A method and system for predicting the corrosion resistance of a zinc-aluminum-magnesium coating

Abstract

The application relates to the technical field of coating detection, and discloses a zinc-aluminum-magnesium coating corrosion resistance prediction method and system.The method comprises the following steps: segmenting a coating sample microstructure image and identifying a material region to obtain structure partition data; coupling multidimensional geometric shapes and spatial distribution characteristics to obtain a comprehensive morphology feature set; fusing chemical composition data and the comprehensive morphology feature set, and performing feature dimension reduction processing on the fused feature set to obtain a standard feature identifier; taking the standard feature identifier as a node, and taking the correlation between the measured corrosion resistance grades of zinc-aluminum-magnesium coating samples as edges to construct a corrosion resistance knowledge graph; inputting original data of a coating to be predicted, and identifying similar sample nodes; connecting the similar sample nodes into a relationship path of the zinc-aluminum-magnesium coating to be predicted, and performing traversal exploration along the relationship path to obtain a corrosion resistance prediction grade corresponding to the zinc-aluminum-magnesium coating to be predicted; and the application can improve the corrosion resistance prediction efficiency.

Description

Technical Field

[0001] This invention relates to the field of coating inspection technology, and in particular to a method and system for predicting the corrosion resistance of zinc-aluminum-magnesium coatings. Background Technology

[0002] Zinc-aluminum-magnesium (ZAM) coatings are widely used in industry due to their excellent protective properties, and their corrosion resistance is a core indicator for evaluating material quality and service life. Current methods for predicting the corrosion resistance of ZAM coatings largely rely on traditional experimental testing methods. These methods not only consume a large number of samples and time but also only allow for post-construction evaluation after coating preparation, failing to provide advance guidance for production process optimization. Furthermore, these methods often focus only on single-dimensional characteristics or analyze microstructure and chemical composition in isolation, neglecting the intrinsic relationships between multiple characteristics. This leads to significant discrepancies between predicted and actual corrosion resistance performance, making it difficult to meet the needs of accurate evaluation.

[0003] As industrial production demands higher efficiency and accuracy, some prediction methods attempt to integrate multi-dimensional data. However, these methods suffer from significant shortcomings in feature processing: either they fail to effectively reduce the dimensionality of the fused high-dimensional features, leading to data redundancy and soaring computational costs; or they lack stable data association models, resulting in poor predictive adaptability and insufficient result stability when faced with coating samples under different process parameters. This makes it difficult to efficiently support rapid performance assessment in mass production, further increasing the R&D and production costs for enterprises. Therefore, improving the efficiency of predicting the corrosion resistance of zinc-aluminum-magnesium coatings has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for predicting the corrosion resistance of zinc-aluminum-magnesium coatings, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings, comprising:

[0006] S1. The microstructure image of the zinc-aluminum-magnesium coating sample is segmented into different analytical levels, and the data of different material regions in the analytical levels are identified to obtain the structural partition data of the zinc-aluminum-magnesium coating sample.

[0007] S2. Perform multidimensional coupling on the geometric morphological features and spatial distribution features in the structural partition data to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample;

[0008] S3. The chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set are fused together, and the feature set after fusion is subjected to feature dimensionality reduction processing to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0009] S4. Using the standard feature identifiers as nodes and the correlation between the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges, construct a knowledge graph of the corrosion resistance of the zinc-aluminum-magnesium coating samples.

[0010] S5. Input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted.

[0011] S6. Connect the similar sample nodes to form a relationship path for the zinc-aluminum-magnesium coating to be predicted, and traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

[0012] In a preferred embodiment, the step of segmenting the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels and identifying different material regions at the analytical levels to obtain structural partitioning data of the zinc-aluminum-magnesium coating sample includes:

[0013] Microstructure images of zinc-aluminum-magnesium coating samples were acquired, and multi-scale Gaussian filtering was performed on the microstructure images to obtain a multi-scale image set of the zinc-aluminum-magnesium coating samples.

[0014] Boundary feature identification is performed on the filtered regions between the phases in the multi-scale image to obtain the phase boundary distribution information of the zinc-aluminum-magnesium coating sample;

[0015] Based on the phase boundary distribution information, the multi-scale image set is segmented using region growing technology to obtain independent partitions of the aluminum-magnesium coating sample;

[0016] Morphological optimization processing is performed on the independent partitions to obtain the material regions of the zinc-aluminum-magnesium coating sample;

[0017] The geometric and spatial characteristics of the material region are quantified to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

[0018] In a preferred embodiment, the multidimensional coupling of geometric features and spatial distribution features in the structural partitioning data to obtain a comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample includes:

[0019] The geometric descriptor of the zinc-aluminum-magnesium coating sample is obtained by parsing the region contour information in the structural partition data.

[0020] Based on the regional spatial coordinates and spatial topology in the structural partitioning data, a regional relationship network of the zinc-aluminum-magnesium coating sample is constructed.

[0021] Identify the regional distribution patterns in the regional relationship network to obtain the spatial distribution feature descriptor of the zinc-aluminum-magnesium coating sample;

[0022] The geometric descriptor and the spatial distribution feature descriptor are standardized and integrated to obtain the geometric morphology feature set and spatial distribution feature set of the zinc-aluminum-magnesium coating sample;

[0023] Tensor synthesis is performed on the geometric feature set and the spatial distribution feature set to obtain the geometric feature vector and spatial feature vector of the zinc-aluminum-magnesium coating sample;

[0024] The geometric feature vector and the spatial feature vector are coupled to obtain the comprehensive feature value of the zinc-aluminum-magnesium coating sample. The comprehensive feature value is then integrated to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample.

[0025] In a preferred embodiment, the formula for calculating the comprehensive feature value is:

[0026] ;

[0027] in, This represents the comprehensive feature value. Indicates the first The geometric feature vectors This represents the mean of the geometric feature vectors. Indicates the first The aforementioned spatial feature vectors The mean of the spatial feature vectors is represented. This represents the preset weighting coefficient. This represents the number of all feature vectors.

[0028] In a preferred embodiment, the process of fusing the chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set, and then performing feature dimensionality reduction on the fused feature set to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample, includes:

[0029] The chemical composition data of the zinc-aluminum-magnesium coating sample were normalized to obtain the standard composition set of the zinc-aluminum-magnesium coating sample.

[0030] The standard component set and the comprehensive morphological feature set are deeply coupled to obtain the joint feature set of the zinc-aluminum-magnesium coating sample;

[0031] Screen the feature subsets in the joint feature set that have a high correlation with the corrosion resistance level of the zinc-aluminum-magnesium coating samples;

[0032] Spatial compression is performed on the feature subset to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0033] In a preferred embodiment, the step of constructing a corrosion resistance knowledge graph of the zinc-aluminum-magnesium coating samples, using the standard feature identifiers as nodes and the correlation relationships of the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges, includes:

[0034] Spatial clustering analysis was performed on the standard feature identifiers to obtain feature similarity groups of the zinc-aluminum-magnesium coating samples;

[0035] The standard feature identifiers are mapped to nodes, and the nodes are grouped according to feature similarity to establish the topological connection relationship of the nodes, thereby obtaining the initial spectral structure of the zinc-aluminum-magnesium coating sample.

