Silicon wafer cutting penetration judgment method and device, electronic equipment and storage medium

Abstract

The application provides a silicon wafer cutting-through judgment method and device, electronic equipment and storage medium. The method comprises the following steps: acquiring an infeed parameter of a current infeed position and an outfeed parameter of a current outfeed position; acquiring a target infeed classification matched with the infeed parameter from M pre-divided infeed classifications according to the infeed parameter; judging whether the actual outfeed feed force average is less than a cutting-in judgment threshold corresponding to the target infeed classification; wherein the cutting-in judgment threshold is determined according to a minimum average value in the feed force average of the cutting-in infeed in historical cutting data corresponding to the target infeed classification; or is determined according to a maximum average value in the feed force average of the non-cutting-in infeed in the historical cutting data corresponding to the target infeed classification; if less, it is determined that the silicon rod corresponding to the current infeed is in a cutting-through state. The application can realize automatic judgment of whether the silicon rod is cut through, and improve the judgment efficiency.

Description

Technical Field

[0001] This application relates to the field of silicon wafer cutting technology, and more specifically, to a method, apparatus, electronic device, and storage medium for determining whether a silicon wafer has been cut through. Background Technology

[0002] Currently, the slicing machine uses a reverse cutting process. One drawback of the reverse cutting process is that it can create wire bows, meaning that the cutting depth of the steel wires on the right and left sides of the silicon rod is different, resulting in an uneven wire mesh. Therefore, after the machine is stopped normally after cutting according to the process formula, there may be a problem that the silicon rod is not cut through.

[0003] Currently, the method for determining whether a silicon rod has been cut through is to manually open the slicing machine, use a strong flashlight to observe the wire mesh, and visually inspect whether it has been cut through. This method relies on manual labor and is inefficient. Summary of the Invention

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

[0005] This application provides a method for determining silicon wafer cut-through, comprising: obtaining the feed parameters of the current cut position and the exit parameters of the current cut position, wherein the feed parameters include the average actual feed force at the current cut position and the exit parameters include the average actual exit feed force at the current cut position; obtaining a target cut category matching the feed parameters from M pre-divided cut categories according to the feed parameters; wherein the M cut categories are determined based on historical feed parameters of historical cut positions, and M is an integer greater than 1; determining whether the average actual exit feed force is less than the additional cutting determination threshold corresponding to the target cut category; wherein the additional cutting determination threshold is determined based on the minimum average feed force of additional cutting cuts in the historical cutting data corresponding to the target cut category; or based on the maximum average feed force of non-additional cutting cuts in the historical cutting data corresponding to the target cut category; if it is less than, determining that the silicon rod corresponding to the current cut is cut through.

[0006] In the above implementation process, the minimum average value of the feed force of the additional cutting cuts in the historical cutting data corresponding to the target feed category is used to determine the additional cutting judgment threshold, or the maximum average value of the feed force of the non-additional cutting cuts in the historical cutting data corresponding to the target feed category is used to determine the additional cutting judgment threshold. The average value of the exit feed force of the current cut belonging to the target feed category is then judged. If the average value of the exit feed force of the current cut is less than the additional cutting judgment threshold, it is determined that the silicon rod corresponding to the current cut is in the cut-through state. Since the minimum average of the feed forces in the additional cutting passes reflects the historical minimum average feed force required when additional cutting is needed, and the maximum average of the feed forces in the non-additional cutting passes reflects the historical maximum average feed force required when additional cutting is not needed, the additional cutting threshold determined based on either the minimum average of the feed forces in the additional cutting passes or the maximum average of the feed forces in the non-additional cutting passes can be used as a relatively accurate basis for determining whether additional cutting is needed in the current cut. In other words, it can more accurately determine whether the silicon rod corresponding to the current cut is cut through. Therefore, compared with related technologies, it can realize the automated judgment of whether the silicon rod is cut through, thus improving the judgment efficiency.

[0007] Furthermore, in the above implementation, M cutting parameters based on historical cutting positions are pre-defined to classify the cutting process into categories. Then, based on the current cutting parameters, a target cutting category is determined from these M categories, and the cutting threshold corresponding to the target cutting category is used for judgment. In other words, the above implementation also categorizes the cutting situation based on the cutting parameters, thereby determining the cutting threshold based on the cutting category that best matches the current cutting situation. This improves the reliability of the cutting threshold and further enhances the accuracy of determining whether the silicon rod is cut through.

[0008] Further, according to the feed parameters, a target feed category matching the feed parameters is obtained from the pre-divided M feed categories, including: if the feed parameters include the current machine and the current wafer number corresponding to the current cut, then the target feed category is obtained from the M feed categories according to the current machine, the current wafer number and the average actual feed force.

