Disc ring ultrasonic water immersion detection method and device

Abstract

The application provides a disc ring piece ultrasonic water immersion detection method and device. The method comprises the following steps: obtaining three-dimensional model data of a disc ring piece to be detected of an engine; collecting ultrasonic data of the disc ring piece to be detected according to the three-dimensional model data, to obtain ultrasonic data; preprocessing the ultrasonic data to obtain preprocessed data; performing defect detection on the disc ring piece to be detected according to the preprocessed data to obtain defect detection data; performing coordinate mapping according to the defect detection data and the three-dimensional model data to obtain defect distribution data; and obtaining an ultrasonic detection report of the disc ring piece to be detected according to the defect detection data and the defect distribution data. The application can improve the accuracy of defect detection on the disc ring piece, and reduce the misjudgment rate and the missed judgment rate.

Description

A method and apparatus for ultrasonic water immersion testing of disc ring components Technical Field

[0001] This invention relates to the field of ultrasonic testing technology, and also to a method and apparatus for ultrasonic water immersion testing of disc ring components. Background Technology

[0002] Disc-ring components are core parts of high-end equipment such as aero-engines, gas turbines, and wind power equipment. Their structures are mostly thin-walled rings / discs, operating under high temperature, high pressure, and high speed loads. Internal defects such as cracks, porosity, and inclusions can directly lead to the failure of the entire machine, causing major safety accidents. Ultrasonic testing is one of the mainstream non-destructive testing technologies for disc-ring components. Water immersion ultrasonic testing is widely used in mass production scenarios due to the stability of the coupling agent (water), good acoustic impedance matching, and high testing efficiency. However, due to interference signals such as multiple reflected waves, electrical noise, and workpiece surface clutter in water immersion testing, traditional algorithms (such as threshold filtering and simple Fourier transform) are difficult to effectively separate defect signals from interference signals, resulting in a high false positive and false negative rate, failing to meet the requirements of high-precision testing. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an ultrasonic water immersion testing method and apparatus for disc ring components, so as to improve the accuracy of defect detection of disc ring components.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] A first aspect of the present invention provides an ultrasonic water immersion testing method for a disc ring component, comprising:

[0006] Obtain the 3D model data of the disc-ring component to be tested in the engine;

[0007] Based on the three-dimensional model data, ultrasonic data is acquired from the disc ring component to be tested to obtain ultrasonic data.

[0008] The ultrasonic data is preprocessed to obtain preprocessed data;

[0009] Defect detection data is obtained by performing defect detection on the disc ring component to be inspected based on the preprocessed data.

[0010] Based on the defect detection data and the three-dimensional model data, coordinate mapping is performed to obtain defect distribution data;

[0011] Based on the defect detection data and the defect distribution data, an ultrasonic test report for the disc ring component to be tested is obtained.

[0012] Optionally, ultrasonic data is acquired from the disc ring component to be tested based on the three-dimensional model data to obtain ultrasonic data, including:

[0013] The three-dimensional model data is used to divide the data into sub-regions to obtain sub-region data;

[0014] Based on the sub-region data, determine the detection path;

[0015] Ultrasonic data is acquired by performing ultrasonic data acquisition on the disc ring component to be tested according to the detection path.

[0016] Optionally, the detection path is determined based on the sub-region data, including:

[0017] Based on the sub-region data and the preset normal calculation model, normal vector data is obtained;

[0018] pass Obtain the step size data; where, Step size, For the maximum allowable step size, K represents the minimum curvature, and K is the curvature value of the current detection point. This is the minimum allowable step size;

[0019] Based on the normal vector data and the step size data, coordinate data is obtained;

[0020] The detection path is determined based on the coordinate data and preset robotic arm parameters.

[0021] Optionally, the ultrasonic data is preprocessed to obtain preprocessed data, including:

[0022] pass Obtain DC data; among which, To remove DC data, For ultrasound data, The mean value of the ultrasound data;

[0023] Gain processing is performed on the de-DC data based on the mean of the effective data in the de-DC data to obtain preprocessed data.

[0024] Optionally, defect detection is performed on the disc ring component to be inspected based on the preprocessed data to obtain defect detection data, including:

[0025] according to The sound wave propagation time was obtained;

[0026] according to The thickness of the water coupling layer is obtained;

[0027] according to Obtain the defect depth;

[0028] Defect data is obtained by performing defect detection based on the preprocessed data and the trained defect detection model.

[0029] Based on the defect depth and the defect data, defect detection data is obtained;

[0030] in, For the sound wave propagation time, To determine the propagation time of sound waves in the water coupling layer in the preprocessed data, The propagation time of sound waves inside the disk ring component is used to preprocess the data. Where is the thickness of the water coupling layer, and L is the distance from the sensor probe to the surface of the disk ring component. H represents the thickness of the sensor probe's housing, and H represents the defect depth. The sound velocity of the disc ring material. The propagation time of sound waves within the disc ring component is determined by... We obtained, among which, This is the speed of sound in water.

[0031] Optionally, coordinate mapping is performed based on the defect detection data and the three-dimensional model data to obtain defect distribution data, including:

[0032] The defect coordinates are obtained by performing coordinate transformation based on the defect depth in the defect detection data;

[0033] Based on the three-dimensional model data, the defect coordinates are mapped to obtain defect distribution data.

