Silicon wafer cut-through judgment method and device, electronic equipment and storage medium

By calculating the torque ratio of the current tool and comparing it with the threshold of the cutting torque ratio of the target subdivided group, it automatically determines whether the silicon rod is cut through, solving the problem of inefficient judgment in the prior art, and achieving more efficient automated judgment.

CN120196053AActive Publication Date: 2025-06-24QINGDAO GAOCE TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311741023.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-12-15
Publication Date
2025-06-24
Estimated Expiration
2043-12-15

AI Technical Summary

Technical Problem

In the prior art, it is inefficient to judge whether a silicon rod is cut through, and it depends on manual observation and is not efficient.

Method used

By obtaining the feed torque average, periodic torque average and process-related parameters of the current tool time, calculate the current torque ratio, and determine the cutting torque ratio threshold of the target subdivided group based on the pre-divided process group and subdivided group, and determine whether the current torque ratio is less than the threshold to determine whether the silicon rod is cut through.

Benefits of technology

It realizes an automated judgment of whether the silicon rod is cut through, improves the judgment efficiency, and is more accurate and efficient than manual observation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120196053A_ABST
    Figure CN120196053A_ABST
Patent Text Reader

Abstract

The invention provides a silicon wafer cut-through judgment method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a feed torque mean value of a current cutting time, a period torque mean value of a last period and process related parameters; according to the feed torque mean value and the periodic torque mean value, the current torque ratio of the current tool time is obtained; determining a target process group corresponding to the process related parameters from pre-divided N process groups according to the process related parameters; according to the feed torque mean value, determining a target subdivision group corresponding to the current cutting time from the target process group; whether the current torque ratio is smaller than a tangent torque ratio threshold value corresponding to the target subdivision group or not is judged, and the tangent torque ratio threshold value is determined according to the minimum torque ratio of the target subdivision group; and if yes, determining that the silicon rod corresponding to the current cutting time is in a cut-through state. Whether the silicon rod is cut through or not can be automatically judged, and the judgment efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the technical field of silicon wafer cutting. Specifically, it relates to a method, device, electronic device and storage medium for judging silicon wafer penetration. Background Art

[0002] Currently, the slicing machine adopts the reverse cutting process. One disadvantage of the reverse cutting process is that it will form a wire bow, that is, the cutting depth of the steel wire on the right side of the silicon rod is different from that on the left side, resulting in an uneven entire wire mesh. Therefore, after normal shutdown according to the process recipe during cutting, there will be a problem that the entire silicon rod is not cut through.

[0003] Currently, the way to judge whether the silicon rod is cut through is for workers to open the slicing machine and use a strong flashlight to irradiate and observe the wire mesh, and judge whether it is cut through by the naked eye. This method relies on manual operation and has low judgment efficiency. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, electronic device and computer-readable storage medium for judging silicon wafer penetration, so as to solve the problem of low judgment efficiency when judging whether a silicon rod is cut through in the related art.

[0005] The embodiments of this application provide a method for judging silicon wafer penetration, including: obtaining the average feed torque of the current cutting pass, the average cycle torque of the last cycle and process-related parameters, where the process-related parameters include silicon wafer number, process time and process tension; obtaining the current torque ratio of the current cutting pass according to the average feed torque and the average cycle torque; determining the target process group corresponding to the process-related parameters from N pre-divided process groups according to the process-related parameters, where the N process groups are determined according to the historical process-related parameters of historical cutting passes, each process group corresponds to at least two sub-groups, and N is an integer greater than 1; determining the target sub-group corresponding to the current cutting pass from the target process group according to the average feed torque; judging whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group, where the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target sub-group; if it is less, it is determined that the silicon rod corresponding to the current cutting pass is in a cut-through state.

[0006] In the above implementation process, the additional cutting torque ratio threshold of the target sub-group corresponding to the current tool pass in the target process group is used to judge the current torque ratio of the current tool pass belonging to the target sub-group. Furthermore, when the current torque ratio of the current tool pass is less than the additional cutting torque ratio threshold, it is determined that the silicon rod corresponding to the current tool pass is in a cut-through state. Since the additional cutting torque ratio threshold is determined based on the minimum torque ratio of the target sub-group, and the minimum torque ratio of the target sub-group can reflect the minimum torque ratio required in history when additional cutting is needed, the additional cutting torque ratio threshold determined based on the minimum torque ratio of the target sub-group can be used as a relatively accurate basis for judging whether additional cutting is required for the current tool pass, that is, it can relatively accurately determine whether the silicon rod corresponding to the current tool pass is in a cut-through state. Therefore, compared with the related art, automatic judgment of whether the silicon rod is cut through can be realized, and the judgment efficiency is improved.

