Intelligent cutting method and system for sponge processing

Abstract

The invention relates to an intelligent cutting method and system for sponge processing, and relates to the technical field of sponge production.The method comprises the steps that a sponge surface image is obtained; determining a sponge placement model according to each sponge surface image, and determining surface defect features and surface defect positions in the sponge placement model; generating a random number of demand product models, placing the demand product models in the sponge placement model, and generating a product processing scheme according to placement conditions corresponding to the demand product models; defining an effective processing scheme in each product processing scheme; defining the number of required product models in the effective processing scheme as an actual production number, and defining a use processing scheme according to the actual production number; single cutting paths are determined according to the contour line of the demand product model in the use machining scheme, an overall cutting path is determined according to all the single cutting paths, and a cutting tool is controlled to conduct cutting operation along the overall cutting path. The method has the effect of improving the qualified rate of final sponge finished products.

Description

Technical Field

[0001] The present application relates to the field of sponge production technology, and in particular to an intelligent cutting method and system for sponge processing. Background Art

[0002] In the field of sponge processing, CNC cutting machines are widely used to cut foamed sponge blocks into finished products of specific shapes.

[0003] At present, the traditional CNC sponge cutting method mainly relies on workers to plan the cutting path in computer-aided design (CAD) software in advance and import the program into the cutting machine control system so that the equipment can perform cutting operations according to the established trajectory.

[0004] However, since the cutting program of this method is pre-set, once the sponge blank has defects such as bubbles, uneven density or foreign impurities in the cutting area, the cutting machine will still execute according to the original path, resulting in a lower pass rate of the final product and even material waste. There is still room for improvement. Summary of the Invention

[0005] In order to improve the qualification rate of the final sponge product, the present application provides an intelligent cutting method and system for sponge processing.

[0006] In a first aspect, the present application provides an intelligent cutting method for sponge processing, which adopts the following technical solutions:

[0007] An intelligent cutting method for sponge processing, comprising:

[0008] Get the area placement status of the preset sponge placement area;

[0009] When the regional placement state is consistent with the preset in-place placement state, the required product model is obtained and the preset image capturing device is controlled to move along the preset image capturing path to obtain the sponge surface image;

[0010] Performing three-dimensional modeling processing based on each sponge surface image to determine a sponge placement model, performing feature recognition in the sponge placement model to determine surface defect features, and determining the surface defect location based on the surface defect features;

[0011] Generate a random number of demand product models and place them in the sponge placement model, and generate product processing plans based on the placement conditions corresponding to each demand product model;

[0012] In each product processing plan, a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect location is defined as a valid processing plan;

[0013] The number of required product models in the effective processing plan is defined as the actual production quantity, and the effective processing plan corresponding to the actual production quantity with the largest value is defined as the used processing plan;

[0014] The individual cutting paths are determined according to the contour lines of the required product model in the processing plan, and the overall cutting path is determined according to all the individual cutting paths, and the preset cutting tool is controlled to perform cutting operations along the overall cutting path.

[0015] Optionally, the step of generating a random number of demand product models and placing them in the sponge placement model includes:

[0016] Determine the overall model volume based on the sponge placement model, and determine the product model volume based on the required product model;

[0017] Calculate the upper limit of placement quantity based on the overall model volume and the product model volume;

[0018] Calculate the distance between any two surface defects based on their locations;

[0019] A surface defect position is randomly selected from all surface defect positions and defined as a central defect position. Surface defects whose distance from the central defect position is less than a preset mutual influence distance are summarized to form a monomer concentrated combination.

[0020] Re-determine the central defect position in the surface defect features outside the monomer concentration combination to determine the monomer concentration combination until all surface defect features are within the monomer concentration combination, and determine the feature concentration scheme based on each monomer concentration combination;

[0021] Counting the individual concentration combinations in each feature concentration scheme to determine the number of concentration combinations, and calculating the number of representative combinations based on all the concentration combination numbers;

[0022] The lower limit placement quantity is determined by calculating based on the upper limit placement quantity, the representative combination quantity and the preset loose fixing quantity;

[0023] The quantity generation range is determined based on the upper and lower limit placement quantities, and quantities are generated from top to bottom within the quantity generation range to place the required product model.