[0009] It is understandable that the cutting conditions may differ depending on the machine tool and the silicon wafer specifications. In the above implementation, the target cutting category is obtained from M cutting categories based on the current machine tool, the current silicon wafer number, and the average actual feed force. This ensures that the target cutting category is the one that best matches the current machine tool, the current silicon wafer number, and the average actual feed force. Consequently, the cutting threshold is more consistent with the cutting condition of the current cut, improving the reliability of the cutting threshold and further enhancing the accuracy of determining whether the silicon ingot is cut through.

[0010] Further, the step of obtaining the M tool feed categories includes: obtaining the historical tool feed parameters of the historical tool feed positions; wherein, the historical tool feed parameters include the historical machine, historical silicon wafer, and historical average feed force corresponding to the historical tool feed position; wherein, the number of historical machine and the number of historical silicon wafer are multiple; grouping according to the historical machine and the historical silicon wafer to obtain a machine-wafer group set; for each machine-wafer group in the machine-wafer group set, classifying according to the historical average feed force of the machine-wafer group to obtain N tool feed categories of the machine-wafer group; wherein, N is an integer greater than 1; obtaining the M tool feed categories according to the N tool feed categories of each machine-wafer group.

[0011] In the above implementation, historical machine tools and silicon wafers corresponding to historical cut positions are grouped to obtain machine tool and silicon wafer group sets. Then, for each machine tool and silicon wafer group, the average historical feed force of the machine tool and silicon wafer group is used for classification, resulting in N cut classifications for each machine tool and silicon wafer group, and thus a total of M cut classifications. The M cut classifications obtained in this way can distinguish the different cutting situations corresponding to different machine tools and silicon wafers of different specifications, making the cut classification more comprehensive and detailed. Consequently, after determining the target cut classification, the cutting judgment threshold of the target cut classification is more consistent with the cutting situation of the current cut.

[0012] Furthermore, for each silicon wafer group in the aforementioned silicon wafer grouping set, the historical average feed force of the silicon wafer group is used for classification to obtain N feed classifications of the silicon wafer group, including: for each silicon wafer group, the historical average feed force of the silicon wafer group is classified using a quantile classification method to obtain N feed classifications of the silicon wafer group.

[0013] Further, based on the current machine tool, the current wafer number, and the average actual feed force, the target feed category is obtained from the M feed categories, including: based on the current machine tool and the current wafer number, obtaining the target machine tool wafer group corresponding to the current cut from the machine tool wafer group set; and based on the average actual feed force, determining the feed category corresponding to the current cut from the N feed categories of the target machine tool wafer group as the target feed category.

[0014] In the above implementation, firstly, based on the current machine and the current wafer number, the target machine wafer group corresponding to the current cut is obtained from the machine wafer group set. Then, based on the average actual feed force, the feed category corresponding to the current cut is determined from the N feed categories of the target machine wafer group as the target feed category. The target feed category determined in this way is more closely aligned with the cutting situation of the current cut.

[0015] Further, based on the actual average feed force, determining the feed category corresponding to the current cut as the target feed category from the N feed categories of the target machine silicon wafer group includes: obtaining the average feed force range of each feed category in the N feed categories of the target machine silicon wafer group; and determining the feed category whose average feed force range includes the actual average feed force as the target feed category from the N feed categories of the target machine silicon wafer group.

[0016] In the above implementation, by obtaining the average feed force range of each of the N feed categories in the target machine silicon wafer group, and taking the feed category whose average feed force range includes the actual percentile value as the target feed category, the target feed category can be quickly determined. The solution is simple and reliable.

[0017] Further, determining whether the average actual cutter feed force is less than the additional cutting determination threshold corresponding to the target cutter category includes: if there are no additional cutting cuts in all historical cuts corresponding to the target cutter category, then determining the additional cutting determination threshold as the maximum average value corresponding to the target cutter category; and determining whether the average actual cutter feed force is less than the maximum average value corresponding to the target cutter category.

[0018] In the above implementation, when there are no additional cutting operations in all historical cutting operations corresponding to the target cutting category, the maximum value of the average feed force of the non-additional cutting operations can reflect the average maximum feed force required in history when no additional cutting is needed. Using this as the cutting determination threshold can more accurately determine whether the silicon rod corresponding to the current cutting operation is cut through. Therefore, compared with related technologies, it can realize the automatic judgment of whether the silicon rod is cut through, thus improving the judgment efficiency.

[0019] Further, determining whether the average actual feed force is less than the cut-in determination threshold corresponding to the target feed category includes: if there are cut-in operations in all historical cuts corresponding to the target feed category, then the cut-in determination threshold is determined to be the minimum average value corresponding to the target feed category; determining whether the average actual feed force is less than the minimum average value corresponding to the target feed category.

