WO2023184281A1 - Procédé et appareil d'analyse de paramètres d'inspection - Google Patents

Procédé et appareil d'analyse de paramètres d'inspection Download PDF

Info

Publication number
WO2023184281A1
WO2023184281A1 PCT/CN2022/084212 CN2022084212W WO2023184281A1 WO 2023184281 A1 WO2023184281 A1 WO 2023184281A1 CN 2022084212 W CN2022084212 W CN 2022084212W WO 2023184281 A1 WO2023184281 A1 WO 2023184281A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
detection parameters
parameters
parameter
measurement point
Prior art date
Application number
PCT/CN2022/084212
Other languages
English (en)
Chinese (zh)
Other versions
WO2023184281A9 (fr
Inventor
王瑜
吴建波
代言玉
吴建民
柴栋
王洪
李园园
王萍
王建宙
沈国梁
陈韵
Original Assignee
京东方科技集团股份有限公司
北京中祥英科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司, 北京中祥英科技有限公司 filed Critical 京东方科技集团股份有限公司
Priority to PCT/CN2022/084212 priority Critical patent/WO2023184281A1/fr
Priority to CN202280000628.4A priority patent/CN117157541A/zh
Publication of WO2023184281A1 publication Critical patent/WO2023184281A1/fr
Publication of WO2023184281A9 publication Critical patent/WO2023184281A9/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/28—Testing of electronic circuits, e.g. by signal tracer
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C7/00—Arrangements for writing information into, or reading information out from, a digital store