[0007] In addition, in the above implementation method, N process groups are also pre-divided based on N process groups, and then the target process group is determined from the N process groups based on the N process groups of the current tool pass. Furthermore, the additional cutting torque ratio threshold of the target sub-group corresponding to the current tool pass in the target process group is used for judgment. That is, in the above implementation method, the cutting situation is also matched based on the process-related parameters of the current tool pass and the average feed torque, and then the additional cutting torque ratio threshold of the target sub-group in the target process group that best matches the cutting situation of the current tool pass is used for judgment, thereby improving the reliability of the additional cutting torque ratio threshold and further improving the judgment accuracy of whether the silicon rod is in a cut-through state.

[0008] Further, the step of determining the target sub-group corresponding to the current tool pass from the target process group according to the average feed torque includes: for each sub-group in the target process group, comparing the average feed torque with the minimum average feed torque and the maximum average feed torque of the sub-group to obtain the comparison result corresponding to the sub-group; and determining whether the sub-group is the target sub-group according to the comparison result corresponding to the sub-group.

[0009] In the above implementation method, by comparing the average feed torque with the minimum average feed torque and the maximum average feed torque of the sub-group, it can be determined whether the average feed torque falls within the range of the average feed torque of the sub-group, so as to quickly determine whether the sub-group is the target sub-group.

[0010] Further, if each process group corresponds to two sub-groups, the method further includes: for each process group, obtaining the average historical feed torque of multiple historical tool passes in the process group; and dividing the average historical feed torque of multiple historical tool passes by using the quantile classification method to obtain the high-torque sub-group and the low-torque sub-group corresponding to the process group.

[0011] Further, for each process group, the average historical feed torque of multiple historical tool passes is divided by using a quantile classification method to obtain a high-torque subgroup and a low-torque subgroup corresponding to the process group, including: for each historical tool pass among the multiple historical tool passes in each process group, sorting the average historical feed torque of the historical tool pass, and obtaining the torque at the set quantile as the sub-divided torque of the process group; dividing the process group into a high-torque subgroup and a low-torque subgroup according to the sub-divided torque of the process group and the average historical feed torque of the multiple historical tool passes.

[0012] In the above implementation, by using the quantile classification method to divide the average historical feed torque of multiple historical tool passes and dividing the process group into a high-torque subgroup and a low-torque subgroup at the set quantile, the high-torque subgroup and the low-torque subgroup have the same probability of becoming the target subgroup corresponding to the current tool pass.

[0013] Further, determining the target subgroup corresponding to the current tool pass from the target process group according to the average feed torque includes: if the target process group includes a target high-torque subgroup and a target low-torque subgroup, comparing the average feed torque with the minimum and maximum average feed torques of the target high-torque subgroup to obtain the comparison result of the target high-torque subgroup; comparing the average feed torque with the minimum and maximum average feed torques of the target low-torque subgroup to obtain the comparison result of the target low-torque subgroup; determining the target subgroup from the target high-torque subgroup and the target low-torque subgroup according to the comparison result of the target high-torque subgroup and the comparison result of the target low-torque subgroup.

[0014] In the above implementation, by comparing the average feed torque with the minimum and maximum average feed torques of the target high-torque subgroup of the target process group respectively, and with the minimum and maximum average feed torques of the target low-torque subgroup of the target process group, it can be determined whether the average feed torque specifically falls within the range of the average feed torque of the target high-torque subgroup or within the range of the average feed torque of the target low-torque subgroup, so that the target subgroup can be quickly determined.

[0015] Further, before determining whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target subgroup, the method further includes: obtaining M historical torque ratios of M historical additional cutting tool passes in the target subgroup; selecting the minimum value from the M historical torque ratios as the minimum torque ratio of the target subgroup; obtaining the additional cutting torque ratio threshold corresponding to the target subgroup according to the minimum torque ratio of the target subgroup.

[0016] In the above implementation, by taking the minimum value of the M historical torque ratios of the M historical cutting tool addition and removal times in the target sub-group as the minimum torque ratio of the target sub-group, the minimum torque ratio can effectively reflect the minimum torque ratio required in history when cutting is needed, so that the cutting torque ratio threshold determined based on the minimum torque ratio of the target sub-group can be accurately used as the basis for judging whether cutting is needed for the current tool pass, thereby improving the accuracy of the judgment result.

[0017] Further, after judging whether the current torque ratio is less than the cutting torque ratio threshold corresponding to the target sub-group, the method further includes: if it is not less than, determining that the silicon rod corresponding to the current tool pass is in a non-penetrated state, and using the cutting addition process to cut the silicon rod corresponding to the current tool pass.

