CN115600769A - Semiconductor equipment management optimization method and system based on semiconductor industry chain - Google Patents
Semiconductor equipment management optimization method and system based on semiconductor industry chain Download PDFInfo
- Publication number
- CN115600769A CN115600769A CN202211517054.6A CN202211517054A CN115600769A CN 115600769 A CN115600769 A CN 115600769A CN 202211517054 A CN202211517054 A CN 202211517054A CN 115600769 A CN115600769 A CN 115600769A
- Authority
- CN
- China
- Prior art keywords
- adjustment
- time
- measure
- rate
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- H01L21/67276—Production flow monitoring, e.g. for increasing throughput
-
- 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
Abstract
The invention discloses a semiconductor equipment management optimization method and system based on a semiconductor industry chain, and relates to the field of data processing, wherein the method comprises the following steps: according to the equipment production information set, obtaining a real-time first starting rate, a real-time second starting rate and a product percent of pass, and calculating according to the real-time first starting rate, the real-time second starting rate and the product percent of pass to obtain comprehensive production efficiency; judging whether the comprehensive production efficiency meets the preset requirement or not; if yes, continuing production; if not, obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set based on the equipment management database, optimizing according to the optimizing optimization rule, obtaining and optimizing the first adjusting measure, optimizing the second adjusting measure and optimizing the third adjusting measure, and managing and optimizing the wafer production equipment. The invention solves the technical problem of poor management effect on the wafer production equipment of the semiconductor industry chain in the prior art. The technical effects of improving the management quality of the wafer production equipment and the like are achieved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a semiconductor equipment management optimization method and system based on a semiconductor industry chain.
Background
With the continuous progress of science and technology, the semiconductor industry chain develops towards automation, maturation and intellectualization, higher-level requirements are provided for the management of semiconductor equipment, and the optimization of the management of the semiconductor equipment is concerned widely. Wafer production is an important link of a semiconductor industry chain, wafer production equipment is one of important semiconductor equipment, and management optimization of the wafer production equipment has very important practical significance for management optimization of the semiconductor equipment.
In the prior art, the technical problems of low management comprehensiveness and insufficient accuracy of wafer production equipment aiming at a semiconductor industrial chain and poor management effect of the wafer production equipment are solved.
Disclosure of Invention
The application provides a semiconductor equipment management optimization method and system based on a semiconductor industry chain. The technical problems that in the prior art, the management comprehensiveness of the wafer production equipment of a semiconductor industry chain is not high, the accuracy is not enough, and the management effect of the wafer production equipment is poor are solved.
In view of the above problems, the present application provides a semiconductor device management optimization method and system based on a semiconductor industry chain.
In a first aspect, the present application provides a semiconductor device management optimization method based on a semiconductor industry chain, where the method is applied to a semiconductor device management optimization system based on a semiconductor industry chain, and the method includes: acquiring production information of a plurality of current production information indexes of wafer production equipment to obtain an equipment production information set, wherein the wafer production equipment is included in a semiconductor production industrial chain; calculating to obtain the current real-time first starting rate, the real-time second starting rate and the product percent of pass of the wafer production equipment according to the equipment production information set, and calculating to obtain the comprehensive production efficiency of the wafer production equipment according to the real-time first starting rate, the real-time second starting rate and the product percent of pass; judging whether the comprehensive production efficiency meets a preset requirement or not; if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range, wherein the equipment management database is constructed and obtained based on the production information of the wafer production equipment in the historical time; matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database; and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment.
In a second aspect, the present application further provides a semiconductor device management optimization system based on a semiconductor industry chain, wherein the system includes: the production information acquisition module is used for acquiring the production information of a plurality of current production information indexes of wafer production equipment to obtain an equipment production information set, wherein the wafer production equipment is included in a semiconductor production industrial chain; the calculation module is used for calculating and obtaining the current real-time first starting rate, the real-time second starting rate and the product qualified rate of the wafer production equipment according to the equipment production information set, and calculating and obtaining the comprehensive production efficiency of the wafer production equipment according to the real-time first starting rate, the real-time second starting rate and the product qualified rate; the judging module is used for judging whether the comprehensive production efficiency meets a preset requirement; a judgment result execution module, configured to continue production if the judgment result execution module is yes, and input the real-time first start rate, the real-time second start rate and the product qualification rate into a pre-constructed device management database for data matching if the judgment result execution module is not so as to obtain a first start rate range, a second start rate range and a product qualification rate range, where the device management database is constructed and obtained based on production information in the wafer production device historical time; the adjustment measure matching module is used for matching to obtain a first adjustment measure set, a second adjustment measure set and a third adjustment measure set according to the first starting rate range, the second starting rate range and the product qualified rate range in the equipment management database; and the management optimization module is used for constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the method comprises the steps of acquiring the production information of a plurality of current production information indexes of the wafer production equipment to obtain an equipment production information set, calculating the current real-time first starting rate, the real-time second starting rate and the product percent of pass of the wafer production equipment according to the current real-time first starting rate and the current real-time second starting rate; calculating and obtaining the comprehensive production efficiency of the wafer production equipment based on the obtained real-time first starting rate, the real-time second starting rate and the product percent of pass; judging whether the comprehensive production efficiency meets the preset requirement or not; if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range; matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database; and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment. The comprehensiveness, the accuracy and the adaptability of the management of the wafer production equipment are improved, the intelligent and scientific management optimization of the wafer production equipment is realized, and the management quality of the wafer production equipment is improved; powerful guarantee is provided for the normal operation of the wafer production equipment; the technical effect of improving the integrity of the management optimization of the semiconductor equipment is achieved.
Drawings
FIG. 1 is a schematic flow chart illustrating a semiconductor device management optimization method based on the semiconductor industry chain according to the present application;
FIG. 2 is a schematic flow chart illustrating a method for optimizing semiconductor device management based on semiconductor industry chain to obtain a device production information set according to the present application;
fig. 3 is a schematic structural diagram of a semiconductor device management optimization system based on a semiconductor industry chain according to the present application.
Description of the reference numerals: the system comprises a production information acquisition module 11, a calculation module 12, a judgment module 13, a judgment result execution module 14, an adjustment measure matching module 15 and a management optimization module 16.
Detailed Description
The application provides a semiconductor equipment management optimization method and system based on a semiconductor industry chain. The technical problems that in the prior art, the management comprehensiveness of the wafer production equipment of a semiconductor industry chain is not high, the accuracy is not enough, and the management effect of the wafer production equipment is poor are solved. The comprehensiveness, the accuracy and the adaptability of managing the wafer production equipment are improved, the intelligent and scientific management optimization of the wafer production equipment is realized, and the management quality of the wafer production equipment is improved; powerful guarantee is provided for the normal operation of wafer production equipment; the technical effect of improving the integrity of the management optimization of the semiconductor equipment is achieved.