[0034] Optionally, based on the defect detection data and the defect distribution data, an ultrasonic testing report for the disc-ring component to be tested is obtained, including:

[0035] The target defect level is obtained based on the defect data and the preset defect level in the defect detection data;

[0036] An ultrasonic test report for the disc ring component to be tested is obtained based on the target defect level, the defect detection data, and the defect distribution data.

[0037] A second aspect of the present invention provides an ultrasonic water immersion testing device for a disc ring component, comprising:

[0038] The acquisition module is used to acquire the three-dimensional model data of the disc ring component to be tested in the engine;

[0039] The processing module is used to acquire ultrasonic data from the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data; preprocess the ultrasonic data to obtain preprocessed data; perform defect detection on the disc-ring component to be tested based on the preprocessed data to obtain defect detection data; perform coordinate mapping between the defect detection data and the three-dimensional model data to obtain defect distribution data; and obtain an ultrasonic test report for the disc-ring component to be tested based on the defect detection data and the defect distribution data.

[0040] A third aspect of the present invention provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described in the first aspect.

[0041] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method as described in the first aspect.

[0042] The above-described solution of the present invention has at least the following beneficial effects:

[0043] The above-described solution of the present invention obtains three-dimensional model data of the disc-ring component to be inspected in the engine, and performs ultrasonic data acquisition on the disc-ring component to be inspected based on the three-dimensional model data to obtain ultrasonic data. The ultrasonic data is preprocessed to obtain preprocessed data. Defect detection is performed on the disc-ring component to be inspected based on the preprocessed data to obtain defect detection data. Coordinate mapping is performed on the defect detection data and the three-dimensional model data to obtain defect distribution data. Finally, an ultrasonic inspection report of the disc-ring component to be inspected is obtained based on the defect detection data and the defect distribution data. This method can improve the accuracy of defect detection of disc-ring components and reduce the false positive rate and false negative rate. Attached Figure Description

[0044] Figure 1 is a schematic flowchart of the ultrasonic water immersion detection method in an embodiment of the present invention;

[0045] Figure 2 shows a three-dimensional model of the disk ring component to be tested in an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of the ultrasonic water immersion detection device in an embodiment of the present invention.

[0047] Explanation of reference numerals in the attached diagram: 100 - Disc ring to be tested. Detailed Implementation

[0048] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0049] As shown in Figure 1, an embodiment of the present invention provides an ultrasonic water immersion testing method for a disc ring component, comprising the following steps:

[0050] Step 101: Obtain the three-dimensional model data of the disc ring component to be tested in the engine;

[0051] Step 102: Acquire ultrasonic data of the disc ring to be tested based on the three-dimensional model data to obtain ultrasonic data;

[0052] Step 103: Preprocess the ultrasonic data to obtain preprocessed data;

[0053] Step 104: Perform defect detection on the disc ring component to be tested based on the preprocessed data to obtain defect detection data;

[0054] Step 105: Perform coordinate mapping based on the defect detection data and the three-dimensional model data to obtain defect distribution data;

[0055] Step 106: Based on the defect detection data and the defect distribution data, obtain the ultrasonic test report of the disc ring component to be tested.

[0056] The ultrasonic water immersion testing method for disc and ring components according to this invention acquires three-dimensional model data of the disc and ring components to be tested in an engine, and performs ultrasonic data acquisition on the disc and ring components to be tested based on the three-dimensional model data to obtain ultrasonic data. The ultrasonic data is preprocessed to obtain preprocessed data. Defect detection is performed on the disc and ring components to be tested based on the preprocessed data to obtain defect detection data. Coordinate mapping is performed between the defect detection data and the three-dimensional model data to obtain defect distribution data. Finally, an ultrasonic testing report of the disc and ring components to be tested is obtained based on the defect detection data and the defect distribution data. This method can improve the accuracy of defect detection of disc and ring components and reduce the false positive rate and false negative rate.

[0057] In an optional embodiment of the present invention, step 101, acquiring the three-dimensional model data of the disc ring component to be tested in the engine, includes:

[0058] Step 1011: Obtain the three-dimensional model of the disc ring component to be tested in the engine;

[0059] Step 1012: Extract data from the three-dimensional model to obtain the three-dimensional model data of the disk ring component to be tested.

[0060] Specifically, as shown in Figure 2, the three-dimensional model of the disc-ring component to be tested can be a CAD (Computer-Aided Design) three-dimensional model. Three-dimensional model data such as the outer radius, inner radius, thickness (varying with circumferential angle), and fillet radius of the disc-ring component to be tested are extracted from this model. The three-dimensional model data can also include the three-dimensional model of the disc-ring component to be tested.