[0024] Optionally, the method further includes a step of determining a mutual influence distance, which includes:

[0025] Randomly select two points on the surface of the required product model to determine the distance between the contours;

[0026] The contour separation distance with the largest value is defined as the upper limit separation distance, and the upper limit proximity range is determined by calculation based on the upper limit separation distance and the preset proximity distance;

[0027] The points corresponding to the distances between the contours being within the upper limit are defined as impact points, and the impact points are counted to determine the number of surface impacts.

[0028] Count the surface points of the required product model to determine the number of product surfaces, and calculate the impact ratio based on the number of product surfaces and the number of surface impacts;

[0029] The influence coefficient corresponding to the influence ratio is determined according to the preset influence matching relationship, and the mutual influence distance is determined by calculation based on the influence coefficient and the upper limit distance.

[0030] Optionally, after the feature concentration solution is determined, the intelligent cutting method for sponge processing also includes:

[0031] Counting is performed according to each characteristic concentration scheme to determine the number of characteristic schemes;

[0032] Randomly select two surface defect features to combine to form a defect feature combination, and define the feature concentration scheme when the two surface defect features in the defect feature combination are in the same monomer concentration combination as the feature internal scheme;

[0033] Count the internal solutions of the features to determine the number of internal solutions, calculate the internal proportion based on the number of internal solutions and the number of feature solutions, and compare the internal proportion with the preset critical proportion to determine the relative status of the demand for the defect feature combination;

[0034] In a single feature concentration scheme, the actual relative state is determined based on each defect feature combination, and the defect feature combination whose actual relative state is consistent with the required relative state is defined as a high-quality combination, and the remaining defect feature combinations are defined as low-quality combinations;

[0035] Calculations are performed based on high-quality combinations and low-quality combinations to determine the high-quality ratio, and feature concentration solutions whose high-quality ratio is less than the preset demand ratio are eliminated.

[0036] Optionally, after the high-quality ratio is determined, the intelligent cutting method for sponge processing also includes:

[0037] Determine the reasonable boundary ratio based on the relative status of the requirements of each defect feature combination;

[0038] Calculate the reasonable compensation parameters based on the internal proportions of each high-quality portfolio and low-quality portfolio and the corresponding reasonable boundary proportions;

[0039] The quality ratio is updated by calculation based on reasonable compensation parameters and quality ratio.

[0040] Optionally, after the actual production quantity is determined, the intelligent cutting method for sponge processing also includes:

[0041] Determine whether there are at least two effective processing plans with the same and maximum actual production quantity;

[0042] If there are not at least two valid processing plans with the same actual production quantity and the largest actual production quantity, the valid processing plan corresponding to the largest actual production quantity is defined as the used processing plan;

[0043] If there are at least two effective processing plans with the same actual production quantity and the largest actual production quantity, the effective processing plan corresponding to the largest actual production quantity is defined as the alternative processing plan;

[0044] Determine the individual cutting paths in each alternative processing scheme, and randomly sort them according to the required product models to determine the model processing order;

[0045] Connecting the individual cutting paths according to the model processing sequence to form a simulation operation path, and determining the simulation operation distance according to the simulation operation path;

[0046] The alternative processing scheme corresponding to the simulated operation distance with the smallest value is defined as the used processing scheme, and the simulated operation path corresponding to the simulated operation distance with the smallest value is determined as the overall cutting path.

[0047] In a second aspect, the present application provides an intelligent cutting system for sponge processing, which adopts the following technical solutions:

[0048] An intelligent cutting system for sponge processing, comprising:

[0049] An acquisition module, used to obtain the area placement status of a preset sponge placement area;

[0050] A processing module, connected to the acquisition module and the judgment module, for storing and processing information;

[0051] The judgment module is connected with the acquisition module and the processing module and is used for judging the information;

[0052] When the judgment module determines that the regional placement state is consistent with the preset in-place placement state, the acquisition module acquires the required product model and causes the processing module to control the preset image capturing device to move along the preset image capturing path so that the acquisition module acquires the sponge surface image;

[0053] The processing module performs three-dimensional modeling processing based on each sponge surface image to determine a sponge placement model, performs feature recognition in the sponge placement model to determine surface defect features, and determines the surface defect location based on the surface defect features;

[0054] The processing module generates a random number of demand product models and places them in the sponge placement model, and generates a product processing plan based on the placement conditions corresponding to each demand product model;

[0055] The processing module defines, among the product processing plans, a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect position as a valid processing plan;

[0056] The processing module defines the number of required product models in the effective processing plan as the actual production quantity, and defines the effective processing plan corresponding to the actual production quantity with the largest value as the used processing plan;

[0057] The processing module determines a single cutting path according to the contour line of the required product model in the processing plan, determines an overall cutting path according to all the single cutting paths, and controls a preset cutting tool to perform cutting operations along the overall cutting path.