[0036] Based on the correlation strength of the measured corrosion resistance level in the zinc-aluminum-magnesium coating sample, the weight magnitude of the edges of the initial pattern structure is applied to obtain the intermediate pattern structure of the zinc-aluminum-magnesium coating sample.

[0037] The intermediate graph structure is optimized to eliminate isolated nodes, thereby obtaining the corrosion resistance knowledge graph of the zinc-aluminum-magnesium coating sample.

[0038] In a preferred embodiment, the step of inputting the original analytical data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identifying similar sample nodes to the zinc-aluminum-magnesium coating to be predicted includes:

[0039] The original analytical data of the zinc-aluminum-magnesium coating to be predicted is mapped to a feature space consistent with the zinc-aluminum-magnesium coating sample to obtain a temporary feature identifier of the zinc-aluminum-magnesium coating to be predicted.

[0040] The temporary feature identifier is compared with the standard feature identifier in the corrosion resistance knowledge graph in multiple dimensions to obtain candidate similar nodes of the zinc-aluminum-magnesium coating to be predicted.

[0041] Based on the topology of the corrosion resistance knowledge graph, the candidate similar nodes are expanded to obtain the associated nodes of the zinc-aluminum-magnesium coating to be predicted.

[0042] The confidence level of the associated nodes is evaluated, and nodes with high confidence levels are selected as similar sample nodes for the zinc-aluminum-magnesium coating to be predicted.

[0043] In a preferred embodiment, the step of connecting the similar sample nodes into a relationship path for the zinc-aluminum-magnesium coating to be predicted, and traversing along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted, includes:

[0044] Based on the spatial distribution of the similar sample nodes in the corrosion resistance knowledge graph, an initial path framework for the zinc-aluminum-magnesium coating to be predicted is established.

[0045] Based on the similarity of the similar sample nodes and the correlation between the corrosion resistance level in the corrosion resistance knowledge graph, the paths in the initial path framework are prioritized to obtain the priority path framework for the zinc-aluminum-magnesium coating to be predicted.

[0046] A multi-path search strategy is adopted to explore the priority path framework and obtain candidate paths for the zinc-aluminum-magnesium coating to be predicted.

[0047] The coherence of the candidate paths is verified to obtain the relationship path of the zinc-aluminum-magnesium coating to be predicted.

[0048] In a preferred embodiment, the step of connecting the similar sample nodes into a relationship path for the zinc-aluminum-magnesium coating to be predicted, and traversing along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted, includes:

[0049] Starting from the starting node of the relationship path, the similar sample nodes are traversed preferentially according to the path weight of the relationship path to obtain the corrosion resistance level characteristics of the similar sample nodes.

[0050] By integrating the corrosion resistance level features and eliminating feature conflicts between similar sample nodes, the corrosion resistance level feature set of the zinc-aluminum-magnesium coating to be predicted is obtained.

[0051] Trend analysis is performed on the corrosion resistance level feature set to obtain the predicted corrosion resistance level of the zinc-aluminum-magnesium coating to be predicted.

[0052] To address the above problems, the present invention also provides a corrosion resistance prediction system for zinc-aluminum-magnesium coatings, the system comprising:

[0053] The data partitioning module is used to segment the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels, and identify the data of different material regions in the analytical levels to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

[0054] The feature coupling module is used to perform multidimensional coupling of the geometric morphological features and spatial distribution features in the structural partition data to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample.

[0055] The standard feature identifier generation module is used to fuse the chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set, and to perform feature dimensionality reduction processing on the fused feature set to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0056] The corrosion resistance map construction module is used to construct a corrosion resistance knowledge map of the zinc-aluminum-magnesium coating samples, with the standard feature identifiers as nodes and the correlation between the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges.

[0057] The similar node identification module is used to input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted.

[0058] The corrosion resistance level prediction module is used to connect the similar sample nodes into a relationship path for the zinc-aluminum-magnesium coating to be predicted, and to traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. This invention accurately obtains structural partitioning data by segmenting the microstructure image of zinc-aluminum-magnesium coating samples into different analytical levels and identifying material region data. Then, it performs multidimensional coupling of geometric morphological features and spatial distribution features to form a comprehensive morphological feature set. Simultaneously, it integrates chemical composition data and performs feature dimensionality reduction processing to obtain standard feature identifiers. This series of operations achieves comprehensive extraction and optimization of multidimensional key features of the coating, making the feature characterization more closely aligned with the actual influencing factors of the coating's corrosion resistance. This significantly improves the accuracy and effectiveness of the feature data, providing a high-quality data foundation for subsequent corrosion resistance prediction.

[0061] 2. This invention constructs a corrosion resistance knowledge graph using standard feature identifiers as nodes and the correlation between measured corrosion resistance levels of samples as edges. Subsequently, the original analytical data of the coating to be predicted is input into the graph, accurately identifying similar sample nodes and connecting them into relational paths. The predicted level is then obtained by traversing these paths. This process establishes a stable correlation model between features and corrosion resistance, enabling efficient matching of similar samples of the coating to be predicted, achieving accurate derivation of the corrosion resistance level, effectively improving the efficiency of corrosion resistance prediction, and providing reliable technical support for the performance evaluation and application selection of zinc-aluminum-magnesium coating materials. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating a method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings according to an embodiment of the present invention.

[0063] Figure 2 This is a functional block diagram of a zinc-aluminum-magnesium coating corrosion resistance prediction system provided in an embodiment of the present invention;

[0064] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0065] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0066] This application provides a method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0067] Reference Figure 1 The diagram shown is a flowchart illustrating a method for predicting the corrosion resistance of a zinc-aluminum-magnesium coating according to an embodiment of the present invention. In this embodiment, the method for predicting the corrosion resistance of a zinc-aluminum-magnesium coating includes:

[0068] S1. The microstructure image of the zinc-aluminum-magnesium coating sample is segmented into different analytical levels, and the data of different material regions in the analytical levels are identified to obtain the structural partition data of the zinc-aluminum-magnesium coating sample.

[0069] In this embodiment of the invention, the step of segmenting the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels and identifying different material regions at the analytical levels to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample includes:

[0070] Microstructure images of zinc-aluminum-magnesium coating samples were acquired, and multi-scale Gaussian filtering was performed on the microstructure images to obtain a multi-scale image set of the zinc-aluminum-magnesium coating samples.