[0061] In an optional embodiment of the present invention, step 102, which involves acquiring ultrasonic data from the disc ring component to be tested based on the three-dimensional model data to obtain ultrasonic data, may include:

[0062] Step 1021: Divide the data into sub-regions based on the three-dimensional model data to obtain sub-region data;

[0063] Specifically, firstly, the 3D model of the disk-ring component to be detected in the 3D model data is triangulated to generate discrete point cloud data; then, through... The Gaussian curvature of each discrete point in the discrete point cloud data is calculated. Where a, b, and c are fitting coefficients, obtained by solving the quadratic surface equation. The result is obtained, where d, e, and f are fitting coefficients, and u and v are the local tangent plane coordinates of discrete points. Sub-regions are divided according to preset partitioning conditions to obtain sub-regions. The 3D model data is then divided into planar region data, arc region data, and transition rounded corner region data according to the corresponding sub-regions to obtain sub-region data (sub-region data includes discrete point cloud data of each sub-region). Here, the preset partitioning conditions may include: planar region... The arc-shaped area is Transition rounded corner area .

[0064] In one specific embodiment, the three-dimensional model of the disc ring to be tested can also be divided into sub-regions such as planar region, arc region, and transition rounded corner region according to preset geometric feature data. Then, the three-dimensional model data can be divided into planar region data, arc region data, and transition rounded corner region data according to the corresponding sub-regions. The sub-region data includes planar region data, arc region data, and transition rounded corner region data. The preset geometric feature data can be: the geometric feature corresponding to the planar region is a constant surface normal vector and curvature K=0; the geometric feature corresponding to the arc region is a cylindrical / conical surface with curvature K=1 / R, where R is the radius of the arc surface; the geometric feature corresponding to the transition rounded corner region is a spherical / circular transition surface with curvature K=1 / r, where r is the radius of the rounded corner.

[0065] Step 1022: Determine the detection path based on the sub-region data;

[0066] In an optional embodiment of the present invention, step 1022 includes:

[0067] Step 10221: Obtain normal vector data based on the sub-region data and the preset normal calculation model;

[0068] Specifically, the preset normal calculation model includes: planar region normal calculation model. Arc-shaped region normal calculation model The calculation model for the normals in the transition rounded corner area is consistent with that of the arc-shaped area. Normal vector data is obtained by inputting sub-region data into the preset normal calculation model. Among them, Let be the unit normal vector of the i-th detection point in the planar region. These are all coefficients of the plane equation fitted to the planar region. The plane equation fitted to the planar region is: ,in, , , d1 is a constant term in the cylindrical coordinate system of the disk-ring component. Let be the unit normal vector of the i-th detection point in the arc-shaped region. , , Let be the cylindrical coordinates of the i-th detection point in the arc-shaped region. , , The cylindrical coordinates are the center of the arc-shaped region.

[0069] Step 10222, through Obtain the step size data; where, Let i be the step size corresponding to the i-th detection point. For the maximum allowable step size, K represents the minimum curvature, and K is the curvature value of the current detection point. For the minimum allowable step size, The step size is a maximum value function, and the step size data includes the step size corresponding to each detection point;

[0070] Step 10223: Obtain coordinate data based on the normal vector data and the step size data;

[0071] Specifically, the geometric center of each sub-region is selected as the starting point of the path. Starting from the path starting point, the path is traversed along the tangent direction of the region's outline. Generate the next path point ,in, For the (k+1)th path point, For the k-th path point, Let k be the step size corresponding to the k-th path point in the step size data. Let be the unit tangent direction vector at the k-th path point, through We obtain , where is the unit normal vector at the k-th path point. This is the main extension direction vector of the region contour. The coordinate data includes all path points and their corresponding coordinates, which are based on the origin O at the center of the disc ring, with the axial direction as the Z-axis, the radial direction as the R-axis, and the circumferential direction as... The cylindrical coordinate system OR established by the axes Z obtained.

[0072] Step 10224: Determine the detection path based on the coordinate data and preset robotic arm parameters.

[0073] Specifically, the preset robotic arm parameters include maximum speed and acceleration. It should be noted that, depending on the actual situation, the preset robotic arm parameters can also be preset truss (or frame) parameters, which also include maximum speed and acceleration. After smoothing the path points in the coordinate data, a continuous motion trajectory is generated to avoid robotic arm jitter. The coordinates of the path points in the cylindrical coordinate system are converted to Cartesian coordinates (X, Y, Z) that the robotic arm can recognize. Based on the converted coordinates, normal direction, and preset robotic arm parameters, a detection path with path control instructions is generated. This detection path includes the converted coordinates, normal direction, and preset robotic arm parameters.

[0074] Step 1023: Perform ultrasonic data acquisition on the disc ring component to be tested according to the detection path to obtain ultrasonic data.

[0075] Specifically, the detection path with path control instructions is sent to the controller of the data acquisition device. This controller controls a three-axis linkage robotic arm equipped with an ultrasonic probe, which, in conjunction with a laser displacement sensor, acquires the detection data of the disk / ring component under test in real time. The ultrasonic probe is a focused ultrasonic probe with a center frequency of 5 to 10 MHz. The ultrasonic probe emits pulsed sound waves, and the receiver collects the reflected wave signals to obtain the raw time-domain signal data. The laser displacement sensor measures the surface coordinates of the disk / ring component at the current detection point. The ultrasonic data includes the raw time-domain signal data acquired by the ultrasonic probe and the coordinate data acquired by the laser displacement sensor.

