A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
The invention discloses a foundation pit deformation monitoring method and system, and the method comprises the steps: obtaining foundation pit monitoring data, determining a prediction index and a feature index of a foundation pit, carrying out the data preprocessing of the selected monitoring data, carrying out the feature extraction of the preprocessed foundation pit monitoring data through a variational auto-encoder, and constructing an original time series data set; and sliding the time window to construct a sample data set, inputting the sample data set into the trained LSTM model for training to obtain low-dimensional hidden features, performing model optimization on the LSTM model, and inputting a test set into the optimized LSTM foundation pit deformation prediction model. A mean square error, a mean absolute error and a decision coefficient are used as evaluation indexes to evaluate a model prediction effect, and the foundation pit deformation prediction model can make full use of time information of time sequence data to make high-precision prediction; and meanwhile, the generalization ability of the model and the stability of the prediction effect can be improved by utilizing the strong feature expression ability of the auto-encoder.
本发明公开了一种基坑变形监测方法及系统，通过获取基坑监测数据并确定基坑的预测指标与特征指标，将选取好的监测数据进行数据预处理，将预处理后的基坑监测数据通过变分自编码器进行特征提取并构造出原始时序数据集，时间窗滑动以构建样本数据集，将样本数据集输入至已训练的LSTM模型进行训练得到具有低维隐藏特征，对LSTM模型进行模型优化并将测试集输入到优化后的LSTM基坑变形预测模型中，使用均方误差、平均绝对误差和决定系数作为评价指标对模型预测效果进行评估，基坑变形预测模型不仅能够充分利用时序数据的时间信息作出较高精度预测，同时也可以利用自编码器强大的特征表达能力增加模型的泛化能力和预测效果的稳定性。
The invention discloses a foundation pit deformation monitoring method and system, and the method comprises the steps: obtaining foundation pit monitoring data, determining a prediction index and a feature index of a foundation pit, carrying out the data preprocessing of the selected monitoring data, carrying out the feature extraction of the preprocessed foundation pit monitoring data through a variational auto-encoder, and constructing an original time series data set; and sliding the time window to construct a sample data set, inputting the sample data set into the trained LSTM model for training to obtain low-dimensional hidden features, performing model optimization on the LSTM model, and inputting a test set into the optimized LSTM foundation pit deformation prediction model. A mean square error, a mean absolute error and a decision coefficient are used as evaluation indexes to evaluate a model prediction effect, and the foundation pit deformation prediction model can make full use of time information of time sequence data to make high-precision prediction; and meanwhile, the generalization ability of the model and the stability of the prediction effect can be improved by utilizing the strong feature expression ability of the auto-encoder.
本发明公开了一种基坑变形监测方法及系统，通过获取基坑监测数据并确定基坑的预测指标与特征指标，将选取好的监测数据进行数据预处理，将预处理后的基坑监测数据通过变分自编码器进行特征提取并构造出原始时序数据集，时间窗滑动以构建样本数据集，将样本数据集输入至已训练的LSTM模型进行训练得到具有低维隐藏特征，对LSTM模型进行模型优化并将测试集输入到优化后的LSTM基坑变形预测模型中，使用均方误差、平均绝对误差和决定系数作为评价指标对模型预测效果进行评估，基坑变形预测模型不仅能够充分利用时序数据的时间信息作出较高精度预测，同时也可以利用自编码器强大的特征表达能力增加模型的泛化能力和预测效果的稳定性。
Foundation pit deformation monitoring method and system
一种基坑变形监测方法及系统
MENG JUN (author)
2023-05-02
Patent
Electronic Resource
Chinese
IPC:
G06F
ELECTRIC DIGITAL DATA PROCESSING
,
Elektrische digitale Datenverarbeitung
/
E02D
FOUNDATIONS
,
Gründungen
/
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
/
G06Q
Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke
,
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES
Foundation pit deformation intelligent monitoring method and system
| European Patent Office | 2022
Foundation pit deformation monitoring device and monitoring method
| European Patent Office | 2024
Automatic deformation monitoring system for foundation pit
| European Patent Office | 2021