Inspection system and method for damage measurement

Abstract

A system may include sensors including sensors configured to capture data from a part of an engine. The system is configured to form a three-dimensional (3D) surface model of a part of the engine based on signals received from the sensor system, determine a non-planar reference surface based on the 3D surface model of the part, and measure a characteristic of a damaged portion of the part of the engine based on the 3D surface model and the non-planar reference surface.

Description

Technical Field

[0001] The present subject matter relates generally to an imaging tool, and in particular to a three-dimensional (3D) imaging tool for inspection. Background Art

[0002] Complex equipment, such as jet engines, can suffer damage during daily use, leading to performance degradation and failure. Wear and tear can occur at various locations on the equipment, including internal areas that are difficult to access without disassembling the equipment. Insertion imaging systems, such as borescopes, can be inserted through inspection ports to inspect the interior of a jet engine. Traditionally, anomaly measurements are made based on manually selected reference points in the captured image. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] A full and enabling disclosure of the present disclosure, including the best mode thereof, to one of ordinary skill in the art is set forth in the specification with reference to the accompanying drawings, in which:

[0004] Figure 1 is a schematic cross-sectional view of a high bypass turbofan jet engine according to some embodiments of the present disclosure.

[0005] Figure 2 is a block diagram of an inspection system according to some embodiments of the present disclosure;

[0006] Figure 3 is a flowchart of a method according to some embodiments of the present disclosure; and

[0007] Figure 4A , 4B , 4C and 4D are illustrations of a reference surface estimation process according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0008] Reference will now be made in detail to embodiments of the present disclosure, one or more examples of which are illustrated in the accompanying drawings. Each example is provided in a manner to explain the present disclosure, rather than to limit the present disclosure. In fact, it will be apparent to those skilled in the art that various modifications and variations may be made in the present disclosure without departing from the scope or spirit of the present disclosure. For example, a feature illustrated or described as part of one embodiment may be used together with another embodiment to produce yet another embodiment. Therefore, the present disclosure is intended to encompass such modifications and variations that fall within the scope of the appended claims and their equivalents.

[0009] As used herein, the terms "first," "second," "third," etc. may be used interchangeably to distinguish one component from another, and are not intended to indicate the position or importance of each component.

[0010] Unless otherwise specified herein, the terms "coupled," "fixed," "attached to," and the like refer to both direct coupling, fixing, or attachment as well as indirect coupling, fixing, or attachment through one or more intermediate components or features.

[0011] The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

[0012] As used throughout the specification and claims, approximate language can be used to modify any quantitative representation that can allow variation without causing a change in the basic function associated therewith. Therefore, the value modified by one or more terms (such as "approximately", "approximately", "almost" and "substantially") is not limited to the specified exact value. In some cases, approximate language can correspond to the accuracy of the instrument used to measure the value. For example, approximate language can refer to within a margin of 1%, 2%, 4%, 10%, 15% or 20%. These approximate margins can be applied to a single value, any one or two endpoints of a defined numerical range and / or the margin of the range between the endpoints. Here and throughout the specification and claims, range limitations are combined and interchanged, and unless otherwise indicated by context or language, these ranges are identified and include all sub-ranges contained therein. For example, all ranges disclosed herein include endpoints, and the endpoints can be combined independently of each other.

[0013] Technologies used for engine inspection may include various profilometry techniques (e.g., structured light, depth from focus or phase, time of flight, LiDAR, etc.) These techniques are used to detect and / or measure defects or damage to parts, such as a portion of a fan blade, vane, casing, etc. Defects or damage may include cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notches, gas corrosion, oxidation, fretting, pitting, etc.

[0014] Measurement of damage (including wear, tear, and defects) identified during inspection can be based on an estimate of the location of the undamaged surface. Operators can manually establish reference points in a three-dimensional (3D) image to estimate the undamaged surface and make defect measurements. For example, an operator can manually select three points to create a flat / flat reference surface on the damaged area. However, conventional processes require skilled operators who can select appropriate reference points. Flat reference surfaces also do not provide accurate measurements of damage on curved surfaces. Therefore, due to the variability of human interpretation, measurement results may vary from inspection to inspection and operator to operator. Given the potential for higher measurement errors, the variability of conventional processes drives more conservative limits to allow for adequate safety margins.

[0015] In some embodiments, the systems and methods described herein reduce the maintenance burden and operator skill required to make accurate and repeatable measurements of defects for part handling and evaluation based on usable limits that are independent of operator interpretation. In some embodiments, the undamaged surface topography is reconstructed as a non-planar reference surface based on automatic surface approximation methods, such as CAD geometry, surface interpolation or extrapolation using surrounding undamaged areas, using adjacent part surfaces as references, using "as built" or previously measured surface topography of the inspected part, and / or using similar part topography. In some embodiments, based on the type and location of the defect, a set of standardized rules can be used to determine a standardized measurement technique to establish repeatable measurements of defects using non-planar reference surface estimates that are independent of operator interpretation. Once the reference surface is reconstructed, the measured surface topography and the reconstructed estimate of the undamaged surface can be used to complete the measurement of the characterization, statistical quantification, or volume constraints involving the maximum or minimum range of the defect through calculations set by enumeration or algorithm optimization. In addition, knowledge of the part, sensor characteristics, measured topographic variations, and surface estimation techniques can be used to establish error limits for the calculated measurements.

[0016] In some embodiments, the techniques described herein may be applicable to equipment, such as an engine production line, that has service maintenance requirements that involve visual inspection and assessment of defect measurements against serviceable limits.

[0017] Reference is now made to the drawings, wherein like numerals refer to like elements throughout the several views. Figure 1 is a schematic cross-sectional view of a conventional gas turbine engine 10 of an aircraft in which the imaging and inspection systems described herein may be operated. The engine 10 has a generally longitudinally extending axis or centerline 12 extending from a front portion 14 to an aft portion 16. The engine 10 includes, in downstream series flow relationship, a fan section 18 including a fan 20; a compressor section 22 including a supercharger or low pressure (LP) compressor 24 and a high pressure (HP) compressor 26; a combustion section 28 including a combustor 30; a turbine section 32 including an HP turbine 34 and an LP turbine 36; and an exhaust section 38.

[0018] Fan section 18 includes a fan housing 40 surrounding fan 20. Fan 20 includes a plurality of fan blades 42 radially disposed about centerline 12.

[0019] HP compressor 26 , combustor 30 , and HP turbine 34 form a core 44 of engine 10 , which produces combustion gases. Core 44 is surrounded by a core housing 46 , which may be coupled to fan housing 40 .

[0020] An HP shaft or spool 48 disposed coaxially about the centerline 12 of the engine 10 drivingly connects the HP turbine 34 to the HP compressor 26. An LP shaft or spool 50 disposed coaxially about the centerline 12 of the engine 10 within the larger diameter annular HP spool 48 drivingly connects the LP turbine 36 to the LP compressor 24 and the fan 20.

