Novel substrate cutting method

Through the new substrate cutting method, the cutting process is optimized using digital twin models and substrate cutting simulation models, which solves the problem of low cutting efficiency and yield of semiconductor substrates, improves production efficiency and product quality, and reduces the overall production cost.

CN119057261AActive Publication Date: 2024-12-03SHENZHEN NUOXINBO COMM CO LTD

Patent Information

Application Number
CN202411477058.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-12-03
Estimated Expiration
2044-10-22

AI Technical Summary

Technical Problem

The existing semiconductor substrate cutting method leads to low production efficiency and low yield, resulting in a significant increase in overall production costs.

Method used

Using a new substrate cutting method, by obtaining substrate cutting task data and equipment data, digital twin models and substrate cutting simulation models are used to simulate and optimize the cutting process, including the selection of measurement tools, optimization of cutting steps and cost prediction, and using genetic algorithms Intelligent optimization algorithms can improve cutting accuracy and efficiency.

Benefits of technology

It improves cutting efficiency and yield, reduces production costs, enhances the flexibility and adaptability of the system, reduces manual intervention and errors, and improves the automation and intelligence level of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119057261A_ABST
    Figure CN119057261A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of laser cutting control, and provides a novel substrate cutting method which comprises the following steps: acquiring substrate cutting task data and equipment data, generating a real-time to-be-cut substrate image by using a digital twin model, and performing simulated cutting through a substrate cutting simulation model. And compared with cutting target data, the quality is improved. If the cutting is qualified, predicting the cost; and if the cost does not meet the target, optimizing the simulation model. And performing clustering analysis and optimization on the cutting steps, and simulating and screening out the optimal cutting step by using the optimized model. According to the invention, the cutting efficiency and yield of the semiconductor substrate are effectively improved, the manufacturing cost is reduced, and the problem of cost increase caused by low yield of the substrate in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of laser cutting control, and in particular to a novel substrate cutting method. Background Art

[0002] Semiconductor substrate products are small in size and have low efficiency in single-piece processing. Therefore, they are actually processed in large pieces, and then cut into small pieces to make the final product. To facilitate understanding, a practical example is provided below. The most common semiconductor substrate finished product is a rectangle. When actually cutting, it is first cut horizontally and then cut vertically, and finally a small rectangular piece is produced. However, due to the needs of actual product design, it is sometimes necessary to cut it into a non-rectangular shape, such as an equilateral triangle. The conventional practice is to still cut it into a rectangle first, and then grind it to form the required triangular shape.

[0003] The existing semiconductor substrate cutting method first cuts the semiconductor substrate into quadrilaterals, including rectangles or squares, and then performs secondary processing on the semiconductor substrate, which results in low semiconductor substrate production efficiency and low semiconductor substrate yield, resulting in a significant increase in the overall production cost of the semiconductor substrate, which affects the mass production of semiconductor substrates. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a novel substrate cutting method to solve the problem that the overall production cost of semiconductor substrates is greatly increased due to the low yield of semiconductor substrates.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides a novel substrate cutting method, comprising: Step S101, obtaining substrate cutting task data and substrate cutting equipment data, wherein the substrate cutting task data includes substrate cutting target data and substrate cutting parameter standards, and the substrate cutting equipment data includes substrate cutting equipment operation status, cutting equipment accuracy, and cutting equipment environment information; Step S102, collecting size data of the substrate to be cut and position data of the substrate to be cut according to the substrate cutting task data, substituting the size data of the substrate to be cut and the position data of the substrate to be cut into a preset digital twin model, and generating real-time image data of the substrate to be cut; Step S103, substituting the real-time image data of the substrate to be cut into a preset substrate cutting simulation model to obtain a substrate cutting simulation result, and comparing the substrate cutting simulation result with the substrate cutting target data to obtain a substrate cutting comparison result; Step S104, if the substrate cutting comparison result shows that the substrate cutting is qualified, the substrate cutting comparison result is substituted into a preset substrate cutting cost model to obtain a substrate cutting cost prediction result; if the substrate cutting cost prediction result does not meet the substrate cutting target data, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model; Step S105, use the optimized substrate cutting simulation model to process the real-time image data of the substrate to be cut to obtain a real-time substrate to be cut data set, cluster analyze the data in the real-time substrate to be cut data set to obtain the real-time substrate to be cut data cluster analysis result, if the real-time substrate to be cut data cluster analysis result is lower than the substrate cutting target data, then optimize the substrate cutting step, receive the substrate cutting step data group, use the optimized substrate cutting simulation model to use the cutting steps in the substrate cutting step data group in sequence, obtain multiple groups of cutting step simulation results, substitute the multiple groups of cutting step simulation results into the preset substrate cutting cost model, obtain multiple groups of cutting step cost prediction results, and select the cutting steps that meet the substrate cutting target data from the multiple groups of cutting step cost prediction results as the real-time substrate cutting steps.