Definitions

  • the present application relates to the field of data analysis, and in particular to a detection parameter analysis method and device.
  • a detection parameter analysis method includes: obtaining multiple sets of first detection parameters of a product; the first detection parameters include detection parameters of multiple measurement points, and the measurement points are on the product. position point; according to the interpolation algorithm, perform interpolation processing on multiple sets of first detection parameters to determine multiple sets of second detection parameters; the number of groups of the second detection parameters is the same as the number of groups of the first detection parameters; according to the correlation Analysis algorithm, determines the correlation evaluation value between multiple sets of second detection parameters; the correlation evaluation value is used to characterize the correlation between the multiple sets of second detection parameters corresponding to each of the measurement points; output Correlation evaluation values between multiple sets of second detection parameters.
  • the above-mentioned interpolation algorithm is the Kriging interpolation method; according to the interpolation algorithm, interpolation processing is performed on multiple sets of first detection parameters to determine multiple sets of second detection parameters, including: determining the relationship between the first measurement point and the second measurement point.
  • the coordinate distance and semivariance between Semivariance determines the semivariance of multiple prediction points; the prediction point is a measurement point that does not have a corresponding detection parameter in each group of first detection parameters among multiple measurement points corresponding to multiple sets of first detection parameters; according to Determine the weight coefficient based on the semivariance of multiple prediction points; determine the target interpolation values of multiple prediction points based on the weight coefficient and multiple sets of first detection parameters; perform interpolation on multiple sets of first detection parameters based on the target interpolation values of multiple prediction points Processing and determining multiple sets of second detection parameters.
  • determining the semi-variance of multiple prediction points based on the coordinate distance and the semi-variance between the first measurement point and the second measurement point includes: based on the coordinate distance between the first measurement point and the second measurement point. The coordinate distance and semivariance are used to determine the semivariance fitting curve; based on the semivariance fitting curve, the semivariance of multiple prediction points is determined.
  • the coordinate distance between the above-mentioned first measurement point and the second measurement point satisfies the following formula:
  • d ij represents the coordinate distance between the first measurement point and the second measurement point
  • i represents the number of the first measurement point
  • xi represents the abscissa of the first measurement point
  • y i represents the ordinate of the first measurement point
  • j represents the number of the second measurement point
  • x j represents the abscissa of the second measurement point
  • y j represents the ordinate of the second measurement point.
  • r ij represents the semivariance between the first measurement point and the second measurement point
  • E represents the covariance
  • z i represents the detection parameter of the first measurement point
  • z j represents the detection parameter of the second measurement point.
  • ⁇ k represents the weight coefficient
  • z k represents the detection parameter of a measurement point numbered k.
  • the above correlation analysis algorithm is Pearson correlation analysis method, and the correlation evaluation values between multiple sets of second detection parameters satisfy the following formula:
  • ⁇ represents the correlation evaluation value
  • X and Y respectively represent a second detection parameter
  • ⁇ X represents the average value of the second detection parameter X
  • ⁇ Y represents the average value of the second detection parameter Y
  • ⁇ The standard deviation of the detection parameter X, ⁇ Y represents the standard deviation of the second detection parameter Y.
  • the above-mentioned correlation analysis algorithm is the Kruskal-Wallis test method; according to the correlation analysis algorithm, determining the correlation evaluation values between multiple sets of second detection parameters includes: according to Sort the multiple sets of second detection parameters in increasing order; determine the ranks of the multiple sets of second detection parameters; determine the statistics of the multiple sets of second detection parameters based on the ranks of the multiple sets of second detection parameters; based on the multiple sets of second detection parameters The statistic of the second detection parameter determines the correlation evaluation values between multiple sets of second detection parameters.
  • the statistics of the plurality of sets of second detection parameters satisfy the following formula:
  • H represents the statistics of multiple sets of second detection parameters
  • N represents the number of detection parameters included in multiple sets of second detection parameters
  • n represents the number of detection parameters included in one second detection parameter
  • R The sum of the ranks of the detection parameters X, R Y represents the sum of the ranks of the second detection parameter Y.
  • P represents the correlation evaluation value between multiple sets of second detection parameters
  • H represents the statistics of multiple sets of second detection parameters
  • k represents the number of second detection parameters
  • ⁇ represents the gamma distribution function
  • the method further includes: determining contour plots of multiple sets of second detection parameters; the contour plots are used to characterize the magnitude of detection parameters corresponding to each area on the product; and outputting the multiple sets of second detection parameters. Contour map.
  • obtaining the first detection parameters of the product includes: determining a statistical aggregation table; and obtaining multiple sets of first detection parameters of the product according to the statistical aggregation table.
  • the statistical aggregation table is the Haidup database HBase statistical aggregation table.
  • the above determination of the HBase statistical aggregation table includes: obtaining the third detection parameters of multiple products from the detection device according to the Haidup database; the third detection The parameters include the first detection parameter; data aggregation of the third detection parameters of multiple products is performed according to the structured query language SQL to determine the HBase statistical aggregation table.
  • the third detection parameters include the first detection parameters; determine the HBase statistical aggregation table according to the third detection parameters of the multiple products; obtain the first detection parameter of the product according to the HBase statistical aggregation table. Detect parameters.
  • the above-mentioned multiple sets of first detection parameters include key process parameters and electro-permanent magnet EPM electrical parameters;
  • the key process parameters include surface resistance RS parameters, alignment accuracy TP parameters, line width CD parameters, and film thickness THK parameters. , and at least one of the fitting accuracy OL parameters;
  • the electrical parameters include at least one of the threshold voltage VTH parameter, the mobility MOB parameter, the operating current ION parameter, and the reverse cut-off current IOFF parameter.
  • the method further includes: before outputting the correlation evaluation values between the plurality of sets of second detection parameters, sorting the correlation evaluation values between the plurality of sets of second detection parameters.
  • a parameter analysis device including: an acquisition unit, a processing unit and an output unit; the acquisition unit is configured to acquire multiple sets of first detection parameters of the product; the first detection parameters include detection parameters of multiple measurement points , the measurement point is a position point on the product; the processing unit is configured to perform interpolation processing on multiple sets of first detection parameters according to the interpolation algorithm to obtain multiple sets of second detection parameters; the number of second detection parameters is the same as the first detection parameter The number is the same; the processing unit is also configured to determine the correlation evaluation values between multiple sets of second detection parameters according to the correlation analysis algorithm; the correlation evaluation values are used to characterize the multiple sets of second detection corresponding to each measurement point Correlation between parameters; the output unit is configured to output correlation evaluation values of multiple sets of second detection parameters.
  • the processing unit is further configured to determine the coordinate distance and semivariance between the first measurement point and the second measurement point; the first measurement point and the second measurement point are measurement points among the plurality of measurement points. ; The processing unit is further configured to determine the semivariance of the plurality of prediction points according to the distance between the first measurement point and the second measurement point and the semivariance; the processing unit is further configured to determine the semivariance of the plurality of prediction points according to the distance between the first measurement point and the second measurement point and the semivariance; , determine the weight coefficient; the processing unit is also configured to determine the target interpolation of multiple prediction points based on the weight coefficient and multiple sets of first detection parameters; the processing unit is also configured to determine the target interpolation of multiple prediction points based on the target interpolation of the multiple prediction points.
  • a set of first detection parameters is interpolated to determine multiple sets of second detection parameters.
  • the processing unit is further configured to determine the semivariance fitting curve according to the coordinate distance between the first measurement point and the second measurement point and the semivariance; the processing unit is further configured to determine the semivariance fitting curve according to the semivariance fitting curve. The combined curve is used to determine the semivariance of multiple prediction points.
  • the coordinate distance between the first measurement point and the second measurement point satisfies the following formula:
  • d ij represents the coordinate distance between the first measurement point and the second measurement point
  • i represents the number of the first measurement point
  • xi represents the abscissa of the first measurement point
  • y i represents the ordinate of the first measurement point
  • j represents the number of the second measurement point
  • x j represents the abscissa of the second measurement point
  • y j represents the ordinate of the second measurement point.
  • r ij represents the semivariance between the first measurement point and the second measurement point
  • E represents the covariance
  • z i represents the detection parameter of the first measurement point
  • z j represents the detection parameter of the second measurement point.
  • ⁇ k represents the weight coefficient
  • z k represents the detection parameter of a measurement point numbered k.
  • the correlation analysis algorithm is Pearson correlation analysis method, and the correlation evaluation values between multiple sets of second detection parameters satisfy the following formula:
  • ⁇ represents the correlation evaluation value
  • X and Y respectively represent a second detection parameter
  • ⁇ X represents the average value of the second detection parameter X
  • ⁇ Y represents the average value of the second detection parameter Y
  • ⁇ The standard deviation of the detection parameter X, ⁇ Y represents the standard deviation of the second detection parameter Y.
