CN116433109B - Method and system for monitoring, cleaning and managing semiconductor production environment - Google Patents
Method and system for monitoring, cleaning and managing semiconductor production environment Download PDFInfo
- Publication number
- CN116433109B CN116433109B CN202310691683.9A CN202310691683A CN116433109B CN 116433109 B CN116433109 B CN 116433109B CN 202310691683 A CN202310691683 A CN 202310691683A CN 116433109 B CN116433109 B CN 116433109B
- Authority
- CN
- China
- Prior art keywords
- index
- static
- correlation
- dynamic
- vector
- 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
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 223
- 239000004065 semiconductor Substances 0.000 title claims abstract description 64
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000004140 cleaning Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 230
- 230000003068 static effect Effects 0.000 claims abstract description 170
- 239000011159 matrix material Substances 0.000 claims abstract description 134
- 238000007726 management method Methods 0.000 claims abstract description 78
- 230000008859 change Effects 0.000 claims description 69
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 239000000428 dust Substances 0.000 description 21
- 238000004458 analytical method Methods 0.000 description 10
- 230000001105 regulatory effect Effects 0.000 description 10
- 239000002912 waste gas Substances 0.000 description 8
- 239000007789 gas Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003749 cleanliness Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000001259 photo etching Methods 0.000 description 2
- 229920002120 photoresistant polymer Polymers 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 239000000809 air pollutant Substances 0.000 description 1
- 231100001243 air pollutant Toxicity 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000013043 chemical agent Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Factory Administration (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
Abstract
The invention provides a method and a system for monitoring and cleaning management of a semiconductor production environment, which relate to the technical field of semiconductor production environment management, and the method comprises the following steps: acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor; obtaining a static index matrix and a dynamic index matrix; obtaining a plurality of production areas; performing correlation vector recognition to obtain a static correlation vector and a dynamic correlation vector; performing management parameter adjustment on the static correlation vector and the dynamic correlation vector, and outputting parameter adjustment results, wherein the parameter adjustment results are parameter adjustment results of management grades; and outputting the clean management index matrixes corresponding to the production areas respectively according to the parameter adjustment results, solving the technical problem of low clean management efficiency caused by insufficient detail of data analysis of different production processes in the prior art, and achieving the technical effect of improving the clean management efficiency and accuracy.
Description
Technical Field
The invention relates to the technical field of semiconductor production environment management, in particular to a method and a system for monitoring, cleaning and managing a semiconductor production environment.
Background
Semiconductors are very important for both economic development and resident life today, where technology is evolving at a high rate. Most of the core elements of electronic products, such as integrated circuits, are of great relevance to semiconductors. At present, the cleaning management of the semiconductor production environment in the traditional method mainly depends on manual management adjustment, the intelligent degree is low, and the technical problem of low cleaning management efficiency is caused by insufficient detail of data analysis of different production processes.
Disclosure of Invention
The invention provides a method and a system for monitoring and cleaning management of a semiconductor production environment, which are used for solving the technical problem of low cleaning management efficiency caused by insufficient detail of data analysis of different production processes in the prior art.
According to a first aspect of the present invention, there is provided a method for monitoring, cleaning and managing a semiconductor production environment, comprising: acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index that parameter change is close to static in a workshop production process, and the workshop dynamic environment index is an index that parameter change is dynamic in the workshop production process; generating a matrix according to the workshop static environment index and the workshop dynamic environment index to obtain a static index matrix and a dynamic index matrix; dividing a production workshop of the target semiconductor into a plurality of production areas, wherein each production area corresponds to one production node; carrying out related vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix to obtain a static related vector and a dynamic related vector; performing management parameter adjustment on the static correlation vector and the dynamic correlation vector, and outputting parameter adjustment results, wherein the parameter adjustment results are parameter adjustment results of management grades; and outputting the cleaning management index matrixes respectively corresponding to the production areas according to the parameter adjustment result.
According to a second aspect of the present invention, there is provided a monitoring, cleaning and management system for a semiconductor production environment, comprising: the environment index acquisition module is used for acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index of which the parameter change is close to static in the workshop production process, and the workshop dynamic environment index is an index of which the parameter change is dynamic in the workshop production process; the index matrix generation module is used for generating a matrix according to the workshop static environment index and the workshop dynamic environment index to obtain a static index matrix and a dynamic index matrix; the workshop area dividing module is used for dividing areas of the production workshops of the target semiconductor to obtain a plurality of production areas, wherein each production area corresponds to one production node; the correlation vector identification module is used for obtaining a static correlation vector and a dynamic correlation vector by carrying out correlation vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix; the management parameter adjusting module is used for carrying out management parameter adjustment on the static correlation vector and the dynamic correlation vector and outputting parameter adjusting results, wherein the parameter adjusting results are parameter adjusting results of management grades; and the clean management index matrix output module is used for outputting the clean management index matrix corresponding to the production areas respectively according to the parameter adjustment result.
