Machine table difference identification method and system, electronic device and storage medium
By grouping machines of the same model and process into clusters, and calculating the standard deviation and ratio of the target process parameters of the computer machines, the differences between machines can be automatically identified. This solves the problems of low efficiency and inaccurate results in the existing technology, and achieves efficient and accurate identification of machine differences.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NEXCHIP SEMICON CO LTD
- Filing Date
- 2026-04-01
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies cannot automatically identify and quantify performance differences between different machines of the same model and with the same process parameters, resulting in low efficiency and reliance on manual analysis, making it difficult to guarantee the objectivity and comprehensiveness of the results.
By grouping multiple machines of the same model and process into a cluster, the target process parameter standard deviation of the machine is calculated, and the machine difference index value is determined based on the ratio, thus automatically identifying the machines with differences.
It enables automatic identification of machine differences, improves work efficiency, ensures the accuracy and consistency of identification results, and can adapt to changes in production line status and environment.
Smart Images
Figure CN121959064B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of semiconductor processing and manufacturing technology, and in particular to a method, system, electronic device, and storage medium for identifying differences between equipment. Background Technology
[0002] In semiconductor integrated circuit manufacturing, analyzing the individual machine differences among similar machines under the same process conditions is extremely important for semiconductor production. The greater the machine differences under the same process conditions, the more difficult the process transfer becomes, and the harder it is to control product quality consistency. Therefore, machine performance consistency is a core element in ensuring product yield and production stability. Currently, the industry commonly uses Fault Detection and Classification (FDC) systems to monitor machines. FDC systems use multiple sensors deployed at key locations on the machine to collect process parameters including temperature, pressure, flow rate, and voltage. This enables real-time acquisition and calculation of production data, and allows for real-time monitoring and alarming of abnormal conditions by setting production control thresholds.
[0003] However, current FDC systems can only monitor the parameters of individual machines, and cannot automatically identify and quantify performance differences between different machines of the same model and with the same process parameters from massive amounts of data. When it is necessary to evaluate whether the performance of various machines of the same model and with the same process parameters is consistent, engineers need to compare and analyze millions of monitoring charts one by one. This method is extremely inefficient, consumes a huge amount of manpower, relies on personal experience, and makes it difficult to guarantee the objectivity and comprehensiveness of the analysis results. Summary of the Invention
[0004] The purpose of this invention is to provide a machine difference identification method, system, electronic device and storage medium that can automatically identify machine differences and effectively improve work efficiency.
[0005] To achieve the above objectives, the present invention provides a machine difference identification method, comprising: dividing multiple machines belonging to the same machine type and performing the same process into a machine group based on the machine type information and process information corresponding to each machine; for each machine in the machine group, filtering the target process parameter data of the machine under the target process step based on the production data of the machine in a preset time period, and calculating the standard deviation of the target process parameter corresponding to the machine based on the target process parameter data of the machine under the target process step; calculating the standard deviation of the target process parameter corresponding to the machine group based on the standard deviation of the target process parameter corresponding to each machine in the machine group; for each machine in the machine group, determining the machine difference index value corresponding to the machine based on the ratio of the standard deviation of the target process parameter corresponding to the machine to the standard deviation of the target process parameter corresponding to the machine group; for each machine in the machine group, if the machine difference index value corresponding to the machine is greater than a preset machine difference threshold, then determining the machine as a difference machine.
[0006] Optionally, the step of calculating the standard deviation of the target process parameters corresponding to the machine based on the target process parameter data of the machine in the target process step includes: filtering the target process parameter data of the machine in the target process step to remove abnormal data; and calculating the standard deviation of the target process parameters corresponding to the machine based on the filtered target process parameter data of the machine in the target process step.
[0007] Optionally, filtering the target process parameter data of the machine tool under the target process step includes: statistically analyzing the target process parameter data of the machine tool under the target process step to determine the distribution type of the target process parameter data; and selecting a corresponding filtering criterion to filter the target process parameter data according to the distribution type of the target process parameter data.
[0008] Optionally, the machine difference identification method provided by the present invention further includes: for each machine in the machine group, drawing a scatter plot or box plot corresponding to the machine based on the filtered target process parameter data of the machine under the target process step; displaying the scatter plots or box plots corresponding to all machines in the machine group on the same plot, and highlighting the scatter plots or box plots corresponding to the machines with differences.
[0009] Optionally, the step of calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group includes: calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group and the weight value.