Example one
Referring to fig. 1, an embodiment of the present application provides a semiconductor device management optimization method based on a semiconductor industry chain, where the method is applied to a semiconductor device management optimization system based on a semiconductor industry chain, and the method specifically includes the following steps:
step S100: acquiring production information of a plurality of current production information indexes of wafer production equipment to obtain an equipment production information set, wherein the wafer production equipment is included in a semiconductor production industrial chain;
further, as shown in fig. 2, step S100 of the present application further includes:
step S110: collecting the working time, the scheduled downtime, the fault downtime and the equipment initialization time of the wafer production equipment in the current preset time period;
step S120: collecting the wafer production capacity, the actual production period and the theoretical production period of the wafer production equipment within the current preset time period;
step S130: acquiring qualified wafer production capacity of the wafer production equipment within a current preset time period;
step S140: and obtaining the equipment production information set according to the working time, the planned downtime, the fault downtime, the equipment initialization time, the wafer production capacity, the actual production period, the theoretical production period and the qualified wafer production capacity.
Specifically, information collection is performed on the wafer production equipment according to a plurality of current production information indexes, and an equipment production information set is obtained. Namely, based on the current preset time period, the wafer production equipment is subjected to acquisition of working time, planned downtime, fault downtime, equipment initialization time, wafer production quantity, actual production period, theoretical production period and qualified wafer production quantity, and an equipment production information set is obtained. The wafer production equipment is any wafer manufacturing equipment which uses the semiconductor equipment management optimization system based on the semiconductor industry chain to carry out intelligent management optimization. The plurality of production information indicators include on-time, scheduled downtime, down time, equipment initialization time, wafer production, actual production cycle, theoretical production cycle, qualified wafer production. The current preset time period may be adaptively set and determined. For example, the current preset time period may be a preset time period of currently completing production, such as the previous 1 week, the previous 1 month, the previous half year, and the like. The equipment production information set comprises the working time, the scheduled downtime, the fault downtime, the equipment initialization time, the wafer production quantity, the actual production period, the theoretical production period and the qualified wafer production quantity of the wafer production equipment corresponding to the current preset time period. The technical effects that the wafer production equipment is subjected to information acquisition through the current preset time period and a plurality of production information indexes, a reliable equipment production information set is obtained, and a foundation is laid for the follow-up management optimization of the wafer production equipment are achieved.
Step S200: calculating to obtain the current real-time first starting rate, the real-time second starting rate and the product percent of pass of the wafer production equipment according to the equipment production information set, and calculating to obtain the comprehensive production efficiency of the wafer production equipment according to the real-time first starting rate, the real-time second starting rate and the product percent of pass;
further, step S200 of the present application further includes:
step S210: calculating the real-time first actuation rate according to the operating time, the scheduled downtime, the downtime for the fault, and the equipment initialization time, by the following formula:
wherein the content of the first and second substances,for the first start-up rate to be real-time,in order to be the working time, the working time is,in order to plan for the down-time,in order to provide for a period of down time,initializing time for the device;
step S220: calculating the real-time second actuation rate according to the wafer production volume, the actual production period and the theoretical production period, and according to the following formula:
wherein the content of the first and second substances,for the second start-up rate to be real-time,in order to have a net rate of actuation in real time,for real-time speed turn-on rate, S is wafer throughput,in order to realize the actual production cycle,a theoretical production cycle;
step S230: calculating to obtain the product qualified rate according to the wafer production capacity and the qualified wafer production capacity, and according to the following formula:
wherein the content of the first and second substances,the method is used for the qualified rate of the product,qualified wafer throughput;
step S240: calculating to obtain the comprehensive production efficiency according to the real-time first starting rate, the real-time second starting rate and the product percent of pass, and adopting the following formula:
wherein the content of the first and second substances,the comprehensive production efficiency is improved.
Specifically, the working time, the planned downtime, the fault downtime and the equipment initialization time are extracted from the obtained equipment production information set and are used as input information to be input into a real-time first starting rate calculation formulaAnd obtaining a real-time first starting rate. Calculating formula of first start rate in real timeIn (1),for the real-time first actuation rate of the output,in order to input the working time of the device,for the purpose of the input of the planned downtime,for the purpose of the incoming down time of the fault,time is initialized for the entered device.
Further, from the acquired equipment production information set, the working time, the scheduled downtime, the downtime for the failure, the equipment initialization time, the wafer production amount, the actual production period, and the theoretical production period are extracted and used as input information to be input into the real-time second start-up rate calculation formula set、、And obtaining a real-time second starting rate. In the set of real-time second actuation rate calculation formulas,for the real-time second actuation rate of the output,to calculate the net real-time opening rate obtained,for calculating the real-time speed turn-on rate obtained, S is the input wafer throughput,for the purpose of inputting the actual production cycle,for the input of the theoretical production cycle,for input ofThe working time is as long as the device is in operation,for the purpose of the input of the planned downtime,for the purpose of the incoming down time of the fault,time is initialized for the entered device.
Then, from the obtained equipment production information set, the acceptable wafer production amount and the wafer production amount are extracted and input as input information into a product yield calculation formulaAnd obtaining the product percent of pass. Formula for calculating product percent of passIn (1),in order to obtain the qualified rate of the output product,s is the input wafer throughput.
Further, the obtained real-time first starting rate, real-time second starting rate and product percent of pass are used as input information and input into a calculation formula of comprehensive production efficiencyAnd comprehensive production efficiency is obtained. Formula for calculating comprehensive production efficiencyIn (1),in order to achieve the comprehensive production efficiency of the output,for the input real-time first actuation rate,for the input real-time second actuation rate,the input product percent of pass.
The method achieves the technical effects of accurately and efficiently evaluating the production efficiency of the wafer production equipment and obtaining accurate and reliable comprehensive production efficiency by scientifically and hierarchically calculating the production information set of the equipment, thereby improving the adaptability and accuracy of managing and optimizing the wafer production equipment.
Step S300: judging whether the comprehensive production efficiency meets a preset requirement or not;
specifically, whether the comprehensive production efficiency meets the preset requirement is judged, and if the comprehensive production efficiency meets the preset requirement, the wafer production equipment is used for continuing production. Wherein the preset requirement comprises a preset comprehensive production efficiency threshold value. The technical effects of adaptively managing and optimizing the wafer production equipment based on comprehensive production efficiency and preset requirements and improving the rationality and scientificity of management and optimization of the wafer production equipment are achieved.