  • the processing unit is further configured to sort the plurality of sets of second detection parameters in increasing order; the processing unit is further configured to determine the ranks of the sorted plurality of sets of second detection parameters; the processing unit, It is also configured to determine the statistics of multiple sets of second detection parameters based on the ranks of the multiple sets of second detection parameters; the processing unit is also configured to determine the multiple sets of second detection parameters based on the statistics of the multiple sets of second detection parameters. correlation evaluation value.
  • the statistics of the plurality of sets of second detection parameters satisfy the following formula:
  • H represents the statistics of multiple sets of second detection parameters
  • N represents the number of detection parameters included in multiple sets of second detection parameters
  • n represents the number of detection parameters included in one second detection parameter
  • R The sum of the ranks of the detection parameters X, R Y represents the sum of the ranks of the second detection parameter Y.
  • P represents the correlation evaluation value between multiple sets of second detection parameters
  • H represents the statistics of multiple sets of second detection parameters
  • k represents the number of second detection parameters
  • ⁇ represents the gamma distribution function
  • the processing unit is also configured to determine contour plots of multiple sets of second detection parameters; the contour plots are used to characterize the magnitude of the detection parameters corresponding to each area on the product; the output unit is also configured Contour plots of multiple sets of second detection parameters are output.
  • the processing unit is further configured to determine a statistical aggregation table; the obtaining unit is further configured to obtain multiple sets of first detection parameters of the product according to the statistical aggregation table.
  • the acquisition unit is further configured to acquire third detection parameters of multiple products from the detection device according to the Haidup database; the third detection parameters include the first detection parameters; and the processing unit is further configured to acquire the third detection parameters of the plurality of products according to the Haidup database.
  • the structured query language SQL aggregates data on the third detection parameters of multiple products and determines the HBase statistical aggregation table.
  • the multiple sets of first detection parameters include key process parameters and electropermanent magnet EPM electrical parameters;
  • the key process parameters include surface resistance RS parameters, alignment accuracy TP parameters, line width CD parameters, film thickness THK parameters, and at least one of the fitting accuracy OL parameters;
  • the electrical parameters include at least one of the threshold voltage VTH parameter, the mobility MOB parameter, the operating current ION parameter, and the reverse cut-off current IOFF parameter.
  • the processing unit is further configured to sort the correlation evaluation values between the plurality of sets of second detection parameters before outputting the correlation evaluation values between the plurality of sets of second detection parameters.
  • a detection parameter analysis application is provided, wherein the detection parameter analysis application includes an application interactive interface.
  • the detection parameter analysis application is executed as described in any of the above embodiments. Parameter analysis device method.
  • a computer-readable storage medium stores computer program instructions.
  • the computer program instructions When the computer program instructions are run on a computer (for example, a parameter analysis device), they cause the computer to execute the parameter analysis device method as described in any of the above embodiments.
  • a computer program product includes computer program instructions.
  • the computer program instructions When the computer program instructions are executed on a computer (for example, a parameter analysis device), the computer program instructions cause the computer to execute the parameter analysis device method as described in any of the above embodiments.
  • a computer program is provided.
  • the computer program When the computer program is executed on a computer (for example, a parameter analysis device), the computer program causes the computer to execute the parameter analysis device method as described in any of the above embodiments.
  • Figure 1 is a schematic diagram of an application scenario of a parameter analysis method according to some embodiments
  • Figure 2 is a flow chart of a parameter analysis method provided according to some embodiments.
  • Figure 3 is an application interaction interface provided according to some embodiments.
  • Figure 4 is a schematic line diagram of a correlation evaluation value provided according to some embodiments.
  • Figure 5 is a flow chart of another parameter analysis method provided according to some embodiments.
  • Figure 6 is a flow chart of another parameter analysis method provided according to some embodiments.
  • Figure 7 is a flow chart of another parameter analysis method provided according to some embodiments.
  • Figure 8 is a contour map provided according to some embodiments.
  • Figure 9 is another contour map provided in accordance with some embodiments.
  • Figure 10 is a structural diagram of a parameter analysis device provided according to some embodiments.
  • Figure 11 is a structural diagram of another parameter analysis device provided according to some embodiments.
  • first and second are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as “first” and “second” may explicitly or implicitly include one or more of these features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.
  • At least one of A, B and C has the same meaning as “at least one of A, B or C” and includes the following combinations of A, B and C: A only, B only, C only, A and B The combination of A and C, the combination of B and C, and the combination of A, B and C.
  • a and/or B includes the following three combinations: A only, B only, and a combination of A and B.
  • the term “if” is optionally interpreted to mean “when” or “in response to” or “in response to determining” or “in response to detecting,” depending on the context.
  • the phrase “if it is determined" or “if [stated condition or event] is detected” is optionally interpreted to mean “when it is determined" or “in response to the determination" or “on detection of [stated condition or event]” or “in response to detection of [stated condition or event]”.
  • parallel includes absolutely parallel and approximately parallel, and the acceptable deviation range of approximately parallel may be, for example, a deviation within 5°;
  • perpendicular includes absolutely vertical and approximately vertical, and the acceptable deviation range of approximately vertical may also be, for example, Deviation within 5°.
  • equal includes absolute equality and approximate equality, wherein the difference between the two that may be equal within the acceptable deviation range of approximately equal is less than or equal to 5% of either one, for example.
  • HBase is a distributed storage system for storing structured data.
  • HBase is a distributed massive list non-relational database, that is, the data in HBase is stored based on column families, and a column family contains several columns. HBase can be used when real-time reading and writing and random access to very large data sets are required.
  • the HBase statistical aggregation table is a table for statistical data based on the data set stored in HBase and using mature computer languages such as structured query language (SQL) to perform aggregation operations.
  • SQL structured query language
  • the HBase statistical aggregation table can also be updated synchronously.
  • the HBase statistical aggregation table stores various detection parameters about the product obtained from the production equipment, such as key process parameters and electro permanent magnet (EPM) electrical parameters.
  • Key process parameters may include: resistance surface (RS) parameters, total pitch (TP) parameters, critical dimension (CD) parameters, film thickness (thickness, THK) parameters, and fitting accuracy.
  • EPM electrical parameters may include: threshold voltage (voltage of threshold, VTH) parameters, mobility (MOB) parameters, operating current (represented by ION) parameters, and reverse cutoff current (represented by IOFF) parameters.
  • every certain preset time period the preset time period can be set manually, the HBase statistical aggregation table will update its own stored detection parameters based on the update of the detection parameters of the production equipment.
  • the interpolation algorithm is an important method for discrete function approximation. It can be used to estimate the approximate value of the function at other points through the value of the function at a limited number of points.
  • interpolation refers to the interpolation of a continuous function based on discrete data so that this continuous curve passes through all given discrete data points. Interpolation is an important method for approximating discrete functions. It can be used to estimate the approximate value of a function at other points through the value of the function at a limited number of points. In the field of images, interpolation is used to fill the gaps between pixels when the image is transformed.
  • Kriging interpolation is a commonly used interpolation algorithm in the field of data analysis.
  • the parameter analysis device can interpolate multiple different types of detection parameters obtained from measurement points through the Kriging interpolation method to ensure the unity of these multi-category detection parameters, This is to avoid negative impacts on the correlation analysis of detection parameters due to differences in the distribution and number of measurement points.
  • Contour maps are generally used in the fields of geographical exploration and map drawing. They connect points with the same height on the surface to form a loop and directly project it onto the plane to form a horizontal curve. Loops with different heights will not coincide.
  • contour maps are widely used. To put it simply, a contour map connects points with the same height on the surface into a loop and directly projects it onto the plane to form a horizontal curve. Loops at different heights will not coincide unless the surface shows cliffs or cliffs, which will cause the lines to be too dense and overlap. For example, if there is a flat and open hillside on the surface, the distance between the curves will be quite wide, and its baseline is based on the mean tide line of the sea level. There are marking instructions at the bottom of each map for the convenience of users. , the main illustrations include scale, drawing number, frame connection table, legend and azimuth angle.
  • the parameter analysis device is based on detection parameters detected at measurement points in different areas of the product. After interpolating these detection parameters, a contour map is drawn based on these and detection parameters. It is used to intuitively represent the size of the detection parameters in different areas of the product to assist staff in analyzing the correlation analysis results of the detection parameters.
  • Correlation analysis algorithm refers to an algorithm that analyzes two or more correlated variable elements to measure the close correlation between two variable factors.
  • Correlation analysis refers to the analysis of two or more correlated variable elements to measure the close correlation between the two variable factors. There needs to be a certain connection or probability between the correlation elements before correlation analysis can be performed. Correlation is not equal to causation, nor is it simple personalization. The scope and fields covered by correlation cover almost every aspect we see. The definition of correlation in different disciplines is also very different.
  • the Pearson algorithm, the Kruskal-Wallist (K-W) test method and the Mann-Whitney (M-W) rank sum test method are the fields of data correlation analysis. The most commonly used algorithm.