According to the method for monitoring and cleaning management of the semiconductor production environment, the workshop environment of a production target semiconductor is analyzed to obtain a static index matrix and a dynamic index matrix, a production workshop of the target semiconductor is further divided according to production nodes to obtain a plurality of production areas, the static correlation vector and the dynamic correlation vector are obtained by carrying out correlation vector identification on the plurality of production areas, the static correlation vector and the dynamic correlation vector, and further management and parameter adjustment are carried out on the static correlation vector and the dynamic correlation vector, and a parameter adjustment result is output, wherein the parameter adjustment result is a parameter adjustment result of management level, and clean management index matrixes corresponding to the plurality of production areas are output according to the parameter adjustment result, so that independent parameter adjustment is carried out on different production nodes and different production areas, and the effect of improving the cleaning management accuracy and the management efficiency is achieved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for monitoring and cleaning a semiconductor production environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of obtaining static correlation vectors and dynamic correlation vectors according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of managing and adjusting parameters of each production area based on parameter adjustment coefficients according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a system for monitoring and cleaning a semiconductor production environment according to an embodiment of the present invention.
Reference numerals illustrate: the system comprises an environment index acquisition module 11, an index matrix generation module 12, a workshop area division module 13, a correlation vector identification module 14, a management parameter adjustment module 15 and a clean management index matrix output module 16.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to solve the technical problem of low cleaning management efficiency caused by insufficient detail of data analysis of different production flows in the prior art, the inventor of the invention obtains the method and the system for monitoring and cleaning management of the semiconductor production environment through creative labor.
Example 1
Fig. 1 is a diagram of a method for monitoring and cleaning a semiconductor production environment according to an embodiment of the present invention, as shown in fig. 1, where the method includes:
step S100: acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index that parameter change is close to static in a workshop production process, and the workshop dynamic environment index is an index that parameter change is dynamic in the workshop production process;
specifically, a semiconductor is a generic term for a class of materials, which refers to a material having conductivity between that of a conductor and an insulator at ordinary temperature. Semiconductors are used in integrated circuits, consumer electronics, communication systems, photovoltaic power generation, lighting, high power conversion, etc., and diodes are devices fabricated using semiconductors. The target semiconductor is a semiconductor type produced in a production workshop, and when the target semiconductor is produced, workshop static environment indexes and workshop dynamic environment indexes which influence the production quality of the semiconductor and the health of workers are obtained, the workshop static environment indexes are environment indexes such as temperature and humidity in a workshop environment, and the parameter variation amplitude of the environment indexes is generally smaller and approaches to the static state in the semiconductor production process, so that the workshop static environment indexes are called. The dynamic environment index of the workshop refers to granular pollutants such as dust, waste gas and the like in the workshop, and the real-time dynamic change amplitude of parameters of the indexes is obvious, so that the indexes are called as the static environment index of the workshop.
Step S200: generating a matrix according to the workshop static environment index and the workshop dynamic environment index to obtain a static index matrix and a dynamic index matrix;
specifically, the index matrix is used for recording the relation between the index and the dimension, is used for constructing a visual data structure, and colloquially speaking, the workshop static environment index comprises index parameters under a plurality of dimensions such as environment temperature, environment humidity and the like according to the index and the dimension layout matrix structure, and constructs a static index matrix according to the number of the environment index dimensions contained in the workshop static environment index; the workshop dynamic environment index comprises index parameters of dust, waste gas and the like in a workshop, a dynamic index matrix is constructed according to index dimensions contained in the workshop dynamic environment index, and the static index matrix and the dynamic index matrix are updated in real time.
Step S300: dividing a production workshop of the target semiconductor into a plurality of production areas, wherein each production area corresponds to one production node;
specifically, the semiconductor manufacturing process includes a plurality of manufacturing nodes, such as cleaning, photoresist homogenizing, photoresist removing, etching, developing, and the like, and manufacturing equipment and manufacturing areas used by different manufacturing nodes are different, and each manufacturing area corresponds to one process node, so that a plurality of manufacturing areas are obtained.
Step S400: carrying out related vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix to obtain a static related vector and a dynamic related vector;
specifically, the indexes contained in the static index matrix and the dynamic index matrix refer to various indexes which can affect the production process and the health of staff in the production process of a target semiconductor, including temperature, humidity, waste gas, particulate matters and the like, but the produced pollutants and the influence on the environment are different in different production nodes, for example, the particulate matters and dust generated by the nodes in the production of a semiconductor substrate, photoetching and the like are more, the waste gas generated by the chemical agent on the cleaning outer surface is more, the index parameters in the static index matrix and the dynamic index matrix corresponding to different production areas are updated and changed in real time, the concentration of the particulate matters and the concentration of the dust corresponding to the nodes in the production of the semiconductor substrate, photoetching and the like are more severely changed, the dynamic correlation vectors of the production areas are extracted, and similarly, indexes which are more severely changed in the production areas are respectively extracted from the static index matrix and the dynamic index matrix as the static correlation vectors and the dynamic correlation vectors of the production areas.
As shown in fig. 2, step S400 of the embodiment of the present invention further includes:
step S410: performing data monitoring on the semiconductor production process of each production area in the plurality of production areas to obtain a monitoring data set;
step S420: performing index identification according to the monitoring data set to obtain a monitoring index matrix;
step S430: extracting a change vector according to the monitoring index matrix to obtain a change vector;
step S440: and carrying out vector recognition on the workshop static environment index and the workshop dynamic environment index based on the change vector to obtain a static correlation vector and a dynamic correlation vector.