[0071] Boundary feature identification is performed on the filtered regions between the phases in the multi-scale image to obtain the phase boundary distribution information of the zinc-aluminum-magnesium coating sample;

[0072] Based on the phase boundary distribution information, the multi-scale image set is segmented using region growing technology to obtain independent partitions of the aluminum-magnesium coating sample;

[0073] Morphological optimization processing was performed on the independent partitions to obtain the material regions of the zinc-aluminum-magnesium coating sample;

[0074] The geometric and spatial characteristics of the material region are quantified to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

[0075] When acquiring microscopic images of zinc-aluminum-magnesium coating samples, high-resolution microscopic imaging equipment was used to capture images at different locations and focal lengths of the coating samples. This ensured that the images clearly presented the phase distribution, microstructure, and various detailed features within the coating, obtaining complete original microscopic images. When performing multi-scale Gaussian filtering on these microscopic images, multiple different filtering scales were set. The original image was smoothed separately for each scale, reducing random noise interference while fully preserving key phase details at the corresponding scale. Each scale resulted in a corresponding filtered image. All filtered images at different scales were then integrated and combined to form a multi-scale image set of the zinc-aluminum-magnesium coating samples.

[0076] The filtered regions in the multi-scale image set are transitional regions formed after filtering of different phases. When identifying the boundary features of these regions, the filtered regions in each scale image are analyzed one by one. The gray value changes, texture differences, and contour directions of the filtered regions and adjacent phase regions are observed. By capturing continuous points with abrupt changes in gray value, the boundary lines between different phases are determined. At the same time, the phase type corresponding to each boundary is labeled. The boundary information identified in all scale images is summarized and integrated to finally obtain the phase boundary distribution information of the zinc-aluminum-magnesium coating sample.

[0077] Based on the acquired phase boundary distribution information, when segmenting multi-scale image sets using region growing technology, the phase boundaries marked in the phase boundary distribution information are used as explicit constraints. Core pixels inside the phase are selected as the growth starting point in each scale image. According to the similarity criteria between the gray value, texture features and core pixels of the pixels, the growth gradually expands to the surrounding adjacent pixels. During the growth process, the identified phase boundaries are strictly not crossed. When there are no more pixels that meet the similarity criteria to be added to the growth area, the growth stops. Each complete region formed by growth is an independent partition. After completing the segmentation operation of images at all scales, independent partitions of zinc-aluminum-magnesium coating samples are obtained.

[0078] When performing morphological optimization on independent partitions, internal defects are first addressed for each partition, filling in the tiny holes formed by residual noise to ensure the internal structure of the partition is complete and without defects. Then, edge issues are addressed, eliminating burrs, irregular protrusions, and other redundant structures at the partition edges. Edge lines are made continuous and regular by smoothing edge pixels, while maintaining the overall outline and original size of the partition. Each independent partition after the above processing is the material area of ​​the zinc-aluminum-magnesium coating sample.

[0079] When quantifying the geometric and spatial characteristics of material regions, for geometric characteristics, quantifiable indicators such as the area, perimeter, and regularity of the shape of each material region are statistically analyzed, and the specific values ​​of each indicator are directly recorded. For spatial characteristics, the specific position coordinates of each material region in the image are analyzed, the straight-line distance between different material regions is measured, and whether there is overlap and the extent of overlap are determined. At the same time, the arrangement and distribution of each material region are recorded. The quantification results of the geometric characteristics and spatial characteristics of all material regions are systematically integrated and summarized to finally obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

[0080] The beneficial effect is that through a systematic and meticulous image processing and feature quantization process, the structural partition data of zinc-aluminum-magnesium coating samples were accurately obtained. This not only effectively eliminated image noise interference and clarified the accurate range of phase boundaries and material regions, but also comprehensively captured the geometric features and spatial relationship features of the material regions. This provides accurate and reliable basic data support for subsequent multi-dimensional feature coupling and corrosion resistance prediction, ensuring the scientific nature and accuracy of the entire prediction process.

[0081] S2. Perform multidimensional coupling on the geometric morphological features and spatial distribution features in the structural partition data to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample;

[0082] In this embodiment of the invention, the multidimensional coupling of geometric morphological features and spatial distribution features in the structural partitioning data to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample includes:

[0083] The geometric descriptor of the zinc-aluminum-magnesium coating sample is obtained by parsing the region contour information in the structural partition data.

[0084] Based on the regional spatial coordinates and spatial topology in the structural partitioning data, a regional relationship network of the zinc-aluminum-magnesium coating sample is constructed.

[0085] Identify the regional distribution patterns in the regional relationship network to obtain the spatial distribution feature descriptor of the zinc-aluminum-magnesium coating sample;

[0086] The geometric descriptor and the spatial distribution feature descriptor are standardized and integrated to obtain the geometric morphology feature set and spatial distribution feature set of the zinc-aluminum-magnesium coating sample;

[0087] Tensor synthesis is performed on the geometric feature set and the spatial distribution feature set to obtain the geometric feature vector and spatial feature vector of the zinc-aluminum-magnesium coating sample;

[0088] The geometric feature vector and the spatial feature vector are coupled to obtain the comprehensive feature value of the zinc-aluminum-magnesium coating sample. The comprehensive feature value is then integrated to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample.

[0089] The formula for calculating the comprehensive feature value is as follows:

[0090] ;

[0091] in, This represents the comprehensive feature value. Indicates the first The geometric feature vectors This represents the mean of the geometric feature vectors. Indicates the first The aforementioned spatial feature vectors The mean of the spatial feature vectors is represented by . This represents the preset weighting coefficient. This represents the number of all feature vectors.

[0092] When parsing the regional contour information in the structural partition data, edge tracking is performed on each material region contained in the structural partition data one by one. The position information of the boundary pixels of the material region is recorded sequentially to form a complete and continuous regional contour line. Then, key features are extracted based on the contour line, including the curvature of the contour, the number of turns, the regularity of the overall shape, and the range of the region enclosed by the contour. These extracted information about the regional contour are systematically organized to obtain the geometric descriptor of the zinc-aluminum-magnesium coating sample.

[0093] When constructing a regional relationship network based on the regional spatial coordinates and spatial topology in the structural partition data, the specific spatial coordinates of each material region are first extracted from the structural partition data to clarify the position of each region in the overall coating structure. Then, the spatial topological relationships between each material region are analyzed, including adjacent contact relationships, inclusion relationships, and separation relationships. Each material region is treated as an independent node in the network, and nodes with topological relationships are connected by lines. The corresponding topological relationship type is clearly marked on the lines, and finally, a regional relationship network of zinc-aluminum-magnesium coating samples is formed.

[0094] When identifying regional distribution patterns in a regional relationship network, first observe the overall arrangement of all nodes in the network to determine whether the nodes are evenly distributed, clustered, or arranged in a specific shape. Then, count the number and proportion of node pairs with different topological relationships in the network, analyze the density distribution of connections between nodes, and observe whether there are repeated node association combinations. Integrate these observations and statistical information on regional arrangement and association characteristics to obtain a spatial distribution characteristic descriptor for zinc-aluminum-magnesium coating samples.