  • the parameter analysis device will perform correlation analysis on multiple categories of detection parameters of the interpolated product based on the Pearson algorithm and the K-W test method, so that the staff can perform correlation analysis based on Correlation analysis results are used to identify defective areas of the product and make process improvements or equipment troubleshooting.
  • TFT-LCD thin film transistor liquid crystal display
  • the key parameters of the product will be tested.
  • the staff analyzes these key parameters through manual inspection to determine whether there are defects in the product and the causes of the defects. Then the staff will improve the manufacturing process or troubleshoot the manufacturing equipment based on the causes of the defects.
  • due to the complex manufacturing process and large quantity of products relying on manual inspection to locate the cause of defects is extremely limited in timeliness and accuracy, making it difficult to meet the growing production demand.
  • Solution 1 A defect pattern analysis method based on bad maps (CN112184691A). This solution is aimed at a certain product type and organizes the defect measurement results of the same product from different sources and the various characteristic measurement values of the product into certain standards according to certain standards. Displays the coordinate data information associated with the panel Map coordinates. Taking the defective coordinate position information of the display panel as the analysis object, a density clustering model of defective data information and display panel data is established for different product types. The clustering categories depend on the defect information of the corresponding display panel production tools and product characteristics and defects. The correlation degree of coordinates is used to determine the similarity between the bad information of each product and the corresponding density clustering type through the similarity coefficient of the density clustering model, and several effective bad types are screened out. In summary, this solution quickly locates bad information into bad types.
  • Option 2 A bad root cause path analysis method and system based on association rule mining (CN111932394A).
  • CN111932394A A bad root cause path analysis method and system based on association rule mining.
  • this solution is based on an improved association rule mining algorithm, traverses all possible device path combinations, and automatically and quickly locates the root cause of the problem.
  • the present disclosure provides a parameter analysis method and device to solve the problem in the prior art that when analyzing product detection parameters, the processing time limit and accuracy are limited, making it difficult to meet the growing production demand.
  • the method provided by this disclosure can also quantify the correlation between parameters into indicators and quickly locate the root cause of the failure of the previous site, so that business personnel can adjust parameters in an efficient and timely manner for verification, testing and maintenance.
  • the execution subject is the parameter analysis device.
  • the parameter analysis device may be a server, or may be a part of a device coupled to the server, such as a chip system in the server.
  • the parameter analysis device includes:
  • the processor can be a general central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more programs for controlling the disclosed solution implemented integrated circuit.
  • CPU central processing unit
  • ASIC application-specific integrated circuit
  • Transceiver can be any device such as a transceiver used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks, WLAN) etc.
  • RAN radio access network
  • WLAN wireless local area networks
  • memory can be read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM) or other types that can store information and instructions.
  • Type of dynamic storage device it can also be electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage, optical disc Storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store the desired program code in the form of instructions or data structures and can be used by Any other media accessible by a computer, but not limited to this.
  • the memory can exist independently and be connected to the processor through communication lines. Memory can also be integrated with the processor.
  • Figure 1 is a schematic diagram of an application scenario of a parameter analysis method provided according to some embodiments.
  • a parameter analysis device 10 and a production equipment 20 are included.
  • the parameter analysis device 10 is used to obtain detection parameters from the production equipment 20 and perform parameter analysis so that business personnel can conduct verification, testing and maintenance of the production equipment 20 based on the results of parameter analysis.
  • Production equipment 20 used for producing products. And in the production equipment 20, various types of inspection stations are provided.
  • a testing station is used to measure a type of testing parameters of a product.
  • the production equipment 20 obtains the detection parameters of the product according to the detection station set by itself, it sends these detection parameter items to the parameter analysis device 10 .
  • the parameter analysis device 10 summarizes the detection parameters collected by the detection stations set by the production equipment 20 set on the production line, and performs parameter analysis and analyzes the parameters. After the results are output, the staff can remotely determine the cause of the defective product through the analysis results, and then improve the production process or repair the production equipment 20 on the production line.
  • Figure 2 is a parameter analysis method provided according to some embodiments. The method includes the following steps:
  • Step 201 The parameter analysis device obtains multiple sets of first detection parameters of the product.
  • the product can be a panel, flat module or display product.
  • the display product may include at least one of a glass screen (Class), a liquid crystal screen (Liquid Crystal Display, LCD), and a plasma display panel (Plasma Display Panel, PDP).
  • the product testing parameters can be divided into key process parameters and EPM electrical parameters.
  • the key process parameters include at least one of the following parameters: surface resistance RS parameter, alignment accuracy TP parameter, line width CD parameter, film thickness THK parameter, and alignment accuracy OL parameter.
  • the EPM electrical parameters include at least one of the following parameters: threshold voltage VTH parameter, mobility MOB parameter, operating current ION parameter, and reverse cut-off current IOFF parameter.
  • the first detection parameter includes at least one of the key process parameters and at least one of the EPM electrical parameters, that is, a group of first detection parameters includes the same key process parameter or EPM electrical parameter.
  • the product is a glass screen (Class)
  • its corresponding key process parameters can include: the surface resistance RS parameter of the Class, the alignment accuracy TP parameter, the line width CD parameter, and the film thickness.
  • the corresponding EPM electrical parameters of the THK parameter and fitting accuracy OL parameter may include: the threshold voltage VTH parameter, the mobility MOB parameter, the operating current ION parameter, and the reverse cut-off current IOFF parameter of the Class.
  • the parameter analysis device can obtain the reverse cut-off current IOFF parameters and film thickness THK parameters of different measurement points on the Class, and use the obtained reverse cut-off current IOFF parameters and film thickness THK parameters as the first detection parameters of the Class;
  • the parameter analysis device can obtain the reverse cut-off current IOFF parameters and surface resistance RS parameters of different measurement points on the Class, and use the obtained reverse cut-off current IOFF parameters and surface resistance RS parameters as the first detection parameters of the Class.
  • the measurement point is the location point selected on the product for measuring the detection parameters by the parameter analysis device when acquiring the detection parameters of the product.
  • the number of measurement points is between 20 and 180.
  • the parameter analysis device obtains multiple sets of first detection parameters of the product from a statistical aggregation table.
  • the statistical aggregation table includes: RS parameters, TP parameters, CD parameters, THK parameters, OL parameters, VTH parameters, MOB parameters, ION parameters, and IOFF parameters of the product.
  • the parameter analysis device obtains third detection parameters of multiple products from the detection equipment.
  • the third detection parameters of the products include all types of key process parameters and EPM electrical parameters of the products.
  • the above statistical aggregation table is an HBase statistical aggregation table.
  • the parameter analysis device can obtain the third detection parameters of multiple products from the detection device according to HBase.
  • the detection equipment is the equipment installed on the production equipment of the product for obtaining the detection parameters of the product.
  • the parameter analysis device performs data aggregation on the third detection parameters of multiple products based on SQL, stores them in table form, and determines the HBase statistical aggregation table.
  • the third detection parameter includes the first detection parameter. Furthermore, the HBase statistical aggregation table determined based on the third detection parameter includes the first detection parameter, and the parameter analysis device obtains the first detection parameter of the product from the HBase statistical aggregation table according to the user's detection requirements.
  • the staff's detection requirements can be used to instruct the user to detect the first detection parameters required for detection.
  • the detection requirements include the identification information of the first detection parameters to be detected and other information, such as the filtering conditions of the first detection parameters, etc., in accordance with Only the first detection parameters of these screening conditions can be used for detection analysis.
  • the staff can send the detection requirement to the parameter analysis device through the application interactive interface, so that the parameter analysis device obtains the first detection parameter of the product from the HBase statistical aggregation table according to the detection requirement.
  • the parameter analysis device provides an application interactive interface, and the staff can set the acquisition conditions of the first detection parameter on this application interaction interface. After the acquisition conditions of the first detection parameter are set, Afterwards, the staff performs a confirmation operation to obtain multiple sets of first detection parameters from the data stored in the HBase statistical aggregation table. For example, the staff can set to obtain the products with factory number ARRAY, model number BNA650QU5V402, Class ID 1, and detection site numbers 990G and 576K between July 1, 2021 and July 22, 2021.
  • the first detection parameter whose detection parameter type is IOFF1_20 (that is, IOFF parameter) and THICKNESS (that is, THK parameter).
  • the parameter analysis device stores the multiple sets of first detection parameters in the form of a table, as shown in Table 1 below. Shown:
  • Step represents the site number of the detection station
  • Item represents the type of detection parameter
  • x and y represent the abscissa and ordinate of the measurement point respectively
  • Value represents the specific value of the detection parameter.
  • Step 202 The parameter analysis device performs interpolation processing on multiple sets of first detection parameters according to the interpolation algorithm, and determines multiple sets of second detection parameters.
  • the interpolation algorithm is an interpolation algorithm.
  • the interpolation algorithm may be Kriging interpolation method or other interpolation algorithms, which is not specifically limited in this disclosure.
  • the specific implementation process of interpolating multiple sets of first detection parameters according to the Kriging interpolation method can be referred to as shown in Figure 5 below, and will not be described again here.
