Weld SEAM tracking for non-destructive test (NDT)

Abstract

Techniques for controlling an alignment of a non-destructive test (NDT) inspection probe are described. The techniques include receiving laser profile data from a laser profiling sensor corresponding to a weld location and surface properties of an object under non-destructive testing and receiving image data from an image sensor corresponding to the weld location. The laser profile data and the image sensor may be fused to generate fused data corresponding to the weld location. A control signal is generated to adjust a robotic manipulator of the NDT probe based on the fused data.

Description

WELD SEAM TRACKING FOR NON DESTRUCTIVE TEST (NDT)CLAIM OF PRIORITYThis patent application claims the benefit of priority of Badeau, et al., U.S. Provisional Patent Application Number 63 / 618,105, titled “WELD SEAM TRACKING FOR NON-DESTRUCTIVE TEST (NDT),” filed on January 5, 2024 (Attorney Docket No. 6409.272PRV), which is hereby incorporated by reference herein in its entirety.FIELD OF THE DISCLOSUREThis document pertains generally, but not by way of limitation, to apparatus and techniques for non-destructive inspection and more particularly, to apparatus and techniques for performing automated or semi-automated scanning of a probe assembly including performing probe alignment for weld seam tracking.BACKGROUNDNon-destructive testing (NDT) can refer to use of one or more different techniques to inspect regions on or within an object, such as to ascertain whether flaws or defects exist, or to otherwise characterize the object being inspected. Examples of non-destructive test approaches can include use of an eddy current testing approach where electromagnetic energy is applied to the object and resulting induced currents on or within the object are detected, with the values of a detected current (or a related impedance) providing an indication of the structure of the object under test, such as to indicate a presence of a crack, void, porosity, or other inhomogeneity.Another approach for NDT can include use of an acoustic inspection technique, such as where one or more electroacoustic transducers are used to insonify a region on or within the object under test, and acoustic energy that is scattered or reflected can be detected and processed. Such scattered or reflected energy can be referred to as an acoustic echo signal. Generally, such an acoustic inspection scheme involves use of acoustic frequencies in an ultrasonic range of frequencies, such as including pulses having energy in a specified range that can include value from, forexample, a few hundred kilohertz, to tens of megahertz, as an illustrative example.SUMMARY OF THE DISCLOSURENon-destructive test (NDT), such as acoustic inspection, can include use of a machine-implemented (e.g., automated) technique. In such a technique, sensed data can be acquired, indicative of at least one of a location or an orientation of a weld and surrounding portion of a structure under test. In response, a representation of a correction can be determined to steer at least one of a location or an orientation of a probe assembly. For example, a laser profder and a two-dimensional imaging camera can be used to perform such sensing, separate from an acoustic transducer included in the probe assembly.A robotic manipulator can be used to control a test probe orientation or position (or both) and can also support respective sensors. Such a manipulator can include programmability, such as to compensate for variations in the object under test or other factors that cause a desired path for a particular measurement or inspection operation to vary from an ideal or nominal path. For example, Fanuc offers a Dynamic Path Modification (DPM) package, providing very fast compensation to a preprogrammed path by transmitting appropriate corrections corresponding to respective (e.g., five) degrees of freedom. The techniques described herein can provide inputs to such a compensation scheme. This can ensure precise alignment and placement of the probes at or near an inspection surface. While the examples herein use the Fanuc DPM capability as an illustrative example, such examples are generally applicable to various techniques or software solutions, such as depending on the robotic manipulator used for an inspection application. Generally, the subject matter herein can include or use a combination of laser profiling and machine vision to locate a weld and its orientation (direction). Such laser profiling and vision outputs can be used to control a position and orientation of robotic EOAT (End-of-Arm Tooling), enhancing positioning accuracy of the probe for inspection of a weld structure.The present inventors have recognized among other things, that generally, in relation to ultrasonic and eddy current inspections, precise alignment of the probe relative to a structure being inspected (e.g., weld) is to be maintained. However, forsizable items such as train tank cars or rocket fuel tanks, positioning these items precisely in relation to the robot is challenging. Both the robotic unit and the part being inspected may be mobile or situated in unpredictable environments, leading to probe misalignment and acquisition of unreliable data.In an example, machine-implemented method for controlling an alignment of a non-destructive test (NDT) inspection probe, the machine-implemented method comprising: receiving laser profile data from a laser profiling sensor corresponding to a weld location and surface properties of an object under non-destructive testing; receiving image data from an image sensor corresponding to the weld location; fusing the laser profile data and the image sensor to generate fused data corresponding the weld location; and transmitting a control signal to adjust a robotic manipulator of the NDT probe based on the fused data.In an example, a system can be used for controlling an alignment of a nondestructive test (NDT) inspection probe, the system comprising a first sensor configured to acquire laser profile data corresponding to a weld location and surface properties of an object under non-destructive testing; a second sensor configured to acquire image data corresponding to the weld location; at least one processor circuit; at least one memory circuit comprising instructions that, when executed by the at least one processor circuit, cause the system to perform operations comprising: receiving laser profile data from a laser profiling sensor