Preparation method of high-strength calcium carbonate veneer

Abstract

The invention discloses a preparation method of a high-strength calcium carbonate veneer, and relates to the related field of building material preparation, and the method comprises the following steps: obtaining a target decoration panel diagram, and introducing a panel diagram significant evaluation plan to carry out significant evaluation analysis on the target decoration panel diagram to obtain a target significant block; marking the target significant block as a first-level significant block, and obtaining a first-level particle size strategy corresponding to the first-level significant block; screening a target calcium carbonate raw material of the target decoration panel diagram based on a first-level particle size strategy to obtain a first-level particle size raw material; performing global optimization analysis on the surface modification database by taking the first-level particle size raw material as a target optimization constraint to obtain an optimal modification strategy; and carrying out surface modification treatment on the first-grade particle size raw material according to the optimal modification strategy to obtain the target calcium carbonate veneer. The technical problems that existing calcium carbonate veneer preparation lacks high efficiency and is insufficient in accuracy are solved, and the technical effect of improving the calcium carbonate veneer preparation efficiency, accuracy and product process management capacity is achieved.

Description

Technical Field

[0001] The present application relates to the field of building material preparation, and in particular to a method for preparing a high-strength calcium carbonate decorative panel. Background Art

[0002] In the field of building decoration materials, calcium carbonate decorative panels are highly favored due to their good physical properties, beautiful appearance and environmental protection characteristics. The traditional preparation process of calcium carbonate decorative panels relies on manual experience and trial and error. During the preparation process, the ratio of raw materials, the selection of particle size and modification treatment rely on experience and judgment, and lack of precise control means, which not only leads to low production efficiency, but also makes it difficult to ensure the consistency of product quality. Therefore, there is an urgent need for an efficient and accurate preparation method that can optimize the design and production of calcium carbonate decorative panels according to decorative requirements.

[0003] In the current related technologies, the preparation of high-strength calcium carbonate decorative panels has technical problems such as lack of efficiency and insufficient precision. Summary of the invention

[0004] The present application provides a method for preparing high-strength calcium carbonate decorative panels, and adopts technical means such as obtaining a target decorative panel image, conducting a significant evaluation analysis, obtaining a primary particle size strategy, screening primary particle size raw materials, performing a global optimization analysis to obtain an optimal modification strategy, and surface modification treatment, thereby achieving the technical effect of improving the efficiency, accuracy, and product process management capabilities of the preparation of calcium carbonate decorative panels.

[0005] The present application provides a method for preparing a high-strength calcium carbonate decorative panel, comprising: obtaining a target decorative panel diagram, and introducing a panel diagram significance evaluation plan to perform significance evaluation analysis on the target decorative panel diagram to obtain a target significant block; recording the target significant block as a primary significance, and obtaining a primary particle size strategy corresponding to the primary significance; screening a target calcium carbonate raw material of the target decorative panel diagram based on the primary particle size strategy to obtain a primary particle size raw material; taking the primary particle size raw material as a target optimization constraint, performing a global optimization analysis on a surface modification database to obtain an optimal modification strategy; performing surface modification treatment on the primary particle size raw material according to the optimal modification strategy to obtain a target calcium carbonate decorative panel.

[0006] In a possible implementation, a target decorative panel image is obtained, and a panel image significance evaluation plan is introduced to perform significance evaluation analysis on the target decorative panel image to obtain a target significant block, and the following processing is performed: the target decorative panel image is segmented into blocks to obtain a segmentation result, wherein the segmentation result includes multiple blocks; a predetermined spatial dimension in the panel image significance evaluation plan is extracted; spatial features of a first block among the multiple blocks are collected based on the predetermined spatial dimension to obtain a first spatial feature; a predetermined center-surrounding difference quantization mechanism is read, and a difference quantization analysis is performed on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient; the multiple blocks are sorted in descending order based on the first difference coefficient to obtain a target difference coefficient; and the block corresponding to the target difference coefficient is recorded as the target significant block.

[0007] In a possible implementation, the following processing is performed: the predetermined spatial dimension includes a color dimension, a brightness dimension, and a direction dimension, and the color dimension includes a red dimension, a green dimension, and a blue dimension.