[0021] The LP compressor 24 and the HP compressor 26 each include a plurality of compressor stages 52, 54, wherein a set of compressor blades 56, 58 rotate relative to a corresponding set of static compressor vanes 60, 62 (also referred to as nozzles) to compress or pressurize a fluid flow through the stage. In a single compressor stage 52, 54, the plurality of compressor blades 56, 58 may be provided in the form of a ring and extend radially outward from a blade platform to a blade tip relative to the centerline 12, while the corresponding static compressor vanes 60, 62 are positioned downstream of and adjacent to the rotating blades 56, 58. Notably, Figure 1 The numbers of blades, buckets, and compressor stages shown in FIG. 5 are selected for illustrative purposes only, and other numbers are possible.

[0022] The HP turbine 34 and the LP turbine 36 each include a plurality of turbine stages 64, 66, wherein a set of turbine blades 68, 70 rotate relative to a corresponding set of static turbine vanes 72, 74 (also referred to as nozzles) to extract energy from a fluid flow passing through the stage. In a single turbine stage 64, 66, the plurality of turbine blades 68, 70 may be provided in the form of a ring and extend radially outwardly from a blade platform to a blade tip relative to the centerline 12, while the corresponding static turbine vanes 72, 74 are positioned upstream of and adjacent to the rotating blades 68, 70. Notably, Figure 1 The numbers of blades, buckets, and turbine stages shown in FIG. 5 are selected for illustrative purposes only, and other numbers are possible.

[0023] In operation, the rotating fan 20 supplies ambient air to the LP compressor 24, which then supplies the pressurized ambient air to the HP compressor 26, which further pressurizes the ambient air. The pressurized air from the HP compressor 26 is mixed with fuel in the combustor 30 and ignited, thereby producing combustion gases. Some work is extracted from these gases by the HP turbine 34, which drives the HP compressor 26. The combustion gases are exhausted into the LP turbine 36, which extracts additional work to drive the LP compressor 24, and the exhaust gases are ultimately exhausted from the engine 10 via the exhaust section 38. The drive of the LP turbine 36 drives the LP spool 50 to rotate the fan 20 and the LP compressor 24.

[0024] It should be appreciated that the engine 10 may also define a plurality of openings to allow inspection of various components within the engine 10. For example, the engine 10 may define a plurality of insertion tool openings at various axial locations within the compressor section, the combustion section 28, and the turbine section 32. Additionally, the engine 10 may include one or more igniter ports, such as within the combustion section 28 of the engine 10, which may allow inspection of the combustion section 28.

[0025] It should also be understood that Figure 1 The exemplary engine 10 shown in is by way of example only, and in other exemplary embodiments, the engine 10 may have any other suitable configuration, including, for example, any other suitable number of shafts or spools, turbines, compressors, and the like. In addition, or alternatively, in other exemplary embodiments, any other suitable turbine engine may be inspected using the systems and methods described herein. For example, in other exemplary embodiments, the engine may not be a turbofan engine, but may be configured as a turboshaft engine, a turboprop engine, a turbojet engine, or the like, or may be an industrial gas turbine engine for power generation, fluid pumping, and the like. In some embodiments, the systems and methods described herein may be used to inspect other aircraft or vehicle components. The engine 10 may be an example of the equipment described herein. In some embodiments, the systems and methods described herein may be used to inspect any type of equipment suspected of having external or internal surface damage (e.g., cracks, dents, scratches, corrosion, wear, oxidation, and the like).

[0026] Reference now Figure 2 , an inspection system 200 is shown. The inspection system 200 includes an inspection controller 210, an imaging device 215, and an inspection database 260. The imaging device 215 includes a sensor system 230, and in some embodiments, also includes an insertion tool 250.

[0027] The inspection controller 210 includes a processor 212 coupled to a computer readable storage memory 213. In some embodiments, the inspection controller 210 may also include a data and / or network interface device for communicating with an imaging device 215 and / or one or more databases and services for image processing and data storage, as discussed herein. In some embodiments, the inspection controller 210 may include one or more of a control circuit, a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), etc., and may be configured to execute computer readable instructions stored on the computer readable storage memory 213. The computer readable storage memory 213 may include volatile and / or non-volatile memory and has stored thereon computer readable code that, when executed by the processor, causes the inspection controller 210 to receive and process data received from the sensor system 230 for damage characteristic measurements based on non-planar reference surface determination. In some embodiments, the processor 212 may also be configured to control capture parameters / configurations (e.g., sensor selection, image resolution, focal length, sweep speed, cycle time, etc.). In some embodiments, the inspection controller 210 may also be configured to control the movement of one or more automatic or semi-automatic insertion tools 250 (e.g., a snake arm robot or a robotic arm) of the imaging device 215. In some embodiments, the inspection controller 210 is configured to perform the operations described herein. Figure 3 The inspection controller 210 may be located locally or remotely from the engine being inspected and communicate with the imaging device via a wired connection, a wireless LAN connection, and / or a wide area network. In some embodiments, the inspection controller 210 may communicate with imaging devices 215 in one or more inspection spaces for inspecting one or more devices (e.g., aircraft parts). In some embodiments, the inspection controller 210 may be implemented on multiple geographically distributed devices, such as a handheld device local to the inspected device and a remote or cloud-based server.

[0028] The sensor system 230 may include one or more sensors 235, and one or more sensors 235 are configured to capture 3D data. In some embodiments, the sensor 235 is configured to capture a depth image or data, which can be processed by the inspection controller 210 to generate a depth image (e.g., a 3D point cloud). In some embodiments, the data captured by the sensor 235 can be used to form a point cloud, a depth map, and / or a stereogram, which can be converted into a 3D surface model. In some embodiments, the sensor 235 may include a 2D optical sensor, a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM), and / or an ultrasonic imager. In some embodiments, the depth data can be determined based on a 2D image using a shadow shape, a motion shape, or other 3D estimation techniques. In some embodiments, the sensor system 230 may include different types of sensors.

[0029] Insertion tool 250 generally refers to a tool configured to insert one or more sensors of sensor system 230 into a limited or narrow space to perform inspection. In some embodiments, insertion tool 250 may be a borescope tool, which is configured to be inserted through a port on the housing of an assembled engine to capture an image of the interior of an engine (e.g., engine 10). In some embodiments, insertion tool 250 may include a flexible insertion tool, a rigidizable insertion tool, a robot arm, or a snake arm robot. In some embodiments, insertion tool 250 may be a manually operated tool, a semi-automatic tool, or an automatic tool. In some embodiments, insertion tool 250 may be configured to position the sensor at a predefined position and orientation within the engine interior when inserted. In some embodiments, insertion tool 250 may include one or more channels for wiring to transmit signals between inspection controller 210 and sensor system 230. In some embodiments, imaging device 215 may include an insertion tool 250 configured to be interchangeably connected to a plurality of different types of sensors, an insertion tool 250 connected to a plurality of different types of sensors, or a plurality of insertion tools 250 each connected to one or more types of sensors of sensor system 230.