corresponding to a weld location and surface properties of an object under non-destructive testing; receiving image data from an image sensor corresponding to the weld location; fusing the laser profile data and the image sensor to generate fused data corresponding the weld location; and transmitting a control signal to adjust a robotic manipulator of the NDT probe based on the fused data.In an example, machine-storage medium embodying instructions that, when executed by a machine, cause the machine to perform operations comprising: receiving laser profile data from a laser profiling sensor corresponding to a weld location and surface properties of an object under non-destructive testing; receiving image data from an image sensor corresponding to the weld location; fusing the laser profile data and the image sensor to generate fused data corresponding the weldlocation; and transmitting a control signal to adjust a robotic manipulator of the NDT probe based on the fused data.This summary is intended to provide an overview of subject matter of the present patent application. It is not intended to provide an exclusive or exhaustive explanation of the invention. The detailed description is included to provide further information about the present patent application.BRIEF DESCRIPTION OF THE DRAWINGSIn the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like numerals having different letter suffixes may represent different instances of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.FIG. 1 illustrates generally an example comprising an acoustic inspection system, such as can be used to perform at least a portion one or more techniques as shown and described herein.FIG. 2 shows an illustrative example of a coordinate system and degrees of freedom used for robotic manipulation of a probe assembly.FIG. 3 is a flow diagram of a method for controlling a robotic manipulator for acoustic sensing based on at least two sensors.FIG. 4 shows example portions of a weld profile based on laser profiling.FIG. 5 shows a camera framework for capturing images of a weld.FIG. 6 shows a visual representation of an example of determining a weld center position using machine vision.FIG. 7 shows a block diagram comprising a generalized control loop architecture that can use the laser profiler and camera data as inputs and can fuse such data to provide compensation for control of a robotic manipulator.FIG. 8 shows plots of detected weld center and detected weld width using laser profiling and machine vision compared to laser profiling alone.FIG. 9 illustrates a block diagram of an example comprising a machine upon which any one or more of the techniques (e.g., methodologies) discussed herein maybe performed.DETAILED DESCRIPTIONNon-destructive testing of manufactured structures can be performed using various approaches, such as an using an eddy current or acoustic inspection technique. In an example, for acoustic inspection, a phased-array transducer architecture and associated processing (e.g., beamforming and imaging) can be performed. Similarly, for eddy current inspection, an eddy current array (ECA) probe can be used, such as scanned across a surface of an object under test. The present subject matter can be used to perform probe alignment, such as on a dynamic basis, as the probe assembly is manipulated (e.g., translated) by a robotic manipulator in support of a scanning operation.FIG. 1 illustrates generally an example comprising an acoustic inspection system 100, such as can be used to perform at least a portion one or more techniques as shown and described herein. The inspection system 100 can include a test instrument 140, such as a hand-held or portable assembly. The test instrument 140 can be electrically coupled to a probe assembly 150, such as using a multi -conductor interconnect 130. The probe assembly 150 can include one or more electroacoustic transducers, such as a transducer array 152 including respective transducers 154A through 154N. The transducers array can follow a linear or curved contour or can include an array of elements extending in two axes, such as providing a matrix of transducer elements. The elements need not be square in footprint or arranged along a straight-line axis. Element size and pitch can be varied according to the inspection application.A modular probe assembly 150 configuration can be used, such as to allow a test instrument 140 to be used with various different probe assemblies. Generally, the transducer array 152 includes piezoelectric transducers, such as can be acoustically coupled to a target 158 (e.g., a test specimen or “object-under-test”) through a coupling medium 156. The coupling medium can include a fluid or gel or a solid membrane (e.g., an elastomer or other polymer material), or a combination of fluid, gel, or solid structures. For example, an acoustic transducer assembly can include atransducer array coupled to a wedge structure comprising a rigid thermoset polymer having known acoustic propagation characteristics (for example, Rexolite® available from C-Lec Plastics Inc.), and water can be injected between the wedge and the structure under test as a coupling medium 156 during testing, or testing can be conducted with an interface between the probe assembly 150 and the target 158 otherwise immersed in a coupling medium.The test instrument 140 can include digital and analog circuitry, such as a front-end circuit 122 including one or more transmit signal chains, receive signal chains, or switching circuitry (e.g., transmit / receive switching circuitry). The transmit signal chain can include amplifier and filter circuitry, such as to provide transmit pulses for delivery through an interconnect 130 to a probe assembly 150 for insonification of the target 158, such as to image or otherwise detect a weld (or flaw) 160 on or within the target 158 structure by receiving scattered or reflected acoustic energy elicited in response to the insonification.While FIG. 1 shows a single probe assembly 150 and a single transducer array 152, other configurations can be used, such as multiple probe assemblies connected to a single test instrument 140, or multiple transducer arrays 152 used with a single probe assembly 150 or multiple probe assemblies for pitch / catch inspection modes. Similarly, a test protocol can be performed using coordination between multiple test instruments 140, such as in response to an overall test scheme established from a master test instrument 140 or established by another remote