A gas turbine blade robot spraying compensation control method, system, device and medium

Abstract

The application provides a gas turbine blade robot spraying compensation control method, system, equipment and medium, comprising the following steps: completing blade spraying according to an original spraying program, collecting blade surface visual data and film thickness instrument measured data, fusing the data to obtain a blade surface visual film thickness estimation field calibrated or corrected by measured data; obtaining local film thickness residual error according to local film thickness estimation value and target film thickness, determining a film thickness abnormal area; performing responsibility attribution on the abnormal area, determining a dynamic spraying band responsibility window participating in compensation; generating a compensation vector and a compensation version spraying program according to the compensation distribution proportion of the window; the application determines the film thickness abnormal area by using the visual film thickness estimation field and the film thickness residual error field after spraying is completed; further determines the compensation distribution proportion according to the adjacent spraying band lap joint relationship, generates a compensation patch acting on the original spraying program copy, and realizes local correction and compensation re-measurement judgment of the robot spraying program.

Description

Technical Field

[0001] This invention relates to the field of robotic automatic spraying technology for gas turbine blades, and in particular to a method, system, equipment, and medium for compensation control of robotic spraying of gas turbine blades. Background Technology

[0002] Gas turbine blades are complex curved surface parts, with intricate structures such as top edges, convex areas, concave areas, concave inner corners, and blade root transition zones. During robotic painting, even if the robot follows a pre-planned painting trajectory, the actual coating thickness is still affected by factors such as spray gun distance, spray gun attitude, trajectory speed, overlap of adjacent paint zones, spray gun start / stop response, local blade curvature, clamping errors, and paint atomization status. This can lead to abnormal film thicknesses in localized areas, such as thinner areas, exposed substrate, thicker areas, paint accumulation, or runs.

[0003] In the current process of robotic spraying of gas turbine blades, the common practice is to first generate the robot spraying trajectory through offline programming, manual teaching or pre-spraying simulation, and then the operator manually adjusts parameters such as trajectory speed, spray gun start and stop sequence, spray distance, spray gun attitude or local trajectory position based on the post-spray appearance, film thickness gauge discrete point measurement results or on-site experience. While these methods can improve coating quality to some extent, they still have the following shortcomings: First, there is no clear correspondence between the post-spraying detection results and the robot spraying program, making it difficult to determine which row of spraying, which segment of the robot trajectory, or which target points should be responsible for compensation in a certain area of ​​abnormal film thickness. Second, there is overlap between adjacent spraying bands, and local film thickness anomalies are often caused by both the central spraying band and adjacent spraying bands. Existing methods cannot determine the compensation allocation ratio between the central responsibility trajectory segment and the adjacent overlapping trajectory segments. Third, the compensation directions required for thinner and thicker areas are opposite. If relying on overall overspraying or overall underspraying, it is easy to introduce new problems such as local overthrow, local thinning, paint accumulation, sagging, or exposed substrate. Fourth, the program correction process relies on human experience and lacks local compensation patches that act on copies of the original spraying program, resulting in insufficient executability, verifiability, and traceability of the compensation process. Fifth, there is a lack of a retesting and judgment mechanism based on visual film thickness feedback after compensation, making it difficult to form a closed-loop control process for continuous optimization.

[0004] Therefore, how to establish a robot spraying compensation control method that integrates post-spray visual film thickness feedback with visual film thickness estimation field, film thickness residual field, film thickness anomaly responsibility attribution, dynamic spraying band responsibility window determination, central responsibility trajectory segment and adjacent superimposed trajectory segment determination, compensation allocation ratio determination, compensation vector generation and compensation patch writing is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, the present invention aims to provide a method, system, equipment, and medium for compensation control of robotic spraying of gas turbine blades. Compared with traditional discrete detection, manual parameter adjustment, lookup table compensation, and one-time models, the present invention can reduce the number of trial sprays and manual parameter adjustments, improve the consistency, traceability, program reusability, and batch production adaptability of robotic spraying quality for gas turbine blades, and provide an executable, verifiable, and iteratively updated technical path for closed-loop control of coating quality for complex curved surface blades.

[0006] The first objective of this invention is to provide a robotic spraying compensation control method for gas turbine blades; The technical solution provided by this invention is as follows: A method for compensating and controlling the spraying of gas turbine blades by robots includes the following steps: The gas turbine blades were sprayed according to the original spraying procedure; After the coating is completed, visual inspection data of the blade surface is collected, and actual measurement data of the film thickness gauge is obtained. The visual film thickness estimation field of the blade surface is obtained based on the visual inspection data of the blade surface, the measured data of the film thickness gauge, and the visual film thickness estimation model. The local film thickness estimates in the visual film thickness estimation field are compared with the target film thickness to obtain the film thickness residuals of each local evaluation region, and the film thickness abnormal regions are determined based on the film thickness residuals. Based on the location, shape, residual direction, residual amplitude of the abnormal film thickness area, and the coverage relationship between the abnormal film thickness area and the sprayed strip, the responsibility for the abnormal film thickness area is assigned, and the responsibility window of the dynamic sprayed strip participating in the compensation is determined. A compensation vector is generated based on the compensation allocation ratio of the responsibility window of the dynamic spraying zone; A safety check is performed based on the compensation vector, and a compensation version of the spraying program is generated.

[0007] Preferably, the method for constructing the visual membrane thickness estimation model is as follows: Using the film thickness calibration sample database, film thickness gauge measurement points, and blade surface geometric correction information, the visual film thickness estimation model is constructed, wherein the visual film thickness estimation model can be expressed as a visual film thickness estimation function: ; in, This represents the local visual membrane thickness estimate for the i-th evaluation region; θ represents the feature vector formed by visual features and geometric correction features; F represents the estimation function in the visual film thickness estimation model; θ represents the model parameters determined by the film thickness calibration sample database and / or measured film thickness points and can be updated with each batch.

[0008] Preferably, the step of comparing the local film thickness estimates in the visual film thickness estimation field with the target film thickness to obtain the film thickness residuals for each local evaluation region is as follows: The local film thickness estimate in the visual film thickness estimation field is compared with the target film thickness value to obtain the film thickness residual: ; in, This represents the residual film thickness in the i-th local evaluation region. This represents the target film thickness value for the i-th local evaluation region.

[0009] Preferably, determining the abnormal film thickness region based on the film thickness residual specifically includes: When the residual film thickness is less than a preset negative threshold, the region corresponding to the residual film thickness is judged to be a thinner region. When the residual film thickness is greater than a preset positive threshold, the region corresponding to the residual film thickness is judged to be a region that is too thick. The abnormal film thickness region includes: the thinner region and the thicker region.

[0010] Preferably, before attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the coating strip, and determining the responsibility window for the dynamic coating strip participating in compensation, the method further includes: The sprayed surface of the gas turbine blade is parametrically unfolded into a two-dimensional evaluation region; The two-dimensional evaluation area is used to express the correspondence between the blade surface film thickness evaluation area and the robot spraying trajectory.

