Dynamic Feature Extraction Software for Structural Health Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing structural health monitoring (SHM) systems face challenges in extracting dynamic features from data sets due to the lack of a generic, user-friendly approach, leading to inadequate and unreliable detection of structural deterioration in structures like bridges and buildings.
Innovation Solution
A software tool that utilizes time-domain analysis, frequency domain decomposition, and eigensystem realization algorithms to extract dynamic features from SHM data sets, guiding users through parameter selection and automatically performing the chosen method to determine frequencies and modal shapes, with graphical representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual visual inspection is performed, then inspection can be conducted with simple equipment, but the inspection is time-consuming, labor-intensive, and unreliable for detecting hidden deterioration
Solution Approach 1:
The patent replaces manual visual inspection with an automated SHM system that uses sensors (accelerometers, strain gauges, corrosion sensors) to collect structural data. The system substitutes human engineers with automated data acquisition units and software tools that continuously monitor structural conditions, eliminating the time-consuming manual inspection process while improving detection reliability through objective, continuous measurement.
Solution Approach 2:
The SHM system enables structures to self-monitor their own condition through embedded sensors and data acquisition units. The system automatically collects, stores, and processes structural data without requiring external manual inspection, allowing the structure to provide its own health assessment through continuous self-measurement and data generation.
2Reliability
If automated SHM systems with multiple sensors are deployed, then detection capability is improved, but the system complexity and difficulty of extracting dynamic features increase
Solution Approach 1:
The patent introduces software tools as intermediary components that bridge the gap between raw sensor data and useful structural information. These tools automatically perform feature extraction, transform complex multi-sensor data into meaningful dynamic features (frequencies, modal shapes), and present results in user-friendly formats, thereby reducing the complexity burden on users while maintaining high detection reliability.
Solution Approach 2:
The software tool is designed as a universal platform that can process data from multiple sensor types and perform various analysis functions (time-domain analysis, frequency domain decomposition, eigensystem realization). This multi-functional approach consolidates what would otherwise be multiple separate complex systems into a single unified tool, improving reliability while managing complexity through integration.
3Measurement precision
If comprehensive feature extraction methods are used, then detection precision is improved, but the ease of operation decreases due to complex parameter selection requirements
Solution Approach 1:
The software tool performs preliminary computation of effective parameter values and pre-processes the data to identify meaningful features before the user needs to interpret results. The system automatically determines which parameters are most relevant for the given structural data, eliminating the need for users to manually select from complex parameter sets while maintaining high measurement precision through sophisticated automated feature extraction.
Solution Approach 2:
The tool incorporates feedback mechanisms that automatically adjust parameter selection and extraction methods based on the input data characteristics. The system evaluates the data and adapts its processing approach in real-time, providing guidance to users while maintaining optimal precision. This feedback loop ensures that comprehensive feature extraction is achieved automatically, reducing operational complexity for the user.
Data Source
AI summary
In an example embodiment, a dynamic feature extraction tool receives a data set from a SHM system that includes a plurality of sensors affixed to a structure (e.g., a bridge, dam, building, etc.), the data set including at least one of ambient vibration data or earthquake vibration data. A solution method is selected from among, for example, time domain analysis, frequency domain decomposition or eigensystem realization analysis. The dynamic feature extraction tool guides a user to select at least one parameter value used in the selected solution method from a subset of determined-effective parameter values computed by the software tool. The dynamic feature extraction tool then automatically performs the selected solution method on the data set using the selected at least one parameter value to determine dynamic features (e.g., frequencies or modal shapes), and displays a graphical representation of the dynamic features in a UI.