[0006] Furthermore, in the novel substrate cutting method provided by the present invention, the step S102 comprises: Extracting information from substrate cutting task data including specific requirements, target size, shape, and accuracy of substrate cutting; Determine the measuring tool used to measure the semiconductor substrate according to the substrate material, size and cutting requirements, determine the measurement method, and use the determined measuring tool to measure the length, width and thickness of the substrate; Accurately mark the cutting positions and lines on the substrate, and record the coordinates or relative positions of the marked points.

[0007] Furthermore, in the novel substrate cutting method provided by the present invention, step S103 comprises: Loading the cutting simulation results obtained by processing the real-time substrate image data to be cut through a preset substrate cutting simulation model into the comparison system; The cutting target data in the substrate cutting task data are loaded, including cutting size, shape, and precision index; According to the requirements of the cutting task and the cutting simulation results, the comparison indicators include cutting accuracy, size deviation and shape fit; Use comparison software to compare the cutting simulation results with the cutting target data one by one, calculate the difference or ratio, and use image recognition contour matching technology to compare graphic indicators; According to the results of the comparison operation, the differences between the cutting simulation results and the cutting target data are analyzed and a comparison result report is generated.

[0008] Furthermore, in the novel substrate cutting method provided by the present invention, the step S104 comprises: If the substrate cutting comparison result shows that the substrate cutting is unqualified, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model.

[0009] Furthermore, in the novel substrate cutting method provided by the present invention, the step S104 comprises: According to the parameters and variables of the substrate cutting simulation model, a suitable encoding method is selected to represent each individual, and each individual has a set of cutting parameters; Initialize a population containing multiple individuals, each of which represents a cutting scheme; For each individual in the population, substitute it into the substrate cutting simulation model to obtain the cutting simulation result; According to the comparison between the cutting simulation results and the substrate cutting target data, the fitness value of each individual is calculated; According to the fitness value, the tournament selection method is used to select individuals with higher fitness from the population as parents; Perform a crossover operation on the selected parent individuals to generate new offspring individuals by exchanging gene fragments or recombining chromosomes, and perform mutation operations on the offspring individuals. The fitness evaluation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached or other stopping conditions are met.

[0010] Furthermore, in the novel substrate cutting method provided by the present invention, step S105 comprises: receiving a substrate cutting step data set from a database, the substrate cutting step data set including a cutting sequence, a cutting depth, and a cutting speed of a plurality of cutting steps; In the optimized substrate cutting simulation model, the simulation environment is initialized according to the real-time image data of the substrate to be cut. The initialization of the simulation environment includes setting the size parameters, shape parameters, material parameters of the substrate, and the type and parameters of the cutting tool.

[0011] Furthermore, in the novel substrate cutting method provided by the present invention, step S105 comprises: According to the order of the substrate cutting step data combination, the simulation of each cutting step is performed in sequence, and during the simulation process, the cutting effect, cutting force, and cutting temperature indicators are collected; Record simulation results for each cutting step, including the shape and size of the substrate after cutting and the cutting quality; After completing the simulation of all cutting steps, multiple sets of cutting step simulation results are generated. The multiple sets of cutting step simulation results include recording the simulation situation of each cutting step and the state of the substrate after cutting.

