A method for controlling electroplating on a titanium alloy surface

Abstract

The application belongs to the technical field of electroplating process optimization, and specifically discloses a titanium alloy surface electroplating control method, which comprises the following steps: dynamically generating a hanger posture configuration scheme based on real-time collected three-dimensional profile data of a workpiece; synchronously collecting bubble distribution images and electroplating liquid flow field data, and generating a bubble-flow field coupling feature set through multimodal fusion; real-time linkage adjusting the workpiece rotation speed and swing amplitude according to the coupling feature set; collecting plating layer thickness, edge integrity and surface defect data after electroplating is completed, and combining workpiece position information to form a multi-source plating layer data set; comprehensively judging the hanger layout adjustment according to historical data and real-time data, and starting hanger spacing dynamic reconstruction optimization when adjustment is needed. The application realizes multi-parameter collaborative control and closed-loop quality optimization of the electroplating process, significantly improves the uniformity and integrity of the titanium alloy workpiece plating layer, and effectively suppresses the generation of bubble-related defects.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of electroplating process optimization, and particularly relates to a titanium alloy surface electroplating control method. BACKGROUND

[0002] Titanium alloy is widely used in the fields of aerospace, marine engineering, medical devices, high-end equipment manufacturing, etc. due to its high strength, low density, excellent corrosion resistance and high-temperature mechanical properties. However, the surface of titanium alloy also has some inherent defects, so electroplating is often used to improve it. The control of the electroplating process directly affects the quality of the final product.

[0003] Prior art 1, such as the electroplating equipment and electroplating method disclosed in Chinese patent application No. 201810487847.5, uses multiple electrodes to form an independently controllable electric field on the wafer surface. By applying an independently adjustable electric field strength in different areas, especially in the wafer notch, the total amount of electricity received by the notch area during electroplating is directly reduced, thereby precisely controlling the electroplating height of the area. This method improves the accuracy and reliability of control compared to the traditional method of adjusting wafer speed, and also improves the electroplating efficiency.

[0004] Prior art 2, such as the chip electroplating system and chip electroplating control method disclosed in Chinese patent application No. 202011615619.5, uses a pneumatic cylinder to drive a push plate to move in the electroplating solution to adjust the liquid level, and controls the chip clamping device to move cooperatively with the push plate to form a counter pressure on the surface of the chip when it is immersed in the electroplating solution, thereby enhancing the expulsion of attached bubbles and reducing air residues on the chip surface during electroplating, thereby improving the copper pit defect of electroplating.

[0005] The above two prior art technical solutions still have the following shortcomings in the control of the electroplating process: 1. Prior art 1 focuses on adjusting the electroplating height of the wafer notch area by independently controlling the electric field with multiple electrodes, but its control basis is mainly the pre-set electric field distribution, which is a feedforward control. It lacks real-time monitoring and feedback adjustment of the workpiece surface state and bubbles, making it difficult to achieve the expected adjustment effect.

[0006] 2. Prior art 1 improves the deposition uniformity at the wafer notch by adjusting the electric field, but its focus is limited to the electroplating height of the notch, and it does not fully consider the uniformity of the coating thickness of the workpieces at different positions on the same hanger.

[0007] 3. Prior art 2 uses a mechanical method to generate a counter pressure to expel bubbles by the push plate and clamping, but this method is relatively rough and cannot accurately locate the bubble distribution characteristics and size, making it difficult to guarantee the effectiveness of the elimination method, and its bubble elimination effect and adaptability may be limited.

[0008] 4. Both existing patents focus on a single control dimension, such as electric field and current, and lack multi-parameter collaborative optimization. The single control dimension cannot comprehensively improve the electroplating quality. Summary of the Invention

[0009] In view of this, in order to solve the above problems, a method for controlling electroplating on titanium alloy surfaces is proposed.

[0010] The objective of this invention can be achieved through the following technical solution: This invention provides a method for controlling electroplating on the surface of titanium alloys, the method comprising: S1, dynamically generating a fixture posture configuration scheme that matches the geometric features of the workpiece based on the collected three-dimensional contour data of the titanium alloy workpiece.

[0011] S2. Immerse the workpiece in the electroplating solution according to the fixture posture configuration scheme, and simultaneously collect bubble distribution images and electroplating solution flow field data on the workpiece surface during the electroplating process. Generate a bubble-flow field coupling feature set through multimodal data fusion.

[0012] S3. Based on the bubble-flow field coupling feature set, adjust the rotation speed and oscillation amplitude of the workpiece in real time.

[0013] S4. When electroplating is completed, simultaneously collect coating thickness distribution data, edge integrity image data, and surface defect distribution data, and associate them with the spatial coordinates of the workpiece on the hanger to form a multi-source coating dataset for the current workpiece.

[0014] S5. Based on the historical workpiece coating data sequence of the fixture and the multi-source coating dataset of the current workpiece, determine the need for fixture layout adjustment.

[0015] S6. If it is determined that adjustment is needed, then start the dynamic reconstruction optimization of the hanger spacing and then control the spacing.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention realizes dynamic monitoring and feedback control of bubble behavior during electroplating by collecting bubble distribution images and electroplating liquid flow field data on the workpiece surface in real time and performing multimodal fusion analysis. This overcomes the shortcomings of traditional feedforward control methods in responding to real-time changes in working conditions and significantly improves the control accuracy and reliability of the electroplating process.

[0017] (2) Based on three-dimensional contour data, this invention identifies high-risk electroplating areas and generates matching fixture posture configuration schemes. Combined with simulation verification methods, it ensures that workpieces with different geometric features can obtain stable electrolyte coverage and current distribution, effectively improving the problem of coating uniformity among multiple workpieces on the same fixture.

[0018] (3) The application realizes accurate quantitative evaluation of bubble size, distribution and aggregation tendency by introducing bubble morphology feature extraction and sub-region division mechanism, and then implements targeted bubble elimination strategy by linkage adjustment of workpiece rotation speed and swing amplitude, overcoming the poor adaptability and extensive action of mechanical bubble elimination method.

[0019] (4) The application builds a multi-dimensional collaborative optimization system covering bubble behavior, flow field state and coating quality by comprehensively using flow field simulation, image processing, machine learning and other multi-source information fusion technologies, realizes the leap from single parameter control to multi-parameter coupled optimization in the electroplating process, and comprehensively improves the coating consistency and defect suppression capability.