Specifically, the semiconductor production process of each production area in the plurality of production areas is subjected to data monitoring to obtain a monitoring data set, the monitoring data set comprises change data of workshop static environment indexes and workshop dynamic environment indexes in the semiconductor production process of each production area, such as environment temperature change data, humidity change data, dust concentration change data and the like of each production area, data types in the monitoring data set are further obtained for index identification, namely, the data types contained in the monitoring data set are analyzed to obtain a plurality of data types, such as temperature, humidity, dust concentration and the like, the monitoring data set is orderly arranged according to the data types, a multi-dimensional data square matrix is obtained as a monitoring index matrix, and each production area corresponds to one monitoring index matrix. Further, according to the monitoring index matrix, different types of monitoring data of each production area are analyzed, a plurality of types of data with larger variation degrees are screened out, the data with larger variation degrees are extracted into variation vectors, parameters with larger variation degrees are used as the variation vectors, for example, the dust concentration in a certain production area is changed greatly, the dust concentration is used as the variation vector, and the variation vector of one production area can be one or more. And carrying out vector recognition on the workshop static environment index and the workshop dynamic environment index based on the change vector, taking the environment index matched with the change vector in the workshop static environment index as a static correlation vector, and taking the index matched with the change vector in the workshop dynamic environment index as a dynamic correlation vector. By analyzing the change vectors of different production areas, the technical effects of providing data support for subsequent management and parameter adjustment and improving the cleanliness of the semiconductor production environment are achieved.
Step S500: performing management parameter adjustment on the static correlation vector and the dynamic correlation vector, and outputting parameter adjustment results, wherein the parameter adjustment results are parameter adjustment results of management grades;
specifically, the static correlation vector and the dynamic correlation vector are managed and the parameter adjusting result is output, the parameter adjusting result refers to adjustment of the cleaning force of the cleaning device in each production area, for example, the equipment for adjusting the environmental indexes such as the temperature adjusting device and the humidity adjusting device is adjusted according to the static correlation vector, so that the environmental temperature and the humidity are in a normal range; the dust removing device, the cleaning device and the like in each production area are regulated through dynamic correlation vectors, that is, one production area may have a plurality of parameter regulating results, each parameter regulating result corresponds to one index, for example, the temperature and the dust concentration are regulated, wherein the parameter regulating results are parameter regulating results of the management grades, that is, the influences on the environment temperature and humidity and the quantity of generated dust, particles and waste gas in the production process of different production areas corresponding to different production nodes are different, based on the dynamic correlation vectors, the production areas are classified according to the requirement of a production workshop on the air cleanliness, the larger the influence on the environment temperature and humidity is, the higher the quantity of generated dust, particles and waste gas is, the different management grades are, the corresponding parameter regulating results are different, the higher the management grades are, the regulating forces on the temperature regulating device, the humidity regulating device, the dust removing device, the cleaning device and the like are larger, and the power in the working process of the devices is also larger, so that the temperature, the dust concentration and the like in each production area are located in the standard range.
Step S600: and outputting the cleaning management index matrixes respectively corresponding to the production areas according to the parameter adjustment result.
Specifically, the control adjustment is performed on the devices for purifying and adjusting air in the production areas in the production workshop according to the parameter adjusting results, the parameter adjusting results of the production areas are different, the clean management index matrixes corresponding to the production areas are constructed according to the types of the parameter adjusting results corresponding to the production areas, and the parameter adjusting results of one production area comprise temperature and dust concentration adjustment, so that the clean management index matrixes corresponding to the production areas are formed according to the temperature and the dust concentration, the clean management of the production areas is convenient to directly follow, and the management efficiency is improved.
As shown in fig. 3, step S700 of the embodiment of the present invention further includes:
step S710: generating a static correlation matrix and a dynamic correlation matrix by using the static correlation vector and the dynamic correlation vector;
each production area comprises a group of static correlation matrixes and a group of dynamic correlation matrixes, wherein the static correlation matrixes are subsets of the static index matrixes, and the dynamic correlation matrixes are subsets of the dynamic index matrixes;
step S720: and identifying based on the static correlation matrix and the dynamic correlation matrix, outputting parameter adjusting coefficients, and managing and adjusting parameters of each production area based on the parameter adjusting coefficients.
The step S720 of the embodiment of the present invention further includes:
step S721: n vectors which are larger than or equal to a preset correlation degree in the static correlation matrix are obtained, wherein N is a positive integer larger than 0;
step S722: obtaining M vectors which are larger than or equal to a preset correlation degree in the dynamic correlation matrix, wherein M is a positive integer larger than 0;
step S723: and calculating based on the N vectors and the M vectors, and outputting the parameter adjusting coefficient.