[0020] In the above implementation, when there are additional cutting operations among all historical cutting operations corresponding to the target feed category, the minimum average of the average feed forces of the additional cutting operations can reflect the average minimum feed force required in history when additional cutting is needed. Using this as the additional cutting judgment threshold can more accurately determine whether the current cutting operation needs additional cutting, that is, it can more accurately determine whether the silicon rod corresponding to the current cutting operation is cut through. Therefore, compared with related technologies, it can realize the automated judgment of whether the silicon rod is cut through, and improve the judgment efficiency.

[0021] Furthermore, if no target cutting category matching the cutting parameters is obtained among the M cutting categories, the method further includes: determining that the silicon rod corresponding to the current cutting stroke is in a non-through cutting state.

[0022] In the above implementation, if there is no matching target feed category among the M feed categories for the current cut, it means that the feed situation of the current cut is not in the historical situation. Then it can be considered that a feed abnormality has occurred, such as abnormal feed speed. At this time, it is determined that the silicon rod corresponding to the current cut is in a non-cut-through state, so additional cutting can prevent the silicon rod from being cut through.

[0023] Furthermore, the method also includes: determining whether there is an abnormal state in the current cut, wherein the abnormal state includes a disconnection state and a downtime exceeding a preset time threshold; if the abnormal state exists in the current cut, then it is determined that the silicon rod corresponding to the current cut is in the non-through state.

[0024] In the above implementation, if a break occurs in the current cutting stroke or the downtime exceeds the preset time 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 cutting stroke is in a non-cut-through state, so additional cutting can be performed to prevent the silicon rod from being cut through.

[0025] This application embodiment also provides a silicon wafer cut-through determination device, including: an acquisition module, configured to acquire the feed parameters of the current cut entry position and the exit parameters of the current cut exit position, wherein the feed parameters include the average actual feed force at the current cut entry position, and the exit parameters include the average actual exit feed force at the current cut exit position; the acquisition module is further configured to acquire a target cut category matching the feed parameters from a pre-divided M cut categories based on the feed parameters; wherein the M cut categories are based on historical... The historical feed parameters for the current cut position are determined, where M is an integer greater than 1. The decision module is used to determine whether the average actual cut feed force is less than the cutting threshold corresponding to the target cut category. If it is less, it is determined that the silicon rod corresponding to the current cut is in a cut-through state. The cutting threshold is determined based on the minimum average feed force of the cutting cuts in the historical cutting data corresponding to the target cut category, or based on the maximum average feed force of the non-cutting cuts in the historical cutting data corresponding to the target cut category.

[0026] This application also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above-described silicon wafer cut-through determination methods.

[0027] This application also provides a computer-readable storage medium storing a computer program, which, when executed by at least one processor, implements any of the above-described silicon wafer cut-through determination methods. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A schematic flowchart illustrating a silicon wafer cut-through determination method provided in an embodiment of this application;

[0030] Figure 2A flowchart illustrating the process of obtaining M tool feed categories provided in an embodiment of this application;

[0031] Figure 3 A flowchart illustrating another process for obtaining M tool feed categories provided in an embodiment of this application;

[0032] Figure 4 This is a schematic diagram of a silicon wafer cut-through determination device provided in an embodiment of this application;

[0033] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0035] To address the problem of low efficiency in determining whether a silicon ingot has been cut through in related technologies, this application provides a method for determining whether a silicon wafer has been cut through. See also... Figure 1 As shown, Figure 1 This is a flowchart illustrating the silicon wafer cut-through determination method provided in the embodiments of this application, including:

[0036] S101: Obtain the feed parameters of the current cut position and the exit parameters of the current cut position.

[0037] In this embodiment, the feed parameters include the average actual feed force at the feed position of the current cut, and the exit parameters include the average actual exit feed force at the exit position of the current cut.

[0038] In this embodiment, the actual feed force at the infeed position and the actual feed force at the exit position can be obtained by setting sensors at the infeed and exit positions. Alternatively, the actual feed force at the infeed position and the actual feed force at the exit position can be calculated based on the radius of the diamond wire used for cutting, the cutting speed at the infeed position, and the cutting speed at the exit position. This embodiment does not limit the method used to obtain the actual feed force at the infeed position and the actual feed force at the exit position.

[0039] After obtaining the actual feed force at the infeed position and the actual feed force at the exit position, the average feed force at the infeed position and the average feed force at the exit position can be obtained by averaging the actual feed force at the infeed position and the actual feed force at the exit position, respectively.

[0040] In the embodiments of this application, the actual feed force at the infeed position can be the feed force within a certain range from the infeed position, for example, the feed force collected from the infeed position in the range of 10mm to 30mm. Similarly, the actual feed force at the exit position can be the feed force within a certain range from the exit position.

