CN112130518B - Method and system for monitoring parameters in semiconductor production process and computer readable storage medium - Google Patents

Method and system for monitoring parameters in semiconductor production process and computer readable storage medium Download PDF

Info

Publication number
CN112130518B
CN112130518B CN202011367625.3A CN202011367625A CN112130518B CN 112130518 B CN112130518 B CN 112130518B CN 202011367625 A CN202011367625 A CN 202011367625A CN 112130518 B CN112130518 B CN 112130518B
Authority
CN
China
Prior art keywords
parameter
parameters
jumping point
trend
jumping
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202011367625.3A
Other languages
Chinese (zh)
Other versions
CN112130518A (en
Inventor
孙姗姗
徐东东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jingxincheng Beijing Technology Co Ltd
Original Assignee
Jingxincheng Beijing Technology Co Ltd
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 Jingxincheng Beijing Technology Co Ltd filed Critical Jingxincheng Beijing Technology Co Ltd
Priority to CN202011367625.3A priority Critical patent/CN112130518B/en
Publication of CN112130518A publication Critical patent/CN112130518A/en
Application granted granted Critical
Publication of CN112130518B publication Critical patent/CN112130518B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G05B19/0423—Input/output
    • G05B19/0425—Safety, monitoring
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
    • H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
    • H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
    • H01L21/67005—Apparatus not specifically provided for elsewhere
    • H01L21/67242—Apparatus for monitoring, sorting or marking
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
    • H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
    • H01L22/10—Measuring as part of the manufacturing process
    • H01L22/12—Measuring as part of the manufacturing process for structural parameters, e.g. thickness, line width, refractive index, temperature, warp, bond strength, defects, optical inspection, electrical measurement of structural dimensions, metallurgic measurement of diffusions
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
    • H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
    • H01L22/10—Measuring as part of the manufacturing process
    • H01L22/14—Measuring as part of the manufacturing process for electrical parameters, e.g. resistance, deep-levels, CV, diffusions by electrical means

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Computer Hardware Design (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Condensed Matter Physics & Semiconductors (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The embodiment of the application discloses a method and a system for monitoring parameters in the semiconductor production process and a computer readable storage medium, wherein the method comprises the following steps: s1 determines parameters needing trend identification and/or skip point identification, parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period are obtained, S2 sequences the obtained parameter data according to a time sequence, S3 calls a data identification algorithm to change and identify the sequenced parameter data to obtain change information of the parameters, S4 searches parameter data corresponding to the parameters of other products or other machines, and S2-S3 is executed, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, early warning prompt of the parameters is carried out. Through implementing this application, solve the data identification efficiency that exists among the prior art lower, the consumption time is longer and the rate of accuracy is lower scheduling problem.

