# US 2016/0238438 A1 · Determining a health condition of a structure

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0238438 A1
- Document ID: US20160238438A1
- Status: Published application
- Kind: A1
- Application number: 14/787,912
- Filed: 2013-11-22
- Published: 2016-08-18
- Earliest claimed: 2013-05-01
- Assignees: National ICT Australia Limited
- Applicants: National Ict Australia Limited
- Inventors: FANG CHEN; Matt ZHANG; Zhidong LI; Yang WANG
- Web page: https://patentgrep.com/patent/US20160238438A1

## CPC

- G01H 13/00: Measuring resonant frequency
- G01H 1/00: Measuring {characteristics of} vibrations in solids by using direct conduction to the detector (G01H9/00, G01H11/00 take precedence)
- G01M 5/0008: {of bridges}
- G01M 5/0033: {by determining damage, crack or wear}
- G01M 5/0066: {by exciting or detecting vibration or acceleration (vibration testing of structures G01M7/00)}
- G01M 7/00: Vibration-testing of structures; Shock-testing of structures (G01M9/00 takes precedence)
- G01M 7/025: {Measuring arrangements}
- G01H: MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR

## Abstract

The disclosure relates to structural health monitoring (SHM). In particular determining a health condition of a structure, such as a bridge, based on vibration data measured of the bridge. Measured vibration data is calibrated (410-450). Features are then extracted from the calibrated data (610-630) and a support vector machine classifier is then applied (720) to the extracted features to determine (730) the health condition of a part of the structure. Training of the support vector machine classifier by a machine learning process (910) is also described.

## Claims

### Claim 1

A computer-implemented method for determining a health condition of a part of a structure, comprising:
receiving or accessing vibration data of the part of the structure, the vibration data being measured by at least one accelerometer;
extracting a feature of the vibration data based on frequency analysis of the vibration data; and
determining the health condition of the part of the structure by a support vector machine classifier based on the feature of the vibration data.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the vibration data comprises data in rest and data in movement, wherein the data in rest represents acceleration of the part of the structure substantially caused by ambient factors, and the data in movement represents acceleration of the part of the structure substantially caused by an external vibration source.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the method further comprising:
calibrating coordinate axis directions of the at least one accelerometer based on the vibration data of the part of the structure by principal component analysis to calibrate the vibration data.

### Claim 4 (depends on 3)

The method according to claim 3, wherein calibrating coordinate axis directions of the at least one accelerometer comprises aligning X axis direction of the at least one accelerometer with a direction along which the external vibration source moves based on the data in movement.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the vibration data is stored in a datastore and the determined health score is stored in the same or different datastore.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the frequency analysis comprises fast Fourier transform of the vibration data.

### Claim 7 (depends on 6)

The method according to claim 6, the feature of the vibration data comprises amplitude spectrums of the fast Fourier transform of the vibration data.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the support vector machine classifier comprises a classification function g taking a form of g(E)=wE−b, where E represents the feature of the vibration data, wand bare parameters determined by a machine learning process.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the machine learning process comprises an unsupervised machine learning process.

### Claim 10 (depends on 1)

A non-transitory computer-readable medium, including computer-executable instructions, stored thereon that when executed by a processor, causes the processor to perform the method of claim 1.

### Claim 11

A system for determining a health condition of a part of a structure, the system comprising:
a data acquisition unit, configured to receive or access vibration data of the part of the structure, the vibration data being measured by at least one accelerometer;
a feature extraction unit connected to the data acquisition unit, the feature extraction unit being configured to extract a feature of the vibration data based on frequency analysis of the vibration data; and
a health condition determination unit connected to the feature extraction unit, the health condition determination unit being configured to determine the health condition of the part of the structure by a support vector machine classifier based on the feature of the vibration data.

### Claim 12

A computer-implemented method for training a support vector machine classifier for use in determining a health condition of a part of a structure, the method comprising:
receiving or accessing vibration data of one or more parts of one or more structures measured by one or more accelerometers;
extracting two or more features of the vibration data based on frequency analysis of the vibration data; and
applying a machine learning process to determine the support vector machine classifier based on the two or more features of the vibration data.

### Claim 13 (depends on 12)

A non-transitory computer-readable medium including computer-executable instructions, stored thereon that when executed by a processor, causes the processor to perform the method of claim 12.

### Claim 14

A system for training a support vector machine classifier for use in determining a health condition of a part of a structure, the system comprising:
a data acquisition unit, configured to receive or access vibration data of one or 5 more parts of one or more structures measured by one or more accelerometers;
a feature extraction unit connected to the data acquisition unit, the feature extraction unit being configured to extract two or more features of the vibration data by frequency analysis of the vibration data; and
a support vector machine trainer unit connected to the feature extraction unit, the support vector machine trainer unit being configured to apply a machine learning process to determine the support vector machine classifier based on the two or more features of the vibration data.