[0058] In a third aspect, the present application provides a computer storage medium capable of storing corresponding programs, which has the characteristics of improving the qualification rate of the final sponge product, and adopts the following technical solutions:

[0059] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned intelligent cutting methods for sponge processing.

[0060] In summary, this application includes at least one of the following beneficial technical effects:

[0061] 1. During the sponge product cutting process, defect analysis can be performed based on the state of the sponge before cutting to ensure that defects are avoided during the cutting process while achieving better product processing and improving the qualification rate of the final sponge product;

[0062] 2. During the analysis of product cutting quantity, the range of quantity can be determined to improve data analysis efficiency;

[0063] 3. Analyze the mutual influence between defects based on the distance between each defect, so as to improve the accuracy of subsequent quantity range determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of the intelligent cutting method for sponge processing.

[0065] Figure 2It is a module flow chart of the intelligent cutting method for sponge processing. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-Figure 2 It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0067] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0068] The present application discloses an intelligent cutting method for sponge processing, referring to Figure 1 The method flow of the intelligent cutting method for sponge processing includes the following steps:

[0069] Step S100: obtaining the area placement status of a preset sponge placement area.

[0070] The sponge placement area is an area on the cutting machine used to place unprocessed sponges and wait for the cutting tool to process them. The area placement status refers to whether there is a sponge to be processed placed on the sponge placement area, which can be obtained and determined by various sensors. The sponge is placed in the sponge placement area in a suspended state to facilitate data acquisition of images of each surface of the sponge.

[0071] Step S101: when the regional placement state is consistent with the preset in-place placement state, a required product model is obtained and a preset image capturing device is controlled to move along a preset image capturing path to capture a sponge surface image.

[0072] The in-place placement state is the placement state of the area when there is a sponge to be processed on the sponge placement area; the required product model is the model of the product to be processed, and the staff can input the data into drawing software such as CAD to obtain the data; the image shooting device is a device with an image shooting function, and the image shooting path is the path that the image shooting device travels when it can completely capture the surface of the sponge on the sponge placement area. The path is fixed, and the sponge surface image is the acquired image of the sponge surface.

[0073] Step S102: performing 3D modeling processing based on each sponge surface image to determine a sponge placement model, performing feature recognition in the sponge placement model to determine surface defect features, and determining the surface defect position based on the surface defect features.

[0074] The sponge placement model is a model of the sponge on the sponge placement area obtained after point cloud fusion processing of each sponge surface image; the surface defect feature is the defect feature existing on the sponge placement model. The specific recognition method can be achieved through prior multi-sample neural training to build a recognition database, and then the sponge surface image is input into the recognition database to determine the corresponding defect feature; the surface defect position is the actual position of the surface defect feature.

[0075] Step S103: Generate a random number of required product models and place them in the sponge placement model, and generate a product processing plan according to the placement conditions corresponding to each required product model.

[0076] The sponge cutting situation can be simulated by randomly generating a required product model and placing it in the sponge placement model. At this time, the specific placement situation is the product processing plan that reflects the product processing situation.

[0077] Step S104 : defining a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect position as a valid processing plan.

[0078] When there is no overlap of demand product models and no demand product model includes a surface defect position, it means that the products can be processed according to the designated placement positions of the demand product models, and all processed products have no defects, that is, the defects can be effectively avoided while processing is guaranteed. At this time, an effective processing plan is defined to distinguish different product processing plans for the convenience of subsequent analysis.

[0079] Step S105: defining the quantity of the required product models in the effective processing plan as the actual production quantity, and defining the effective processing plan corresponding to the actual production quantity with the largest value as the used processing plan.