[0020] (5) The application realizes intelligent judgment of hanger layout adjustment demand and dynamic optimization of spacing scheme by establishing a correlation analysis mechanism of historical coating data and real-time production data, forms a complete closed-loop quality control, and further significantly enhances the adaptability and continuous optimization capability of the electroplating process. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 It is a whole implementation flowchart of the electroplating of titanium alloy surface.

[0023] Figure 2 It is a hanger posture configuration scheme generation flowchart.

[0024] Figure 3 It is a whole schematic diagram of multi-modal data fusion process.

[0025] Figure 4 It is a schematic diagram of linkage adjustment of rotation speed and swing amplitude. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0027] Please refer to Figure 1As shown, the present application provides a titanium alloy surface electroplating control method, which comprises the following steps: S1, based on the collected three-dimensional profile data of the titanium alloy workpiece, dynamically generating a hanger posture configuration scheme matched with the geometric features of the workpiece.

[0028] S2, according to the hanger posture configuration scheme, carrying out workpiece electroplating liquid immersion, and synchronously collecting workpiece surface bubble distribution image and electroplating liquid flow field data in the electroplating process, and generating bubble-flow field coupling feature set through multi-modal data fusion.

[0029] S3, based on the bubble-flow field coupling feature set, real-time linkage adjusting the rotation speed and swing amplitude of the workpiece.

[0030] S4, when the electroplating is completed, synchronously collecting plating layer thickness distribution data, edge integrity image data and surface defect distribution data, and associating with the spatial position coordinates of the workpiece on the hanger, to form a multi-source plating layer data set of the current workpiece.

[0031] S5, comprehensively considering the historical workpiece plating layer data sequence of the hanger and the multi-source plating layer data set of the current workpiece, judging the need for hanger layout adjustment.

[0032] S6, if it is judged that adjustment is needed, then starting the dynamic reconstruction optimization of the hanger spacing and then controlling the spacing.

[0033] Understandably, the three-dimensional profile data in S1 step is collected by adopting the combination of laser three-dimensional scanner and structured light imaging system to obtain data including surface curvature distribution, edge contour feature and geometric size parameter, etc.

[0034] Specifically, please refer to Figure 2 As shown, the specific generation process of the hanger posture configuration scheme in S1 step is as follows: S11, obtaining the coordinate information and geometric feature parameters of each point on the workpiece surface, and the geometric feature parameters include curvature, surface area and concave-convex region distribution.

[0035] S12, constructing a three-dimensional model based on the obtained workpiece surface coordinate information and geometric feature parameters, and identifying high-risk electroplating areas.

[0036] Understandably, the high-risk electroplating area includes convex or concave area with absolute curvature value greater than a preset threshold, and complex structure area with surface area ratio exceeding a preset proportion.

[0037] Exemplarily, the preset absolute curvature value threshold is determined according to the material characteristics of the titanium alloy workpiece and the electroplating process requirements, and the value range is generally , and the preset surface area ratio threshold is 20%-30%. The complex structure region of the titanium alloy workpiece can be defined from the geometric complexity, feature quantity, and connection mode of the workpiece. If a region contains three or more different types of geometric features, such as a plane, a cylindrical surface, and a conical surface, and the transition radius between these features is less than a certain value, such as 0.5 mm, and the size tolerance of at least two features in the region is less than a certain range, such as ±0.05 mm, the region can be defined as a complex structure region. Alternatively, when a region contains interlaced and nested structures, and the number of interlaced or nested layers reaches three or more, it can also be determined as a complex structure region.

[0038] S13, generating an initial hanger posture configuration scheme based on the three-dimensional model, the high-risk electroplating region, and a preset hanger constraint condition.

[0039] Understandably, the hanger constraint condition includes the number of contact points between the hanger and the workpiece, the contact point load range, and the structure size limitation of the hanger itself. In the hanger constraint condition, the number of contact points between the hanger and the workpiece is determined according to the weight of the workpiece. Exemplarily, the number of contact points corresponding to each 1 kg of workpiece is not less than 2, and the contact points are uniformly distributed in the non-high-risk region. The contact point load range is 5-20 N, which avoids workpiece deformation caused by excessive load.

[0040] S14, verifying the electrolyte coverage rate and current density uniformity of the high-risk region in the initial scheme through fluid dynamics simulation.

[0041] Understandably, in the simulation verification step, the computational fluid dynamics method is used to simulate the flow state of the electrolyte, and the finite element analysis method is used to simulate the current distribution. The preset coverage rate standard is not less than 95%, and the current density uniformity standard is that the ratio of the maximum current density to the minimum current density is not more than 1.5. The above-mentioned methods all use existing technical means, and will not be described here.

[0042] Among them, the electrolyte coverage rate is quantified by calculating the percentage of the effective area of the high-risk region in contact with the electrolyte to the total area of the region. The current density uniformity is quantified by calculating the ratio of the standard deviation to the average value of the current density of each measuring point in the high-risk region, i.e. the coefficient of variation.

[0043] S15, when the verification result meets the preset threshold, outputting the initial hanger posture configuration scheme as the final scheme, otherwise adjusting the contact parameters between the hanger and the workpiece and re-verifying until a qualified hanger posture configuration scheme is obtained, the contact parameters including the contact point position and angle.

[0044] It should be noted that in the step of adjusting the contact point position and angle of the hanger and the workpiece, the contact points near the high-risk area are preferentially adjusted, so that the distance between the contact points and the high-risk area is not less than 5mm, and the adjustment angle of the hanger posture is not more than 10° each time, to ensure the stability of the adjustment process.

[0045] It should be noted that for the problem of uneven plating in the high-risk area of the titanium alloy workpiece with complex geometric features, the influence of the hanger posture on the electrolyte flow and current distribution is pre-evaluated and optimized in a virtual environment through three-dimensional modeling and simulation verification. The generated hanger configuration scheme can significantly improve the electrolyte coverage effect and current density uniformity in the high-risk area, reduce plating defects caused by workpiece geometric features from the source, and improve the stability of the electroplating process and the consistency of the plating quality.

[0046] Specifically, please refer to Figure 3 As shown in the S2 step, the specific process of the multi-modal data fusion includes: S21, acquiring bubble distribution images through multi-angle industrial cameras arranged around the electroplating tank, and pre-processing and binary conversion of the images.

[0047] Understandably, the pre-processing of the bubble distribution image includes but is not limited to denoising, contrast enhancement and brightness adjustment to improve the distinction between bubbles and background. The pre-processing and binary conversion both adopt existing mature technical means, which will not be described one by one here.

[0048] S22, based on the marker point constraint of bubble morphology prior, using watershed algorithm to segment the adherent bubbles, and extracting the morphological feature parameters of each independent bubble, including equivalent diameter, topography factor and three-dimensional space coordinates.