system such as a compute facility 108 or general-purpose computing device such as a laptop 132, tablet, smartphone, desktop computer, or the like. The test scheme may be established according to a published standard or regulatory requirement and may be performed upon initial fabrication or on a recurring basis for ongoing surveillance, as illustrative examples.The receive signal chain of the front-end circuit 122 can include one or more fdters or amplifier circuits, along with an analog-to-digital conversion facility, such as to digitize echo signals received using the probe assembly 150. Digitization can be performed coherently, such as to provide multiple channels of digitized data aligned or referenced to each other in time or phase. The front-end circuit can be coupled to and controlled by one or more processor circuits, such as a processor circuit 102included as a portion of the test instrument 140. The processor circuit 102 can be coupled to a memory circuit 104, such as to execute instructions that cause the test instrument 140 to perform one or more of acoustic transmission, acoustic acquisition, processing, or storage of data relating to an acoustic inspection, or to otherwise perform techniques as shown and described herein. The test instrument 140 can be communicatively coupled to other portions of the system 100, such as using a wired or wireless communication interface 120.For example, performance of one or more techniques as shown and described herein can be accomplished on-board the test instrument 140 or using other processing or storage facilities such as using a compute facility 108 or a general- purpose computing device such as a laptop 132, tablet, smart-phone, desktop computer, or the like. For example, processing tasks that would be undesirably slow if performed on-board the test instrument 140 or beyond the capabilities of the test instrument 140 can be performed remotely (e.g., on a separate system), such as in response to a request from the test instrument 140. Similarly, storage of imaging data or intermediate data such as A-scan matrices of time-series data or other representations of such data, for example, can be accomplished using remote facilities communicatively coupled to the test instrument 140. The test instrument can include a display 110, such as for presentation of configuration information or results, and an input device 112 such as including one or more of a keyboard, trackball, function keys or soft keys, mouse-interface, touch-screen, stylus, or the like, for receiving operator commands, configuration information, or responses to queries.Generally, the probe assembly 150 can be manipulated by hand, such as scanned across the target 158 by a user. Alternatively, or in addition, the probe assembly 150 can be positioned or oriented (or both) using a manipulator 170, such as a robotic arm supporting multiple mechanical degrees of freedom, or using other equipment such as a gantry, crane, or other apparatus including one or more linear or rotary actuators. A wrist region 174 (e.g., defining or including a mounting plate or flange) can be coupled to the probe assembly 150, where the probe assembly 150 serves as an end effector. A manipulator controller 172 (e.g., a hardware platform that can execute a manipulator control routine, such as to control one or more linear orrotary actuators to guide the probe assembly 150 in support of an inspection acquisition). While the system 100 of FIG. 1 shows an acoustic inspection application, such a configuration can be similar for eddy current inspection, such as where the probe assembly 150 comprises an eddy current transducer array.As mentioned above, the present subject matter can be used to align a probe assembly to facilitate non-destructive inspection. The techniques described herein are generally applicable to performing probe alignment (e.g., through controlling one or more of a probe orientation or a probe position, or both) to track a varying or even unknown geometry of a surface of an object under test. Generally, as described herein, such a surface can be tracked in the context of an automated scanning operation using sensors, such as laser profiling sensors and camera. The camera may be provided as a two-dimensional imaging camera. For example, laser profiling sensors can be used to obtain profiling data corresponding to locations on the object.In support of the discussion herein, FIG. 2 shows an illustrative example of a coordinate system and degrees of freedom used for robotic manipulation of a probe assembly. In this illustration, rotation around the x-axis is designated as "w," the y- axis as "p," and the z-axis as "r". The rotation directions conform to the right-hand rule. The axis system is precisely aligned with the robot tool center point (TCP) and moves in unison with it. In the illustrative examples herein, robot trajectory corrections will be transmitted and interpreted based on this coordinate system. Below is a summary of each source of correction for the five corrected degrees of freedom and to what physical value they correspond, as described in further detail below.X (Weld Center Position): Utilizes a combination of machine vision and laser profiling to determine the weld's center position. Z (Distance to Weld): Measures the distance between the weld and the sensor using laser profiling (e.g., exclusively). W (Tooling Angle around X-axis): Determines the angle of the tooling around the X-axis relative to the surface, relying on laser profiling (e.g., exclusively). P (Tooling Angle around Y-axis): Determines the angle of the tooling around the Y-axis relative to the surface, using laser profiling (e.g., exclusively). R (Weld Direction): Assesses the weld direction in relation to the robot's direction using data obtained from bothmachine vision and laser profiling.FIG. 3 is a flow diagram of a method 300 for controlling a robotic manipulator for acoustic sensing based on at least two sensors. The at least two sensors include a laser profiler and an imaging camera, as described herein. The two sensors are different from the acoustic sensors used to perform non-destructive testing on the object.At operation 302, weld location and adjacent surface properties are identified using laser profiling, as described in further detail below.At operation 304, weld location is determined based on an image using machine vision, as described in further detail below.At operation 306, outputs of the laser profiling and machine vision