[0080] The actual production quantity is defined to determine the number of products that can be produced in each plan. Therefore, by defining the processing plan, the effective technical plan that can produce the most products is marked to facilitate subsequent analysis.

[0081] Step S106: determining a single cutting path according to the contour line of the required product model in the processing plan, determining an overall cutting path according to all the single cutting paths, and controlling a preset cutting tool to perform cutting operations along the overall cutting path.

[0082] The single cutting path is the operating path of the cutting tool when it can perform better cutting processing on the required product model. The overall cutting path is the operating path that can process all required product models. At this time, the cutting tool is controlled to operate to ensure normal processing of the product.

[0083] The steps of generating a random number of demand product models and placing them in the sponge placement model include:

[0084] Step S200: determining the overall model volume according to the sponge placement model, and determining the product model volume according to the required product model.

[0085] The overall model volume is the volume of the sponge placement model, and the product model volume is the volume of the required product model.

[0086] Step S201: Calculate the upper limit of placement quantity based on the overall model volume and the product model volume.

[0087] The upper limit placement quantity is the maximum number of products that can be cut out under theoretical circumstances. It is obtained by dividing the overall model volume by the product model volume. The integer in the result is the upper limit placement quantity.

[0088] Step S202: performing calculation based on the positions of any two surface defects to determine the distance between the defects.

[0089] The defect separation distance is the straight-line distance between two surface defect locations.

[0090] Step S203: randomly selecting a surface defect position from all surface defect positions as a central defect position, and summarizing the surface defects whose distance from the central defect position is less than a preset mutual influence distance to form a monomer concentrated combination.

[0091] The central defect position is defined to distinguish different data; the mutual influence distance is the maximum defect distance allowed between two defects that are likely to be divided into the same model during the product model division process. The defect distribution is determined by unifying some similar defects into a single concentrated combination.

[0092] Step S204: re-determine the central defect position in the surface defect features outside the monomer concentration combination to determine the monomer concentration combination, until all surface defect features are within the monomer concentration combination, and then determine the feature concentration scheme according to each monomer concentration combination.

[0093] By continuously determining the central defect position to determine the monomer concentration combination, the defects can be effectively divided. At this time, the scheme formed by combining the monomer concentration combinations formed is the feature concentration scheme.

[0094] Step S205 : Counting individual concentration combinations in each feature concentration scheme to determine the number of concentration combinations, and performing calculation based on all the numbers of concentration combinations to determine the number of representative combinations.

[0095] The number of concentrated combinations is the number of determined monomer concentrated combinations, that is, the number of product models that will be affected. The representative combination number is the average number of concentrated combinations of all determined feature concentration schemes.

[0096] Step S206: performing calculations based on the upper limit placement quantity, the representative combination quantity, and the preset loose fixed quantity to determine the lower limit placement quantity.

[0097] The loose fixed quantity is a fixed quantity set by the staff. The lower limit placement quantity is obtained by subtracting the representative combination quantity and the loose fixed quantity from the upper limit placement quantity. The lower limit placement quantity is the minimum number of products that can be obtained under theoretical circumstances based on the specific distribution of defects in the current sponge.

[0098] Step S207: determining a quantity generation range according to the upper limit placement quantity and the lower limit placement quantity, and generating quantities from top to bottom in the quantity generation range to place the required product model.

[0099] By determining the quantity generation range, the required product model can be effectively generated and placed, thereby reducing the amount of data required for analysis and improving overall work efficiency. At the same time, analysis is performed based on the situation of a larger number of required product models to ensure that the processing plan can be determined more quickly.

[0100] The method further includes a step of determining a mutual influence distance, the step comprising:

[0101] Step S300: Randomly select two points on the surface of the required product model to determine the distance between the contours.

[0102] The contour separation distance is the straight-line distance between any two points on the surface of the required product model.

[0103] Step S301: defining the contour separation distance with the largest value as the upper limit separation distance, and performing calculation according to the upper limit separation distance and the preset proximity distance to determine the upper limit proximity range.

[0104] The upper limit separation distance is defined to determine the distance with the greatest mutual influence on the model. The close distance is the maximum distance value that can appear between the upper limit separation distance and the remaining distances that are closer to the upper limit separation distance set by the staff. The lower limit value of the upper limit close range can be determined by subtracting the close distance from the upper limit separation distance. The upper limit value of the upper limit close range is the upper limit separation distance.