[0010] Optionally, for each machine in the machine group, a weight value is determined based on the number of pieces processed by that machine within the preset time period, wherein the machine with more pieces processed within the preset time period has a higher weight value.
[0011] Optionally, the step of filtering the target process parameter data of each machine in the machine group under the target process step based on the production data of that machine within a preset time period includes: filtering the target process parameter data of each machine in the machine group under the target process step based on the production data of that machine when producing the target product within a preset time period; the machine difference identification method provided by the present invention further includes: taking the machine with the smallest machine difference index value in the machine group as the optimal production machine corresponding to the target product.
[0012] To achieve the above objectives, the present invention also provides a machine difference identification system, comprising: a division module configured to divide multiple machines belonging to the same machine type and performing the same process into a machine group based on the machine type information and process information corresponding to each machine; and a first calculation module configured to, for each machine in the machine group, filter out the target process parameter data of the machine under the target process step based on the production data of the machine within a preset time period, and calculate the standard deviation of the target process parameter corresponding to the machine based on the target process parameter data of the machine under the target process step. The second calculation module is configured to calculate the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group; the third calculation module is configured to determine the machine difference index value corresponding to each machine in the machine group based on the ratio of the standard deviation of the target process parameters corresponding to the machine to the standard deviation of the target process parameters corresponding to the machine group; and the judgment module is configured to determine that the machine is a difference machine if the machine difference index value corresponding to the machine in the machine group is greater than a preset machine difference threshold.
[0013] To achieve the above objectives, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the machine difference identification method described above.
[0014] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the machine difference identification method described above.
[0015] Compared with existing technologies, the machine difference identification method, system, electronic device, and storage medium provided by this invention have the following unexpected technical effects: This invention, by grouping multiple machines belonging to the same model and performing the same process into a machine group, avoids comparing machines of different models and processes, thereby effectively ensuring the accuracy of the subsequently obtained machine difference identification results; for each machine in the machine group, based on the machine's production data within a preset time period, the target process parameter data for that machine under the target process step is selected, and based on the target process parameter data for that machine under the target process step, the standard deviation of the target process parameter corresponding to that machine is calculated. Thus, by using the standard deviation to quantify the machine's stability, the accuracy of the machine difference identification results can be effectively ensured; by considering the production data of each machine in the machine group corresponding to the target process step, the machine difference identification results can be effectively ensured; and by considering the production data of each machine in the machine group, the machine difference identification results can be effectively ensured. The standard deviation of the target process parameters is calculated for the machine group. This ensures that the standard deviation of the machine group can adaptively adjust to the overall production line status, machine aging, and seasonal environmental changes, thereby further improving the accuracy of machine difference identification. For each machine in the machine group, the machine difference index value is determined based on the ratio of the standard deviation of the target process parameters corresponding to that machine to the standard deviation of the target process parameters corresponding to the machine group. This allows the volatility of different machines to be uniformly converted to the same scale for measurement, making cross-machine comparison possible. Since for each machine in the machine group, if the machine difference index value corresponding to that machine is greater than a preset machine difference threshold, it indicates that the divergence level of that machine is higher than the average divergence level of the machine group, thus determining that the machine has machine differences (i.e., that machine is a differential machine). In summary, this invention can automatically identify machine differences and effectively improve work efficiency. Attached Figure Description
[0016] Figure 1 This is a flowchart of a machine difference identification method provided in one embodiment of the present invention.
[0017] Figure 2 This is a schematic diagram of the process parameters before filtration.
[0018] Figure 3 This is a schematic diagram of the process parameter data after filtration.
[0019] Figure 4 This is a scatter plot of the process parameter data for each machine in the DTA machine group.
[0020] Figure 5 This is a box plot of the process parameter data for each machine in the DTA machine group.
[0021] Figure 6 This is a block diagram of a machine difference recognition system provided in one embodiment of the present invention.
[0022] Figure 7 This is a block diagram of an electronic device provided according to an embodiment of the present invention.
[0023] The reference numerals in the attached drawings are explained as follows: Division module - 110; First calculation module - 120; Second calculation module - 130; Third calculation module - 140; Judgment module - 150; Drawing module - 160; Display module - 170; Processor - 210; Communication interface - 220; Memory - 230; Communication bus - 240. Detailed Implementation
[0024] The machine difference identification method, system, electronic device, and storage medium proposed in this invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of this invention will become clearer from the following description.