are combined using sensor fusion, as described in further detail below.At operation 308, corrections for control of the robotic manipulator are determined based on the combined / fused outputs.Next, techniques for identifying weld location and surface properties using laser profiling (e.g., operation 302) are described. FIG. 4 shows example portions of a weld profile based on laser profiling. Data from one or more laser profiling sensors is received. The sensor data may be noisy. A filter may be applied accordingly. After applying a condition on the data to remove the outliers, a low pass filter can be applied that is appropriate for the expected weld.A linear or polynomial regression to the profiling data may be applied at the beginning and end to estimate the position and orientation of the surface adjacent to weld. The P orientation of the surface adjacent to the weld may be determined. In the case of linear regression (flat surface) of form y = (3-yx + ft, the system compute: p = tan”1(ft)For the case of a polynomial regression (curved surface) of form y = ft%2+ ft % + ft, the system may determine:The weld peak position may be determined, which may correspond to thepoint where the distance between the weld profile and the linear regression is greatest:(.Xpeak, yPeak) max (y - y)The weld center position of the profde may be detected, which might differ from the weld peak location. Given that the weld profde might not always be circular, the center and peak might not align. To address this possible misalignment, the system may use a secondary linear regression, offset from the primary. Starting from the identified weld peak, the system may find the left and right intersections by noting where this secondary regression is crossed. Then the x position of the weld center is:Xright Xleft%c= - ~2-The weld height, width, and distance to the weld base may then be measured. To measure the weld width, the following can be determined: width = J (xright- xleft)2+ (yright- yieft)2To measure the weld height, the system can identify point xL,yL') that perpendicularly intersects the linear regression from the peak. Once this point is found, the following can be determined: heightTo measure the weld base distance, a point (%c, yc) can be identified that perpendicularly intersect the linear regression from the weld center, then distance to base = yc.The w orientation of the surface adjacent to the weld may be determined. To find the w, unlike p. the system can use two measured locations and the corresponding measured center intersection. Then, the system can find: yc= yc, 2 - yc, i-The system can identify the difference in the robot position on the Y-axis by:Roboty = Roboty2— RobotYi.Hence, the angle w becomes:The system may determine the direction of the weld, r. Also, unlikep, the system may use two different points for the robot and the corresponding measured weld center position. Then, the system may determine:A%c= Xc, 2 — xc, !The system may also identify the difference in the robot position on the Y-axis by: ARoboty = Roboty2— RobotYi.The angle r then becomes:Axcr = tan1ARobotyNext, techniques for determining weld location (e.g., weld center position) using machine vision (e.g., operation 304) are described. FIG. 5 shows a camera framework for capturing images of a weld. FIG. 5 shows a camera 502 located opposite of a weld location. FIG. 5 also shows a field of view of the camera 502 (from the image sensor origin). As described in further detail below, the machine vision techniques may depend on the distance measurement from the profiler for the pixel- to-length-units conversion.FIG. 6 shows a visual representation of an example of determining a weld center position using machine vision. At step I, an image of the surface of the object is imported from a 2D camera (e.g., camera 502). The source of this image could be a camera included as a portion of a laser profiler device, or it could come from a different device.At step II, glare from the image is removed using a thresholding technique. Glare removal may be performed to mitigate the effects of uneven lighting and overexposure (pixel values that are too close to white). Glare in the image can introduce unwanted edges and visual features that might distort the results.At step III, an edge detection algorithm is used to distinguish the visualfeatures of the weld from the adjacent surface. For example, the Canny edge detection algorithm may be used, as shown in the example of FIG. 6.At step IV, a line detection algorithm is employed to identify visual features representing the sides of the weld, which can also be referred to as “weld fusion lines.” For example, the Hough algorithm may be used, as shown in the example of FIG. 6. By identifying the left and right boundaries of the weld, the central position may be determined using the midpoint between these two lines, which allows corrections on the X axis. Furthermore, the orientation of these lines provides insights into the direction of the weld, guiding corrections on the R (rotation) axis.After the operations noted above, an image weld center coordinate, denoted as u, is currently expressed in pixels. To convert this from a pixel-based measurement to an actual physical measurement (e.g., mm), a value ycamcanbe used from the profding data. This value corresponds to the average distance between the camera and the surface being photographed. Coupled with the camera's known field-of-view, 0, the image width, denoted as w, can be determined as proportional to ycam' w = 2ycam■ tan(0 / 2)Consequently, the pixel scaling conversion factor, denoted as s, can be calculated by dividing the image width, by the number of pixels in the image, denoted as N: w s = — NWith this scaling factor, the weld center coordinate value can be converted to a physical value by first translating it relative to the image principal point and then applying the scaling. With cxas the principal point coordinate in pixels (the image center in camera coordinates), then the conversion is: xc= s(u — cx~)Next, techniques for combining the outputs of the laser profiling and machine vision using sensor fusion (e.g., operation 306) are described. FIG. 7 shows a block diagram comprising a generalized control loop architecture that can use the laser profiler and camera data as inputs and can fuse such data to provide compensation for control of a robotic manipulator.At 702, laser profile data, as described above, is received. For example, weld center position (X), distance