Visual systems and statistical methods for non-destructively evaluating component parts
AssigneeThe Boeing Company
InventorDavid Michael Gayle
Life of this patent
Estimating the term…
Abstract
A system and a method include a light emitter configured to emit light onto or into a part to illuminate the part. A detector is configured to acquire one or more digital images of the part as illuminated by the light. A control unit is in communication with the detector. The control unit is configured to receive the one or more digital images of the part as illuminated by the light from the detector, and automatically analyze the one or more digital images of the part (to normalize out, such as by removing, known geometric features) as illuminated by the light to one or both of detect one or more defects of the part, or determine a porosity of the part.
Claims21
A system comprising:
- a light emitter including one or more light emitting diodes (LEDs) configured to emit light onto or into a part to illuminate the part;
- a detector including a digital camera configured to acquire one or more digital images of the part as illuminated by the light;
- and
- a control unit including one more processors, wherein the control unit is in communication with the detector, wherein the control unit is configured to:
- receive the one or more digital images of the part as illuminated by the light from the detector,
- automatically select a region of interest within the one or more digital images, wherein the region of interest is automatically selected as a limited sample area to provide a reference area that is devoid of extraneous features,
- generate a histogram with respect to the region of interest, wherein the histogram includes a mean and a standard deviation, wherein the light emitter is changed in response to one or both of the mean or the standard deviation being unacceptable, and
- in response to the mean and the standard deviation being acceptable, automatically analyze the one or more digital images of the part as illuminated by the light to perform one or both of detecting one or more defects of the part, or determining a porosity of the part.
A method for a system comprising:
- a light emitter including one or more light emitting diodes (LEDs) configured to emit light onto or into a part to illuminate the part;
- a detector including a digital camera configured to acquire one or more digital images of the part as illuminated by the light;
- and
- a control unit including one more processors, wherein the control unit is in communication with the detector, wherein the control unit is configured to:
- receive the one or more digital images of the part as illuminated by the light from the detector,
- automatically select a region of interest within the one or more digital images, wherein the region of interest is automatically selected as a limited sample area to provide a reference area that is devoid of extraneous features,
- generate a histogram with respect to the region of interest, wherein the histogram includes a mean and a standard deviation, wherein the light emitter is changed in response to one or both of the mean or the standard deviation being unacceptable, and
- in response to the mean and the standard deviation being acceptable, automatically analyze the one or more digital images of the part as illuminated by the light to perform one or both of detecting one or more defects of the part, or determining a porosity of the part,
- the method comprising:
- emitting, by the light emitter, the light onto or into the part to illuminate the part;
- acquiring, by the detector, the one or more digital images of the part as illuminated by the light;
- receiving, by the control unit, the one or more digital images of the part as illuminated by the light from the detector;
- automatically selecting, by the control unit, the region of interest within the one or more digital images;
- generating, by the control unit, the histogram with respect to the region of interest;
- and
- in response to the mean and the standard deviation being acceptable, automatically analyzing, by the control unit, the one or more digital images of the part as illuminated by the light, wherein said automatically analyzing comprises one or both of detecting the one or more defects of the part, or determining the porosity of the part.
A system comprising:
- a light emitter including one or more light emitting diodes (LEDs) configured to emit light onto or into a part to illuminate the part, wherein the light emitter is separated from the part;
- a detector including a digital camera configured to acquire one or more digital images of the part as illuminated by the light, wherein the detector comprises a digital camera;
- a control unit including one more processors, wherein the control unit is in communication with the detector, wherein the control unit is configured to:
- receive the one or more digital images of the part as illuminated by the light from the detector,
- automatically select a region of interest within the one or more digital images, wherein the region of interest is automatically selected as a limited sample area to provide a reference area that is devoid of extraneous features,
- generate a histogram with respect to the region of interest, wherein the histogram includes a mean and a standard deviation, wherein the light emitter is changed in response to one or both of the mean or the standard deviation being unacceptable, and
- in response to the mean and the standard deviation being acceptable, automatically analyze the one or more digital images of the part as illuminated by the light to detect one or more defects of the part, and determine a porosity of the part, wherein the control unit is configured to automatically analyze the one or more digital images by determining a signal-to-noise ratio (SNR) of one or more portions of the one or more digital images;
- and
- a user interface in communication with the control unit, wherein the user interface comprises a display, and wherein the control unit is configured to show information regarding the part on the display.
Dependencies are inferred from the claim text.