Step S400: if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range, wherein the equipment management database is constructed and obtained based on the production information of the wafer production equipment in the historical time;
further, step S400 of the present application further includes:
step S410: acquiring a first starting rate, a second starting rate and a product percent of pass of the wafer production equipment in a plurality of preset time periods within historical time to obtain a plurality of historical first starting rates, a plurality of historical second starting rates and a plurality of historical product percent of pass;
step S420: acquiring first adjustment measures, second adjustment measures and third adjustment measures for equipment management optimization of the wafer production equipment in a plurality of preset time periods within historical time to obtain a plurality of historical first adjustment measures, a plurality of historical second adjustment measures and a plurality of historical third adjustment measures;
step S430: respectively carrying out cluster analysis on the plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical qualified starting rates of products to obtain a plurality of first categories, a plurality of second categories and a plurality of third categories;
step S440: obtaining a plurality of historical first starting rate ranges, a plurality of historical second starting rate ranges and a plurality of historical product yield ranges according to the plurality of first categories, the plurality of second categories and the plurality of third categories, and obtaining a plurality of historical first adjusting measure sets, a plurality of historical second adjusting measure sets and a plurality of historical third adjusting measure sets;
specifically, when judging whether the comprehensive production efficiency meets the preset requirement, if the comprehensive production efficiency does not meet the preset requirement, acquiring a first start rate, a second start rate and a product percent of pass for wafer production equipment based on a plurality of preset time periods in historical time to obtain a plurality of historical first start rates, a plurality of historical second start rates and a plurality of historical product percent of pass; and acquiring a first adjusting measure, a second adjusting measure and a third adjusting measure for equipment management optimization of the wafer production equipment to obtain a plurality of historical first adjusting measures, a plurality of historical second adjusting measures and a plurality of historical third adjusting measures. And a plurality of preset time periods in the historical time can be determined in a self-defined mode, such as a plurality of previous months. The plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical product qualified rates comprise a plurality of first starting rates, a plurality of second starting rates and a plurality of product qualified rates of wafer production equipment corresponding to a plurality of preset time periods in historical time. The plurality of historical first adjustment measures includes a plurality of adjustment measures having an effect on a plurality of historical first start-up rates of the wafer production facility over a plurality of preset time periods within a historical time. The plurality of historical second adjustment actions includes a plurality of adjustment actions having an effect on a plurality of historical second start rates of the wafer production equipment over a plurality of preset time periods within the historical time. The plurality of historical third adjustment measures include a plurality of adjustment measures having an effect on a plurality of historical product yields of the wafer production facility over a plurality of preset time periods within a historical time. For example, the plurality of historical first adjustment measures include adjusting the operating time of the wafer production equipment, and the like. The plurality of historical second adjustment measures comprise adjusting the production speed, the production intensity, the production control parameters and the like of the wafer production equipment. The plurality of historical third adjustment measures include adjusting qualified wafer standards of the wafer production equipment, and the like.
And then, performing cluster analysis based on the plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical product qualified rates, namely classifying similar data information in the plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical product qualified rates into one class, and obtaining a plurality of first classes, a plurality of second classes and a plurality of third classes. Wherein the plurality of first categories are a plurality of historical first start rate categories, each first category including a similar plurality of historical first start rates. The plurality of second categories are a plurality of historical second start rate categories, each second category including a similar plurality of historical second start rates. The plurality of third categories are a plurality of historical product yield categories, each third category including a similar plurality of historical product yield drive rates. Illustratively, clustering analysis is carried out on a plurality of historical first starting rates, a plurality of historical second starting rates and a plurality of historical product yield rates by adopting a K-means clustering method.
Further, data range analysis is respectively carried out on the multiple first categories, the multiple second categories and the multiple third categories to obtain multiple historical first starting rate ranges, multiple historical second starting rate ranges and multiple historical product qualification rate ranges. Then, the plurality of historical first adjusting measures, the plurality of historical second adjusting measures and the plurality of historical third adjusting measures are correspondingly classified and matched based on the plurality of historical first starting rate ranges, the plurality of historical second starting rate ranges and the plurality of historical product yield ranges, and a plurality of historical first adjusting measure sets, a plurality of historical second adjusting measure sets and a plurality of historical third adjusting measure sets are obtained. Based on this, a device management database is obtained. The plurality of historical first starting rate ranges comprise data range information of a plurality of historical first starting rates corresponding to a plurality of first classes. The plurality of historical second actuation rate ranges includes data range information for a plurality of historical second actuation rates corresponding to a plurality of second categories. The plurality of historical product yield ranges include data range information for a plurality of historical product yield activation rates corresponding to a plurality of third categories. The plurality of sets of historical first adjustment measures includes a plurality of historical first adjustment measures corresponding to a plurality of historical first start rate ranges. The plurality of sets of historical second adjustment measures includes a plurality of historical second adjustment measures corresponding to a plurality of historical second start rate ranges. The plurality of historical third adjustment measure sets comprise a plurality of historical third adjustment measures corresponding to a plurality of historical product yield ranges.
The technical effect of acquiring the first starting rate, the second starting rate and the product qualification rate of the wafer production equipment in a plurality of preset time periods within the historical time and acquiring the first adjusting measure, the second adjusting measure and the third adjusting measure for optimizing equipment management of the wafer production equipment in a plurality of preset time periods within the historical time when the comprehensive production efficiency does not meet the preset requirement is achieved, and reliable data support is provided for subsequently constructing an equipment management database.
Step S450: constructing and obtaining the equipment management database;
further, step S450 of the present application further includes:
step S451: obtaining a plurality of first entity information, a plurality of second entity information and a plurality of third entity information based on a knowledge graph according to the plurality of first categories, the plurality of second categories and the plurality of third categories;
step S452: obtaining a first attribute, a second attribute, a third attribute, a plurality of first attribute values, a plurality of second attribute values and a plurality of third attribute values according to the plurality of historical first start rate ranges, the plurality of historical second start rate ranges and the plurality of historical product qualification rate ranges;
step S453: obtaining a fourth attribute, a fifth attribute, a sixth attribute, a plurality of fourth attribute values, a plurality of fifth attribute values and a plurality of sixth attribute values according to the plurality of historical first adjustment measure sets, the plurality of historical second adjustment measure sets and the plurality of historical third adjustment measure sets;
step S454: and constructing and acquiring the equipment management database based on the knowledge graph.
Specifically, a plurality of first categories, a plurality of second categories, and a plurality of third categories are set as a plurality of first entity information, a plurality of second entity information, and a plurality of third entity information, respectively, based on the knowledge graph. Further, based on a plurality of historical first start rate ranges, a plurality of historical second start rate ranges and a plurality of historical product qualification rate ranges, obtaining a first attribute, a second attribute, a third attribute, a plurality of first attribute values, a plurality of second attribute values and a plurality of third attribute values; and obtaining a fourth attribute, a fifth attribute, a sixth attribute, a plurality of fourth attribute values, a plurality of fifth attribute values and a plurality of sixth attribute values based on the plurality of historical first adjustment measure sets, the plurality of historical second adjustment measure sets and the plurality of historical third adjustment measure sets, and determining the equipment management database by combining the knowledge graph based on the fourth attribute, the fifth attribute, the sixth attribute, the plurality of fourth attribute values, the plurality of fifth attribute values and the plurality of sixth attribute values.