to weld base (Z), surface angle (W and P), and weld direction (R) are determined using data from one or more laser profiling sensors as described above. In some examples, weld height and width may also be determined using data from the one or more laser profiling sensors.At 704, image data using machine vision, as described above, is received. For example, weld center position (X) and weld direction (R) determined using machine vision, as described above. Distance from the laser profiler and camera to weld base may also be obtained. In some examples, weld width may also be determined using machine vision.At 706, the laser profile data and image are fused. In some examples, Kalman filter is used for combining the laser profile data and image data to generate fused data. For example, a Kalman filter architecture can be used to optimally estimate a state of a system from multiple measurements with varying degrees of reliability. Specifically, the variance (low vs. high) of each measurement technique will generally influence the weighting in the Kalman filter, ensuring that the integrated data output is both accurate and dependable. The use of a Kalman filter is illustrative, and other types of sensor fusion algorithms could be used.At 708, the wanted robot pose with respect to weld surface is received. For example, X0mm (Weld center), ZTCPz (Distance to weld base), W - 0°, P - 0°, and R - 0° are received.An error estimation can be performed at 710, such as to compare a robotic manipulator state (e.g., position or orientation, or both) to a desired position or orientation (or both), to produce an error vector, e[k], where k represents an iteration index, or other representation of error.A proportional-integral-derivative (PID) controller 712 receives the error vector. The PID controller 712 can apply a proportional component at 712A, an integral component at 712B, and a differential or “derivative” component at 712C, using respective gain values Kp, Ki, Ka, to provide an input vector u[k] to a dynamic correction interface, such as a path modification routine, at 714. For example, the input vector u[k] can be provided as an input to registers associated with DPM wherea Fanuc system is used as the manipulator controller. The gain values Kp, K,. Ka affect the dynamic performance of the probe orientation and position adjustment, and suitable gain values will generally depend on specific test configuration, such as degree of curvature of the surface being inspected, a velocity of the translation of the probe assembly across the surface, and dynamic behavior of the robotic manipulator system.Various empirical techniques can be used to establish gain values Kp, Ki, Ka, such as a Ziegler-Nichols technique or other approach (e.g., an example of a manual approach can include increasing Kpuntil oscillation is observed, dividing that Kpvalue by a factor of 2, then increasing K until stability is achieved, then tuning Ka for dynamic performance). As mentioned above, an output of the path modification routine at 714 can be used to establish a new robotic manipulator position at 716, and the coordinates or other representation of the new robotic manipulator position can be fed back for use with distance measurement (or measurements) to provide an updated determination of a current state (e.g., orientation or position or both), for use in another error determination at 716 in a closed-loop manner, such as for successive different locations where data is received and successive determinations of parameters such as offset values are established for comparison with the desired target values. Such updates can be performed in discrete iterations such that the loop formed by the architecture 700 forms an auxiliary control loop independent of primary motion control of the robotic manipulator. For example, such an auxiliary control loop can function to modify a path and orientation established by a primary control loop where the primary control loop is providing motion control according to a nominal path or orientation. The dynamic correction interface at 714 can provide an interface between the loop defined by the control architecture 700 and a separate primary control architecture.Compared to existing laser profiling systems for weld detection, the present subject matter can incorporate use of machine vision in situations where laser profiling can lack the reliability for robust trajectory correction. By combining the strengths of both methods (visible light imaging and laser profiling), this approach can address limitations of use of laser profiling alone.FIG. 8 shows plots of detected weld center and detected weld width using laser profding and machine vision compared to laser profding alone. FIG. 8 shows that the combined approach, as described herein, does not show the instability (unstable region) that would otherwise occur in using laser profiling alone, when applied to a complex weld geometry.FIG. 9 illustrates a block diagram of an example comprising a machine 900 upon which any one or more of the techniques (e.g., methodologies) discussed herein may be performed. Machine 900 (e.g., computer system) may include a hardware processor 902 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 904 and a static memory 906, connected via an interlink 930 (e.g., link or bus), as some or all of these components may constitute hardware for systems or related implementations discussed above.Generally, the hardware processor 902 may, for example, include at least one of a Central Processing Unit (CPU), a Reduced Instruction Set Computing (RISC) Processor, a Complex Instruction Set Computing (CISC) Processor, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), a Tensor Processing Unit (TPU), a Neural Processing Unit (NPU), a Vision Processing Unit (VPU), a Machine Learning Accelerator, an Artificial Intelligence Accelerator, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Radio- Frequency Integrated Circuit (RFIC), aNeuromorphic Processor, a Quantum Processor, or any combination thereof. A processor circuit may further be a multi -core processor having two or more independent processors (sometimes referred to as "cores") that may execute instructions contemporaneously. Multi-core processors contain multiple computational cores on a single integrated circuit die, each of which can independently execute program instructions in parallel. Parallel processing on multi-core processors may be implemented via architectures like superscalar, VLIW, vector