[0011] Preferably, the step of attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the coating strip, and determining the dynamic coating strip responsibility window for compensation, specifically involves: Based on the location, shape, residual direction, residual amplitude, and coverage relationship between the film thickness anomaly region and the sprayed strip in the two-dimensional evaluation region, the film thickness anomaly responsibility mode is determined. The film thickness anomaly region A is obtained according to the aforementioned film thickness anomaly responsibility mode; The responsibility window W(A) of the dynamic spraying zone is constructed with the abnormal film thickness region A as the center.

[0012] Preferably, the compensation allocation ratio specifically includes: The compensation allocation ratio is determined based on one or more of the following factors: overlap area between the film thickness anomaly region A and each spray band within the dynamic spray band responsibility window W(A); spray width coverage ratio; residual centroid distance; distance relationship; film thickness residual distribution; and / or visual film thickness estimation confidence level; as well as local deposition contribution calibrated by the spray band contribution test. And the compensation allocation ratio satisfy: .

[0013] Preferably, generating the compensation vector based on the compensation allocation ratio of the responsibility window in the dynamic spraying process specifically includes: Based on the direction of the film thickness residual, the magnitude of the film thickness residual, the film thickness anomaly responsibility mode, and the compensation allocation ratio, a compensation vector is generated that acts on one or more responsibility trajectory segments.

[0014] Preferably, before performing safety verification based on the compensation vector and generating the compensation version spraying program, the method further includes: Based on the location of the abnormal film thickness area within the spraying zone, the corresponding original trajectory target point or local sub-interval between adjacent target points is determined, and compensation is applied only to the local target point or the local sub-interval.

[0015] Preferably, it further includes: Using the original trajectory target point as a reference, a compensation amount is superimposed on the position and / or attitude of the original trajectory target point to generate a compensated target point. : ; in, , , This represents the three-dimensional position offset of the original trajectory target point in the preset coordinate system; , , The value represents the amount of rotation of the spray gun attitude; T represents the transformation operation of position offset and / or attitude rotation of the original trajectory target point; the preset coordinate system includes the robot base coordinate system, workpiece coordinate system, tool coordinate system or blade local surface coordinate system.

[0016] Preferably, the step of performing safety verification based on the compensation vector and generating a compensation version spraying program specifically includes: Based on the film thickness anomaly area number, film thickness anomaly responsibility mode, spray surface unit number, dynamic spraying zone responsibility window, responsibility trajectory segment number, local target point or local sub-interval, compensation allocation ratio, and local compensation parameters, a compensation patch is generated that applies to the original spraying program copy. After writing the compensation patch to a copy of the original paint program, a compensated version of the paint program is generated.

[0017] The second objective of this invention is to provide a robotic spraying compensation control system for gas turbine blades; The technical solution provided by this invention is as follows: A robotic spraying compensation control system for gas turbine blades includes: an initial spraying module, a data acquisition module, a film thickness estimation field acquisition module, an abnormal region determination module, a window determination module, a compensation vector module, and a spraying program generation module. The original spraying module is used to spray the gas turbine blades according to the original spraying program; The data acquisition module is used to collect visual inspection data of the blade surface and obtain measured data from the film thickness gauge after the coating is completed. The film thickness estimation field acquisition module is used to acquire the visual film thickness estimation field of the blade surface based on the visual inspection data of the blade surface, the measured data of the film thickness gauge and the visual film thickness estimation model. The abnormal region determination module is used to compare the local film thickness estimate in the visual film thickness estimation field with the target film thickness to obtain the film thickness residual of each local evaluation region, and determine the film thickness abnormal region based on the film thickness residual. The window determination module is used to assign responsibility for the abnormal film thickness area based on the location, shape, residual direction, residual amplitude, and coverage relationship between the abnormal film thickness area and the sprayed strip, and to determine the dynamic sprayed strip responsibility window that participates in the compensation. The compensation vector module is used to generate a compensation vector based on the compensation allocation ratio of the responsibility window of the dynamic spraying band. The spraying program generation module is used to perform safety verification based on the compensation vector and generate a compensated version of the spraying program.

[0018] The third objective of this invention is to provide an electronic device; The technical solution provided by this invention is as follows: An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the steps of any one of the gas turbine blade robot spraying compensation control methods.

[0019] A fourth objective of this invention is to provide a computer-readable storage medium; The technical solution provided by this invention is as follows: A computer-readable storage medium for storing a computer program for causing a computer to execute the steps of any one of the gas turbine blade robot spraying compensation control methods.

[0020] Compared with existing technologies, the present invention provides a robotic spraying compensation control method for gas turbine blades, comprising the following steps: spraying gas turbine blades according to the original spraying program; after spraying, acquiring visual inspection data of the blade surface and obtaining measured data from a film thickness gauge; obtaining a visual film thickness estimation field of the blade surface based on the visual inspection data, the measured data from the film thickness gauge, and a visual film thickness estimation model; comparing the local film thickness estimates in the visual film thickness estimation field with the target film thickness to obtain the film thickness residuals of each local evaluation area, and determining film thickness anomaly areas based on the film thickness residuals; and determining the film thickness anomaly areas based on the location, shape, residual direction, residual amplitude, and coverage relationship between the film thickness anomaly areas and the sprayed coating. The process involves attributing responsibility for the abnormal film thickness areas and determining the responsibility window of the dynamic spraying band participating in compensation; generating a compensation vector based on the compensation allocation ratio of the dynamic spraying band responsibility window; performing safety verification based on the compensation vector and generating a compensated version of the spraying program; this application does not simply perform pre-spray path planning, visual positioning calibration, or virtual thickness optimization, but rather, after spraying, uses the visual film thickness estimation field and film thickness residual field to determine the abnormal film thickness areas, and maps the abnormal areas to the spraying band, the central responsibility trajectory segment, and adjacent superimposed trajectory segments; further, it determines the compensation allocation ratio based on the overlap relationship of adjacent spraying bands, generates a compensation patch acting on the original spraying program copy, and realizes local correction and post-compensation retest judgment of the robot spraying program.

[0021] The present invention also provides a gas turbine blade robot spraying compensation control system. Since this system and the gas turbine blade robot spraying compensation control method solve the same technical problem and belong to the same technical concept, they should have the same beneficial effects, and will not be described in detail here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart of a robotic spraying compensation control method for gas turbine blades provided in this application embodiment; Figure 2A flowchart illustrating another method for compensating for robotic spraying of gas turbine blades provided in this application embodiment; Figure 3 A schematic diagram illustrating the parameterized unfolding of the blade spraying surface into a spraying strip and the construction of a dynamic spraying strip responsibility window provided in an embodiment of this application; Figure 4 A schematic diagram of a gas turbine blade robot spraying compensation control system provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] like Figures 1 to 2 As shown in the figure, an embodiment of the present invention provides a robotic spraying compensation control method for gas turbine blades, comprising the following steps: S1. Spray the gas turbine blades according to the original spraying procedure; S2. After the coating is completed, collect visual inspection data of the blade surface and obtain the measured data of the film thickness gauge; S3. Obtain the visual film thickness estimation field of the blade surface based on the visual inspection data of the blade surface, the measured data of the film thickness gauge, and the visual film thickness estimation model; S4. Compare the local film thickness estimates in the visual film thickness estimation field with the target film thickness to obtain the film thickness residuals of each local evaluation region, and determine the film thickness abnormal region based on the film thickness residuals; S5. Based on the location, shape, residual direction, residual amplitude of the abnormal film thickness area and the coverage relationship between the abnormal film thickness area and the sprayed strip, assign responsibility for the abnormal film thickness area and determine the responsibility window of the dynamic sprayed strip participating in the compensation. S6. Generate a compensation vector based on the compensation allocation ratio of the responsibility window of the dynamic spraying zone; S7. Perform a safety check based on the compensation vector and generate a compensation version spraying program.