[0018] In the above implementation, if the current torque ratio is not less than the cutting torque ratio threshold corresponding to the target sub-group, it can be considered that the silicon rod has not been penetrated in the current tool pass, so the cutting addition process is used to cut the silicon rod corresponding to the current tool pass, improving the probability of the silicon rod being penetrated.

[0019] Further, the method further includes: judging whether the current tool pass has an abnormal state, where the abnormal state includes a wire break state and a state where the downtime exceeds a preset downtime threshold; if the current tool pass has the abnormal state, determining that the silicon rod corresponding to the current tool pass is in the non-penetrated state, and using the cutting addition process to cut the silicon rod corresponding to the current tool pass.

[0020] In the above implementation, when there is a wire break in the current cutting tool pass or the downtime exceeds the preset downtime threshold, it indicates that an abnormality has occurred in the cutting process. At this time, it is determined that the silicon rod corresponding to the current tool pass is in a non-penetrated state, and the cutting addition process is used to cut the silicon rod corresponding to the current tool pass, which can prevent the situation where the silicon rod is not penetrated.

[0021] The embodiment of the present application further provides a silicon wafer penetration judgment device, including: an acquisition module, configured to acquire the average feed torque of the current cutting pass, the average cycle torque of the last cycle, and process-related parameters, and acquire the current torque ratio of the current cutting pass according to the average feed torque and the average cycle torque; wherein, the process-related parameters include the silicon wafer number, the process time, and the process tension; a determination module, configured to determine a target process group corresponding to the process-related parameters from N pre-divided process groups according to the process-related parameters, and determine a target sub-group corresponding to the current cutting pass from the target process group according to the average feed torque; wherein, the N process groups are determined according to the historical process-related parameters of historical cutting passes, each process group corresponds to at least two sub-groups, and N is an integer greater than 1; a judgment module, configured to judge whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group, and if so, determine that the silicon rod corresponding to the current cutting pass is in a penetrated state; wherein, the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target sub-group.

[0022] The embodiment of the present application further provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement any one of the above silicon wafer penetration judgment methods.

[0023] The embodiment of the present application also provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by at least one processor, any one of the above silicon wafer penetration judgment methods is implemented. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a schematic flowchart of a silicon wafer penetration judgment method provided by an embodiment of the present application;

[0026] Figure 2 It is a schematic flowchart of a process for obtaining the additional cutting torque ratio threshold of a target sub-group provided by an embodiment of the present application;

[0027] Figure 3 It is a schematic structural diagram of a silicon wafer penetration judgment device provided by an embodiment of the present application;

[0028] Figure 4A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0029] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application.

[0030] To solve the problem of low judgment efficiency in judging whether a silicon rod is cut through in the related art, an embodiment of the present application provides a method for judging silicon wafer penetration. Refer to Figure 1 as shown in Figure 1 a flowchart of the method for judging silicon wafer penetration provided by an embodiment of the present application, including:

[0031] S101: Obtain the average feed torque of the current cutting pass, the average cycle torque of the last cycle, and process-related parameters.

[0032] In an embodiment of the present application, multiple torques at the feed position during the cutting of the current cutting pass can be obtained by sampling, and the average value is calculated to obtain the average feed torque of the current cutting pass. In addition, it is also possible to only obtain the torque at the feed position when the current cutting pass starts to cut, and use it as the average feed torque of the current cutting pass.

[0033] In an embodiment of the present application, multiple torques at the feed position in the last cycle of the current cutting pass can be obtained by sampling, and the average value is calculated to obtain the average cycle torque of the last cycle of the current cutting pass. Alternatively, it is also possible to only obtain the torque at the feed position when the last cycle of the current cutting pass starts, and use it as the average cycle torque of the last cycle of the current cutting pass.

[0034] It can be understood that during the cutting process of a cutting pass, the number of cutting cycles or the cutting time is often set. For example, 120 cycles are set, and each cycle is 1 minute, which is equivalent to a total cutting time of 120 minutes. Then when the current cutting pass cuts to the last minute, that is, cuts to the last cycle.

[0035] In an embodiment of the present application, the torque at the feed position can be obtained by setting a sensor at the feed position. In addition, the torque at the feed position can also be calculated according to the radius, tension, cutting speed, etc. of the diamond wire used for cutting. The present application does not limit the acquisition method of the torque at the feed position.