Description

Method and system for monitoring parameters in semiconductor production process and computer readable storage medium
Technical Field
The present application relates to the field of semiconductor technologies, and in particular, to a method and a system for monitoring parameters during a semiconductor manufacturing process, and a computer-readable storage medium.
Background
Various types of parameter data, such as inline metrology data (inline), electrical test data, tool sensing data, tool parameter data, etc., are generated during semiconductor manufacturing. When these parameter data are abnormal, the yield may be reduced, and the chip may be scrapped. Engineers need to monitor these parameter data in real time, check the long-term change state of these parameter data, whether there is trend or the condition of jumping occurs along with the change of time, and find out the root cause (root cause) of the parameter data with problems in time, so as to improve the process and the yield.
At present, engineers adopt manual methods for identifying long-term change trends and jumping points of the parameter data. Specifically, the engineer draws a trend graph (trend chart) of the parameter data at regular time, and identifies the parameter having tendency or having jumping point by human eyes. However, in practice, it is found that the method for identifying the trend or the skip point of the parameter data has low efficiency, long time consumption and low accuracy, and is not beneficial to effectively monitoring the semiconductor production process.
Disclosure of Invention
The embodiment of the application provides a method and a system for monitoring parameters in a semiconductor production process and a computer readable storage medium, which can solve the problems of low efficiency, long time consumption, low accuracy and the like in the prior art.
In a first aspect, a semiconductor data identification method is provided, including:
step S1, determining parameters needing trend identification and/or jumping point identification, and acquiring parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period;
step S2, sequencing the acquired parameter data according to time sequence;
step S3, invoking a data recognition algorithm to perform change recognition on the sorted parameter data to obtain change information of the parameter, where the change information includes a trend type and/or trip point information, and the trip point information includes at least one of the following items: the jumping point type, the jumping point position, the jumping point number and the jumping point occurrence time;
step S4, searching parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine, executing steps S2-S3, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, performing early warning prompt of the parameters.
In some embodiments, the change is identified as the trend identification, and the step S3 specifically includes:
calling a trend matching M-K algorithm to perform trend identification on the sorted parameter data so as to obtain a trend type of the parameter;
wherein the trend type includes an ascending trend, a descending trend, or a smooth trend.
In some embodiments, the change identification is a skip point identification, and the step S3 specifically includes:
calling a jumping point detection algorithm to perform jumping point identification on the sequenced parameter data to obtain jumping point information of the parameters;
wherein if the jumping point detection algorithm is a jumping point detection pettitt algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point shift, and the jumping point information includes at least one of the following items: the positions of the mutation points, the number of the mutation points and the occurrence time of the mutation points;
if the jumping point detection algorithm is a standard normal detection SNHT algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point jump, and the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points and the occurrence time of the jumping points.
The mutation point refers to a position point of a mutation moment corresponding to the semiconductor data mutating from one stable stage to another stable stage; the jumping point refers to a position point where the semiconductor data abruptly changes.
In some embodiments, after the step S4, the method further includes:
in an event management system TMS, matching whether a corresponding machine operation event exists in the preset time period according to the change information of the parameters;
and if the corresponding machine operation event exists, generating a feedback result, wherein the feedback result is used for prompting that the machine operation event is possibly a reason for generating the change information of the parameter.
In some embodiments, the variation information of the parameter includes a trend type and a skip point information, and after obtaining the variation information of the parameter in step S3, the method further includes:
drawing a curve of the trend type of the parameter, and marking the jumping point information on the curve of the trend type so as to visualize the change information of the parameter.
In some embodiments, the parameter comprises at least one of an electrical test parameter, an inline metrology parameter, a yield parameter, a tool sensor parameter, a tool parameter, the parameter data comprising at least one of an electrical test data, an inline metrology data, a yield data, a tool sensor data, and a tool parameter data.
In a second aspect, a terminal device is provided, where the terminal device may perform the method in the first aspect or any one of the optional implementation manners of the first aspect. The function can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more units corresponding to the above functions. The unit may be software and/or hardware.
In a third aspect, another parameter monitoring system is provided, the system comprising a processor and a memory coupled to the processor; wherein the memory comprises computer readable instructions; the processor is configured to execute the computer readable instructions in the memory, thereby causing the system to perform the aspects of the first aspect or any one of the alternative embodiments of the first aspect.
In a fourth aspect, there is provided a computer program product which, when run on a computer, causes the computer to perform the method of the first aspect or any one of the alternative embodiments of the first aspect.
In a fifth aspect, there is provided a chip product for carrying out the method of the first aspect or any one of the alternative embodiments of the first aspect.
A sixth aspect provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the method of the first aspect or any one of the alternative embodiments of the first aspect.
Drawings
Fig. 1 is a schematic flowchart of a method for monitoring parameters in a semiconductor manufacturing process according to an embodiment of the present disclosure.
Fig. 2-7 are schematic diagrams of several parameter data provided by embodiments of the present application.
Fig. 8 is a schematic structural diagram of a parameter monitoring system according to an embodiment of the present application.
Fig. 9 is a schematic structural diagram of another parameter monitoring system according to an embodiment of the present application.
Detailed Description
