Damage Control Method and System for Sapphire Wafer Cutting

Abstract

The present invention relates to the technical field of wafer cutting analysis, and particularly to a damage control method and system for sapphire wafer cutting. The present invention analyzes the pre-cutting state of a sapphire wafer based on laser cutting control data and ingot manufacturing process data; analyzes the pre-delivery state of auxiliary gas based on auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer; evaluates the chipping risk of the sapphire wafer after laser cutting based on the ingot manufacturing process data and chipping data of the sapphire wafer; constructs a chipping risk prediction model for the sapphire wafer according to the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk evaluation result, and predicts the chipping risk of the sapphire wafer to be cut; and optimizes the laser cutting process of the sapphire wafer. The present invention can optimize the laser cutting process of the sapphire wafer; improve the yield and overall performance of the sapphire wafer.

Description

Technical Field

[0001] The present invention relates to the technical field of wafer cutting analysis, and particularly to a damage control method and system for sapphire wafer cutting. Background Art

[0002] Sapphire wafers are materials with excellent physical and chemical properties and are widely used in manufacturing fields such as optics and semiconductors. They are excellent raw materials for manufacturing LED substrates, optical windows, and camera lenses. Therefore, high-precision cutting of sapphire ingots is required to avoid damage to the final sapphire wafer products. Traditional sapphire wafer cutting methods usually involve mechanical cutting using a grinding wheel or the like. This method has a low cost, but due to the high hardness of sapphire, large stress concentrations will be generated on the ingot during the cutting process. This stress concentration will cause cracks to appear at the edges of the sapphire wafers and even cause the wafers to break as a whole, reducing the yield rate of sapphire wafers and affecting the subsequent processing of the wafers. Therefore, to solve the problem of stress concentration, laser cutting technology has emerged. By using a high-energy laser beam to locally heat the material, melting or vaporizing it, the cutting of sapphire wafers can be achieved, effectively avoiding the problem of stress concentration. However, because laser cutting uses a high-energy laser beam to locally heat the material, it will cause thermal stress changes at the cutting edge, resulting in the phenomenon of chipping.

[0003] However, when analyzing the cutting damage of sapphire wafers in the prior art, only the damage caused by stress changes during cutting to the wafers is analyzed, and the in-depth analysis of the chipping problem that occurs in the wafers after laser cutting is not considered. At the same time, it also ignores how to reduce the impact on the chipping situation of sapphire wafers by controlling the relevant parameters of the laser cutting process and the assist gas. As a result, the quality of the cut sapphire wafer products is uneven, reducing the wafer yield rate and the cutting efficiency of sapphire wafers, and further affecting the performance of the subsequent production products.

[0004] To solve these problems, the present application designs a damage control method and system for sapphire wafer cutting. Summary of the Invention

[0005] The object of the present invention is to provide a damage control method and system for sapphire wafer cutting. The damage control method for sapphire wafer cutting provided by the embodiments of the present invention can comprehensively analyze the cutting state and the assist gas delivery state, and analyze the risk of chipping, thereby realizing the prediction of the chipping risk of the wafer to be cut. It can optimize the laser cutting process of sapphire wafers and improve the yield rate and overall performance of sapphire wafers.

[0006] The present invention is implemented as follows:

[0007] In a first aspect, the present invention provides a damage control method for sapphire wafer cutting, including the following steps:

[0008] S1. Obtain the laser cutting control data and auxiliary gas delivery data of the sapphire wafer, and at the same time obtain the ingot manufacturing process data and chipping data of the sapphire wafer;

[0009] S2. Import the laser cutting control data and the ingot manufacturing process data into a pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer;

[0010] S3. Import the auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer into an auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas;

[0011] S4. Import the ingot manufacturing process data and the chipping data of the sapphire wafer into a chipping risk assessment model to evaluate the chipping risk of the sapphire wafer after laser cutting;

[0012] S5. Construct a chipping risk prediction model for the sapphire wafer based on the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk assessment result, so as to predict the chipping risk of the sapphire wafer to be cut;

[0013] S6. Optimize the laser cutting process of the sapphire wafer according to the chipping risk prediction result of the sapphire wafer to be cut.