[0012] The beneficial effects of the present invention are mainly reflected in the following aspects: By acquiring accurate substrate cutting task data and equipment data, the present invention can improve the cutting process based on the latest and most accurate information, thereby improving cutting efficiency and yield. By using the digital twin model and substrate cutting simulation model, the present invention can simulate and optimize the cutting process before actual cutting, reduce errors and waste in the cutting process, and further improve cutting efficiency and yield.

[0013] The present invention performs cost prediction after qualified cutting, and optimizes the substrate cutting simulation model according to the cost prediction result, thereby improving the cutting quality requirements while trying to reduce the production cost. By optimizing and screening the cutting steps, the present invention can find the cutting steps that best meet the target data and further reduce the production cost.

[0014] The present invention determines appropriate measuring tools and methods according to the substrate material, size and cutting requirements, improves the accurate measurement of the substrate size, and accurately marks the cutting position and lines on the substrate, thereby improving the cutting accuracy. The cutting simulation results are compared with the cutting target data one by one using comparison software, including indicators such as cutting accuracy, size deviation, shape fit, etc., to improve the cutting quality to meet the requirements.

[0015] The present invention can quickly adapt to different substrate cutting tasks and equipment states through the preset digital twin model and substrate cutting simulation model, thereby improving the flexibility and adaptability of the system. During the cutting step optimization process, the present invention can receive multiple cutting step data sets from the database, and use the optimized model for simulation and screening to find the cutting step that best suits the current task.

[0016] The present invention reduces manual intervention and errors through automated data acquisition, simulation, comparison and optimization processes, and improves the automation and intelligence level of the system. The substrate cutting simulation model is optimized using intelligent optimization algorithms such as genetic algorithms, further improving the intelligence level and optimization efficiency of the system.

[0017] In summary, the present invention effectively solves the problem of low yield of semiconductor substrates leading to a significant increase in production costs through intelligent steps, improves cutting efficiency and product quality, reduces overall production costs, and enhances the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A schematic diagram of a novel substrate cutting method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0021] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0022] The present invention provides a novel substrate cutting method, comprising: Step S101, obtaining substrate cutting task data and substrate cutting equipment data, wherein the substrate cutting task data includes substrate cutting target data and substrate cutting parameter standards, and the substrate cutting equipment data includes substrate cutting equipment operation status, cutting equipment accuracy, and cutting equipment environment information; In step S101 , substrate cutting task data and substrate cutting equipment data need to be acquired first.

[0023] The substrate cutting task data includes substrate cutting target data and substrate cutting parameter standards, which define the expected results and required accuracy of cutting, etc.

[0024] The substrate cutting equipment data includes the operating status of the substrate cutting equipment, the cutting equipment accuracy and the environmental information of the cutting equipment. These data help to understand the current performance of the equipment and the environmental factors that affect the cutting results.

[0025] The substrate cutting target data specifically includes the size, shape, precision and other requirements that the substrate should achieve after cutting.

[0026] The substrate cutting parameter standards include recommended values ​​or allowable ranges for parameters such as cutting speed, cutting depth, and cutting angle.

[0027] The equipment operation status includes whether the equipment is operating normally, whether it is faulty or needs maintenance, etc. The cutting equipment accuracy reflects the cutting capability of the equipment, that is, the cutting accuracy that can be achieved. The environmental information of the cutting equipment includes temperature, humidity, dust concentration, etc. These factors affect the cutting quality and equipment performance.

[0028] Obtaining accurate substrate cutting task data and substrate cutting equipment data is a prerequisite for improving cutting quality. Data is obtained through sensors, measuring tools, manual input, etc. After data acquisition, preprocessing is required, such as cleaning, format conversion, etc., to meet the requirements of subsequent steps.

[0029] As the cutting task progresses and the equipment runs, the task data and equipment data will change. Therefore, this data needs to be updated regularly to improve the accuracy and reliability of the cutting process. When acquiring, storing and processing this data, it is necessary to improve data security and privacy protection, including preventing risks such as data leakage, damage or illegal access.

