Unlock instant, AI-driven research and patent intelligence for your innovation.

Bridge static displacement prediction technology based on deep learning LSTM network

A technology of static displacement and deep learning, which is applied in the field of bridge structure safety, can solve problems such as difficulty in meeting bridge safety expectations and lack of bridge prediction, and achieve the effect of accurate judgment

Pending Publication Date: 2021-05-11
杭州鲁尔物联科技有限公司
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above-mentioned technical solutions only survey the status quo of the bridge, lack the prediction of the bridge, and are difficult to meet the expected judgment on the safety of the bridge

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bridge static displacement prediction technology based on deep learning LSTM network
  • Bridge static displacement prediction technology based on deep learning LSTM network
  • Bridge static displacement prediction technology based on deep learning LSTM network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Embodiment: a kind of bridge static displacement prediction technology based on deep learning LSTM network of the present embodiment, such as figure 1 shown, including the following steps:

[0035] (1) Collect bridge deflection static response monitoring data;

[0036] (2) Preprocessing by bridge deflection data;

[0037] (3) Establish LSTM neural network for training;

[0038] (4) Use the trained LSTM neural network model to predict the bridge deflection.

[0039] The bridge deflection data in step 2 are preprocessed by zero-mean normalization method. The specific formula is as follows.

[0040]

[0041] In the formula: x' i Forecast data normalized for the i-th moment; x i is the forecast data at the i-th moment, σ is the standard deviation of the data, and u is the average value of the data.

[0042] The LSTM neural network in step 3 is an improved RNN network. By adding input gates, output gates, forgetting gates and cell states, the weight parameters of t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a bridge static displacement prediction technology based on a deep learning LSTM network. The technology comprises the following steps: collecting bridge deflection static response monitoring data; carrying out preprocessing through the bridge deflection data; establishing an LSTM neural network for training; and predicting the deflection of the bridge by using the trained LSTM neural network model. According to the technical scheme, based on the deep learning artificial intelligence algorithm LSTM RNN and the long short-term memory recurrent neural network, the sample data is obtained from the deflection monitoring data of the bridge to perform neural network model training, and the bridge deflection is predicted from the neural network model trained by the past bridge deflection information. Finally, the purpose of predicting and early warning the deflection of the bridge is achieved, and evaluation of the working performance of the bridge and accurate judgment of the structural safety are achieved.

Description

technical field [0001] The invention relates to the technical field of bridge structure safety, in particular to a bridge static displacement prediction technology based on a deep learning LSTM network. Background technique [0002] The static displacement of the bridge is an important monitoring content of the bridge structure safety monitoring. The change of the bridge deflection can most directly reflect the change of the overall vertical stiffness and bearing capacity of the bridge. The prediction of the deformation trend of the bridge structure can contribute to the assessment of the performance of the bridge and the early warning of the structural safety. [0003] Some data show that the commonly used forecasting models have certain defects, which cannot better meet the accuracy requirements, which will inevitably lead to large errors and lead to unreliable forecasting results. At present, the monitoring data of bridge deflection has many outliers due to environmental...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F30/13G06F30/27G06N3/04G06N3/08
CPCG06F30/13G06F30/27G06N3/08G06N3/044G06N3/045
Inventor 康春光包元锋胡辉
Owner 杭州鲁尔物联科技有限公司