[0014] Preferably, on the basis of the above solution, in step S2, the pre-cutting state coefficient is accurately calculated by substituting the laser cutting control data and the ingot manufacturing process data of the sapphire wafer into the pre-cutting state coefficient calculation formula, realizing the accurate quantification of the overall state of the laser cutting process of the sapphire wafer. In this embodiment, step S2 not only provides scientific and quantified data of the reference laser cutting state for subsequent calculation of the delivery state coefficient and the chipping risk coefficient, but also, as a key input parameter, the pre-cutting state coefficient not only enhances the accuracy and efficiency of the quantification of the cutting state of the sapphire wafer, but also helps to evaluate the efficiency of the gas delivery system and the chipping risk. The controllability and stability of the entire cutting process are significantly improved, laying a solid technical foundation for the high-quality cutting of the sapphire wafer. Step S2 includes the following specific steps:

[0015] S21. Extract the laser cutting control data and the ingot manufacturing process data of the sapphire wafer;

[0016] S22. Import the laser cutting control data and the ingot manufacturing process data of the sapphire wafer into the pre-cutting state coefficient calculation formula to calculate the pre-cutting state coefficient of the sapphire wafer; the pre-cutting state coefficient calculation formula is:

[0017] ;

[0018] In the formula, QG represents the pre-cutting state coefficient of the sapphire wafer, P is the preset laser cutting power of the sapphire wafer in the laser cutting control data, Pmax and Pmin respectively represent the maximum laser cutting power and the minimum laser cutting power of the laser cutting equipment in the laser cutting control data; D represents the diameter of the sapphire ingot in the ingot manufacturing process data, t represents the preset cutting thickness of the sapphire wafer in the ingot manufacturing process data, and R represents the surface roughness of the sapphire ingot in the ingot manufacturing process data.

[0019] S23. Obtain the pre-cutting state coefficients of multiple sapphire wafers calculated historically.

[0020] On the basis of the above solution, preferably, the auxiliary gas plays a crucial role in laser cutting. It is mainly used to blow away molten materials, cool the cutting area, protect the cutting area, enhance cutting energy, improve the quality of the cutting surface, prevent slag sticking and improve cutting stability. The auxiliary gas can effectively remove the molten materials at the incision through high-pressure injection, prevent the re-solidification of the slag, and at the same time cool the cutting area, reduce thermal stress and material deformation, providing guarantee for the high-precision cutting of materials such as sapphire wafers. Therefore, there is an inseparable relationship between the conveying state of the auxiliary gas and the cutting state of the wafer. In step S3 of this embodiment, by extracting the relevant data of the auxiliary gas conveying and combining it with the pre-cutting state coefficient of the sapphire wafer, the pre-conveying state coefficient of the auxiliary gas is calculated through the pre-conveying state coefficient calculation formula. It can comprehensively and systematically evaluate the overall efficiency of the gas conveying system, ensure that during the actual operation process, the gas flow rate and pressure can accurately meet the various strict requirements of the cutting process, thereby improving the cutting quality and stability. In this embodiment, introducing the pre-cutting state coefficient into the above formula can not only closely combine the overall state of the cutting process with the gas conveying state, but also make the pre-conveying state coefficient more accurately reflect various complex situations under the actual cutting conditions. In this way, the gas conveying parameters are optimized and adjusted to ensure that it can maintain the best performance in different cutting stages. Step S3 includes the following specific steps:

[0021] S31. Extract the auxiliary gas conveying data and the calculated pre-cutting state coefficient of the sapphire wafer;

[0022] S32. Import the auxiliary gas conveying data and the pre-cutting state coefficient of the sapphire wafer into the pre-conveying state coefficient calculation formula to calculate the pre-conveying state coefficient of the auxiliary gas; the pre-conveying state coefficient calculation formula is:

[0023] ;

[0024] Wherein, SS represents the pre-delivery state coefficient of the auxiliary gas, Q represents the pre-set auxiliary gas flow rate in the auxiliary gas delivery data, Qmax represents the maximum auxiliary gas flow rate allowed by the delivery equipment in the auxiliary gas delivery data, Pt represents the target pressure of the auxiliary gas pre-set in the auxiliary gas delivery data, represents the pressure loss generated during the auxiliary gas delivery process in the auxiliary gas delivery data;