Specific embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The applicant has also found in the course of the present application that: at present, engineers adopt manual methods for identifying long-term trend change and skip points of parameter data, specifically, engineers draw a trend change graph (trend chart) of parameter data at regular time, and identify parameters with trends or skip points by human eyes; and then, manually matching the parameter data of the trend change or the jump point with the events recorded in an event Management System (TMS) to find the reason of the trend change or the jump point. In addition, because the types of the parameter data are various, the comparison and analysis of the same type of data are also realized through artificial comparison, the comparison process is more complicated, and the labor is consumed. Therefore, the conventional parameter data trend or skip point identification method is low in implementation efficiency, time and labor consumption and low in accuracy.
In order to solve the above problems, the present application provides a method, a system and a computer storage medium for monitoring parameters in a semiconductor manufacturing process. Fig. 1 is a schematic flow chart illustrating a method for monitoring parameters in a semiconductor manufacturing process according to an embodiment of the present disclosure. The method as shown in fig. 1 comprises the following implementation steps:
step S1, the parameter monitoring system determines the parameters that need trend identification and/or skip point identification, and obtains the parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period.
The parameters of the present application refer to various types of parameters generated during the semiconductor manufacturing process, which may include, but are not limited to, on-line (inline) measurement parameters, yield parameters, electrical measurement parameters, tool sensor parameters, tool parameters, or other parameters. The parameter Data refers to Data corresponding to the parameter, and may include, but is not limited to, on-line (inline) measurement Data, yield Data (Chip Probe, CP), electrical measurement Data (WAT), tool sensor Data (FDC), or tool parameter Data (ED).
In the semiconductor production process, the parameter monitoring system can collect parameters needing trend identification and/or jump point identification, and the parameters can be set by the system in a self-defined mode or the user in a self-defined mode, such as machine parameters ED or electrical property measurement parameters WAT. After determining the parameters which need to be subjected to trend identification and/or skip point identification, the parameter monitoring system can also acquire parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period. For example, in the parameter monitoring system, a user may input a parameter name for trend identification and/or skip point identification, and then the system obtains parameter data corresponding to the parameter generated by the target product or the target machine within a preset time period according to the parameter name. The preset time period is a time period which is set by a system or a user in a self-defined way, such as every day, every week, every month and the like.
And step S2, the parameter monitoring system sorts the acquired parameter data according to time sequence.
In the present application, the parameter monitoring system sorts the parameter data acquired in step S1 according to the time sequence to obtain a time sequence arranged according to the time sequence, that is, the sorted parameter data.
Step S3, the parameter monitoring system calls a data recognition algorithm to perform change recognition on the sorted parameter data to obtain the change information of the parameters, wherein the change information comprises a trend type and/or jumping point information, and the jumping point information comprises at least one of the following items: the type of the jumping point, the position of the jumping point, the number of the jumping points and the occurrence time of the jumping point.
As a possible implementation manner, if the data identification algorithm is a trend matching M-K algorithm, the parameter monitoring system invokes the M-K algorithm to perform trend identification on the sorted parameter data, so as to obtain a trend type of the parameter, where the trend type includes at least one of the following: a trend up/descending, a trend down/descending, and a smooth trend (also referred to as no trend).
The M-K algorithm refers to a Mann-Kendall algorithm, and is an algorithm commonly used for mutation detection or trend detection in meteorology/climate. The M-K algorithm does not require that the parameter data is normally distributed and does not require the variation trend, and the principle can be used for carrying out pairing comparison on two observation values which are separated, namely the observation value XjAnd Xk，Xj-XkAbout have
Figure DEST_PATH_IMAGE001
And determining the sign (namely the sign) of the difference value of each pair by using the pairs, and judging the variation trend of the parameter data (namely the trend type of the parameter) by using the positive and negative values of the total difference value. Where j > K, and n is the number of parameter data (also referred to as data number) input to the M-K algorithm.
Specifically, the parameter monitoring system invokes an M-K algorithm to pair and compare two observation values (which may also be referred to as observation data) separated from each other in the sorted parameter data, so as to obtain respective signs of a plurality of paired difference values. Then carrying out statistical operation on the differences of the multiple pairs to obtain total differences corresponding to the multiple pairs, and if the total differences are positive values and the absolute values of the total differences are greater than a certain threshold, determining that the trend type of the parameters is an ascending trend; and if the total difference value is a negative value and the absolute value of the total difference value is greater than a certain threshold, determining that the trend type of the parameter is a descending trend, otherwise, determining that the trend type of the parameter is a steady trend.
For example, please refer to fig. 2, which illustrates a schematic diagram of parameter data. The parameter data shown in FIG. 2 is ED data, which includes 5 observed values, x respectively1=206、x2=223、x3=235、x4=264 and x5=229, the parameter monitoring system invokes the M-K algorithm to pair and compare two adjacent observed values in the parameter data to obtain the sign of the difference value of 4 pairs, specifically the first pair (x)2，x1) = (223, 206), its difference 223-; by analogy accordingly, a second pairing (x) can be obtained3，x2) The difference value of (a) is a positive value, and the sign of the difference value is also a positive sign; third pairing (x)4，x3) The difference value of (a) is a positive value, and the sign of the difference value is also a positive sign; fourth pairing (x)5，x4) The difference of (a) is a negative value, and the sign thereof is a negative sign. From the above statistics it follows that: if there are 3 positive values and 1 negative value in the 4 paired difference values, statistical operation can be further performed on the 4 paired difference values to determine that the parameter data in this example is in an ascending trend.