[0036] In an embodiment of the present application, the process-related parameters refer to the parameters related to the silicon wafer cutting process, which include the silicon wafer specifications, process time, and process tension. In addition, the process-related parameters may also include at least one of parameters such as the machine tool, the wire diameter of the diamond wire used for cutting, and the length of the silicon rod to be cut.

[0037] In the embodiments of the present application, process-related parameters can be input by a user into an electronic device that executes the method of the embodiments of the present application, so that the electronic device obtains the process-related parameters of the current tool pass.

[0038] S102: Obtain the current torque ratio of the current tool pass according to the average feed torque and the average cycle torque.

[0039] In the embodiments of the present application, the ratio between the average feed torque of the current tool pass and the average cycle torque of the last cycle can be calculated, and this ratio is used as the current torque ratio of the current tool pass.

[0040] In the actual application process, the ratio is usually the value obtained by dividing the average cycle torque of the last cycle by the average feed torque. Of course, the ratio can also be the value obtained by dividing the average feed torque by the average cycle torque of the last cycle. Here, specifically, the example where the ratio is the value obtained by dividing the average cycle torque of the last cycle by the average feed torque is taken.

[0041] S103: Determine the target process group corresponding to the process-related parameters from the pre-divided N process groups according to the process-related parameters of the current tool pass.

[0042] In the embodiments of the present application, the N process groups are determined according to the historical process-related parameters of historical tool passes. Each process group corresponds to at least two sub-groups, and N is an integer greater than 1.

[0043] Exemplarily, assume that the historical process-related parameters include m machines, n types of silicon wafers, k wire diameters, j rod lengths, l process tensions, and p process times. And each machine can cut these n types of silicon wafers with these k wire diameters, j rod lengths, l process tensions, and p process times. Then, N = m * n * k * j * l * p process groups can be divided. And according to the machine number, silicon wafer number, wire diameter, rod length, process tension, and process time of the current tool pass, the target process group with the machine number, silicon wafer number, wire diameter, rod length, process tension, and process time of the current tool pass can be found from these m * n * k * j * l * p process groups.

[0044] S104: Determine the target sub-group corresponding to the current tool pass from the target process group according to the average feed torque of the current tool pass.

[0045] In the embodiments of the present application, for each process group, the average historical feed torque of multiple historical tool passes in the process group can be obtained, and then the average historical feed torque of multiple historical tool passes is divided to obtain K sub-groups corresponding to the process group.

[0046] In the embodiments of the present application, the specific value of K can be configured according to actual needs. The larger K is, the more detailed the division of the average historical feed torque is.

[0047] In the embodiment of the present application, the average historical feed torque of the historical tool passes can be obtained by obtaining the historical feed torque of the historical tool passes and then calculating the average value.

[0048] In the embodiment of the present application, the average historical feed torque of multiple historical tool passes can be divided by using, but not limited to, the quantile classification method.

[0049] In the embodiment of the present application, when performing step S104, for each subgroup in the target process group, the average feed torque can be compared with the minimum average feed torque and the maximum average feed torque of the subgroup to obtain the comparison result corresponding to the subgroup, and then according to the comparison result corresponding to the subgroup, it can be determined whether the subgroup is the target subgroup.

[0050] It can be understood that the minimum average feed torque and the maximum average feed torque of the subgroup reflect the range of the average feed torque of the subgroup. By comparing the average feed torque with the minimum average feed torque and the maximum average feed torque of the subgroup, it can be determined whether the average feed torque falls within the range of the average feed torque of the subgroup, so that it can be quickly determined whether the subgroup is the target subgroup.

[0051] The following is an example for illustration when K takes the value of 2 and the quantile classification method is used:

[0052] For each historical tool pass among multiple historical tool passes in each process group, the average historical feed torque of the historical tool passes can be sorted, and the torque at the set quantile in the sorting can be obtained as the sub-divided torque of the process group. Then, according to the sub-divided torque of the process group and the historical feed torque of multiple historical tool passes, the process group can be divided into a high-torque subgroup and a low-torque subgroup.

[0053] Exemplarily, the set quantile can be two-thirds, or one-half, or three-fourths, etc. The specific value of the set quantile can be set by the engineer according to actual needs.

[0054] For example, assume that the average historical feed torques of the historical tool passes in a process group are a1, a2, a3, a4, a5, a6 in sequence, and a1 < a2 < a3 < a4 < a5 < a6. Assume that the set quantile takes two-thirds and K is 2. Then the torque corresponding to the set quantile is a4, and the low-torque subgroup [a1, a4] and the high-torque subgroup (a4, a6] of the process group can be obtained.