[0076] In an optional embodiment of the present invention, step 103, preprocessing the ultrasonic data to obtain preprocessed data, may include:

[0077] Step 1031, through Obtain DC data; among which, To remove DC data, This refers to the raw time-domain signal data in the ultrasonic data. The mean value of the ultrasound data;

[0078] Specifically, due to constant offsets in the signal caused by factors such as probe circuit noise and static scattering from water, it is necessary to remove the DC component from the original time-domain signal data in the ultrasonic data to improve data accuracy.

[0079] Step 1032: Perform gain processing on the deDC data based on the mean of the effective data in the deDC data to obtain preprocessed data.

[0080] Specifically, firstly through The peak amplitude of the signal is calculated; where, The peak amplitude of the signal. To remove DC data, It is a function for maximizing the value.

[0081] Valid data is obtained based on the peak amplitude of the signal and a preset noise threshold; here, DC data in the range where the peak amplitude of the signal is greater than the preset noise threshold is determined as valid data.

[0082] Based on the peak amplitude of the valid data, the mean of the peak amplitude is obtained; the mean of the peak amplitude is the average of the peak amplitudes of all valid data.

[0083] Gain is determined based on preset judgment conditions and the average peak amplitude to obtain a judgment result. Here, the preset judgment conditions include: when the average peak amplitude is greater than a first preset value (e.g., 50mV), the signal strength is strong; when the average peak amplitude is greater than a second preset value (e.g., 10mV) and less than the first preset value, the signal strength is medium; when the average peak amplitude is less than the second preset value, the signal strength is weak. By comparing the average peak amplitude with the preset judgment conditions, a judgment result of strong, medium, or weak signal strength can be obtained.

[0084] Based on the judgment result, the DC data is subjected to gain processing to obtain preprocessed data. Here, when the judgment result indicates strong or weak signal strength, the DC data undergoes significant gain processing; when the judgment result indicates moderate signal strength, the DC data undergoes moderate gain processing. The gain coefficient is dynamically adjusted according to the signal amplitude distribution, focusing on amplifying weak signal areas (such as curved surface oblique reflection echoes) and limiting the gain in strong signal areas (such as workpiece bottom surface echoes) to avoid signal saturation, improve data quality, and enhance the accuracy of subsequent detection.

[0085] In an optional embodiment of the present invention, step 104, performing defect detection on the disc ring component to be inspected based on the preprocessed data to obtain defect detection data, may include:

[0086] Step 1041, according to The sound wave propagation time was obtained;

[0087] Step 1042, according to The thickness of the water coupling layer is obtained;

[0088] Step 1043, according to Obtain the defect depth;

[0089] Step 1044: Perform defect detection based on the preprocessed data and the trained defect detection model to obtain defect data;

[0090] Step 1045: Obtain defect detection data based on the defect depth and the defect data;

[0091] in, For the sound wave propagation time, To determine the propagation time of sound waves in the water coupling layer in the preprocessed data, The propagation time of sound waves inside the disk ring component is used to preprocess the data. Where is the thickness of the water coupling layer, and L is the distance from the sensor probe to the surface of the disk ring component. H represents the thickness of the sensor probe's housing, and H represents the defect depth. The sound velocity of the disc ring material. The propagation time of sound waves within the disc ring component is determined by... We obtained, among which, This is the speed of sound in water.

[0092] Specifically, in step 1044, the preprocessed data is first decomposed into small packets. Based on the db4 wavelet basis, the decomposition layer is 5 layers. Then, through... The energy entropy is calculated; where, Let N be the energy entropy, and N be the number of sampling points in the k-th frequency band. The energy percentage of the i-th sampling point in the k-th frequency band is used; the high-frequency band (e.g., 2 to 5 MHz) where the defective signal is concentrated is retained, and the low-frequency noise band and high-frequency clutter band are removed to reconstruct the denoised signal.

[0093] Data extraction is performed on the denoised signal to obtain feature data. The feature data includes: maximum peak amplitude, rise time, pulse width, and center frequency. The maximum peak amplitude is the maximum absolute value of the denoised signal; the rise time is the time difference between the signal rising from 10% peak to 90% peak; the pulse width is the duration for which the signal amplitude is greater than 50% peak; and the center frequency is determined by... The calculation yielded that, f is the center frequency of the frequency band. Let f be the power spectral density at frequency f.

[0094] The feature data is input into the first processing layer of the trained defect detection model to obtain the first processing result. Here, the first processing layer performs data standardization on the feature data to eliminate the dimensional differences of different feature parameters.

[0095] The first processing result is input into the second processing layer of the trained defect detection model to obtain the second processing result. Here, the second processing layer implicitly maps the first processing result in the low-dimensional space to the high-dimensional feature space through a kernel function, making the originally linearly inseparable defect / interference signal features linearly separable in the high-dimensional space. Here, the kernel function is... ,in, This is the second processing result. This is the low-dimensional space normalized feature vector of the i-th sample in the first processing result. This is the low-dimensional space normalized feature vector of the j-th sample in the first processing result. This is the kernel function, with values ​​ranging from 0.01 to 1. It is an exponential function.