Also shown in fig. 3-5 are schematic diagrams of parameter data for three different trend types. In all of the 3 diagrams, the parameter data is taken as the ED data of the machine sensor as an example, as shown in fig. 3: the parameter monitoring system calls an M-K algorithm to recognize that the trend type of the ED data shown in FIG. 3 is an ascending trend, as shown in FIG. 4: the parameter monitoring system calls the M-K algorithm to the ED data shown in FIG. 4, wherein the trend type is a descending trend, as shown in FIG. 5: the parameter monitoring system calls an M-K algorithm to recognize that the trend type of the ED data shown in FIG. 5 is a steady trend, i.e. no trend. Details about how to identify the trend type of the ED data based on the M-K algorithm are not described herein.
As another possible implementation manner, if the data identification algorithm is a skip point detection algorithm, the parameter monitoring system calls the skip point detection algorithm to perform skip point identification on the sorted parameter data to obtain skip point information of the parameter, where the skip point information includes at least one of the following items: hop type, hop location, hop count, hop time, or other information used to describe a hop. Wherein the jumping point type comprises a jumping point shift or a jumping point jump. When the hop type indicates that the hop is a burst, the hop information may specifically include at least one of the following: the position of the burst point, the number of the burst points, the time of occurrence of the burst point, or other information used for describing the burst point, and accordingly the skip point detection algorithm may be specifically a burst point detection algorithm, such as a pettitt algorithm. Conversely, when the jumping point type indicates that the jumping point is a jumping point, the jumping point information may specifically include at least one of the following: the jumping point detection algorithm may specifically be a jumping point detection algorithm, such as a Standard Normal Homogeneeity Test (SNHT) algorithm, for example.
In a specific embodiment, if the jumping point detection algorithm is a jumping point detection petttitt algorithm, that is, the data identification algorithm is a petttitt algorithm, the parameter monitoring system calls the petttitt algorithm to identify the jumping points of the sorted parameter data, so as to obtain the jumping point information of the parameter, where the jumping point information includes at least one of the following: the location of the mutation point, the number of mutation points, the time at which the mutation point occurred, or other information used to describe the mutation point. The pettitt algorithm is mainly based on the principle that two adjacent observed values are used for carrying out pairing comparison or matching comparison, if an observer of the latter is larger than the observed value of the former, the observed value is marked as 1, otherwise, the observed value is marked as-1, the accumulated statistic of the semiconductor data is counted in sequence, when the accumulated statistic reaches the maximum value, the moment of occurrence of the mutation point (also called the time of occurrence of the mutation point) is determined, and the position point corresponding to the moment is called the mutation point. The embodiments of the present application are not explained much about the pettitt algorithm.
For example, please refer to fig. 6, which shows a schematic diagram of parameter data with mutation points. As shown in fig. 6, taking the parameter data as the ED data as an example, the parameter monitoring system calls a petttitt algorithm to perform mutation point detection/identification on the ED data shown in fig. 6, so as to obtain a mutation point indicated by an arrow in the figure. As shown in fig. 6, there is a mutation point in the ED data, and the occurrence time of the mutation point (referred to as the mutation point occurrence time) is 1096 seconds(s). In practical applications, the number of mutation points in the parameter data is not limited to one, and may be a plurality of mutation points. This example illustrates only one mutation point, but is not limited thereto.
The mutation point referred to in the present application refers to a position point of a mutation moment corresponding to the sequenced parameter data from one stationary phase to another stationary phase, for example, the mutation point shown by an arrow in fig. 6 is that the parameter data is in one stationary phase before the period 0-1096, the parameter data is in another stationary phase during the period 1096 and 6000, and 1096 is a mutation occurrence time when the parameter data jumps from one stationary phase to another stationary phase, and the position point corresponding to the time is a mutation point.
In another embodiment, if the jumping point detection algorithm is the SNHT algorithm, that is, the data identification algorithm is the SNHT algorithm, the parameter monitoring system calls the SNHT algorithm to perform jumping point identification on the sorted parameter data, so as to obtain jumping point information of the parameter, where the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points, the occurrence time of the jumping point, and other information describing the jumping point. The principle of the SNHT algorithm is mainly to divide sorted parameter data into at least two subsequences, and determine whether a step, i.e. a jump point, exists between two adjacent subsequences by comparing the difference between the two adjacent subsequences. The embodiments of the present application are not explained herein too much with respect to the SNHT algorithm.
For example, please refer to fig. 7, which illustrates a schematic diagram of parameter data with jumping points. As shown in fig. 7, the parameter monitoring system invokes the SNHT algorithm to perform jumping point identification on the parameter data shown in fig. 7, so as to obtain jumping points marked by circles in fig. 7. In practical applications, there may be one or more jumping points (referred to as jumping points), and the illustration shows a plurality of jumping points as an example, but the illustration is not limited thereto.
The jumping points referred to in the present application refer to the position points where the sorted parameter data suddenly changes, for example, jumping points where the parameter data changes significantly at two times, 1049s and 1100s, as shown in fig. 7.
Step S4, the parameter monitoring system searches parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine, and executes steps S2-S3, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, early warning prompt of the parameters is carried out.
In the application, adaptive input and output windows of different types of data (for example, ED data or WAT data and the like) can be preset in the parameter monitoring system, so that the system can perform change identification/analysis on the different types of data in the window period, the analysis requirements of different demanders on the different types of data are met, and the system is simple to operate. For example, after obtaining the change information of the parameter, the parameter monitoring system may search for parameter data corresponding to the parameter of other similar products or machines, where the parameter data may specifically refer to parameter data corresponding to the parameter generated within the preset time period by other products or machines that belong to the same type as the target product or the target machine in step S1. And executing steps S2-S3, namely sequencing the parameter data, calling a data identification algorithm to identify the change of the sequenced parameter data, and obtaining the change information of the parameter. For how to realize the identification of the change of the parameter data and the change information of the parameter based on the data identification algorithm, reference may be made to the related description in the foregoing step S3, and details are not repeated here.