[0008] In a possible implementation, a predetermined center-surrounding difference quantization mechanism is read, and a difference quantization analysis is performed on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient, and the following processing is performed: a first surrounding block set of the first block is obtained, the first surrounding block set includes M surrounding blocks, and M is an integer greater than or equal to 2 and less than or equal to 4; a first surrounding block among the M surrounding blocks is extracted, and a first surrounding spatial feature of the first surrounding block is collected and obtained; according to the predetermined center-surrounding difference quantization mechanism, an average of the first difference values ​​obtained by normalizing and weighting the first surrounding spatial feature and the first difference feature between the first spatial feature is recorded as the first difference coefficient.

[0009] In a possible implementation, the following processing is also performed: extracting any block from the multiple blocks; performing similarity calculation on any spatial feature of the arbitrary block and the target spatial feature of the target significant block to obtain any similarity; judging whether the arbitrary similarity is within a predetermined similarity threshold; if the arbitrary similarity is within the predetermined similarity threshold, recording the arbitrary block as secondary significance, and screening the target calcium carbonate raw material according to the secondary particle size strategy corresponding to the secondary significance to obtain a secondary particle size raw material; and performing global optimization using the secondary particle size raw material as the target optimization constraint.

[0010] In a possible implementation, the following processing is performed: if the arbitrary similarity is not within the predetermined similarity threshold, the arbitrary block is recorded as the third-level significance, and the target calcium carbonate raw material is screened according to the third-level particle size strategy corresponding to the third-level significance to obtain the third-level particle size raw material, and the third-level particle size raw material is used as the target optimization constraint for global optimization.

[0011] In a possible implementation, taking the primary particle size raw material as the target optimization constraint, performing a global optimization analysis on the surface modification database to obtain the optimal modification strategy, and performing the following processing: extracting a first data group from the surface modification database, wherein the first data group includes a first calcium carbonate particle size; when the first calcium carbonate particle size meets the target optimization constraint, adding the first data group to the target optimization space; reading a modification fitness evaluation function, and using the modification fitness evaluation function as a target optimization evaluation index; performing a global optimization analysis on the target optimization space based on the target optimization evaluation index to obtain the optimal modification strategy.

[0012] In a possible implementation, the following processing is performed: the expression of the modified fitness evaluation function is as follows: ; in, refers to the modified fitness, , , , and These refer to the dispersion, oil absorption, compatibility, gloss and transparency of the modified calcium carbonate raw materials. , , , and are weight coefficients, and .

[0013] In a possible implementation, a global optimization analysis is performed on the target optimization space based on the target optimization evaluation index to obtain the optimal modification strategy, and the following processing is performed: randomly obtaining any data group in the target optimization space; calculating any modified features in the arbitrary data group according to the target optimization evaluation index to obtain any fitness; iterative optimization is performed with the maximum of the arbitrary fitness as the goal to obtain the target data group corresponding to the target fitness; and the target modification strategy in the target data group is used as the optimal modification strategy.

[0014] A method for preparing a high-strength calcium carbonate decorative panel proposed in this application first obtains a target decorative panel image, and introduces a panel image significance evaluation plan to perform a significance evaluation analysis on the target decorative panel image to obtain a target significant block, then records the target significant block as a first-level significance, and obtains a first-level particle size strategy corresponding to the first-level significance, then screens the target calcium carbonate raw material of the target decorative panel image based on the first-level particle size strategy to obtain a first-level particle size raw material, and then uses the first-level particle size raw material as a target optimization constraint to perform a global optimization analysis on the surface modification database to obtain the optimal modification strategy, and finally performs surface modification on the first-level particle size raw material according to the optimal modification strategy to obtain the target calcium carbonate decorative panel, thereby achieving the technical effect of improving the efficiency and accuracy of the preparation of calcium carbonate decorative panels and the product process management capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic flow chart of a method for preparing a high-strength calcium carbonate decorative panel provided in an embodiment of the present application.