[0049] It should be noted that the adherent state is a state in which the edges of two or more bubbles overlap or contact.

[0050] Understandably, the marker point constraint based on the bubble morphology prior specifically includes: obtaining the potential bubble area through distance transformation, generating marker points combined with the circularity prior and size prior of the bubbles, and constraining the starting position of the watershed transformation.

[0051] Understandably, the watershed algorithm specifically includes: preliminarily extracting the bubble area through Otsu threshold segmentation, and performing distance transformation on the binary image to obtain a distance mapping graph.

[0052] Based on the circularity threshold and size range threshold set by the bubble morphology prior, the areas meeting the conditions are selected as marker points.

[0053] The marker points are input into the watershed algorithm as constraint conditions to complete the accurate segmentation of the bubbles.

[0054] The Otsu threshold segmentation described above is a prior art segmentation method, and the segmentation process will not be described in detail.

[0055] It should be noted that the threshold setting is based on a large amount of experimental data statistics and process requirements, and the shape feature difference between normal bubbles and abnormal bubbles is analyzed to determine the circularity threshold for distinguishing near-circular bubbles and deformed bubbles, and the size range threshold for filtering invalid bubble signals that are too large or too small.

[0056] Understandably, a high-precision optical imaging system such as a laser confocal microscope can be used to take a two-dimensional image of the bubbles in the sub-region, and an image segmentation algorithm such as threshold segmentation method, edge detection method, etc. can be used to extract the contour of each bubble, calculate the area S of each bubble contour, and calculate the equivalent diameter according to the equivalent diameter formula.

[0057] Understandably, the topography factor is quantified by circularity, and the circularity formula is , , wherein C represents the circularity, , wherein S represents the area of the bubble contour, , wherein L represents the perimeter of the bubble contour, and the value range of the circularity is 0-1, and when the circularity is 1, it is a standard circle. The smaller the circularity, the more irregular the bubble topography.

[0058] Understandably, three-dimensional scanning technology such as structured light three-dimensional scanner can be used to obtain the three-dimensional coordinates of each bubble in the sub-region.

[0059] S23, divide the electroplating liquid container into a plurality of unit sub-regions according to the grid size matching the minimum diameter of the bubbles.

[0060] Understandably, the setting of the grid size needs to meet the requirements that a single grid can completely accommodate the minimum bubble and avoid insufficient feature accuracy due to too large grid size. For example, for a container with a volume of 100L, a cubic grid with a side length of 5-10mm can be divided.

[0061] It should be noted that the grid size is set according to the volume of the electroplating liquid in the container and the bubble detection accuracy requirement, and the volume of a single unit grid is not more than 0.5% of the total volume of the container.

[0062] For example, if the surface area of the workpiece is small, such as a micro-precision part, the area is less than , and the average diameter of the bubbles is 0.1-1mm, it is generally recommended that the grid size be set to 5-10mm to ensure that each sub-region contains at least 3-5 bubbles, avoiding too high data contingency due to too small area. If the surface area of the workpiece is large, such as a large plate, the area is greater than and the average diameter of the bubbles is 1-5 mm, the grid size can be set to 20-50 mm, which can ensure the representativeness of the data while reducing the subsequent calculation amount.

[0063] S24, the binary image of each sub-region is spatially matched with the three-dimensional grid, and the volume proportion of each sub-region is calculated to obtain the bubble coverage.

[0064] S25, the particle image velocimetry technology is used to obtain the flow velocity vector field of the electroplating solution, and the flow velocity and flow direction of the position of each bubble are measured as the flow field parameters of each bubble.

[0065] S26, based on the extracted morphological feature parameters and flow field parameters of the bubbles, the real-time R value of each bubble is calculated, and the aggregation tendency index of each sub-region is calculated according to the R value, and the R value is the ratio of drag force to buoyancy.

[0066] S27, the bubble coverage, aggregation tendency index and flow field parameters are spatiotemporally aligned and then fused at the feature level by a feature fusion algorithm to generate a bubble-flow field coupling feature set.

[0067] It should be noted that single type sensor data cannot comprehensively reflect the complex bubble-flow field coupling state in the electroplating process. By fusing visual image and flow velocity field measurement data, a multi-dimensional feature representation system can be established to establish a quantitative correlation between bubble morphology distribution, motion characteristics and flow field parameters, provide real-time and comprehensive data basis for subsequent precise control of workpiece motion parameters, and thus realize active intervention and elimination of bubble behavior, and significantly improve the plating layer quality.

[0068] Further, the specific calculation process of the aggregation tendency index in S26 includes: 1) the distribution characteristics of the morphological feature parameters of each bubble in the sub-region are counted, the distribution characteristics are normalized, and the bubble dynamic instability index is obtained by dynamic weighted fusion based on the first fusion function according to the titanium alloy-electrolyte interface characteristics.

[0069] Specifically, the specific statistical process of the distribution characteristics includes: based on the equivalent diameter of each bubble, the coefficient of variation of the equivalent diameter of the bubbles in the sub-region is calculated, and the variance and skewness of the R value of all bubbles in the sub-region are calculated.

[0070] The topographic factor value is divided into several discrete intervals and the frequency is counted, and the distribution entropy value of the bubble topographic factor in the sub-region is calculated based on the frequency.

[0071] The dynamic weighted fusion strategy of the first fusion function specifically includes: B1, the composition, thickness and porosity of the surface oxide film of the titanium alloy sample under different pretreatment processes are determined by experiment.

[0072] It is understandable that the component measurement is usually used to accurately identify the type and content of relevant oxides in the oxide film by X-ray photoelectron spectroscopy or Auger electron spectroscopy, and the thickness measurement is performed by an ellipsometer or a scanning electron microscope cross-section observation. The porosity measurement is realized by image analysis method or gas adsorption method. The image analysis method and the gas adsorption method are prior art methods, and will not be described.

[0073] It should be noted that the characteristics of the oxide film on the surface of the titanium alloy directly affect the adhesion and uniformity of the subsequent electroplated layer, and this step provides experimental basis for selecting the optimal pretreatment process and controlling the quality of the oxide film.

[0074] B2. Under the same electroplating process, the initial nucleation rate of bubbles, the average residence time and the final porosity of the plated layer on the surface of the sample are collected synchronously.