Further, when the parameter of the other product or the other machine has the same change information as the target product and the target machine, for example, has the same trend type or has the same trip point information, the parameter monitoring system may perform an early warning prompt of the parameter to prompt that the other product or the other machine has the same problem (issue) as the target product or the target machine, for example, has the same trend type, in the preset time period.
In an optional embodiment, after obtaining the change information of the parameter, the parameter monitoring system may further draw a curve of the trend type of the parameter according to the sorted parameter data, that is, draw a change trend graph (trend chart) of the parameter data. And further marking the jumping point information on a curve of the trend type of the parameter, for example, marking the jumping point position, the jumping point occurrence time and other information on a change trend graph, thereby realizing the visualization of the change information of the parameter.
In an optional embodiment, when the parameter monitoring system monitors and identifies the sorted parameter data, if it is found that the parameter has change information (for example, a skip point or a change trend type has occurred) in a preset time period, the parameter monitoring system may further quickly search/match whether a corresponding machine operation event (TMS event) exists in the preset time period in the TMS system, where at least one event related to the machine, for example, a machine maintenance event, is recorded in the TMS system. And if the corresponding machine operation event exists, generating a feedback result, wherein the feedback result is used for prompting that the machine operation event is possibly a reason for causing the change information of the parameter. If the corresponding machine operation event does not exist, the process is ended.
For example, taking the change information of the parameter as an example, the parameter monitoring system may first determine a trip point occurrence time corresponding to the trip point position, then search the parameter data in the TMS system for whether a corresponding machine operation event (for example, a machine maintenance event, etc.) exists at the trip point occurrence time, and if so, generate a feedback result for prompting an engineer that the trip point generated by the parameter data at the trip point occurrence time may be due to the machine maintenance event, so that the engineer further confirms a specific reason for the trip point generation, and the like.
By implementing the embodiment of the application, the parameter monitoring system determines the parameters needing trend identification and/or jumping point identification, acquiring parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period, sequencing the acquired parameter data according to a time sequence, calling a data identification algorithm to change and identify the sequenced parameter data to obtain the change information of the parameters, searching the parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine, and executing the steps of sequencing the acquired parameter data according to a time sequence, calling a data identification algorithm to change and identify the sequenced parameter data to obtain the change information of the parameters, and when the parameters of the other products or other machines and the parameters of the target products or target machines have the same change information, performing early warning prompt on the parameters. On one hand, data change identification can be avoided by comparing the change trend graph of the parameter data one by one manually, manpower is saved, the identification efficiency of an engineer for the parameter data is improved, and on the other hand, the change identification/analysis is carried out on the parameter data through an algorithm, so that the problem occurrence time can be captured, and the event problem (event issue) which causes the problem to appear can be found in time. In addition, the problems of low efficiency, time consumption, labor consumption, low accuracy and the like in the conventional parameter data identification method can be solved, and the accuracy and the efficiency of parameter monitoring are improved.
Please refer to fig. 8, which is a schematic structural diagram of a parameter monitoring system according to an embodiment of the present application. The parameter monitoring system 800 shown in fig. 8 includes an obtaining unit 801, a sorting unit 802, an identifying unit 803, and a processing unit 804, wherein:
the acquiring unit 801 is configured to determine a parameter that needs to perform trend identification and/or skip point identification, and acquire parameter data corresponding to the parameter generated by a target product or a target machine within a preset time period;
the sorting unit 802 is configured to sort the acquired parameter data according to a time sequence;
the identifying unit 803 is configured to invoke a data identification algorithm to perform change identification on the sorted parameter data to obtain change information of the parameter, where the change information includes a trend type and/or trip point information, and the trip point information includes at least one of the following: the jumping point type, the jumping point position, the jumping point number and the jumping point occurrence time;
the processing unit 804 is configured to search parameter data corresponding to the parameter of another product or another machine of the same type as the target product or the target machine, call the functions of the sorting unit 802 and the identifying unit 803 to perform corresponding processing on the parameter data, and perform an early warning prompt on the parameter when the parameter of the another product or the another machine and the parameter of the target product or the target machine have the same change information.
In some embodiments, the change identification is the trend identification, and the identifying unit 803 is specifically configured to invoke a trend matching M-K algorithm to perform trend identification on the sorted parameter data to obtain a trend type of the parameter;
wherein the trend type includes an ascending trend, a descending trend, or a smooth trend.
In some embodiments, the change identification is a skip point identification, and the identifying unit 803 is specifically configured to invoke a skip point detection algorithm to perform skip point identification on the sorted parameter data, so as to obtain skip point information of the parameter;
wherein if the jumping point detection algorithm is a jumping point detection pettitt algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point shift, and the jumping point information includes at least one of the following items: the positions of the mutation points, the number of the mutation points and the occurrence time of the mutation points;