Specifically, each production area may have a plurality of static correlation vectors and a plurality of dynamic correlation vectors, the static correlation matrices are obtained by orderly arranging the index types of the plurality of static correlation vectors, the dynamic correlation matrices are obtained by orderly arranging the index types of the dynamic correlation vectors, each production area includes a group of static correlation matrices and a group of dynamic correlation matrices, in short, the static correlation matrices and the dynamic correlation matrices corresponding to each production area are indexes with larger part of variation degrees extracted from the static index matrices and the dynamic index matrices, so the static correlation matrices are subsets of the static index matrices, and the dynamic correlation matrices are subsets of the dynamic index matrices. And identifying based on the static correlation matrix and the dynamic correlation matrix, outputting parameter adjusting coefficients, and managing parameter adjusting for each production area based on the parameter adjusting coefficients.
The process of outputting the parameter adjusting coefficient is as follows: the method comprises the steps of obtaining N vectors with the correlation degree larger than or equal to a preset value in a static correlation matrix, wherein N is a positive integer larger than 0, in short, the static correlation matrix comprises a plurality of index parameters related to a semiconductor production environment, such as temperature, humidity and the like, production processes corresponding to different production areas are different, influences on the environment temperature, the humidity and the like are different, for example, the production process carried out in a certain production area can lead to larger temperature rising amplitude, but the influence on the humidity is smaller, the correlation degree of the temperature index vectors is larger, the correlation degree of the humidity index vectors is smaller, the preset correlation degree is reference data for screening a plurality of vectors in the static correlation matrix, the correlation degree of the vectors in the static correlation matrix is set by a worker according to actual conditions, and N vectors with the correlation degree larger than or equal to the preset correlation degree in the static correlation matrix are obtained, wherein N is a positive integer larger than 0. Similarly, the dynamic correlation matrix also includes a plurality of dynamic index parameters related to the semiconductor production environment, such as exhaust gas concentration, dust concentration, etc., corresponding production processes of different production areas are different, the generated exhaust gas and dust are different, for example, a large amount of exhaust gas can be generated by a production process performed in a certain production area, so that the correlation degree of the exhaust gas concentration vector of the production area is large, based on the correlation degree, M vectors with the correlation degree greater than or equal to a preset degree in the dynamic correlation matrix are obtained, wherein M is a positive integer greater than 0, calculation is performed based on the N vectors and the M vectors, parameter adjustment coefficients are output, the larger the variation amplitude of the static index vector and the dynamic index vector is, for example, the larger the influence on the environment temperature and humidity is, and the larger the corresponding parameter adjustment coefficient is.
The calculation formula of the parameter adjusting coefficient is as follows:
wherein ,in this embodiment, the parameter adjustment level of the air adjustment device in each production area is indicated to be higher, which indicates that the higher the parameter adjustment level is, the larger the adjustment range is, that is, the more air pollutants are generated in the production area; n represents the vector number greater than or equal to the preset correlation degree in the static correlation matrix, N is a positive integer greater than 0, the static correlation matrix comprises a plurality of static index vectors such as temperature, humidity and the like, and N static vectors with larger variation degree are screened out from the static index vectors; m represents the vector number greater than or equal to the preset correlation degree in the dynamic correlation matrix, M is a positive integer greater than 0, the dynamic correlation matrix comprises a plurality of dynamic index vectors such as waste gas concentration, dust concentration and the like, and M dynamic index vectors with larger variation degree are screened out from the dynamic correlation matrix, namely, the static correlation matrix and the dynamic correlation matrix both comprise a plurality of index vectors, the variation degree of different index vectors is different, the influence of the index with smaller variation degree (smaller correlation degree) on the parameter adjustment level is smaller and can be ignored, so that the number of index vectors with larger variation degree is screened out, parameter adjustment coefficient calculation is carried out, and the data operation amount is reduced while the adjustment precision is ensured; />The mean value coefficient reflects the variation degree of the M vectors, specifically, the M vectors are averaged firstly, then difference values between the M vectors and the average value are calculated through decomposition, and then the M difference values are averaged again and used as the mean value coefficient; />Characterizing a static correlation matrix;the dynamic correlation matrix is characterized. The parameter adjustment coefficient calculation formula is used for analyzing the static correlation matrix and the change degree of the static vector and the dynamic vector in the dynamic correlation matrix of each production area to obtain the parameter adjustment coefficient used for representing the parameter adjustment level, and the larger the parameter adjustment coefficient is, the larger the adjustment amplitude of the control parameter of the device is, the corresponding parameter adjustment coefficient of one production area is, and the parameter adjustment coefficients of different production areas can be different.
The step S800 of the embodiment of the present invention further includes:
step S810: acquiring static correlation vectors and dynamic correlation vectors respectively corresponding to each production area in the plurality of production areas;
step S820: carrying out similarity recognition on the static correlation vector and the dynamic correlation vector which correspond to each production area in the plurality of production areas respectively to obtain an area variable similarity index, wherein the area variable similarity index is used for the similarity degree of variables between every two areas;
step S830: and setting the same management level for the two areas with the area variable similarity indexes in the preset interval.