[0017] Figure 2 A schematic diagram of a process for significantly evaluating and analyzing a target decorative panel image in a method for preparing a high-strength calcium carbonate decorative panel provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application provides a method for preparing a high-strength calcium carbonate decorative panel. Figure 1 As shown, the method includes: Step S100, obtaining a target decorative panel image, and introducing a panel image significant evaluation plan to perform significant evaluation analysis on the target decorative panel image to obtain a target significant block.

[0022] Specifically, an image file containing the desired decorative effect is received from a client or designer. This image file may be a high-definition photo, a vector image, or any format that can clearly show the decorative intent. A panel image saliency assessment plan is introduced, which is a set of predefined rules or algorithms for evaluating salient areas in an image. These rules can be based on a variety of factors such as color contrast, texture complexity, spatial frequency, etc. For example, a saliency assessment method can be based on a visual attention model, which calculates the saliency value of each pixel in the image and then determines which areas are salient based on these values. The target decorative panel image is saliency assessed using the plan to determine the most eye-catching blocks in the image, specifically including dividing the image into multiple small blocks, calculating the saliency value for each block, and then sorting them according to these values. Finally, the block with the highest saliency value is selected as the target salient block.

[0023] like Figure 2As shown, in a possible implementation, a target decorative panel image is obtained, and a panel image significant evaluation plan is introduced to perform significant evaluation analysis on the target decorative panel image to obtain a target significant block, and step S100 further includes step S110, performing block segmentation on the target decorative panel image to obtain a segmentation result, wherein the segmentation result includes multiple blocks. Specifically, the target decorative panel image is segmented into blocks so that each block can be subsequently significantly evaluated. Block segmentation can be performed in a variety of ways, such as adaptive segmentation based on image content, fixed-size grid segmentation, etc. For example, an adaptive image segmentation algorithm is used, which can automatically determine the block boundaries based on features such as color and texture in the image, thereby obtaining multiple blocks of different sizes and shapes.

[0024] Step S120, extracting the predetermined spatial dimensions in the panel image saliency assessment plan. Specifically, in the panel image saliency assessment plan, some spatial dimensions for assessing image saliency are defined, such as color contrast, texture complexity, directionality, etc. These predetermined spatial dimensions are extracted from the plan and used to collect spatial features of the blocks.

[0025] Step S130, based on the predetermined spatial dimension, spatial features are collected for the first block among the multiple blocks to obtain a first spatial feature. Specifically, spatial features are collected for each block (first block) obtained by segmentation, and feature values ​​of the block in each predetermined spatial dimension are calculated. For example, if the predetermined spatial dimension includes color contrast and texture complexity, the feature values ​​of the first block in these two dimensions need to be calculated respectively.

[0026] Step S140, read a predetermined center-surrounding difference quantization mechanism, and perform a difference quantization analysis on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient. Specifically, read a predetermined center-surrounding difference quantization mechanism, which is used to quantify the degree of difference between a block and its surrounding environment. The difference quantification analysis includes calculating the difference values ​​between the block and the surrounding blocks in terms of color, texture, etc., and obtaining a difference coefficient based on these difference values. For example, a statistically based difference quantification method can be used, which can accurately quantify the degree of difference between the block and the surrounding environment.

[0027] Step S150, the plurality of blocks are sorted in descending order based on the first difference coefficient to obtain a target difference coefficient. Specifically, the blocks are sorted in descending order based on the difference coefficient of each block obtained in step S140, that is, the block with the largest difference coefficient is arranged in front, and the block with the smallest difference coefficient is arranged in the back, and the target difference coefficient is the difference coefficient that is ranked first.

[0028] Step S160, record the block corresponding to the target difference coefficient as the target significant block. Specifically, the block with the largest difference coefficient is the target significant block, and the target significant block is the most eye-catching and visually impactful part of the image. This implementation method accurately quantifies the significance of each block through steps such as block segmentation, spatial feature collection, and difference quantitative analysis, ensuring that the final calcium carbonate decorative panel can be consistent with the target decorative panel image in terms of visual effect.

[0029] In a possible implementation, step S120 further includes step S121, the predetermined spatial dimension includes a color dimension, a brightness dimension, and a direction dimension, and the color dimension includes a red dimension, a green dimension, and a blue dimension.