if the jumping point detection algorithm is a standard normal detection SNHT algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point jump, and the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points and the occurrence time of the jumping points.
In some embodiments, the parameter monitoring system 800 further comprises a matching unit 805 and a generating unit 806, wherein:
the matching unit 805 is configured to match, in the event management system TMS, whether a corresponding machine operation event exists within the preset time period according to the change information of the parameter;
the generating unit 806 is configured to generate a feedback result if the corresponding machine operation event exists, where the feedback result is used to prompt that the machine operation event may be a cause of generating the change information of the parameter.
In some embodiments, the change information of the parameter includes a trend type and skip point information, and after obtaining the change of the parameter, the processing unit 804 is further configured to draw a curve of the trend type of the parameter and mark the skip point information on the curve of the trend type, so as to visualize the change information of the parameter.
By implementing the embodiment of the application, the parameter monitoring system determines the parameters needing trend identification and/or jumping point identification, acquiring parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period, sequencing the acquired parameter data according to a time sequence, calling a data identification algorithm to change and identify the sequenced parameter data to obtain the change information of the parameters, searching the parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine, and executing the steps of sequencing the acquired parameter data according to a time sequence, calling a data identification algorithm to change and identify the sequenced parameter data to obtain the change information of the parameters, and when the parameters of the other products or other machines and the parameters of the target products or target machines have the same change information, performing early warning prompt on the parameters. On one hand, data change identification can be avoided by comparing the change trend graph of the parameter data one by one manually, manpower is saved, the identification efficiency of an engineer for the parameter data is improved, and on the other hand, the change identification/analysis is carried out on the parameter data through an algorithm, so that the problem occurrence time can be captured, and the event problem (event issue) which causes the problem to appear can be found in time. In addition, the problems of low efficiency, time consumption, labor consumption, low accuracy and the like in the conventional parameter data identification method can be solved, and the accuracy and the efficiency of parameter monitoring are improved.
Please refer to fig. 9, which is a schematic structural diagram of another parameter monitoring system according to an embodiment of the present application. The parameter monitoring system 900 shown in FIG. 9 includes: at least one input device 901; at least one output device 902; at least one processor 903, e.g., a CPU; and a memory 904, the input device 901, the output device 902, the processor 903, and the memory 904 being connected by a bus 905.
The input device 901 may specifically be a touch panel of a mobile terminal, and includes a touch screen and a touch screen, and is configured to detect an operation instruction on the touch panel of the terminal.
The output device 902 may be a display screen of the mobile terminal, and is used for outputting and displaying information.
The memory 904 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 904 is configured to store a set of program codes, and the input device 901, the output device 902, and the processor 903 are configured to call the program codes stored in the memory 904 to execute corresponding operations, where the processor 903 is specifically configured to execute the following operations:
step S1, determining parameters needing trend identification and/or jumping point identification, and acquiring parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period;
step S2, sequencing the acquired parameter data according to time sequence;
step S3, invoking a data recognition algorithm to perform change recognition on the sorted parameter data to obtain change information of the parameter, where the change information includes a trend type and/or trip point information, and the trip point information includes at least one of the following items: the jumping point type, the jumping point position, the jumping point number and the jumping point occurrence time;
step S4, searching parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine, executing steps S2-S3, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, performing early warning prompt of the parameters.
In some embodiments, the change is identified as the trend identification, and the processor 903 is specifically configured to perform the following steps:
calling a trend matching M-K algorithm to perform trend identification on the sorted parameter data so as to obtain a trend type of the parameter;
wherein the trend type includes an ascending trend, a descending trend, or a smooth trend.
In some embodiments, the change is identified as a skip point identification, and the processor 903 is specifically configured to perform the following steps:
calling a jumping point detection algorithm to perform jumping point identification on the sequenced parameter data to obtain jumping point information of the parameters;
if the jumping point detection algorithm is a jumping point detection pettitt algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point shift, and at this time, the jumping point information includes at least one of the following items: the positions of the mutation points, the number of the mutation points and the occurrence time of the mutation points;
if the jumping point detection algorithm is a standard normal detection SNHT algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point jump, and at this time, the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points and the occurrence time of the jumping points.
In some embodiments, the processor 903 is further configured to perform the following steps:
in an event management system TMS, matching whether a corresponding machine operation event exists in the preset time period according to the change information of the parameters;
and if the corresponding machine operation event exists, generating a feedback result, wherein the feedback result is used for prompting that the machine operation event is possibly a reason for generating the change information of the parameter.
In some embodiments, the variation information of the parameter includes a trend type and a skip point information, and after obtaining the variation information of the parameter in step S3, the processor 903 is further configured to perform the following steps:
drawing a curve of the trend type of the parameter, and marking the jumping point information on the curve of the trend type so as to visualize the change information of the parameter.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims (11)