In the foregoing step, the parameter adjustment result is a parameter adjustment result of a management level, and the setting process of the management level is as follows: firstly, static correlation vectors and dynamic correlation vectors corresponding to each production area in a plurality of production areas are obtained, similarity identification is further carried out on the static correlation vectors and the dynamic correlation vectors corresponding to each production area in the plurality of production areas, and an area variable similarity index is obtained, wherein the area variable similarity index is used for the similarity degree of variables between every two areas, and then the same management level is set for the two areas of which the area variable similarity index is in a preset interval, wherein the preset interval is an interval of similarity self-setting by a worker, that is, the static correlation vectors and the dynamic correlation vectors of the two production areas are difficult to achieve the same, if dust concentration, waste gas concentration and the like generated by the two production areas are relatively close, the corresponding parameter adjustment results are relatively similar, management parameter adjustment analysis can be carried out on one production area only in the later period, and one management parameter adjustment result is used for cleanly managing two or more production areas of the same management level, so that data operation quantity is reduced, and management efficiency is improved.
Performing similarity recognition on a static correlation vector and a dynamic correlation vector corresponding to each production area in the plurality of production areas, to obtain a similarity coefficient of the static correlation vector and a similarity coefficient of the dynamic correlation vector, wherein each similarity coefficient comprises: and training a similarity recognition model according to the quantity index of the change vector and the change index amplitude of the change vector to obtain the regional variable similarity index.
In popular terms, the similarity recognition is to judge the similarity of the influence degree of multiple production areas on the environment, the change vector is changed in real time, the similarity analysis needs to analyze the real-time change condition, the number index of the change vector refers to the numerical value of a static vector or a dynamic vector when the semiconductor is produced, the static vector and the dynamic vector are both updated in real time, the change index amplitude is the difference value of the numerical value caused by data acquisition of the static vector and the dynamic vector after each data update, for example, the dust concentration in a certain production area is 5mg/m3 per cubic meter at a certain moment, the data update becomes 8mg/m3, and the change index amplitude is 2mg/m3. When the similarity recognition is carried out on the two areas, the quantity index of the change vector and the change index amplitude of the change vector are respectively carried out on each static vector and each dynamic vector, and the similarity recognition is carried out according to the quantity index of the change vector and the change index amplitude of the change vector, namely, the overall similarity is higher only when the quantity index of the change vector corresponding to the two production areas and the similarity of the change index amplitude of the change vector are higher, and the area variable similarity index is determined by the two indexes.
The similarity recognition is performed through a similarity recognition model, that is, when the static correlation vector and the dynamic correlation vector corresponding to each production area in the plurality of production areas are subjected to similarity recognition, the static correlation vector and the dynamic correlation vector are analyzed to obtain the number index of the change vector and the change index amplitude of the change vector, and the number index of the change vector and the change index amplitude of the change vector of each production area are compared and analyzed to obtain a comprehensive similarity coefficient as an area variable similarity index. The similarity recognition model is a neural network model in machine learning, and the difference value between the quantity index and the change index amplitude of any two production areas is obtained by comparing and recognizing the quantity index of the change vectors and the change index amplitude of the change vectors of a plurality of production areas, and the smaller the two difference values are, the larger the area variable similarity index is. Specifically, a plurality of groups of sample number indexes and sample change index amplitudes are obtained, differential analysis is carried out on the plurality of groups of sample number indexes and sample change index amplitudes, sample similarity analysis results among the plurality of groups of data are obtained, the plurality of groups of sample number indexes, the sample change index amplitudes and the sample similarity analysis results are used as training data, a similarity analysis model is trained, so that output data of the similarity analysis model are consistent with the sample similarity analysis results, accuracy of the model is tested, a similarity analysis model meeting requirements is obtained, similarity recognition is carried out on static correlation vectors and dynamic correlation vectors corresponding to each production area in the plurality of production areas in the embodiment, an area variable similarity index is obtained, cleaning management is carried out on the production areas of the same level according to the area variable similarity index, and management efficiency is improved.
Based on the analysis, the invention provides a method for monitoring and cleaning and managing a semiconductor production environment, in the embodiment, the workshop environment of a production target semiconductor is analyzed to obtain a static index matrix and a dynamic index matrix, a production workshop of the target semiconductor is further divided into a plurality of production areas according to production nodes, the static index matrix and the dynamic index matrix are subjected to correlation vector identification to obtain a static correlation vector and a dynamic correlation vector, the static correlation vector and the dynamic correlation vector are managed and a parameter adjustment result is output, the parameter adjustment result is a parameter adjustment result of a management level, the clean management index matrix corresponding to each production area is output according to the parameter adjustment result, and independent parameter adjustment of different production nodes and different production areas is realized, so that the technical effects of improving the cleaning and management accuracy and the management efficiency are achieved.
Example two
Based on the same inventive concept as the method for monitoring and cleaning and managing a semiconductor production environment in the foregoing embodiment, as shown in fig. 4, the present invention further provides a system for monitoring and cleaning and managing a semiconductor production environment, the system comprising:
the environment index acquisition module 11 is used for acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index of which the parameter change is close to static in the workshop production process, and the workshop dynamic environment index is an index of which the parameter change is dynamic in the workshop production process;
the index matrix generation module 12 is configured to generate a matrix according to the plant static environment index and the plant dynamic environment index, so as to obtain a static index matrix and a dynamic index matrix;
a workshop area dividing module 13, where the workshop area dividing module 13 is configured to obtain a plurality of production areas by dividing areas of a production workshop of the target semiconductor, where each production area corresponds to one production node;
the correlation vector identification module 14 is configured to obtain a static correlation vector and a dynamic correlation vector by performing correlation vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix;
the management parameter adjusting module 15 is used for performing management parameter adjustment on the static correlation vector and the dynamic correlation vector, and outputting parameter adjustment results, wherein the parameter adjustment results are parameter adjustment results of management grades;
and the clean management index matrix output module 16 is used for outputting the clean management index matrix corresponding to the production areas according to the parameter adjustment result by the clean management index matrix output module 16.