[0055] Correspondingly, when performing step S104, the average feed torque of the current tool pass can be compared with the minimum and maximum average feed torques of the target high-torque sub-group to obtain the comparison result of the target high-torque sub-group; and the average feed torque of the current tool pass can be compared with the minimum and maximum average feed torques of the target low-torque sub-group to obtain the comparison result of the target low-torque sub-group. Then, based on the comparison results of the target high-torque sub-group and the target low-torque sub-group, the target sub-group is determined from the target high-torque sub-group and the target low-torque sub-group. Among them, the target high-torque sub-group and the target low-torque sub-group are the high-torque sub-group and the low-torque sub-group of the target process group.

[0056] Exemplarily, if the average feed torque of the current tool pass is greater than or equal to the minimum average feed torque of the target high-torque sub-group and less than or equal to the maximum average feed torque of the target high-torque sub-group, it can be determined that the target high-torque sub-group is the target sub-group. Correspondingly, if the average feed torque of the current tool pass is greater than or equal to the minimum average feed torque of the target low-torque sub-group and less than or equal to the maximum average feed torque of the target low-torque sub-group, it can be determined that the target low-torque sub-group is the target sub-group.

[0057] S105: Determine whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group.

[0058] In the embodiment of the present application, the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target sub-group.

[0059] In the embodiment of the present application, before determining whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group, reference can also be made to Figure 2 As shown, the additional cutting torque ratio threshold corresponding to the target sub-group is obtained in the following manner:

[0060] S201: Obtain M historical torque ratios of M historical additional cutting tool passes in the target sub-group.

[0061] In the embodiment of the present application, the M historical additional cutting tool passes can be all the historical additional cutting tool passes in the target sub-group. For each historical additional cutting tool pass in the target sub-group, the average historical feed torque of the historical additional cutting tool pass and the average historical cycle torque of the last cycle can be obtained, and then the ratio between the two is calculated to obtain the historical torque ratio of the historical additional cutting tool pass.

[0062] S202: Select the minimum value from the M historical torque ratios as the minimum torque ratio of the target sub-group.

[0063] S203: Obtain the additional cutting torque ratio threshold corresponding to the target sub-group according to the minimum torque ratio of the target sub-group.

[0064] In some embodiments of the present application, the minimum torque ratio of the target sub-group can be used as the additional cutting torque ratio threshold corresponding to the target sub-group.

[0065] In some other embodiments of the present application, the difference or sum between the minimum torque ratio of the target sub-group and a preset value can also be used as the additional cutting torque ratio threshold corresponding to the target sub-group. The preset value can be set by the engineer according to actual requirements.

[0066] It can be understood that in the embodiments of the present application, the additional cutting torque ratio threshold of the target sub-group can be determined for the target sub-group in the above manner each time the silicon wafer penetration judgment is performed. In addition, it can also be that after the sub-groups of each process group are determined, that is, for each sub-group, the additional cutting torque ratio threshold corresponding to the sub-group of each process group is determined in advance in the above Figure 2 manner, and then each time the silicon wafer penetration judgment is performed, after the target sub-group is determined, the additional cutting torque ratio threshold of the target sub-group can be directly called for judgment.

[0067] S106: If the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group, it is determined that the silicon rod corresponding to the current tool pass is in a penetrated state.

[0068] In the embodiments of the present application, if the current torque ratio is greater than or equal to the additional cutting torque ratio threshold corresponding to the target sub-group, it can be determined that the silicon rod corresponding to the current tool pass is in a non-penetrated state, and the additional cutting process is used to cut the silicon rod corresponding to the current tool pass.

[0069] Optionally, in some embodiments of the present application, if the target sub-group corresponding to the current tool pass cannot be determined from the target process group according to the average feed torque of the current tool pass, it can be determined that the silicon rod corresponding to the current tool pass is in a non-penetrated state, and the additional cutting process is used to cut the silicon rod corresponding to the current tool pass. It can be understood that if there is no matching target sub-group for the current tool pass in the target process group, this means that the feed situation of the current tool pass is not within the historical situation, then it can be considered that there is a feed abnormality, such as an abnormal feed speed, etc. At this time, it is determined that the silicon rod corresponding to the current tool pass is in a non-penetrated state, so that additional cutting can prevent the situation that the silicon rod is not cut through.

[0070] Optionally, in some embodiments of the present application, it is possible to determine whether there is an abnormal state in the current cutting pass. If there is an abnormal state in the current cutting pass, it is determined that the silicon rod corresponding to the current cutting pass is in the non-penetrating state. Among them, the abnormal state includes a wire break state and a state where the downtime exceeds a preset duration threshold. The slicing process is used to cut the silicon rod corresponding to the current cutting pass. When a wire break occurs in the current cutting pass or the downtime exceeds the preset duration threshold, it indicates that an abnormality sufficient to prevent the cutting process from continuing has occurred during the cutting process. At this time, it is determined that the silicon rod corresponding to the current cutting pass is in the non-penetrating state, so that slicing can prevent the situation where the silicon rod is not cut through.