[0105] Step S302: defining points corresponding to when the distance between contours is within a range close to the upper limit as influence points, and counting the influence points to determine the number of surface influences.

[0106] Influence points are defined to identify the locations that can influence the production of the product model. The number of surface influences is the total number of identified influence points.

[0107] Step S303: Counting the surface points of the required product model to determine the number of product surfaces, and calculating the impact ratio based on the number of product surfaces and the number of surface impacts.

[0108] The number of product surfaces is the total number of points on the surface of the demand product model. The impact ratio is the ratio of the determined impact points to all points, which is determined by dividing the number of surface impacts by the number of product surfaces.

[0109] Step S304: determining the influence coefficient corresponding to the influence ratio according to the preset influence matching relationship, and performing calculation according to the influence coefficient and the upper limit distance to determine the mutual influence distance.

[0110] The influence coefficient is a parameter used to calculate the mutual influence distance, which is between 0 and 1. The larger the influence ratio, the greater the possibility of being affected by defects under the current model, and therefore the larger the corresponding influence coefficient. The mutual influence distance is determined by subtracting the influence coefficient from the value obtained and multiplying it by the upper limit distance.

[0111] After the feature concentration scheme is determined, the intelligent cutting method for sponge processing also includes:

[0112] Step S400: Counting is performed according to each feature concentration scheme to determine the number of feature schemes.

[0113] The number of feature solutions is the number of solutions in the determined feature set.

[0114] Step S401: randomly selecting two surface defect features to combine to form a defect feature combination, and defining a feature concentration scheme when the two surface defect features in the defect feature combination are in the same single-unit concentration combination as a feature internal scheme.

[0115] By constructing a defect feature combination, the correlation between two defects can be better analyzed; defining a feature internal solution can distinguish the solutions where two defects are in the same monomer concentration combination, which facilitates subsequent analysis.

[0116] Step S402: Count the feature internal solutions to determine the number of internal solutions, calculate the internal proportion based on the number of internal solutions and the number of feature solutions, and compare the internal proportion with the preset critical proportion to determine the relative status of the demand for the defect feature combination.

[0117] The number of internal solutions is the total number of defined characteristic internal solutions, and the internal proportion is the ratio obtained by dividing the number of internal solutions by the number of characteristic solutions; the critical proportion is a parameter value set in advance by the staff to better distinguish the situations between defects. For example, 0-50% means the two are far away from each other, and 50%-100% means the two are close to each other. The internal proportion can be used to know the status of the two defects among multiple solutions. For example, when the internal proportion is within 0-50%, it can be determined that the two are far away from each other in most solutions, that is, the two are not in the same monomer concentrated combination, which is a better allocation scheme. Similarly, when the internal proportion is within 50%-100%, it can be determined that the two are close to each other in most solutions, that is, the two are in the same monomer concentrated combination, which is a better allocation scheme. The required optimal allocation state is the demand relative state, and the specific critical proportion is set by the staff according to actual conditions.

[0118] Step S403: determining the actual relative state according to each defect feature combination in a single feature concentration scheme, defining the defect feature combination whose actual relative state is consistent with the required relative state as a high-quality combination, and defining the remaining defect feature combinations as low-quality combinations.

[0119] The actual relative state is the distribution state of the defect feature combination in a single feature concentration scheme, that is, whether the two are in the same single concentrated combination. When the actual relative state is consistent with the required relative state, it means that the current feature concentration scheme has a relatively accurate distribution of the defect feature combination, so a high-quality combination is defined. Similarly, the remaining defect feature combinations that meet the requirements are inaccurately distributed in the current feature concentration scheme, so they are defined as low-quality combinations.

[0120] Step S404: Calculate the high-quality ratio based on the high-quality combination and the low-quality combination, and eliminate the feature concentration solutions whose high-quality ratio is less than the preset demand ratio.

[0121] The high-quality ratio is a parameter value that reflects whether the feature concentration scheme is reasonable. The larger the value, the more reasonable the scheme is. It is determined by dividing the number of high-quality combinations by the number of all defect feature combinations; the demand ratio is the minimum high-quality ratio that needs to be achieved when the recognition scheme set by the staff has a certain reference significance. By eliminating feature concentration schemes with a high-quality ratio lower than the demand ratio, a more accurate number of representative combinations can be determined for use in subsequent data analysis.