processing, or SIMD that allow each core to run separate instruction streams concurrently. A processor circuit may be emulated in software, running on a physical processor, as a virtual processor or virtual circuit. The virtual processor may behave like an independent processor but is implemented in software rather than hardware.Specific examples of main memory 904 include Random Access Memory (RAM), and semiconductor memory devices, which may include storage locations in semiconductors such as registers. Specific examples of static memory 1006 include non-volatile memory, such as semiconductor memory devices (e.g., Electrically Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM)) and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; RAM; or optical media such as CD-ROM and DVD-ROM disks.The machine 900 may further include a display device 910, an input device 912 (e.g., a keyboard), and a user interface (UI) navigation device 914 (e.g., a mouse). In an example, the display device 910, input device 912, and UI navigation device 914 may be a touch-screen display. The machine 900 may include a mass storage device 908 (e.g., drive unit), a signal generation device 918 (e.g., a speaker), a network interface device 920, and one or more sensors 916, such as a global positioning system (GPS) sensor, compass, accelerometer, or some other sensor. The machine 900 may include an output controller 928, such as a serial (e.g., universal serial bus (USB), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection to communicate or control one or more peripheral devices (e.g., a printer, card reader, etc.).The mass storage device 908 may comprise a machine-readable medium 922 on which is stored one or more sets of data structures or instructions 924 (e.g., software) embodying or utilized by any one or more of the techniques or functions described herein. The instructions 924 may also reside, completely or at least partially, within the main memory 904, within static memory 906, or within the hardware processor 902 during execution thereof by the machine 900. In an example, one or any combination of the hardware processor 902, the main memory 904, the static memory 906, or the mass storage device 908 comprises a machine readable medium.Specific examples of machine-readable media include, one or more of nonvolatile memory, such as semiconductor memory devices (e.g., EPROM or EEPROM) and flash memory devices; magnetic disks, such as internal hard disks andremovable disks; magneto-optical disks; RAM; or optical media such as CD-ROM and DVD-ROM disks. While the machine-readable medium is illustrated as a single medium, the term "machine readable medium" may include a single medium or multiple media (e.g., a centralized or distributed database, or associated caches and servers) configured to store the one or more instructions 924.An apparatus of the machine 900 includes one or more of a hardware processor 902 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 904 and a static memory 906, sensors 916, network interface device 920, antennas, a display device 910, an input device 912, a UI navigation device 914, a mass storage device 908, instructions 924, a signal generation device 918, or an output controller 928. The apparatus may be configured to perform one or more of the methods or operations disclosed herein.The term “machine readable medium” includes, for example, any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 900 and that cause the machine 900 to perform any one or more of the techniques of the present disclosure or causes another apparatus or system to perform any one or more of the techniques, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions. Non-limiting machine- readable medium examples include solid-state memories, optical media, or magnetic media. Specific examples of machine-readable media include: non-volatile memory, such as semiconductor memory devices (e.g., Electrically Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM)) and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; Random Access Memory (RAM); or optical media such as CD-ROM and DVD-ROM disks. In some examples, machine readable media includes non-transitory machine-readable media. In some examples, machine readable media includes machine readable media that is not a transitory propagating signal.The instructions 924 may be transmitted or received, for example, over a communications network 926 using a transmission medium via the network interfacedevice 920 utilizing any one of a number of transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards known as WiFi®), IEEE 802.15.4 family of standards, a Long Term Evolution (LTE) 4G or 5G family of standards, a Universal Mobile Telecommunications System (UMTS) family of standards, peer-to-peer (P2P) networks, satellite communication networks, among others.In an example, the network interface device 920 includes one or more physical jacks (e.g., Ethernet, coaxial, or other interconnection) or one or more antennas to access the communications network 926. In an example, the network interface device 920 includes one or more antennas to wirelessly communicate using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) techniques. In some examples, the network interface device 920 wirelessly communicates using Multiple User MIMO techniques. The term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding or carrying instructions for execution by the machine 900, and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.Various NotesThe above detailed description includes references to the accompanying drawings, which form a part of the detailed description. The drawings show, by way of illustration, specific embodiments in which the invention can be practiced. These embodiments are also referred to generally as “examples.” Such examples can include elements in addition to those shown or described. However, the present inventors also contemplate examples in which only those elements shown or described are provided. Moreover, the present inventors also contemplate examplesusing any combination or permutation of those elements shown or described (or one or more aspects thereof), either with respect to a particular example (or one or more aspects thereof), or with respect to other examples (or one or more aspects thereof) shown or described herein.In the event of inconsistent usages between this document and any documents so incorporated by reference, the usage in this document controls.