[0025] The core idea of this invention is to provide a machine difference identification method, system, electronic device and storage medium that can automatically identify machine differences and effectively improve work efficiency.
[0026] It should be noted that the machine difference identification method provided by the present invention can be applied to the electronic device provided by the present invention. The electronic device can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a hardware device with various operating systems, such as a mobile phone or a tablet computer.
[0027] To achieve the above-mentioned goals, this invention provides a method for identifying machine differences. Please refer to [the relevant documentation]. Figure 1 This is a flowchart of a machine difference identification method provided in one embodiment of the present invention. Figure 1 As shown, the machine difference identification method provided by the present invention includes the following steps: Step S100: Based on the machine type information and process information corresponding to each machine, multiple machines belonging to the same machine type and performing the same process are divided into a machine group; Step S200: For each machine in the machine group, based on the production data of the machine within a preset time period, the target process parameter data of the machine under the target process step is selected, and based on the target process parameter data of the machine under the target process step, the standard deviation of the target process parameter corresponding to the machine is calculated. Step S300: Calculate the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group; Step S400: For each machine in the machine group, determine the machine difference index value corresponding to the machine based on the ratio of the standard deviation of the target process parameters corresponding to the machine to the standard deviation of the target process parameters corresponding to the machine group; Step S500: For each machine in the machine group, if the machine difference index value corresponding to the machine is greater than the preset machine difference threshold, then the machine is determined to be a difference machine.
[0028] Therefore, by grouping multiple machines belonging to the same model and performing the same process (Recipe) into a cluster, comparisons between machines of different models and processes can be avoided, thus effectively ensuring the accuracy of the subsequent machine difference identification results. For each machine in the cluster, based on its production data within a preset time period, the target process parameter data for that machine under the target process step is selected. Then, based on the target process parameter data for that machine under the target process step, the standard deviation of the target process parameter corresponding to that machine is calculated. By using the standard deviation to quantify the stability of the machine, the accuracy of the machine difference identification results can be effectively ensured. Furthermore, by calculating the standard deviation of the target process parameter corresponding to each machine in the cluster, the accuracy of the machine difference identification results can be further enhanced. The standard deviation of the target process parameters ensures that the standard deviation of the machine group can adaptively adjust to the overall production line status, machine aging, and seasonal environmental changes, thereby further improving the accuracy of machine difference identification results. By determining the machine difference index value for each machine in the group based on the ratio of its target process parameter standard deviation to the group's target process parameter standard deviation, the volatility of different machines can be uniformly converted to a single scale for measurement, making cross-machine comparisons possible. Since for each machine in the group, if the machine difference index value is greater than a preset machine difference threshold, it indicates that the machine's divergence level is higher than the group's average divergence level, thus determining that the machine has machine differences (i.e., it is a differential machine). In summary, this invention can automatically identify machine differences, effectively improving work efficiency.
[0029] It should be noted that, as those skilled in the art will understand, the term "machine" in this invention refers to an independently controllable process unit in semiconductor manufacturing, which can be an independent physical device or a single process chamber within a device. It should also be noted that, as those skilled in the art will understand, each process corresponds to multiple process steps. For each process, a key process step can be selected as the target process step, and the process parameter data measured under that key process step can be used as the target process parameter data. Furthermore, it should be noted that, as those skilled in the art will understand, this invention does not limit the specific value of the preset time period; the specific value of the preset time period can be set according to actual needs, for example, the preset time period can be set to the most recent month. Additionally, it should be noted that, as those skilled in the art will understand, this invention does not limit the specific value of the preset machine difference threshold; the specific value of the preset machine difference threshold can be set according to actual conditions, for example, the preset machine difference threshold can be set to 1.
[0030] In some exemplary embodiments, the step of calculating the standard deviation of the target process parameters corresponding to the machine based on the target process parameter data of the machine in the target process step includes: filtering the target process parameter data of the machine in the target process step to remove abnormal data; and calculating the standard deviation of the target process parameters corresponding to the machine based on the filtered target process parameter data of the machine in the target process step.
[0031] Therefore, by filtering the target process parameter data corresponding to each machine in the machine group, abnormal data (such as abnormal data caused by machine downtime) can be effectively removed from the target process parameter data corresponding to that machine. By calculating the standard deviation of the target process parameter of that machine based on the filtered target process parameter data of that machine under the target process step, it can be ensured that the calculated standard deviation of the target process parameter can truly reflect the natural fluctuation level of the machine under normal production conditions. This ensures that the subsequently calculated machine difference index value can correctly reflect the performance difference of the machine, thereby further improving the accuracy of the machine difference identification results.