[0041] S102: Based on the infeed parameters, obtain the target infeed category that matches the infeed parameters from the pre-divided M infeed categories.

[0042] In this embodiment, the M feed categories are determined based on historical feed parameters of historical feed positions, where M is an integer greater than 1. The historical feed parameters include the average historical feed force at each feed position for each historical feed.

[0043] In this embodiment, the value of M can be set according to actual needs, for example, to 5. It can be understood that the larger the value of M, the more detailed the tool approach classification, but correspondingly, the greater the workload in obtaining M tool approach classifications.

[0044] In this embodiment of the application, the feed force at the feed position of each historical cut can be obtained, and then the average feed force at the feed position of each historical cut can be calculated to obtain the historical average feed force of each historical cut.

[0045] In one embodiment of this application, see Figure 2 As shown, the M infeed categories can be obtained in the following way:

[0046] S201: Obtain the historical feed parameters for the historical tool entry positions. These parameters include the average historical feed force corresponding to the historical tool entry positions.

[0047] S202: Classify the feed rate using the historical average feed force to obtain M feed categories.

[0048] Optionally, when classifying using the historical average feed rate, a quantile classification method can be used to classify the historical average feed rate, resulting in M ​​feed rate categories. For example, the historical average feed rate can be sorted in ascending order, and then the sorted historical average feed rate can be divided into M equal parts according to the number of historical average feed rates, resulting in M ​​feed rate categories. It is understood that other classification methods can also be used to classify the historical average feed rate to obtain M feed rate categories in this embodiment, and this embodiment does not limit this.

[0049] In the above embodiments, when obtaining the target feed category that matches the feed parameters from the pre-divided M feed categories according to the feed parameters, the average feed force range of each of the M feed categories can be obtained. Then, from the M feed categories, the feed category whose average feed force range includes the actual average feed force is determined as the target feed category.

[0050] In this embodiment, the average feed force range for each feed category can be determined based on the quantile value when classifying the feed. The quantile value refers to the value used to divide the average feed force.

[0051] For example, suppose the historical average feed rates are a1, a2, a3, a4, a5, a6, and a1 < a2 < a3 < a4 < a5 < a6. Assuming a quantile classification method, and setting M to 2, the quantile value corresponding to the 50th percentile is (a3 + a4) / 2. Therefore, the historical average feed rate for the first feed rate category is (a1, a2, a3), with a range of [a1, (a3 + a4) / 2]. The historical average feed rate for the second feed rate category is (a4, a5, a6), with a range of ((a3 + a4) / 2, a6). Assuming the actual average feed rate for the current cut is A, and a4 < A < a5, then the second feed rate category can be determined as the target feed rate category.

[0052] In another embodiment of this application, see [link to relevant documentation]. Figure 3 As shown, the M infeed categories can also be obtained in the following way:

[0053] S301: Obtain historical feed parameters for historical tool feed positions.

[0054] The historical feed parameters include the historical machine tool, historical silicon wafer, and average historical feed force corresponding to the historical feed position. There are multiple historical machine tools and multiple historical silicon wafers.

[0055] S302: Group the historical equipment and historical silicon wafers to obtain the equipment and silicon wafer group set.

[0056] For example, assuming there are m (m≥2) cutting machines and n (n≥2) types of silicon wafers, the historical average feed rate for the same type of silicon wafer for each cutting machine can be used to group the wafers into a single cutting machine group. If all m cutting machines can cut these n types of wafers, then there can be m*n cutting machine wafer groups.

[0057] S303: For each wafer group in the wafer grouping set, classify the wafer groups using the historical average feed force to obtain N feed categories. Based on the N feed categories for each wafer group, M feed categories can be obtained. Here, N is an integer greater than 1.

[0058] It's understandable that, assuming there are m cutting machines, and each of these m machines can cut silicon wafers of n different sizes, then the wafers can be divided into m*n groups, resulting in a total of m*n*N cutting paths. That is, M equals m*n*N.

[0059] In this embodiment, the value of N can be set according to actual needs, for example, to 5. It can be understood that the larger the value of N, the more detailed the tool approach classification, but correspondingly, the greater the workload in obtaining M tool approach classifications.

[0060] Optionally, for each silicon wafer group, the historical average feed force of the silicon wafer group can be classified using a quantile classification method to obtain N feed classifications for the silicon wafer group.

[0061] Accordingly, the process of obtaining the target feed category matching the feed parameters from the pre-divided M feed categories can include: if the feed parameters include the current machine and the current wafer number corresponding to the current cut, then the target feed category is obtained from the M feed categories based on the current machine, the current wafer number and the average actual feed force.

