DETECTION AND CHARACTERIZATION OF WELDING DEFECTS

1 . A method comprising:

receiving, from an imaging device, an inspection image of a target object;

determining an inspection thickness of the target object based on the inspection image;

converting into a multilevel thresholded thickness map based on a particular sensitivity;

determining a defect of the target object based on the inspection thickness;

quantifying and characterizing the defect;

determining a critical level of the defect of the target object by comparing a parameter of the defect to a critical threshold; and

generating a recommendation based on the critical level.

2 . The method of claim 1 , wherein the target object comprises a portion of an industrial asset, wherein the portion of the industrial asset comprises a pipe wall at a first location of an insulated pipe.

3 . The method of claim 1 , further comprising:

identifying seed points on the multilevel thresholded image; and

region growing the seed points to determine the spatial extents of defects.

4 . The method of claim 1 , wherein quantifying and characterizing the defect comprises:

determining a loss of material or a gain of material;

determining a size of the defect;

estimating a shape of the defect by determining image metrics comprising an aspect ratio, a perimeter, or a moment of inertia; and

determining a location of the defect.

5 . The method of claim 1 , wherein generating the recommendation comprises an instruction for a repairing device to automatically repair the target object by correcting the defect.

6 . The method of claim 1 , wherein the recommendation is generated using a defect characterization application comprising a predictive model.

7 . The method of claim 1 , further comprising:

providing the recommendation based on the critical level in a display of a processing system, the display comprising a highlight of the defect atop a color map of the inspection image.

8 . The method of claim 1 , wherein the defect comprises a material loss measurement or a material gain measurement of the pipe wall.

9 . The method of claim 1 , wherein the imaging device comprises a radiographic source, a radiographic detector, and a crawler device including a processor, a controller, and a plurality of positioning mechanisms configured to position the radiographic source and the radiographic detector at one or more locations along a length of the target object.

10 . A system comprising:

a memory; and

a processor, coupled to the memory, the processor configured to perform operations including

receiving, from an imaging device, an inspection image of a target object;

determining an inspection thickness of the target object based on the inspection image;

converting into a multilevel thresholded thickness map based on a particular sensitivity;

determining a defect of the target object based on the inspection thickness;

quantifying and characterizing the defect;

determining a critical level of the defect of the target object by comparing a parameter of the defect to a critical threshold; and

generating a recommendation based on the critical level.

11 . The system of claim 10 , wherein the target object comprises a portion of an industrial asset, wherein the portion of the industrial asset comprises a pipe wall at a first location of an insulated pipe.

12 . The system of claim 10 , wherein the operations further comprise:

identifying seed points on the multilevel thresholded image;

region growing the seed points to determine the spatial extents of defects;

determining a loss of material or a gain of material;

determining a size of the defect;

estimating a shape of the defect by determining image metrics comprising an aspect ratio, a perimeter, or a moment of inertia; and

determining a location of the defect.

13 . The system of claim 10 , wherein generating the recommendation comprises an instruction for a repairing device to automatically repair the target object by correcting the defect, wherein the recommendation is generated using a defect characterization application comprising a predictive model.

14 . The system of claim 10 , wherein the defect comprises a material loss measurement or a material gain measurement of the pipe wall.

15 . The system of claim 10 , wherein the imaging device comprises a radiographic source, a radiographic detector, and a crawler device including a processor, a controller, and a plurality of positioning mechanisms configured to position the radiographic source and the radiographic detector at one or more locations along a length of the target object.

16 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor that comprises at least one physical core and a plurality of logical cores, cause the at least one programmable processor to perform operations comprising:

receiving, from an imaging device, an inspection image of a target object;

determining an inspection thickness of the target object based on the inspection image;

converting into a multilevel thresholded thickness map based on a particular sensitivity;

determining a defect of the target object based on the inspection thickness;

quantifying and characterizing the defect;

determining a critical level of the defect of the target object by comparing a parameter of the defect to a critical threshold; and

generating a recommendation based on the critical level.

17 . The computer program product of claim 16 , wherein the target object comprises a portion of an industrial asset, wherein the portion of the industrial asset comprises a pipe wall at a first location of an insulated pipe.

18 . The computer program product of claim 16 , wherein the operations further comprise:

identifying seed points on the multilevel thresholded image;

region growing the seed points to determine the spatial extents of defects;

determining a loss of material or a gain of material;

determining a size of the defect;

estimating a shape of the defect by determining image metrics comprising an aspect ratio, a perimeter, or a moment of inertia; and

determining a location of the defect.

19 . The computer program product of claim 16 , wherein generating the recommendation comprises an instruction for a repairing device to automatically repair the target object by correcting the defect, wherein the recommendation is generated using a defect characterization application comprising a predictive model.

20 . The computer program product of claim 16 , wherein the defect comprises a material loss measurement or a material gain measurement of the pipe wall.