  • the number of sets of second detection parameters is the same as the number of sets of first detection parameters. That is to say, the number of categories of detection parameters will not change before and after the interpolation process.
  • the second detection parameter is only obtained by interpolating the corresponding first detection parameter according to the interpolation algorithm by the parameter analysis device. Compared with the first detection parameters, some new parameter values of prediction points are added to the second detection parameters.
  • the prediction point is a measurement point that does not have a corresponding detection parameter in each set of first detection parameters among all measurement points corresponding to multiple sets of first detection parameters.
  • the parameter analysis device divides the Class into 16*14 grid points. At this time, there are a total of 224 position points corresponding to the interpolation process. That is, the goal of interpolation processing is to make both the IOFF parameter and the THK parameter have parameter values of 224 identical position points.
  • the selection of prediction points can be divided into two types:
  • THK parameters include the detection parameters of these measurement points, and the IOFF parameters do not include them, then these measurement points are used as prediction points when interpolating the IOFF parameters.
  • prediction points can also be divided into two types:
  • the IOFF parameters include the detection parameters of these measurement points, and the THK parameters do not include them, then these measurement points are used as prediction points when interpolating the THK parameters.
  • the prediction points are only the position points selected by the interpolation algorithm for this set of first detection parameters and to be interpolated.
  • the parameter values of these prediction points are calculated according to the interpolation algorithm, and the parameter analysis device does not actually measure the first detection parameters of the group at the prediction points.
  • the parameter value of the newly added prediction point is combined with the parameter value included in the first detection parameter and obtained after actual detection of the measurement point to form the second detection parameter.
  • the parameter analysis device divides Class into 16*14 grid points, one grid point serves as a measurement point or prediction point, and one measurement point or prediction point corresponds to one or more groups. Detect parameters. It is assumed that the parameter analysis device obtains two sets of first detection parameters of Class, which are IOFF parameters and THK parameters respectively. Among them, there are 100 measurement points for the IOFF parameter, that is, the IOFF parameter includes a total of IOFF values of 100 position points. There are 140 measurement points for THK parameters, that is, the THK parameters include a total of 140 THK values of position points. Among the measurement points corresponding to the IOFF parameter and the THK parameter, some are the same and some are different. At this time, it is necessary to interpolate the IOFF parameters and THK parameters according to the interpolation algorithm to ensure the unity of the IOFF and THK parameters and facilitate subsequent correlation analysis.
  • the IOFF parameters include IOFF values of 224 position points, of which the IOFF values of 100 position points are actual detection measurements.
  • the IOFF value of the point, and the IOFF value of the other 124 position points are the newly added IOFF values after interpolation processing according to the interpolation algorithm.
  • the THK parameters are the THK values of 140 position points.
  • the THK values of 140 position points are the IOFF values of the actual detected measurement points
  • the THK values of the other 84 position points are new after interpolation processing based on the interpolation algorithm. Increased THK value.
  • the parameter analysis device uses the interpolated IOFF parameters and THK parameters, each including parameter values of 224 position points, as multiple sets of second detection parameters. It can be understood that at this time, for all position points included in the two sets of first detection parameters (that is, the 224 position points mentioned above), each position point has a corresponding IOFF parameter value and a THK parameter value, so the The uniformity of the two first detection parameters after interpolation is improved.
  • Step 203 The parameter analysis device determines correlation evaluation values between multiple sets of second detection parameters according to the correlation analysis algorithm.
  • the correlation analysis algorithm is a correlation analysis algorithm.
  • the correlation evaluation values between multiple sets of second detection parameters can be used to characterize the degree of correlation between multiple sets of second detection parameters.
  • the correlation analysis algorithm may be at least one of the Pearson algorithm and the K-W test method.
  • the specific implementation process of Pearson algorithm can be based on the following formula (4)-formula (5).
  • the specific implementation process of the K-W test method can be referred to as shown in Figure 6 below, and will not be described again here.
  • the parameter analysis device can simultaneously determine the correlation evaluation values between multiple sets of second detection parameters based on multiple correlation analysis algorithms.
  • each correlation analysis algorithm has its corresponding correlation evaluation value.
  • the staff can study the process problems reflected in the detection parameters of Class based on the correlation evaluation values obtained by multiple algorithms. Compared with Instead of evaluating Class's process problems based only on the correlation evaluation value obtained by one algorithm, using multiple correlation evaluation algorithms to evaluate Class's process problems can better ensure the accuracy and efficiency of process improvement or equipment maintenance.
  • the second detection parameters include the IOFF parameter and the THK parameter, and both the IOFF parameter and the THK parameter undergo interpolation processing.
  • the parameter analysis device performs correlation analysis on the IOFF parameters and THK parameters according to the correlation analysis algorithm, and obtains the correlation evaluation results of the IOFF parameters and THK parameters. For the IOFF parameter value and THK parameter value of each measurement point, there is a The correlation evaluation value represents the degree of correlation between the IOFF parameter and the THK parameter above this measurement point.
  • Step 204 The parameter analysis device outputs correlation evaluation values between multiple sets of second detection parameters.
  • the parameter analysis device can output correlation evaluation values between multiple sets of second detection parameters in various ways.
  • the correlation evaluation value is used to characterize the correlation between multiple sets of second detection parameters corresponding to each measurement point.
  • the parameter analysis device outputs the correlation evaluation values between multiple sets of second detection parameters in the form of a line graph.
  • the parameter analysis device sorts the correlation evaluation values between the multiple sets of second detection parameters, so that the staff can intuitively see The degree of correlation between the detection parameters corresponding to each measurement point.
  • the staff can determine the defective areas of the product based on the correlation evaluation values.
  • the staff compares the correlation evaluation value of the detection parameter of each measurement point on the product reflected in the correlation evaluation value with the preset threshold to determine whether the process evaluation result of the measurement point is good or bad.
  • the correlation analysis algorithm is the Pearson algorithm and the preset threshold is set to 0.65
  • the correlation evaluation value of the IOFF parameter and the THK parameter of a certain measurement point is 0.7. Since 0.7 is greater than 0.65, the process evaluation value of this measurement point The result is good.
  • the staff determines the set of measurement points with poor process evaluation results as the poor process areas of the product.
  • the parameter analysis device in the present disclosure obtains multiple types of detection parameters of the product, and performs interpolation processing on each type of detection parameters through an interpolation algorithm to determine the multiple types of interpolated detection parameters, After interpolation processing, the data unity between each detection parameter can be maintained to provide support for subsequent correlation analysis; after that, the parameter analysis device correlates various types of detection parameters after interpolation according to the correlation analysis algorithm. evaluation to determine the specific correlation evaluation value. This quantifies the correlation between the detection parameters, and the staff can quickly locate the bad areas reflected by the detection parameters at the detection site, so that the staff can adjust the parameters efficiently and timely for verification testing and maintenance, effectively improving In order to ensure processing timeliness and accuracy, it can meet the growing production needs.
  • step 202 specifically includes the following steps:
  • Step 501 The parameter analysis device determines the coordinate distance and semivariance between the first measurement point and the second measurement point.
  • the first detection parameters include detection parameters for multiple measurement points.
  • the first detection parameters include the IOFF parameter and the THK parameter.
  • the IOFF parameter includes the IOFF values of multiple measurement points on Class
  • the THK parameter includes the THK values of multiple measurement points on Class.
  • the first measurement point and the second measurement point are measurement points among multiple measurement points corresponding to the same group of first detection parameters.
  • the first detection parameter includes an IOFF parameter and a THK parameter
  • the first measurement point and the second measurement point are any two measurement points corresponding to the IOFF parameter, or the first measurement point and the second measurement point are corresponding to the THK parameter. any two measurement points.
  • the parameter analysis device first determines the coordinates of the first measurement point and the second measurement point, and then calculates the distance between the first measurement point and the second measurement point.
  • calculating the distance between the first measurement point and the second measurement point satisfies the following formula 1:
  • d ij represents the coordinate distance between the first measurement point and the second measurement point
  • i represents the number of the first measurement point
  • xi represents the abscissa of the first measurement point
  • y i represents the ordinate of the first measurement point
  • j represents the number of the second measurement point
  • x j represents the abscissa of the second measurement point
  • y j represents the ordinate of the second measurement point.
  • the parameter analysis device first calculates the covariance between the first measurement point and the second measurement point, and calculates the semivariance between the first measurement point and the second measurement point based on this.
  • calculating the semivariance between the first measurement point and the second measurement point satisfies the following formula 2:
  • r ij represents the semivariance between the first measurement point and the second measurement point
  • E represents the covariance
  • z i represents the detection parameter of the first measurement point
  • z j represents the detection parameter of the second measurement point.
  • Step 502 The parameter analysis device determines semi-variances of multiple prediction points based on the distance and semi-variance between the first measurement point and the second measurement point.
  • the parameter analysis device determines the points within a specific neighborhood range of the measurement points corresponding to the multiple sets of first detection parameters, or a specific number of adjacent points, as multiple prediction points.
  • the IOFF parameter there are currently two first detection parameters, which are the IOFF parameter and the THK parameter.