[0062] For example, based on the current machine and the current wafer number, the target machine wafer group corresponding to the current cut can be obtained from the machine wafer group set. Then, based on the average actual feed force, the feed category corresponding to the current cut can be determined from the N feed categories of the target machine wafer group as the target feed category.

[0063] In this embodiment, the silicon wafer number is a wafer specification number, indicating the type of silicon wafer being produced. Therefore, based on the current machine and the current silicon wafer number, the target machine silicon wafer group corresponding to the current cut can be obtained from the machine silicon wafer group set.

[0064] In the above embodiments, when determining the feed category corresponding to the current cut as the target feed category from the N feed categories of the target machine silicon wafer group based on the actual average feed force, the range of the average feed force of each feed category in the N feed categories of the target machine silicon wafer group can be obtained. Then, from the N feed categories of the target machine silicon wafer group, the feed category whose average feed force range includes the actual average feed force can be determined as the target feed category.

[0065] The method for determining the average range of the feed force can be found in the previous text.

[0066] It is understandable that the cutting conditions may differ depending on the machine and the silicon wafer specifications. For example, different machines may have different operating speeds, and the process requirements (such as cutting speed) for different silicon wafer specifications may also differ. However, the above embodiment considers the differences between the same machine and different silicon wafer specifications when classifying the feed rate, thus classifying the historical average feed force of the same machine wafer group based on machine wafer grouping, resulting in a more detailed classification. Furthermore, since each feed rate category corresponds to the historical cutting data of a machine wafer group, the additional cutting judgment threshold corresponding to a feed rate category is obtained based on the historical cutting data saved when cutting the same type of silicon wafer on the same machine. This makes the additional cutting judgment threshold corresponding to the feed rate category more accurate. Accordingly, when determining the target cutting category, the target machine silicon wafer group is first determined based on the current machine and the current silicon wafer number of the current cut. Then, the cutting category corresponding to the current cut is determined from the N cutting categories corresponding to the target machine silicon wafer group as the target cutting category. Then, the cutting judgment threshold corresponding to the target cutting category is used for judgment, so as to obtain a more accurate judgment result on whether the silicon rod has been cut through.

[0067] S103: Determine whether the average actual feed force is less than the cutting threshold corresponding to the target feed category.

[0068] In this embodiment, the threshold for determining additional cutting is determined based on the minimum average of the average feed forces of the additional cutting cuts in the historical cutting data corresponding to the target cutting category; or based on the maximum average of the average feed forces of the non-additional cutting cuts in the historical cutting data corresponding to the target cutting category.

[0069] In some embodiments, the process of determining whether the average actual feed force is less than the cutting threshold corresponding to the target feed category may include:

[0070] If there are additional cutting operations in all historical cutting operations corresponding to the target cutting category, then the threshold for determining additional cutting is set to the minimum average value corresponding to the target cutting category; then it is determined whether the average value of the actual cutting feed force is less than the minimum average value corresponding to the target cutting category.

[0071] In some embodiments, the process of determining whether the average actual feed force is less than the cutting threshold corresponding to the target feed category may further include:

[0072] If there are no additional cutting operations in all historical cuts corresponding to the target feed category, then the additional cutting judgment threshold is determined to be the maximum value of the average cutout value of the non-additional cutting operations corresponding to the target feed category; then it is determined whether the average value of the actual cutout feed force is less than the maximum value of the average cutout value corresponding to the target feed category.

[0073] S104: If the average actual feed force is less than the cut determination threshold corresponding to the target feed category, then the silicon rod corresponding to the current cut is determined to be in the cut-through state.

[0074] In this embodiment, if the average actual feed force is greater than or equal to the cutting threshold corresponding to the target feed category, it can be determined that the silicon rod corresponding to the current cut is in a non-through-cut state. If it is determined that the silicon rod corresponding to the current cut is in a non-through-cut state, the slicing machine can be controlled to cut the silicon rod.

[0075] Optionally, in some embodiments of this application, if no target feed category matching the feed parameters is obtained among the M feed categories, it can be determined that the silicon rod corresponding to the current cut is in a non-through-cut state. It can be understood that if no matching target feed category exists among the M feed categories for the current cut, it means that the feed situation of the current cut is not within the historical range. Therefore, it can be considered that a feed anomaly has occurred, such as an abnormal feed speed. In this case, determining that the silicon rod corresponding to the current cut is in a non-through-cut state, and thus performing additional cutting, can prevent the silicon rod from being incompletely cut.