[0030] Step S102, collecting size data of the substrate to be cut and position data of the substrate to be cut according to the substrate cutting task data, substituting the size data of the substrate to be cut and the position data of the substrate to be cut into a preset digital twin model, and generating real-time image data of the substrate to be cut; Extract key information from substrate cutting task data, including specific requirements, target size, shape, and accuracy of substrate cutting. Determine appropriate measurement tools and methods based on substrate material, size, and cutting requirements. This is to improve measurement accuracy and ensure cutting accuracy. Use the specified measurement tools to measure the length, width, and thickness of the substrate. The accuracy of the measurement results directly affects the accuracy and quality of subsequent cutting.

[0031] Accurately mark the cutting position and line on the substrate, which is an important reference in the cutting process. At the same time, record the coordinates or relative positions of the marked points for subsequent operations and records. During the execution of the entire step S102, it is necessary to improve the accuracy of measurement and marking to avoid errors and waste in the subsequent cutting process. At the same time, it is also necessary to flexibly adjust the measurement method and marking method according to the specific substrate material and cutting requirements to achieve the best cutting effect.

[0032] After completing the above steps, the size data of the substrate to be cut and the position data of the substrate to be cut are substituted into the preset digital twin model to generate real-time image data of the substrate to be cut. This step provides an important reference and basis for subsequent cutting simulation and actual operation. Through the detailed execution of step S102, the subsequent cutting simulation and actual operation can be improved to be more accurate and efficient, thereby improving the precision and quality of substrate cutting.

[0033] Step S103, substituting the real-time image data of the substrate to be cut into a preset substrate cutting simulation model to obtain a substrate cutting simulation result, and comparing the substrate cutting simulation result with the substrate cutting target data to obtain a substrate cutting comparison result; The cutting simulation results obtained after the real-time substrate image data to be cut is processed by the preset substrate cutting simulation model are loaded into the comparison system. At the same time, the cutting target data in the substrate cutting task data is loaded, which includes cutting size, shape, accuracy index, etc. According to the requirements of the cutting task and the cutting simulation results, the comparison indicators are determined, mainly including cutting accuracy, size deviation and shape fit.

[0034] Use comparison software to compare the cutting simulation results with the cutting target data one by one, and calculate the difference or ratio. For graphic indicators, use image recognition contour matching technology to compare to improve the accuracy of the shape. According to the results of the comparison operation, analyze the difference between the cutting simulation results and the cutting target data. Generate a comparison result report to record the difference between the cutting simulation results and the cutting target data in detail.

[0035] If it is found that there is a large difference between the cutting simulation result and the cutting target data, it can return to step S102 or S104 for further optimization. Optimization includes adjusting the measurement tools, measurement methods, cutting parameters or simulation models, etc. Through these specific execution methods and related details, step S103 can improve the accuracy and reliability of the cutting simulation results, providing strong support for subsequent cost prediction and cutting step optimization.

[0036] Step S104, if the substrate cutting comparison result shows that the substrate cutting is qualified, the substrate cutting comparison result is substituted into a preset substrate cutting cost model to obtain a substrate cutting cost prediction result; if the substrate cutting cost prediction result does not meet the substrate cutting target data, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model; Step S104 is a key step in the technical solution of the present invention, involving substrate cutting cost prediction and optimization of substrate cutting simulation model. The following is a detailed explanation of the specific execution method and related details of this step: First, it is necessary to determine whether the substrate cutting comparison result is qualified. This step is the basis for subsequent operations, and only qualified cutting results will be used for cost prediction. If the substrate cutting is qualified: execute the next step, substitute the substrate cutting comparison result into the preset substrate cutting cost model, and obtain the substrate cutting cost prediction result. If the substrate cutting is unqualified: directly optimize the substrate cutting simulation model to obtain a more accurate cutting result.