[0071] Among them, the preset duration threshold can be set by the engineer according to the actual situation. For example, it can be set to 30 minutes.

[0072] The silicon wafer penetration judgment method provided by the embodiments of the present application uses the additional cutting torque ratio threshold of the target subgroup corresponding to the current cutting pass in the target process group to judge the current torque ratio of the current cutting pass belonging to the target subgroup. Furthermore, when the current torque ratio of the current cutting pass is less than the additional cutting torque ratio threshold, it is determined that the silicon rod corresponding to the current cutting pass is in the penetrated state. Since the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target subgroup, and the minimum torque ratio of the target subgroup can reflect the minimum torque ratio required historically in the case of additional cutting, the additional cutting torque ratio threshold determined based on the minimum torque ratio of the target subgroup can be used as a relatively accurate basis for judging whether additional cutting is required for the current cutting pass, that is, it can relatively accurately determine whether the silicon rod corresponding to the current cutting pass is in the penetrated state. Therefore, compared with the related art, it is possible to realize the automatic judgment of whether the silicon rod is penetrated, improving the judgment efficiency.

[0073] In addition, in the silicon wafer penetration judgment method provided by the embodiments of the present application, N process groups are also pre-divided based on N process groups. Furthermore, based on the N process groups of the current cutting pass, the target process group is determined from the N process groups, and then the additional cutting torque ratio threshold of the target subgroup corresponding to the current cutting pass in the target process group is used for judgment. That is, in the above implementation manner, the cutting situation is also matched based on the process-related parameters and the average feed torque of the current cutting pass, and then the additional cutting torque ratio threshold of the target subgroup in the target process group that best matches the cutting situation of the current cutting pass is used for judgment, thereby improving the reliability of the additional cutting torque ratio threshold and further improving the judgment accuracy of whether the silicon rod is in the penetrated state.

[0074] Based on the same inventive concept, an apparatus 300 for judging silicon wafer penetration is also provided in the embodiments of the present application. Please refer to Figure 3 as shown, Figure 3 which shows the adoption of Figure 1The method of the silicon wafer cutting through judgment device shown in the figure. It should be understood that the specific functions of the device 300 can be referred to the description above, and the detailed description is appropriately omitted here to avoid repetition. The device 300 includes at least one software function module that can be stored in the memory in the form of software or firmware or fixed in the operating system of the device 300. Specifically:

[0075] See also Figure 3 As shown, the apparatus 300 includes: an acquisition module 301, a determination module 302 and a judgment module 303. Among them:

[0076] The acquisition module 301 is used to acquire the mean value of the feed torque of the current cut, the mean value of the cycle torque of the last cycle and process-related parameters, and acquire the current torque ratio of the current cut according to the mean value of the feed torque and the mean value of the cycle torque; wherein the process-related parameters include the silicon wafer number, process time and process tension;

[0077] The determination module 302 is used to determine, according to the process-related parameters, a target process group corresponding to the process-related parameters from the pre-divided N process groups, and determine, according to the mean value of the feed torque, a target subdivision group corresponding to the current cut from the target process group; wherein the N process groups are determined according to the historical process-related parameters of the historical cuts, each process group corresponds to at least two subdivision groups, and N is an integer greater than 1;

[0078] The judgment module 303 is used to judge whether the current torque ratio is less than the cutting torque ratio threshold corresponding to the target subdivision group. If it is less than, it is determined that the silicon rod corresponding to the current knife pass is in a cut-through state; wherein the cutting torque ratio threshold is determined according to the minimum torque ratio of the target subdivision group.

[0079] In a feasible implementation manner of the embodiment of the present application, the determination module 302 is specifically used to: for each subdivision group in the target process group, compare the feed torque mean with the minimum feed torque mean and the maximum feed torque mean of the subdivision group, obtain the comparison result corresponding to the subdivision group, and determine whether the subdivision group is the target subdivision group based on the comparison result corresponding to the subdivision group.

[0080] In a feasible implementation of the embodiment of the present application, if each process group corresponds to two sub-groups, the acquisition module 301 is also used to obtain, for each process group, the historical feed torque average of multiple historical cuts in the process group; and divide the historical feed torque averages of multiple historical cuts by quantile classification to obtain a high-torque sub-group and a low-torque sub-group corresponding to the process group.