[0030] Specifically, the RGB color space is used to represent color, which consists of three components: red (R), green (G), and blue (B), and the value range of each component is 0 to 255. The color dimension includes red dimension, green dimension, and blue dimension, which correspond to the three components R, G, and B in the RGB color space respectively.

[0031] In the RGB color space, brightness can be obtained by calculating the weighted sum of the three components R, G, and B (for example, common weighting coefficients are 0.299, 0.587, and 0.114, corresponding to the R, G, and B components, respectively). You can also directly use a color component (such as the green component G, because the human eye is most sensitive to green) or the average value of the R, G, and B components as a measure of brightness.

[0032] The directional dimension is used to describe the directionality of texture or edges in an image, and can be obtained by calculating the image gradient (such as Sobel operator, Prewitt operator, etc.). The gradient is a vector whose magnitude indicates the rate of change of the image at that point, and its direction indicates the direction of the fastest change.

[0033] The color dimension can capture the color features in the image, the brightness dimension can reflect the changes in brightness and darkness of the image, and the direction dimension can describe the texture or edge directionality in the image. This implementation method improves the accuracy of image saliency assessment by combining these predetermined spatial dimensions for spatial feature collection, providing a reliable basis for subsequent particle size strategy selection and surface modification treatment.

[0034] In a possible implementation, a predetermined center-surrounding difference quantization mechanism is read, and a difference quantization analysis is performed on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient. Step S140 further includes step S141, obtaining a first surrounding block set of the first block, wherein the first surrounding block set includes M surrounding blocks, and M is an integer greater than or equal to 2 and less than or equal to 4. Specifically, a surrounding block set of the first block is determined, and these surrounding blocks are used to compare with the first block to quantify its significance. In a specific implementation, the adjacent blocks above, below, left and right of the first block can be selected as surrounding blocks according to the position of the first block in the image. The number of surrounding blocks M selected can be determined according to actual needs, wherein the value range of M is 2 to 4, which can balance the computational complexity and the accuracy of the significance evaluation. For example, if M=4, four adjacent blocks above, below, left and right of the first block can be selected as the first surrounding block set. If the image is two-dimensional and the tiles are arranged in a grid, then these surrounding tiles can be found by determining the row and column indices of the first tile and then calculating the row and column indices of its neighboring tiles.

[0035] Step S142: extract the first surrounding block from the M surrounding blocks, and collect the first surrounding spatial features of the first surrounding block. Specifically, collect spatial features for each first surrounding block, and these features are consistent with the spatial features of the first block collected in step S130.

[0036] Step S143, according to the predetermined center-surrounding difference quantization mechanism, the first difference value obtained by normalizing and weighting the first difference feature between the first surrounding spatial feature and the first spatial feature is recorded as the first difference coefficient. Specifically, since the dimensions and value ranges of different features are different, the features need to be normalized before the difference calculation so that they have the same scale. The normalization method can be linear normalization, logarithmic normalization, etc. Different features have different effects on significance, and this difference is reflected by weighting, and the weight is determined according to the experimental results. After normalization and weighting, the difference value between the first block and each of its surrounding blocks is calculated, and this difference value can be a metric such as Euclidean distance, Manhattan distance, cosine similarity, etc. Then, the mean of these difference values ​​is calculated as the first difference coefficient. This implementation method not only considers the spatial features within the block, but also considers the relative relationship between the blocks by comparing the differences in spatial features between the first block and its surrounding blocks, thereby accurately evaluating the significance of the first block.

[0037] Step S200: record the target salient block as primary salient, and obtain a primary particle size strategy corresponding to the primary salient.

[0038] Specifically, the target salient block is marked as primary salient, that is, the salient block identified as the highest level in the salient assessment. A primary particle size strategy is obtained. The primary particle size strategy is a preset rule or data set that defines the optimal particle size distribution of the calcium carbonate raw material corresponding to the primary salient block. This strategy is based on experimental data. For example, if the primary salient block contains a large amount of fine details, a smaller particle size needs to be selected to retain these details.