[0076] Optionally, in some embodiments of this application, it can be determined whether there is an abnormal state in the current cut. If there is an abnormal state in the current cut, it is determined that the silicon rod corresponding to the current cut is in the non-through-cut state. Abnormal states include wire breakage and downtime exceeding a preset threshold. If a wire breakage occurs in the current cutting cut, or if the downtime exceeds the preset threshold, it indicates that an abnormality has occurred in the cutting process that is sufficient to prevent the cutting process from continuing. In this case, it is determined that the silicon rod corresponding to the current cut is in the non-through-cut state, and additional cutting can prevent the silicon rod from being cut incompletely.

[0077] The preset duration threshold can be set by engineers according to the actual situation, for example, it can be set to 30 minutes.

[0078] The silicon wafer cut-through determination method provided in this application uses the minimum average value of the feed force of the additional cutting cuts in the historical cutting data corresponding to the target cutting category to determine the additional cutting determination threshold, or uses the maximum average value of the feed force of the non-additional cutting cuts in the historical cutting data corresponding to the target cutting category to determine the additional cutting determination threshold, to judge the average exit feed force of the current cut belonging to the target cutting category, and then determines that the silicon rod corresponding to the current cut is cut through when the average exit feed force of the current cut is less than the additional cutting determination threshold. Since the minimum average of the feed forces in the additional cutting passes reflects the historical minimum average feed force required when additional cutting is needed, and the maximum average of the feed forces in the non-additional cutting passes reflects the historical maximum average feed force required when additional cutting is not needed, the additional cutting threshold determined based on either the minimum average of the feed forces in the additional cutting passes or the maximum average of the feed forces in the non-additional cutting passes can be used as a relatively accurate basis for determining whether additional cutting is needed in the current cut. In other words, it can more accurately determine whether the silicon rod corresponding to the current cut is cut through. Therefore, compared with related technologies, it can realize the automated judgment of whether the silicon rod is cut through, thus improving the judgment efficiency.

[0079] Furthermore, in the above implementation, M cutting parameters based on historical cutting positions are pre-defined to classify the cutting process into categories. Then, based on the current cutting parameters, a target cutting category is determined from these M categories, and the cutting threshold corresponding to the target cutting category is used for judgment. In other words, the above implementation also categorizes the cutting situation based on the cutting parameters, thereby determining the cutting threshold based on the cutting category that best matches the current cutting situation. This improves the reliability of the cutting threshold and further enhances the accuracy of determining whether the silicon rod is cut through.

[0080] Based on the same inventive concept, this application also provides a silicon wafer cutting-through determination device 400. Please refer to... Figure 4 As shown, Figure 4 It shows the use of Figure 1 The method illustrated uses a silicon wafer cut-through determination device. It should be understood that the specific functions of device 400 are described above; to avoid repetition, detailed descriptions are omitted here. Device 400 includes at least one software function module that can be stored in memory or embedded in the operating system of device 400 in the form of software or firmware. Specifically:

[0081] See Figure 4 As shown, the device 400 includes: an acquisition module 401 and a decision module 402. Wherein:

[0082] The acquisition module 401 is used to acquire the feed parameters of the current cut infeed position and the exit parameters of the current cut outfeed position, wherein the feed parameters include the average actual feed force at the current cut infeed position and the exit parameters include the average actual exit feed force at the current cut outfeed position.

[0083] The acquisition module 401 is further configured to acquire a target infeed category that matches the infeed parameters from a pre-divided M infeed categories based on the infeed parameters; wherein the M infeed categories are determined based on historical infeed parameters of historical tool infeed positions, and M is an integer greater than 1;

[0084] The decision module 402 is used to determine whether the average actual feed force is less than the cutting threshold corresponding to the target feed category; if it is less, it is determined that the silicon rod corresponding to the current cut is in the through-cut state; wherein, the cutting threshold is determined based on the minimum average feed force of the cutting cuts in the historical cutting data corresponding to the target feed category; or based on the maximum average feed force of the non-cutting cuts in the historical cutting data corresponding to the target feed category.

[0085] In one feasible embodiment of this application, the acquisition module 401 is specifically used to: if the feed parameters include the current machine and the current silicon wafer number corresponding to the current cut, then obtain the target feed category from the M feed categories based on the current machine, the current silicon wafer number and the average actual feed force.

[0086] In the above feasible embodiments, the acquisition module 401 is further configured to obtain M feed classifications according to the following acquisition steps:

[0087] Obtain the historical feed parameters for the historical feed positions; wherein, the historical feed parameters include the historical machine tool, historical silicon wafer, and average historical feed force corresponding to the historical feed position; wherein, the number of historical machine tools is multiple, and the number of historical silicon wafers is multiple;

[0088] Based on the historical equipment and the historical silicon wafers, a set of equipment and silicon wafer groups is obtained;

[0089] For each silicon wafer group in the aforementioned silicon wafer grouping set, the historical average feed force of the silicon wafer group is used for classification to obtain N feed classifications of the silicon wafer group; where N is an integer greater than 1.