[0025] Among them, the pressure loss generated during the auxiliary gas delivery process in the auxiliary gas delivery data has the following calculation formula:

[0026] ;

[0027] Wherein, f represents the friction coefficient of the auxiliary gas delivery pipeline, Lg represents the length of the auxiliary gas delivery pipeline, Dg represents the inner diameter of the auxiliary gas delivery pipeline, v represents the average flow velocity of the auxiliary gas in the delivery pipeline, represents the gas density of the auxiliary gas;

[0028] S33. Obtain the pre-delivery state coefficients of the auxiliary gas corresponding to multiple sapphire wafers in history obtained by calculation.

[0029] On the basis of the above solution, preferably, in step S4, the manufacturing process data and chipping data of the sapphire wafer crystal bar are substituted into the chipping risk coefficient calculation formula to accurately calculate the chipping risk coefficient of the sapphire wafer. The accurate quantification of the chipping risk is realized, and the severity and distribution of chipping during the cutting process are accurately evaluated. In this embodiment, the chipping is divided into circumferential chipping and diffusion chipping, which can more comprehensively and meticulously evaluate the impact of chipping on the cutting quality of the sapphire wafer. Among them, the circumferential chipping mainly reflects the edge damage of the sapphire wafer and can help optimize the cutting parameters; the diffusion chipping reflects the internal damage of the sapphire wafer and can help evaluate the material integrity and process stability. By combining the data of circumferential chipping and diffusion chipping, the chipping risk can be more accurately evaluated and analyzed. Step S4 includes the following specific contents:

[0030] S41. Extract the crystal bar manufacturing process data and chipping data of the sapphire wafer;

[0031] S42. Import the crystal bar manufacturing process data and chipping data into the chipping risk coefficient calculation formula to calculate the chipping risk coefficient of the sapphire wafer; the chipping risk coefficient calculation formula is:

[0032] ;

[0033] Wherein, BF represents the edge chipping risk coefficient of the sapphire wafer, N represents the number of sapphire wafers cut from the sapphire ingot in the ingot manufacturing process data, L represents the length of the sapphire ingot in the ingot manufacturing process data, ta represents the thickness of the sapphire wafer actually cut in the edge chipping data, Ln represents the length of the diffused edge chipping on the sapphire wafer actually cut in the edge chipping data, and Lw represents the length of the circumferential edge chipping on the sapphire wafer actually cut in the edge chipping data;

[0034] S43. Obtain the calculated edge chipping risk coefficients of multiple sapphire wafers in history.

[0035] Preferably, on the basis of the above solution, step S5 includes the following specific steps:

[0036] S51. Obtain the sapphire wafer edge chipping sample data for training the sapphire wafer edge chipping risk prediction model. The sapphire wafer edge chipping sample data includes the ingot manufacturing process data of multiple sapphire wafers in history, the calculated pre-cutting state coefficients of multiple sapphire wafers in history, and the pre-delivery state coefficients of the corresponding auxiliary gases. At the same time, it also includes the edge chipping risk coefficients of multiple sapphire wafers in history;

[0037] S52. Divide the sapphire wafer edge chipping sample data for training the sapphire wafer edge chipping risk prediction model into an edge chipping sample training set and an edge chipping sample test set, construct a regression network model. Use the ingot manufacturing process data, pre-cutting state coefficients of the sapphire wafers in the edge chipping sample training set, and the pre-delivery state coefficients of the corresponding auxiliary gases as the input of the regression network model, and use the edge chipping risk coefficients of the sapphire wafers in the edge chipping sample training set as the output of the regression network model to train the regression network model to obtain an initial regression network model; Use the mean square error algorithm to evaluate the model effect of the initial regression network model, and select the corresponding initial regression network model greater than or equal to the preset evaluation value as the sapphire wafer edge chipping risk prediction model;

[0038] S53. Calculate the pre-cutting state coefficient of the sapphire wafer to be cut and the pre-delivery state coefficient of the corresponding auxiliary gas, and input the ingot manufacturing process data, pre-cutting state coefficient of the sapphire wafer to be cut, and the pre-delivery state coefficient of the corresponding auxiliary gas into the sapphire wafer edge chipping risk prediction model, and output the predicted edge chipping risk coefficient of the sapphire wafer to be cut.