Further, the system further comprises:
the data monitoring module is used for monitoring the data of the semiconductor production process of each production area in the plurality of production areas to obtain a monitoring data set;
the index identification module is used for carrying out index identification according to the monitoring data set to obtain a monitoring index matrix;
the change vector extraction module is used for extracting a change vector according to the monitoring index matrix to obtain a change vector;
and the correlation vector acquisition module is used for carrying out vector identification on the workshop static environment index and the workshop dynamic environment index based on the change vector to obtain a static correlation vector and a dynamic correlation vector.
Further, the system further comprises:
the correlation matrix generation module is used for generating a static correlation matrix and a dynamic correlation matrix by the static correlation vector and the dynamic correlation vector;
each production area comprises a group of static correlation matrixes and a group of dynamic correlation matrixes, wherein the static correlation matrixes are subsets of the static index matrixes, and the dynamic correlation matrixes are subsets of the dynamic index matrixes;
and the parameter adjustment coefficient output module is used for identifying based on the static correlation matrix and the dynamic correlation matrix, outputting parameter adjustment coefficients, and managing parameter adjustment for each production area based on the parameter adjustment coefficients.
Further, the system further comprises:
the static vector extraction module is used for acquiring N vectors with the correlation degree larger than or equal to a preset value in the static correlation matrix, wherein N is a positive integer larger than 0;
the dynamic vector extraction module is used for obtaining M vectors with the correlation degree larger than or equal to a preset value in the dynamic correlation matrix, wherein M is a positive integer larger than 0;
and the vector calculation module is used for calculating based on the N vectors and the M vectors and outputting the parameter adjusting coefficient.
The parameter adjusting coefficient has the following calculation formula:
wherein ,the parameter adjustment coefficient is marked; n represents the vector number which is larger than or equal to a preset correlation degree in the static correlation matrix; m represents the vector number which is larger than or equal to a preset correlation degree in the dynamic correlation matrix; />As the mean coefficients of the M vectors,characterizing a static correlation matrix; />The dynamic correlation matrix is characterized.
Further, the system further comprises:
the regional correlation vector acquisition module is used for acquiring static correlation vectors and dynamic correlation vectors corresponding to each production region in the plurality of production regions respectively;
the similarity recognition module is used for performing similarity recognition on static correlation vectors and dynamic correlation vectors corresponding to each production area in the plurality of production areas respectively to obtain area variable similarity indexes, wherein the area variable similarity indexes are used for the similarity degree of variables between every two areas;
and the management level setting module is used for setting the same management level for the two areas with the area variable similarity indexes in the preset interval.
Further, performing similarity recognition on a static correlation vector and a dynamic correlation vector corresponding to each production area in the plurality of production areas to obtain a similarity coefficient of the static correlation vector and a similarity coefficient of the dynamic correlation vector, where each similarity coefficient includes:
and training a similarity recognition model according to the quantity index of the change vector and the change index amplitude of the change vector to obtain the regional variable similarity index.
The specific example of the method for monitoring and cleaning management of a semiconductor production environment in the first embodiment is also applicable to the system for monitoring and cleaning management of a semiconductor production environment in the present embodiment, and by the foregoing detailed description of the method for monitoring and cleaning management of a semiconductor production environment, those skilled in the art can clearly know the system for monitoring and cleaning management of a semiconductor production environment in the present embodiment, so that the details thereof will not be described herein for brevity.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (5)
1. A method for monitoring, cleaning and managing a semiconductor manufacturing environment, the method comprising:
acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index that parameter change is close to static in a workshop production process, and the workshop dynamic environment index is an index that parameter change is dynamic in the workshop production process;
generating a matrix according to the workshop static environment index and the workshop dynamic environment index to obtain a static index matrix and a dynamic index matrix;
dividing a production workshop of the target semiconductor into a plurality of production areas, wherein each production area corresponds to one production node;
carrying out related vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix to obtain a static related vector and a dynamic related vector;
performing management parameter adjustment on the static correlation vector and the dynamic correlation vector, and outputting parameter adjustment results, wherein the parameter adjustment results are parameter adjustment results of management grades;
outputting a clean management index matrix corresponding to each of the plurality of production areas according to the parameter adjustment result;
wherein, manage and call parameters to the static correlation vector and the dynamic correlation vector, including:
generating a static correlation matrix and a dynamic correlation matrix by using the static correlation vector and the dynamic correlation vector;
each production area comprises a group of static correlation matrixes and a group of dynamic correlation matrixes, wherein the static correlation matrixes are subsets of the static index matrixes, and the dynamic correlation matrixes are subsets of the dynamic index matrixes;
identifying based on the static correlation matrix and the dynamic correlation matrix, outputting parameter adjustment coefficients, and managing parameter adjustment for each production area based on the parameter adjustment coefficients;
wherein, based on the static correlation matrix and the dynamic correlation matrix, identifying, outputting parameter adjustment coefficients, including:
n vectors which are larger than or equal to a preset correlation degree in the static correlation matrix are obtained, wherein N is a positive integer larger than 0;
obtaining M vectors which are larger than or equal to a preset correlation degree in the dynamic correlation matrix, wherein M is a positive integer larger than 0;
calculating based on the N vectors and the M vectors, and outputting the parameter adjusting coefficient;
the parameter adjusting coefficient has the following calculation formula:
；
wherein ,the parameter adjustment coefficient is marked; n represents the vector number which is larger than or equal to a preset correlation degree in the static correlation matrix; m represents the vector number which is larger than or equal to a preset correlation degree in the dynamic correlation matrix; />As the mean coefficients of the M vectors,characterizing a static correlation matrix; />The dynamic correlation matrix is characterized.