[0081] In the above feasible implementation, the obtaining module 301 is specifically configured to, for each historical cutting pass among multiple historical cutting passes in each process group, sort the average historical feed torque of the historical cutting passes, obtain the torque at the set quantile as the sub - torque of the process group, and divide the process group into a high - torque subgroup and a low - torque subgroup according to the sub - torque of the process group and the average historical feed torque of the multiple historical cutting passes.

[0082] In the above feasible implementation, the determining module 302 is specifically configured to:

[0083] If the target process group includes a target high - torque subgroup and a target low - torque subgroup, then compare the average feed torque with the minimum and maximum average feed torques of the target high - torque subgroup to obtain the comparison result of the target high - torque subgroup;

[0084] Compare the average feed torque with the minimum and maximum average feed torques of the target low - torque subgroup to obtain the comparison result of the target low - torque subgroup;

[0085] Determine the target subgroup from the target high - torque subgroup and the target low - torque subgroup according to the comparison result of the target high - torque subgroup and the comparison result of the target low - torque subgroup.

[0086] In a feasible implementation of the embodiment of the present application, the obtaining module 301 is further configured to: before the decision module 303 determines whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target subgroup, obtain the M historical torque ratios of the M historical additional cutting passes in the target subgroup, select the minimum value from the M historical torque ratios as the minimum torque ratio of the target subgroup, and obtain the additional cutting torque ratio threshold corresponding to the target subgroup according to the minimum torque ratio of the target subgroup.

[0087] In the embodiment of the present application, the decision module 303 is further configured to, if the current torque ratio is not less than the additional cutting torque ratio threshold corresponding to the target subgroup, determine that the silicon rod corresponding to the current cutting pass is in a non - cut - through state, and perform cutting on the silicon rod corresponding to the current cutting pass using the additional cutting process.

[0088] In a feasible implementation of the embodiment of the present application, the decision module 303 is further configured to determine whether the current cutting pass has an abnormal state. If the current cutting pass has the abnormal state, then determine that the silicon rod corresponding to the current cutting pass is in the non - cut - through state. Wherein, the abnormal state includes a wire - break state and a state where the shutdown duration exceeds a preset duration threshold.

[0089] It should be understood that, for the sake of brevity of description, the content described in some method embodiments will not be repeated in the device embodiments.

[0090] Based on the same inventive concept, an embodiment of the present application further provides an electronic device. Referring to Figure 4 as shown, it includes a processor 401 and a memory 402. Among them:

[0091] A computer program is stored in the memory 402, and the processor 401 is configured to execute one or more computer programs stored in the memory 402 to implement the above-mentioned silicon wafer penetration judgment method.

[0092] It can be understood that the processor 401 can be a processor core or a processor chip, or other circuits that can be programmed and run. The memory 402 can be RAM (Random Access Memory), ROM (Read-Only Memory), flash memory, etc., but this is not a limitation.

[0093] It can also be understood that Figure 4 the structure shown is only schematic, and the electronic device may further include more or fewer components than those shown in Figure 4 or have a different configuration from that shown in Figure 4 For example, it may also have an internal communication bus for realizing communication between the processor 401 and the memory 402; for another example, it may also have an external communication interface, such as a USB (Universal Serial Bus) interface, a CAN (Controller Area Network) bus interface, etc.; for another example, it may also have an information display component such as a display screen, but this is not a limitation.

[0094] Based on the same inventive concept, this embodiment further provides a computer-readable storage medium, such as a floppy disk, an optical disc, a hard disk, a flash memory, a USB flash drive, an SD (Secure Digital Memory Card) card, an MMC (Multimedia Card) card, etc. One or more computer programs for implementing the above-mentioned steps are stored in the computer-readable storage medium, and these one or more computer programs can be executed by one or more processors to implement the above-mentioned silicon wafer penetration judgment method. Details will not be described herein again.

[0095] The embodiments in the embodiments of the present application can be combined with each other without conflict to obtain new embodiments.

[0096] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0097] In addition, the units described as separate components may or may not be physically separated.

[0098] Furthermore, in each embodiment of this application, the various functional modules may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

[0099] In this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0100] In this document, "a plurality of" means two or more.

[0101] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A method for judging silicon wafer penetration, characterized in that, Including: Obtain the average feed torque of the current tool pass, the average cycle torque of the last cycle, and process-related parameters, where the process-related parameters include the silicon wafer number, process time, and process tension; Obtain the current torque ratio of the current tool pass according to the average feed torque and the average cycle torque; Determine a target process group corresponding to the process-related parameters from N pre-divided process groups according to the process-related parameters, where the N process groups are determined according to the historical process-related parameters of historical tool passes, and each process group corresponds to at least two sub-groups, and N is an integer greater than 1; Determine a target sub-group corresponding to the current tool pass from the target process group according to the average feed torque; Judge whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target sub-group, where the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target sub-group; If it is less than, it is determined that the silicon rod corresponding to the current tool pass is in a cut-through state.