  • the IOFF parameter there are 100 measurement points for the IOFF parameter, that is, the IOFF parameter includes a total of 100 points of IOFF values
  • the THK parameter there are 140 measurement points for the THK parameter, that is, the THK parameter includes a total of 140 points of THK values.
  • the IOFF parameter needs to be interpolated so that the IOFF parameter includes the parameter values of 224 points.
  • the THK parameter value is the same.
  • the 124 points corresponding to the new parameter value in the IOFF parameter and the 84 points corresponding to the new parameter value in the THK parameter are the prediction points.
  • the parameter analysis device determines the semivariance fitting curve based on the coordinate distance and the semivariance between the first measurement point and the second measurement point. After that, the parameter analysis device determines the semivariance of multiple prediction points according to the semivariance fitting curve.
  • the above-mentioned semi-variance fitting curve is calculated by the parameter analysis device after the distance and semi-variance between all possible any two points among the measurement points corresponding to the multiple sets of first detection parameters are completed.
  • the distances and semivariances corresponding to all measurement points are plotted into a scatter plot, and an optimal curve is found for fitting.
  • Step 503 The parameter analysis device determines the weight coefficient based on the semivariance of multiple prediction points.
  • the weight coefficient is used to weight and sum the parameter values of all measurement points included in the multiple sets of first detection parameters to determine the target interpolation of the prediction point.
  • the weight coefficient ⁇ k here satisfies the estimated value
  • the optimal set of coefficients with the smallest difference from the true value z 0 that is At the same time, the conditions for unbiased estimation are satisfied That is, the covariance between the target interpolation value of the prediction point calculated by the parameter analysis device and the true value of the prediction point is 0.
  • Step 504 The parameter analysis device determines the target interpolation values of multiple prediction points based on the weight coefficients and multiple sets of first detection parameters.
  • the parameter analysis device multiplies and sums the detection parameters of each measurement point included in the plurality of sets of first detection parameters by its corresponding weight coefficient to obtain a plurality of prediction points. target interpolation.
  • the target interpolation of multiple prediction points satisfies the following formula 3:
  • ⁇ k represents the weight coefficient
  • z k represents the detection parameter of the measurement point numbered k.
  • Step 505 The parameter analysis device performs interpolation processing on multiple sets of first detection parameters based on the target interpolation of multiple prediction points, and determines multiple sets of second detection parameters.
  • the product is Class
  • the parameter analysis device divides Class into 16*14 grid points.
  • One grid point serves as a measurement point or prediction point
  • the IOFF parameter and the THK parameter are Perform interpolation processing. That is, after interpolation processing, the IOFF parameters include IOFF values of 224 points. Among them, the IOFF values of 100 points are the IOFF values of the actual detected measurement points, and the IOFF values of the other 124 points are parameters.
  • the analysis device performs interpolation processing on the IOFF parameter based on the target interpolation of multiple prediction points and adds a new IOFF value. The same is true for the THK parameters.
  • the THK values of 140 points are the IOFF values of the actual measured measurement points, and the THK values of the other 84 points are the parameter analysis device based on multiple prediction points.
  • the target interpolation is the newly added THK value after interpolating the THK parameters.
  • the parameter analysis device uses the interpolated IOFF parameters and THK parameters, each including parameter values of 224 points, as multiple sets of second detection parameters.
  • the parameter analysis device in the present disclosure performs interpolation processing on multiple types of detection parameters through the Kriging interpolation method.
  • the interpolation processing in this step can maintain the data uniformity between each detection parameter, so as to facilitate the subsequent steps. Evaluate the correlation between product detection parameters to improve the accuracy of correlation evaluation.
  • the correlation analysis algorithm may be Pearson correlation analysis method.
  • the Pearson correlation coefficient is a method of measuring the similarity of data. It is used to describe the tendency of two sets of data to change and move together. It is a value between -1 and 1. When the linear relationship between two sets of data increases, the correlation coefficient tends to -1 or 1; when one variable increases, the other variable also increases, indicating that there is a positive correlation between them, and the correlation coefficient is greater than 0; when one variable increases When the other variable is large, it indicates that there is a negative correlation between them, and the correlation coefficient is less than 0; if the correlation coefficient is equal to 0, it indicates that there is no linear correlation between them.
  • the calculation formula of the Pearson correlation analysis method is expressed as the covariance of two variables divided by the standard deviation of the two variables.
  • the correlation evaluation values between multiple sets of second detection parameters satisfy the following formula 4:
  • ⁇ represents the correlation evaluation value
  • X and Y respectively represent a second detection parameter
  • ⁇ X represents the average value of the second detection parameter X
  • ⁇ Y represents the average value of the second detection parameter Y
  • ⁇ The standard deviation of the detection parameter X, ⁇ Y represents the standard deviation of the second detection parameter Y.
  • X can be expressed as n detection values ( X 1 , detection values (Y 1 , Y 2 ,..., Y n ).
  • the correlation analysis algorithm is introduced above when it is the Pearson correlation analysis method.
  • the correlation evaluation values between multiple sets of second detection parameters can be determined, so that the staff can determine based on the correlation analysis results. Identify defective areas of the product and make process improvements or equipment troubleshooting.
  • step 203 specifically includes the following steps:
  • Step 601 The parameter analysis device sorts multiple sets of second detection parameters in increasing order.
  • sample X is used to represent the IOFF parameter
  • sample Y is used to represent the THK parameter.
  • Step 602 The parameter analysis device determines the ranks of the multiple sets of sorted second detection parameters.
  • the parameter analysis device sums the ranks of each second detection parameter.
  • Rx represents the sum of the ranks of the IOFF parameters in the sorting
  • Ry represents the sum of the ranks of the THK parameters in the sorting.
  • Step 603 The parameter analysis device determines the statistics of the multiple sets of second detection parameters based on the ranks of the multiple sets of second detection parameters.
  • H represents the statistics of multiple sets of second detection parameters
  • N represents the number of detection parameters included in multiple sets of second detection parameters
  • n represents the number of detection parameters included in one second detection parameter
  • R The sum of the ranks of the detection parameters X, R Y represents the sum of the ranks of the second detection parameter Y.
  • Step 604 The parameter analysis device determines the correlation evaluation values between the multiple sets of second detection parameters based on the statistics of the multiple sets of second detection parameters.
  • the correlation evaluation values between multiple sets of second detection parameters satisfy the following formula 7:
  • P represents the correlation evaluation value between multiple sets of second detection parameters
  • H represents the statistics of multiple sets of second detection parameters
  • k represents the number of second detection parameters
  • ⁇ represents the gamma distribution function
  • the second detection parameter X and the second detection parameter Y are considered to be relatively relevant.
  • the correlation analysis algorithm is introduced above when it is the K-W test method.
  • the correlation evaluation value between multiple sets of second detection parameters can be determined, so that the staff can determine the product based on the correlation analysis results. defective areas and make process improvements or equipment troubleshooting.
  • the correlation analysis algorithm may be the M-W rank sum test method.
  • the main idea of the M-W rank sum test method is to assume that the two parameter samples participating in the analysis come from two identical populations except for the overall mean. The purpose is to test whether there is a significant difference in the means of the two populations.
  • the specific algorithm steps of the M-W rank sum test method are as follows:
  • Step 1 Mix the two sets of data and arrange the levels in order of size.
  • the smallest data level is 1, the second smallest data level is 2, and so on (if there are equal data, the average of these data sortings is taken as its level).
  • Step 2 Find the grades and W 1 and W 2 of the two samples respectively.
  • Step 3 Calculate the MW rank sum test statistics U 1 and U 2 of the two parameter samples.
  • n 1 is the size of the first sample
  • n 2 is the size of the second sample.
  • U ⁇ U a it is considered that the two parameter samples are more relevant; when U > U a , it is considered that the two parameter samples are more related. irrelevant.
  • the value of U a is generally selected as 0.05.
  • the correlation analysis algorithm is introduced above when it is the M-W rank sum test method.
  • the correlation evaluation value between multiple sets of second detection parameters can be determined, so that the staff can determine based on the correlation analysis results. Identify defective areas of the product and make process improvements or equipment troubleshooting.
  • the correlation analysis algorithm in the embodiment of the present disclosure can also include multiple correlation analysis algorithms.
  • the correlation analysis algorithm can include Pearson correlation analysis method, K-W test method and M-W rank sum test method at the same time, or it can also include Pearson correlation analysis method, K-W test method and M-W rank sum test method at the same time. Includes other correlation analysis algorithms. It can be understood that the correlation analysis algorithm includes multiple correlation analysis algorithms, and multiple correlation analysis results can be obtained, thereby providing more evidence for the staff.
  • the parameter analysis device may output the correlation analysis results in the form of Table 2 below.
  • Step represents the site number of the detection station
  • Item represents the type of detection parameters.
  • the parameter analysis method provided by the present disclosure also includes the following steps:
  • Step 701 The parameter analysis device determines contour maps of multiple sets of second detection parameters.
  • contour map is used to characterize the size of the detection parameters corresponding to each area on the product.
  • contour maps are generally used in the fields of geographical exploration and map drawing. They connect points with the same height on the surface to form a loop and directly project it onto the plane to form a horizontal curve. Loops with different heights will not coincide.
  • This characteristic of the contour map when combined with the embodiments of the present disclosure, can intuitively represent the size of the detection parameters in different areas of the product, so as to assist the staff in analyzing the correlation analysis results of the detection parameters.
  • Step 702 The parameter analysis device outputs multiple sets of contour maps of the second detection parameters.
  • the parameter analysis device can output multiple sets of contour maps of the second detection parameters in various ways.