[0026] In step S1, the robot sprays the gas turbine blades according to the original spraying program. The original spraying program includes multiple spraying surface units, each corresponding to the sprayable surface of the blade at a certain working angle. When executing a spraying surface unit, the robot completes the processes of approaching, initiating spraying, effective spraying, moving out and stopping spraying, and working position rotation according to a preset trajectory. Preferably, the spray gun is turned on outside the effective spraying area of ​​the blade, enters the effective spraying area of ​​the blade after passing through the initiation and stabilization section; after completing the spraying surface unit, the robot first moves out of the effective spraying area of ​​the blade, and then turns off the spray gun outside the effective spraying area of ​​the blade.

[0027] In steps S2 and S3, after the coating is completed, the vision inspection system collects visual inspection data of the blade surface and uses a thickness gauge to obtain measured film thickness data of the blade surface. Based on the film thickness calibration sample database, the film thickness gauge's measured data, and the blade surface geometric correction information, the system establishes, corrects, or calls a visual film thickness estimation model, and uses this model to estimate the film thickness of the visual inspection data, obtaining the visual film thickness estimation field of the blade surface. This visual film thickness estimation field is not the actual dry film thickness directly measured by the camera, but rather a film thickness estimation result based on visual features, film thickness gauge measured data, calibration relationships, the sample database, and geometric corrections.

[0028] In step S4, the local film thickness estimates in the visual film thickness estimation field are compared with the target film thickness to obtain the film thickness residuals of each local evaluation region, and the film thickness residual field is formed by the film thickness residuals of multiple local evaluation regions.

[0029] In step S5, based on the location, shape, residual direction, residual amplitude, and coverage relationship between the abnormal film thickness area and the sprayed strip, the responsibility for the abnormal film thickness is attributed, and the responsibility window of the dynamic sprayed strip participating in the compensation is determined. When the abnormal film thickness area is mainly located within the k-th row of the sprayed strip, the trajectory segment corresponding to the k-th row of the sprayed strip is... The central responsibility trajectory segment is determined; when the area with abnormal film thickness is affected by the overlap of adjacent sprayed strips, the (k-1)th row trajectory segment that has a spray width overlap relationship with the kth row of sprayed strips will be designated as the central responsibility trajectory segment. and / or the trajectory segment in row k+1 The trajectory segments are identified as adjacent superimposed segments. The responsibility window for the dynamic spraying band can be a single line, double line, three lines, or multiple lines, with three consecutive lines of spraying band compensation being a preferred implementation.

[0030] In step S6, compensation vectors are generated based on the film thickness residual direction, film thickness residual magnitude, film thickness anomaly responsibility mode, and compensation allocation ratio, acting on one or more responsibility trajectory segments. The compensation vectors may include one or more of the following: local velocity correction, spray distance correction, spray gun attitude correction, spray gun start / stop timing correction, local trajectory offset, and subsequent pass allocation. If the spraying equipment supports programmed adjustment, it may also include flow rate correction and / or pressure correction. For thicker areas, primary reduction compensation is applied to the central responsibility trajectory segment, and adjacent band reduction compensation is applied to adjacent superimposed trajectory segments to weaken local deposition superposition caused by continuous spray band overlap. For thinner areas, primary augmentation compensation is applied to the central responsibility trajectory segment, and auxiliary augmentation compensation is applied to adjacent superimposed trajectory segments based on the coverage of adjacent spray bands to compensate for insufficient local coverage.

[0031] In step S7, before generating the compensated version of the robot painting program, a safety check is performed on the compensation vector or compensation patch. The safety check includes one or more of the following: visual film thickness estimation reliability judgment, process parameter boundary judgment, robot target point reachability judgment, robot motion interference judgment, spray gun attitude continuity judgment, and post-compensation predicted film thickness judgment. When the safety check passes, the system generates a compensation patch based on the compensation vector, applies it to the original painting program copy, and writes the compensation patch to the original painting program copy, generating the compensated version of the robot painting program. When the safety check fails, the system does not automatically write the compensated version of the robot painting program, but instead generates a draft compensation program, risk warning, or manual confirmation request. After the robot executes the compensated version of the robot painting program, visual inspection data of the blade surface is collected again, the visual film thickness estimation field and film thickness residual field are regenerated, and the changes in film thickness residual before and after compensation are compared. When the film thickness residual after compensation falls within the allowable range, the compensation is deemed effective and the compensation result is recorded; when there is still a thin or thick film thickness after compensation, the system regenerates a compensation suggestion or proceeds to the manual confirmation process.

[0032] The safety verification criteria are shown in Table 1: Table 1. Criteria for Safety Verification of Compensation Procedures

[0033] Preferably, the method for constructing the visual membrane thickness estimation model is as follows: Using the film thickness calibration sample database, film thickness gauge measurement points, and blade surface geometric correction information, the visual film thickness estimation model is constructed, wherein the visual film thickness estimation model can be expressed as a visual film thickness estimation function: ; in, This represents the local visual membrane thickness estimate for the i-th evaluation region; θ represents the feature vector formed by visual features and geometric correction features; F represents the estimation function in the visual film thickness estimation model; θ represents the model parameters determined by the film thickness calibration sample database and / or measured film thickness points and can be updated with each batch.

[0034] In practical applications, the surface of a gas turbine blade is divided into several local evaluation regions or surface micro-elements, denoted as Si. For the i-th local evaluation region, the visual inspection system extracts image features, surface geometric features, and detection condition correction features to form a feature vector. Image features include one or more of the following: brightness, color difference, grayscale gradient, multi-band reflection intensity, and features after specular suppression; surface geometric features include one or more of the following: surface normal angle, local curvature, viewing angle correction parameters, and illumination angle correction parameters.

[0035] The system utilizes a database of film thickness calibration samples, actual measurement points from film thickness gauges, and geometric correction information for blade surfaces to establish or update a visual film thickness estimation model. In one embodiment, the visual film thickness estimation model can be expressed as a visual film thickness estimation function: ; in, This represents the local visual membrane thickness estimate for the i-th evaluation region; The eigenvectors represent the visual features and geometrically corrected features; F represents the estimation function in the visual film thickness estimation model; θ represents the model parameters determined by the film thickness calibration sample database and / or measured film thickness points and can be updated batch by batch. The visual film thickness estimates of multiple local evaluation regions are combined to form the visual film thickness estimation field. This embodiment establishes a visual film thickness estimation model using a film thickness calibration sample database, blade surface geometric correction information, and / or a small number of measured film thickness points. This model is then used to transform the post-spraying visual inspection results into a visual film thickness estimation field. The local film thickness estimates in this field are then compared with the target film thickness to obtain the film thickness residual and the film thickness residual field. Therefore, post-spray film thickness quality evaluation no longer relies solely on manual visual judgment or discrete point measurements by a film thickness gauge. Instead, it generates continuous or semi-continuous film thickness feedback information for the blade surface area, providing a calculable data foundation for subsequent robotic spraying program compensation.