2. The method of claim 1, wherein the method further comprises:
performing data monitoring on the semiconductor production process of each production area in the plurality of production areas to obtain a monitoring data set;
performing index identification according to the monitoring data set to obtain a monitoring index matrix;
extracting a change vector according to the monitoring index matrix to obtain a change vector;
and carrying out vector recognition on the workshop static environment index and the workshop dynamic environment index based on the change vector to obtain a static correlation vector and a dynamic correlation vector.
3. The method of claim 2, wherein after the extracting the change vector according to the monitoring index matrix, the method further comprises:
acquiring static correlation vectors and dynamic correlation vectors respectively corresponding to each production area in the plurality of production areas;
carrying out similarity recognition on the static correlation vector and the dynamic correlation vector which correspond to each production area in the plurality of production areas respectively to obtain an area variable similarity index, wherein the area variable similarity index is used for the similarity degree of variables between every two areas;
and setting the same management level for the two areas with the area variable similarity indexes in the preset interval.
4. The method of claim 3, wherein similarity recognition is performed on a static correlation vector and a dynamic correlation vector corresponding to each production area of the plurality of production areas, respectively, to obtain a similarity coefficient of the static correlation vector and a similarity coefficient of the dynamic correlation vector, each similarity coefficient comprising:
and training a similarity recognition model according to the quantity index of the change vector and the change index amplitude of the change vector to obtain the regional variable similarity index.
5. A system for monitoring, cleaning and managing a semiconductor manufacturing environment, the system comprising:
the environment index acquisition module is used for acquiring a workshop static environment index and a workshop dynamic environment index of a production target semiconductor, wherein the workshop static environment index is an index of which the parameter change is close to static in the workshop production process, and the workshop dynamic environment index is an index of which the parameter change is dynamic in the workshop production process;
the index matrix generation module is used for generating a matrix according to the workshop static environment index and the workshop dynamic environment index to obtain a static index matrix and a dynamic index matrix;
the workshop area dividing module is used for dividing areas of the production workshops of the target semiconductor to obtain a plurality of production areas, wherein each production area corresponds to one production node;
the correlation vector identification module is used for obtaining a static correlation vector and a dynamic correlation vector by carrying out correlation vector identification on the plurality of production areas, the static index matrix and the dynamic index matrix;
the management parameter adjusting module is used for carrying out management parameter adjustment on the static correlation vector and the dynamic correlation vector and outputting parameter adjusting results, wherein the parameter adjusting results are parameter adjusting results of management grades;
the clean management index matrix output module is used for outputting clean management index matrixes corresponding to the production areas respectively according to the parameter adjustment results;
the correlation matrix generation module is used for generating a static correlation matrix and a dynamic correlation matrix by the static correlation vector and the dynamic correlation vector;
each production area comprises a group of static correlation matrixes and a group of dynamic correlation matrixes, wherein the static correlation matrixes are subsets of the static index matrixes, and the dynamic correlation matrixes are subsets of the dynamic index matrixes;
the parameter adjustment coefficient output module is used for identifying based on the static correlation matrix and the dynamic correlation matrix, outputting parameter adjustment coefficients, and managing parameter adjustment for each production area based on the parameter adjustment coefficients;
the static vector extraction module is used for acquiring N vectors with the correlation degree larger than or equal to a preset value in the static correlation matrix, wherein N is a positive integer larger than 0;
the dynamic vector extraction module is used for obtaining M vectors with the correlation degree larger than or equal to a preset value in the dynamic correlation matrix, wherein M is a positive integer larger than 0;
the vector calculation module is used for calculating based on the N vectors and the M vectors and outputting the parameter adjusting coefficient;
the parameter adjusting coefficient has the following calculation formula:
；