[0075] It is understandable that the initial nucleation rate of bubbles is obtained by shooting the sample surface with a high-speed industrial camera and counting the number of newly generated bubbles per unit time. The average residence time is recorded by image tracking technology, which records the time from nucleation to separation of a single bubble, and the average value of multiple bubbles is taken. The final porosity of the plated layer is observed by metallographic microscope or indirectly reflected by measuring the corrosion current through salt water immersion test.

[0076] It is understandable that the initial nucleation rate of bubbles reflects the speed of bubble generation, the average residence time reflects the stability of bubble adsorption on the surface, and the porosity of the plated layer directly reflects the core index of the corrosion resistance of the electroplated product.

[0077] It should be added that if a large number of bubbles stay in the electroplating process, it will cause defects such as pinholes and bubbles in the plated layer. This step quantifies the relationship between bubble behavior and plated layer quality to provide direction for subsequent optimization of bubble control.

[0078] B3. Through causal correlation analysis based on partial least squares path model, a set of oxide film characteristic parameters with dominant influence on bubble behavior is identified.

[0079] It should be added that the partial least squares path model is an existing model. First, the oxide film characteristic parameters are set as exogenous latent variables, and the bubble behavior parameters are set as endogenous latent variables. The path coefficients of each oxide film parameter on bubble behavior are calculated by the model. The greater the absolute value of the path coefficient, the stronger the influence, and the dominant parameter set is determined by combining cross-validation.

[0080] It should be noted that this step realizes the focusing from multiple parameters to core parameters, and only a few dominant parameters need to be controlled in the subsequent step, so that the bubble behavior can be efficiently regulated and the complexity of process control can be reduced.

[0081] B4. Real-time collection of surface micro-time sequence images of the current workpiece, and extraction of oxide film characteristic parameter estimates by using a trained deep learning model.

[0082] Understandably, the deep learning model usually adopts a combined architecture of image segmentation and feature regression, such as a U-Net-based semantic segmentation model that first segments the oxide film area from the microscopic time-series image, and then extracts features such as texture and gray scale in the area through a convolutional neural network such as ResNet to output estimated values corresponding to the dominant parameters, such as porosity percentage and thickness value.

[0083] It should be noted that this step can realize real-time perception of the characteristics of the oxide film, which is the premise of subsequent dynamic adjustment of process parameters and early intervention of bubble defects, breaking the passive mode of traditional post-detection and batch rejection.

[0084] B5, calculate the expected detachment time of the bubble based on the bubble force balance mechanism, and obtain the adsorption stability deviation degree index combined with the actual average residence time.

[0085] Understandably, the actual average residence time of the bubble can be calculated by analyzing the time-series image, and the standardized residual between the expected detachment time and the actual average residence time can be calculated as the adsorption stability deviation degree index.

[0086] It should be noted that this step converts the bubble behavior from qualitative description to quantitative description, providing clear numerical basis for subsequent judgment of whether to adjust the process.

[0087] B6, the adsorption stability deviation degree index and the normalized value of the distribution characteristics are weighted and summed to obtain the final bubble dynamic instability index.

[0088] Understandably, when weighted and summed, the weights are determined by the analytic hierarchy process or actual process experience, such as the adsorption stability having a more direct impact on the plating layer defects, with the adsorption stability deviation degree index weight being 0.6 and the distribution characteristic normalized value weight being 0.4.

[0089] 2) Through time-series analysis of the fluctuation characteristics of the bubble coverage rate in the sub-region, obtain the bubble coverage instability index.

[0090] Understandably, the sliding window method and time domain analysis method can be used to extract the fluctuation characteristics, for example: set the window size to 10 time points, calculate the coverage rate variance, the maximum value of the coverage rate change rate and the fluctuation period in the sliding window. The coverage rate variance reflects the short-term fluctuation intensity, the maximum value of the coverage rate change rate reflects the coverage rate mutation degree, and the fluctuation period is extracted by Fourier transform, reflecting the periodic fluctuation rule of the coverage rate.

[0091] After normalizing the fluctuation characteristics, the bubble coverage instability index is obtained by weighted summation, and the weights can be set in combination with experience, for example, short-term fluctuations have a more direct impact on instantaneous aggregation. The weight of the short-term fluctuation variance is 0.5, the weight of the maximum value of the coverage rate change rate is 0.3, and the weight of the fluctuation period is 0.2. Short-term fluctuations have a more direct impact on instantaneous aggregation.

[0092] It should be noted that this step compensates for the shortcomings of static morphology analysis through the fluctuation characteristics in the time dimension, and can capture the dynamic change risk of bubble coverage, for example, the coverage rate of a sub-region increases from 10% to 40% in 1s, and the coverage instability index is close to 1, indicating that the region may have rapid bubble aggregation, and early intervention is required.

[0093] 3) Generate adsorption energy density field based on titanium alloy-electrolyte interface characteristic parameters.

[0094] Understandably, the titanium alloy-electrolyte interface characteristic parameters include the surface energy of the titanium alloy, the composition of the oxide film, the micro roughness, and the composition of the electrolyte.

[0095] Specifically, based on the composition of the oxide film, the micro roughness, and the composition of the electrolyte on the surface of the titanium alloy workpiece, an adsorption energy density field representing the adsorption strength distribution of bubbles at different surface locations is generated through molecular dynamics simulation or experimental calibration.

[0096] It should be noted that the adsorption energy density field is a key bridge connecting the physical characteristics of the interface and the behavior of the bubbles, for example, the roughness at the scratch on the titanium alloy surface is high, and the adsorption energy density is significantly higher than that in other areas, and bubbles are easy to aggregate here, so the instability index weight of this area needs to be focused on when the index is corrected.

[0097] 4) Interface correct the bubble dynamic instability index and bubble coverage instability index through the adsorption energy density field, input the corrected index and adsorption energy density field into the pre-trained physical information neural network, and output the final aggregation tendency index of the sub-region.

[0098] Understandably, the physical information neural network adopts a combined architecture of fully connected layers and physical constraint layers, the input layer is the modified double index and adsorption energy density field data, the hidden layer extracts features through the ReLU activation function, the physical constraint layer embeds the core physical laws of bubble aggregation, such as the higher the adsorption energy, the more the bubble aggregation probability and the adsorption time are positively correlated, and the output layer is the aggregation tendency index.

[0099] It should be added that this step incorporates the physical essence through interface modification, and integrates data-driven approaches with physical laws through PINN, solving the problem of traditional pure data models being detached from actual processes or pure physical models lacking accuracy. The final output index can directly guide the dynamic control of the electroplating production line. For example, adjusting the plating solution flow rate and optimizing the rack posture in high-risk sub-regions can reduce plating defects caused by bubble aggregation.