[0039] Preferably, on the basis of the above solution, step S5 includes the following specific content:

[0040] Obtain the predicted edge chipping risk coefficient of the sapphire wafer to be cut, preset an edge chipping risk threshold. When the edge chipping risk coefficient of the sapphire wafer to be cut is greater than the edge chipping risk threshold, give an early warning for the optimization of the sapphire wafer laser cutting process to the cutting operator.

[0041] In a second aspect, the present invention provides a damage control system for sapphire wafer cutting, comprising:

[0042] A data acquisition module, configured to acquire laser cutting control data and auxiliary gas delivery data of the sapphire wafer, and at the same time acquire ingot manufacturing process data and chipping data of the sapphire wafer;

[0043] A pre-cutting state analysis module, configured to import the laser cutting control data and the ingot manufacturing process data into a pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer;

[0044] A pre-delivery state analysis module, configured to import the auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer into an auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas;

[0045] A chipping risk assessment module, configured to import the ingot manufacturing process data and the chipping data of the sapphire wafer into a chipping risk assessment model to assess the chipping risk of the sapphire wafer after laser cutting;

[0046] A chipping risk prediction module, configured to construct a chipping risk prediction model for the sapphire wafer based on the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk assessment result, for predicting the chipping risk of the sapphire wafer to be cut;

[0047] A laser cutting process optimization module, configured to optimize the laser cutting process of the sapphire wafer according to the chipping risk prediction result of the sapphire wafer to be cut;

[0048] A control module, configured to control the operation of the data acquisition module, the pre-cutting state analysis module, the pre-delivery state analysis module, the chipping risk assessment module, the chipping risk prediction module, and the laser cutting process optimization module.

[0049] In a third aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein a computer program callable by the processor is stored in the memory; the processor executes a damage control method for sapphire wafer cutting by calling the computer program stored in the memory.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which when run on a computer, cause the computer to execute a damage control method for sapphire wafer cutting.

[0051] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0052] The present invention analyzes the pre-cutting state of a sapphire wafer based on laser cutting control data and ingot manufacturing process data of the sapphire wafer; analyzes the pre-delivery state of the auxiliary gas based on the auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer; evaluates the chipping risk of the sapphire wafer after laser cutting according to the ingot manufacturing process data and chipping data of the sapphire wafer; constructs a chipping risk prediction model for the sapphire wafer based on the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk evaluation result, predicts the chipping risk of the sapphire wafer to be cut; and optimizes the laser cutting process of the sapphire wafer. The present invention can optimize the laser cutting process of the sapphire wafer, improve the yield and overall performance of the sapphire wafer. Description of the Drawings

[0053] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments read in conjunction with the accompanying drawings:

[0054] Figure 1 It is a schematic overall process flow diagram of the damage control method for sapphire wafer cutting according to the present invention;

[0055] Figure 2 It is a schematic structural diagram of the damage control system for sapphire wafer cutting according to the present invention;

[0056] Figure 3 It is a schematic process flow diagram of laser cutting of a sapphire wafer in the damage control method for sapphire wafer cutting according to the present invention. Detailed Embodiments

[0057] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. Without conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0058] Embodiment 1

[0059] As Figure 1 、 Figure 3 shown, this embodiment provides a damage control method for sapphire wafer cutting, which specifically includes the following steps:

[0060] S1. Obtain the laser cutting control data and auxiliary gas delivery data of the sapphire wafer, and at the same time obtain the ingot manufacturing process data and chipping data of the sapphire wafer;

[0061] S2. Import the laser cutting control data and the ingot manufacturing process data into the pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer;

[0062] S3. Import the auxiliary gas delivery data and the analysis results of the pre-cutting state of the sapphire wafer into the auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas;

[0063] S4. Import the ingot manufacturing process data and chipping data of the sapphire wafer into the chipping risk assessment model to evaluate the chipping risk of the sapphire wafer after laser cutting;

[0064] S5. Construct a chipping risk prediction model for the sapphire wafer based on the analysis results of the pre-cutting state of the sapphire wafer, the analysis results of the pre-delivery state of the auxiliary gas, and the chipping risk assessment results, which is used to predict the chipping risk of the sapphire wafer to be cut;

[0065] S6. Optimize the laser cutting process of the sapphire wafer according to the chipping risk prediction result of the sapphire wafer to be cut.