The knowledge graph comprises a mode layer and a data layer. The data layer consists of a series of facts; the mode layer is constructed on the data layer and is mainly used for carrying out canonical expression on a series of facts of the data layer. A knowledge graph can be viewed as a relational network that connects heterogeneous information together. The plurality of first entity information includes a plurality of first categories. The plurality of second entity information includes a plurality of second categories. The plurality of third entity information includes a plurality of third categories. The first attribute includes a historical first range of start rates. The plurality of first attribute values includes a plurality of historical first start rate ranges. The second attribute includes a historical second range of start rates. The plurality of second attribute values includes a plurality of historical second start rate ranges. The third attribute includes a historical product yield range. The plurality of third attribute values includes a plurality of historical product yield ranges. The fourth attribute includes a historical set of first adjustment measures. The plurality of fourth attribute values includes a plurality of sets of historical first adjustment measures. The fifth attribute includes a historical second set of adjustment measures. The plurality of fifth attribute values includes a plurality of historical second adjustment measure sets. The sixth attribute includes a historical third set of adjustment measures. The plurality of sixth attribute values includes a plurality of historical third adjustment measure sets. The device management database includes a knowledge graph composed of a plurality of first entity information, a plurality of second entity information, a plurality of third entity information, a first attribute, a second attribute, a third attribute, a plurality of first attribute values, a plurality of second attribute values, a plurality of third attribute values, a fourth attribute, a fifth attribute, a sixth attribute, a plurality of fourth attribute values, a plurality of fifth attribute values, and a plurality of sixth attribute values. The technical effects that the equipment management database with large data information amount, reliability and strong representativeness is constructed through the knowledge map, and therefore the accuracy and the reliability of data matching by subsequently utilizing the equipment management database are improved are achieved.
Step S460: and inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into the equipment management database for data matching to obtain the first starting rate range, the second starting rate range and the product percent of pass range.
Step S500: matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database;
specifically, a real-time first starting rate, a real-time second starting rate and a product percent of pass are used as input information, the input information is input into an equipment management database, and the real-time first starting rate, the real-time second starting rate and the product percent of pass are subjected to data matching through a plurality of historical first starting rate ranges, a plurality of historical second starting rate ranges and a plurality of historical product percent of pass ranges in the equipment management database, namely the real-time first starting rate, the real-time second starting rate and the product percent of pass are matched with a plurality of first attribute values, a plurality of second attribute values and a plurality of third attribute values in the equipment management database to obtain a first starting rate range, a second starting rate range and a product percent of pass range. Further, the obtained first starting rate range, second starting rate range and product percent of pass range are matched with a plurality of historical first adjusting measure sets, a plurality of historical second adjusting measure sets and a plurality of historical third adjusting measure sets in the equipment management database, namely the first starting rate range, the second starting rate range and the product percent of pass range are matched with a plurality of fourth attribute values, a plurality of fifth attribute values and a plurality of sixth attribute values in the equipment management database to obtain a first adjusting measure set, a second adjusting measure set and a third adjusting measure set. The first starting rate range, the second starting rate range and the product percent of pass range comprise a historical first starting rate range, a historical second starting rate range and a historical product percent of pass range corresponding to the real-time first starting rate, the real-time second starting rate and the product percent of pass in the equipment management database. The first adjustment measure set, the second adjustment measure set and the third adjustment measure set comprise historical first adjustment measure sets, historical second adjustment measure sets and historical third adjustment measure sets corresponding to a first starting rate range, a second starting rate range and a product qualification rate range in a device management database. The method achieves the technical effects that the data ranges of the real-time first starting rate, the real-time second starting rate and the product percent of pass are matched through the equipment management database, the accurate first starting rate range, the accurate second starting rate range and the accurate product percent of pass range are obtained, the reliable first adjustment measure set, the reliable second adjustment measure set and the reliable third adjustment measure set are determined according to the obtained first starting rate range, the obtained second starting rate range and the obtained product percent of pass range, and the follow-up accuracy of optimizing the first adjustment measure set, the reliable second adjustment measure set and the reliable third adjustment measure set is improved.
Step S600: and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment.
Further, step S600 of the present application further includes:
step S610: optimizing a first adjusting measure in the first adjusting measure set according to the optimizing optimization rule to obtain an optimized first adjusting measure;
further, step S610 of the present application further includes:
step S611: randomly selecting a first adjustment measure from the first adjustment measure set as a parent first adjustment measure and as an optimized first adjustment measure;
step S612: calculating the optimization score of the parent first adjustment measure according to the optimization searching rule to obtain a first optimization score;
further, step S612 of the present application further includes:
step S6121: acquiring adjustment cost information of the parent first adjustment measure;
step S6122: acquiring a first starting rate before adjustment and a first starting rate after adjustment by adopting a parent first adjustment measure in historical time;
step S6123: calculating to obtain an adjustment optimization amplitude according to the first starting rate before adjustment and the first starting rate after adjustment;
step S6124: evaluating the adjustment cost information and the adjustment optimization amplitude to obtain a first sub-score and a second sub-score;
step S6125: and performing weighted calculation on the first sub-score and the second sub-score to obtain the first optimization score.
Specifically, random selection is performed based on the first adjustment measure set, a parent first adjustment measure is obtained, and the parent first adjustment measure is set as a current optimized first adjustment measure. And further, based on the historical time, acquiring adjustment cost information of the first adjustment measure of the parent and acquisition of first opening rates before and after adjustment to obtain the adjustment cost information, the first opening rate before adjustment and the first opening rate after adjustment. Further, a first sub-score is obtained by evaluating the adjustment cost information. And further, performing difference calculation on the adjusted first starting rate and the first starting rate before adjustment to obtain an adjustment optimization amplitude, and evaluating the adjustment optimization amplitude to obtain a second sub-score. Then, a first optimization score is obtained by performing weighted calculation on the first sub-score and the second sub-score. The parent first adjustment measure may be any adjustment measure in the first adjustment measure set. The adjustment cost information comprises an adjustment cost parameter corresponding to the first adjustment measure of the parent. The first starting rate before adjustment comprises a historical first starting rate corresponding to the wafer production equipment before the wafer production equipment is adjusted by adopting a parent first adjustment measure in historical time. The adjusted first start rate comprises a historical first start rate corresponding to the wafer production equipment after the wafer production equipment is adjusted by adopting a parent first adjustment measure in historical time. The historical time may be adaptively set for determination. The adjusted optimal magnitude comprises a difference between the adjusted first actuation rate and the first actuation rate before adjustment. The first sub-score comprises an evaluation score corresponding to the adjustment cost information. For example, when the adjustment cost information indicates that the adjustment cost of the parent first adjustment measure is lower, the corresponding first sub-score is higher. The second sub-score comprises an evaluation score corresponding to the adjusted optimization magnitude. For example, when the adjustment optimization magnitude indicates that the difference between the adjusted first actuation rate and the first actuation rate before the adjustment is larger, the corresponding second sub-score is higher. The first optimization score comprises a weighted calculation of the first sub-score and the second sub-score. The technical effects of randomly selecting the first adjustment measure set, obtaining the first adjustment measure of the parent, calculating the optimization score of the first adjustment measure of the parent through the optimization searching rule, obtaining the first optimization score, and improving the accuracy and the scientificity of subsequently optimizing the first adjustment measure set are achieved.
Step S613: randomly selecting a first adjusting measure from the first adjusting measure set again to serve as a child first adjusting measure;
step S614: calculating the optimization score of the first adjustment measure of the child generation according to the optimization searching rule again to obtain a second optimization score;
step S615: judging whether the second optimization score is larger than the first optimization score, if so, taking the child first adjustment measure as an optimization management measure, and if not, taking the child first adjustment measure as an optimization management measure according to a probability, wherein the probability is calculated by the following formula:
wherein, e is a natural logarithm, and the natural logarithm is a natural logarithm,in order to achieve the second optimization score,c is a first optimization score and is an optimization rate parameter;
step S616: and continuously performing iterative optimization until a preset iteration number is reached, and obtaining and outputting a final optimization management measure.
