Method and system for detecting and identifying thermal defects

Abstract

A system and related method for thermal inspection of structures are provided. The method provides an unmanned aerial vehicle (UAV) comprising a thermal camera for capturing thermal image data, a visible light camera for capturing visible light image data, and a positioning system for acquiring positioning data, and includes operating the UAV by flying it along a predetermined flight path around the structure to be inspected, and simultaneously capturing thermal image data, visible light image data, and positioning data of the structure to be inspected at regular intervals while the UAV is flying along the flight path.

Claims

1. A thermal testing method, A step of providing an unmanned aerial vehicle (UAV), wherein the UAV comprises a thermal camera for capturing thermal image data, a visible light camera for capturing visible light image data, and a positioning system for capturing positioning data. The steps include operating the UAV by having it fly along a predetermined flight path around the inspection structure, The steps include simultaneously capturing thermal image data of the inspection structure, visible light image data of the inspection structure, and positioning data at regular intervals while the UAV is flying along the flight path, The steps include defining the boundary around the building element in the thermal image data, A step of identifying the highest temperature pixel within the boundary of the building element, wherein the highest temperature pixel is associated with the highest temperature, The steps include defining a pixel region around the highest temperature pixel according to the provided maximum walk parameters, Steps include expanding the pixel region by the provided maximum step parameter and defining the expanded pixel region, A thermal inspection method comprising the step of analyzing the shape of the enlarged pixel region to identify a thermal anomaly.

2. The method according to claim 1, A step of calculating the heat loss rate of the aforementioned building element, A step of estimating the heat loss rate of the building elements in the case where the aforementioned thermal anomaly does not exist, A method further comprising the step of outputting a comparison between an estimated heat loss rate and a calculated heat loss rate.

3. A method according to claim 1 or 2, wherein the temperature characteristics of the enlarged pixel region are analyzed to identify a thermal anomaly.

4. A method according to any one of claims 1 to 3, wherein the parameters for the maximum step and the maximum walk are provided to the method by a human operator.

5. A method according to any one of claims 1 to 4, further comprising the step of classifying the thermal anomaly as a known thermal anomaly class.

6. A method according to any one of claims 1 to 5, wherein the step of analyzing the shape of the enlarged pixel region to identify a thermal anomaly further comprises the step of comparing the shape of the enlarged pixel region with the shape of a known thermal anomaly.

7. A method according to any one of claims 1 to 6, further comprising the step of generating a thermal loss map, which is a thermal loss map corresponding to the building envelope of the inspection structure, and which shows the thermal loss rate of the inspection structure.

8. A method according to any one of claims 1 to 7, further comprising the step of analyzing the shape of the enlarged pixel region to identify a thermal anomaly, by applying a machine learning model trained to analyze the shape.

9. A method according to claim 8, wherein the trained machine learning model is pre-trained using known thermal anomaly data.

10. A method according to claim 8 or 9, wherein the trained machine learning model includes a neural network.

11. A thermal inspection system, An unmanned aerial vehicle (UAV) comprising a thermal camera for capturing thermal image data, a visible light camera for capturing visible light image data, and a positioning system for capturing positioning data, An inspection structure for inspection using the aforementioned UAV, Equipped with a processor, The UAV is configured to fly along a predetermined flight path around the inspection structure and to simultaneously capture thermal image data, visible light image data, and positioning data of the inspection structure at regular intervals while the UAV is flying along the flight path. The aforementioned processor, Define the boundary around the building element in the thermal image data, Identify the highest temperature pixel within the boundary of the building element, and the highest temperature pixel is associated with the highest temperature. According to the provided maximum walk parameters, define the pixel region around the highest temperature pixel, The pixel area is expanded by the provided maximum step parameter, and the expanded pixel area is defined. A system configured to identify thermal anomalies by analyzing the shape of the enlarged pixel region.

12. The system according to claim 11, wherein the processor further The heat loss rate of the aforementioned building elements is calculated, The heat loss rate of the building element is estimated assuming that the aforementioned thermal anomaly does not exist. A system configured to output a comparison between the estimated heat loss rate and the calculated heat loss rate.

13. A system according to claim 11 or 12, wherein the temperature characteristics of the enlarged pixel region are analyzed to identify a thermal anomaly.

14. A system according to any one of claims 11 to 13, wherein the parameters for maximum step and maximum walk are provided to the method by a human operator.

15. A system according to any one of claims 11 to 14, wherein the processor is further configured to classify the thermal anomaly as a known thermal anomaly class.

16. A system according to any one of claims 11 to 15, further comprising: analyzing the shape of the enlarged pixel region to identify a thermal anomaly; comparing the shape of the enlarged pixel region with the shape of a known thermal anomaly.

17. A system according to any one of claims 11 to 16, wherein the processor is further configured to generate a thermal loss map, which is a thermal loss map corresponding to the building envelope of the inspection structure, and which shows the thermal loss rate of the inspection structure.

18. A system according to any one of claims 11 to 17, further comprising: analyzing the shape of the enlarged pixel region to identify a thermal anomaly; applying a machine learning model trained to analyze the shape.

19. The system according to claim 18, wherein the trained machine learning model is pre-trained using known thermal anomaly data.

20. A system according to claim 18 or 19, wherein the trained machine learning model includes a neural network.

Images