2. The method according to claim 1, characterized in that, The determining a target sub-group corresponding to the current tool pass from the target process group according to the average feed torque includes: For each sub-group in the target process group, compare the average feed torque with the minimum average feed torque and the maximum average feed torque of the sub-group to obtain a comparison result corresponding to the sub-group; determine whether the sub-group is the target sub-group according to the comparison result corresponding to the sub-group.

3. The method according to claim 1, characterized in that, If each process group corresponds to two sub-groups, the method further includes: For each process group, obtain the average historical feed torque of multiple historical tool passes in the process group; use the quantile classification method to divide the average historical feed torque of multiple historical tool passes to obtain a high-torque sub-group and a low-torque sub-group corresponding to the process group.

4. The method according to claim 3, wherein The using the quantile classification method to divide the average historical feed torque of multiple historical tool passes for each process group to obtain a high-torque sub-group and a low-torque sub-group corresponding to the process group includes: For each historical tool pass among multiple historical tool passes in each process group, sort the average historical feed torque of the historical tool pass to obtain the torque at the set quantile as the sub-divided torque of the process group; divide the process group into a high-torque sub-group and a low-torque sub-group according to the sub-divided torque of the process group and the average historical feed torque of multiple historical tool passes.

5. The method according to claim 3, characterized in that, The determining a target sub-group corresponding to the current tool pass from the target process group according to the average feed torque includes: If the target process group includes a target high-torque sub-group and a target low-torque sub-group, compare the average feed torque with the minimum average feed torque and the maximum average feed torque of the target high-torque sub-group to obtain a comparison result of the target high-torque sub-group; Compare the average feed torque with the minimum average feed torque and the maximum average feed torque of the target low-torque sub-group to obtain a comparison result of the target low-torque sub-group; Determine the target subgroup from the target high-torque subgroup and the target low-torque subgroup according to the comparison results of the target high-torque subgroup and the comparison results of the target low-torque subgroup.

6. The method according to claim 1, characterized in that Before determining whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target subgroup, the method further includes: Obtain M historical torque ratios of M historical additional cutting tool passes in the target subgroup; Select the minimum value from the M historical torque ratios as the minimum torque ratio of the target subgroup; Obtain the additional cutting torque ratio threshold corresponding to the target subgroup according to the minimum torque ratio of the target subgroup.

7. The method according to claim 1, characterized in that After determining whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target subgroup, the method further includes: If it is not less than, determine that the silicon rod corresponding to the current tool pass is in a non-penetrating state, and perform cutting on the silicon rod corresponding to the current tool pass using the additional cutting process.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Determine whether the current tool pass has an abnormal state, where the abnormal state includes a wire break state and a state where the downtime exceeds a preset downtime threshold; If the current tool pass has the abnormal state, determine that the silicon rod corresponding to the current tool pass is in a non-penetrating state, and perform cutting on the silicon rod corresponding to the current tool pass using the additional cutting process.

9. A silicon wafer penetration judgment device, characterized in that, Includes: An acquisition module, configured to acquire the average feed torque of the current tool pass, the average cycle torque of the last cycle, and process-related parameters, and obtain the current torque ratio of the current tool pass according to the average feed torque and the average cycle torque; where the process-related parameters include the silicon wafer number, the process time, and the process tension; A determination module, configured to determine a target process group corresponding to the process-related parameters from N pre-divided process groups according to the process-related parameters, and determine a target subgroup corresponding to the current tool pass from the target process group according to the average feed torque; where the N process groups are determined according to the historical process-related parameters of historical tool passes, each process group corresponds to at least two subgroups, and N is an integer greater than 1; A decision module, configured to determine whether the current torque ratio is less than the additional cutting torque ratio threshold corresponding to the target subgroup, and if it is less than, determine that the silicon rod corresponding to the current tool pass is in a penetrating state; where the additional cutting torque ratio threshold is determined according to the minimum torque ratio of the target subgroup.

10. An electronic device, characterized in that, Includes a processor and a memory, where the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method according to any one of claims 1-8 is implemented.

Citation Information

Patent Citations

  • Grinding wheel cutter comprehensive state detection method, device and equipment and storage medium

    CN114012603A

  • Fragmentation box, cutting fluid system and wire cutting machine

    CN219902825U