[0036] In an embodiment of a visual film thickness estimation model and a calibration generation method for a visual film thickness estimation field, a film thickness calibration sample database is established, as shown in the table below. The film thickness calibration sample database is not simply a single sample containing five fixed film thickness regions, but rather a data set composed of multiple film thickness calibration samples, multiple known film thickness regions, different film thickness grades, different blade regions, different lighting and camera acquisition conditions, measured film thickness points, and compensated re-measurement records. The sample film thickness range in the database can be set around the target film thickness, or it can be expanded to more dense film thickness grades according to the coating system, blade type, and process tolerance. For example, multiple gradients can be set in the range of 30μm to 70μm, or further coverage can be provided for more samples below, close to, and above the target film thickness. 30μm, 40μm, 50μm, 60μm, and 70μm are merely exemplary calibration grades and do not constitute a limitation on the number of calibration samples, film thickness grades, or database size. The system acquires calibration sample images under identical or recordable light source, camera distance, exposure, and polarization conditions. It extracts features such as brightness, color difference, grayscale gradient, multi-band reflection intensity, post-suppression specular features, surface normal angle, and curvature to establish or update a visual film thickness estimation model. Subsequently, the surface angle is corrected based on the blade detection results, and the model parameters can be calibrated using actual film thickness gauge measurements, compensated re-measurements, or high-reliability historical batch records.

[0037] Table 2. Composition and Application of the Film Thickness Calibration Sample Database

[0038] Preferably, the step of comparing the local film thickness estimates in the visual film thickness estimation field with the target film thickness to obtain the film thickness residuals for each local evaluation region is as follows: The local film thickness estimate in the visual film thickness estimation field is compared with the target film thickness value to obtain the film thickness residual: ; in, This represents the residual film thickness in the i-th local evaluation region. This represents the target film thickness value for the i-th local evaluation region.

[0039] In practical applications, the visual membrane thickness estimate is compared with the target membrane thickness value to obtain the membrane thickness residual: ; in, This represents the residual film thickness in the i-th local evaluation region. This represents the target film thickness value for the i-th local evaluation region. When the film thickness residual... When it is less than the preset negative threshold, it is related to the residual thickness of the film. The corresponding area is judged to be a thinner region; when the film thickness residual... When it exceeds a preset positive threshold, it is related to the residual thickness of the film. The corresponding area is identified as a relatively thick area.

[0040] Preferably, before attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the coating strip, and determining the responsibility window for the dynamic coating strip participating in compensation, the method further includes: The sprayed surface of the gas turbine blade is parametrically unfolded into a two-dimensional evaluation region; The two-dimensional evaluation area is used to express the correspondence between the blade surface film thickness evaluation area and the robot spraying trajectory.

[0041] In practical applications, the sprayed surface of the gas turbine blade is parametrically unfolded into a two-dimensional evaluation region, such as... Figure 2 As shown in the figure, when the film thickness anomaly region is located near the k-th row of the spraying strip, the central responsibility trajectory segment corresponding to the k-th row of the spraying strip, and the adjacent superimposed trajectory segments corresponding to the (k-1)-th and / or k+1-th row of the spraying strip, are illustrated. The process of determining the compensation allocation ratio based on one or more of the following: overlap area, spray coverage ratio, residual centroid distance, film thickness residual distribution, and / or visual film thickness estimation confidence level, as well as local deposition contribution calibrated by the spraying strip contribution test. The two-dimensional evaluation region does not represent that the blade is actually a planar structure, but rather is used to express the correspondence between the film thickness evaluation region on the blade surface and the robot spraying trajectory. The system divides the two-dimensional evaluation region into several spraying strips along the robot spraying trajectory arrangement direction, with each spraying strip corresponding to a trajectory segment or several continuous trajectory sub-segments in the robot spraying program.

[0042] Preferably, the step of attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the coating strip, and determining the dynamic coating strip responsibility window for compensation, specifically involves: Based on the location, shape, residual direction, residual amplitude, and coverage relationship between the film thickness anomaly region and the sprayed strip in the two-dimensional evaluation region, the film thickness anomaly responsibility mode is determined. The film thickness anomaly region A is obtained according to the aforementioned film thickness anomaly responsibility mode; The responsibility window W(A) of the dynamic spraying zone is constructed with the abnormal film thickness region A as the center.

[0043] In practical applications, the responsibility for film thickness anomalies is attributed based on the location, shape, residual direction, residual amplitude, and coverage relationship between the anomaly area and the sprayed strip, and the responsibility window for the dynamic sprayed strip involved in compensation is determined. When the anomaly area is mainly located within the k-th row of the sprayed strip, the trajectory segment corresponding to the k-th row of the sprayed strip is... The central responsibility trajectory segment is determined; when the area with abnormal film thickness is affected by the overlap of adjacent sprayed strips, the (k-1)th row trajectory segment that has a spray width overlap relationship with the kth row of sprayed strips will be designated as the central responsibility trajectory segment. and / or the trajectory segment in row k+1 The adjacent superimposed trajectory segments are identified. The dynamic spray coating responsibility window can be a single row, double row, three rows, or multiple rows, with three consecutive rows of spray coating compensation being a preferred implementation. This embodiment establishes a film thickness anomaly responsibility attribution mechanism based on film thickness residual topology and spray coating coverage relationship. By parameterizing and unfolding the gas turbine blade spray surface into a two-dimensional evaluation region, and combining the location, shape, residual direction, residual amplitude, and coverage relationship between the film thickness anomaly region and the spray coating, it is possible to determine whether the anomaly belongs to the single spray coating dominant type, the adjacent spray coating overlapping type, the boundary insufficient coverage type, or the local surface accumulation type. Thus, the thin, thick, paint accumulation, or sagging risk areas found after spraying are reverse-located to the corresponding central responsibility trajectory segment, adjacent superimposed trajectory segment, and local target point sub-interval.

[0044] Specifically, for film thickness anomaly region A, its film thickness anomaly responsibility mode is first determined based on the region's location, shape, residual direction, residual amplitude, and coverage relationship with the sprayed strips within the two-dimensional evaluation area. Responsibility modes include one or more of the following: single sprayed strip dominant type, adjacent sprayed strip overlapping type, insufficient boundary coverage type, and local curved surface accumulation type.