[0095] When standardizing and integrating geometric descriptors and spatial distribution feature descriptors, the feature representation formats of both are first unified. Different types of contour features in the geometric descriptors are classified and organized according to preset unified classification rules. The arrangement patterns, correlation ratios, and other information in the spatial distribution feature descriptors are also classified according to corresponding rules to ensure that the representation of all features is consistent and unambiguous. Then, all relevant information of the classified and organized geometric descriptors is compiled into a book to obtain the geometric morphological feature set of the zinc-aluminum-magnesium coating sample. All relevant information of the classified and organized spatial distribution feature descriptors is compiled into a book to obtain the spatial distribution feature set of the zinc-aluminum-magnesium coating sample.

[0096] When performing tensor synthesis on the geometric morphology feature set and the spatial distribution feature set, for the geometric morphology feature set, each geometric feature is assigned a unique dimension position according to the attribute category order of various geometric features in the feature set. All geometric features are then arranged sequentially according to their assigned dimension positions to form an ordered feature combination, resulting in the geometric feature vector of the zinc-aluminum-magnesium coating sample. For the spatial distribution feature set, the same method is used, assigning dimension positions according to the attribute category order of various spatial features in the feature set. All spatial features are then arranged sequentially according to their dimension positions to form an ordered feature combination, resulting in the spatial feature vector of the zinc-aluminum-magnesium coating sample.

[0097] The mean of geometric eigenvectors is calculated by summing the eigenvalues ​​corresponding to all geometric eigenvectors, and then dividing the sum by the total number of geometric eigenvectors.

[0098] The mean of spatial feature vectors is calculated by summing the feature values ​​corresponding to all spatial feature vectors, and then dividing the sum by the total number of spatial feature vectors.

[0099] The preset weighting coefficients are fixed values ​​determined based on the importance of geometric and spatial characteristics to the corrosion resistance of zinc-aluminum-magnesium coatings, through preliminary research and practical application verification of the influence law on coating performance.

[0100] The total number of all eigenvectors refers to the total number of geometric eigenvectors obtained after tensor synthesis. Since geometric eigenvectors and spatial eigenvectors are generated based on the same batch of structural partition data, their numbers are exactly the same.

[0101] No. The first geometric eigenvector is the first geometric eigenvector obtained after tensor synthesis, arranged in order. The vector, the first The nth spatial eigenvector is the nth spatial eigenvector obtained after tensor synthesis, arranged in order. A vector.

[0102] When coupling geometric feature vectors and spatial feature vectors, the two types of vectors are fused according to a specific calculation logic. During the calculation, the difference between each geometric feature vector and the mean of the geometric feature vectors, and the difference between each spatial feature vector and the mean of the spatial feature vectors are calculated separately. The two differences at each corresponding position are multiplied together, and then multiplied by a preset weight coefficient. All the obtained product results are accumulated to obtain the value of the numerator.

[0103] Then, square the differences between all geometric feature vectors and the mean, and sum them up. Take the square root of the sum to get the first denominator factor. Square the differences between all spatial feature vectors and the mean, and sum them up. Take the square root of the sum to get the second denominator factor. Multiply the two denominator factors to get the value of the denominator.

[0104] Finally, the value of the numerator is divided by the value of the denominator to obtain the comprehensive feature value. The core of this calculation process is to quantitatively reflect the correlation and comprehensive effect of geometric feature vectors and spatial feature vectors. Each comprehensive feature value can comprehensively reflect the synergistic effect of geometric and spatial features in the corresponding dimension. The comprehensive feature values ​​corresponding to all dimensions are sorted and summarized in the original dimension order to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample.

[0105] The beneficial effect is that through a series of coherent and meticulous feature extraction, integration, synthesis and coupling operations, the geometric morphology and spatial distribution characteristics of zinc-aluminum-magnesium coating samples are captured comprehensively and accurately, forming a complete set of comprehensive morphological features. This set of features not only retains the individual morphological characteristics of each material region of the coating, but also reflects the correlation between regions. It provides a comprehensive, reliable and strongly correlated morphological feature basis for subsequent corrosion resistance prediction by integrating chemical composition data, ensuring the scientificity and accuracy of the subsequent prediction process.

[0106] S3. The chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set are fused together, and the feature set after fusion is subjected to feature dimensionality reduction processing to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0107] In this embodiment of the invention, the process of fusing the chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set, and performing feature dimensionality reduction processing on the fused feature set to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample, includes:

[0108] The chemical composition data of the zinc-aluminum-magnesium coating sample were normalized to obtain the standard composition set of the zinc-aluminum-magnesium coating sample.

[0109] The standard component set and the comprehensive morphological feature set are deeply coupled to obtain the joint feature set of the zinc-aluminum-magnesium coating sample;

[0110] Screen the feature subsets in the joint feature set that have a high correlation with the corrosion resistance level of the zinc-aluminum-magnesium coating samples;

[0111] Spatial compression is performed on the feature subset to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0112] When normalizing the chemical composition data of zinc-aluminum-magnesium coating samples, the various chemical elements contained in the sample and their specific content data are first identified, the value range of each chemical element is determined, the maximum and minimum values ​​of the element in all the test data are found, the minimum value is subtracted from the specific content of the element in each sample, and the difference is divided by the difference between the maximum and minimum values. Through this operation, the content data of all chemical elements are uniformly mapped to the same numerical range, eliminating the dimensional differences between the contents of different elements. All the processed chemical element content data are systematically organized to obtain the standard composition set of zinc-aluminum-magnesium coating samples.

[0113] When deeply coupling the standard component set and the comprehensive morphological feature set, a single zinc-aluminum-magnesium coating sample is used as the basic unit. First, the normalized content data of all chemical elements in the standard component set of the sample are extracted. Then, all comprehensive feature values ​​in the comprehensive morphological feature set of the sample are extracted. According to the correspondence logic of "chemical element content - comprehensive feature value", the two types of feature data of the same sample are matched and associated one by one to ensure that the content of each chemical element forms a complete feature combination with the corresponding comprehensive feature value. All such feature combinations of all samples are summarized and integrated to form a set containing both chemical composition and morphological feature information, thus obtaining the joint feature set of zinc-aluminum-magnesium coating samples.

[0114] When screening the subset of features in the joint feature set that are highly correlated with the corrosion resistance level of zinc-aluminum-magnesium coating samples, first determine the measured corrosion resistance level corresponding to each sample, and then analyze the correspondence between the numerical change of each feature in the joint feature set and the corrosion resistance level. When the value of a certain feature changes regularly, if the corrosion resistance level of the sample also shows a clear synchronous change trend, that is, when the value of the feature increases or decreases, the corrosion resistance level also increases or decreases accordingly, it indicates that the feature is highly correlated with the corrosion resistance level. All such features with clear synchronous change trends are selected, and the set formed is the feature subset of zinc-aluminum-magnesium coating samples.