[0122] After the high-quality ratio is determined, the intelligent cutting method used for sponge processing also includes:

[0123] Step S500: Determine a reasonable boundary ratio based on the relative state of requirements for each defect feature combination.

[0124] The reasonable boundary ratio is the best internal ratio of each defect feature combination under theoretical circumstances. When the relative state of the input requirements is a state of being far away from each other, the corresponding reasonable boundary ratio can be 0%. The distance relationship between the two is determined in advance by the staff.

[0125] Step S501: Calculate and determine reasonable compensation parameters based on the internal proportions of each high-quality combination and low-quality combination and the corresponding reasonable boundary proportions.

[0126] The actual quality of each combination can be determined by calculating the difference between the internal proportion and the reasonable boundary proportion. The reasonable compensation parameter can be determined by summing up all the differences and taking the inverse. The larger the value, the more reasonable the distribution of each defect feature.

[0127] Step S502: performing calculations based on reasonable compensation parameters and the high-quality ratio to update the high-quality ratio.

[0128] By combining reasonable compensation parameters with the high-quality ratio, the high-quality ratio can be updated better and the accuracy of data analysis can be improved.

[0129] After the actual production quantity is determined, the intelligent cutting method used for sponge processing also includes:

[0130] Step S600: Determine whether there are at least two valid processing plans with the same and maximum actual production quantity.

[0131] The purpose of the judgment is to find out whether there are multiple effective processing solutions that meet the requirements, so as to determine the only processing solution to be used.

[0132] Step S6001: If there are not at least two valid processing plans with the same actual production quantity and the largest actual production quantity, the valid processing plan corresponding to the largest actual production quantity is defined as the used processing plan.

[0133] When there are not at least two valid processing plans with the same and largest actual production quantity, it means that there is only one valid processing plan that meets the requirements. In this case, it can be determined as the processing plan to be used.

[0134] Step S6002: If there are at least two valid processing plans with the same actual production quantity and the largest actual production quantity, the valid processing plan corresponding to the largest actual production quantity is defined as the alternative processing plan.

[0135] When there are at least two valid processing plans with the same and maximum actual production quantity, it means that there are multiple valid processing plans that meet the requirements. At this time, alternative processing plans are defined to distinguish different valid processing plans, which is convenient for subsequent analysis.

[0136] Step S601: Determine a single cutting path in each alternative processing solution, and randomly sort the required product models to determine the model processing order.

[0137] The model processing sequence is the simulation sequence for processing and cutting each product.

[0138] Step S602: connecting the individual cutting paths according to the model processing sequence to form a simulated operation path, and determining a simulated operation distance according to the simulated operation path.

[0139] The simulated operation path is the path of controlling the cutting tool to operate according to the single cutting path in sequence according to the model processing order, that is, the movement path of the cutting tool to complete the product processing operation. The simulated operation distance is the distance value moved by the cutting tool.

[0140] Step S603: defining the alternative processing solution corresponding to the simulated operation distance with the smallest value as the used processing solution, and determining the simulated operation path corresponding to the simulated operation distance with the smallest value as the overall cutting path.

[0141] The solution with the highest cutting efficiency is determined by determining the simulated working distance with the smallest value. At this time, the processing plan and the overall cutting path are defined to facilitate the subsequent control of the cutting tool.

[0142] Reference Figure 2 Based on the same inventive concept, an embodiment of the present invention provides an intelligent cutting system for sponge processing, comprising:

[0143] An acquisition module, used to obtain the area placement status of a preset sponge placement area;

[0144] A processing module, connected to the acquisition module and the judgment module, for storing and processing information;

[0145] The judgment module is connected with the acquisition module and the processing module and is used for judging the information;

[0146] When the judgment module determines that the regional placement state is consistent with the preset in-place placement state, the acquisition module acquires the required product model and causes the processing module to control the preset image capturing device to move along the preset image capturing path so that the acquisition module acquires the sponge surface image;

[0147] The processing module performs three-dimensional modeling processing based on each sponge surface image to determine a sponge placement model, performs feature recognition in the sponge placement model to determine surface defect features, and determines the surface defect location based on the surface defect features;