[0039] Step S300, screening the target calcium carbonate raw material of the target decorative panel diagram based on the primary particle size strategy to obtain the primary particle size raw material.

[0040] Specifically, a batch of calcium carbonate raw materials are prepared as candidates for screening, i.e., target calcium carbonate raw materials, which can come from different suppliers, batches or production processes. According to the obtained primary particle size strategy, the target calcium carbonate raw materials are screened, including measuring the size distribution, shape and uniformity of the raw material particles, and comparing them with the optimal particle size distribution defined in the primary particle size strategy. Only raw materials that meet or are close to the optimal particle size distribution will be selected as primary particle size raw materials.

[0041] Step S400, taking the primary particle size raw material as the target optimization constraint, performing global optimization analysis on the surface modification database to obtain the optimal modification strategy.

[0042] Specifically, the obtained primary particle size raw materials are used as constraints for global optimization analysis, that is, the characteristics of these raw materials, such as particle size distribution, chemical composition, etc., must be considered when searching for the optimal modification strategy. Prepare a database containing a variety of modification methods and conditions, which include chemical reactions, physical treatments, or a combination of both, to improve the properties of calcium carbonate raw materials, such as improving strength, weather resistance, or processability. Use a global optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) to search the surface modification database to find the optimal modification strategy that meets the primary particle size raw material constraints. This process includes multiple iterations and evaluations until a modification strategy that meets all conditions and has the best performance is found.

[0043] In a possible implementation, the primary particle size raw material is used as the target optimization constraint, and a global optimization analysis is performed on the surface modification database to obtain the optimal modification strategy. Step S400 further includes step S410, extracting the first data group in the surface modification database, wherein the first data group includes the first calcium carbonate particle size. Specifically, data is extracted from a pre-established surface modification database, which contains data on a variety of calcium carbonate particle sizes and corresponding modification strategies and their effects. The first data group is a subset in the database, which at least contains the key information of the first calcium carbonate particle size. In addition, detailed information such as the type of modifier, the amount of modifier, and the modification conditions related to the particle size is also included.

[0044] Step S420, when the first calcium carbonate particle size meets the target optimization constraint, the first data set is added to the target optimization space. Specifically, it is determined whether the calcium carbonate particle size in the extracted first data set is consistent with the particle size of the primary particle size raw material obtained in step S300. If it is consistent, the data set is added to the target optimization space, which is a space or set for storing data sets that meet the constraints to perform global optimization analysis.

[0045] Step S430, read the modified fitness evaluation function, and use the modified fitness evaluation function as the target optimization evaluation index. Specifically, read the predefined modified fitness evaluation function, which is used to evaluate the performance of the calcium carbonate veneer under different modification strategies. The modified fitness evaluation function can be based on a variety of factors, such as the strength, wear resistance, weather resistance, etc. of the calcium carbonate veneer.

[0046] Step S440, based on the target optimization evaluation index, a global optimization analysis is performed on the target optimization space to obtain the optimal modification strategy. Specifically, a global optimization analysis is performed on the data in the target optimization space, that is, a global optimization algorithm is used to compare and evaluate multiple modification strategies, and the optimal modification strategy is found through iteration and search according to the result of the modification fitness evaluation function. This implementation method can quickly find the optimal modification strategy through global optimization analysis, thereby shortening the preparation time and improving production efficiency. The optimal modification strategy can optimize the performance of the calcium carbonate veneer, thereby meeting the user's requirements for product quality.

[0047] In a possible implementation, step S430 further includes step S431, and the expression of the modified fitness evaluation function is as follows: ; in, refers to the modified fitness, , , , and These refer to the dispersion, oil absorption, compatibility, gloss and transparency of the modified calcium carbonate raw materials. , , , and are weight coefficients, and .