[0037] If the substrate cutting is qualified, the substrate cutting comparison result is substituted into the preset substrate cutting cost model. This model is based on historical data and algorithms and can predict the cost of the current cutting plan. Through cost prediction, enterprises can understand the economic benefits of the cutting process and provide a basis for subsequent cost control. The obtained substrate cutting cost prediction result will be compared with the substrate cutting target data to determine whether it meets the cost requirements. If the cost prediction result does not meet the target data, it means that the current cutting plan is not the optimal solution and needs to be optimized.

[0038] If the substrate cutting cost prediction result does not meet the substrate cutting target data, the substrate cutting simulation model needs to be optimized. The optimization process involves adjusting model parameters, improving algorithms, etc. to improve the accuracy and reliability of the simulation results. By optimizing the model, more accurate cutting results and cost predictions can be obtained, thereby improving production efficiency and economic benefits.

[0039] When the substrate cutting is unqualified, the genetic algorithm can be used to optimize the substrate cutting simulation model. Genetic algorithm is an optimization algorithm based on the principle of biological evolution, which solves complex problems by simulating natural selection and genetic mechanisms.

[0040] Coding method: According to the parameters and variables of the substrate cutting simulation model, a suitable coding method is selected to represent each individual. Each individual represents a set of cutting parameters, that is, a cutting scheme.

[0041] Initialize the population: Initialize a population containing multiple individuals, each of which represents a cutting scheme. Through iterative optimization of the genetic algorithm, the optimal cutting scheme can be gradually approached.

[0042] Iterative optimization: The population is iteratively optimized through genetic algorithms (including fitness evaluation, selection, crossover and mutation operations) until the preset number of iterations is reached or other stop conditions are met. During the iterative process, the cutting scheme is continuously screened and optimized to improve cutting efficiency and yield.

[0043] The optimized substrate cutting simulation model will be used for subsequent substrate cutting simulation and cost prediction. The optimized model can more accurately reflect the actual cutting situation and improve cutting efficiency and yield. At the same time, the optimization results can also provide strong support for the company's production planning and cost control.

[0044] The entire step S104 is an iterative optimization process. Through continuous comparison, prediction and optimization, the optimal cutting scheme and cost target are gradually approached. This method can significantly improve the production efficiency and yield of semiconductor substrates and reduce the overall production cost. At the same time, iterative optimization also helps enterprises maintain their competitive advantage in the fierce market competition.

[0045] By predicting and optimizing the cost of substrate cutting, enterprises can better control production costs and improve economic benefits. Cost control is one of the important links in enterprise management. Through effective cost control strategies and methods, production costs can be reduced, product quality and market competitiveness can be improved.

[0046] In summary, step S104 improves the accuracy and economy of the substrate cutting process by judging the substrate cutting comparison results, predicting the substrate cutting cost, optimizing the substrate cutting simulation model, applying the genetic algorithm, applying the optimization results, iterative optimization, and cost control. This step is an indispensable part of the technical solution of the present invention, and provides strong support for improving the production efficiency and yield of semiconductor substrates and reducing the overall production cost.

[0047] Step S105, use the optimized substrate cutting simulation model to process the real-time image data of the substrate to be cut to obtain a real-time substrate to be cut data set, cluster analyze the data in the real-time substrate to be cut data set to obtain the cluster analysis result of the real-time substrate to be cut data, if the cluster analysis result of the real-time substrate to be cut data is lower than the substrate cutting target data, optimize the substrate cutting step, receive the substrate cutting step data group, use the optimized substrate cutting simulation model to use the cutting steps in the substrate cutting step data group in sequence to obtain multiple groups of cutting step simulation results, substitute the multiple groups of cutting step simulation results into the preset substrate cutting cost model to obtain multiple groups of cutting step cost prediction results, select the cutting steps that meet the substrate cutting target data from the multiple groups of cutting step cost prediction results as the real-time substrate cutting steps, send the real-time substrate cutting steps to the substrate cutting equipment, and the substrate cutting equipment executes the real-time substrate cutting steps to cut the substrate.

[0048] A substrate cutting step data set is received from a database, the data set including a cutting sequence, a cutting depth, and a cutting speed of a plurality of cutting steps, so as to provide detailed cutting parameters for a subsequent simulation process.