[0096] The second processing result is input into the third processing layer of the trained defect detection model to obtain the third processing result; here, through The classification scores were obtained, among which, To score by category, This is the low-dimensional space-normalized feature vector of the k-th signal to be tested in the second processing result. For optimal Lagrange multipliers, For sample labels, This is the normalized feature vector derived from the support vectors obtained during the training phase. This is a bias term. The third processing result includes classification scores.

[0097] Defect detection is performed based on the third processing result to obtain defect data. Here, when the classification score in the third processing result is greater than 0, it is determined to be a defect signal; when the classification score is not greater than 0, it is determined to be an interference signal. The defect signal is then bound to the corresponding path point coordinates as defect data.

[0098] Here, defect detection data includes defect depth and defect data.

[0099] In an optional embodiment of the present invention, the training process of the defect detection model includes:

[0100] Acquire training samples; the training samples include positive samples and negative samples, wherein positive samples are ultrasonic echo signals containing defects (such as cracks, inclusion echoes), and negative samples are interference signals (such as multiple reflections, surface clutter, electrical noise).

[0101] The training samples are divided into a training set and a test set;

[0102] The pre-set network model is trained based on the training set and its corresponding classification labels until the accuracy of the test set reaches the pre-set accuracy (e.g., 95%). Training is then stopped, and the trained defect detection model is obtained.

[0103] In an optional embodiment of the present invention, step 105, which involves performing coordinate mapping based on the defect detection data and the three-dimensional model data to obtain defect distribution data, may include:

[0104] Step 1051: Perform coordinate transformation based on the defect depth in the defect detection data to obtain the defect coordinates;

[0105] Specifically, a spatial rectangular coordinate system O-xyz is established with the center of the disc ring to be inspected as the origin, and the circumferential angle of the current inspection point is... The radial coordinate is r, combined with the defect depth H, through , , Calculate the defect coordinates (X, Y, Z).

[0106] Step 1052: Map the defect coordinates to the three-dimensional model data to obtain defect distribution data.

[0107] Specifically, the defect coordinates are mapped onto the three-dimensional model of the disk ring component to generate a three-dimensional defect distribution map. The defect distribution data includes the three-dimensional defect distribution map.

[0108] In an optional embodiment of the present invention, step 106, obtaining an ultrasonic testing report for the disc ring component to be tested based on the defect detection data and the defect distribution data, may include:

[0109] Step 1061: Obtain the target defect level based on the defect data and preset defect level in the defect detection data;

[0110] Specifically, based on the magnitude, size, and location of the defect, the corresponding target defect level is obtained from the preset defect levels.

[0111] Step 1062: Based on the target defect level, the defect detection data, and the defect distribution data, obtain the ultrasonic test report of the disc ring component to be tested.

[0112] Specifically, a preset report template can be obtained, and then the target defect level, defect detection data, and defect distribution data can be filled into the preset report template to quickly generate an ultrasonic test report for the disc ring component to be tested. The ultrasonic test report for the disc ring component to be tested can include data such as the number, location, size, and level of defects.

[0113] A specific embodiment of the ultrasonic water immersion testing method for disc ring components according to the present invention includes:

[0114] Step 111: Obtain the 3D model data of the disc ring component to be tested in the engine;

[0115] Figure 2 shows a CAD 3D model of a disc-ring component 100 to be inspected. By acquiring the CAD 3D model of the disc-ring component to be inspected, key parameters such as the outer circle radius, inner hole radius, thickness, and fillet radius are extracted.

[0116] Step 112: Acquire ultrasonic data from the disc ring component to be tested based on the three-dimensional model data to obtain ultrasonic data;

[0117] After determining the detection path based on the 3D model data, a three-axis linkage robotic arm with an angle-adjustable gimbal is used to carry an ultrasonic probe, which is combined with a laser displacement sensor to collect the surface normal angle of the detection point in real time; and a focused ultrasonic probe is used to emit pulse sound waves and receive the reflected wave signal to obtain the original time domain signal.

[0118] Step 113: Preprocess the ultrasonic data to obtain preprocessed data;

[0119] By performing DC removal and gain adjustment on the raw time-domain signal in the ultrasonic data, the quality of the acquired data is improved, thereby increasing the accuracy of subsequent defect detection.

[0120] Step 114: Perform defect detection on the disc ring component to be tested based on the preprocessed data to obtain defect detection data;

[0121] The defect depth is calculated based on the preprocessed data, and the defect detection model is used to detect the defect, resulting in defect detection data with defect coordinates.

[0122] Step 115: Perform coordinate mapping based on the defect detection data and the three-dimensional model data to obtain defect distribution data;

[0123] Mapping the defect coordinates onto the 3D model makes it easy to see the location of the defect intuitively.

[0124] Step 116: Based on the defect detection data and the defect distribution data, obtain the ultrasonic test report of the disc ring component to be tested.

[0125] By filling in the data according to the preset report template, an ultrasonic test report for the disc ring to be tested can be generated quickly and accurately, improving user satisfaction and processing efficiency.

[0126] The ultrasonic water immersion testing method for disc and ring components in this invention can improve the detection coverage by determining the detection path, reduce the false detection rate and false negative rate to less than 1%, reduce the number of repeated adjustments to the detection path, shorten the single-piece detection time by more than 30%, and greatly improve the efficiency and accuracy of defect detection for disc and ring components.