[0066] As a preferred technical solution of the present invention, step S2 includes the following specific steps:

[0067] S21. Extract the laser cutting control data and ingot manufacturing process data of the sapphire wafer;

[0068] S22. Import the laser cutting control data and ingot manufacturing process data of the sapphire wafer into the pre-cutting state coefficient calculation formula to calculate the pre-cutting state coefficient of the sapphire wafer; the pre-cutting state coefficient calculation formula is:

[0069] ;

[0070] In the formula, QG represents the pre-cutting state coefficient of the sapphire wafer, P is the preset laser cutting power of the sapphire wafer in the laser cutting control data, Pmax and Pmin respectively represent the maximum laser cutting power and the minimum laser cutting power of the laser cutting equipment in the laser cutting control data; D represents the diameter of the sapphire ingot in the ingot manufacturing process data, t represents the preset cutting thickness of the sapphire wafer in the ingot manufacturing process data, and R represents the surface roughness of the sapphire ingot in the ingot manufacturing process data;

[0071] S23. Obtain the pre-cutting state coefficients of multiple historical sapphire wafers calculated.

[0072] As a preferred technical solution of the present invention, step S3 includes the following specific steps:

[0073] S31. Extract the auxiliary gas delivery data and the calculated pre-cutting state coefficient of the sapphire wafer;

[0074] S32. Import the auxiliary gas delivery data and the pre-cutting state coefficient of the sapphire wafer into the pre-delivery state coefficient calculation formula to calculate the pre-delivery state coefficient of the auxiliary gas; the pre-delivery state coefficient calculation formula is:

[0075] ;

[0076] In the formula, SS represents the pre-delivery state coefficient of the auxiliary gas, Q represents the pre-set auxiliary gas flow rate in the auxiliary gas delivery data, Qmax represents the maximum auxiliary gas flow rate allowed by the delivery equipment in the auxiliary gas delivery data, Pt represents the target pressure of the auxiliary gas pre-set in the auxiliary gas delivery data, represents the pressure loss generated during the auxiliary gas delivery process in the auxiliary gas delivery data;

[0077] S33. Obtain the pre-delivery state coefficients of the auxiliary gas corresponding to multiple sapphire wafers in history calculated.

[0078] As a preferred technical solution of the present invention, step S4 includes the following specific contents:

[0079] S41. Extract the ingot manufacturing process data and chipping data of the sapphire wafer;

[0080] S42. Import the ingot manufacturing process data and chipping data into the chipping risk coefficient calculation formula to calculate the chipping risk coefficient of the sapphire wafer; the chipping risk coefficient calculation formula is:

[0081] ;

[0082] In the formula, BF represents the chipping risk coefficient of the sapphire wafer, N represents the number of sapphire wafers cut from the sapphire ingot in the ingot manufacturing process data, L represents the length of the sapphire ingot in the ingot manufacturing process data, ta represents the thickness of the sapphire wafer actually cut in the chipping data, Ln represents the length of the diffusion chipping on the sapphire wafer actually cut in the chipping data, and Lw represents the length of the circumferential chipping on the sapphire wafer actually cut in the chipping data;

[0083] S43. Obtain the chipping risk coefficients of multiple sapphire wafers in history calculated.

[0084] As a preferred technical solution of the present invention, step S5 includes the following specific steps:

[0085] S51. Obtain the chipping sample data of sapphire wafers for training the chipping risk prediction model of sapphire wafers. The chipping sample data of sapphire wafers includes the ingot manufacturing process data of multiple historical sapphire wafers, the calculated pre-cutting state coefficients of multiple historical sapphire wafers, and the pre-delivery state coefficients of the corresponding auxiliary gases. At the same time, it also includes the chipping risk coefficients of multiple historical sapphire wafers;