[0049] In the optimized substrate cutting simulation model, the simulation environment is initialized according to the real-time image data of the substrate to be cut. This includes setting the size parameters, shape parameters, material parameters of the substrate, as well as the type and parameters of the cutting tool, so as to ensure that the simulation environment is consistent with the actual cutting conditions.

[0050] According to the order in the substrate cutting step data group, the simulation of each cutting step is performed in sequence. During the simulation process, key indicators such as cutting effect, cutting force, and cutting temperature are collected to evaluate the feasibility and efficiency of the cutting step.

[0051] For each cutting step, the simulation results are recorded, including the shape and size of the substrate after cutting, as well as the cutting quality. These results will be used for subsequent analysis and optimization.

[0052] After completing the simulation of all cutting steps, multiple sets of cutting step simulation results are generated. These results record the simulation of each cutting step and the state of the substrate after cutting, providing data support for subsequent screening and optimization.

[0053] Substitute multiple sets of cutting step simulation results into a preset substrate cutting cost model to obtain multiple sets of cutting step cost prediction results. Then, the cutting steps that meet the substrate cutting target data are selected from these results as real-time substrate cutting steps.

[0054] If the cluster analysis result of the real-time substrate data to be cut is lower than the substrate cutting target data, the substrate cutting step is optimized. The cutting efficiency and substrate quality are improved by adjusting the cutting parameters, cutting sequence or introducing new cutting technology. Through these specific execution methods and related details, step S105 can improve the accuracy and efficiency of substrate cutting, while reducing production costs and improving overall production efficiency.

[0055] Specifically, the novel substrate cutting method provided by the present invention, the step S102 comprises: Extracting information from substrate cutting task data including specific requirements, target size, shape, and accuracy of substrate cutting; Determine the measuring tool used to measure the semiconductor substrate according to the substrate material, size and cutting requirements, determine the measurement method, and use the determined measuring tool to measure the length, width and thickness of the substrate; Accurately mark the cutting positions and lines on the substrate, and record the coordinates or relative positions of the marked points.

[0056] Specifically, the novel substrate cutting method provided by the present invention, step S103, comprises: Loading the cutting simulation results obtained by processing the real-time substrate image data to be cut through a preset substrate cutting simulation model into the comparison system; The cutting target data in the substrate cutting task data are loaded, including cutting size, shape, and precision index; According to the requirements of the cutting task and the cutting simulation results, the comparison indicators include cutting accuracy, size deviation and shape fit; Use comparison software to compare the cutting simulation results with the cutting target data one by one, calculate the difference or ratio, and use image recognition contour matching technology to compare graphic indicators; According to the results of the comparison operation, the differences between the cutting simulation results and the cutting target data are analyzed and a comparison result report is generated.

[0057] Specifically, the novel substrate cutting method provided by the present invention, the step S104 comprises: If the substrate cutting comparison result shows that the substrate cutting is unqualified, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model.

[0058] Specifically, the novel substrate cutting method provided by the present invention, the step S104 comprises: According to the parameters and variables of the substrate cutting simulation model, a suitable encoding method is selected to represent each individual, and each individual has a set of cutting parameters; Initialize a population containing multiple individuals, each of which represents a cutting scheme; For each individual in the population, substitute it into the substrate cutting simulation model to obtain the cutting simulation result; According to the comparison between the cutting simulation results and the substrate cutting target data, the fitness value of each individual is calculated; According to the fitness value, the tournament selection method is used to select individuals with higher fitness from the population as parents; Perform a crossover operation on the selected parent individuals to generate new offspring individuals by exchanging gene fragments or recombining chromosomes, and perform mutation operations on the offspring individuals. The fitness evaluation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached or other stopping conditions are met.

[0059] Specifically, the novel substrate cutting method provided by the present invention, the step S105 comprises: receiving a substrate cutting step data set from a database, the substrate cutting step data set including a cutting sequence, a cutting depth, and a cutting speed of a plurality of cutting steps; In the optimized substrate cutting simulation model, the simulation environment is initialized according to the real-time image data of the substrate to be cut. The initialization of the simulation environment includes setting the size parameters, shape parameters, material parameters of the substrate, and the type and parameters of the cutting tool.