[0045] A dynamic spray band responsibility window W(A) is constructed centered on the film thickness anomaly region A. When the film thickness anomaly region is mainly located within a single spray band, the dynamic spray band responsibility window W(A) can include one spray band; when the film thickness anomaly region crosses adjacent spray bands or is affected by spray overlap, the dynamic spray band responsibility window W(A) can include two, three, or more adjacent spray bands. For a film thickness anomaly region located near the k-th row of spray bands and affected by three consecutive rows of spray bands, the dynamic spray band responsibility window W(A) can include the (k-1)-th, k-th, and (k+1)-th rows of spray bands, where the k-th row of spray bands corresponds to the central responsibility trajectory segment. The spraying strips in rows k-1 and k+1 correspond to adjacent superimposed trajectory segments. and This embodiment proposes a dynamic spray zone responsibility window and compensation allocation method. When the film thickness anomaly area is mainly located within a single spray zone, the responsibility window can be a single row; when the film thickness anomaly area crosses adjacent spray zones or is affected by spray overlap, the responsibility window can be expanded to two, three, or more rows. The system determines the compensation allocation ratio of each trajectory segment within the responsibility window based on one or more of the following: overlap area, spray coverage ratio, residual centroid distance, film thickness residual distribution and / or visual film thickness estimation confidence level, and local deposition contribution calibrated by the spray zone contribution test. This avoids simply attributing local film thickness anomalies to a single trajectory segment and improves the accuracy of spray compensation for complex curved blade surfaces.

[0046] Preferably, the compensation allocation ratio specifically includes: The compensation allocation ratio is determined based on one or more of the following factors: overlap area between the film thickness anomaly region A and each spray band within the dynamic spray band responsibility window W(A); spray width coverage ratio; residual centroid distance; distance relationship; film thickness residual distribution; and / or visual film thickness estimation confidence level; as well as local deposition contribution calibrated by the spray band contribution test. And the compensation allocation ratio satisfy: .

[0047] In practical applications, the compensation allocation ratio is determined based on one or more of the following factors: the overlap area between the abnormal film thickness region A and each spray band within the dynamic spray band responsibility window W(A); the spray width coverage ratio; the distance between the residual centroids; the distance relationship; the film thickness residual distribution; and / or the confidence level of the visual film thickness estimate; as well as the local deposition contribution calibrated by the spray band contribution test. ,satisfy: ; If the average residual thickness of the abnormal film thickness region A is The target for correcting the total film thickness in this region can then be expressed as: ; Among them, when When the value is positive, it corresponds to a thicker region, and C represents a negative reduction compensation target; when... When the value is negative, it corresponds to a thinner region, and C is the target for positive addition compensation.

[0048] The film thickness correction target undertaken by each participating trajectory segment within the responsibility window of the dynamic spraying zone can be expressed as: ; in, This indicates the target thickness correction for the j-th trajectory segment. This indicates the compensation allocation ratio corresponding to the trajectory segment.

[0049] In a preferred embodiment, when the abnormal film thickness area is mainly located within the k-th row of the spray band and is affected by the overlap of the (k-1)-th and (k+1)-th rows of the spray band, a three-row responsibility window can be constructed, using the following example proportions: ; The above ratios are for illustrative purposes only. Actual compensation ratios can be adjusted based on factors such as spray width, overlap of the spray band, residual film thickness distribution, residual centroid position, visual estimation confidence level, and local surface features.

[0050] Preferably, before performing safety verification based on the compensation vector and generating the compensation version spraying program, the method further includes: Based on the location of the abnormal film thickness area within the spraying zone, the corresponding original trajectory target point or local sub-interval between adjacent target points is determined, and compensation is applied only to the local target point or the local sub-interval.

[0051] In practical applications, when the abnormal film thickness area corresponds only to a local position in a certain responsibility trajectory segment, the system does not uniformly compensate the entire trajectory segment. Instead, it determines the corresponding original trajectory target point or local sub-interval between adjacent target points based on the position of the abnormal film thickness area within the spraying zone, and applies compensation only to the local target point or local sub-interval.

[0052] The film thickness correction target undertaken by each trajectory segment can be further converted into local compensation parameters in the robot spraying program. Local compensation parameters include one or more of the following: trajectory speed correction, spray distance correction, local trajectory offset, spray gun attitude correction, and spray gun start-stop timing correction; if the spraying equipment supports programmed adjustment, it may also include flow rate correction and / or pressure correction.

[0053] For areas with excessively thick paint, the preferred methods for reducing coverage are to increase the local trajectory speed, appropriately increase the spray distance, slightly move the trajectory away from the area with excessive paint accumulation, fine-tune the spray gun posture, and reduce the programmable flow rate or pressure. For areas with excessively thin paint, the preferred methods for increasing coverage are to decrease the local trajectory speed, appropriately decrease the spray distance, move the trajectory closer to the area with insufficient coverage, fine-tune the spray gun posture, and increase the programmable flow rate or pressure. Spray gun start-stop timing correction is preferably used for adjusting the starting and ending boundaries of the spray surface unit, rather than for frequent on / off control of arbitrary points in the middle of the blade. This invention can simultaneously handle both thin and thick areas. For thin areas, the system uses a method of primarily increasing coverage in the central responsibility trajectory segment and supplementing with additional coverage in adjacent overlapping trajectory segments to compensate for insufficient local coverage. For thick areas, the system uses a method of primarily decreasing coverage in the central responsibility trajectory segment and reducing coverage in adjacent overlapping trajectory segments to weaken the local deposition caused by the overlap of continuous spraying bands. This reduces the risks of secondary thickening, secondary thinning, paint accumulation, sagging, or exposed substrate caused by overall overspraying or underspraying.

[0054] Preferably, it further includes: Using the original trajectory target point as a reference, a compensation amount is superimposed on the position and / or attitude of the original trajectory target point to generate a compensated target point. : ; in, , , This represents the three-dimensional position offset of the original trajectory target point in the preset coordinate system; , , The value represents the amount of rotation of the spray gun attitude; T represents the transformation operation of position offset and / or attitude rotation of the original trajectory target point; the preset coordinate system includes the robot base coordinate system, workpiece coordinate system, tool coordinate system or blade local surface coordinate system.

[0055] In practical applications, for the original trajectory target points that require compensation Using the original trajectory target point as a reference, compensation is superimposed on its position and / or attitude to generate a compensated target point. : ; in, , , This represents the three-dimensional position offset of the original trajectory target point in the preset coordinate system. , , The value represents the amount of rotation of the spray gun's attitude, and T represents the transformation operation of position offset and / or attitude rotation on the original trajectory target point. The preset coordinate system includes the robot base coordinate system, workpiece coordinate system, tool coordinate system, or blade local surface coordinate system.

[0056] When the abnormal film thickness region corresponds only to a local sub-interval between adjacent target points, compensation target points can be generated only for the target points at both ends of the local sub-interval or the interpolated target points in the sub-interval, and the trajectory target points that do not participate in the compensation will keep their original program parameters unchanged.

[0057] Preferably, the step of performing safety verification based on the compensation vector and generating a compensation version spraying program specifically includes: Based on the film thickness anomaly area number, film thickness anomaly responsibility mode, spray surface unit number, dynamic spraying zone responsibility window, responsibility trajectory segment number, local target point or local sub-interval, compensation allocation ratio, and local compensation parameters, a compensation patch is generated that applies to the original spraying program copy. After writing the compensation patch to a copy of the original paint program, a compensated version of the paint program is generated.