[0001] In this document, the terms “a” or “an” are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of “at least one” or “one or more.” In this document, the term “or” is used to refer to a nonexclusive or, such that “A or B” includes “A but not B,” “B but not A,” and “A and B,” unless otherwise indicated. In this document, the terms “including” and “in which” are used as the plain-English equivalents of the respective terms “comprising” and “wherein.” Also, in the following claims, the terms “including” and “comprising” are open-ended, that is, a system, device, article, composition, formulation, or process that includes elements in addition to those listed after such a term in a claim are still deemed to fall within the scope of that claim. Moreover, in the following claims, the terms “first,” “second,” and “third,” etc., are used merely as labels, and are not intended to impose numerical requirements on their objects.Method examples described herein can be machine or computer-implemented at least in part. Some examples can include a computer-readable medium or machine- readable medium encoded with instructions operable to configure an electronic device to perform methods as described in the above examples. An implementation of such methods can include code, such as microcode, assembly language code, a higher-level language code, or the like. Such code can include computer readable instructions for performing various methods. The code may form portions of computer program products. Such instructions can be read and executed by one or more processors to enable performance of operations comprising a method, for example. The instructions are in any suitable form, such as but not limited to source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like.Further, in an example, the code can be tangibly stored on one or more volatile, non- transitory, or non-volatile tangible computer-readable media, such as during executionor at other times. Examples of these tangible computer-readable media can include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., compact disks and digital video disks), magnetic cassettes, memory cards or sticks, random access memories (RAMs), read only memories (ROMs), and the like.The above description is intended to be illustrative, and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. Other embodiments can be used, such as by one of ordinary skill in the art upon reviewing the above description. The Abstract is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Also, in the above Detailed Description, various features may be grouped together to streamline the disclosure. This should not be interpreted as intending that an unclaimed disclosed feature is essential to any claim. Rather, inventive subject matter may he in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that such embodiments can be combined with each other in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

