Method for detecting anomalies on or in the surface of a structure

A method of detecting anomalies on a surface of a structure comprising:

• taking a thermal image of the surface of the structure,
• conducting a thermal image numerical analysis on the thermal image wherein the thermal image numerical analysis comprises the steps of:
• i. obtaining a thermal image numerical value table comprising a plurality of pixels with each pixel having an X coordinate, a Y coordinate, and a Z coordinate with the X coordinate and the Y coordinate corresponding to a specific spatial location of the pixel on the surface of the structure, and the Z coordinate corresponding to a thermal value of said pixel which is a real number greater than or equal to 0;
• ii. obtaining a surface nominal thermal value;
• iii eliminating a first subset of pixels from the plurality of pixels wherein each of the first subset of pixels has a thermal value which is within a nominal thermal variation of a surface material of the surface to the surface nominal thermal value;
• iv. comparing a thermal value of each pixel of the plurality of pixels not in the first subset of pixels to the surface nominal thermal value to identify at least one anomaly;
• v. comparing the thermal value of a second number (n2) of a second anomalies from the thermal image numerical value table wherein n2 is an integer greater than or equal to 0 to the surface nominal thermal value in order to identify a type of anomaly selected from a group consisting of an energy loss anomaly, and a live load anomaly, and
• vi. removing a first number (ni) of first anomalies from the thermal image numerical value table wherein ni is an integer greater than or equal to 0, and the first anomalies are selected from the group consisting of at least one non-delta anomaly, at least one non-signature anomaly, at least one non-pattern anomaly, at least one non-visual anomaly, and at least one non-cavity anomaly.