[0086] S52. Divide the chipping sample data of sapphire wafers for training the chipping risk prediction model of sapphire wafers into a chipping sample training set and a chipping sample test set. Construct a regression network model. Use the ingot manufacturing process data, pre-cutting state coefficients of sapphire wafers, and pre-delivery state coefficients of the corresponding auxiliary gases in the chipping sample training set as the input of the regression network model, and use the chipping risk coefficients of sapphire wafers in the chipping sample training set as the output of the regression network model. Train the regression network model to obtain an initial regression network model; Use the mean squared error algorithm to evaluate the model effect of the initial regression network model, and select the corresponding initial regression network model greater than or equal to the preset evaluation value as the chipping risk prediction model of sapphire wafers;

[0087] S53. Calculate the pre-cutting state coefficient of the sapphire wafer to be cut and the pre-delivery state coefficient of the corresponding auxiliary gas. Input the ingot manufacturing process data, pre-cutting state coefficient of the sapphire wafer to be cut, and the pre-delivery state coefficient of the corresponding auxiliary gas into the chipping risk prediction model of sapphire wafers, and output the predicted chipping risk coefficient of the sapphire wafer to be cut.

[0088] As a preferred technical solution of the present invention, step S5 includes the following specific contents:

[0089] Obtain the predicted chipping risk coefficient of the sapphire wafer to be cut, and preset a chipping risk threshold. When the chipping risk coefficient of the sapphire wafer to be cut is greater than the chipping risk threshold, give an early warning of the laser cutting process optimization of the sapphire wafer to the cutting operator; It should be noted that the value-taking method of the chipping risk threshold is: obtain the chipping data and ingot manufacturing process data of multiple historical sapphire wafers, input the chipping data and ingot manufacturing process data into the chipping risk coefficient calculation formula for calculation to obtain the chipping risk coefficient; obtain the chipping risk judgment results of multiple historical sapphire wafers, input the chipping risk coefficients and chipping risk judgment results of multiple historical sapphire wafers into the fitting software, and output the value-taking of the corresponding chipping risk threshold that meets the highest chipping risk judgment accuracy rate.

[0090] Embodiment 2

[0091] As Figure 2 shown, this embodiment provides a damage control system for sapphire wafer cutting, including:

[0092] A data acquisition module, configured to acquire laser cutting control data and auxiliary gas delivery data of a sapphire wafer, and at the same time acquire ingot manufacturing process data and chipping data of the sapphire wafer;

[0093] A pre-cutting state analysis module, configured to import the laser cutting control data and the ingot manufacturing process data into a pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer;

[0094] A pre-delivery state analysis module, configured to import the auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer into an auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas;

[0095] A chipping risk assessment module, configured to import the ingot manufacturing process data and the chipping data of the sapphire wafer into a chipping risk assessment model to assess the chipping risk of the sapphire wafer after laser cutting;

[0096] A chipping risk prediction module, configured to construct a chipping risk prediction model for the sapphire wafer according to the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk assessment result, and used to predict the chipping risk of the sapphire wafer to be cut;

[0097] A laser cutting process optimization module, configured to optimize the laser cutting process of the sapphire wafer according to the chipping risk prediction result of the sapphire wafer to be cut;

[0098] A control module, configured to control the operation of the data acquisition module, the pre-cutting state analysis module, the pre-delivery state analysis module, the chipping risk assessment module, the chipping risk prediction module, and the laser cutting process optimization module.

[0099] For the parameters and the steps for each unit module in the above-mentioned damage control system for sapphire wafer cutting according to the present invention to implement corresponding functions, reference may be made to the parameters and steps in the embodiments of the damage control method for sapphire wafer cutting in the foregoing text, and details are not described herein again.

[0100] Embodiment 3

[0101] An electronic device according to an embodiment of the present invention includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory, and the processor executes a damage control method for sapphire wafer cutting by calling the computer program stored in the memory. It should be noted that: all computer programs of the damage control method for sapphire wafer cutting are implemented using the C language. Among them, the data acquisition module, the pre-cutting state analysis module, the pre-delivery state analysis module, the chipping risk assessment module, the chipping risk prediction module, the laser cutting process optimization module, and the control module are all controlled by a remote server.

[0102] Example 4

[0103] This embodiment provides a computer-readable storage medium, on which a rewritable computer program is stored.