[0058] In practical applications, compensation patches are generated based on the film thickness anomaly area number, film thickness anomaly responsibility mode, spray surface unit number, dynamic spraying zone responsibility window, responsibility trajectory segment number, local target point or local sub-interval, compensation allocation ratio, and local compensation parameters. These patches are applied to a copy of the original spraying program. The compensation patches describe the local program objects that need correction and their corresponding compensation amounts, rather than regenerating the entire robot spraying path.

[0059] The compensation patch includes one or more of the following: film thickness anomaly area number, spray surface unit number, responsibility window number, responsibility trajectory segment number, local target point or local sub-interval, speed correction, spray gun start / stop timing correction, spray distance correction, local trajectory offset, spray gun attitude correction, safety verification result, and / or retest result. If the spraying equipment supports programmed adjustment, it may also include flow rate correction and / or pressure correction. After writing the compensation patch into a copy of the original spraying program, a compensated version of the robot spraying program is generated. The compensated version of the robot spraying program maintains the overall movement sequence and spray surface unit sequence of the original spraying program, only correcting the local target points, local sub-intervals, or local parameters corresponding to the film thickness anomaly area. This invention does not regenerate the entire robot spraying path, nor does it simply adjust the overall spraying parameters. Instead, it generates a local compensation patch on a copy of the original spraying program and only corrects the local target points, local sub-intervals, trajectory speed, spray distance, spray gun attitude, spray gun start / stop timing, and / or local trajectory position corresponding to the film thickness anomaly area. For trajectory segments and target points not involved in compensation, the original spraying procedure parameters remain unchanged. This method reduces the scope of program modifications, decreases the verification difficulty caused by replanning the entire path, and facilitates version management, rollback, traceability, and on-site implementation of the compensation program.

[0060] This invention incorporates a safety verification process before generating the compensated version of the robot spraying program. By assessing the reliability of visual film thickness estimation, process parameter boundaries, robot target point reachability, motion interference, spray gun posture continuity, and the predicted film thickness after compensation, the risks of miscompensation, overcompensation, abnormal robot motion, and exceeding process parameter limits can be reduced.

[0061] This invention re-acquires visual inspection data and / or measured data from a film thickness gauge on the blade surface after the compensation procedure is executed. It then regenerates the visual film thickness estimation field and film thickness residual field using a visual film thickness estimation model. The compensation effect is judged by the change in film thickness residual before and after compensation. This forms a closed-loop process of "post-spray visual film thickness feedback—local compensation procedure generation—compensation execution—retesting and judgment," improving the verifiability and continuous optimization capability of robotic spraying compensation control.

[0062] The present invention will be further described below with reference to specific embodiments. It should be understood that the following embodiments are only used to illustrate the technical concept and implementation of the present invention, and are not intended to limit the scope of protection of the present invention. For different types of gas turbine blades, different robot brands, different spraying process parameters, and different coating materials, those skilled in the art can adjust the film thickness threshold, the number of sprayed strips, the compensation allocation ratio, the compensation parameters, and the robot program format without departing from the technical concept of the present invention.

[0063] 1. The object to be sprayed and the original spraying procedure Taking a certain type of gas turbine blade as an example, the target film thickness is set to 50μm. The robot's original spraying program includes multiple spraying surface units, each corresponding to the sprayable surface of the blade at a certain station angle. Each spraying surface unit includes an approach section, a spraying start section, an effective spraying section, a removal and stopping spraying section, and a station rotation section.

[0064] During the initial spraying procedure, the robot sprays the blades according to a pre-planned spraying trajectory. The spray gun is preferably activated outside the effective spraying area of ​​the blade, and after passing through the initial stabilization phase, it enters the effective spraying area. After completing the spraying of the current surface unit, the robot first moves out of the effective spraying area and then closes the spray gun outside the effective spraying area. Subsequently, the workstation or blade fixture rotates to the next spraying angle, and the robot continues to execute the next spraying surface unit.

[0065] 2. Compensation Implementation Example for the Thinner Top Edge Area of ​​P01 After spraying, the vision inspection system acquires image data of the blade surface and, in conjunction with the film thickness calibration sample database, surface geometry correction information, and film thickness gauge measured data, establishes or calls upon a visual film thickness estimation model calibrated or corrected by the measured data to generate a visual film thickness estimation field. The system compares the local film thickness estimates in the visual film thickness estimation field with the target film thickness to obtain the film thickness residual and the film thickness residual field.

[0066] In this embodiment, the estimated visual film thickness of the top edge region of P01 is 38 μm, the target film thickness is 50 μm, and the film thickness residual is:

[0067] Since the residual thickness is less than the preset negative threshold, the system judges P01 as a thin region.

[0068] The system maps the position of P01 in the visual film thickness estimation field to a two-dimensional evaluation region and determines that it is mainly located within the top edge spraying zone. Since P01 is located in the blade boundary region, there is no complete adjacent spraying zone on one side of it. The system then assigns the first line trajectory segment corresponding to the top edge spraying zone to the top edge spraying zone. The central responsibility trajectory segment is determined, and based on the overlap of the spray width between P01 and the second row of spraying strips, it is determined whether the second row trajectory segment should be included. As adjacent superimposed trajectory segments.

[0069] When the thinness of P01 is mainly caused by insufficient coverage of the top edge, the system... Apply the main acceleration compensation. If the first line of the trajectory segment If the system includes P11, P12, P13, P14, and P15, and the thinner region of P01 mainly corresponds to a local location between P13 and P14, then the system only applies compensation to the local sub-intervals of P13, P14, or P13-P14, rather than the entire region. Unified compensation.

[0070] In one implementation, the system can reduce the local trajectory velocity in the P13-P14 sub-interval, shift the trajectory towards the top edge, appropriately reduce the spray distance, or fine-tune the spray gun attitude to improve the effective deposition in that area. If the system determines that the second row of sprayed material has a certain auxiliary covering effect on the P01 area, it can then... Apply small auxiliary compensation to boundary target points or local sub-intervals close to P01. Trajectory points and trajectory sub-intervals not involved in compensation retain their original program parameters.

[0071] 3. Compensation Implementation Example for the Thickened Area at the Concave Inner Corner of P08 In another embodiment, the visual film thickness estimate for the inner corner region of the concave surface of P08 is 72 μm, the target film thickness is 50 μm, and the film thickness residual is:

[0072] Since the residual thickness of the film is greater than the preset positive threshold, the system judges P08 as an area that is too thick.

[0073] The system maps the position of P08 in the visual film thickness estimation field to the two-dimensional evaluation area and determines that it is mainly located within the 8th row of the spraying strip, while also being affected by the continuous overlap of the 7th, 8th, and 9th rows of the spraying strip. The system maps the trajectory segment of the 8th row... The 7th line of the trajectory segment is designated as the central responsibility trajectory segment. and the 9th line of trajectory segment It was determined to be an adjacent superimposed trajectory segment.