[0032] Please continue to refer to this. Figure 2 and Figure 3 ,in, Figure 2 This is a schematic diagram of the process parameters before filtration. Figure 3 This is a schematic diagram of the filtered process parameter data. For example... Figure 2 As shown, Figure 2 The data points marked with red circles are outlier data points. For example... Figure 3 As shown, by analyzing Figure 2 The process parameter data shown can be filtered to effectively remove abnormal data points.
[0033] In some exemplary embodiments, filtering the target process parameter data of the machine tool under the target process step includes: statistically analyzing the target process parameter data of the machine tool under the target process step to determine the distribution type of the target process parameter data; and selecting a corresponding filtering criterion to filter the target process parameter data according to the distribution type of the target process parameter data.
[0034] Therefore, for each machine, the target process parameter data of the machine under the target process step is first statistically analyzed to determine the distribution type of the target process parameter data corresponding to the machine. Then, the filtering criteria corresponding to the determined distribution type are selected to filter the target process parameter data of the machine. This can deal with various complex real data forms and effectively improve the accuracy of abnormal data filtering, thus laying a good foundation for obtaining accurate machine difference identification results in the future.
[0035] Specifically, for each machine, if the distribution type of the target process parameter data corresponding to that machine is a normal distribution, then the Laida criterion can be used ( The criteria are used to filter the target process parameter data corresponding to the machine tool; if the distribution type of the target process parameter data corresponding to the machine tool is skewed (such as log-normal distribution), then the quantile-based criteria can be selected to filter the target process parameter data corresponding to the machine tool.
[0036] It should be noted that the specific details regarding how to statistically analyze the target process parameter data for each machine at the target process step to determine the distribution type of the target process parameter data for that machine can be adapted to relevant content in the field of data processing known to those skilled in the art, and will not be elaborated upon here. It should also be noted that the application of the Raida criterion (…) The specific details of filtering target process parameter data using the criteria and how to use quantile-based criteria for filtering target process parameter data can be adapted to the relevant content in the field of data processing known to those skilled in the art, and will not be elaborated here.
[0037] In some exemplary embodiments, the step of calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each of the machine stations in the machine group includes: calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each of the machine stations in the machine group and the weight value.
[0038] Therefore, by calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation and weight value of the target process parameters of each machine in the machine group, it can be ensured that the calculated standard deviation of the target process parameters of the machine group can more accurately reflect the actual process fluctuation level on the production line, thereby providing an accurate benchmark for machine difference identification and further improving the accuracy of the machine difference identification method.
[0039] Specifically, the standard deviation of the target process parameters corresponding to the machine group can be calculated according to the following formula. :
[0040]
[0041] In the formula, n represents the total number of machines in the machine group, w i This represents the weight value corresponding to the i-th machine. This represents the standard deviation of the target process parameters corresponding to the i-th machine.
[0042] When the weight values corresponding to each machine in the machine group are equal, the standard deviation of the target process parameters corresponding to the machine group can be calculated according to the following formula. :
[0043]
[0044] In the formula, This represents the standard deviation of the target process parameters corresponding to the first machine. This represents the standard deviation of the target process parameters corresponding to the second machine. This represents the standard deviation of the target process parameters corresponding to the nth machine.
[0045] Furthermore, the machine difference index value K corresponding to the i-th machine can be calculated according to the following formula. i :
[0046]
[0047] In some exemplary embodiments, for each machine in the machine group, a weight value is determined based on the number of pieces that the machine runs within the preset time period, wherein the machine with more pieces running within the preset time period has a higher weight value.
[0048] Therefore, when calculating the standard deviation of the target process parameters corresponding to the aforementioned machine group... In this case, setting a higher weight value for machines with a higher number of wafers produced can effectively ensure that the calculated standard deviation of the target process parameters of the machine group can more accurately reflect the actual process fluctuation level on the production line. This can provide a more accurate benchmark for machine difference identification and further improve the accuracy of machine difference identification methods.
[0049] Specifically, the weight value w corresponding to the i-th machine can be calculated according to the following formula. i :
[0050]
[0051] In the formula, Num i This represents the number of pieces that the i-th machine runs within the preset time period.