[0048] Specifically, the modification fitness evaluation function is used to quantitatively evaluate the performance of calcium carbonate raw materials under different modification strategies. Modification fitness is an indicator of comprehensive evaluation. Dispersion refers to the uniformity of the dispersion of calcium carbonate raw materials in the medium, which affects the uniformity and stability of the final product; the oil absorption value indicates the ability of calcium carbonate raw materials to absorb oil and fat, which is related to the particle size, shape and surface properties of the raw materials; compatibility refers to the compatibility of calcium carbonate raw materials when mixed with other materials (such as resins, plastics, etc.), which affects the physical and chemical properties of the final product; gloss refers to the reflective ability of the surface of the calcium carbonate veneer, which affects the appearance quality of the product; transparency refers to the ability of the calcium carbonate veneer to transmit light, which affects the transparency and visual effect of the product. The weight coefficient is used to adjust the relative importance of each performance indicator in the comprehensive evaluation, and is set according to actual application requirements and professional knowledge. During execution, for each calcium carbonate raw material under a modification strategy, its dispersion, oil absorption value, compatibility, gloss and transparency are measured, and these values ​​are substituted into the above evaluation function to calculate the corresponding modification fitness. Then, the performance of different modification strategies is compared based on these modification fitness values, so as to select the optimal modification strategy. This implementation method can comprehensively and objectively evaluate the performance of calcium carbonate raw materials under different modification strategies by defining a modification fitness evaluation function containing multiple performance indicators, thus avoiding the one-sidedness of single indicator evaluation.

[0049] In a possible implementation, the target optimization space is globally optimized based on the target optimization evaluation index to obtain the optimal modification strategy, and step S440 further includes step S441, randomly obtaining any data group in the target optimization space. Specifically, the target optimization space contains all modification strategy data groups that may meet the primary particle size constraint, and a data group in the target optimization space is randomly selected by programming using a random number generator, and this data group contains all relevant information about the modification strategy, such as the type of modifier, the amount of modifier, the modification temperature, the modification time, etc.

[0050] Step S442, calculate any modified feature in the arbitrary data set according to the target optimization evaluation index to obtain any fitness. Specifically, calculate the modification strategy in the selected data set according to a predefined modification fitness evaluation function to obtain its corresponding fitness value, which comprehensively considers multiple modified features and their relative importance.

[0051] Step S443, iterative optimization is performed with the maximum arbitrary fitness as the goal, and a target data group corresponding to the target fitness is obtained. Specifically, in the programming implementation, a loop is set, and each loop attempts to find a data group with a higher fitness. This can be achieved through operations such as mutation, crossover, and selection. When the loop reaches a preset number of iterations or the fitness converges to a certain threshold, it is considered that the optimal or approximately optimal solution has been found.

[0052] Step S444, taking the target modification strategy in the target data group as the optimal modification strategy. Specifically, after the iterative optimization process is completed, a data group with the highest fitness is obtained, and the modification strategy in this data group is the optimal modification strategy to be found. The optimal modification strategy is saved and used to perform surface modification on the primary particle size raw material to obtain a high-strength calcium carbonate veneer. This implementation method ensures that there is a chance to find the global optimal solution by randomly selecting a data group as the starting point and searching in the entire target optimization space. Even in the worst case, a near-optimal solution can be found.

[0053] Step S500, performing surface modification treatment on the primary particle size raw material according to the optimal modification strategy to obtain a target calcium carbonate decorative panel.

[0054] Specifically, according to the optimal modification strategy obtained, the surface modification treatment is performed on the primary particle size raw materials screened, for example, the raw materials are exposed to specific chemical reagents, temperature, pressure or radiation conditions to change their surface properties. The modified raw materials are used to prepare the final calcium carbonate decorative panels, including a series of processing techniques such as mixing, molding, and curing the raw materials. The embodiment of the present application adopts technical means such as obtaining the target decorative panel map, performing significant evaluation analysis, obtaining the primary particle size strategy, screening the primary particle size raw materials, global optimization analysis to obtain the optimal modification strategy and surface modification treatment, so as to achieve the technical effect of improving the efficiency, accuracy and product process management capabilities of the preparation of calcium carbonate decorative panels.

[0055] In a possible implementation, the method further includes step S600, extracting any block from the plurality of blocks. Specifically, using image processing software or an algorithm to traverse the block set generated by step S110. Through programming logic (such as a loop statement), these blocks are extracted one by one.