Specifically, the first adjustment measure set is randomly selected again to obtain child first adjustment measures, and optimization scores of the child first adjustment measures are calculated according to the optimization searching rule to obtain second optimization scores. The second optimization score is the same as the first optimization score, and for the sake of brevity of the description, the details are not repeated here. And further, judging whether the second optimization score is larger than the first optimization score, and if the second optimization score is larger than the first optimization score, setting the child first adjustment measure as the current optimized first adjustment measure. If the second optimization score is not greater than the first optimization score, utilizing a probabilistic calculation formulaAfter calculation, the child first adjustment measure is set as the current optimized first adjustment measure according to the probability. And then, performing iteration optimization of preset iteration times on the current optimized first adjustment measure, and outputting the current optimized first adjustment measure as a final optimized first adjustment measure when the current optimized first adjustment measure is not changed after the current optimized first adjustment measure is subjected to the iteration optimization of the preset iteration times. The child first adjustment measure may be any adjustment measure in the first adjustment measure set that is different from the parent first adjustment measure. The preset iteration times can be adaptively set and determined according to the requirement of iterative optimization. Illustratively, the preset number of iterations is 30. In 30 iterations of optimization, if none of the current first adjustment measures for optimization has changed, it indicates that it is difficult to find a new current first adjustment measure for optimization, and the current first adjustment measure for optimization may be considered as global optimum, i.e. the current first adjustment measure for optimization is the optimal final first adjustment measure for optimization.
Formula for calculating probabilityWherein e is a natural logarithm,in order to achieve the second optimization score,for the first optimization score, C is the optimization rate parameter that gradually decreases with the number of iterative optimizations. In the initial stage of iterative optimization, C is larger, the probability of the first adjustment measure of the parent is larger than that of the first adjustment measure of the final optimization, the first adjustment measure of the child is probably locally optimal, in order to avoid the situation that the optimization process is stopped at the first adjustment measure of the parent, C is larger, the probability P is larger, the first adjustment measure of the child is accepted as the first adjustment measure of the final optimization with larger probability, and the probability is related to the difference value between the first optimization score and the second optimization score, so that the optimization rate is improved, and the iterative optimization is fast. And in the later stage of iterative optimizationThe probability of the previous optimized first adjustment measure is probably the final optimized first adjustment measure of the global optimum, and in order to improve the accuracy of the iterative optimization, C is smaller, so that the probability P is smaller, the current optimized first adjustment measure which is difficult to be inferior is the current optimized first adjustment measure of the global optimum, and the accuracy of the iterative optimization is improved. Optionally, the reduction manner of C may be any reduction manner in the prior art, such as exponential reduction or logarithmic reduction, and the value of C and the reduction manner may be determined according to the number of adjustment measures in the first adjustment measure set. The method achieves the technical effects that the final optimized first adjustment measure with optimal overall situation and high accuracy is obtained by performing iteration optimization of preset iteration times on the current optimized first adjustment measure, and the accuracy of management and optimization on the wafer production equipment is improved.
Step S620: optimizing a second adjusting measure in the second adjusting measure set according to the optimizing optimization rule to obtain the optimized second adjusting measure;
step S630: optimizing a third adjusting measure in the third adjusting measure set according to the optimizing optimization rule to obtain an optimized third adjusting measure;
step 640: and managing and optimizing the wafer production equipment by adopting the optimized first adjustment measure, the optimized second adjustment measure and the optimized third adjustment measure.
Specifically, based on the optimization searching rule, the optimization is respectively performed on the second adjustment measure set and the third adjustment measure set, so that the second adjustment measure and the third adjustment measure are optimized. And further, managing and optimizing the wafer production equipment according to the optimized first adjustment measure, the optimized second adjustment measure and the optimized third adjustment measure. The specific processes for optimizing the second adjustment measure, optimizing the third adjustment measure and optimizing the first adjustment measure are the same, and for the simplicity of the description, the details are not repeated here. The technical effects that the first adjustment measure, the second adjustment measure and the third adjustment measure are optimized, the adaptability is high, the accuracy is high, and the quality of management and optimization of wafer production equipment is improved are achieved.
In summary, the semiconductor device management optimization method based on the semiconductor industry chain provided by the present application has the following technical effects:
1. acquiring production information of a plurality of current production information indexes of the wafer production equipment to obtain an equipment production information set, and calculating a current real-time first starting rate, a real-time second starting rate and a product qualification rate of the wafer production equipment according to the equipment production information set; calculating and obtaining the comprehensive production efficiency of the wafer production equipment based on the obtained real-time first starting rate, real-time second starting rate and product percent of pass; judging whether the comprehensive production efficiency meets the preset requirement or not; if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range; matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database; and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment. The comprehensiveness, the accuracy and the adaptability of the management of the wafer production equipment are improved, the intelligent and scientific management optimization of the wafer production equipment is realized, and the management quality of the wafer production equipment is improved; powerful guarantee is provided for the normal operation of wafer production equipment; the technical effect of improving the integrity of the management optimization of the semiconductor equipment is achieved.
2. By scientifically calculating the production information set at multiple levels, the production efficiency of the wafer production equipment is accurately and efficiently evaluated, and the accurate and reliable comprehensive production efficiency is obtained, so that the adaptability and the accuracy of management optimization of the wafer production equipment are improved.
3. The wafer production equipment is adaptively managed and optimized based on comprehensive production efficiency and preset requirements, and the rationality and the scientificity of the management and optimization of the wafer production equipment are improved.
4. The current optimized first adjustment measure is subjected to iteration optimization of preset iteration times, so that the final optimized first adjustment measure with the optimal overall situation and high accuracy is obtained, and the accuracy of management optimization of the wafer production equipment is improved.
Example two
Based on the same inventive concept as the semiconductor device management optimization method based on the semiconductor industry chain in the foregoing embodiment, the present invention further provides a semiconductor device management optimization system based on the semiconductor industry chain, referring to fig. 3, where the system includes:
the production information acquisition module 11 is configured to acquire production information of a plurality of current production information indexes of wafer production equipment, and obtain an equipment production information set, where the wafer production equipment is included in a semiconductor production industry chain;
a calculating module 12, wherein the calculating module 12 is configured to calculate and obtain a current real-time first start rate, a real-time second start rate, and a product yield of the wafer production equipment according to the equipment production information set, and calculate and obtain a comprehensive production efficiency of the wafer production equipment according to the real-time first start rate, the real-time second start rate, and the product yield;
the judging module 13 is used for judging whether the comprehensive production efficiency meets the preset requirement or not;
a judgment result execution module 14, where the judgment result execution module 14 is configured to continue production if the first real-time start rate, the second real-time start rate, and the product yield are input into a pre-constructed device management database for data matching if the first real-time start rate, the second real-time start rate, and the product yield are not input into the pre-constructed device management database, and a first start rate range, a second start rate range, and a product yield range are obtained, where the device management database is constructed and obtained based on production information in the historical time of the wafer production device;
an adjustment measure matching module 15, wherein the adjustment measure matching module 15 is configured to match, in the device management database, a first adjustment measure set, a second adjustment measure set and a third adjustment measure set according to the first start rate range, the second start rate range and the product yield range;
and the management optimization module 16 is configured to construct an optimization rule, perform optimization in the first adjustment measure set, the second adjustment measure set, and the third adjustment measure set, obtain a first adjustment measure, a second adjustment measure, and a third adjustment measure, and perform management optimization on the wafer production equipment.
