Check patentability & draft patents in minutes with Patsnap Eureka AI!

Structural health monitoring data detection method and device based on multi-modal neural network

A health monitoring and neural network technology, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as false alarms and economic losses in structural safety status assessment, alleviate imbalance problems, improve accuracy, Good classification performance

Pending Publication Date: 2022-04-15
GUANGZHOU UNIVERSITY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Abnormal data may lead to false positives in structural safety status assessment, causing unnecessary economic losses

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
  • Structural health monitoring data detection method and device based on multi-modal neural network
  • Structural health monitoring data detection method and device based on multi-modal neural network
  • Structural health monitoring data detection method and device based on multi-modal neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described in conjunction with the following application scenarios.

[0035] see figure 1 , which shows a multimodal neural network-based detection method for structural health monitoring data, including:

[0036] S0 trains the data anomaly detection model based on the multimodal deep learning network.

[0037] In one embodiment, see figure 2 , step S0 specifically includes:

[0038] Obtain sample monitoring data;

[0039] Marking the sample monitoring data to obtain the detection result identification corresponding to the sample monitoring data;

[0040] Preprocessing the sample monitoring data to obtain a feature data set of the sample monitoring data, and forming a training set from the feature data set of the sample monitoring data and the detection result identification;

[0041] The obtained training set is used to train the data anomaly detection model based on the multimodal deep learning network, and the trained data a...

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 provides a structural health monitoring data detection method and device based on a multi-modal neural network, and the method comprises the steps: S1, obtaining structural health monitoring data; s2, the obtained structural health monitoring data are preprocessed, a feature data set of the structural health monitoring data is obtained, and the feature data set comprises original data and a time-frequency graph of the structural health monitoring data; and S3, inputting the obtained feature data set into the trained data anomaly detection model based on the multi-modal deep learning network to obtain an output data detection result. According to the invention, anomaly detection is carried out on the sensor data through the data anomaly detection model based on the multi-modal deep learning network, the model can identify most of distorted data, the classification performance is good, and the accuracy of abnormal data detection is improved.

Description

technical field [0001] The invention relates to the technical field of bridge structure health monitoring, in particular to a method and device for detecting structural health monitoring data based on a multimodal neural network. Background technique [0002] Structural health monitoring system (SHM) is widely used in civil infrastructure such as bridges and roads. It aims to identify structural damage in a timely manner by monitoring structural response and evaluating structural performance in real time. It is an important research direction in the field of civil engineering [1]. Structural health monitoring systems are installed on more and more bridges. Among them, sensors are used to obtain structural response and other various monitoring information. Collecting accurate data through sensors is an important task for SHM. However, when processing and analyzing bridge health monitoring data, it is often found that some special data or data segments behave significantly d...

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): G06F30/13G06F30/27G06F119/02
CPCG06F30/13G06F30/27G06F2119/02
Inventor 叶锡钧湛晓宇何沛衡潘楚东邓军汪大洋周军勇刘爱荣陈炳聪
Owner GUANGZHOU UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com