[0030] The inspection database 260 includes one or more computer readable memory storage devices. The inspection database 260 is generally configured to store inspection data generated by the inspection controller 210 based on communication with the imaging device 215. In some embodiments, the inspection database 260 can store equipment inspection history records for any number of devices. In some embodiments, the inspection database 260 can also store reference data from manufacturers and third parties, such as maintenance requirements, service manuals, serviceability indicators, etc. In some embodiments, the inspection database 260 can also store inspection rules for different equipment, components, parts and / or damage types. In some embodiments, the inspection rules can specify inspection configurations, such as sensor selection, capture parameters, reference surface reconstruction rules, and feature measurement rules. For example, different inspection rules can be defined for LE wear on LP compressor airfoils, LE cracks on LP compressor airfoils, TE cracks on LP compressor airfoils, LE wear on HP compression airfoils, dents on LP compressor casings, etc. In some embodiments, the inspection rules can further specify tolerances for part dispositions (e.g., no action, repair, replacement, etc.). For example, the inspection rules can specify the depth of the repair task or replacement task that triggers the LE wear on the LP compression airfoil. In some embodiments, the data in the inspection database 260 can be implemented as one or more database structures. In some embodiments, the inspection database 260 can be implemented on one or more physical devices, such as local storage memory, server storage memory, cloud-based storage memory. In some embodiments, the inspection database 260 can be implemented at least in part on the computer-readable storage memory 213 of the inspection controller 210. In some embodiments, the inspection controller 210 can access the inspection database 260 through a network (e.g., the Internet).

[0031] Next reference Figure 3 , showing a method for performing the inspection. In some embodiments, reference Figure 2 The inspection system 200 described herein performs Figure 3 one or more steps.

[0032] In some embodiments, prior to step 310, an insertion tool (e.g., insertion tool 250) is inserted into a confined space (e.g., an internal cavity of an engine (e.g., combustion section 28)). In some embodiments, the insertion tool can be manually operated, semi-automatic, or automatic. In some embodiments, the insertion tool can include a rigidizable tool that is inserted and rigidified to position the sensor 235 of the imaging device 215 in a predefined position and / or orientation. In some embodiments, the insertion tool 250 can be mechanically driven into place by a signal from a controller.

[0033] In step 305, the inspection system 200 determines the equipment component or equipment area associated with the data captured in step 310. In some embodiments, the equipment component or equipment area is identified based on the capture position of the sensor 235, machine vision feature recognition, artificial intelligence image recognition, and / or a computer model of the equipment. In some embodiments, the equipment component or equipment area is identified based on a sensor different from the sensor 235. For example, the sensor system 230 may include a camera for capturing 2D color images and a 3D camera for capturing 3D data. The equipment component or equipment area can be determined based on the image captured by the 2D camera before the 3D scan is started. In some embodiments, the equipment component or equipment area can be determined based on the insertion position of the insertion tool and / or the sensor of the imaging device. In some embodiments, the equipment component or equipment area can be received as an operator input. For example, a user interface can be provided for the operator to select from multiple parts or areas. In some embodiments, the equipment area includes a region of a component, wherein the region includes a leading edge, a trailing edge, a tip, a root fillet, a platform, a suction side, a pressure side, or a component area identifier. In some embodiments, step 305 may occur after step 310 and is based on the data captured in step 310.

[0034] In step 308, the inspection system 200 may further identify the type of damage. In some embodiments, the type of damage may be identified based on sensor data captured from the part, equipment maintenance history, equipment usage history, or operator input. In some embodiments, the type of damage may be determined based on a color image, a hyperspectral image, a thermal image, a radiographic image, and / or equipment history. For example, a machine learning computer vision algorithm may be used to identify the type of damage based on a 2D or 3D image. In some embodiments, the type of damage may be input by an operator through a user interface provided on the inspection system 200. In some embodiments, the types of damage include cracks, dents, wear, erosion, bending, creep, thermal fatigue, spalling, notches, gas corrosion, oxidation, fretting, and / or pitting. In some embodiments, the type of damage may be determined based on the data captured in 310 or data captured by a different sensor.

[0035] In some embodiments, the damage type determined in step 308 and / or the equipment component / area determined in step 305 may be used to determine and configure parameters for data capture in step 310, select a reconstruction method and / or parameters in step 320, and / or set characteristic measurement rules in step 330. In some embodiments, the inspection system 200 is configured to select a sensor 235 from different types of sensors of the sensor system 230 to capture data from the part based on the equipment region / component and / or the damage type. In some embodiments, the inspection system 200 is configured to determine capture parameters of the sensor 235 based on the equipment region / component and / or the damage type. For example, the capture resolution or focal length of the sensor may be set based on the inspected part (e.g., engine LP compressor blades, inlet passages, etc.) and / or the damage type. In some embodiments, the damage type determined in step 308 and / or the equipment component / area determined in step 305 may be further used to determine subsequent tasks in step 350. For example, a treatment threshold and / or repair method may be determined based on the damage type and / or location. In some embodiments, the damage type determined in step 308 and / or the equipment component / area determined in step 305 may be used to select from inspection rules stored in inspection database 260 .

[0036] In step 310, the sensors of the sensor system 200 capture data from the inspected part to form a 3D surface model of the surface. In some embodiments, the data may be captured by a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM), or an ultrasonic imager. In some embodiments, the data may include data captured by multiple sensors and combined into a 3D surface model. In some embodiments, the data may be captured while the part is rotating. For example, the inspected part may be located on a rotating airfoil of an engine. In some embodiments, the sensor may be configured to generate a 3D point cloud. In some embodiments, the processor 212 of the inspection system 200 may be configured to process the captured data (e.g., a stereo 2D image) to form a 3D surface model.

[0037] In step 320, the inspection controller 210 of the inspection system 200 determines a non-planar reference surface based on the 3D surface model formed in step 310. In some embodiments, the non-planar reference surface corresponds to an estimate of the original condition of the undamaged surface and / or part. In some embodiments, the non-planar reference surface can be determined based on segmenting the damaged area and the undamaged area on the part of the equipment in step 315. In some embodiments, the damaged area is segmented based on the 3D surface model and / or another image captured by a different sensor of the sensor system 230. In some embodiments, the damaged area is segmented based on an image-based computer vision recognition algorithm. In some embodiments, the damaged area is segmented by classifying the minimum curvature radius limit of the undamaged surface and identifying the area where the surface exceeds the minimum curvature radius limit as a damaged area. In some embodiments, the damaged area is identified based on comparing the color, reflectivity, surface texture, thermal properties, or electrical properties of the area of ​​the part. In some embodiments, the damaged area is identified based on comparing the 3D surface model with a computer-aided design (CAD) model of the part or a previously captured surface model of the part. In some embodiments, the damaged area can be segmented based at least in part on an operator input / selection in the image of the part.

[0038] In some embodiments, in step 320, the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation, and / or bicubic interpolation on the 3D surface model. In some embodiments, the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met. In some embodiments, the fitting of the reference surface can be determined based on an error or outlier detection algorithm, such as mean square error estimation, R square fit analysis, regression analysis, L1 or L2 principal component analysis, random sample consistency (RANSAC) analysis, minimum median square analysis, etc. In some embodiments, the non-planar reference surface is determined based on fitting the 3D surface model to multiple candidate geometries associated with the device component or a device region associated with the part. In some embodiments, the 3D surface model can be selected based on the minimum description length, Akaike information criterion, Bayesian information criterion, etc. In some embodiments, the non-planar reference surface is determined based on fitting an idealized surface model on an undamaged area to interpolate a non-planar reference surface on a damaged area. In some embodiments, the undamaged area segmented in step 315 can be used as a reference data point for interpolation.