Further, the system further comprises:
the first information acquisition module is used for acquiring the working time, the scheduled downtime, the fault downtime and the equipment initialization time of the wafer production equipment within the current preset time period;
the second information acquisition module is used for acquiring the wafer production amount, the actual production period and the theoretical production period of the wafer production equipment within the current preset time period;
the third information acquisition module is used for acquiring qualified wafer production within the current preset time period of the wafer production equipment;
and the equipment production information set obtaining module is used for obtaining the equipment production information set according to the working time, the planned downtime, the fault downtime, the equipment initialization time, the wafer production quantity, the actual production period, the theoretical production period and the qualified wafer production quantity.
Further, the system further comprises:
a real-time first start-up rate determination module to calculate the real-time first start-up rate from the operating time, planned downtime, and equipment initialization time by:
wherein the content of the first and second substances,for the first start-up rate to be real-time,in order to be the working time, the working time is,in order to plan for the down-time,in order to provide for a period of down time,initializing time for the device;
a real-time second start-up rate determination module for calculating the real-time second start-up rate from the wafer throughput, the actual production cycle, the theoretical production cycle by:
wherein the content of the first and second substances,for the second start-up rate to be real-time,is made ofThe time-net starting rate is that,for real-time speed turn-on rate, S is wafer throughput,in order to realize the actual production cycle,a theoretical production cycle;
a product yield determination module, configured to calculate and obtain the product yield according to the wafer throughput and the qualified wafer throughput, according to the following formula:
wherein the content of the first and second substances,the method is used for the qualified rate of the product,qualified wafer throughput;
the comprehensive production efficiency determining module is used for calculating and obtaining the comprehensive production efficiency according to the real-time first starting rate, the real-time second starting rate and the product qualified rate and is represented by the following formula:
wherein the content of the first and second substances,the comprehensive production efficiency is improved.
Further, the system further comprises:
the historical information acquisition module is used for acquiring a first starting rate, a second starting rate and a product percent of pass of the wafer production equipment in a plurality of preset time periods within historical time to obtain a plurality of historical first starting rates, a plurality of historical second starting rates and a plurality of historical product percent of pass;
the adjustment measure acquisition module is used for acquiring a first adjustment measure, a second adjustment measure and a third adjustment measure for equipment management optimization of the wafer production equipment in a plurality of preset time periods within historical time, and acquiring a plurality of historical first adjustment measures, a plurality of historical second adjustment measures and a plurality of historical third adjustment measures;
the cluster analysis module is used for respectively carrying out cluster analysis on the plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical qualified starting rates of products to obtain a plurality of first categories, a plurality of second categories and a plurality of third categories;
a historical adjustment measure set determination module, configured to obtain a plurality of historical first start rate ranges, a plurality of historical second start rate ranges, and a plurality of historical product yield ranges according to the plurality of first categories, the plurality of second categories, and the plurality of third categories, and obtain a plurality of historical first adjustment measure sets, a plurality of historical second adjustment measure sets, and a plurality of historical third adjustment measure sets;
the first execution module is used for constructing and acquiring the equipment management database;
and the data matching module is used for inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into the equipment management database for data matching to obtain the first starting rate range, the second starting rate range and the product percent of pass range.
Further, the system further comprises:
an entity information determination module, configured to obtain, based on a knowledge graph, a plurality of first entity information, a plurality of second entity information, and a plurality of third entity information according to the plurality of first categories, the plurality of second categories, and the plurality of third categories;
a first attribute information determination module for obtaining a first attribute, a second attribute, a third attribute, a plurality of first attribute values, a plurality of second attribute values, and a plurality of third attribute values based on the plurality of historical first start rate ranges, the plurality of historical second start rate ranges, and the plurality of historical product yield ranges;
a second attribute information determination module, configured to obtain a fourth attribute, a fifth attribute, a sixth attribute, a plurality of fourth attribute values, a plurality of fifth attribute values, and a plurality of sixth attribute values according to the plurality of historical first adjustment measure sets, the plurality of historical second adjustment measure sets, and the plurality of historical third adjustment measure sets;
a second execution module to construct and obtain the device management database based on a knowledge graph.
Further, the system further comprises:
an optimized first adjustment measure determining module, configured to perform optimization of a first adjustment measure in the first adjustment measure set according to the optimization rule, to obtain the optimized first adjustment measure;
an optimized second adjustment measure determining module, configured to perform optimization of a second adjustment measure in the second adjustment measure set according to the optimization rule, so as to obtain the optimized second adjustment measure;
an optimized third adjustment measure determination module, configured to perform optimization of a third adjustment measure in the third adjustment measure set according to the optimization rule, so as to obtain an optimized third adjustment measure;
and the third execution module is used for managing and optimizing the wafer production equipment by adopting the first adjustment optimizing measure, the second adjustment optimizing measure and the third adjustment optimizing measure.
Further, the system further comprises:
a fourth execution module, configured to randomly select a first adjustment measure from the first adjustment measure set, as a parent first adjustment measure, and as an optimized first adjustment measure;
the first optimization score determining module is used for calculating the optimization score of the parent first adjusting measure according to the optimizing optimization rule to obtain a first optimization score;
a fifth execution module, configured to randomly select a first adjustment measure again from the first adjustment measure set as a child first adjustment measure;
a second optimization score determining module, configured to calculate, according to the optimization-seeking optimization rule again, an optimization score of the child first adjustment measure, so as to obtain a second optimization score;
a sixth executing module, configured to determine whether the second optimization score is greater than the first optimization score, if so, use the child first adjustment measure as an optimization management measure, and if not, use the child first adjustment measure as an optimization management measure according to a probability, where the probability is calculated by the following formula:
wherein, e is a natural logarithm, and the natural logarithm is a natural logarithm,in order to achieve the second optimization score,c is a first optimization score and is an optimization rate parameter;
and the seventh execution module is used for continuing iterative optimization until a preset iteration number is reached, and obtaining and outputting a final optimization management measure.
Further, the system further comprises:
the cost information acquisition module is used for acquiring adjustment cost information of the parent first adjustment measure;
the historical first starting rate determining module is used for acquiring a first starting rate before adjustment and a first starting rate after adjustment by adopting a parent first adjusting measure in historical time;
the adjustment optimization amplitude obtaining module is used for calculating and obtaining an adjustment optimization amplitude according to the first starting rate before adjustment and the first starting rate after adjustment;
an eighth execution module, configured to evaluate the adjustment cost information and the adjustment optimization magnitude, and obtain a first sub-score and a second sub-score;
a ninth execution module, configured to perform weighted calculation on the first sub-score and the second sub-score to obtain the first optimization score.