[0104] When the computer program runs on a computer device, it causes the computer device to execute the above-described damage control method for sapphire wafer cutting.

[0105] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0106] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A damage control method for sapphire wafer cutting, characterized in that Including the following steps: S1. Obtain the laser cutting control data and auxiliary gas delivery data of the sapphire wafer, and simultaneously obtain the crystal bar manufacturing process data and chipping data of the sapphire wafer; S2. Import the laser cutting control data and the crystal bar manufacturing process data into the pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer; S3. Import the auxiliary gas delivery data and the analysis result of the pre-cutting state of the sapphire wafer into the auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas; S4. Import the crystal bar manufacturing process data and the chipping data of the sapphire wafer into the chipping risk assessment model to evaluate the chipping risk of the sapphire wafer after laser cutting; S5. Construct a chipping risk prediction model for the sapphire wafer based on the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the chipping risk assessment result, which is used to predict the chipping risk of the sapphire wafer to be cut; S6. Optimize the laser cutting process of the sapphire wafer according to the chipping risk prediction result of the sapphire wafer to be cut.

2. The damage control method for sapphire wafer cutting according to claim 1, wherein The step S2 includes the following specific steps: S21. Extract the laser cutting control data and the crystal bar manufacturing process data of the sapphire wafer; S22. Import the laser cutting control data and the crystal bar manufacturing process data of the sapphire wafer into the pre-cutting state coefficient calculation formula to calculate the pre-cutting state coefficient of the sapphire wafer; the pre-cutting state coefficient calculation formula is: ； In the formula, QG represents the pre-cutting state coefficient of the sapphire wafer, P is the preset laser cutting power of the sapphire wafer in the laser cutting control data, Pmax and Pmin respectively represent the maximum laser cutting power and the minimum laser cutting power of the laser cutting equipment in the laser cutting control data; D represents the diameter of the sapphire crystal bar in the crystal bar manufacturing process data, t represents the preset cutting thickness of the sapphire wafer in the crystal bar manufacturing process data, and R represents the surface roughness of the sapphire crystal bar in the crystal bar manufacturing process data; S23. Obtain the pre-cutting state coefficients of multiple historical sapphire wafers calculated.

3. The damage control method for sapphire wafer cutting according to claim 2, wherein The step S3 includes the following specific steps: S31. Extract the auxiliary gas delivery data and the calculated pre-cutting state coefficient of the sapphire wafer; S32. Import the auxiliary gas delivery data and the pre-cutting state coefficient of the sapphire wafer into the pre-delivery state coefficient calculation formula to calculate the pre-delivery state coefficient of the auxiliary gas; the pre-delivery state coefficient calculation formula is: ； In the formula, SS represents the pre-delivery state coefficient of the auxiliary gas, Q represents the pre-set auxiliary gas flow rate in the auxiliary gas delivery data, Qmax represents the maximum auxiliary gas flow rate allowed by the delivery equipment in the auxiliary gas delivery data, Pt represents the target pressure of the auxiliary gas pre-set in the auxiliary gas delivery data, represents the pressure loss generated during the auxiliary gas delivery process in the auxiliary gas delivery data; S33. Obtain the pre-delivery state coefficients of the auxiliary gas corresponding to multiple historical sapphire wafers calculated.

4. The damage control method for sapphire wafer cutting according to claim 3, characterized in that, The step S4 includes the following specific contents: S41. Extract the crystal bar manufacturing process data and the chipping data of the sapphire wafer; S42. Import the crystal bar manufacturing process data and the chipping data into the chipping risk coefficient calculation formula to calculate the chipping risk coefficient of the sapphire wafer; the chipping risk coefficient calculation formula is: ； In the formula, BF represents the edge chipping risk coefficient of the sapphire wafer, N represents the number of sapphire wafers cut from the sapphire ingot in the ingot manufacturing process data, L represents the length of the sapphire ingot in the ingot manufacturing process data, ta represents the thickness of the sapphire wafer actually cut in the edge chipping data, Ln represents the length of the diffused edge chipping on the sapphire wafer actually cut in the edge chipping data, and Lw represents the length of the circumferential edge chipping on the sapphire wafer actually cut in the edge chipping data; S43. Obtain the calculated edge chipping risk coefficients of multiple historical sapphire wafers.