[0100] It should be added that, by integrating multi-dimensional information such as bubble morphology and distribution characteristics, temporal fluctuation patterns, and interfacial adsorption energy fields, and by introducing a physical information neural network for coupled analysis, a quantitative assessment model for bubble aggregation tendency that conforms to the physical laws of electrochemical interfaces was established. This model can accurately predict and intervene in bubble aggregation behavior, thereby effectively suppressing coating defects caused by bubble merging and adhesion.

[0101] Furthermore, the specific execution process of the correction includes: multiplying the bubble dynamic instability index of each sub-region by the average adsorption energy density of the corresponding region to obtain the bubble dynamic instability index after interface correction.

[0102] The bubble dynamic instability index of each sub-region is multiplied by the adsorption energy gradient of the corresponding region to obtain the bubble coverage instability index after interface correction.

[0103] Understandably, the bubble dynamic instability index is used to assess the unevenness of forces acting on bubbles and the instability of their motion trends. The bubble coverage instability index is used to assess the volatility and severity of bubble adhesion distribution on surfaces.

[0104] Specifically, please refer to Figure 4 As shown, the specific execution process of the linkage adjustment in step S3 is as follows: S31, calculate the overall bubble coverage rate, bubble coverage uniformity and bubble coverage concentration based on the bubble coverage rate of each sub-region, and form a bubble coverage feature vector.

[0105] Understandably, the overall bubble coverage rate is calculated using a weighted average method, which involves summing and quantifying the product of the bubble coverage rate of all sub-regions and the ratio of the area of ​​the corresponding sub-region to the total area of ​​the workpiece. The bubble coverage uniformity is quantified by the coefficient of variation method to determine the dispersion of the coverage rate of each sub-region. The bubble coverage concentration is determined by spatial clustering analysis, which uses the DBSCAN clustering algorithm to identify sub-regions with coverage rates higher than a threshold, such as 30%, that form continuous clusters. The concentration is calculated by multiplying the ratio of the total area of ​​the sub-regions within the cluster to the total area of ​​the workpiece by the ratio of the average coverage rate within the cluster to the overall bubble coverage rate. A larger value indicates that the bubbles are more concentrated in a local area.

[0106] It should be added that the single overall bubble coverage cannot fully reflect the spatial distribution characteristics of the bubbles on the workpiece surface, and the uniformity of the distribution needs to be evaluated by the coverage uniformity, and the local aggregation area is identified by the coverage concentration. Further, the multi-dimensional feature vector of the bubble spatial distribution form can be fully characterized, which provides accurate input basis for subsequent motion parameter adjustment, and realizes the differential and accurate regulation of different bubble distribution modes such as uniform distribution and local aggregation.

[0107] S32, extract the flow rate and flow direction parameters of each sub-region, form a flow field feature vector, and form a bubble aggregation feature vector based on the aggregation tendency index of each sub-region.

[0108] Understandably, the flow field parameters directly affect the migration and detachment of the bubbles, and low flow rate is easy to cause bubble residence, and chaotic flow direction is easy to cause local accumulation of bubbles, and the aggregation tendency index can early warn the potential aggregation risk, and the combination of the two can extend the process evaluation from the static status to the dynamic trend, which can significantly improve the forward-looking of the adjustment decision.

[0109] S33, according to the workpiece material thickness and electroplating process parameters, query the corresponding reference motion parameter group and corresponding feature tolerance range from the preset process knowledge base.

[0110] Understandably, the data in the process knowledge base can be constructed by a large number of experiments and combined with empirical data.

[0111] It should be added that for the three types of feature vectors of bubble coverage, flow field, and aggregation tendency, the allowed fluctuation interval is set, such as titanium alloy thickness 3mm, current density 2A / When the bubble coverage feature vector tolerance range is: overall coverage 15%-30%, uniformity ≥0.6, and concentration ≤0.5.

[0112] S34, when all feature vectors are within the corresponding tolerance range, the reference motion parameter group is used as the control output.

[0113] S35, otherwise, start the motion parameter adjustment mechanism and output the adjustment motion parameter category and adjustment proportion, and output after correcting the reference motion parameter based on the motion parameter category and adjustment proportion.

[0114] Further, the specific execution process of the motion parameter adjustment mechanism is as follows: F1, determine the adjustment motion parameter category according to the situation that the feature vector exceeds the tolerance range, the category includes rotation speed and swing amplitude.

[0115] It should be added that if any one of the following conditions is true: the bubble aggregation tendency index exceeds the upper limit of the tolerance range, the overall bubble coverage exceeds the upper limit of the tolerance range, or the flow field flow rate is lower than the lower limit of the tolerance range, then the adjustment parameter is determined as the rotation speed.

[0116] If any of the bubble coverage concentration, bubble coverage uniformity, or overall bubble coverage rate exceeds the upper limit of the corresponding tolerance range, it is determined that the adjustment parameter is the swing amplitude.

[0117] F2, if the rotation speed is determined to be adjusted, the output rotation speed adjustment ratio is calculated by a Sigmoid function based on the bubble aggregation tendency index, the degree of exceeding of the overall bubble coverage rate, and the degree of being lower than the flow field flow rate, which is quantified by the relative deviation value.

[0118] F3, if the swing amplitude is determined to be adjusted, the swing amplitude adjustment ratio is calculated by a Sigmoid function based on the degree of exceeding of the bubble coverage concentration, the bubble coverage uniformity, and the overall bubble coverage rate.

[0119] Understandably, the rotation speed mainly affects the fluid shear force and bubble detachment effect, and is suitable for processing macro-bubble problems caused by high aggregation tendency, excessive overall coverage, or insufficient flow field flow rate. The swing amplitude mainly changes the local flow state and contact frequency of the workpiece surface, and is suitable for improving the uniformity of bubble distribution and eliminating local concentrated areas. Its role is to establish a mapping relationship between multi-parameter abnormal states and the best control method, and to achieve smooth proportional adjustment through a Sigmoid function, avoiding the interference of parameter mutations on the electroplating process, and enabling precise and stable dynamic control for different bubble defect modes.

[0120] Specifically, in the S4 step, an X-ray fluorescence thickness gauge can be used to collect the plating layer thickness distribution data of the workpiece surface, the sampling point density is not less than 5 points per square centimeter, the thickness values of each sampling point are obtained, and the thickness coefficient of variation, i.e. the ratio of the standard deviation to the mean of the thickness data, is calculated. A high-resolution industrial camera with a resolution of not less than 2048x2048 is used to collect the image of the edge area of the workpiece, a Canny operator is used for edge detection to identify the edge integrity, and the edge defect length ratio, i.e. the ratio of the total length of the edge defects to the total length of the workpiece edge, is calculated. A laser scanning microscope with a scanning accuracy of not more than 1 micrometer is used to collect surface defect data, identify defect types such as pinholes, pitting, and peeling, and calculate the defect density, which is the ratio of the total number of defects in the defect density detection area to the detection area.