The application provides a semiconductor equipment management optimization method based on a semiconductor industry chain, wherein the method is applied to a semiconductor equipment management optimization system based on the semiconductor industry chain, and the method comprises the following steps: acquiring production information of a plurality of current production information indexes of the wafer production equipment to obtain an equipment production information set, and calculating a current real-time first starting rate, a real-time second starting rate and a product qualification rate of the wafer production equipment according to the equipment production information set; calculating and obtaining the comprehensive production efficiency of the wafer production equipment based on the obtained real-time first starting rate, the real-time second starting rate and the product percent of pass; judging whether the comprehensive production efficiency meets the preset requirement or not; if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range; matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database; and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment. The technical problems that in the prior art, the management comprehensiveness of the wafer production equipment of a semiconductor industry chain is not high, the accuracy is not enough, and the management effect of the wafer production equipment is poor are solved. The comprehensiveness, the accuracy and the adaptability of managing the wafer production equipment are improved, the intelligent and scientific management optimization of the wafer production equipment is realized, and the management quality of the wafer production equipment is improved; powerful guarantee is provided for the normal operation of wafer production equipment; the technical effect of improving the integrity of the management optimization of the semiconductor equipment is achieved.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The specification and drawings are merely illustrative of the present application, and it is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the invention and its equivalents.
Claims (9)
1. A semiconductor equipment management optimization method based on a semiconductor industry chain is characterized by comprising the following steps:
acquiring production information of a plurality of current production information indexes of wafer production equipment to obtain an equipment production information set, wherein the wafer production equipment is included in a semiconductor production industrial chain;
calculating to obtain the current real-time first starting rate, the real-time second starting rate and the product percent of pass of the wafer production equipment according to the equipment production information set, and calculating to obtain the comprehensive production efficiency of the wafer production equipment according to the real-time first starting rate, the real-time second starting rate and the product percent of pass;
judging whether the comprehensive production efficiency meets a preset requirement or not;
if so, continuing production, otherwise, inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into a pre-constructed equipment management database for data matching to obtain a first starting rate range, a second starting rate range and a product percent of pass range, wherein the equipment management database is constructed and obtained based on the production information of the wafer production equipment in the historical time;
matching and obtaining a first adjusting measure set, a second adjusting measure set and a third adjusting measure set according to the first starting rate range, the second starting rate range and the product percent of pass range in the equipment management database;
and constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment.
2. The method of claim 1, wherein collecting production information for a plurality of production information indicators for a current wafer production facility comprises:
collecting the working time, the scheduled downtime, the fault downtime and the equipment initialization time of the wafer production equipment in the current preset time period;
collecting the wafer production capacity, the actual production period and the theoretical production period of the wafer production equipment within the current preset time period;
acquiring qualified wafer production capacity of the wafer production equipment within a current preset time period;
and obtaining the equipment production information set according to the working time, the planned downtime, the fault downtime, the equipment initialization time, the wafer production capacity, the actual production period, the theoretical production period and the qualified wafer production capacity.
3. The method as claimed in claim 2, wherein calculating the current real-time first start-up rate, real-time second start-up rate and product yield of the wafer production equipment according to the equipment production information set, and calculating the comprehensive production efficiency of the wafer production equipment according to the real-time first start-up rate, real-time second start-up rate and product yield comprises:
calculating the real-time first actuation rate according to the operating time, the scheduled downtime, the downtime for the fault, and the equipment initialization time, by the following formula:
wherein the content of the first and second substances,for the first start-up rate to be real-time,in order to be the working time, the working time is,in order to plan for the down-time,in order to provide for a period of downtime for the fault,initializing time for the device;
calculating the real-time second starting rate according to the wafer production, the actual production period and the theoretical production period, and according to the following formula:
wherein the content of the first and second substances,for the second start-up rate to be real-time,in order to have a net rate of actuation in real time,for real-time speed turn-on rate, S is wafer throughput,in order to realize the actual production cycle,a theoretical production cycle;
calculating to obtain the product qualified rate according to the wafer production capacity and the qualified wafer production capacity, and according to the following formula:
wherein the content of the first and second substances,the method is used for the qualified rate of the product,qualified wafer throughput;
calculating to obtain the comprehensive production efficiency according to the real-time first starting rate, the real-time second starting rate and the product percent of pass, and adopting the following formula:
4. The method of claim 1, wherein entering the real-time first start-up rate, the real-time second start-up rate, and the product yield into a pre-built equipment management database for data matching comprises:
acquiring a first starting rate, a second starting rate and a product percent of pass of the wafer production equipment in a plurality of preset time periods within historical time to obtain a plurality of historical first starting rates, a plurality of historical second starting rates and a plurality of historical product percent of pass;
acquiring first adjustment measures, second adjustment measures and third adjustment measures for equipment management optimization of the wafer production equipment in a plurality of preset time periods within historical time to obtain a plurality of historical first adjustment measures, a plurality of historical second adjustment measures and a plurality of historical third adjustment measures;
respectively carrying out cluster analysis on the plurality of historical first starting rates, the plurality of historical second starting rates and the plurality of historical product qualified starting rates to obtain a plurality of first categories, a plurality of second categories and a plurality of third categories;
obtaining a plurality of historical first start rate ranges, a plurality of historical second start rate ranges and a plurality of historical product yield ranges according to the plurality of first categories, the plurality of second categories and the plurality of third categories, and obtaining a plurality of historical first adjustment measure sets, a plurality of historical second adjustment measure sets and a plurality of historical third adjustment measure sets;
constructing and obtaining the equipment management database;
and inputting the real-time first starting rate, the real-time second starting rate and the product percent of pass into the equipment management database for data matching to obtain the first starting rate range, the second starting rate range and the product percent of pass range.
5. The method of claim 4, wherein building the device management database comprises:
obtaining a plurality of first entity information, a plurality of second entity information and a plurality of third entity information based on a knowledge graph according to the plurality of first categories, the plurality of second categories and the plurality of third categories;
obtaining a first attribute, a second attribute, a third attribute, a plurality of first attribute values, a plurality of second attribute values and a plurality of third attribute values according to the plurality of historical first start rate ranges, the plurality of historical second start rate ranges and the plurality of historical product qualification rate ranges;
obtaining a fourth attribute, a fifth attribute, a sixth attribute, a plurality of fourth attribute values, a plurality of fifth attribute values and a plurality of sixth attribute values according to the plurality of historical first adjustment measure sets, the plurality of historical second adjustment measure sets and the plurality of historical third adjustment measure sets;
and constructing and acquiring the equipment management database based on the knowledge graph.
6. The method of claim 1, wherein constructing an optimization rule for optimizing within the first, second, and third sets of adjustment measures comprises:
optimizing a first adjusting measure in the first adjusting measure set according to the optimizing optimization rule to obtain an optimized first adjusting measure;
optimizing a second adjusting measure in the second adjusting measure set according to the optimizing optimization rule to obtain the optimized second adjusting measure;
optimizing a third adjusting measure in the third adjusting measure set according to the optimizing optimization rule to obtain an optimized third adjusting measure;
and managing and optimizing the wafer production equipment by adopting the optimized first adjustment measure, the optimized second adjustment measure and the optimized third adjustment measure.