[0115] When spatially compressing the feature subset to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample, the core connotation of each feature in the feature subset is first comprehensively analyzed to determine whether different features reflect the same essential law affecting corrosion resistance. Similar features reflecting the same law are merged, and duplicate or redundant information is removed, while key content that can reflect the core influencing law is retained. Then, according to the importance of each feature to corrosion resistance, the merged core features are arranged in an orderly manner to form a set of concise, concentrated features that can comprehensively cover the key characteristics of the sample. This feature combination is the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0116] The beneficial effects are that by normalizing the chemical composition data, deeply coupling the two types of feature sets, screening highly correlated features, and performing spatial compression operations, the representation format of chemical composition data is unified, and the deep integration of chemical composition and morphological features is achieved. At the same time, redundant information is eliminated and core features are focused on. The resulting standard feature identifiers are accurate and concise, providing high-quality core node data for the subsequent construction of corrosion resistance knowledge graphs, and ensuring the accuracy and efficiency of subsequent similar sample matching and corrosion resistance prediction.

[0117] S4. Using the standard feature identifiers as nodes and the correlation between the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges, construct a knowledge graph of the corrosion resistance of the zinc-aluminum-magnesium coating samples.

[0118] In this embodiment of the invention, the step of constructing a corrosion resistance knowledge graph of the zinc-aluminum-magnesium coating samples, using the standard feature identifiers as nodes and the correlation relationships of the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges, includes:

[0119] Spatial clustering analysis was performed on the standard feature identifiers to obtain feature similarity groups for the zinc-aluminum-magnesium coating samples;

[0120] The standard feature identifiers are mapped to nodes, and the nodes are grouped according to feature similarity to establish the topological connection relationship of the nodes, thereby obtaining the initial spectral structure of the zinc-aluminum-magnesium coating sample.

[0121] Based on the correlation strength of the measured corrosion resistance level in the zinc-aluminum-magnesium coating sample, the weight magnitude of the edges of the initial pattern structure is applied to obtain the intermediate pattern structure of the zinc-aluminum-magnesium coating sample.

[0122] The intermediate graph structure is optimized to eliminate isolated nodes, thereby obtaining the corrosion resistance knowledge graph of the zinc-aluminum-magnesium coating sample.

[0123] When performing spatial cluster analysis on the standard feature identifiers of zinc-aluminum-magnesium coating samples, the core feature content contained in each standard feature identifier is extracted one by one. The core features of any two standard feature identifiers are comprehensively compared, and the overlap between the two in terms of feature type, feature value trend, etc. is statistically analyzed. When the overlap of the core features of two standard feature identifiers reaches the set unified judgment standard, the two standard feature identifiers are grouped into the same group. According to the same comparison method, the pairwise comparison and classification of all standard feature identifiers are completed, and finally multiple sets with similar feature attributes are formed, resulting in the feature similarity grouping of zinc-aluminum-magnesium coating samples.

[0124] Each standard feature identifier of the zinc-aluminum-magnesium coating sample is assigned to an independent node, and each node uniquely represents a standard feature identifier. Based on the feature similarity grouping results, all nodes within the same group are connected to each other with straight lines. Nodes in different groups are not connected at the moment. In this way, the initial correlation between nodes is clarified, forming a basic structure containing nodes and initial connections between nodes, thus obtaining the initial spectral structure of the zinc-aluminum-magnesium coating sample.

[0125] The measured corrosion resistance grades of each zinc-aluminum-magnesium coating sample were collected. The measured corrosion resistance grades of the samples corresponding to the two nodes connected by each line in the initial spectrum structure were analyzed. If the measured corrosion resistance grades of the samples corresponding to the two nodes were completely consistent, the correlation strength between the two was determined to be the highest. If the grades were similar, the correlation strength was medium. If the grades differed greatly, the correlation strength was the lowest. According to the different correlation strength grades, a corresponding weight label was marked for each line. The weight label directly reflects the degree of correlation between the corrosion resistance grades between the nodes. After completing the weight labeling of all lines, the intermediate spectrum structure of the zinc-aluminum-magnesium coating sample was obtained.

[0126] When optimizing the intermediate graph structure of zinc-aluminum-magnesium coating samples, all nodes in the graph are thoroughly examined to identify isolated nodes that are not connected to any other nodes. For each isolated node, its corresponding standard feature identifier is re-compared with the core features of all feature similarity groups to find the group with the highest degree of overlap of core features. A weakly weighted identifier is then established between the isolated node and any node in the group to ensure that all nodes in the graph have at least one connection. After eliminating all isolated nodes, a knowledge graph of the corrosion resistance of zinc-aluminum-magnesium coating samples with a complete structure and reasonable node associations is obtained.

[0127] The beneficial effects are that spatial clustering analysis clarifies feature similarity groups, establishes node topological connections based on groups to form an initial graph, assigns edge weights based on measured corrosion resistance levels, and further optimizes and eliminates isolated nodes. The final corrosion resistance knowledge graph has clear node association logic, weight assignments that conform to actual corrosion resistance association rules, and a complete and non-redundant structure. It provides a stable and reliable graph foundation for subsequent matching of similar samples of the coating to be predicted and the derivation of corrosion resistance levels, effectively ensuring the accuracy and efficiency of the subsequent prediction process.

[0128] S5. Input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted.

[0129] In this embodiment of the invention, the step of inputting the original analytical data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identifying similar sample nodes to the zinc-aluminum-magnesium coating to be predicted includes:

[0130] The original analytical data of the zinc-aluminum-magnesium coating to be predicted is mapped to a feature space consistent with the zinc-aluminum-magnesium coating sample to obtain a temporary feature identifier of the zinc-aluminum-magnesium coating to be predicted.

[0131] The temporary feature identifier is compared with the standard feature identifier in the corrosion resistance knowledge graph in multiple dimensions to obtain candidate similar nodes of the zinc-aluminum-magnesium coating to be predicted.

[0132] Based on the topology of the corrosion resistance knowledge graph, the candidate similar nodes are expanded to obtain the associated nodes of the zinc-aluminum-magnesium coating to be predicted.

[0133] The confidence level of the associated nodes is evaluated, and nodes with high confidence levels are selected as similar sample nodes for the zinc-aluminum-magnesium coating to be predicted.

[0134] When mapping the original analytical data of the zinc-aluminum-magnesium coating to be predicted to a feature space consistent with that of the zinc-aluminum-magnesium coating sample, the original analytical data of the coating to be predicted is first extracted, including chemical composition data and microstructure-related data. According to the standard used in the processing of zinc-aluminum-magnesium coating samples, the original chemical composition data is normalized, and the original microstructure data is sequentially subjected to image segmentation, feature coupling, and other operations consistent with the sample to obtain the comprehensive morphological features of the coating to be predicted. Then, according to the feature type, classification rules, and arrangement order of the sample feature space, the normalized chemical composition data and the comprehensive morphological features are integrated to make the feature representation format and dimensional composition of the coating to be predicted completely match the feature space of the sample. The final feature combination is the temporary feature identifier of the zinc-aluminum-magnesium coating to be predicted.

[0135] When performing multi-dimensional similarity comparisons between temporary feature identifiers and standard feature identifiers in the corrosion resistance knowledge graph, the comparisons are conducted from three dimensions: feature type, feature numerical trend, and core feature connotation. The corresponding features of each temporary feature identifier and each standard feature identifier are compared one by one. The numerical matching of the two in the same feature type, the consistency of feature change trends, and the overlap of the patterns reflected by the core features are statistically analyzed. When the overall matching degree of the three reaches the set unified judgment standard, the graph node corresponding to the standard feature identifier is the candidate similar node of the zinc-aluminum-magnesium coating to be predicted. After completing the comparison of all standard feature identifiers, the candidate similar node set is obtained.

[0136] When expanding the domain of candidate similar nodes based on the topological structure of the corrosion resistance knowledge graph, first clarify all the topological connections that each candidate similar node has established in the graph, find all nodes that are directly connected to each candidate similar node through lines. Since these nodes have a clear topological association with the candidate similar nodes, it indicates that their corresponding standard feature identifiers are related to the features of the candidate similar nodes. All directly connected nodes of all candidate similar nodes are included and together with the candidate similar nodes form a set of associated nodes, thus obtaining the associated nodes of the zinc-aluminum-magnesium coating to be predicted.

[0137] When assessing the confidence of associated nodes, two core dimensions are considered: first, the degree of multi-dimensional similarity between the standard feature identifier and the temporary feature identifier corresponding to the associated node; and second, the weight identifier of the connection between the associated node and the candidate similar node. The higher the degree of similarity and the larger the weight identifier of the connection, the stronger the reliability and the higher the confidence of the associated node. According to the unified confidence judgment standard, nodes that meet the requirements of both the degree of similarity and the weight identifier are selected and these nodes are used as similar sample nodes for the zinc-aluminum-magnesium coating to be predicted.

[0138] The beneficial effects are that by mapping the coating data to be predicted to a unified feature space, the comparability with the sample features is ensured; multi-dimensional similarity comparison accurately locks the initial candidate nodes; domain expansion based on topology expands the correlation range; confidence assessment effectively screens out reliable nodes; and the final similar sample nodes have both similarity and correlation, providing an accurate and reliable basis for the subsequent derivation of corrosion resistance level, and ensuring the scientificity and accuracy of the subsequent prediction process.

[0139] S6. Connect the similar sample nodes to form a relationship path for the zinc-aluminum-magnesium coating to be predicted, and traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

[0140] In this embodiment of the invention, connecting the similar sample nodes into the relationship path for predicting the zinc-aluminum-magnesium coating includes:

[0141] Based on the spatial distribution of the similar sample nodes in the corrosion resistance knowledge graph, an initial path framework for the zinc-aluminum-magnesium coating to be predicted is established.

[0142] Based on the similarity of the similar sample nodes and the correlation between the corrosion resistance level in the corrosion resistance knowledge graph, the paths in the initial path framework are prioritized to obtain the priority path framework for the zinc-aluminum-magnesium coating to be predicted.

[0143] A multi-path search strategy is adopted to explore the priority path framework and obtain candidate paths for the zinc-aluminum-magnesium coating to be predicted.

[0144] The coherence of the candidate paths is verified to obtain the relationship path of the zinc-aluminum-magnesium coating to be predicted.

[0145] The process of traversing the relationship path to obtain the predicted corrosion resistance level of the zinc-aluminum-magnesium coating includes:

[0146] Starting from the starting node of the relationship path, the similar sample nodes are traversed preferentially according to the path weight of the relationship path to obtain the corrosion resistance level characteristics of the similar sample nodes.

[0147] By integrating the corrosion resistance level features and eliminating feature conflicts between similar sample nodes, the corrosion resistance level feature set of the zinc-aluminum-magnesium coating to be predicted is obtained.

[0148] Trend analysis is performed on the corrosion resistance level feature set to obtain the predicted corrosion resistance level of the zinc-aluminum-magnesium coating to be predicted.

[0149] When establishing the initial path framework for the zinc-aluminum-magnesium coating to be predicted based on the spatial distribution of similar sample nodes in the corrosion resistance knowledge graph, the specific location of each similar sample node in the graph and the existing topological connections between the nodes are first clarified. All similar sample nodes are marked and located in the graph. Then, based on the distribution density and connection tightness of the nodes, the potential path directions that can be extended from different sample nodes are initially sorted out. These potential path directions are combined with the actual connections between nodes to construct a basic path set containing all possible connection methods, forming the initial path framework for the zinc-aluminum-magnesium coating to be predicted.

[0150] When prioritizing paths in the initial path framework based on the similarity of similar sample nodes and the correlation between corrosion resistance levels in the corrosion resistance knowledge graph, the similarity between all similar sample nodes on each path and the temporary feature identifier of the coating to be predicted is first determined. Then, the correlation between the corrosion resistance level corresponding to each node on each path and the core influencing factors of coating corrosion resistance is confirmed. The sum of similarity and the sum of correlation of each path are comprehensively considered. The higher the sum of similarity and the closer the sum of correlation, the higher the priority of the path. All paths in the initial path framework are sorted according to this unified standard, and the high-priority paths are selected to form a new framework, thus obtaining the priority path framework for the zinc-aluminum-magnesium coating to be predicted.

[0151] When exploring the priority path framework using a multi-path search strategy, we start from the starting point of each high-priority path in the priority path framework and gradually extend in different directions along the lines connecting the nodes. During the extension process, we record the connection order and corresponding path weight of each node to ensure that the exploration process covers all possible extension directions of the high-priority paths in the framework and does not miss any complete paths with valid connections. All the complete paths that have been explored and meet the high-priority criteria are collected and summarized to obtain the candidate paths for the zinc-aluminum-magnesium coating to be predicted.

[0152] When verifying the coherence of candidate paths to obtain the relationship path of the zinc-aluminum-magnesium coating to be predicted, the connection logic of the nodes on each candidate path is checked one by one to confirm whether the connection between adjacent nodes on the path has a reasonable weight label, whether the feature attributes corresponding to the nodes have a continuous correlation trend, and whether there are no unrelated node jumps or broken connections. At the same time, it is ensured that the corrosion resistance level correlation direction from the starting point to the ending point of the path is consistent and without logical contradictions. After verification, all coherent candidate paths without logical defects are retained to obtain the relationship path of the zinc-aluminum-magnesium coating to be predicted.