[0127] As shown in Figure 3, an embodiment of the present invention provides an ultrasonic water immersion testing device 300 for a disc ring component, comprising:

[0128] The acquisition module 301 is used to acquire the three-dimensional model data of the disc ring component to be tested in the engine;

[0129] The processing module 302 is used to acquire ultrasonic data from the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data; preprocess the ultrasonic data to obtain preprocessed data; perform defect detection on the disc-ring component to be tested based on the preprocessed data to obtain defect detection data; perform coordinate mapping between the defect detection data and the three-dimensional model data to obtain defect distribution data; and obtain an ultrasonic test report for the disc-ring component to be tested based on the defect detection data and the defect distribution data.

[0130] Optionally, ultrasonic data is acquired from the disc ring component to be tested based on the three-dimensional model data to obtain ultrasonic data, including:

[0131] The three-dimensional model data is used to divide the data into sub-regions to obtain sub-region data;

[0132] Based on the sub-region data, determine the detection path;

[0133] Ultrasonic data is acquired by performing ultrasonic data acquisition on the disc ring component to be tested according to the detection path.

[0134] Optionally, the detection path is determined based on the sub-region data, including:

[0135] Based on the sub-region data and the preset normal calculation model, normal vector data is obtained;

[0136] pass Obtain the step size data; where, Step size, For the maximum allowable step size, K represents the minimum curvature, and K is the curvature value of the current detection point. This is the minimum allowable step size;

[0137] Based on the normal vector data and the step size data, coordinate data is obtained;

[0138] The detection path is determined based on the coordinate data and preset robotic arm parameters.

[0139] Optionally, the ultrasonic data is preprocessed to obtain preprocessed data, including:

[0140] pass Obtain DC data; among which, To remove DC data, For ultrasound data, The mean value of the ultrasound data;

[0141] Gain processing is performed on the de-DC data based on the mean of the effective data in the de-DC data to obtain preprocessed data.

[0142] Optionally, defect detection is performed on the disc ring component to be inspected based on the preprocessed data to obtain defect detection data, including:

[0143] according to The sound wave propagation time was obtained;

[0144] according to The thickness of the water coupling layer is obtained;

[0145] according to Obtain the defect depth;

[0146] Defect data is obtained by performing defect detection based on the preprocessed data and the trained defect detection model.

[0147] Based on the defect depth and the defect data, defect detection data is obtained;

[0148] in, For the sound wave propagation time, To determine the propagation time of sound waves in the water coupling layer in the preprocessed data, The propagation time of sound waves inside the disk ring component is used to preprocess the data. Where is the thickness of the water coupling layer, and L is the distance from the sensor probe to the surface of the disk ring component. H represents the thickness of the sensor probe's housing, and H represents the defect depth. The sound velocity of the disc ring material. The propagation time of sound waves within the disc ring component is determined by... We obtained, among which, This is the speed of sound in water.

[0149] Optionally, coordinate mapping is performed based on the defect detection data and the three-dimensional model data to obtain defect distribution data, including:

[0150] The defect coordinates are obtained by performing coordinate transformation based on the defect depth in the defect detection data;

[0151] Based on the three-dimensional model data, the defect coordinates are mapped to obtain defect distribution data.

[0152] Optionally, based on the defect detection data and the defect distribution data, an ultrasonic testing report for the disc-ring component to be tested is obtained, including:

[0153] The target defect level is obtained based on the defect data and the preset defect level in the defect detection data;

[0154] An ultrasonic test report for the disc ring component to be tested is obtained based on the target defect level, the defect detection data, and the defect distribution data.

[0155] The ultrasonic water immersion testing device for disc and ring components of this invention acquires three-dimensional model data of the disc and ring components to be tested in an engine, and performs ultrasonic data acquisition on the disc and ring components to be tested based on the three-dimensional model data to obtain ultrasonic data. The ultrasonic data is preprocessed to obtain preprocessed data. Defect detection is performed on the disc and ring components to be tested based on the preprocessed data to obtain defect detection data. Coordinate mapping is performed on the defect detection data and the three-dimensional model data to obtain defect distribution data. Finally, an ultrasonic test report of the disc and ring components to be tested is obtained based on the defect detection data and the defect distribution data. This method can improve the accuracy of defect detection of disc and ring components and reduce the false positive rate and false negative rate.

[0156] It should be noted that this device corresponds to the method described above, and all implementations in the method embodiments described above are applicable to the embodiments of this device and can achieve the same technical effect. Further details are omitted in this embodiment.

[0157] This invention also provides a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects. Further details are omitted in this embodiment.

[0158] This invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method as described in any of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects. Further details are omitted in this embodiment.

[0159] It should be noted that in the apparatus and method of the present invention, the components or steps can obviously be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Furthermore, the steps for performing the above series of processes can naturally be performed in the order described and in chronological order, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel, overlapping, or independently of each other.

[0160] It should be noted that in the above embodiments, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments described above is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0161] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for ultrasonic water immersion testing of disc ring components, characterized in that, include: Acquire the three-dimensional model data of the disc-ring component to be tested in the engine; perform ultrasonic data acquisition on the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data; preprocess the ultrasonic data to obtain preprocessed data; Defect detection is performed on the disc-ring component to be tested based on the preprocessed data to obtain defect detection data; coordinate mapping is performed on the defect detection data and the three-dimensional model data to obtain defect distribution data; an ultrasonic testing report of the disc-ring component to be tested is obtained based on the defect detection data and the defect distribution data; wherein, ultrasonic data acquisition is performed on the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data, including: triangulating the three-dimensional model of the disc-ring component to be tested in the three-dimensional model data to generate discrete point cloud data; through The Gaussian curvature of each discrete point in the discrete point cloud data is calculated. Where a, b, and c are fitting coefficients, obtained by solving the quadratic surface equation. The data is obtained by dividing the model into sub-regions according to preset division conditions. The 3D model data is further divided into planar region data, arc region data, and transition rounded corner region data according to the corresponding sub-regions, resulting in sub-region data. The sub-region data includes discrete point cloud data for each sub-region. A detection path is determined based on the sub-region data. Ultrasonic data is acquired from the disc ring component to be inspected according to the detection path, resulting in ultrasonic data. Determining the detection path based on the sub-region data includes: obtaining normal vector data based on the sub-region data and a preset normal calculation model. The preset normal calculation model includes: a planar region normal calculation model. Arc-shaped region normal calculation model The normal calculation model for the transition rounded corner area is obtained by inputting sub-region data into a preset normal calculation model to obtain normal vector data; among which... Let be the unit normal vector of the i-th detection point in the planar region. These are all coefficients of the plane equation fitted to the planar region. The plane equation fitted to the planar region is: ,in, 、 、 d1 is a constant term in the cylindrical coordinate system of the disk-ring component. Let be the unit normal vector of the i-th detection point in the arc-shaped region. 、 、 Let be the cylindrical coordinates of the i-th detection point in the arc-shaped region. 、 、 Cylindrical coordinates of the center of the arc-shaped region; through Obtain the step size data; where, Step size, For the maximum allowable step size, K represents the minimum curvature, and K is the curvature value of the current detection point. The minimum allowable step size is determined; coordinate data is obtained based on the normal vector data and the step size data; the geometric center of each sub-region is selected as the path starting point, and starting from the path starting point, the path is traversed along the tangent direction of the region contour. Generate the next path point ,in, For the (k+1)th path point, For the k-th path point, Let k be the step size corresponding to the k-th path point in the step size data. Let be the unit tangent direction vector at the k-th path point. ,in, Let be the unit normal vector at the k-th path point. The main extension direction vector of the region contour is defined, and the coordinate data includes all path points and their corresponding coordinates. Based on the coordinate data and preset robotic arm parameters, the detection path is determined. The ultrasonic data is preprocessed to obtain preprocessed data, including: through... Obtain DC data; among which, To remove DC data, For ultrasound data, The mean of the ultrasound data; through The peak amplitude of the signal is calculated; where, The peak amplitude of the signal. To remove DC data, The maximum value function is used; effective data is obtained based on the peak amplitude of the signal and a preset noise threshold; the mean of the peak amplitude is obtained based on the peak amplitude of the effective data; gain judgment is performed based on preset judgment conditions and the mean of the peak amplitude to obtain a judgment result; gain processing is performed on the de-DC data based on the judgment result to obtain preprocessed data; wherein, defect detection is performed on the disk ring component to be tested based on the preprocessed data to obtain defect detection data, including: based on Obtain the sound wave propagation time; according to The thickness of the water coupling layer is obtained; according to The defect depth is obtained; defect detection is performed based on the preprocessed data and the trained defect detection model to obtain defect data; defect detection data is obtained based on the defect depth and the defect data; wherein, For the sound wave propagation time, To determine the propagation time of sound waves in the water coupling layer in the preprocessed data, The propagation time of sound waves inside the disk ring component is used to preprocess the data. Where is the thickness of the water coupling layer, and L is the distance from the sensor probe to the surface of the disk ring component. H represents the thickness of the sensor probe's housing, and H represents the defect depth. The sound velocity of the disc ring material. The propagation time of sound waves within the disc ring component is determined by... We obtained, among which, The speed of sound in water; wherein, based on the defect detection data and the three-dimensional model data, coordinate mapping is performed to obtain defect distribution data, including: performing coordinate transformation based on the defect depth in the defect detection data to obtain defect coordinates; establishing a spatial rectangular coordinate system O-xyz with the center of the disc ring to be detected as the origin, and the circumferential angle of the current detection point is... The radial coordinate is r, combined with the defect depth H, through 、 、 Calculate the defect coordinates (X, Y, Z); perform coordinate mapping on the defect coordinates based on the three-dimensional model data to obtain defect distribution data.

2. The ultrasonic water immersion testing method for disc ring components according to claim 1, characterized in that, Based on the defect detection data and the defect distribution data, an ultrasonic test report for the disc-ring component to be tested is obtained, including: obtaining a target defect level based on the defect data and a preset defect level in the defect detection data; and obtaining an ultrasonic test report for the disc-ring component to be tested based on the target defect level, the defect detection data, and the defect distribution data.