5. The damage control method for sapphire wafer cutting according to claim 4, wherein, The step S5 includes the following specific steps: S51. Obtain the edge chipping sample data of sapphire wafers for training the edge chipping risk prediction model of sapphire wafers. The edge chipping sample data of sapphire wafers includes the ingot manufacturing process data of multiple historical sapphire wafers, the calculated pre-cutting state coefficients of multiple historical sapphire wafers, and the pre-delivery state coefficients of the corresponding auxiliary gases. At the same time, it also includes the edge chipping risk coefficients of multiple historical sapphire wafers; S52. Divide the edge chipping sample data of sapphire wafers for training the edge chipping risk prediction model of sapphire wafers into an edge chipping sample training set and an edge chipping sample test set. Construct a regression network model. Use the ingot manufacturing process data, pre-cutting state coefficients of the sapphire wafers in the edge chipping sample training set, and the pre-delivery state coefficients of the corresponding auxiliary gases as the input of the regression network model, and use the edge chipping risk coefficients of the sapphire wafers in the edge chipping sample training set as the output of the regression network model. Train the regression network model to obtain an initial regression network model; use the equalization error algorithm to evaluate the model effect of the initial regression network model, and select the corresponding initial regression network model greater than or equal to the preset evaluation value as the edge chipping risk prediction model of sapphire wafers; S53. Calculate the pre-cutting state coefficient of the sapphire wafer to be cut and the pre-delivery state coefficient of the corresponding auxiliary gas. Input the ingot manufacturing process data, pre-cutting state coefficient of the sapphire wafer to be cut, and the pre-delivery state coefficient of the corresponding auxiliary gas into the edge chipping risk prediction model of sapphire wafers, and output the predicted edge chipping risk coefficient of the sapphire wafer to be cut.

6. The damage control method for sapphire wafer cutting according to claim 5, characterized in that, The step S5 includes the following specific content: Obtain the predicted edge chipping risk coefficient of the sapphire wafer to be cut, and preset an edge chipping risk threshold. When the edge chipping risk coefficient of the sapphire wafer to be cut is greater than the edge chipping risk threshold, give an early warning for the optimization of the laser cutting process of the sapphire wafer to the cutting operator.

7. A damage control system for sapphire wafer cutting, which is implemented based on the damage control method for sapphire wafer cutting according to any one of claims 1-6, characterized in that, The system includes: A data acquisition module, which is used to acquire the laser cutting control data and auxiliary gas delivery data of the sapphire wafer, and at the same time acquire the ingot manufacturing process data and edge chipping data of the sapphire wafer; A pre-cutting state analysis module, which is used to import the laser cutting control data and ingot manufacturing process data into the pre-cutting state analysis model to analyze the pre-cutting state of the sapphire wafer; A pre-delivery state analysis module, which is used to import the auxiliary gas delivery data and the pre-cutting state analysis result of the sapphire wafer into the auxiliary gas pre-delivery state analysis model to analyze the pre-delivery state of the auxiliary gas; An edge chipping risk assessment module, which is configured to import the ingot manufacturing process data and edge chipping data of a sapphire wafer into an edge chipping risk assessment model to assess the edge chipping risk of the sapphire wafer after laser cutting; An edge chipping risk prediction module, which is configured to construct an edge chipping risk prediction model for a sapphire wafer according to the analysis result of the pre-cutting state of the sapphire wafer, the analysis result of the pre-delivery state of the auxiliary gas, and the edge chipping risk assessment result, and is used to predict the edge chipping risk of the sapphire wafer to be cut; A laser cutting process optimization module, which is configured to optimize the laser cutting process of the sapphire wafer according to the edge chipping risk prediction result of the sapphire wafer to be cut; A control module, which is configured to control the operation of the data acquisition module, the pre-cutting state analysis module, the pre-delivery state analysis module, the edge chipping risk assessment module, the edge chipping risk prediction module, and the laser cutting process optimization module.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the damage control method for sapphire wafer cutting according to any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, Stored with instructions, when the instructions run on a computer, the computer is caused to execute the damage control method for sapphire wafer cutting according to any one of claims 1-6.

Images