[0090] The M tool feed categories are obtained based on the N tool feed categories of each machine's silicon wafer group.

[0091] In the above feasible implementation, the acquisition module 401 is specifically used to classify the historical average feed force of each silicon wafer group using a quantile classification method to obtain N feed classifications for the silicon wafer group.

[0092] In the above feasible implementation, the acquisition module 401 is specifically used to acquire the target machine silicon wafer group corresponding to the current cut from the machine silicon wafer group set according to the current machine and the current silicon wafer number, and determine the cut category corresponding to the current cut from the N cut categories of the target machine silicon wafer group as the target cut category according to the average actual cut feed force.

[0093] In the above feasible implementation, the acquisition module 401 is specifically used to acquire the average feed force range of each feed category in the N feed categories of the target machine silicon wafer group, and determine the feed category whose average feed force range includes the actual average feed force as the target feed category from the N feed categories of the target machine silicon wafer group.

[0094] In one feasible embodiment of this application, the decision module 402 is specifically used to: if there are no additional cutting cuts in all historical cuts corresponding to the target cutting category, determine that the additional cutting determination threshold is the average maximum value corresponding to the target cutting category; and determine whether the average value of the actual cutting feed force is less than the average maximum value corresponding to the target cutting category.

[0095] In one feasible embodiment of this application, the decision module 402 is specifically used to: if there are additional cutting cuts among all historical cuts corresponding to the target cutting category, determine that the additional cutting determination threshold is the minimum average value corresponding to the target cutting category; and determine whether the average value of the actual exit feed force is less than the minimum average value corresponding to the target cutting category.

[0096] In one feasible embodiment of this application, the decision module 402 is further configured to determine that the silicon rod corresponding to the current cut is in a non-penetrating state if no target cut category matching the cut parameters is obtained among the M cut categories.

[0097] In one feasible embodiment of this application, the decision module 402 is further configured to determine whether there is an abnormal state in the current cut; if the current cut has the abnormal state, then it is determined that the silicon rod corresponding to the current cut is in the non-through-cut state. The abnormal state includes a broken wire state and a downtime exceeding a preset time threshold.

[0098] It should be understood that, for the sake of brevity, some of the content described in the method embodiments will not be repeated in the device embodiment section.

[0099] Based on the same inventive concept, this application also provides an electronic device, see [link to relevant documentation]. Figure 5 As shown, it includes a processor 501 and a memory 502. Wherein:

[0100] The memory 502 stores a computer program, and the processor 501 executes one or more computer programs stored in the memory 502 to implement the above-mentioned silicon wafer cut-through determination method.

[0101] It is understandable that processor 501 can be a processor core or processor chip, or other circuitry capable of program configuration and execution. Memory 502 can be RAM (Random Access Memory), ROM (Read-Only Memory), flash memory, etc., but this is not a limitation.

[0102] It's understandable. Figure 5 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 5 The more or fewer components shown, or having the same Figure 5 Different configurations are shown. For example, it may also have an internal communication bus for communication between the processor 501 and the memory 502; or it may have an external communication interface, such as a USB (Universal Serial Bus) interface, a CAN (Controller Area Network) bus interface, etc.; or it may have an information display component such as a display screen, but this is not a limitation.

[0103] Based on the same inventive concept, this embodiment also provides a computer-readable storage medium, such as a floppy disk, optical disk, hard disk, flash memory, USB flash drive, SD (Secure Digital Memory Card), MMC (Multimedia Card), etc., in which one or more computer programs implementing the above steps are stored. These one or more computer programs can be executed by one or more processors to implement the above silicon wafer cut-through determination method. Further details will not be elaborated here.

[0104] The embodiments in this application can be combined with each other without conflict to obtain new embodiments.

[0105] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0106] Furthermore, the units described as separate components may or may not be physically separate.

[0107] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0108] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0109] In this article, "multiple" refers to two or more.

[0110] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for determining whether a silicon wafer has been cut through, characterized in that, include: Obtain the feed parameters at the current feed position and the exit parameters at the current exit position, wherein the feed parameters include the average actual feed force at the current feed position and the exit parameters include the average actual exit feed force at the current exit position. Based on the feed parameters, a target feed category matching the feed parameters is obtained from M pre-divided feed categories; wherein, the M feed categories are determined based on the historical feed parameters of historical feed positions, and M is an integer greater than 1; Determine whether the average actual feed force is less than the additional cutting threshold corresponding to the target feed category; wherein, the additional cutting threshold is determined based on the minimum average feed force of the additional cutting cuts in the historical cutting data corresponding to the target feed category; or based on the maximum average feed force of the non-additional cutting cuts in the historical cutting data corresponding to the target feed category; If it is less than, then the silicon rod corresponding to the current cut is determined to be in the cut-through state.