[0056] Step S700, performing similarity calculation on the arbitrary spatial features of the arbitrary block and the target spatial features of the target salient block to obtain arbitrary similarity. Specifically, the same feature extraction process as in step S130 is performed on the arbitrary block extracted in step S600. The similarity between the arbitrary spatial features and the target spatial features is calculated using a similarity metric (such as cosine similarity, Euclidean distance, etc.).

[0057] Step S800, determining whether the arbitrary similarity is within a predetermined similarity threshold. Specifically, the calculated arbitrary similarity is compared with a predetermined similarity threshold, which is set based on experimental data to determine when the similarity of two blocks is high enough to be considered similar.

[0058] Step S900, if the arbitrary similarity is within the predetermined similarity threshold, the arbitrary block is marked as secondary significant, and the target calcium carbonate raw material is screened according to the secondary particle size strategy corresponding to the secondary significant, to obtain the secondary particle size raw material. Specifically, if step S800 determines that the similarity is above the predetermined threshold, the current block is marked as secondary significant. Then, the secondary particle size strategy associated with this secondary significant block is searched, and this strategy is used to screen the target calcium carbonate raw material.

[0059] Step S1000, a global optimization is performed using the secondary particle size raw material as the target optimization constraint. Specifically, a global optimization algorithm is used to search for the optimal surface modification strategy, and this search process is constrained by the characteristics of the secondary particle size raw material. The algorithm tries different combinations of modification strategies until the optimal strategy that meets specific performance requirements is found. This implementation method can more finely control the particle size and modification strategy of different areas by introducing block similarity analysis and secondary significant blocks, ensuring that each block is properly treated according to its importance, thereby improving the overall quality and consistency of the veneer.

[0060] In a possible implementation, the method further includes step S1100, if the arbitrary similarity is not within the predetermined similarity threshold, the arbitrary block is recorded as the third-level significance, and the target calcium carbonate raw material is screened according to the third-level particle size strategy corresponding to the third-level significance to obtain the third-level particle size raw material, and the third-level particle size raw material is used as the target optimization constraint for global optimization.

[0061] Specifically, through programming logic, such as using conditional statements (such as if-else), according to the judgment result of step S800, those blocks whose similarity does not reach the predetermined threshold are marked as three-level significant blocks. Then, a corresponding particle size strategy is selected for each three-level significant block, and the target calcium carbonate raw material is screened using the selected three-level particle size strategy to obtain raw materials suitable for these three-level significant blocks. Finally, these three-level particle size raw materials are used as target optimization constraints, and a global optimization analysis is performed on the surface modification database to find the best surface modification strategy to optimize the performance of these three-level significant blocks, such as improving strength, wear resistance or stain resistance. This implementation method can better meet the functional and visual requirements of decorative panels in different areas by subdividing the significant levels of blocks and selecting appropriate particle size strategies and surface modification strategies for each level. For those blocks with lower importance (such as three-level significant blocks), raw materials and modification strategies with lower cost and moderate performance can be selected, thereby reducing costs without sacrificing overall performance.

[0062] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for preparing a high-strength calcium carbonate decorative panel, characterized in that: include: Obtain a target decorative panel image, and introduce a panel image significant assessment plan to perform significant assessment analysis on the target decorative panel image to obtain a target significant block; Recording the target significant block as primary significant, and obtaining a primary particle size strategy corresponding to the primary significant; Screening the target calcium carbonate raw material of the target decorative panel diagram based on the primary particle size strategy to obtain a primary particle size raw material; Taking the primary particle size raw material as the target optimization constraint, a global optimization analysis is performed on the surface modification database to obtain the optimal modification strategy; The primary particle size raw material is subjected to surface modification treatment according to the optimal modification strategy to obtain a target calcium carbonate decorative panel.