1. A method for monitoring parameters in a semiconductor manufacturing process, comprising:
step S1, determining parameters needing trend identification and/or jumping point identification, and acquiring first parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period;
step S2, sequencing the acquired first parameter data according to time sequence;
step S3, invoking a data recognition algorithm to perform change recognition on the sorted first parameter data to obtain change information of the parameter, where the change information includes a trend type and/or trip point information, and the trip point information includes at least one of the following: the jumping point type, the jumping point position, the jumping point number and the jumping point occurrence time;
step S4, second parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine are searched, steps S2-S3 are executed, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, early warning prompt of the parameters is carried out.
2. The method for monitoring parameters in a semiconductor manufacturing process according to claim 1, wherein the change is identified as the trend identification, and the step S3 specifically includes:
calling a trend matching M-K algorithm to perform trend identification on the sorted first parameter data so as to obtain a trend type of the parameter;
wherein the trend type includes an ascending trend, a descending trend, or a smooth trend.
3. The method according to claim 1, wherein the change is identified as a skip point, and the step S3 specifically includes:
calling a jumping point detection algorithm to perform jumping point identification on the sorted first parameter data to obtain jumping point information of the parameters;
wherein if the jumping point detection algorithm is a jumping point detection pettitt algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point shift, and the jumping point information includes at least one of the following items: the positions of the mutation points, the number of the mutation points and the occurrence time of the mutation points;
if the jumping point detection algorithm is a standard normal detection SNHT algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point jump, and the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points and the occurrence time of the jumping points.
4. The method of claim 1, wherein after the step S4, the method further comprises:
in an event management system TMS, matching whether a corresponding machine operation event exists in the preset time period according to the change information of the parameters;
and if the corresponding machine operation event exists, generating a feedback result, wherein the feedback result is used for prompting that the machine operation event is possibly a reason for generating the change information of the parameter.
5. The method for monitoring parameters in the semiconductor manufacturing process according to any one of claims 1 to 4, wherein the variation information of the parameters includes trend type and trip point information, and the step S3 further includes, after obtaining the variation information of the parameters:
drawing a curve of the trend type of the parameter, and marking the jumping point information on the curve of the trend type so as to visualize the change information of the parameter.
6. A parameter monitoring system in a semiconductor manufacturing process, comprising a processor and a memory coupled to the processor, wherein the memory includes computer-readable instructions, and wherein the processor is configured to execute the computer-readable instructions in the memory, thereby causing the parameter monitoring system to perform the steps of:
step S1, determining parameters needing trend identification and/or jumping point identification, and acquiring first parameter data corresponding to the parameters generated by a target product or a target machine within a preset time period;
step S2, sequencing the acquired first parameter data according to time sequence;
step S3, invoking a data recognition algorithm to perform change recognition on the sorted first parameter data to obtain change information of the parameter, where the change information includes a trend type and/or trip point information, and the trip point information includes at least one of the following: the jumping point type, the jumping point position, the jumping point number and the jumping point occurrence time;
step S4, second parameter data corresponding to the parameters of other products or other machines of the same type as the target product or the target machine are searched, steps S2-S3 are executed, and when the parameters of the other products or other machines and the parameters of the target product or the target machine have the same change information, early warning prompt of the parameters is carried out.
7. The parameter monitoring system according to claim 6, wherein the change identification is the trend identification, and the parameter monitoring system is specifically configured to perform the following steps when performing step S3:
calling a trend matching M-K algorithm to perform trend identification on the sorted first parameter data so as to obtain a trend type of the parameter;
wherein the trend type includes an ascending trend, a descending trend, or a smooth trend.
8. The parameter monitoring system according to claim 6, wherein the change identification is a skip point identification, and the parameter monitoring system is specifically configured to perform the following steps when performing step S3:
calling a jumping point detection algorithm to perform jumping point identification on the sorted first parameter data to obtain jumping point information of the parameters;
if the jumping point detection algorithm is a jumping point detection pettitt algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point shift, and at this time, the jumping point information includes at least one of the following items: the positions of the mutation points, the number of the mutation points and the occurrence time of the mutation points;
if the jumping point detection algorithm is a standard normal detection SNHT algorithm, the jumping point type in the jumping point information indicates that the jumping point is a jumping point jump, and at this time, the jumping point information includes at least one of the following items: the position of the jumping point, the number of the jumping points and the occurrence time of the jumping points.
9. The parameter monitoring system of claim 6, wherein after performing step S4, the parameter monitoring system is further configured to perform the steps of:
in an event management system TMS, matching whether a corresponding machine operation event exists in the preset time period according to the change information of the parameters;
and if the corresponding machine operation event exists, generating a feedback result, wherein the feedback result is used for prompting that the machine operation event is possibly a reason for generating the change information of the parameter.
10. The parameter monitoring system according to any one of claims 6-9, wherein the variation information of the parameter includes a trend type and a skip point information, and the parameter monitoring system, when executing step S3, after obtaining the variation information of the parameter, is further configured to execute the following steps:
drawing a curve of the trend type of the parameter, and marking the jumping point information on the curve of the trend type so as to visualize the change information of the parameter.
11. A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to execute the method for parameter monitoring in a semiconductor manufacturing process according to any one of claims 1-5.
CN202011367625.3A 2020-11-30 2020-11-30 Method and system for monitoring parameters in semiconductor production process and computer readable storage medium Active CN112130518B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011367625.3A CN112130518B (en) 2020-11-30 2020-11-30 Method and system for monitoring parameters in semiconductor production process and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011367625.3A CN112130518B (en) 2020-11-30 2020-11-30 Method and system for monitoring parameters in semiconductor production process and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN112130518A CN112130518A (en) 2020-12-25
CN112130518B true CN112130518B (en) 2021-02-12