[0153] When obtaining the corrosion resistance level characteristics of similar sample nodes by prioritizing the traversal of similar sample nodes according to the path weight of the relation path, the starting node of each relation path is determined as the traversal starting point. The traversal order is determined according to the weight of the connection between each node on the path. The next node corresponding to the connection with the larger weight is traversed first. During the traversal, the measured corrosion resistance level corresponding to each similar sample node is recorded one by one. These recorded measured corrosion resistance levels are the corrosion resistance level characteristics of similar sample nodes.

[0154] When integrating corrosion resistance grade features and eliminating feature conflicts between similar sample nodes to obtain the corrosion resistance grade feature set of the zinc-aluminum-magnesium coating to be predicted, firstly, all the corrosion resistance grade features obtained through traversal are classified and summarized according to feature type. Then, it is checked whether there are conflicts of inconsistent grades for the same type of features corresponding to different similar sample nodes. When a conflict occurs, the grade features corresponding to nodes with high similarity and large path weight are retained based on the similarity between the node and the coating to be predicted, while the conflicting low-priority features are eliminated. Finally, a set of conflict-free grade features is formed, which is the corrosion resistance grade feature set of the zinc-aluminum-magnesium coating to be predicted.

[0155] When performing trend analysis on the corrosion resistance grade feature set to obtain the predicted corrosion resistance grade of the zinc-aluminum-magnesium coating to be predicted, the frequency of each type of corrosion resistance grade in the feature set is statistically analyzed, the central trend of the grade distribution is analyzed, and the correlation between the grade in the feature set and the path weight and node similarity is combined to determine the corrosion resistance grade with the highest proportion and corresponding high similarity and high weight nodes. This grade is the most representative core grade in the feature set, and this core grade is determined as the predicted corrosion resistance grade of the zinc-aluminum-magnesium coating to be predicted.

[0156] The beneficial effects are that by gradually constructing a path framework, screening high-priority paths, verifying path coherence, and traversing nodes according to weight, the corrosion resistance level features that conflict are fully integrated and eliminated. Finally, the prediction level is accurately locked through trend analysis. The whole process is logically coherent and progressive, which not only makes full use of the effective information of similar sample nodes, but also avoids the interference of invalid data and conflicting features, ensuring the accuracy and reliability of the corrosion resistance prediction level, and providing a precise basis for the performance evaluation of the zinc-aluminum-magnesium coating to be predicted.

[0157] like Figure 2 The diagram shown is a functional block diagram of a zinc-aluminum-magnesium coating corrosion resistance prediction system provided in an embodiment of the present invention.

[0158] The zinc-aluminum-magnesium coating corrosion resistance prediction system 100 described in this invention can be installed in electronic devices. Depending on the functions implemented, the zinc-aluminum-magnesium coating corrosion resistance prediction system 100 may include a data partitioning module 101, a feature coupling module 102, a standard feature identifier generation module 103, a corrosion resistance map construction module 104, a similar node identification module 105, and a corrosion resistance level prediction module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0159] In this embodiment, the functions of each module / unit are as follows:

[0160] The data partitioning module 101 is used to segment the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels, and identify different material regions on the analytical levels to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

[0161] The feature coupling module 102 is used to perform multidimensional coupling of the geometric morphological features and spatial distribution features in the structural partition data to obtain a comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample.

[0162] The standard feature identifier generation module 103 is used to fuse the chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set, and to perform feature dimensionality reduction processing on the fused feature set to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

[0163] The corrosion resistance map construction module 104 is used to construct a corrosion resistance knowledge map of the zinc-aluminum-magnesium coating sample, with the standard feature identifier as nodes and the correlation relationship of the measured corrosion resistance level in the zinc-aluminum-magnesium coating sample as edges.

[0164] The similar node identification module 105 is used to input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted.

[0165] The corrosion resistance level prediction module 106 is used to connect the similar sample nodes into a relationship path for the zinc-aluminum-magnesium coating to be predicted, and to traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

[0166] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0167] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0169] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0170] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings, characterized in that, The method includes: S1. The microstructure image of the zinc-aluminum-magnesium coating sample is segmented into different analytical levels, and the data of different material regions in the analytical levels are identified to obtain the structural partition data of the zinc-aluminum-magnesium coating sample. S2. Multidimensionally couple the geometric morphological features and spatial distribution features in the structural partitioning data to obtain a comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample, including: The geometric descriptor of the zinc-aluminum-magnesium coating sample is obtained by parsing the region contour information in the structural partition data. Based on the regional spatial coordinates and spatial topology in the structural partitioning data, a regional relationship network of the zinc-aluminum-magnesium coating sample is constructed. Identify the regional distribution patterns in the regional relationship network to obtain the spatial distribution feature descriptor of the zinc-aluminum-magnesium coating sample; The geometric descriptor and the spatial distribution feature descriptor are standardized and integrated to obtain the geometric morphology feature set and spatial distribution feature set of the zinc-aluminum-magnesium coating sample; Tensor synthesis is performed on the geometric feature set and the spatial distribution feature set to obtain the geometric feature vector and spatial feature vector of the zinc-aluminum-magnesium coating sample; The geometric feature vector and the spatial feature vector are coupled to obtain the comprehensive feature value of the zinc-aluminum-magnesium coating sample. These comprehensive feature values ​​are then integrated to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample. The formula for calculating the comprehensive feature value is as follows: ; in, This represents the comprehensive feature value. Indicates the first The geometric feature vectors This represents the mean of the geometric feature vectors. Indicates the first The aforementioned spatial feature vectors The mean of the spatial feature vectors is represented. This represents the preset weighting coefficient. This represents the number of all feature vectors; S3. The chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set are fused together, and the feature set after fusion is subjected to feature dimensionality reduction processing to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample. S4. Using the standard feature identifiers as nodes and the correlation between the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges, construct a knowledge graph of the corrosion resistance of the zinc-aluminum-magnesium coating samples. S5. Input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted. S6. Connect the similar sample nodes to form a relationship path for the zinc-aluminum-magnesium coating to be predicted, and traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

2. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The process of segmenting the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels and identifying different material regions within those analytical levels to obtain structural partitioning data of the zinc-aluminum-magnesium coating sample includes: Microstructure images of zinc-aluminum-magnesium coating samples were acquired, and multi-scale Gaussian filtering was performed on the microstructure images to obtain a multi-scale image set of the zinc-aluminum-magnesium coating samples. Boundary feature identification is performed on the filtered regions between the phases in the multi-scale image to obtain the phase boundary distribution information of the zinc-aluminum-magnesium coating sample; Based on the phase boundary distribution information, the multi-scale image set is segmented using region growing technology to obtain independent partitions of the zinc-aluminum-magnesium coating sample; Morphological optimization processing is performed on the independent partitions to obtain the material regions of the zinc-aluminum-magnesium coating sample; The geometric and spatial characteristics of the material region are quantified to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample.

3. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The process involves fusing the chemical composition data of the zinc-aluminum-magnesium coating sample with the comprehensive morphological feature set, and then performing feature dimensionality reduction on the fused feature set to obtain the standard feature identifiers of the zinc-aluminum-magnesium coating sample, including: The chemical composition data of the zinc-aluminum-magnesium coating sample were normalized to obtain the standard composition set of the zinc-aluminum-magnesium coating sample. The standard component set and the comprehensive morphological feature set are deeply coupled to obtain the joint feature set of the zinc-aluminum-magnesium coating sample; Screen the feature subsets in the joint feature set that have a high correlation with the corrosion resistance level of the zinc-aluminum-magnesium coating samples; Spatial compression is performed on the feature subset to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample.

4. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The process involves constructing a knowledge graph of the corrosion resistance of the zinc-aluminum-magnesium coating samples, using the standard feature identifiers as nodes and the correlation relationships of the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges. This includes: Spatial clustering analysis was performed on the standard feature identifiers to obtain feature similarity groups of the zinc-aluminum-magnesium coating samples; The standard feature identifiers are mapped to nodes, and the nodes are grouped according to feature similarity to establish the topological connection relationship of the nodes, thereby obtaining the initial spectral structure of the zinc-aluminum-magnesium coating sample. Based on the correlation strength of the measured corrosion resistance level in the zinc-aluminum-magnesium coating sample, the weight magnitude of the edges of the initial pattern structure is applied to obtain the intermediate pattern structure of the zinc-aluminum-magnesium coating sample. The intermediate graph structure is optimized to eliminate isolated nodes, thereby obtaining the corrosion resistance knowledge graph of the zinc-aluminum-magnesium coating sample.

5. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The process of inputting the original analytical data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identifying similar sample nodes to the zinc-aluminum-magnesium coating to be predicted includes: The original analytical data of the zinc-aluminum-magnesium coating to be predicted is mapped to a feature space consistent with the zinc-aluminum-magnesium coating sample to obtain a temporary feature identifier of the zinc-aluminum-magnesium coating to be predicted. The temporary feature identifier is compared with the standard feature identifier in the corrosion resistance knowledge graph in multiple dimensions to obtain candidate similar nodes of the zinc-aluminum-magnesium coating to be predicted. Based on the topology of the corrosion resistance knowledge graph, the candidate similar nodes are expanded to obtain the associated nodes of the zinc-aluminum-magnesium coating to be predicted. The confidence level of the associated nodes is evaluated, and nodes with high confidence levels are selected as similar sample nodes for the zinc-aluminum-magnesium coating to be predicted.

6. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The step of connecting the similar sample nodes into the relationship path for predicting the zinc-aluminum-magnesium coating includes: Based on the spatial distribution of the similar sample nodes in the corrosion resistance knowledge graph, an initial path framework for the zinc-aluminum-magnesium coating to be predicted is established. Based on the similarity of the similar sample nodes and the correlation between the corrosion resistance level in the corrosion resistance knowledge graph, the paths in the initial path framework are prioritized to obtain the priority path framework for the zinc-aluminum-magnesium coating to be predicted. A multi-path search strategy is adopted to explore the priority path framework and obtain candidate paths for the zinc-aluminum-magnesium coating to be predicted. The coherence of the candidate paths is verified to obtain the relationship path of the zinc-aluminum-magnesium coating to be predicted.

7. The method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings as described in claim 1, characterized in that, The process of traversing the relationship path to obtain the predicted corrosion resistance level of the zinc-aluminum-magnesium coating includes: Starting from the starting node of the relationship path, the similar sample nodes are traversed preferentially according to the path weight of the relationship path to obtain the corrosion resistance level characteristics of the similar sample nodes. By integrating the corrosion resistance level features and eliminating feature conflicts between similar sample nodes, the corrosion resistance level feature set of the zinc-aluminum-magnesium coating to be predicted is obtained. Trend analysis is performed on the corrosion resistance level feature set to obtain the predicted corrosion resistance level of the zinc-aluminum-magnesium coating to be predicted.

8. A system for predicting the corrosion resistance of zinc-aluminum-magnesium coatings, used to implement the method for predicting the corrosion resistance of zinc-aluminum-magnesium coatings according to claim 1, the system comprising: The data partitioning module is used to segment the microstructure image of the zinc-aluminum-magnesium coating sample into different analytical levels, and identify the data of different material regions in the analytical levels to obtain the structural partitioning data of the zinc-aluminum-magnesium coating sample. The feature coupling module is used to perform multidimensional coupling of the geometric morphological features and spatial distribution features in the structural partitioning data to obtain a comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample, including: The geometric descriptor of the zinc-aluminum-magnesium coating sample is obtained by parsing the region contour information in the structural partition data. Based on the regional spatial coordinates and spatial topology in the structural partitioning data, a regional relationship network of the zinc-aluminum-magnesium coating sample is constructed. Identify the regional distribution patterns in the regional relationship network to obtain the spatial distribution feature descriptor of the zinc-aluminum-magnesium coating sample; The geometric descriptor and the spatial distribution feature descriptor are standardized and integrated to obtain the geometric morphology feature set and spatial distribution feature set of the zinc-aluminum-magnesium coating sample; Tensor synthesis is performed on the geometric feature set and the spatial distribution feature set to obtain the geometric feature vector and spatial feature vector of the zinc-aluminum-magnesium coating sample; The geometric feature vector and the spatial feature vector are coupled to obtain the comprehensive feature value of the zinc-aluminum-magnesium coating sample. These comprehensive feature values ​​are then integrated to obtain the comprehensive morphological feature set of the zinc-aluminum-magnesium coating sample. The formula for calculating the comprehensive feature value is as follows: ; in, This represents the comprehensive feature value. Indicates the first The geometric feature vectors This represents the mean of the geometric feature vectors. Indicates the first The aforementioned spatial feature vectors The mean of the spatial feature vectors is represented. This represents the preset weighting coefficient. This represents the number of all feature vectors; The standard feature identifier generation module is used to fuse the chemical composition data of the zinc-aluminum-magnesium coating sample and the comprehensive morphological feature set, and to perform feature dimensionality reduction processing on the fused feature set to obtain the standard feature identifier of the zinc-aluminum-magnesium coating sample. The corrosion resistance map construction module is used to construct a corrosion resistance knowledge map of the zinc-aluminum-magnesium coating samples, with the standard feature identifiers as nodes and the correlation between the measured corrosion resistance levels in the zinc-aluminum-magnesium coating samples as edges. The similar node identification module is used to input the original analysis data of the zinc-aluminum-magnesium coating to be predicted into the corrosion resistance knowledge graph and identify similar sample nodes to the zinc-aluminum-magnesium coating to be predicted. The corrosion resistance level prediction module is used to connect the similar sample nodes into a relationship path for the zinc-aluminum-magnesium coating to be predicted, and to traverse and explore along the relationship path to obtain the corrosion resistance prediction level corresponding to the zinc-aluminum-magnesium coating to be predicted.

Images