  • Figure 8 and Figure 9 show two contour maps.
  • Figure 8 represents the contour map of the IOFF parameters in the Glass
  • Figure 9 represents the Contour plot of THK parameters in Glass. It is not difficult to see that the closer to the middle area of Glass, the smaller the IOFF parameter value is, and conversely, the larger the THK parameter is. Therefore, the staff can clearly see that there is a negative correlation between the IOFF parameter and the THK parameter.
  • Embodiments of the present disclosure can divide the parameter analysis device into functional modules or functional units according to the above method examples.
  • each functional module or functional unit can be divided corresponding to each function, or two or more functions can be integrated into one in the processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules or functional units.
  • the division of modules or units in the embodiments of the present disclosure is schematic and is only a logical function division. In actual implementation, there may be other division methods.
  • FIG. 10 it is a schematic structural diagram of a parameter analysis device 1000 provided according to some embodiments.
  • the device includes: an acquisition unit 1001, a processing unit 1002 and an output unit 1003.
  • the obtaining unit 1001 is configured to obtain the first detection parameter of the product.
  • the acquisition unit 1001 is specifically configured to perform step 201.
  • the processing unit 1002 is configured to perform interpolation processing on the first detection parameter according to the interpolation algorithm to obtain the second detection parameter.
  • the processing unit 1002 is specifically configured to perform step 202.
  • the processing unit 1002 is further configured to determine the correlation evaluation value between the second detection parameters according to the correlation analysis algorithm.
  • the processing unit 1002 is specifically configured to perform step 203.
  • the output unit 1003 is configured to output the correlation evaluation value of the second detection parameter.
  • the output unit 1003 is specifically used to perform step 204.
  • the processing unit 1002 is further configured to determine the coordinate distance and the semivariance between the first measurement point and the second measurement point. For example, with reference to Figure 5, the processing unit 1002 is specifically configured to perform step 501.
  • the processing unit 1002 is further configured to determine semi-variances of the plurality of prediction points based on the distance between the first measurement point and the second measurement point and the semi-variance. For example, with reference to Figure 5, the processing unit 1002 is specifically configured to perform step 502.
  • the processing unit 1002 is further configured to determine the weight coefficient according to the semi-variance of multiple prediction points.
  • the processing unit 1002 is specifically configured to perform step 503.
  • the processing unit 1002 is further configured to determine target interpolations of multiple prediction points based on weight coefficients and multiple sets of first detection parameters. For example, with reference to Figure 5, the processing unit 1002 is specifically configured to perform step 504.
  • the processing unit 1002 is further configured to perform interpolation processing on multiple sets of first detection parameters according to target interpolation of multiple prediction points, and determine multiple sets of second detection parameters.
  • the processing unit 1002 is specifically configured to perform step 505.
  • the processing unit 1002 is further configured to determine a semivariance fitting curve according to the coordinate distance and the semivariance between the first measurement point and the second measurement point.
  • the processing unit 1002 is specifically configured to perform step 502.
  • the processing unit 1002 is further configured to determine semivariances of multiple prediction points according to the semivariance fitting curve. For example, with reference to Figure 5, the processing unit 1002 is specifically configured to perform step 502.
  • the processing unit 1002 is further configured to sort the plurality of sets of second detection parameters in increasing order.
  • the processing unit 1002 is specifically configured to perform step 601.
  • the processing unit 1002 is further configured to determine the ranks of the multiple sets of sorted second detection parameters.
  • the processing unit 1002 is specifically configured to perform step 602.
  • the processing unit 1002 is further configured to determine statistics of multiple sets of second detection parameters based on ranks of multiple sets of second detection parameters. For example, with reference to Figure 6, the processing unit 1002 is specifically configured to perform step 603.
  • the processing unit 1002 is further configured to determine correlation evaluation values between multiple sets of second detection parameters based on statistics of multiple sets of second detection parameters. For example, with reference to Figure 6, the processing unit 1002 is specifically configured to perform step 604.
  • the processing unit 1002 is further configured to determine contour maps of multiple sets of second detection parameters. For example, with reference to Figure 7, the processing unit 1002 is specifically configured to perform step 701.
  • the output unit 1003 is further configured to output contour plots of multiple sets of second detection parameters.
  • the output unit 1003 is specifically used to perform step 702.
  • the processing unit 1002 is further configured to determine a statistical aggregation table.
  • the processing unit 1002 is specifically configured to perform step 201.
  • the acquisition unit 1001 is further configured to acquire multiple sets of first detection parameters of the product according to the statistical aggregation table.
  • the acquisition unit 1001 is specifically configured to perform step 201.
  • the acquisition unit 1001 is further configured to acquire third detection parameters of multiple products from the detection device according to the Haidup database.
  • the acquisition unit 1001 is specifically configured to perform step 201.
  • the processing unit 1002 is further configured to perform data aggregation on the third detection parameters of the multiple products according to the structured query language SQL, and determine the HBase statistical aggregation table.
  • the processing unit 1002 is specifically configured to perform step 201.
  • the processing unit 1002 is further configured to sort the correlation evaluation values between the multiple sets of second detection parameters before outputting the correlation evaluation values between the multiple sets of second detection parameters.
  • the processing unit 1002 is specifically configured to perform step 204.
  • the parameter analysis device 1000 may also include a storage unit (shown as a dotted box in FIG. 10 ), which stores programs or instructions.
  • a storage unit shown as a dotted box in FIG. 10
  • the parameter analysis device 1000 can execute the parameter analysis method described in the above method embodiment.
  • FIG 11 shows another possible structural schematic diagram of the parameter analysis device involved in the above embodiment.
  • the parameter analysis device 1100 includes: a processor 1102 and a communication interface 1103.
  • the processor 1102 is configured to control and manage the actions of the parameter analysis device 1100, for example, perform the steps performed by the above-mentioned acquisition unit 1001, the processing unit 1002 and the output unit 1003, and/or be configured to perform other techniques described herein. process.
  • the communication interface 1103 is configured to support communication between the parameter analysis device 1100 and other network entities.
  • the parameter analysis device 1100 may further include a memory 1101 and a bus 1104 , the memory 1101 being configured to store program codes and data of the parameter analysis device 1100 .
  • the memory 1101 may be the memory in the parameter analysis device 1100, etc.
  • the memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, Hard disk or solid state drive; the memory may also include a combination of the above types of memory.
  • the above-described processor 1102 may implement or execute various exemplary logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various illustrative logical blocks, modules and circuits described in connection with this disclosure.
  • the processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
  • the bus 1104 may be an Extended Industry Standard Architecture (EISA) bus or the like.
  • EISA Extended Industry Standard Architecture
  • the bus 1104 can be divided into an address bus, a data bus, a control bus, etc. For ease of presentation, only one thick line is used in Figure 11, but it does not mean that there is only one bus or one type of bus.
  • the parameter analysis device 1100 in Figure 11 can also be a chip.
  • the chip includes one or more (including two) processors 1102 and communication interfaces 1103.
  • the chip also includes a memory 1101, which may include read-only memory and random access memory, and provides operating instructions and data to the processor 1102.
  • a memory 1101 which may include read-only memory and random access memory, and provides operating instructions and data to the processor 1102.
  • Part of the memory 1101 may also include non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • memory 1101 stores elements, execution modules, or data structures, or subsets thereof, or extended sets thereof.
  • the corresponding operation is performed by calling the operation instructions stored in the memory 1101 (the operation instructions may be stored in the operating system).
  • Some embodiments of the present disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) having computer program instructions stored therein, and the computer program instructions are stored in a computer (e.g., parameters When running on the analysis device), the computer is caused to execute the parameter analysis method as described in any of the above embodiments.
  • a computer-readable storage medium e.g., a non-transitory computer-readable storage medium
  • the computer program instructions are stored in a computer (e.g., parameters When running on the analysis device), the computer is caused to execute the parameter analysis method as described in any of the above embodiments.
  • the computer-readable storage medium may include, but is not limited to: magnetic storage devices (such as hard disks, floppy disks or magnetic tapes, etc.), optical disks (such as CD (Compact Disk, compressed disk), DVD (Digital Versatile Disk, etc.) Digital versatile disk), etc.), smart cards and flash memory devices (e.g., EPROM (Erasable Programmable Read-Only Memory, Erasable Programmable Read-Only Memory), cards, sticks or key drives, etc.).
  • the various computer-readable storage media described in this disclosure may represent one or more devices and/or other machine-readable storage media for storing information.
  • the term "machine-readable storage medium” may include, but is not limited to, wireless channels and various other media capable of storing, containing and/or carrying instructions and/or data.
  • Some embodiments of the present disclosure also provide a computer program product, for example, the computer program product is stored on a non-transitory computer-readable storage medium.
  • the computer program product includes computer program instructions.
  • the computer program instructions When the computer program instructions are executed on a computer (for example, a parameter analysis device), the computer program instructions cause the computer to perform the parameter analysis method as described in the above embodiment.
  • Some embodiments of the present disclosure also provide a computer program.
  • the computer program When the computer program is executed on a computer (for example, a parameter analysis device), the computer program causes the computer to perform the parameter analysis method as described in the above embodiment.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Manufacturing & Machinery (AREA)
  • Automation & Control Theory (AREA)
  • General Engineering & Computer Science (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
  • General Factory Administration (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)