WHAT IS CLAIMED IS:

1. A machine-implemented method for controlling an alignment of a nondestructive test (NDT) inspection probe, the machine-implemented method comprising: receiving laser profde data from a laser profding sensor corresponding to a weld location and surface properties of an object under non-destructive testing; receiving image data from an image sensor corresponding to the weld location; fusing the laser profde data and the image sensor to generate fused data corresponding to the weld location; and transmitting a control signal to adjust a robotic manipulator of the NDT probe based on the fused data.

2. The machine-implemented method of claim 1, wherein further comprising: applying a fdter to the laser profde data; applying a regression technique the laser profde data to determine a position and orientation of a surface adjacent to the weld; and determining a tooling angle around a y-axis relative to the surface of the object based on the laser profde data.

3. The machine-implemented method of claim 2, further comprising: determining a weld peak position and a weld center position based on the laser profde data.

4. The machine-implemented method of any of claims 2 or 3, further comprising: determining a weld height, weld width, and a distance to the weld base based on the laser profde data.

5. The machine-implemented method of any of claims 1 through 4, further comprising:determining a second tooling angle around a x-axis relative to the surface of the object based on the laser profde data.

6. The machine-implemented method of any of claims 1 through 5, further comprising: determining a weld direction based on the laser profde data.

7. The machine-implemented method of any of claims 1 through 7, further comprising: applying a thresholding technique to the image data to reduce glare.

8. The machine-implemented method of any of claims 1 through 7, further comprising: applying an edge detection algorithm to the image data to distinguish visual features of the weld from the adjacent surface.

9. The machine-implemented method any of claims 1 through 8, further comprising: applying a line detection algorithm to the image data to identify a left boundary and a right boundary of the weld; determining a weld center position based on the left boundary and the right boundary.

10. The machine-implemented method of any of claims 1 through 9, wherein fusing the laser profde data and the image sensor comprises applying a Kalman fdter.

11. A system for controlling an alignment of a non-destructive test (NDT) inspection probe, the system comprising: a first sensor configured to acquire laser profile data corresponding to a weld location and surface properties of an object under non-destructive testing;a second sensor configured to acquire image data corresponding to the weld location; at least one processor circuit; at least one memory circuit comprising instructions that, when executed by the at least one processor circuit, cause the system to perform the machine-implemented method of any of claims 1 through 10.

12. A machine-storage medium embodying instructions that, when executed by a machine, cause the machine to perform the machine-implemented method of any of claims 1 through 10.

Images