Family

ID=73852432

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011367625.3A Active CN112130518B (en) 2020-11-30 2020-11-30 Method and system for monitoring parameters in semiconductor production process and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN112130518B (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004047885A (en) * 2002-07-15 2004-02-12 Matsushita Electric Ind Co Ltd Monitoring system and monitoring method of semiconductor manufacturing apparatus
CN101978389B (en) * 2008-02-22 2014-07-09 村田机械株式会社 Vao productivity suite
CN103488135B (en) * 2013-08-14 2015-11-04 沈阳中科博微自动化技术有限公司 A kind of statistical process control method for semiconductor production machining process monitoring
CN204206349U (en) * 2014-11-26 2015-03-11 西安寰微电子科技有限公司 A kind of semiconductor Fab production-line technique supervisory control system
US9915932B2 (en) * 2014-12-01 2018-03-13 Applied Materials, Inc. System and method for equipment monitoring using a group candidate baseline and probabilistic model
CN105759748B (en) * 2014-12-18 2018-09-25 中芯国际集成电路制造(上海)有限公司 A kind of dynamic monitoring system and monitoring method of semiconductor production board hardware performance

Also Published As

Publication number Publication date
CN112130518A (en) 2020-12-25

Similar Documents

Publication Publication Date Title
KR101872342B1 (en) Method and device for intelligent fault diagnosis using improved rtc(real-time contrasts) method
CN107766533B (en) Automatic detection method and system for telephone traffic abnormality, storage medium and electronic equipment
JP6708203B2 (en) Information processing apparatus, information processing method, and program
CN111656418B (en) Method for monitoring an industrial automation system and industrial plant monitoring device
JP2009080612A (en) Method for evaluating distribution, method for producing article, distribution evaluation program, and distribution evaluation system
CN109960232B (en) Method for selecting leading auxiliary parameter and method for equipment maintenance pre-diagnosis
JP2012220978A (en) Abnormal factor specifying method and device, program for making computer execute the abnormal factor specifying method, and computer readable recording medium with the program recorded
EP3869424A1 (en) Equipment failure diagnosis support system and equipment failure diagnosis support method
US10642818B2 (en) Causal analysis device, causal analysis method, and non-transitory computer readable storage medium
WO2020166236A1 (en) Work efficiency evaluating method, work efficiency evaluating device, and program
WO2019030945A1 (en) Cause estimation method and program
CN114926051A (en) Analysis system for evaluating manufacturing capacity of semiconductor equipment
CN111612149A (en) Main network line state detection method, system and medium based on decision tree
JP5532782B2 (en) Traceability system and manufacturing process abnormality detection method
CN112130518B (en) Method and system for monitoring parameters in semiconductor production process and computer readable storage medium
JP6273835B2 (en) State determination device, state determination method, and state determination program
JP2008250910A (en) Data mining method and process management method
JP7034874B2 (en) Process state analysis device and process state display method
KR102093287B1 (en) Method for measuring indirectly tool wear of CNC machine
US11762562B2 (en) Performance analysis apparatus and performance analysis method
WO2016163008A1 (en) Fault diagnostic device and fault diagnostic method
CN112000717B (en) Semiconductor data analysis method, system and computer readable storage medium
CN116307407B (en) Enterprise data visualization processing system and method based on cloud computing
CN114975184A (en) Semiconductor yield monitoring method and device, electronic equipment and storage medium
CN109753427B (en) Analysis system for power generation and supply test unit

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant