap value at the second moment are obtained; performing prediction based on the Bayesian dynamic linear model of the arching monitoring data of the track slab and the upper arching gap value of the track slab at the first moment to obtain predicted value probability distribution of the upper arching gap value of the track slab at the second moment; and determining a Bayesian factor corresponding to the second moment according to the probability distribution of the predicted value of the upper arch gap of the track slab at the second moment and the upper arch gap value of the track slab at the second moment, thereby performing abnormal value early warning according to the Bayesian factor corresponding to the second moment. Therefore, monitoring of the track plate is achieved, monitoring is simple, the accuracy of monitoring data is higher, and the monitoring effect is better. 本发明公开了一种智能免供电无砟轨道板上拱变形状态监测方法,包括:获取第一时刻的轨道板上拱离缝值以及第二时刻的轨道板上拱离缝值;基于轨道板拱起监测数据贝叶斯动态线性模型和第一时刻的轨道板上拱离缝值进行预测,得到第二时刻的轨道板上拱离缝预测值概率分布;根据第二时刻的轨道板上拱离缝预测值概率分布和第二时刻的轨道板上拱离缝值,确定第二时刻对应的贝叶斯因子,从而可以根据第二时刻对应的贝叶斯因子,进行异常值预警。从而实现轨道板的监测,不仅监测简单,且监测数据的准确性更高,因此监测效果更好。 |
Publisher: | 中华人民共和国国家知识产权局 | Rights: | Assignee: 香港理工大学深圳研究院 |
| Appears in Collections: | Patent |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ZL202211603122.0.pdf | 1.55 MB | Adobe PDF | View/Open |
Page views
68
Last Week
1
1
Last month
Citations as of Nov 9, 2025
Downloads
20
Citations as of Nov 9, 2025
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