[0060] Specifically, the novel substrate cutting method provided by the present invention, the step S105 comprises: According to the order of the substrate cutting step data combination, the simulation of each cutting step is performed in sequence, and during the simulation process, the cutting effect, cutting force, and cutting temperature indicators are collected; Record simulation results for each cutting step, including the shape and size of the substrate after cutting and the cutting quality; After completing the simulation of all cutting steps, multiple sets of cutting step simulation results are generated. The multiple sets of cutting step simulation results include recording the simulation situation of each cutting step and the state of the substrate after cutting.

[0061] The technical solution of the present invention solves the problem of low yield of semiconductor substrates leading to a significant increase in production costs by the following methods: Obtain substrate cutting task data and substrate cutting equipment data, including substrate cutting target data, substrate cutting parameter standards, equipment operation status, cutting equipment accuracy, and environmental information, to provide a basis for subsequent precise cutting. According to the substrate cutting task data, collect the size data and position data of the substrate to be cut, substitute them into the preset digital twin model, generate real-time image data of the substrate to be cut, and improve the data accuracy before cutting.

[0062] Substitute the real-time image data of the substrate to be cut into the preset substrate cutting simulation model to obtain the substrate cutting simulation result, and compare it with the substrate cutting target data to improve the cutting quality to meet the requirements.

[0063] If the cutting is qualified, the cost is predicted; if the cost prediction result does not meet the target data, the substrate cutting simulation model is optimized to reduce the production cost and improve the cutting quality.

[0064] The optimized model is used to process the data and perform cluster analysis. If the analysis result is lower than the target data, the cutting steps are optimized, and the cutting step data group is received. The optimized model is used for simulation to screen out the cutting steps that meet the target data as the real-time substrate cutting steps.

[0065] According to the substrate material, size and cutting requirements, determine the measurement tools and methods, accurately measure the substrate size, and mark the cutting position and lines on the substrate to improve cutting accuracy. Use comparison software to compare the cutting simulation results with the cutting target data one by one, including cutting accuracy, size deviation, shape fit, etc., to improve cutting quality.

[0066] Through this series of refined and intelligent steps, the technical solution of the present invention effectively solves the problem of low yield of semiconductor substrates leading to a significant increase in production costs, improves cutting efficiency and product quality, and reduces overall production costs.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. A novel substrate cutting method, characterized in that: include: Step S101, obtaining substrate cutting task data and substrate cutting equipment data, wherein the substrate cutting task data includes substrate cutting target data and substrate cutting parameter standards, and the substrate cutting equipment data includes substrate cutting equipment operation status, cutting equipment accuracy, and cutting equipment environment information; Step S102, collecting size data of the substrate to be cut and position data of the substrate to be cut according to the substrate cutting task data, substituting the size data of the substrate to be cut and the position data of the substrate to be cut into a preset digital twin model, and generating real-time image data of the substrate to be cut; Step S103, substituting the real-time image data of the substrate to be cut into a preset substrate cutting simulation model to obtain a substrate cutting simulation result, and comparing the substrate cutting simulation result with the substrate cutting target data to obtain a substrate cutting comparison result; Step S104, if the substrate cutting comparison result shows that the substrate cutting is qualified, the substrate cutting comparison result is substituted into a preset substrate cutting cost model to obtain a substrate cutting cost prediction result; if the substrate cutting cost prediction result does not meet the substrate cutting target data, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model; Step S105, use the optimized substrate cutting simulation model to process the real-time image data of the substrate to be cut to obtain a real-time substrate to be cut data set, cluster analyze the data in the real-time substrate to be cut data set to obtain the cluster analysis result of the real-time substrate to be cut data, if the cluster analysis result of the real-time substrate to be cut data is lower than the substrate cutting target data, optimize the substrate cutting steps, receive the substrate cutting step data group, use the optimized substrate cutting simulation model to use the cutting steps in the substrate cutting step data group in sequence to obtain multiple groups of cutting step simulation results, substitute the multiple groups of cutting step simulation results into the preset substrate cutting cost model to obtain multiple groups of cutting step cost prediction results, select the cutting steps that meet the substrate cutting target data from the multiple groups of cutting step cost prediction results as the real-time substrate cutting steps, and send the real-time substrate cutting steps to the substrate cutting equipment.