[0039] In some embodiments, the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts. In some embodiments, the part of the device being inspected includes a portion of an airfoil, and the plurality of similar parts include other airfoils of the device, wherein the surface estimate is based on data from the plurality of similar parts captured using sensors at the same location. In some embodiments, measurement data from the plurality of similar parts and data from the sensors are captured while the component to which the airfoil is mounted rotates. In some embodiments, the airfoil may be a rotating blade and / or a stator vane. In some embodiments, the similar parts may be surface segments of a rotating component (e.g., a shaft or blade). In some embodiments, the part of the device being inspected may typically be a rotating (e.g., a rotating blade) or a stationary (e.g., a nozzle and vane) part of the device.

[0040] In some embodiments, a method for non-planar reference surface reconstruction may be selected from the plurality of methods described above based on the component / region determined in step 305 and / or the damage type determined in step 308. In some embodiments, parameters of the method (e.g., interpolation parameters / factors) may be selected based on the component / region and / or damage type.

[0041] In step 330, the inspection controller 210 of the inspection system 200 measures the characteristics of the damage based on the 3D surface model determined in step 330 and the non-planar reference surface determined in step 320. In some embodiments, the characteristics can be measured based on the difference between the damaged area of ​​the 3D surface model and the non-planar reference surface. In some embodiments, the characteristics of the damaged portion include defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to the component, damaged portion volume, and / or spatial relationship with another damaged area. In some embodiments, the depth of the defect can be measured based on the distance from the reference surface to the damaged surface along the normal of the reference surface. In some embodiments, the depth of the defect can be measured based on measuring the minimum distance from all points on the damaged surface of the 3D surface model to any point on the reference / undamaged surface. In some embodiments, the depth of the defect can be measured based on determining the largest sphere fitted between the reference surface and the measured damaged surface. In some embodiments, the defect size can be measured based on length, width, and depth. In some embodiments, the defect size can be measured based on total area, perimeter, and / or connection with another feature (e.g., row x, row 6 of cooling holes). In some embodiments, defect sharpness can be based on the derived stress concentration factor (Kt) to determine the high cycle fatigue (HCF) effect. In some embodiments, defect orientation can be measured based on determining the major axis of the defect. In some embodiments, the measurement can be used to identify damage types, such as cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notches, gas corrosion, oxidation, fretting and / or pitting. In some embodiments, the measured characteristics can be selected based on the damage type. In some embodiments, cracks can also be characterized by their connection to one or more features (e.g., the edge of a component, one or more cooling holes, etc.). In some embodiments, wear / erosion can also be characterized by parts (e.g., leading edges, tips, and coatings). In some embodiments, bending can also be characterized by shape (e.g., tip curling or large bends). In some embodiments, pitting can also be characterized by pit size, spacing, and density on a surface or a portion of a surface. In some embodiments, the linearity and tortuosity of the damage can be characterized based on a non-planar reference surface. In some embodiments, the characteristics of the damage measured in step 330 can be used to determine part disposal and / or subsequent tasks in step 350.

[0042] In some embodiments, step 330 may include receiving user input or predefined rules for characteristics to be measured and outputting numerical measurements. In some embodiments, the measurement rules may be part of an inspection rule selected based on equipment components / areas and / or damage types. In some embodiments, a user interface may be provided so that an operator can select points on a 3D surface model and / or a non-planar reference surface for measurement. In some embodiments, step 330 may include determining the location of the damaged portion on the equipment / component. In some embodiments, the location of the damaged portion includes a distance from an equipment feature, wherein the equipment feature includes a cooling hole, a root fillet, a tip, an airfoil leading edge, an airfoil trailing edge, a ratio of an airfoil chord, or a platform.

[0043] In step 335, the measured characteristics are stored as part of the inspection record for the device in the inspection database 260. In some embodiments, the captured data, 3D surface models, and / or non-planar reference surfaces may also be stored as part of the record.

[0044] In some embodiments, multiple non-planar reference surfaces for a part may be determined by repeating one or more of 310, 305, 320, and 315. For example, a part may include multiple damaged areas and / or damage types. Discrete and / or connected non-planar reference surfaces may be determined for different portions of a part. For example, for an airfoil, a first non-planar reference surface may be determined for damage on a leading edge, and a second non-planar reference surface may be determined for damage on a suction side near the tip.

[0045] In step 350, the system may further determine a subsequent task based on the measured characteristics in step 330. In some embodiments, the measured characteristics in step 330 may be used to determine the disposition of the equipment or component associated with the part (e.g., no action, usable, repairable, unusable, etc.). In some embodiments, the disposition may be determined based on comparing the measured characteristics with a disposition threshold associated with the equipment component / area and / or damage type. For example, the equipment or component may be classified as qualified or unqualified based on comparing the measured characteristics with the damage type and equipment or component specific limits. In some embodiments, the subsequent task may be a re-inspection task. For example, the inspection system may select new sensors and / or captured parameters based on the measured characteristics. In some embodiments, the damage type determined in step 308 may be preliminary, and different damage types may be identified based on the measured characteristics in step 300. In this case, a new set of inspection rules may be selected for the re-inspection task based on the updated damage type. In some embodiments, the process may return to step 310 to execute the re-inspection request. In some embodiments, the subsequent task may be a maintenance or repair task, such as performing a cleaning operation, a welding operation, a surface resurfacing operation, a coating application operation, etc. In some embodiments, the maintenance or repair task type can be determined based on the component / area and / or damage type of the part. For example, a recoating task can be performed in response to the detection of coating loss. In another example, the material or method for filling the damaged area can be selected based on the specific component or component area.

[0046] In step 355, a maintenance or repair operation is performed. In some embodiments, step 335 may be performed via an insertion tool or other tool for accessing the inspected part. In some embodiments, subsequent tasks may be based on the non-planar reference surface determined in step 320. For example, a repair operation may be configured to fill / restore a damaged area to match a non-planar reference surface.

[0047] Figure 4A -D includes illustrations of examples of reference surface determination. Figure 4A A captured 3D surface model 410 of the part is shown. Figure 4B The 3D surface model 410 is shown segmented into damaged areas 425 and undamaged areas 420. In some embodiments, the segmentation may be performed according to step 315. Figure 4C In some embodiments, non-planar reference surface 430 may be formed according to step 320. Figure 4CIn the example shown, non-planar reference surface 430 is formed based on spline interpolation using lines and / or points in undamaged region 420 of 3D surface model 410. Although damaged region 425 is generally shown as a concave surface, in some embodiments, at least a portion of damaged region 425 may protrude above non-planar reference surface 430. Figure 4D is an illustration of a calculated property 440 based on a non-planar reference surface 430 and a 3D surface model 410. Figure 4D In the example shown, the measured characteristic may be the distance between the 3D surface model 410 and the non-planar reference surface 430, corresponding to the depth of the damaged area. Figure 4B The segmentation of the damaged region 425 in may be preliminary. After the non-planar reference surface 430 is reconstructed, damaged region characteristics such as width, length, and radius may be measured with greater accuracy.