[0148] The processing module generates a random number of demand product models and places them in the sponge placement model, and generates a product processing plan based on the placement conditions corresponding to each demand product model;

[0149] The processing module defines, among the product processing plans, a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect position as a valid processing plan;

[0150] The processing module defines the number of required product models in the effective processing plan as the actual production quantity, and defines the effective processing plan corresponding to the actual production quantity with the largest value as the used processing plan;

[0151] The processing module determines a single cutting path according to the contour line of the required product model in the processing plan, determines an overall cutting path according to all the single cutting paths, and controls a preset cutting tool to perform cutting operations along the overall cutting path;

[0152] A quantity range determination module is used to determine the generation quantity range of the demand product model;

[0153] A mutual influence distance determination module, used to determine an appropriate mutual influence distance for use;

[0154] The feature concentration solution elimination module is used to eliminate some feature concentration solutions that cannot meet the requirements;

[0155] A high-quality ratio updating module is used to update the determined high-quality ratio;

[0156] The effective processing scheme screening module is used to screen multiple effective processing schemes that meet the requirements.

[0157] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the division of the above-mentioned functional modules is only used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-mentioned systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0158] An embodiment of the present invention provides a computer-readable storage medium storing a computer program capable of being loaded and executed by a processor for an intelligent cutting method for sponge processing.

[0159] Computer storage media include, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

Claims

1. An intelligent cutting method for sponge processing, characterized in that: include: Get the area placement status of the preset sponge placement area; When the regional placement state is consistent with the preset in-place placement state, the required product model is obtained and the preset image capturing device is controlled to move along the preset image capturing path to obtain the sponge surface image; Performing three-dimensional modeling processing based on each sponge surface image to determine a sponge placement model, performing feature recognition in the sponge placement model to determine surface defect features, and determining the surface defect location based on the surface defect features; Generate a random number of demand product models and place them in the sponge placement model, and generate product processing plans based on the placement conditions corresponding to each demand product model; In each product processing plan, a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect location is defined as a valid processing plan; The number of required product models in the effective processing plan is defined as the actual production quantity, and the effective processing plan corresponding to the actual production quantity with the largest value is defined as the used processing plan; The individual cutting paths are determined according to the contour lines of the required product model in the processing plan, and the overall cutting path is determined according to all the individual cutting paths, and the preset cutting tool is controlled to perform cutting operations along the overall cutting path.

2. The intelligent cutting method for sponge processing according to claim 1, characterized in that: The steps of generating a random number of demand product models and placing them in the sponge placement model include: Determine the overall model volume based on the sponge placement model, and determine the product model volume based on the required product model; Calculate the upper limit of placement quantity based on the overall model volume and the product model volume; Calculate the distance between any two surface defects based on their locations; A surface defect position is randomly selected from all surface defect positions and defined as a central defect position. Surface defects whose distance from the central defect position is less than a preset mutual influence distance are summarized to form a monomer concentrated combination. Re-determine the central defect position in the surface defect features outside the monomer concentration combination to determine the monomer concentration combination until all surface defect features are within the monomer concentration combination, and determine the feature concentration scheme based on each monomer concentration combination; Counting the individual concentration combinations in each feature concentration scheme to determine the number of concentration combinations, and calculating the number of representative combinations based on all the concentration combination numbers; The lower limit placement quantity is determined by calculating based on the upper limit placement quantity, the representative combination quantity and the preset loose fixing quantity; The quantity generation range is determined based on the upper and lower limit placement quantities, and quantities are generated from top to bottom within the quantity generation range to place the required product model.

3. The intelligent cutting method for sponge processing according to claim 2, characterized in that: The method further includes a step of determining a mutual influence distance, the step comprising: Randomly select two points on the surface of the required product model to determine the distance between the contours; The contour separation distance with the largest value is defined as the upper limit separation distance, and the upper limit proximity range is determined by calculation based on the upper limit separation distance and the preset proximity distance; The points corresponding to the distances between the contours being within the upper limit are defined as impact points, and the impact points are counted to determine the number of surface impacts. Count the surface points of the required product model to determine the number of product surfaces, and calculate the impact ratio based on the number of product surfaces and the number of surface impacts; The influence coefficient corresponding to the influence ratio is determined according to the preset influence matching relationship, and the mutual influence distance is determined by calculation based on the influence coefficient and the upper limit distance.