3. An ultrasonic water immersion testing device for disc ring components, characterized in that, include: The acquisition module is used to acquire the three-dimensional model data of the disc-ring component to be tested in the engine; the processing module is used to perform ultrasonic data acquisition on the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data; and to preprocess the ultrasonic data to obtain preprocessed data. Defect detection is performed on the disc-ring component to be tested based on the preprocessed data to obtain defect detection data; coordinate mapping is performed on the defect detection data and the three-dimensional model data to obtain defect distribution data; an ultrasonic testing report of the disc-ring component to be tested is obtained based on the defect detection data and the defect distribution data; wherein, ultrasonic data acquisition is performed on the disc-ring component to be tested based on the three-dimensional model data to obtain ultrasonic data, including: triangulating the three-dimensional model of the disc-ring component to be tested in the three-dimensional model data to generate discrete point cloud data; through The Gaussian curvature of each discrete point in the discrete point cloud data is calculated. Where a, b, and c are fitting coefficients, obtained by solving the quadratic surface equation. The data is obtained by dividing the model into sub-regions according to preset division conditions. The 3D model data is further divided into planar region data, arc region data, and transition rounded corner region data according to the corresponding sub-regions, resulting in sub-region data. The sub-region data includes discrete point cloud data for each sub-region. A detection path is determined based on the sub-region data. Ultrasonic data is acquired from the disc ring component to be inspected according to the detection path, resulting in ultrasonic data. Determining the detection path based on the sub-region data includes: obtaining normal vector data based on the sub-region data and a preset normal calculation model. The preset normal calculation model includes: a planar region normal calculation model. Arc-shaped region normal calculation model The normal calculation model for the transition rounded corner area is obtained by inputting sub-region data into a preset normal calculation model to obtain normal vector data; among which... Let be the unit normal vector of the i-th detection point in the planar region. These are all coefficients of the plane equation fitted to the planar region. The plane equation fitted to the planar region is: ,in, 、 、 d1 is a constant term in the cylindrical coordinate system of the disk-ring component. Let be the unit normal vector of the i-th detection point in the arc-shaped region. 、 、 Let be the cylindrical coordinates of the i-th detection point in the arc-shaped region. 、 、 Cylindrical coordinates of the center of the arc-shaped region; through Obtain the step size data; where, Step size, For the maximum allowable step size, K represents the minimum curvature, and K is the curvature value of the current detection point. The minimum allowable step size is determined; coordinate data is obtained based on the normal vector data and the step size data; the geometric center of each sub-region is selected as the path starting point, and starting from the path starting point, the path is traversed along the tangent direction of the region contour. Generate the next path point ,in, For the (k+1)th path point, For the k-th path point, Let k be the step size corresponding to the k-th path point in the step size data. Let be the unit tangent direction vector at the k-th path point. ,in, Let be the unit normal vector at the k-th path point. The main extension direction vector of the region contour is defined, and the coordinate data includes all path points and their corresponding coordinates. Based on the coordinate data and preset robotic arm parameters, the detection path is determined. The ultrasonic data is preprocessed to obtain preprocessed data, including: through... Obtain DC data; among which, To remove DC data, For ultrasound data, The mean of the ultrasound data; through The peak amplitude of the signal is calculated; where, The peak amplitude of the signal. To remove DC data, The maximum value function is used; effective data is obtained based on the peak amplitude of the signal and a preset noise threshold; the mean of the peak amplitude is obtained based on the peak amplitude of the effective data; gain judgment is performed based on preset judgment conditions and the mean of the peak amplitude to obtain a judgment result; gain processing is performed on the de-DC data based on the judgment result to obtain preprocessed data; wherein, defect detection is performed on the disk ring component to be tested based on the preprocessed data to obtain defect detection data, including: based on Obtain the sound wave propagation time; according to The thickness of the water coupling layer is obtained; according to The defect depth is obtained; defect detection is performed based on the preprocessed data and the trained defect detection model to obtain defect data; defect detection data is obtained based on the defect depth and the defect data; wherein, For the sound wave propagation time, To determine the propagation time of sound waves in the water coupling layer in the preprocessed data, The propagation time of sound waves inside the disk ring component is used to preprocess the data. Where is the thickness of the water coupling layer, and L is the distance from the sensor probe to the surface of the disk ring component. H represents the thickness of the sensor probe's housing, and H represents the defect depth. The sound velocity of the disc ring material. The propagation time of sound waves within the disc ring component is determined by... We obtained, among which, The speed of sound in water; wherein, based on the defect detection data and the three-dimensional model data, coordinate mapping is performed to obtain defect distribution data, including: performing coordinate transformation based on the defect depth in the defect detection data to obtain defect coordinates; establishing a spatial rectangular coordinate system O-xyz with the center of the disc ring to be detected as the origin, and the circumferential angle of the current detection point is... The radial coordinate is r, combined with the defect depth H, through 、 、 Calculate the defect coordinates (X, Y, Z); perform coordinate mapping on the defect coordinates based on the three-dimensional model data to obtain defect distribution data.

4. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 2.

Images