2. The method according to claim 1, characterized in that, Based on the feed parameters, a target feed category matching the feed parameters is obtained from M pre-divided feed categories, including: If the feed parameters include the current machine and the current wafer number corresponding to the current cut, then the target feed category is obtained from the M feed categories based on the current machine, the current wafer number, and the average actual feed force.

3. The method according to claim 2, characterized in that, The steps for obtaining the M infeed categories include: Obtain the historical feed parameters for the historical feed positions; wherein, the historical feed parameters include the historical machine tool, historical silicon wafer, and average historical feed force corresponding to the historical feed position; wherein, the number of historical machine tools is multiple, and the number of historical silicon wafers is multiple; Based on the historical equipment and the historical silicon wafers, a set of equipment and silicon wafer groups is obtained; For each silicon wafer group in the aforementioned silicon wafer grouping set, the historical average feed force of the silicon wafer group is used for classification to obtain N feed classifications of the silicon wafer group; where N is an integer greater than 1. The M tool feed categories are obtained based on the N tool feed categories of each machine's silicon wafer group.

4. The method according to claim 3, characterized in that, For each wafer group in the aforementioned wafer grouping set, the average historical feed force of the wafer group is used for classification, resulting in N feed categories for the wafer group, including: For each silicon wafer group, the historical average feed force of the silicon wafer group is classified using the quantile classification method, resulting in N feed classifications for the silicon wafer group.

5. The method according to claim 4, characterized in that, Based on the current machine tool, the current silicon wafer number, and the average actual feed force, the target feed category is obtained from the M feed categories, including: Based on the current machine and the current wafer number, obtain the target machine wafer group corresponding to the current cut from the machine wafer group set; Based on the average actual feed force, the feed category corresponding to the current cut is determined from the N feed categories of the target machine silicon wafer group as the target feed category.

6. The method according to claim 5, characterized in that, Based on the average actual feed force, the feed category corresponding to the current cut is determined from the N feed categories of the target machine silicon wafer group as the target feed category, including: Obtain the average feed force range for each of the N feed categories in the target machine silicon wafer group; From the N feed categories of the target machine silicon wafer group, the feed category whose average feed force range includes the average actual feed force is determined as the target feed category.

7. The method according to claim 1, characterized in that, Determining whether the average actual feed rate is less than the cutting threshold corresponding to the target feed category includes: If there are no additional cutting operations in all historical cuts corresponding to the target cut category, then the additional cutting determination threshold is determined to be the maximum value of the mean value corresponding to the target cut category; Determine whether the average actual feed force is less than the maximum average value corresponding to the target feed category.

8. The method according to claim 1, characterized in that, Determining whether the average actual feed rate is less than the cutting threshold corresponding to the target feed category includes: If there are additional cutting operations in all historical cuts corresponding to the target cut category, then the additional cutting determination threshold is determined to be the minimum mean value corresponding to the target cut category; Determine whether the average actual feed force is less than the minimum average value corresponding to the target feed category.

9. The method according to any one of claims 1-8, characterized in that, If no target infeed category matching the infeed parameters is found among the M infeed categories, the method further includes: It is determined that the silicon rod corresponding to the current cut is in a non-through state.

10. The method according to any one of claims 1-8, characterized in that, The method further includes: Determine whether there is an abnormal state in the current cut, wherein the abnormal state includes a disconnection state and a downtime exceeding a preset time threshold; If the abnormal state exists in the current cut, it is determined that the silicon rod corresponding to the current cut is in a non-through state.

11. A silicon wafer cut-through judgment device, characterized in that, include: The acquisition module is used to acquire the feed parameters of the current cut entry position and the exit parameters of the current cut exit position, wherein the feed parameters include the average actual feed force at the current cut entry position and the exit parameters include the average actual exit feed force at the current cut exit position. The acquisition module is further configured to acquire a target infeed category that matches the infeed parameters from a pre-divided M infeed categories based on the infeed parameters; wherein the M infeed categories are determined based on historical infeed parameters of historical tool positions, and M is an integer greater than 1; The decision module is used to determine whether the average actual feed force is less than the cutting threshold corresponding to the target feed category; if it is less, it is determined that the silicon rod corresponding to the current cut is in a cut-through state; wherein, the cutting threshold is determined based on the minimum average feed force of the cutting cuts in the historical cutting data corresponding to the target feed category; or based on the maximum average feed force of the non-cutting cuts in the historical cutting data corresponding to the target feed category.

12. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by at least one processor, implements the method as described in any one of claims 1-10.

Images