[0074] The system determines the compensation allocation ratio for each trajectory segment based on the overlap area, spray coverage ratio, distance relationship, or film thickness residual distribution between the thicker area (P08) and the sprayed bands in rows 7, 8, and 9. For example, the system can set: To undertake a 20% reduction in film thickness; To undertake a 60% reduction in film thickness; The target is to achieve a 20% reduction in film thickness. The 20%, 60%, and 20% figures mentioned above are merely example ratios; the actual ratios can be adjusted based on factors such as the overlap of the sprayed strip, the width of the spray pattern, the distribution of residual film thickness, and the characteristics of local curved surfaces.

[0075] If the trajectory segment in line 8 Including P81, P82, P83, P84, and P85, and given that the thicker region of P08 mainly corresponds to a local sub-interval between P83 and P84, the system only applies the main reduction compensation to the local sub-intervals of P83, P84, or P83-P84, and generates the compensation target point. and This reduction compensation can be achieved by increasing the local trajectory speed, moving the trajectory slightly away from the concave inner angle, appropriately increasing the spray distance, or fine-tuning the spray gun attitude.

[0076] For adjacent overlapping trajectory segments and The system does not uniformly reduce the amount of material applied to the entire trajectory segment. Instead, it applies a small amount of adjacent band reduction compensation only to boundary target points or local sub-intervals near the P08 area to weaken the local deposition superposition caused by the overlap of continuous spraying bands. Trajectory points not near P08 retain their original program parameters.

[0077] 4. Compensation Patch Generation and Program Writing The system generates a compensation patch that applies to the original coating program copy based on the film thickness anomaly area number, spray surface unit number, center responsibility trajectory segment, adjacent superimposed trajectory segment, local target point, local sub-interval, compensation allocation ratio, and compensation parameters corresponding to P01 or P08.

[0078] The compensation patch may include one or more of the following: spray surface unit number, responsibility trajectory segment number, local target point or local sub-interval, speed correction, spray distance correction, local trajectory offset, spray gun attitude correction, and spray gun start / stop timing correction. The system writes the compensation patch into a copy of the original spraying program to generate a compensated version of the robot spraying program. The compensated version of the robot spraying program maintains the overall movement sequence and spray surface unit sequence of the original spraying program, and only corrects the local target points, local sub-intervals, or local parameters corresponding to areas with abnormal film thickness.

[0079] 5. Judgment of retest after compensation After the robot executes the compensated version of the robot spraying program, the system again collects visual inspection data of the blade surface and obtains remeasurement data from the film thickness gauge. It then regenerates the visual film thickness estimation field and film thickness residual field corrected by the film thickness gauge remeasurement data. The system combines the film thickness gauge remeasurement data with the changes in film thickness residuals before and after compensation to determine the compensation effect.

[0080] For the thinner region at the top edge of P01, if the estimated visual film thickness after compensation is increased from 38 μm to approximately 48 μm, the residual film thickness after compensation is approximately... The system judges the compensation to be effective at 2 μm. For the thicker area at the inner corner of the concave surface of P08, if the estimated visual film thickness decreases from 72 μm to approximately 55 μm after compensation, the residual film thickness after compensation is approximately +5 μm, and the system's judgment of the degree of thickness deviation is significantly improved.

[0081] When the residual film thickness after compensation falls within the allowable range, the system records the valid compensation result. If the film thickness is still too thin or too thick after compensation, the system can regenerate compensation suggestions or transfer the process to manual confirmation. Through the above retesting process, a closed-loop control process is formed, from visual film thickness feedback after spraying to local compensation procedure correction, and then to retesting and judgment after compensation.

[0082] like Figure 4 As shown, this embodiment of the invention provides a robotic spraying compensation control system for gas turbine blades, including: an original spraying module, a data acquisition module, a film thickness estimation field acquisition module, an abnormal area determination module, a window determination module, a compensation vector module, and a spraying program generation module; The original spraying module is used to spray the gas turbine blades according to the original spraying program; The data acquisition module is used to collect visual inspection data of the blade surface and obtain measured data from the film thickness gauge after the coating is completed. The film thickness estimation field acquisition module is used to acquire the visual film thickness estimation field of the blade surface based on the visual inspection data of the blade surface, the measured data of the film thickness gauge and the visual film thickness estimation model. The abnormal region determination module is used to compare the local film thickness estimate in the visual film thickness estimation field with the target film thickness to obtain the film thickness residual of each local evaluation region, and determine the film thickness abnormal region based on the film thickness residual. The window determination module is used to assign responsibility for the abnormal film thickness area based on the location, shape, residual direction, residual amplitude, and coverage relationship between the abnormal film thickness area and the sprayed strip, and to determine the dynamic sprayed strip responsibility window that participates in the compensation. The compensation vector module is used to generate a compensation vector based on the compensation allocation ratio of the responsibility window of the dynamic spraying band. The spraying program generation module is used to perform safety verification based on the compensation vector and generate a compensated version of the spraying program.

[0083] In practical applications, the gas turbine blade robot spraying compensation control system includes an original spraying module, a data acquisition module, a film thickness estimation field acquisition module, an abnormal area determination module, a window determination module, a compensation vector module, and a spraying program generation module. The data acquisition module is connected to both the original spraying module and the film thickness estimation field acquisition module. The abnormal area determination module is connected to both the film thickness estimation field acquisition module and the window determination module. The compensation vector module is connected to both the window determination module and the spraying program generation module. After spraying, the original spraying module, data acquisition module, film thickness estimation field acquisition module, abnormal area determination module, window determination module, compensation vector module, and spraying program generation module determine abnormal film thickness areas using the visual film thickness estimation field and film thickness residual field, and map these abnormal areas to the spraying strip, the central responsibility trajectory segment, and adjacent superimposed trajectory segments. Furthermore, based on the overlap relationship of adjacent spraying strips, the compensation allocation ratio is determined, and a compensation patch is generated that acts on the original spraying program copy, achieving local correction and post-compensation retesting of the robot's spraying program.

[0084] Furthermore, embodiments of this application also disclose an electronic device, Figure 5 This is a structural diagram of an electronic device according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0085] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this application. The electronic device 20 specifically includes: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the gas turbine blade robot spraying compensation control method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment can specifically be an electronic computer.

[0086] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a gas turbine blade robot spraying compensation control channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0087] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0088] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the data 223 in the memory 22. It can be Windows Server, Netware, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the gas turbine blade robot spraying compensation control method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the gas turbine blade robot spraying compensation control device from external devices, as well as data collected by its own input / output interface 25.

[0089] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0090] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed robotic spraying compensation control method for gas turbine blades. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0091] It should be understood that the use of terms such as "method," "apparatus," "unit," and / or "module" in this application is merely to distinguish one method of different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0092] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "a," and / or "the" are not specifically singular and may include the plural. Generally, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements. An element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, product, or apparatus that includes the element.