4. The intelligent cutting method for sponge processing according to claim 2, characterized in that: After the feature concentration scheme is determined, the intelligent cutting method for sponge processing also includes: Counting is performed according to each characteristic concentration scheme to determine the number of characteristic schemes; Randomly select two surface defect features to combine to form a defect feature combination, and define the feature concentration scheme when the two surface defect features in the defect feature combination are in the same monomer concentration combination as the feature internal scheme; Count the internal solutions of the features to determine the number of internal solutions, calculate the internal proportion based on the number of internal solutions and the number of feature solutions, and compare the internal proportion with the preset critical proportion to determine the relative status of the demand for the defect feature combination; In a single feature concentration scheme, the actual relative state is determined based on each defect feature combination, and the defect feature combination whose actual relative state is consistent with the required relative state is defined as a high-quality combination, and the remaining defect feature combinations are defined as low-quality combinations; Calculations are performed based on high-quality combinations and low-quality combinations to determine the high-quality ratio, and feature concentration solutions whose high-quality ratio is less than the preset demand ratio are eliminated.

5. The intelligent cutting method for sponge processing according to claim 4, characterized in that: After the high-quality ratio is determined, the intelligent cutting method used for sponge processing also includes: Determine the reasonable boundary ratio based on the relative status of the requirements of each defect feature combination; Calculate the reasonable compensation parameters based on the internal proportions of each high-quality portfolio and low-quality portfolio and the corresponding reasonable boundary proportions; The quality ratio is updated by calculation based on reasonable compensation parameters and quality ratio.

6. The intelligent cutting method for sponge processing according to claim 1, characterized in that: After the actual production quantity is determined, the intelligent cutting method used for sponge processing also includes: Determine whether there are at least two effective processing plans with the same and maximum actual production quantity; If there are not at least two valid processing plans with the same actual production quantity and the largest actual production quantity, the valid processing plan corresponding to the largest actual production quantity is defined as the used processing plan; If there are at least two effective processing plans with the same actual production quantity and the largest actual production quantity, the effective processing plan corresponding to the largest actual production quantity is defined as the alternative processing plan; Determine the individual cutting paths in each alternative processing scheme, and randomly sort them according to the required product models to determine the model processing order; Connecting the individual cutting paths according to the model processing sequence to form a simulation operation path, and determining the simulation operation distance according to the simulation operation path; The alternative processing scheme corresponding to the simulated operation distance with the smallest value is defined as the used processing scheme, and the simulated operation path corresponding to the simulated operation distance with the smallest value is determined as the overall cutting path.

7. An intelligent cutting system for sponge processing, characterized in that: include: An acquisition module, used to obtain the area placement status of a preset sponge placement area; The processing module is connected to the acquisition module and the judgment module and is used for storing and processing information; the judgment module is connected to the acquisition module and the processing module and is used for judging information; When the judgment module determines that the regional placement state is consistent with the preset in-place placement state, the acquisition module acquires the required product model and causes the processing module to control the preset image capturing device to move along the preset image capturing path so that the acquisition module acquires the sponge surface image; The processing module performs three-dimensional modeling processing based on each sponge surface image to determine a sponge placement model, performs feature recognition in the sponge placement model to determine surface defect features, and determines the surface defect location based on the surface defect features; The processing module generates a random number of demand product models and places them in the sponge placement model, and generates a product processing plan based on the placement conditions corresponding to each demand product model; The processing module defines, among the product processing plans, a product processing plan in which no required product models overlap with each other and no required product model includes a surface defect position as a valid processing plan; The processing module defines the number of required product models in the effective processing plan as the actual production quantity, and defines the effective processing plan corresponding to the actual production quantity with the largest value as the used processing plan; The processing module determines a single cutting path according to the contour line of the required product model in the processing plan, determines an overall cutting path according to all the single cutting paths, and controls a preset cutting tool to perform cutting operations along the overall cutting path.

8. A computer-readable storage medium, characterized in that The device stores a computer program which can be loaded by a processor and executes the intelligent cutting method for sponge processing according to any one of claims 1 to 6.

Images