2. The novel substrate cutting method according to claim 1, characterized in that: The step S102 includes: Extracting information from substrate cutting task data including specific requirements, target size, shape, and accuracy of substrate cutting; Determine the measuring tool used to measure the semiconductor substrate according to the substrate material, size and cutting requirements, determine the measurement method, and use the determined measuring tool to measure the length, width and thickness of the substrate; Accurately mark the cutting positions and lines on the substrate, and record the coordinates or relative positions of the marked points.

3. The novel substrate cutting method according to claim 1, characterized in that: The step S103 includes: Loading the cutting simulation results obtained by processing the real-time substrate image data to be cut through a preset substrate cutting simulation model into the comparison system; The cutting target data in the substrate cutting task data are loaded, including cutting size, shape, and precision index; According to the requirements of the cutting task and the cutting simulation results, the comparison indicators include cutting accuracy, size deviation and shape fit; Use comparison software to compare the cutting simulation results with the cutting target data one by one, calculate the difference or ratio, and use image recognition contour matching technology to compare graphic indicators; According to the results of the comparison operation, the differences between the cutting simulation results and the cutting target data are analyzed and a comparison result report is generated.

4. The novel substrate cutting method according to claim 1, characterized in that: The step S104 includes: If the substrate cutting comparison result shows that the substrate cutting is unqualified, the substrate cutting simulation model is optimized to obtain an optimized substrate cutting simulation model.

5. The novel substrate cutting method as claimed in claim 4, characterized in that: The step S104 includes: According to the parameters and variables of the substrate cutting simulation model, a suitable encoding method is selected to represent each individual, and each individual has a set of cutting parameters; Initialize a population containing multiple individuals, each of which represents a cutting scheme; For each individual in the population, substitute it into the substrate cutting simulation model to obtain the cutting simulation result; According to the comparison between the cutting simulation results and the substrate cutting target data, the fitness value of each individual is calculated; According to the fitness value, the tournament selection method is used to select individuals with higher fitness from the population as parents; Perform a crossover operation on the selected parent individuals to generate new offspring individuals by exchanging gene fragments or recombining chromosomes, and perform mutation operations on the offspring individuals. The fitness evaluation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached or other stopping conditions are met.

6. The novel substrate cutting method according to claim 1, characterized in that: The step S105 includes: receiving a substrate cutting step data set from a database, the substrate cutting step data set including a cutting sequence, a cutting depth, and a cutting speed of a plurality of cutting steps; In the optimized substrate cutting simulation model, the simulation environment is initialized according to the real-time image data of the substrate to be cut. The initialization of the simulation environment includes setting the size parameters, shape parameters, material parameters of the substrate, and the type and parameters of the cutting tool.

7. The novel substrate cutting method according to claim 6, characterized in that: The step S105 includes: According to the order of the substrate cutting step data combination, the simulation of each cutting step is performed in sequence, and during the simulation process, the cutting effect, cutting force, and cutting temperature indicators are collected; Record simulation results for each cutting step, including the shape and size of the substrate after cutting and the cutting quality; After completing the simulation of all cutting steps, multiple sets of cutting step simulation results are generated. The multiple sets of cutting step simulation results include recording the simulation situation of each cutting step and the state of the substrate after cutting.

Citation Information

Patent Citations

  • Cutting parameter optimization method and device, equipment and medium

    CN116047921A

  • Intelligent control method and system for steel plate cutting

    CN116749085A

  • Automatic blanking track planning method for battery protection plate

    CN118543990A

  • A method of assessing a cutting process

    EP3367191A1

Cited By

  • Crystal cutting method and device and storage medium

    CN119694461A