[0121] Specifically, in the S5 step, the hanging tool layout adjustment requirement judgment includes: S51, based on the thickness distribution data, the surface defect distribution data, and the edge integrity image data, the thickness coefficient of variation, the defect density, and the edge defect length ratio are calculated respectively as the characteristics of each defect.

[0122] S52, traverse the historical batch data, if the thickness variation coefficient or defect density of a batch of workpieces exceeds the preset multiple of the median of the historical data, eliminate the batch data, and record the remaining batches after elimination as effective historical batches.

[0123] Understandably, the preset multiple is usually set to 1.5 times, which can be adjusted according to the production stability.

[0124] S53, based on the statistics of the reference values of each defect feature of all effective historical batch workpieces, calculate the deviation rate of each defect feature of the current workpiece from its reference value and output the comprehensive defect degree after linear weighting.

[0125] Understandably, the weight can be determined by process experts, such as thickness variation coefficient weight 0.4, defect density weight 0.4, and edge defect proportion weight 0.2.

[0126] In one embodiment, the specific statistical process of the reference value of each defect feature includes: filtering the abnormal values of each defect feature for each group of data by quartile method, and calculating the arithmetic mean value of each defect feature for each filtered group of data to obtain the thickness variation coefficient reference, edge defect length proportion reference, and defect density reference.

[0127] If the effective batches of a certain type of feature data in the historical data sequence are less than 3, the industry standard value of the same type of workpiece under the same process condition is used as the initial reference, and the reference value is updated by the above steps after accumulating enough historical data.

[0128] It should be noted that after adding 3-5 batches of qualified workpiece coating data, the abnormal value filtering and average value calculation steps are re-executed, and the thickness variation coefficient reference, edge defect length proportion reference, and defect density reference are iteratively updated to make the reference value always reflect the stable state of the current process. When the process parameters such as electroplating current and electrolyte concentration are changed, the reference value is reset, and the coating data of the first qualified workpiece after the change is used as the starting point to re-accumulate historical data and calculate new reference.

[0129] S54, screen historical workpieces with production time within a preset time window as a reference set.

[0130] Understandably, the preset time window setting can determine the time window length according to the production rhythm, usually 7 days or 20 production batches, to ensure that the sample size of the reference set is sufficient, while avoiding too long time leading to too large production condition difference.

[0131] S55, when the comprehensive defect degree of the current workpiece exceeds the preset threshold, and the proportion of workpieces with defect degree exceeding the threshold in the reference set reaches the preset threshold, it is judged that the hanger layout needs to be adjusted, otherwise, it is judged that no adjustment is needed.

[0132] Understandably, the comprehensive defect degree preset threshold can be set based on historical qualified batch data, usually 0.3, that is, when the comprehensive defect degree is greater than 0.3, the current workpiece quality significantly deviates from the normal level, and the continuous over-standard proportion preset threshold can be set in combination with production stability, usually 30%, that is, referring to the set, when the proportion of batches with defect degree of 3 or more workpieces exceeding the standard is greater than or equal to 30%, it is defined as continuous over-standard.

[0133] It should be added that the double-threshold judgment avoids false adjustment, reduces unnecessary fixture adjustment, reduces downtime and labor cost, and also prevents missed adjustment, which can timely discover fixture layout problems and avoid scrap loss caused by continuous batch defects.

[0134] Specifically, the specific steps of starting the dynamic reconstruction optimization of the fixture spacing in the S6 step are as follows: S61, assigning a unique identifier to each fixture in the electroplating tank and recording its initial horizontal position.

[0135] S62, calculate the horizontal spacing between adjacent fixtures, and evaluate the correlation degree between each spacing value and the corresponding workpiece plating quality index through the Pearson correlation coefficient, and identify the fixture pairs with significant correlation between the spacing value and the quality index.

[0136] Understandably, the correlation coefficient has a value range of [-1, 1], the greater the absolute value, the stronger the linear correlation, and significant correlation is determined by performing a significance test, and setting the significance p value less than 0.05 as significant correlation, for example: if the correlation coefficient of the M01-M02 fixture pair spacing value and the corresponding workpiece thickness uniformity is -0.72, and the significance p value is 0.02, it means that the smaller the spacing, the worse the thickness uniformity, and the correlation is significant.

[0137] S63, based on the preset adjustment constraints of the horizontal spacing of the fixture, design multiple groups of horizontal spacing adjustment schemes, and through flow field and current density distribution simulation analysis, select the candidate scheme that meets the process requirements from the adjustment scheme.

[0138] It should be added that before designing the scheme, it also includes determining the quality defect concentrated area based on the plating quality data of the workpiece corresponding to the fixture pair, and judging whether the defect is caused by unreasonable fixture spacing.

[0139] Exemplarily, the plating quality data of the workpiece suspended by the significantly correlated fixture pair, such as thickness detection report and surface defect image, is analyzed, the grid division method is used to divide the workpiece surface into 10x10 grid units, the number of defects in each unit, such as pinhole and thickness deviation exceeding the standard, is counted, and the defect distribution is visualized through the heat map to determine the grid area of the defect concentration.

[0140] It should be noted that by analyzing the relevance of the hanger to the defect area, non-distance factors such as hanger contact corrosion, workpiece morphology, etc. are first ruled out, ensuring that subsequent distance optimization schemes are only designed for quality problems caused by flow field or electric field interference. This avoids ineffective distance adjustment operations and significantly improves optimization efficiency and scheme relevance.

[0141] It should also be noted that under the same batch, current, temperature, and plating solution, the defect distribution of the workpiece hung by the hanger with different distances can be selected. If the defect density of the defect concentration area increases by more than 30% when the distance is reduced from 120mm to 100mm, and the defect density decreases by more than 20% when the distance is adjusted to 140mm, it indicates that the defect is strongly related to the distance.

[0142] If the defect concentration area coincides with the flow field / current field area affected by the hanger distance, such as the flow field dead angle between the two hangers corresponding to the workpiece defect area, and the defect still changes with the distance after excluding other factors, it is determined that the defect is caused by unreasonable hanger distance.

[0143] Understandably, the adjustment constraints of the horizontal distance of the hanger include space constraints and process constraints. The space constraints are that the minimum distance from the inner wall of the electroplating tank to the edge hanger is greater than or equal to 50mm, and the minimum distance between adjacent hangers is greater than or equal to 80mm, to avoid hanger collision or excessive flow field turbulence. The process constraints are that the adjustment amplitude is less than or equal to ±20mm at a time to avoid sudden changes in the current field caused by large adjustments, which affect the quality of the workpieces of other hangers.

[0144] Specifically, the simulation analysis can simulate the electrolyte flow rate and update frequency between adjacent workpieces under different adjustment schemes through computational fluid dynamics, and simulate the current density distribution through finite element analysis, and select the scheme that meets the flow field uniformity greater than or equal to the preset threshold and the current density distribution deviation less than or equal to the preset deviation as the candidate scheme.

[0145] Understandably, the flow field uniformity threshold is determined by analyzing the flow rate distribution coefficient of variation in the flow field simulation data corresponding to the historical high-quality plating layer, ensuring sufficient electrolyte update and no dead zone. The current density distribution deviation threshold is set according to the correlation analysis of the finite element simulation results and the measured plating layer thickness, and is limited to the maximum relative deviation of the current density corresponding to the allowed thickness tolerance. Both types of thresholds need to meet the process specification requirements and verify their effectiveness through actual production.

[0146] S64, score the candidate schemes based on the comprehensive defect degree of the historical workpieces, and select the scheme with the highest score as the target adjustment scheme.

[0147] Exemplarily, the hanger pairs with a spacing value close to the candidate scheme are screened for the corresponding comprehensive defect degree, for example, the candidate scheme spacing is 120 mm, the matching historical spacing is in the range of 115-125 mm, and the average comprehensive defect degree of each candidate scheme group is calculated. The complement of the average comprehensive defect degree is multiplied by the set rating value such as 100 points to obtain the comprehensive score of each candidate scheme group. The scheme with the highest comprehensive score and no single indicator below 60 points is selected as the target adjustment scheme. The complement is the value obtained by subtracting the average comprehensive defect degree from 1.

[0148] S65, adjust the hanger position according to the target adjustment scheme, and verify and correct the spacing value after adjustment by iterative optimization until the plating quality of the same batch of multiple workpieces is qualified.

[0149] Understandably, after the first workpiece is electroplated according to the target adjustment scheme, if the comprehensive score does not reach the preset threshold, the target spacing is iteratively adjusted within the preset margin range and by the preset step size until the plating quality of the same batch of multiple workpieces is qualified.

[0150] It should be noted that the preset margin range is determined based on the adjustment accuracy of the hanger mechanical structure and the electroplating process tolerance, and is usually set to ±5%-10% of the target spacing value to ensure that the adjustment process is safely performed within the process allowable fluctuation range. The preset step size is comprehensively set according to the spacing adjustment accuracy requirement and production efficiency, and is usually 0.5-2 mm / step, which ensures adjustment accuracy and avoids excessive iteration affecting production rhythm.

[0151] It should be noted that the use of correlation analysis to identify key hanger pairs significantly related to quality defects can avoid the blindness of global adjustment. Through fluid and electric field simulation, candidate schemes that can significantly improve the uniformity of flow field and current distribution are pre-screened in a virtual environment, which can greatly reduce the trial and error cost. Combined with historical data scoring and production iterative verification, an optimized flow closed loop is formed to ensure that the spacing adjustment is not only based on theoretical prediction but also has practical feasibility, and finally the plating quality of the entire batch of workpieces is stably improved.

[0152] The above is only an example and description of the concept of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the concept of the present application or exceed the scope defined by the present application. They should belong to the protection scope of the present application.

Claims

1. A method for controlling electroplating of a titanium alloy surface, characterized by, The method comprises: S1, based on the collected titanium alloy workpiece three-dimensional profile data, dynamically generating a fixture posture configuration scheme matched with the geometric features of the workpiece; S2, according to the fixture posture configuration scheme, the workpiece is soaked in the electroplating solution, and the bubble distribution image and the electroplating solution flow field data are synchronously collected in the electroplating process, and the bubble-flow field coupling feature set is generated through multi-modal data fusion; S3, based on the bubble-flow field coupling feature set, the rotation speed and swing amplitude of the workpiece are adjusted in real time; S4, when the electroplating is completed, the plating layer thickness distribution data, edge integrity image data and surface defect distribution data are synchronously collected, and are associated with the spatial position coordinates of the workpiece on the fixture to form a multi-source plating layer data set of the current workpiece; S5, comprehensively considering the historical workpiece plating layer data sequence of the fixture and the multi-source plating layer data set of the current workpiece, the fixture layout adjustment requirement is judged; S6, if it is judged that adjustment is needed, the dynamic reconstruction optimization of the fixture spacing is started, and then the spacing control is performed.

2. The method for controlling electroplating on titanium alloy surfaces as described in claim 1, characterized in that: The specific generation process of the fixture posture configuration scheme is as follows: Obtain the coordinate information and geometric feature parameters of each point on the workpiece surface, the geometric feature parameters including curvature, surface area and concave-convex region distribution; Based on the obtained workpiece surface coordinate information and geometric feature parameters, a three-dimensional model is constructed, and a high-risk electroplating area is identified; Based on the three-dimensional model, the high-risk electroplating area and the preset fixture constraint condition, an initial fixture posture configuration scheme is generated; The initial fixture posture configuration scheme is verified by fluid dynamics simulation to verify the electrolyte coverage and current density uniformity in the high-risk area; When the verification result meets the preset threshold, the initial fixture posture configuration scheme is output as the final scheme, otherwise the contact parameters of the fixture and the workpiece are adjusted and reverified until a qualified fixture posture configuration scheme is obtained.

3. The method for controlling electroplating on titanium alloy surfaces as described in claim 1, characterized in that: The specific process of the multi-modal data fusion includes: Bubble distribution images are collected by multi-angle industrial cameras arranged around the electroplating tank, and the images are preprocessed and binarized; Based on the marker point constraint of bubble morphology priori, the watershed algorithm is used to segment the adherent bubbles, and the morphological feature parameters of each independent bubble are extracted, including equivalent diameter, topography factor and three-dimensional space coordinates; The electroplating solution container is divided into multiple unit sub-regions according to the grid size matching the minimum diameter of the bubbles; The binary image of each sub-region is spatially matched with the three-dimensional grid to calculate the bubble volume ratio of each sub-region to obtain the bubble coverage rate; The particle image velocimetry technology is used to obtain the electroplating solution flow velocity vector field, and the flow velocity and direction of the position where each bubble is located are measured as the flow field parameters of each bubble; Based on the extracted morphological feature parameters and flow field parameters of the bubbles, the real-time R value of each bubble is calculated, and the aggregation tendency index of each sub-region is calculated accordingly; After the bubble coverage rate, the aggregation tendency index and the flow field parameters are spatio-temporally aligned, the feature-level fusion is performed through a feature fusion algorithm to generate a bubble-flow field coupling feature set.