[0052] In some exemplary embodiments, the machine difference identification method provided by the present invention further includes: for each machine in the machine group, drawing a scatter plot or box plot corresponding to the machine based on the filtered target process parameter data of the machine under the target process step; displaying the scatter plots or box plots corresponding to all machines in the machine group on the same plot, and highlighting the scatter plots or box plots corresponding to the machines with differences.
[0053] Therefore, by displaying the filtered target process parameter data of each machine on the same graph, and highlighting the scatter plots or box plots of the different machines, we can not only more intuitively show the stability of each machine in the whole group, but also more intuitively show the degree of difference between the different machines and other machines.
[0054] Please refer to Table 1, which shows the machine difference identification results for the DTA cluster. As shown in Table 1, the machine difference index value of machine DTA52_B1 is 2.15, the machine difference index value of machine DTA52_B2 is 2.15, the machine difference index value of machine DTA53_B1 is 0.44, the machine difference index value of machine DTA53_B2 is 0.44, the machine difference index value of machine DTA53_C1 is 0.42, and the machine difference index value of machine DTA53_C2 is 0.42. Assuming the preset machine difference threshold is 1, it can be determined that machines DTA52_B1 and DTA52_B2 have machine differences (are different machines), while machines DTA53_B1, DTA53_B2, DTA53_C1, and DTA53_C2 do not have machine differences. It should be noted that, as those skilled in the art will understand, O3TEOS in Table 1 refers to ozone-assisted TEOS (tetraethoxysilane) chemical vapor deposition process, and DTA refers to an artificially defined cluster name.
[0055] Table 1. Results of DTA Cluster Machine Difference Identification
[0056]
[0057] Please continue to refer to this. Figure 4 and Figure 5 ,in, Figure 4 A scatter plot of process parameter data for each machine in the DTA machine group; Figure 5 This is a box plot of the process parameter data for each machine in the DTA machine group. For example... Figure 4 and Figure 5 As shown, dashed boxes can be used to mark the scatter plots and box plots of machines with machine differences (machines DTA52_B1 and DTA52_B2). It should be noted that, although... Figure 4 and Figure 5 The example given is a scatter plot and box plot of machines with machine differences (different machines) highlighted by using dashed boxes. However, as those skilled in the art will understand, this does not constitute a limitation of the present invention. In other embodiments, other methods may be used to highlight the scatter plot and box plot of machines with machine differences (different machines).
[0058] In some exemplary embodiments, the step of filtering target process parameter data for each machine in the machine group under the target process step based on the production data of that machine within a preset time period includes: filtering target process parameter data for each machine in the machine group under the target process step based on the production data of that machine when producing the target product within a preset time period.
[0059] Therefore, by filtering out the target process parameter data of each machine when producing the target product, it is possible to identify machine differences from the product perspective, find the best production machine for each product, and thus help adjust the allocation of production resources and promote the improvement of product yield.
[0060] Furthermore, the machine difference identification method provided by the present invention also includes: taking the machine with the smallest machine difference index value in the machine group as the optimal production machine corresponding to the target product.
[0061] Since the smaller the machine tolerance index value, the smaller the fluctuation of the key process parameters, the better the product yield can be improved by using the machine with the smallest machine tolerance index value as the optimal production machine.
[0062] Based on the same inventive concept, this invention also provides a machine difference identification system, please refer to [reference needed]. Figure 6 Figure 6 shows a block diagram of a machine difference identification system provided by an embodiment of the present invention. As shown in Figure 6, the machine difference identification system provided by the present invention includes: a division module 110, configured to divide multiple machines belonging to the same machine type and performing the same process into a machine group based on the machine type information and process information corresponding to each machine; a first calculation module 120, configured to, for each machine in the machine group, filter out the target process parameter data of the machine under the target process step based on the production data of the machine within a preset time period, and calculate the standard deviation of the target process parameter corresponding to the machine based on the target process parameter data of the machine under the target process step; a second calculation module 120; and a second calculation module 130. Module 130 is configured to calculate the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group; the third calculation module 140 is configured to determine the machine difference index value corresponding to each machine in the machine group based on the ratio of the standard deviation of the target process parameters corresponding to the machine to the standard deviation of the target process parameters corresponding to the machine group; and the judgment module 150 is configured to determine that the machine is a difference machine if the machine difference index value corresponding to each machine in the machine group is greater than a preset machine difference threshold.
