Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Settlement prediction method based on fuzzy information granulation and dynamic neural network
The invention discloses a settlement prediction method based on fuzzy information granulation and a dynamic neural network. An existing method for predicting engineering settlement under a high-speed railway line has defects. The method comprises the following steps: acquiring original time sequence data of section settlement, and performing fuzzy processing on the original time sequence data to obtain upper limit, middle value and lower limit of section settlement change; and constructing a nonlinear autoregressive dynamic neural network prediction model of the settlement interval, and predicting future settlement data of the project by using the prediction model to obtain settlement prediction data. According to the method, the fuzzy information granulation and the dynamic neural network technology are combined, the project settlement development trend and the change range under the high-speed railway line can be accurately predicted, some redundant and irrelevant information is removed, main information is extracted, and the data processing efficiency is greatly improved.
本发明公开了一种基于模糊信息粒化和动态神经网络的沉降预测方法。现有对高速铁路线下工程沉降进行预测的方法存在不足之处。本发明首先获取断面沉降原始时序数据，对其模糊处理得到断面沉降变化上限、中值和下限；构建沉降区间非线性自回归式动态神经网络预测模型，运用预测模型，对工程未来的沉降数据进行预测，得到沉降预测数据。本发明将模糊信息粒化及动态神经网络技术相结合，能够准确预测高速铁路线下工程沉降发展趋势及变化范围，剔除一些冗余和不相关的信息，提取出主要的信息，大大的提高了数据处理的效率。
Settlement prediction method based on fuzzy information granulation and dynamic neural network
The invention discloses a settlement prediction method based on fuzzy information granulation and a dynamic neural network. An existing method for predicting engineering settlement under a high-speed railway line has defects. The method comprises the following steps: acquiring original time sequence data of section settlement, and performing fuzzy processing on the original time sequence data to obtain upper limit, middle value and lower limit of section settlement change; and constructing a nonlinear autoregressive dynamic neural network prediction model of the settlement interval, and predicting future settlement data of the project by using the prediction model to obtain settlement prediction data. According to the method, the fuzzy information granulation and the dynamic neural network technology are combined, the project settlement development trend and the change range under the high-speed railway line can be accurately predicted, some redundant and irrelevant information is removed, main information is extracted, and the data processing efficiency is greatly improved.
本发明公开了一种基于模糊信息粒化和动态神经网络的沉降预测方法。现有对高速铁路线下工程沉降进行预测的方法存在不足之处。本发明首先获取断面沉降原始时序数据，对其模糊处理得到断面沉降变化上限、中值和下限；构建沉降区间非线性自回归式动态神经网络预测模型，运用预测模型，对工程未来的沉降数据进行预测，得到沉降预测数据。本发明将模糊信息粒化及动态神经网络技术相结合，能够准确预测高速铁路线下工程沉降发展趋势及变化范围，剔除一些冗余和不相关的信息，提取出主要的信息，大大的提高了数据处理的效率。
Settlement prediction method based on fuzzy information granulation and dynamic neural network
一种基于模糊信息粒化和动态神经网络的沉降预测方法
WANG YANING (Autor:in) / LI XIAOLUN (Autor:in) / LI KUN (Autor:in) / CHEN DE (Autor:in) / ZHU YANGUI (Autor:in) / SUO WEICHEN (Autor:in) / YAO YIBO (Autor:in)
18.04.2023
Patent
Elektronische Ressource
Chinesisch
IPC:
G06F
ELECTRIC DIGITAL DATA PROCESSING
,
Elektrische digitale Datenverarbeitung
/
E01C
Bau von Straßen, Sportplätzen oder dgl., Decken dafür
,
CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE
/
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
| DOAJ | 2022
Neural network based stochastic design charts for settlement prediction
| Online Contents | 2005
Settlement Prediction of Buildings Based on BP Neural Network
| Trans Tech Publications | 2014
Neural network based stochastic design charts for settlement prediction
| British Library Online Contents | 2005
Prediction of Liquified Soil Settlement Based on Artificial Neural Network
| Springer Verlag | 2023