2. The method for preparing a high-strength calcium carbonate decorative panel according to claim 1, characterized in that: Obtain a target decorative panel image, and introduce a panel image significant assessment plan to perform significant assessment analysis on the target decorative panel image to obtain target significant blocks, including: Performing block segmentation on the target decorative panel image to obtain a segmentation result, wherein the segmentation result includes a plurality of blocks; Extracting predetermined spatial dimensions in the panel chart significant assessment plan; Collecting spatial features of a first block among the multiple blocks based on the predetermined spatial dimension to obtain a first spatial feature; Reading a predetermined center-surrounding difference quantization mechanism, and performing a difference quantization analysis on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient; The plurality of blocks are sorted in descending order based on the first difference coefficient to obtain a target difference coefficient; The block corresponding to the target difference coefficient is recorded as the target significant block.

3. The method for preparing a high-strength calcium carbonate decorative panel according to claim 2, characterized in that: The predetermined spatial dimensions include a color dimension, a brightness dimension, and a direction dimension, and the color dimension includes a red dimension, a green dimension, and a blue dimension.

4. The method for preparing a high-strength calcium carbonate decorative panel according to claim 2, characterized in that: Reading a predetermined center-surrounding difference quantization mechanism, and performing a difference quantization analysis on the first spatial feature according to the predetermined center-surrounding difference quantization mechanism to obtain a first difference coefficient, including: Acquire a first surrounding block set of the first block, where the first surrounding block set includes M surrounding blocks, and M is an integer greater than or equal to 2 and less than or equal to 4; Extracting a first surrounding block from the M surrounding blocks, and collecting first surrounding space features of the first surrounding block; According to the predetermined center-surrounding difference quantization mechanism, an average of the first difference values ​​obtained by normalizing and weighting the first difference feature between the first surrounding spatial feature and the first spatial feature is recorded as the first difference coefficient.

5. The method for preparing a high-strength calcium carbonate decorative panel according to claim 2, characterized in that: Also includes: Extracting any block from the plurality of blocks; Performing similarity calculation on any spatial feature of the arbitrary block and the target spatial feature of the target salient block to obtain any similarity; Determining whether any similarity is within a predetermined similarity threshold; If the arbitrary similarity is within the predetermined similarity threshold, the arbitrary block is recorded as secondary significance, and the target calcium carbonate raw material is screened according to the secondary particle size strategy corresponding to the secondary significance to obtain the secondary particle size raw material; The secondary particle size raw material is used as the target optimization constraint for global optimization.

6. The method for preparing a high-strength calcium carbonate decorative panel according to claim 5, characterized in that: If any similarity is not within the predetermined similarity threshold, the arbitrary block is recorded as level 3 significance, and the target calcium carbonate raw material is screened according to the level 3 particle size strategy corresponding to the level 3 significance to obtain level 3 particle size raw material, and the level 3 particle size raw material is used as the target optimization constraint for global optimization.

7. The method for preparing a high-strength calcium carbonate decorative panel according to claim 1, characterized in that: Taking the primary particle size raw material as the target optimization constraint, a global optimization analysis is performed on the surface modification database to obtain the optimal modification strategy, including: extracting a first data set from the surface modification database, wherein the first data set includes a first calcium carbonate particle size; When the first calcium carbonate particle size meets the target optimization constraint, adding the first data group to the target optimization space; Reading a modified fitness evaluation function, and using the modified fitness evaluation function as a target optimization evaluation index; Based on the target optimization evaluation index, a global optimization analysis is performed on the target optimization space to obtain the optimal modification strategy.

8. The method for preparing a high-strength calcium carbonate decorative panel according to claim 7, characterized in that: The expression of the modified fitness evaluation function is as follows: ； in, refers to the modified fitness, , , , and These refer to the dispersion, oil absorption, compatibility, gloss and transparency of the modified calcium carbonate raw materials. , , , and are weight coefficients, and .

9. The method for preparing a high-strength calcium carbonate decorative panel according to claim 7, characterized in that: Based on the target optimization evaluation index, a global optimization analysis is performed on the target optimization space to obtain the optimal modification strategy, including: Randomly obtain any data group in the target optimization space; Calculating any modified feature in the arbitrary data set according to the target optimization evaluation index to obtain any fitness; Iterative optimization is performed with the maximum arbitrary fitness as the goal to obtain a target data group corresponding to the target fitness; The target modification strategy in the target data set is used as the optimal modification strategy.

Images