[0093] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0094] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0095] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A robotic spraying compensation control method for gas turbine blades, characterized in that, Includes the following steps: The gas turbine blades were sprayed according to the original spraying procedure; After the coating is completed, visual inspection data of the blade surface is collected, and actual measurement data of the film thickness gauge is obtained. Based on the visual inspection data of the blade surface, the measured data of the film thickness gauge, and the visual film thickness estimation model, the visual film thickness estimation field of the blade surface is obtained. The local film thickness estimates in the visual film thickness estimation field are compared with the target film thickness to obtain the film thickness residuals of each local evaluation region, and the film thickness abnormal regions are determined based on the film thickness residuals. Based on the location, shape, residual direction, residual amplitude of the abnormal film thickness area, and the coverage relationship between the abnormal film thickness area and the sprayed strip, the responsibility for the abnormal film thickness area is assigned, and the responsibility window of the dynamic sprayed strip participating in the compensation is determined. A compensation vector is generated based on the compensation allocation ratio of the responsibility window of the dynamic spraying zone; A safety check is performed based on the compensation vector, and a compensation version of the spraying program is generated.

2. The robotic spraying compensation control method for gas turbine blades according to claim 1, characterized in that, The method for constructing the visual membrane thickness estimation model is as follows: Using the film thickness calibration sample database, film thickness gauge measurement points, and blade surface geometric correction information, the visual film thickness estimation model is constructed, wherein the visual film thickness estimation model can be expressed as a visual film thickness estimation function: ； in, This represents the local visual membrane thickness estimate for the i-th evaluation region; θ represents the feature vector formed by visual features and geometric correction features; F represents the estimation function in the visual film thickness estimation model; θ represents the model parameters determined by the film thickness calibration sample database and / or measured film thickness points and can be updated with each batch.

3. The robotic spraying compensation control method for gas turbine blades according to claim 2, characterized in that, The local film thickness estimate in the visual film thickness estimation field is compared with the target film thickness to obtain the film thickness residual for each local evaluation region. The local film thickness estimate in the visual film thickness estimation field is compared with the target film thickness value to obtain the film thickness residual: ; in, This represents the residual film thickness in the i-th local evaluation region. This represents the target film thickness value for the i-th local evaluation region.

4. The robotic spraying compensation control method for gas turbine blades according to claim 3, characterized in that, The film thickness anomaly region is determined based on the film thickness residual, specifically including: When the residual film thickness is less than a preset negative threshold, the region corresponding to the residual film thickness is judged to be a thinner region. When the residual film thickness is greater than a preset positive threshold, the region corresponding to the residual film thickness is judged to be a region that is too thick. The abnormal film thickness region includes: the thinner region and the thicker region.

5. The robotic spraying compensation control method for gas turbine blades according to claim 1, characterized in that, Before attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the sprayed coating strip, and determining the responsibility window for the dynamic sprayed coating strip participating in compensation, the process further includes: The sprayed surface of the gas turbine blade is parametrically unfolded into a two-dimensional evaluation region; The two-dimensional evaluation area is used to express the correspondence between the blade surface film thickness evaluation area and the robot spraying trajectory.

6. The robotic spraying compensation control method for gas turbine blades according to claim 5, characterized in that, The process involves attributing responsibility for the abnormal film thickness region based on its location, shape, residual direction, residual amplitude, and coverage relationship with the sprayed coating strip, and determining the responsibility window for the dynamic sprayed coating strip involved in compensation. Specifically: Based on the location, shape, residual direction, residual amplitude, and coverage relationship between the film thickness anomaly region and the sprayed strip in the two-dimensional evaluation region, the film thickness anomaly responsibility mode is determined. The abnormal film thickness region is denoted as film thickness abnormality region A; The responsibility window W(A) of the dynamic spraying zone is constructed with the abnormal film thickness region A as the center.

7. The robotic spraying compensation control method for gas turbine blades according to claim 6, characterized in that, The compensation allocation ratio specifically includes: The compensation allocation ratio is determined based on one or more of the following factors: overlap area between the film thickness anomaly region A and each spray band within the dynamic spray band responsibility window W(A); spray width coverage ratio; residual centroid distance; distance relationship; film thickness residual distribution; and / or visual film thickness estimation confidence level; as well as local deposition contribution calibrated by the spray band contribution test. And the compensation allocation ratio satisfy: 。 8. The robotic spraying compensation control method for gas turbine blades according to claim 7, characterized in that, The step of generating a compensation vector based on the compensation allocation ratio of the dynamic spraying zone responsibility window specifically includes: Based on the direction of the film thickness residual, the magnitude of the film thickness residual, the film thickness anomaly responsibility mode, and the compensation allocation ratio, a compensation vector is generated that acts on one or more responsibility trajectory segments.

9. The robotic spraying compensation control method for gas turbine blades according to claim 8, characterized in that, Before performing safety verification based on the compensation vector and generating the compensated version of the spraying program, the process also includes: Based on the location of the abnormal film thickness area within the spraying zone, the corresponding original trajectory target point or local sub-interval between adjacent target points is determined, and compensation is applied only to the local target point or the local sub-interval.

10. The robotic spraying compensation control method for gas turbine blades according to claim 9, characterized in that, Also includes: Using the original trajectory target point as a reference, a compensation amount is superimposed on the position and / or attitude of the original trajectory target point to generate a compensated target point. : ； in, , , This represents the three-dimensional position offset of the original trajectory target point in the preset coordinate system; , , The value represents the amount of rotation of the spray gun attitude; T represents the transformation operation of position offset and / or attitude rotation of the original trajectory target point; the preset coordinate system includes the robot base coordinate system, workpiece coordinate system, tool coordinate system or blade local surface coordinate system.

11. The robotic spraying compensation control method for gas turbine blades according to claim 10, characterized in that, The step of performing safety verification based on the compensation vector and generating a compensated version of the spraying program specifically includes: Based on the film thickness anomaly area number, film thickness anomaly responsibility mode, spray surface unit number, dynamic spraying zone responsibility window, responsibility trajectory segment number, local target point or local sub-interval, compensation allocation ratio, and local compensation parameters, a compensation patch is generated that applies to the original spraying program copy. After writing the compensation patch to a copy of the original paint program, a compensated version of the paint program is generated.

12. A robotic spraying compensation control system for gas turbine blades, characterized in that, include: The system includes a raw spraying module, a data acquisition module, a film thickness estimation field acquisition module, an anomaly area determination module, a window determination module, a compensation vector module, and a spraying program generation module. The original spraying module is used to spray the gas turbine blades according to the original spraying program; The data acquisition module is used to collect visual inspection data of the blade surface and obtain measured data from the film thickness gauge after the coating is completed. The film thickness estimation field acquisition module is used to acquire the visual film thickness estimation field of the blade surface based on the visual inspection data of the blade surface, the measured data of the film thickness gauge and the visual film thickness estimation model. The abnormal region determination module is used to compare the local film thickness estimate in the visual film thickness estimation field with the target film thickness to obtain the film thickness residual of each local evaluation region, and determine the film thickness abnormal region based on the film thickness residual. The window determination module is used to assign responsibility for the abnormal film thickness area based on the location, shape, residual direction, residual amplitude, and coverage relationship between the abnormal film thickness area and the sprayed strip, and to determine the dynamic sprayed strip responsibility window that participates in the compensation. The compensation vector module is used to generate a compensation vector based on the compensation allocation ratio of the responsibility window of the dynamic spraying band. The spraying program generation module is used to perform safety verification based on the compensation vector and generate a compensated version of the spraying program.

13. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The storage medium is used to store a computer program, which is used to cause a computer to perform the method according to any one of claims 1-11.

Images