[0063] In some exemplary embodiments, the first calculation module 120 is configured to, for each machine in the machine group, filter out the target process parameter data of the machine under the target process step based on the production data of the machine when producing the target product within a preset time period; the judgment module 150 is further configured to take the machine with the smallest machine difference index value in the machine group as the best production machine corresponding to the target product.
[0064] Please continue to refer to this. Figure 6 ,like Figure 6 As shown, in some exemplary embodiments, the machine difference identification system provided by the present invention further includes: a plotting module 160, configured to plot a scatter plot or box plot corresponding to each machine in the machine group based on the filtered target process parameter data of the machine under the target process step; and a display module 170, configured to display the scatter plots or box plots corresponding to all machines in the machine group on the same plot, and to highlight the scatter plots or box plots corresponding to the machines with differences.
[0065] It should be noted that the machine difference identification system provided by the present invention can be used to execute the machine difference identification method described above. The technical principles, technical problems solved, and technical effects of the two are similar, and those skilled in the art can clearly understand that, for the sake of convenience and brevity, more details about the machine difference identification system provided by the present invention can be found in the description of the machine difference identification method provided by the present invention above, and will not be repeated here.
[0066] Based on the same inventive concept, the present invention also provides an electronic device, please refer to... Figure 7 This is a block diagram of an electronic device provided in one embodiment of the present invention. Figure 7 As shown, the electronic device includes a processor 210 and a memory 230. The memory 230 stores a computer program. When the computer program is executed by the processor 210, it implements the machine difference identification method described above. Since the electronic device provided by this invention and the machine difference identification method provided by this invention belong to the same inventive concept, the electronic device provided by this invention has at least all the beneficial effects of the machine difference identification method provided by this invention. Therefore, the beneficial effects of the electronic device provided by this invention can be referred to the relevant descriptions of the beneficial effects of the machine difference identification method provided by this invention above, and will not be repeated here.
[0067] Please continue to refer to this. Figure 7 ,like Figure 7As shown, the electronic device also includes a communication interface 220 and a communication bus 240, wherein the processor 210, the communication interface 220, and the memory 230 communicate with each other through the communication bus 240. The communication bus 240 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 240 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 220 is used for communication between the aforementioned electronic device and other devices.
[0068] It should be noted that the processor 210 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 210 is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.
[0069] It should also be noted that the memory 230 can be used to store the computer program, and the processor 210 implements various functions of the electronic device by running or executing the computer program stored in the memory 230 and calling the data stored in the memory 230. The memory 230 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable memory (PROM), electrically programmable memory (EPROM), electrically erasable programmable memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, random access memory is available in a variety of forms, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous random access memory (SDRAM), dual data rate synchronous random access memory (DDRSDRAM), enhanced synchronous random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), memory bus direct random access memory (RDRAM), direct memory bus dynamic random access memory (DRDRAM), and memory bus dynamic random access memory (RDRAM), etc.
[0070] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can implement the machine difference identification method described above. Since the readable storage medium and the machine difference identification method provided by this invention belong to the same inventive concept, the readable storage medium provided by this invention possesses at least all the beneficial effects of the machine difference identification method provided by this invention. Therefore, the beneficial effects of the readable storage medium provided by this invention can be referred to the relevant descriptions of the beneficial effects of the machine difference identification method provided by this invention above, and will not be repeated here.
[0071] The readable storage medium provided by this invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (not exhaustive) of computer-readable storage media include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.
[0072] In summary, compared with the prior art, the machine difference identification method, system, electronic device, and storage medium provided by the present invention have the following unexpected technical effects: The present invention, by grouping multiple machines belonging to the same model and performing the same process into a machine group, avoids comparing machines of different models and processes, thereby effectively ensuring the accuracy of the subsequently obtained machine difference identification results; for each machine in the machine group, based on the machine's production data within a preset time period, the target process parameter data of the machine under the target process step is selected, and based on the target process parameter data of the machine under the target process step, the standard deviation of the target process parameter corresponding to the machine is calculated. Thus, by using the standard deviation to quantify the machine's stability, the accuracy of the machine difference identification results can be effectively ensured; by considering the production data of each machine in the machine group... The standard deviation of the target process parameters is calculated for the machine group, ensuring that the standard deviation of the machine group can adaptively adjust to the overall production line status, machine aging, and seasonal environmental changes, thereby further improving the accuracy of machine difference identification results. For each machine in the machine group, the machine difference index value is determined based on the ratio of the standard deviation of the target process parameters corresponding to that machine to the standard deviation of the target process parameters corresponding to the machine group. This allows the volatility of different machines to be uniformly converted to the same scale for measurement, making cross-machine comparison possible. Since for each machine in the machine group, if the machine difference index value corresponding to that machine is greater than a preset machine difference threshold, it indicates that the divergence level of that machine is higher than the average divergence level of the machine group, thus determining that the machine has machine differences (i.e., that machine is a differential machine). In summary, this invention can automatically identify machine differences, effectively improving work efficiency.