wherein ,the parameter adjustment coefficient is marked; n represents the vector number which is larger than or equal to a preset correlation degree in the static correlation matrix; m represents the vector number which is larger than or equal to a preset correlation degree in the dynamic correlation matrix; />As the mean coefficients of the M vectors,characterizing a static correlation matrix; />The dynamic correlation matrix is characterized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310691683.9A CN116433109B (en) | 2023-06-13 | 2023-06-13 | Method and system for monitoring, cleaning and managing semiconductor production environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310691683.9A CN116433109B (en) | 2023-06-13 | 2023-06-13 | Method and system for monitoring, cleaning and managing semiconductor production environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116433109A CN116433109A (en) | 2023-07-14 |
| CN116433109B true CN116433109B (en) | 2023-09-08 |
Family
ID=87087593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310691683.9A Active CN116433109B (en) | 2023-06-13 | 2023-06-13 | Method and system for monitoring, cleaning and managing semiconductor production environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116433109B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201732021U (en) * | 2010-05-21 | 2011-02-02 | 中芯国际集成电路制造(上海)有限公司 | Sampling device for evaluating production environment of semiconductor device |
| CN113127552A (en) * | 2021-04-26 | 2021-07-16 | 南京市产品质量监督检验院 | Food safety identification method and system based on big data |
| CN115309217A (en) * | 2022-10-12 | 2022-11-08 | 北京聚新工程技术有限公司 | Intelligent monitoring control method and system for textile workshop |
| CN115332101A (en) * | 2022-08-12 | 2022-11-11 | 长鑫存储技术有限公司 | Method and system for monitoring semiconductor processing environment |
| CN115688053A (en) * | 2022-12-30 | 2023-02-03 | 速度时空信息科技股份有限公司 | Mine environment dynamic monitoring management method and system based on data fusion |
| CN116165988A (en) * | 2023-04-24 | 2023-05-26 | 格拉默汽车内饰部件（北京）有限公司 | Production quality control method and system for automobile center console |
-
2023
- 2023-06-13 CN CN202310691683.9A patent/CN116433109B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201732021U (en) * | 2010-05-21 | 2011-02-02 | 中芯国际集成电路制造(上海)有限公司 | Sampling device for evaluating production environment of semiconductor device |
| CN113127552A (en) * | 2021-04-26 | 2021-07-16 | 南京市产品质量监督检验院 | Food safety identification method and system based on big data |
| CN115332101A (en) * | 2022-08-12 | 2022-11-11 | 长鑫存储技术有限公司 | Method and system for monitoring semiconductor processing environment |
| CN115309217A (en) * | 2022-10-12 | 2022-11-08 | 北京聚新工程技术有限公司 | Intelligent monitoring control method and system for textile workshop |
| CN115688053A (en) * | 2022-12-30 | 2023-02-03 | 速度时空信息科技股份有限公司 | Mine environment dynamic monitoring management method and system based on data fusion |
| CN116165988A (en) * | 2023-04-24 | 2023-05-26 | 格拉默汽车内饰部件（北京）有限公司 | Production quality control method and system for automobile center console |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116433109A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Spanos | Statistical process control in semiconductor manufacturing | |
| CN105335752A (en) | Principal component analysis multivariable decision-making tree-based connection manner identification method | |
| JP2000517473A (en) | System for monitoring and analyzing manufacturing processes using statistical simulation with single-step feedback | |
| CN111256965A (en) | Multi-scale information fusion stacked sparse self-coding rotary machine fault diagnosis method | |
| CN110782546A (en) | Resistivity virtual measurement method of semiconductor PVD (physical vapor deposition) process based on combined tree model | |
| CN116599857B (en) | Digital twin application system suitable for multiple scenes of Internet of things | |
| CN117034179A (en) | Abnormal electric quantity identification and tracing method and system based on graph neural network | |
| CN116433109B (en) | Method and system for monitoring, cleaning and managing semiconductor production environment | |
| CN114357870A (en) | Metering equipment operation performance prediction analysis method based on local weighted partial least squares | |
| Butte et al. | Big data and predictive analytics methods for modeling and analysis of semiconductor manufacturing processes | |
| CN113657023A (en) | Near-surface ozone concentration inversion method based on combination of machine learning and deep learning | |
| CN116384843B (en) | Energy efficiency evaluation model training method and monitoring method for digital energy nitrogen station | |
| CN112817954A (en) | Missing value interpolation method based on multi-method ensemble learning | |
| CN107093904B (en) | Power distribution network reactive compensation action point selection method based on random matrix spectrum analysis | |
| CN115860056B (en) | Sensor array neural network method for mixed gas concentration prediction | |
| CN109214268B (en) | Packed tower flooding state online monitoring method based on integrated manifold learning | |
| CN116307844A (en) | Low-voltage transformer area line loss evaluation analysis method | |
| CN112986497B (en) | Pollution gas tracing method based on gas sensor array fingerprint identification | |
| Piplani et al. | Simplification strategies for simulation models of semiconductor facilities | |
| Sim | Hierarchical factor analysis methodology for Intelligent manufacturing | |
| CN109376337B (en) | Distributed soft measurement method based on Girvan-Newman algorithm | |
| TWI230349B (en) | Method and apparatus for analyzing manufacturing data | |
| CN117474298B (en) | Engine connecting rod production management method and system based on upstream and downstream station feedback | |
| CN112200219B (en) | Feature extraction method for defect data of ultra-large-scale wafer | |
| Galimyanov et al. | Testing of streaming data clustering algorithm effectiveness |
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 |