[0048] Further aspects of the disclosure are provided by the subject matter of the following clauses:

[0049] A system for engine inspection, comprising: a sensor configured to capture data from a part of the engine; a memory including instructions; and a processor executing the instructions to: form a three-dimensional (3D) surface model of the part of the engine based on signals received from the sensor; determine a non-planar reference surface based on the 3D surface model of the part; and measure characteristics of a damaged portion of the part of the engine based on the 3D surface model and the non-planar reference surface.

[0050] A system as described in any preceding clause, wherein the engine is an assembled gas turbine engine and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture the data from the interior of the engine.

[0051] A system as described in any preceding clause, wherein the processor executes the instructions to: identify an engine component or an engine area of ​​the engine where the part of the engine is located.

[0052] The system of any preceding clause, wherein the processor executes the instructions to determine a capture parameter of the sensor based on the engine component or the engine region.

[0053] A system as described in any preceding clause, wherein the processor executes the instructions to identify the engine component or the engine area based on the capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the engine.

[0054] A system as described in any preceding clause, wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the engine; wherein the non-planar reference surface is determined based on the undamaged areas of the 3D surface model.

[0055] A system as in any preceding clause, wherein the damaged region is segmented by classifying a minimum radius of curvature limit of an undamaged surface and identifying regions of the surface exceeding the minimum radius of curvature limit as the damaged region.

[0056] A system as in any preceding clause, wherein the damaged region is identified based on comparing color, reflectivity, surface texture or thermal properties of regions of the part.

[0057] A system as in any preceding clause, wherein the non-planar reference surface is determined based on fitting an idealized surface model over the undamaged region to interpolate the non-planar reference surface over the damaged region.

[0058] A system as in any preceding clause, wherein the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts.

[0059] A system as described in any preceding clause, wherein: the part of the engine comprises a portion of an airfoil of the engine, the plurality of similar parts comprises other airfoils of the engine, and the surface estimation is based on data from the plurality of similar parts captured using the sensor at the same location.

[0060] A system as described in any preceding clause, wherein the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation and / or bicubic interpolation on the 3D surface model.

[0061] A system as in any preceding clause, wherein the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met.

[0062] A system as in any preceding clause, wherein the non-planar reference surface is determined based on fitting the 3D surface model to a plurality of candidate geometries associated with an engine component or an engine region associated with the part.

[0063] A system as described in any preceding clause, wherein the processor is further configured to determine the location of the damaged portion.

[0064] A system according to any preceding clause, wherein the characteristic of the damaged portion includes defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to the component, damaged portion volume, or spatial relationship to another damaged area.

[0065] A system as in any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and wherein the characteristic of the damaged portion is measured based on the damage type.

[0066] The system of any preceding clause, wherein the processor is further configured to identify a subsequent task based on the characteristic of the damaged portion.

[0067] A system according to any preceding clause, wherein the subsequent task comprises a re-inspection task, and the system is configured to select a different sensor or a different capture setting of the sensor to perform the re-inspection task based on the characteristics of the damaged part or the damage type.

[0068] A method for engine inspection includes: using a sensor to capture data from a part of the engine; executing instructions through a processor to form a three-dimensional (3D) surface model of the part of the engine based on signals received from the sensor; using the processor to determine a non-planar reference surface based on the 3D surface model of the part; and using the processor to measure characteristics of a damaged portion of the part of the engine based on the 3D surface model and the non-planar reference surface.

[0069] A system for inspecting equipment, comprising: a sensor system, the sensor system including a sensor, the sensor being configured to capture data from a part of the equipment; and a processor, the processor receiving the data from the sensor, the processor being configured to: form a three-dimensional (3D) surface model of the part of the equipment based on signals received from the sensor system; determine a non-planar reference surface based on the 3D surface model of the part; and measure characteristics of a damaged portion of the part of the equipment based on the 3D surface model and the non-planar reference surface.

[0070] A system according to any preceding clause, wherein the sensor comprises a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM), or an ultrasonic imager.

[0071] A system according to any preceding clause, wherein the device includes an assembled gas turbine engine and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture the data from the interior of the assembled gas turbine engine.

[0072] A system as described in any preceding clause, wherein the processor is further configured to: identify an equipment component or equipment area where the part of the equipment is located.

[0073] A system as described in any preceding clause, wherein the sensor system includes different types of sensors, and wherein the processor is further configured to select the sensor from the sensors in the sensor system to capture data from the part based on the equipment component or the equipment area.

[0074] The system of any preceding clause, wherein the processor is further configured to determine capture parameters of the sensor based on the device component or the device region.

[0075] The system of any preceding clause, wherein the processor is further configured to measure the characteristic of the damaged portion based on the device component or the device region.

[0076] A system according to any preceding clause, wherein the device component or the device area is identified based on a capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the device.

[0077] A system as described in any preceding clause, wherein the equipment component or the equipment area is identified based on an image capture device other than the sensor.

[0078] The system of any preceding clause, wherein the equipment region comprises a zone of a component, wherein the zone comprises a leading edge, a trailing edge, a tip, a root fillet, a platform, a suction side, a pressure side, or a component region identifier.

[0079] A system as described in any preceding clause, wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the device; wherein the non-planar reference surface is determined based on the undamaged areas of the 3D surface model.

[0080] A system as in any preceding clause, wherein the damaged area is segmented based on the 3D surface model and / or another image captured by a different sensor of the sensor system.

[0081] A system as in any preceding clause, wherein the damaged region is segmented based on image-based computer vision recognition.

[0082] A system as in any preceding clause, wherein the damaged region is segmented by classifying a minimum radius of curvature limit of an undamaged surface and identifying regions of the surface exceeding the minimum radius of curvature limit as the damaged region.

[0083] A system as in any preceding clause, wherein the damaged region is identified based on comparing color, reflectivity, surface texture or thermal properties of regions of the part.

[0084] A system as in any preceding clause, wherein the damaged area is identified based on comparing the 3D surface model to a computer aided design (CAD) model of the part or a previously captured surface model of the part.

[0085] A system as in any preceding clause, wherein the non-planar reference surface is determined based on fitting an idealized surface model over the undamaged region to interpolate the non-planar reference surface over the damaged region.

[0086] A system as in any preceding clause, wherein the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts.

[0087] A system as described in any preceding clause, wherein: the part of the equipment comprises a portion of an airfoil, the plurality of similar parts comprises other airfoils of the equipment, and the surface estimation is based on data from the plurality of similar parts captured using the sensor at the same location.

[0088] A system as claimed in any preceding clause wherein measurement data from said plurality of similar parts and said data from said sensor are captured as a component to which said airfoil is mounted rotates.

[0089] A system as described in any preceding clause, wherein the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation and / or bicubic interpolation on the 3D surface model.

[0090] A system as in any preceding clause, wherein the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met.

[0091] The system of any preceding clause, wherein the non-planar reference surface is determined based on fitting the 3D surface model to a plurality of candidate geometries associated with an equipment component or an equipment region associated with the part.

[0092] A system as described in any preceding clause, wherein the processor is further configured to determine the location of the damaged portion.

[0093] The system of any preceding clause, wherein the location of the damaged portion comprises a distance from an equipment feature, wherein the equipment feature comprises a cooling hole, a root fillet, a tip, an airfoil leading edge, an airfoil trailing edge, a ratio of an airfoil chord, or a platform.

[0094] A system according to any preceding clause, wherein the position of the damaged portion is determined based on the 3D surface model or data captured by different sensors of the sensor system.

[0095] A system according to any preceding clause, wherein the characteristic of the damaged portion includes defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to the component, damaged portion volume, or spatial relationship to another damaged area.

[0096] The system of any preceding clause, wherein the processor is further configured to identify a type of damage based on the characteristics of the damaged portion and a component or equipment area associated with the piece of equipment.

[0097] The system of any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and cause the sensor system to capture the data based on the damage type.

[0098] The system of any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and measure the characteristic based on the damage type.

[0099] The system of any preceding clause, wherein the damage type comprises cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notches, gas corrosion, oxidation, fretting, and / or pitting.

[0100] The system of any preceding clause, wherein the damage type is further determined based on a color image, a hyperspectral image, a thermal image, a radiological image, and / or a device history.

[0101] The system of any preceding clause, wherein the processor is further configured to identify a subsequent task based on the characteristic of the damaged portion.

[0102] A system according to any preceding clause, wherein the subsequent task is determined based on: determining a threshold based on a component associated with the damaged portion, a location of the damaged portion, a type of damage and / or equipment usage information; and comparing the characteristic to the threshold.

[0103] The system of any preceding clause, wherein the subsequent task comprises a repair task, a maintenance task, or a replacement task.

[0104] A system according to any preceding clause, wherein the subsequent task comprises a re-inspection task, and the system is configured to select a different sensor or a different capture setting of the sensor to perform the re-inspection task based on the characteristics of the damaged part or the damage type.

[0105] A system as in any preceding clause, wherein the processor is further configured to store the 3D surface model and / or the non-planar reference surface in a reference database for future inspection.

[0106] A method for inspecting equipment, comprising: using a sensor system to capture data from a part of the equipment; using a processor to form a three-dimensional (3D) surface model of the part of the equipment based on signals received from the sensor system; using the processor to determine a non-planar reference surface based on the 3D surface model of the part; and using the processor to measure characteristics of a damaged portion of the part of the equipment based on the 3D surface model and the non-planar reference surface.

[0107] A method according to any preceding clause, wherein the sensor comprises a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM) or an ultrasonic imager.

[0108] A method according to any preceding clause, wherein the device is an assembled gas turbine engine and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture the data from the interior of the gas turbine engine.

[0109] A method according to any preceding clause, further comprising: identifying a device component or device area where the part of the device is located.

[0110] The method of any preceding clause, further comprising selecting the sensor from a plurality of types of sensors of the sensor system to capture data from the part based on the equipment component or the equipment region.

[0111] A method as in any preceding clause, further comprising determining a capture parameter of the sensor based on the device component or the device region.

[0112] A method as in any preceding clause, wherein the characteristic of the damaged portion is measured based on the equipment component or the equipment region.

[0113] A method according to any preceding clause, wherein the device component or the device area is identified based on a capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the device.

[0114] A method as in any preceding clause, wherein the device component or the device region is identified based on an image capture device other than the sensor.

[0115] The method of any preceding clause, wherein the equipment region comprises a zone of a component, wherein the zone comprises a leading edge, a trailing edge, a tip, a root fillet, a platform, a suction side, a pressure side, or a component region identifier.

[0116] A method according to any preceding clause, wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the device; wherein the non-planar reference surface is determined based on the undamaged areas of the 3D surface model.

[0117] A method as in any preceding clause, wherein the damaged area is segmented based on the 3D surface model and / or another image captured by a different sensor of the sensor method.

[0118] A method as in any preceding clause, wherein the damaged region is segmented based on image-based computer vision recognition.

[0119] A method as in any preceding clause, wherein the damaged region is segmented by classifying a minimum radius of curvature limit of an undamaged surface and identifying regions of the surface exceeding the minimum radius of curvature limit as the damaged region.

[0120] A method as in any preceding clause, wherein the damaged region is identified based on comparing color, reflectivity, surface texture or thermal properties of regions of the part.

[0121] A method as in any preceding clause, wherein the damaged area is identified based on comparing the 3D surface model to a computer aided design (CAD) model of the part or a previously captured surface model of the part.

[0122] A method as in any preceding clause, wherein the non-planar reference surface is determined based on fitting an idealized surface model over the undamaged region to interpolate the non-planar reference surface over the damaged region.

[0123] A method as in any preceding clause, wherein the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts.

[0124] A method as in any preceding clause, wherein: the part of the equipment comprises a portion of an airfoil, the plurality of similar parts comprises other airfoils of the equipment, and the surface estimation is based on data from the plurality of similar parts captured using the sensor at the same location.

[0125] A method as in any preceding clause, wherein measurement data from said plurality of similar parts and said data from said sensor are captured as a component to which said airfoil is mounted rotates.

[0126] A method according to any preceding clause, wherein the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation and / or bicubic interpolation on the 3D surface model.

[0127] A method as in any preceding clause, wherein the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met.

[0128] A method as in any preceding clause, wherein the non-planar reference surface is determined based on fitting the 3D surface model to a plurality of candidate geometries associated with an equipment component or an equipment region associated with the part.

[0129] A method as in any preceding clause, wherein the processor is further configured to determine a location of the damaged portion.

[0130] A method as in any preceding clause, wherein the location of the damaged portion comprises a distance from an equipment feature, wherein the equipment feature comprises a cooling hole, a root fillet, a tip, an airfoil leading edge, an airfoil trailing edge, a ratio of an airfoil chord, or a platform.

[0131] A method as in any preceding clause, wherein the position of the damaged portion is determined based on the 3D surface model or data captured by different sensors of the sensor method.

[0132] A method according to any preceding clause, wherein the characteristic of the damaged portion comprises defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to a component, damaged portion volume, or spatial relationship to another damaged area.

[0133] A method as in any preceding clause, wherein the processor is further configured to identify a type of damage based on the characteristics of the damaged portion and a component or device region associated with the piece of equipment.

[0134] A method as in any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and cause the sensor method to capture the data based on the damage type.

[0135] A method as in any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and measure the characteristic based on the damage type.

[0136] A method according to any preceding clause, wherein the damage type comprises cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notching, gas corrosion, oxidation, fretting and / or pitting.

[0137] A method as in any preceding clause, wherein the damage type is further determined based on a color image, a hyperspectral image, a thermal image, a radiological image, and / or a device history.

[0138] A method as in any preceding clause, wherein the processor is further configured to identify a subsequent task based on the characteristic of the damaged portion.

[0139] A method according to any preceding clause, wherein the subsequent task is determined based on: determining a threshold based on a component associated with the damaged part, the location of the damaged part, the damage type and / or equipment usage information; and comparing the characteristic to the threshold.

[0140] A method as in any preceding clause, wherein the subsequent task comprises a repair task, a maintenance task, or a replacement task.

[0141] A method according to any preceding clause, wherein the subsequent task comprises a re-inspection task, and the system is configured to select a different sensor or a different capture setting of the sensor to perform the re-inspection task based on the characteristics of the damaged part or the damage type.

[0142] A method as in any preceding clause, wherein the processor is further configured to store the 3D surface model and / or the non-planar reference surface in a reference database for future inspection.

[0143] A system for engine inspection, comprising: a sensor system, the sensor system including a sensor, the sensor being configured to capture data from a part of the engine; and a processor, the processor receiving the data from the sensor, the processor being configured to: form a three-dimensional (3D) surface model of the part of the engine based on signals received from the sensor system; determine a non-planar reference surface based on the 3D surface model of the part; and measure characteristics of a damaged portion of the part of the engine based on the 3D surface model and the non-planar reference surface.

[0144] A system according to any preceding clause, wherein the sensor comprises a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM), or an ultrasonic imager.

[0145] A system as described in any preceding clause, wherein the engine is an assembled gas turbine engine and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture data from an interior of the engine.

[0146] A system as described in any preceding clause, wherein the processor is further configured to: identify an engine component or an engine area of ​​the engine where the part of the engine is located.

[0147] A system as described in any preceding clause, wherein the sensor system includes different types of sensors, and wherein the processor is further configured to select the sensor from the sensors in the sensor system based on the engine component or the engine zone to capture data from the part.

[0148] The system of any preceding clause, wherein the processor is further configured to determine a capture parameter of the sensor based on the engine component or the engine region.

[0149] A system as described in any preceding clause, wherein the processor is further configured to measure the characteristic of the damaged portion based on the engine component or the engine region.

[0150] A system as described in any preceding clause, wherein the engine component or the engine region is identified based on a capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the engine.

[0151] A system as in any preceding clause, wherein the engine component or the engine region is identified based on an image capture device distinct from the sensor.

[0152] The system of any preceding clause, wherein the engine region comprises a zone of a component, wherein the zone comprises a leading edge, a trailing edge, a tip, a root fillet, a platform, a suction side, a pressure side, or a component region identifier.

[0153] A system as described in any preceding clause, wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the engine; wherein the non-planar reference surface is determined based on the undamaged areas of the 3D surface model.

[0154] A system as in any preceding clause, wherein the damaged area is segmented based on the 3D surface model and / or another image captured by a different sensor of the sensor system.

[0155] A system as in any preceding clause, wherein the damaged region is segmented based on image-based computer vision recognition.

[0156] A system as in any preceding clause, wherein the damaged region is segmented by classifying a minimum radius of curvature limit of an undamaged surface and identifying regions of the surface exceeding the minimum radius of curvature limit as the damaged region.

[0157] A system as in any preceding clause, wherein the damaged region is identified based on comparing color, reflectivity, surface texture or thermal properties of regions of the part.

[0158] A system as in any preceding clause, wherein the damaged area is identified based on comparing the 3D surface model to a computer aided design (CAD) model of the part or a previously captured surface model of the part.

[0159] A system as in any preceding clause, wherein the non-planar reference surface is determined based on fitting an idealized surface model over the undamaged region to interpolate the non-planar reference surface over the damaged region.

[0160] A system as in any preceding clause, wherein the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts.

[0161] A system as described in any preceding clause, wherein: the part of the engine comprises a portion of an airfoil of the engine, the plurality of similar parts comprises other airfoils of the engine, and the surface estimation is based on data from the plurality of similar parts captured using the sensor at the same location.

[0162] A system as claimed in any preceding clause wherein measurement data from said plurality of similar parts and said data from said sensor are captured as a component to which said airfoil is mounted rotates.

[0163] A system as described in any preceding clause, wherein the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation and / or bicubic interpolation on the 3D surface model.

[0164] A system as in any preceding clause, wherein the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met.

[0165] A system as in any preceding clause, wherein the non-planar reference surface is determined based on fitting the 3D surface model to a plurality of candidate geometries associated with an engine component or an engine region associated with the part.

[0166] A system as described in any preceding clause, wherein the processor is further configured to determine the location of the damaged portion.

[0167] The system of any preceding clause, wherein the location of the damaged portion comprises a distance from an engine feature, wherein the engine feature comprises a cooling hole, a root fillet, a tip, an airfoil leading edge, an airfoil trailing edge, a ratio of an airfoil chord, or a platform.

[0168] A system according to any preceding clause, wherein the position of the damaged portion is determined based on the 3D surface model or data captured by different sensors of the sensor system.

[0169] A system according to any preceding clause, wherein the characteristic of the damaged portion includes defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to the component, damaged portion volume, or spatial relationship to another damaged area.

[0170] The system of any preceding clause, wherein the processor is further configured to identify a type of damage based on the characteristics of the damaged portion and a component or engine region associated with the part of the engine.

[0171] The system of any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and determine the non-planar reference surface based on the damage type.

[0172] The system of any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and measure the characteristic based on the damage type.

[0173] The system of any preceding clause, wherein the damage type comprises cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notches, gas corrosion, oxidation, fretting, and / or pitting.

[0174] A system as in any preceding clause, wherein the damage type is further determined based on a color image, a hyperspectral image, a thermal image, a radiological image, and / or an engine history.

[0175] The system of any preceding clause, wherein the processor is further configured to identify a subsequent task based on the characteristic of the damaged portion.

[0176] A system according to any preceding clause, wherein the subsequent task is determined based on: determining a threshold based on a component associated with the damaged part, a location of the damaged part, a damage type and / or engine usage information; and comparing the characteristic to the threshold.

[0177] The system of any preceding clause, wherein the subsequent task comprises a repair task, a maintenance task, or a replacement task.

[0178] A system according to any preceding clause, wherein the subsequent task comprises a re-inspection task, and the system is configured to select a different sensor or a different capture setting of the sensor to perform the re-inspection task based on the characteristics of the damaged part or the damage type.

[0179] A system as in any preceding clause, wherein the processor is further configured to store the 3D surface model and / or the non-planar reference surface in a reference database for future inspection.

[0180] A method for engine inspection includes: using a sensor system to capture data from a part of the engine; using a processor to form a three-dimensional (3D) surface model of the part of the engine based on signals received from the sensor system; using the processor to determine a non-planar reference surface based on the 3D surface model of the part; and using the processor to measure characteristics of a damaged portion of the part of the engine based on the 3D surface model and the non-planar reference surface.

[0181] A method according to any preceding clause, wherein the sensor comprises a stereo optical sensor, a structured light projection scanner, a laser scanner, a contact probe, an eddy current imager, a scanning electron microscope (SEM) or an ultrasonic imager.

[0182] A method according to any preceding clause, wherein the engine is an assembled gas turbine engine and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture the data from the interior of the engine.

[0183] A method as claimed in any preceding clause, further comprising identifying an engine component or an engine region of the engine in which the part of the engine is located.

[0184] The method of any preceding clause, further comprising selecting the sensor from a plurality of types of sensors of the sensor system based on the engine component or the engine region to capture data from the part.

[0185] A method as in any preceding clause, further comprising determining a capture parameter of the sensor based on the engine component or the engine region.

[0186] A method as in any preceding clause, wherein the property of the damaged portion is measured based on the engine component or the engine region.

[0187] A method according to any preceding clause, wherein the engine component or the engine region is identified based on a capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the engine.

[0188] A method as in any preceding clause, wherein the engine component or the engine region is identified based on an image capture device distinct from the sensor.

[0189] The method of any preceding clause, wherein the engine region comprises a zone of a component, wherein the zone comprises a leading edge, a trailing edge, a tip, a root fillet, a platform, a suction side, a pressure side, or a component region identifier.

[0190] A method as in any preceding clause, wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the engine; wherein the non-planar reference surface is determined based on the undamaged areas of the 3D surface model.

[0191] A method as in any preceding clause, wherein the damaged area is segmented based on the 3D surface model and / or a further image captured by a different sensor of the sensor system.

[0192] A method as in any preceding clause, wherein the damaged region is segmented based on image-based computer vision recognition.

[0193] A method as in any preceding clause, wherein the damaged region is segmented by classifying a minimum radius of curvature limit of an undamaged surface and identifying regions of the surface exceeding the minimum radius of curvature limit as the damaged region.

[0194] A method as in any preceding clause, wherein the damaged region is identified based on comparing color, reflectivity, surface texture or thermal properties of regions of the part.

[0195] A method as in any preceding clause, wherein the damaged area is identified based on comparing the 3D surface model to a computer aided design (CAD) model of the part or a previously captured surface model of the part.

[0196] A method as in any preceding clause, wherein the non-planar reference surface is determined based on fitting an idealized surface model over the undamaged region to interpolate the non-planar reference surface over the damaged region.

[0197] A method as in any preceding clause, wherein the non-planar reference surface is determined based on an objective function for determining a sampled average surface estimate of an undamaged part from a plurality of similar parts.

[0198] A method according to any preceding clause, wherein: the part of the engine comprises a portion of an airfoil of the engine, the plurality of similar parts comprises other airfoils of the engine, and the surface estimation is based on data from the plurality of similar parts captured using the sensor at the same location.

[0199] A method as in any preceding clause, wherein measurement data from said plurality of similar parts and said data from said sensor are captured as a component to which said airfoil is mounted rotates.

[0200] A method according to any preceding clause, wherein the non-planar reference surface is determined based on performing polynomial interpolation, spline interpolation, bilinear interpolation and / or bicubic interpolation on the 3D surface model.

[0201] A method as in any preceding clause, wherein the non-planar reference surface is determined based on applying a series of interpolation methods to the 3D surface model until a fitting threshold is met.

[0202] A method as in any preceding clause, wherein the non-planar reference surface is determined based on fitting the 3D surface model to a plurality of candidate geometries associated with an engine component or an engine region associated with the part.

[0203] A method as in any preceding clause, wherein the processor is further configured to determine a location of the damaged portion.

[0204] A method as in any preceding clause, wherein the location of the damaged portion comprises a distance from an engine feature, wherein the engine feature comprises a cooling hole, a root fillet, a tip, an airfoil leading edge, an airfoil trailing edge, a ratio of an airfoil chord, or a platform.

[0205] A method as in any preceding clause, wherein the position of the damaged portion is determined based on the 3D surface model or data captured by different sensors of the sensor system.

[0206] A method according to any preceding clause, wherein the characteristic of the damaged portion comprises defect depth, defect size, defect sharpness, defect aspect ratio, defect orientation relative to a component, damaged portion volume, or spatial relationship to another damaged area.

[0207] A method as in any preceding clause, wherein the processor is further configured to identify a type of damage based on the characteristics of the damaged portion and a component or engine region associated with the part of the engine.

[0208] A method as in any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and determine the non-planar reference surface based on the damage type.

[0209] A method as in any preceding clause, wherein the processor is further configured to: identify a damage type associated with the damaged portion; and measure the characteristic based on the damage type.

[0210] A method according to any preceding clause, wherein the damage type comprises cracks, dents, tears, wear, erosion, bending, creep, thermal fatigue, spalling, notching, gas corrosion, oxidation, fretting and / or pitting.

[0211] A method as in any preceding clause, wherein the damage type is further determined based on a color image, a hyperspectral image, a thermal image, a radiological image, and / or an engine history.

[0212] A method as in any preceding clause, wherein the processor is further configured to identify a subsequent task based on the characteristic of the damaged portion.

[0213] A method according to any preceding clause, wherein the subsequent task is determined based on: determining a threshold based on a component associated with the damaged part, a location of the damaged part, a damage type and / or engine usage information; and comparing the characteristic to the threshold.

[0214] A method as in any preceding clause, wherein the subsequent task comprises a repair task, a maintenance task, or a replacement task.

[0215] A method according to any preceding clause, wherein the subsequent task comprises a re-inspection task, and the processor is configured to select a different sensor or a different capture setting of the sensor to perform the re-inspection task based on the characteristics of the damaged part or the damage type.

[0216] A method as in any preceding clause, wherein the processor is further configured to store the 3D surface model and / or the non-planar reference surface in a reference database for future inspection.

[0217] A method according to any preceding clause, wherein the device component or the device area is identified based on a capture position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the device.

[0218] A system as in any preceding clause wherein the light projection is a line.

[0219] This written description uses examples to disclose the present disclosure, including the best mode, and also to enable any person skilled in the art to practice the present disclosure, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the present disclosure is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to fall within the scope of the claims if they include structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements that do not differ substantially from the literal language of the claims.

Claims

1. A system for engine inspection, characterized in that: include: a sensor configured to capture data from a part of the engine; a memory including instructions; and a processor that executes the instructions to: forming a three-dimensional (3D) surface model of the part of the engine based on the signals received from the sensor; determining a non-planar reference surface based on the 3D surface model of the part; and Based on the 3D surface model and the non-planar reference surface, properties of a damaged portion of the part of the engine are measured.

2. The system according to claim 1, characterized in that Wherein the engine is an assembled gas turbine engine, and the sensor is mounted on a borescope tool inserted into a cavity of the assembled gas turbine engine to capture the data from the interior of the engine.

3. The system according to claim 1, characterized in that wherein the processor executes the instructions to: An engine component or an engine region of the engine in which the part of the engine is located is identified.

4. The system according to claim 3, characterized in that The processor executes the instructions to determine a capture parameter of the sensor based on the engine component or the engine region.

5. The system according to claim 3, characterized in that The processor executes the instructions to identify the engine component or the engine region based on the captured position of the sensor, machine vision feature recognition, artificial intelligence image recognition and / or a computer model of the engine.

6. The system according to claim 1, characterized in that wherein the 3D surface model is segmented into damaged areas and undamaged areas on the part of the engine; The non-planar reference surface is determined based on the undamaged area of ​​the 3D surface model.

7. The system according to claim 6, characterized in that The damaged area is segmented by classifying a minimum curvature radius limit of the undamaged surface and identifying the area of ​​the surface exceeding the minimum curvature radius limit as the damaged area.

8. The system according to claim 6, characterized in that Wherein the damaged area is identified based on comparing the color, reflectivity, surface texture or thermal properties of the area of ​​the part.

9. The system according to claim 6, characterized in that The non-planar reference surface is determined based on fitting an idealized surface model on the undamaged region to interpolate the non-planar reference surface on the damaged region.

10. The system according to claim 1, characterized in that The non-planar reference surface is determined based on an objective function for estimating a sampled average surface for determining an undamaged part from a plurality of similar parts.

Images