4. The method of claim 3, wherein the titanium alloy surface is controlled by electroplating.

4. The method of claim 3, wherein the titanium alloy surface is controlled by electroplating. The specific calculation process of the aggregation tendency index includes: The distribution characteristics of the morphological characteristic parameters of each bubble in the statistical sub-region are obtained, the distribution characteristics are normalized, and a bubble dynamic instability index is obtained by dynamically weighting and fusing the distribution characteristics based on the titanium alloy-electrolyte interface characteristics through a first fusion function; A bubble coverage instability index is obtained by analyzing the fluctuation characteristics of the bubble coverage in the sub-region through time series analysis; An adsorption energy density field is generated based on the titanium alloy-electrolyte interface characteristic parameters; The bubble dynamic instability index and the bubble coverage instability index are interface corrected by the adsorption energy density field, and the corrected index and the adsorption energy density field are input into a pre-trained physical information neural network to output the final aggregation tendency index of the sub-region.

5. The method for controlling electroplating on titanium alloy surfaces as described in claim 4, characterized in that: The specific execution process of the correction includes: The kinetic instability index of each sub-region is multiplied by the average adsorption energy density of the corresponding region to obtain the interface corrected bubble dynamic instability index; The bubble dynamic instability index of each sub-region is multiplied by the adsorption energy gradient of the corresponding region to obtain the interface corrected bubble coverage instability index.

6. The method for controlling electroplating on a titanium alloy surface as described in claim 4, characterized in that: The dynamic weighting and fusion strategy of the first fusion function specifically includes: The composition, thickness and porosity of the surface oxide film of the titanium alloy sample under different pretreatment processes are determined by experiment; Under the same electroplating process, the initial nucleation rate, average residence time and final coating porosity of the bubbles on the surface of the sample are synchronously collected; Through causal correlation analysis based on the partial least squares path model, a set of oxide film characteristic parameters that have a dominant influence on bubble behavior are identified; Real-time surface micro-time sequence images of the current workpiece are collected, and trained deep learning models are used to extract oxide film characteristic parameter estimates; Based on the bubble force balance mechanism, the expected detachment time of the bubble is calculated, and the adsorption stability deviation index is obtained in combination with the actual average residence time; The adsorption stability deviation index and the normalized value of the distribution characteristics are weighted and summed to obtain the final bubble dynamic instability index.

7. The method for controlling electroplating on a titanium alloy surface as described in claim 3, characterized in that: The specific execution process of the linkage adjustment is as follows: The overall bubble coverage, bubble coverage uniformity and bubble coverage concentration are calculated based on the bubble coverage of each sub-region to form a bubble coverage feature vector; The flow rate and flow direction parameters of each sub-region are extracted to form a flow field feature vector, and a bubble aggregation feature vector is formed based on the aggregation tendency index of each sub-region; According to the workpiece material thickness and electroplating process parameters, the corresponding reference motion parameter group and corresponding feature tolerance range are queried from the pre-set process knowledge base; When all feature vectors are within the corresponding tolerance range, the reference motion parameter group is used as the control output; Otherwise, the motion parameter adjustment mechanism is started and the adjustment motion parameter category and adjustment proportion are output, and the reference motion parameters are corrected based on the motion parameter category and adjustment proportion to output.

8. The method for controlling electroplating on titanium alloy surfaces as described in claim 7, characterized in that: The specific execution process of the motion parameter adjustment mechanism is as follows: The adjustment motion parameter category is determined according to the situation that the feature vector exceeds the tolerance range, and the category includes rotation speed and swing amplitude; If it is determined to adjust the rotation speed, the output rotation speed adjustment ratio is calculated by a Sigmoid function based on the bubble aggregation tendency index, the exceeding degree of the overall bubble coverage rate, and the lower degree of the flow field flow rate; If it is determined to adjust the swing amplitude, the swing amplitude adjustment ratio is calculated by a Sigmoid function based on the bubble coverage concentration, the bubble coverage uniformity, and the exceeding degree of the overall bubble coverage rate.

9. The method of claim 1, wherein: The need judgment of the hanger layout adjustment includes: The thickness variation coefficient, the defect density, and the edge defect length proportion are calculated based on the thickness distribution data, the surface defect distribution data, and the edge integrity image data, respectively, as the defect characteristics; If the thickness variation coefficient or the defect density of a batch of workpieces exceeds the preset multiple of the median value in the historical data, the batch data is excluded, and the remaining batches after exclusion are recorded as effective historical batches; The reference values of the defect characteristics are calculated based on the defect characteristics of all effective historical batch workpieces, the deviation rates of the defect characteristics of the current workpiece from the reference values are calculated and linearly weighted, and the comprehensive defect degree is output; The historical workpieces with production time within the preset time window are selected as the reference set; When the comprehensive defect degree of the current workpiece exceeds the preset threshold, and the proportion of workpieces with defect degree exceeding the threshold in the reference set reaches the preset threshold, it is judged that the hanger layout needs to be adjusted, otherwise, it is judged that the hanger layout does not need to be adjusted.

10. The method of claim 9, wherein: The specific steps of starting the dynamic reconstruction optimization of the hanger spacing are as follows: A unique identifier is assigned to each hanger in the electroplating tank, and its initial horizontal position is recorded; The horizontal spacing between adjacent hangers is calculated, and the correlation between the spacing values and the corresponding workpiece plating layer quality indicators is evaluated through the Pearson correlation coefficient to identify hanger pairs with significant correlation between the spacing values and the quality indicators; Based on the preset adjustment constraints of the hanger horizontal spacing, multiple horizontal spacing adjustment schemes are designed, and the candidate schemes that meet the process requirements are selected from the adjustment schemes through flow field and current density distribution simulation analysis; The candidate schemes are scored based on the comprehensive defect degree of the historical workpieces, and the scheme with the highest score is selected as the target adjustment scheme; The hanger positions are adjusted according to the target adjustment scheme, and the spacing values are verified and corrected through iterative optimization after adjustment until the plating layer quality of multiple workpieces in the same batch is qualified.

Images