Abstract

Procédé et appareil d'analyse de paramètre d'inspection. Le procédé consiste : à acquérir une pluralité de groupes de premiers paramètres d'inspection d'un produit, les premiers paramètres d'inspection comprenant des paramètres d'inspection d'une pluralité de points de mesure, et les points de mesure étant des points de position sur le produit ; selon un algorithme d'interpolation, à effectuer un traitement d'interpolation sur la pluralité de groupes de premiers paramètres d'inspection pour déterminer une pluralité de groupes de seconds paramètres d'inspection, le nombre de seconds paramètres d'inspection étant le même que le nombre de premiers paramètres d'inspection ; selon un algorithme d'analyse de corrélation, à déterminer une valeur d'évaluation de corrélation entre la pluralité de groupes de seconds paramètres d'inspection, la valeur d'évaluation de corrélation étant utilisée pour représenter la corrélation entre la pluralité de groupes de seconds paramètres d'inspection correspondant à chacun des points de mesure ; et à produire la valeur d'évaluation de corrélation entre la pluralité de groupes de seconds paramètres d'inspection.
PCT/CN2022/084212 2022-03-30 2022-03-30 Procédé et appareil d'analyse de paramètres d'inspection WO2023184281A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2022/084212 WO2023184281A1 (fr) 2022-03-30 2022-03-30 Procédé et appareil d'analyse de paramètres d'inspection
CN202280000628.4A CN117157541A (zh) 2022-03-30 2022-03-30 一种检测参数分析方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/084212 WO2023184281A1 (fr) 2022-03-30 2022-03-30 Procédé et appareil d'analyse de paramètres d'inspection

Publications (2)

Publication Number Publication Date
WO2023184281A1 true WO2023184281A1 (fr) 2023-10-05
WO2023184281A9 WO2023184281A9 (fr) 2024-01-11

Family

ID=88198561

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/084212 WO2023184281A1 (fr) 2022-03-30 2022-03-30 Procédé et appareil d'analyse de paramètres d'inspection

Country Status (2)

Country Link
CN (1) CN117157541A (fr)
WO (1) WO2023184281A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117540258B (zh) * 2024-01-10 2024-05-03 深圳市艾克姆科技发展有限公司 一种注塑生产监测方法、装置及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040228186A1 (en) * 2003-02-25 2004-11-18 Kenichi Kadota Analysis method for semiconductor device, analysis system and a computer program product
CN102608514A (zh) * 2011-01-20 2012-07-25 中国科学院微电子研究所 器件电学特性相关性分析方法及器件结构优化方法
CN113176761A (zh) * 2021-04-28 2021-07-27 西安电子科技大学 基于机器学习的多特征薄板零件质量预测与工艺参数优化

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040228186A1 (en) * 2003-02-25 2004-11-18 Kenichi Kadota Analysis method for semiconductor device, analysis system and a computer program product
CN102608514A (zh) * 2011-01-20 2012-07-25 中国科学院微电子研究所 器件电学特性相关性分析方法及器件结构优化方法
CN113176761A (zh) * 2021-04-28 2021-07-27 西安电子科技大学 基于机器学习的多特征薄板零件质量预测与工艺参数优化

Also Published As

Publication number Publication date
CN117157541A (zh) 2023-12-01
WO2023184281A9 (fr) 2024-01-11

Similar Documents

Publication Publication Date Title
JP3255292B2 (ja) プロセス管理システム
CN110543903B (zh) 一种gis局部放电大数据系统的数据清洗方法及系统
JP2001256480A (ja) 画像自動分類方法及び装置
CN107679734A (zh) 一种用于无标签数据分类预测的方法和系统
WO2020156409A1 (fr) Procédé de traitement de données, procédé de détection de défaut, appareil informatique et support de stockage
WO2023184281A1 (fr) Procédé et appareil d'analyse de paramètres d'inspection
EP4244687A1 (fr) Systèmes et procédés d'apprentissage automatique amélioré utilisant une prédiction hiérarchique et des seuils composés
Huang et al. Handling discontinuous effects in modeling spatial correlation of wafer-level analog/RF tests
KR102470763B1 (ko) 데이터 이상치 탐색 장치 및 방법
CN114930385A (zh) 用于缺陷分析的计算机实现的方法、用于缺陷分析的设备、计算机程序产品和智能缺陷分析系统
CN112949735A (zh) 一种基于离群数据挖掘的液态危化品挥发浓度异常发现方法
US20230169681A1 (en) Quantitative evaluation method and system for prediction result of remote sensing inversion
WO2024000356A1 (fr) Procédé et appareil de traitement de données, procédé et appareil d'affichage de données, et dispositif et support
WO2022227094A1 (fr) Procédé et appareil de traitement de données, dispositif et support de stockage
CN114880954A (zh) 一种基于机器学习的滑坡敏感性的评估方法
CN115034005A (zh) 一种面向构件剩余使用寿命预测的模型分析可视化方法
US20220334043A1 (en) Non-transitory computer-readable storage medium, gate region estimation device, and method of generating learning model
CN111667920A (zh) 一种基于定位数据的人群密切接触排查方法
WO2022088084A1 (fr) Procédé, appareil et système de traitement de données, et dispositif électronique
US11592807B2 (en) Manufacturing defect factor searching method and manufacturing defect factor searching apparatus
Liu Data analytics and smart city operations
Snatkina et al. Determination of fruit quality by image using deep neural network
CN112884167B (zh) 一种基于机器学习的多指标异常检测方法及其应用系统
US20140222489A1 (en) Quantifying the Quality of Trend Lines
CN114860547A (zh) 一种良率预警和诊断分析的方法、装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22934132

Country of ref document: EP

Kind code of ref document: A1