A platform for research: civil engineering, architecture and urbanism
High-speed railway subgrade settlement prediction and early warning method based on deep learning
The invention discloses a high-speed railway subgrade settlement prediction and early warning method based on deep learning, relates to the technical field of geological disaster prediction and early warning, and aims to realize more accurate subgrade settlement prediction and early warning in a complex natural environment. Performing data preprocessing on the data measured by the monitoring sensor to obtain a complete and smooth data set; establishing a high-speed railway subgrade settlement prediction model, dividing a complete and smooth data set into a training set and a test set, and putting the training set into the model for training to obtain a parameter matrix of the model; testing the trained high-speed railway roadbed settlement prediction model through the test set; performing precision evaluation on the prediction model according to a test result; the predicted settlement data is judged through an early warning model, and a corresponding early warning result is given; the method has the advantage of accurate and timely prediction.
本发明公开了一种基于深度学习的高速铁路路基沉降预测及预警方法,涉及地质灾害预测预警技术领域,目的是实现复杂自然环境下更精准的路基沉降预测及预警,包括获取监测传感器所测得的数据;对监测传感器所测得的数据进行数据预处理,得到完整且平滑的数据集;建立高速铁路路基沉降预测模型,将完整且平滑的数据集划分成训练集和测试集,并将训练集投入模型中进行训练获取模型的参数矩阵;通过测试集对训练好的高速铁路路基沉降预测模型进行测试;根据测试结果对预测模型进行精度评估;通过预警模型对预测的沉降数据进行判断并给出相应的预警结果;本发明具有预测准确且及时的优点。
High-speed railway subgrade settlement prediction and early warning method based on deep learning
The invention discloses a high-speed railway subgrade settlement prediction and early warning method based on deep learning, relates to the technical field of geological disaster prediction and early warning, and aims to realize more accurate subgrade settlement prediction and early warning in a complex natural environment. Performing data preprocessing on the data measured by the monitoring sensor to obtain a complete and smooth data set; establishing a high-speed railway subgrade settlement prediction model, dividing a complete and smooth data set into a training set and a test set, and putting the training set into the model for training to obtain a parameter matrix of the model; testing the trained high-speed railway roadbed settlement prediction model through the test set; performing precision evaluation on the prediction model according to a test result; the predicted settlement data is judged through an early warning model, and a corresponding early warning result is given; the method has the advantage of accurate and timely prediction.
本发明公开了一种基于深度学习的高速铁路路基沉降预测及预警方法,涉及地质灾害预测预警技术领域,目的是实现复杂自然环境下更精准的路基沉降预测及预警,包括获取监测传感器所测得的数据;对监测传感器所测得的数据进行数据预处理,得到完整且平滑的数据集;建立高速铁路路基沉降预测模型,将完整且平滑的数据集划分成训练集和测试集,并将训练集投入模型中进行训练获取模型的参数矩阵;通过测试集对训练好的高速铁路路基沉降预测模型进行测试;根据测试结果对预测模型进行精度评估;通过预警模型对预测的沉降数据进行判断并给出相应的预警结果;本发明具有预测准确且及时的优点。
High-speed railway subgrade settlement prediction and early warning method based on deep learning
一种基于深度学习的高速铁路路基沉降预测及预警方法
LIU YANGYANG (author) / DENG ZHIXING (author) / LIU YUHAN (author) / ZHANG CHENGRUI (author) / ZHI HAIXU (author) / YANG DONGQI (author) / NIU YUNBIN (author) / XIE KANG (author) / SU QIAN (author)
2022-07-15
Patent
Electronic Resource
Chinese
IPC:
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
/
E01B
PERMANENT WAY
,
Gleisoberbau
/
E01C
Bau von Straßen, Sportplätzen oder dgl., Decken dafür
,
CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE
/
E02D
FOUNDATIONS
,
Gründungen
/
G01C
Messen von Entfernungen, Höhen, Neigungen oder Richtungen
,
MEASURING DISTANCES, LEVELS OR BEARINGS
/
G01S
RADIO DIRECTION-FINDING
,
Funkpeilung
Goaf site high-speed railway subgrade settlement monitoring device and observation method
European Patent Office | 2021
|DEFORMATION DETECTION AND EARLY WARNING SYSTEM FOR RAILWAY SUBGRADE
European Patent Office | 2021
|Probabilistic Analytical Model for Settlement Risk Assessment of High-Speed Railway Subgrade
British Library Online Contents | 2016
|