SYSTEM AND METHOD FOR DETECTING AND CLASSIFYING LOADING OF A STRUCTURE USING STRAIN MEASUREMENTS
A system includes a sensor network comprising a network of optical sensors coupled to structural members of a structure loaded by vehicles or by an environmental event. A processor is operatively coupled to the sensor network. The processor is configured to receive the strain measurements from the network of optical sensors, calculate total strain energy using the received strain measurements, detect a heavy load on the structure in response to the total strain energy exceeding a total strain energy threshold developed for the structure, and determine whether the heavy load results from a superload vehicle or the environmental event. A transmitter is operatively coupled to the processor and configured to transmit one or both of an alert and a condition assessment report for the structure to a predetermined location in response to determining that the heavy load results from the superload vehicle or the environmental event.
1 . A method, comprising:
receiving strain measurements from a network of optical sensors coupled to a structure loaded by vehicles or by an environmental event;
calculating total strain energy using the received strain measurements;
detecting a heavy load on the structure in response to the total strain energy exceeding a total strain energy threshold developed for the structure; and
determining whether the heavy load results from a superload vehicle or the environmental event.
2 . The method of claim 1 , comprising automatically generating one or both of a report and an alert in response to determining that the heavy load results from the superload vehicle or the environmental event.
3 . The method of claim 2 , wherein the report comprises a condition assessment of the structure.
4 . The method of claim 1 , comprising:
summing the strain measurements acquired from a key load supporting member of the structure; and
calculating the total strain energy using the summed strain measurements acquired from the key load supporting member.
5 . The method of claim 4 , comprising adjusting the total strain energy calculated for the key load supporting member based on a skew angle of the structure.
6 . The method of claim 1 , wherein the total strain energy threshold is developed using weight, equivalent force, or a boundary condition of a representative heavy load applied to a reduced-order physics-based model of the structure.
7 . The method of claim 1 , wherein:
detecting the heavy load vehicle comprises picking a peak of the total strain energy; and
comparing the peak of the total strain energy to the total strain energy threshold.
8 . The method of claim 1 , comprising:
computing the speed of each event of heavy load vehicle detection; and
filtering out events having a speed which is beyond an expected or known speed threshold.
9 . The method of claim 1 , wherein determining whether the heavy load results from the superload vehicle or the environmental event comprises:
computing the speed of each event of heavy load detection;
resampling strain profiles for all events to have the same speed and amplitude;
calculating normalized correlation between the resampled strain profiles to produce an N×N correlation matrix, where N is a number of the detected events; and
classifying resampled strain profiles of the correlation matrix as corresponding to superload vehicles, environmental events, non-superload vehicles, and non-environmental events.
10 . The method of claim 9 , wherein classifying resampled strain profiles of the correlation matrix is based on ground truth data.
11 . The method of claim 10 , wherein the ground truth data comprises one or more of camera data, GPS data acquired from GPS instrumented vehicles, seismometer data, and weather data for extreme weather events.
12 . A system, comprising:
a sensor network comprising a network of optical sensors coupled to structural members of a structure loaded by vehicles or by an environmental event;
a processor operatively coupled to the sensor network and configured to:
receive the strain measurements from the network of optical sensors;
calculate total strain energy using the received strain measurements;
detect a heavy load on the structure in response to the total strain energy exceeding a total strain energy threshold developed for the structure; and
determine whether the heavy load results from a superload vehicle or the environmental event; and
a transmitter operatively coupled to the processor and configured to transmit one or both of an alert and a condition assessment report for the structure to a predetermined location in response to determining that the heavy load results from the superload vehicle or the environmental event.
13 . The system of claim 12 , wherein the processor is configured to automatically generate one or both of the report and the alert in response to determining that the heavy load results from the superload vehicle or the environmental event.
14 . The system of claim 13 , wherein the report comprises a condition assessment of the structure.
15 . The system of claim 12 , wherein the processor is configured to:
sum the strain measurements acquired from a key load supporting member of the structure; and
calculate the total strain energy using the summed strain measurements acquired from the key load supporting member.
16 . The system of claim 15 , wherein the processor is configured to adjust the total strain energy calculated for the key load supporting member based on a skew angle of the structure.
17 . The system of claim 12 , wherein the total strain energy threshold is developed using weight, equivalent force, or a boundary condition of a representative heavy load applied to a reduced-order physics-based model of the structure.
18 . The system of claim 12 , wherein the processor is configured to:
detect the heavy load vehicle by picking a peak of the total strain energy; and
compare the peak of the total strain energy to the total strain energy threshold.
19 . The system of claim 12 , wherein the processor is configured to:
compute the speed of each event of heavy load vehicle detection; and
filter out events having a speed which is beyond an expected or known speed threshold.
20 . The system of claim 12 , wherein the processor is configured to determine whether the heavy load results from the superload vehicle or the environmental event by:
computing the speed of each event of heavy load detection;
resampling strain profiles for all events to have the same speed and amplitude;
calculating normalized correlation between the resampled strain profiles to produce an N×N correlation matrix, where N is a number of the detected events; and
classifying resampled strain profiles of the correlation matrix as corresponding to superload vehicles, environmental events, non-superload vehicles, and non-environmental events.
21 . The system of claim 20 , wherein the processor is configured to classify resampled strain profiles of the correlation matrix based on ground truth data.
22 . The system of claim 21 , wherein the ground truth data comprises one or more of camera data, GPS data acquired from GPS instrumented vehicles, seismometer data, and weather data for extreme weather events.