[0073] It should be noted that the above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the present invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.
Claims
1. A method for identifying machine differences, characterized in that, include: Based on the machine type information and process information corresponding to each machine, multiple machines belonging to the same machine type and performing the same process are divided into a machine group; For each machine in the machine group, based on the production data of the machine in a preset time period, the target process parameter data of the machine under the target process step is selected, and based on the target process parameter data of the machine under the target process step, the standard deviation of the target process parameter corresponding to the machine is calculated. Calculate the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group; For each machine in the machine group, the machine deviation index value corresponding to that machine is determined based on the ratio of the standard deviation of the target process parameter corresponding to that machine to the standard deviation of the target process parameter corresponding to the machine group. For each machine in the machine group, if the machine difference index value corresponding to that machine is greater than the preset machine difference threshold, then the machine is determined to be a defective machine.
2. The machine difference identification method according to claim 1, characterized in that, The step of calculating the standard deviation of the target process parameters corresponding to the machine based on the target process parameter data of the machine in the target process step includes: The target process parameter data of the machine under the target process step is filtered to remove abnormal data; Based on the filtered target process parameter data of the machine under the target process step, calculate the standard deviation of the target process parameter corresponding to the machine.
3. The machine difference identification method according to claim 2, characterized in that, The filtering of the target process parameter data of the machine tool under the target process step includes: The target process parameter data of the machine under the target process step are statistically analyzed to determine the distribution type of the target process parameter data; Based on the distribution type of the target process parameter data, select the corresponding filtering criteria to filter the target process parameter data.
4. The machine difference identification method according to claim 2, characterized in that, The method further includes: For each machine in the machine group, a scatter plot or box plot is drawn based on the filtered target process parameter data of the machine under the target process step. The scatter plots or box plots corresponding to all machines in the machine group are displayed on the same graph, and the scatter plots or box plots corresponding to the machines with differences are highlighted.
5. The machine difference identification method according to claim 1, characterized in that, The step of calculating the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group includes: The standard deviation of the target process parameters corresponding to the machine group is calculated based on the standard deviation and weight value of the target process parameters corresponding to each machine in the machine group.
6. The machine difference identification method according to claim 5, characterized in that, For each machine in the machine group, a weight value is determined based on the number of pieces processed by that machine within the preset time period. The machine with more pieces processed within the preset time period has a higher weight value.
7. The machine difference identification method according to claim 1, characterized in that, For each machine in the machine group, based on the production data of that machine within a preset time period, the target process parameter data for that machine under the target process step is filtered out, including: For each machine in the machine group, the target process parameter data of the machine under the target process step is selected based on the production data of the machine when producing the target product within a preset time period. The method further includes: The machine with the smallest machine difference index value in the machine group is selected as the optimal production machine for the target product.
8. A machine difference recognition system, characterized in that, include: The partitioning module is configured to group multiple machines belonging to the same machine type and performing the same process into a machine group based on the machine type information and process information corresponding to each machine. The first calculation module is configured to, for each machine in the machine group, filter out the target process parameter data of the machine under the target process step based on the production data of the machine within a preset time period, and calculate the standard deviation of the target process parameter corresponding to the machine based on the target process parameter data of the machine under the target process step. The second calculation module is configured to calculate the standard deviation of the target process parameters corresponding to the machine group based on the standard deviation of the target process parameters corresponding to each machine in the machine group; The third calculation module is configured to determine the machine error index value corresponding to each machine in the machine group based on the ratio of the standard deviation of the target process parameter corresponding to the machine to the standard deviation of the target process parameter corresponding to the machine group. as well as The judgment module is configured to determine that a machine is a defective machine if the machine difference index value corresponding to each machine in the machine group is greater than a preset machine difference threshold.
9. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the machine difference identification method according to any one of claims 1 to 7.
10. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the machine difference identification method according to any one of claims 1 to 7.