7. The method of claim 6, wherein optimizing a first adjustment measure within the first set of adjustment measures according to the optimization rule comprises:
randomly selecting a first adjustment measure from the first adjustment measure set as a parent first adjustment measure and as an optimized first adjustment measure;
calculating the optimization score of the parent first adjustment measure according to the optimization searching rule to obtain a first optimization score;
randomly selecting a first adjusting measure from the first adjusting measure set again to serve as a first adjusting measure of a child;
calculating the optimization score of the first adjustment measure of the child generation according to the optimization searching rule again to obtain a second optimization score;
judging whether the second optimization score is larger than the first optimization score, if so, taking the child first adjustment measure as an optimization management measure, and if not, taking the child first adjustment measure as an optimization management measure according to a probability, wherein the probability is calculated by the following formula:
wherein, e is a natural logarithm, and the natural logarithm is a natural logarithm,in order to obtain the second optimization score,c is a first optimization score and is an optimization rate parameter;
and continuously performing iterative optimization until a preset iteration number is reached, and obtaining and outputting a final optimization management measure.
8. The method of claim 7, wherein calculating the optimization score of the parent first adjustment measure according to the optimizing rule comprises:
acquiring adjustment cost information of the parent first adjustment measure;
acquiring a first starting rate before adjustment and a first starting rate after adjustment by adopting a parent first adjustment measure in historical time;
calculating to obtain an adjustment optimization amplitude according to the first starting rate before adjustment and the first starting rate after adjustment;
evaluating the adjustment cost information and the adjustment optimization amplitude to obtain a first sub-score and a second sub-score;
and performing weighted calculation on the first sub-score and the second sub-score to obtain the first optimization score.
9. A semiconductor device management optimization system based on a semiconductor industry chain, the system comprising:
the production information acquisition module is used for acquiring the production information of a plurality of current production information indexes of the wafer production equipment to obtain an equipment production information set, wherein the wafer production equipment is included in a semiconductor production industrial chain;
the calculation module is used for calculating and obtaining the current real-time first starting rate, the real-time second starting rate and the product percent of pass of the wafer production equipment according to the equipment production information set, and calculating and obtaining the comprehensive production efficiency of the wafer production equipment according to the real-time first starting rate, the real-time second starting rate and the product percent of pass;
the judging module is used for judging whether the comprehensive production efficiency meets a preset requirement;
a judgment result execution module, configured to continue production if the judgment result execution module is yes, and input the real-time first start rate, the real-time second start rate and the product qualification rate into a pre-constructed device management database for data matching if the judgment result execution module is not so as to obtain a first start rate range, a second start rate range and a product qualification rate range, where the device management database is constructed and obtained based on production information in the wafer production device historical time;
the adjustment measure matching module is used for matching to obtain a first adjustment measure set, a second adjustment measure set and a third adjustment measure set according to the first starting rate range, the second starting rate range and the product qualified rate range in the equipment management database;
and the management optimization module is used for constructing an optimization rule, optimizing in the first adjustment measure set, the second adjustment measure set and the third adjustment measure set to obtain optimized first adjustment measures, optimized second adjustment measures and optimized third adjustment measures, and managing and optimizing the wafer production equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211517054.6A CN115600769B (en) | 2022-11-30 | 2022-11-30 | Semiconductor equipment management optimization method and system based on semiconductor industry chain |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211517054.6A CN115600769B (en) | 2022-11-30 | 2022-11-30 | Semiconductor equipment management optimization method and system based on semiconductor industry chain |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115600769A true CN115600769A (en) | 2023-01-13 |
CN115600769B CN115600769B (en) | 2023-07-25 |
Family
ID=84852281
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211517054.6A Active CN115600769B (en) | 2022-11-30 | 2022-11-30 | Semiconductor equipment management optimization method and system based on semiconductor industry chain |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115600769B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114137927A (en) * | 2021-12-03 | 2022-03-04 | 麦润智能科技成都有限公司 | Production and manufacturing management system based on real-time production process data |
CN115407739A (en) * | 2022-10-31 | 2022-11-29 | 天津有容蒂康通讯技术有限公司 | Production equipment control method and system for cable manufacturing |
-
2022
- 2022-11-30 CN CN202211517054.6A patent/CN115600769B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114137927A (en) * | 2021-12-03 | 2022-03-04 | 麦润智能科技成都有限公司 | Production and manufacturing management system based on real-time production process data |
CN115407739A (en) * | 2022-10-31 | 2022-11-29 | 天津有容蒂康通讯技术有限公司 | Production equipment control method and system for cable manufacturing |
Also Published As
Publication number | Publication date |
---|---|
CN115600769B (en) | 2023-07-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10921759B2 (en) | Computer system and method for monitoring key performance indicators (KPIs) online using time series pattern model | |
CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
JP2020500420A (en) | Yield prediction system and method for machine learning based semiconductor manufacturing | |
JP2008538429A (en) | Model optimization method and system using zeta statistics | |
CN111898867B (en) | Airplane final assembly production line productivity prediction method based on deep neural network | |
Cao et al. | A novel multi-objective optimization approach of machining parameters with small sample problem in gear hobbing | |
CN117236278B (en) | Chip production simulation method and system based on digital twin technology | |
Salmasnia et al. | A robust intelligent framework for multiple response statistical optimization problems based on artificial neural network and Taguchi method | |
CN116700172A (en) | Industrial data integrated processing method and system combined with industrial Internet | |
CN114169434A (en) | Load prediction method | |
CN113515512A (en) | Quality control and improvement method for industrial internet platform data | |
CN113673679A (en) | Cut tobacco drying process parameter selection method based on particle swarm optimization neural network | |
CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
CN116757059A (en) | Carbon accounting method, device and related medium based on product type and process | |
CN111062539A (en) | Total electric quantity prediction method based on secondary electric quantity characteristic clustering analysis | |
CN115600769A (en) | Semiconductor equipment management optimization method and system based on semiconductor industry chain | |
CN116414095A (en) | Data-driven optimization method for technological parameters in traditional Chinese medicine manufacturing process | |
CN110852496A (en) | Natural gas load prediction method based on LSTM recurrent neural network | |
CN115630433A (en) | Building design method and system based on machine learning and BIM technology | |
CN115616333A (en) | Power distribution network line loss prediction method and system | |
Venkatesh et al. | An efficient method for predicting linear regression with polynomial regression | |
CN113111588B (en) | NO of gas turbine X Emission concentration prediction method and device | |
CN109543930B (en) | Dispatching method and system based on machine multi-level steady-state production rate | |
CN103488145B (en) | The incinerator hazardous emission controls up to par system and method for gunz FUZZY NETWORK | |
JP6892848B2 (en) | Information processing equipment, information processing methods and information processing programs |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230703 Address after: 518000 Taoxian Jinhua Building 1409, Gaofeng Community, Dalang Street, Longhua District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Chongyue Innovation Technology Co.,Ltd. Address before: 226000 5189, Building A2, Jianghai Zhihui Garden, 266 New Century Avenue, Nantong Hi tech Industrial Development Zone, Nantong, Jiangsu Province Applicant before: Nantong Xinjinyi Software Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |