WO2023226675A1 - System for rapidly analyzing equipment difference root cause in semiconductor manufacturing - Google Patents
System for rapidly analyzing equipment difference root cause in semiconductor manufacturing Download PDFInfo
- Publication number
- WO2023226675A1 WO2023226675A1 PCT/CN2023/091120 CN2023091120W WO2023226675A1 WO 2023226675 A1 WO2023226675 A1 WO 2023226675A1 CN 2023091120 W CN2023091120 W CN 2023091120W WO 2023226675 A1 WO2023226675 A1 WO 2023226675A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- module
- data
- difference
- equipment
- parameter
- Prior art date
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 57
- 239000004065 semiconductor Substances 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 239000003086 colorant Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
Definitions
- the invention relates to the technical field of semiconductor production, and in particular to a system for quickly analyzing root causes of equipment differences in semiconductor manufacturing.
- the traditional method of semiconductor manufacturing equipment difference analysis relies on manually obtaining equipment production logs. By manually screening and analyzing each production parameter in the log one by one, and relying on production experience to compare individual parameters one by one, the relevant parameter items of equipment differences are finally obtained. , its analysis efficiency completely depends on the production experience of engineers, and the analysis time of experienced engineers is shorter than that of ordinary engineers. However, when encountering a device type with too many device parameters, it is possible that individual parameters may be missed during analysis due to too many parameters. In the end, the root cause of the differences in some devices cannot be found and become an unsolvable mystery. Cumbersome traditional analysis methods consume a lot of manual analysis time. As semiconductor manufacturing becomes more and more automated and the amount of data in production becomes larger and larger, traditional analysis methods are no longer able to quickly find equipment differences. Reason scene requirements.
- the present invention is made to solve the above problems, and aims to provide a system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing.
- the invention provides a system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing, which is characterized by including: a production parameter acquisition module, a data association module, a database module, a data summary display module, a difference impact proportion ranking module, and key parameter items Data display module; among them, the production parameter acquisition module is used to obtain the production parameter items of each product in the equipment and their corresponding parameter values; the data association module is used to obtain each product name, process name, equipment name, production parameter item name, parameter value for data association; the database module is used to produce the corresponding database from the associated data; the data summary display module is used to summarize the associated data selected by the user from the database through the PCA algorithm, and graphically display the summarized sample scores. ; The difference impact proportion sorting module sorts the production parameter items according to the proportion that affects the difference from large to small; the key parameter item data display module displays the data of key parameter items that affect the difference.
- the system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing provided by the present invention, it is characterized in that it also includes: a key parameter item number setting module, wherein the key parameter item number setting module is used by the user to determine the impact of the difference.
- a key parameter item number setting module is used by the user to determine the impact of the difference.
- the system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing can also have the following features: wherein the key parameter item data display module is The PCA model curve model displays the data of key parameter items in a curve graphic. The differential data and the undifferentiated data in the curve graphic are displayed in different colors.
- the system of the present invention for quickly analyzing the root causes of equipment differences in semiconductor manufacturing establishes an associated database of product information, equipment information and production parameters on the basis of ensuring data integrity through data source selection and processing of missing data values, and analyzes through the PCA algorithm
- the root causes and key production parameters of different individual equipment differences in similar process conditions among similar equipment can also be identified, and the proportion of key production parameters of equipment differences can also be ranked.
- This invention can quickly lock the key production parameters of equipment differences and save more than 10 times the analysis time than the traditional manual analysis method.
- FIG. 1 is a block diagram of a system for quickly analyzing root causes of equipment differences in semiconductor manufacturing in an embodiment of the present invention
- Figure 2 is a graphical display of PCA algorithm sample scores in an embodiment of the present invention
- Figure 3 is a schematic diagram illustrating production parameter items sorted from large to small according to the proportion of influencing differences in the embodiment of the present invention
- Figure 4 is a data display curve chart of the first key parameter item in the embodiment of the present invention.
- Figure 5 is a data display curve chart of the third key parameter item in the embodiment of the present invention.
- Figure 6 is a data display curve chart of the fifth key parameter item in the embodiment of the present invention.
- Figure 7 is a data display curve chart of the eighth key parameter item in the embodiment of the present invention.
- this embodiment provides a system 100 for quickly analyzing the root causes of equipment differences in semiconductor manufacturing.
- the system includes the following functional modules: production parameter acquisition module 1, data association module 2, database module 3, and data summary display module 4 , Difference impact proportion sorting module 5, key parameter item quantity setting module 6, key parameter item data display module 7.
- Each functional module implements the corresponding function by running the corresponding computer algorithm.
- the production parameter acquisition module 1 acquires the production parameter items and corresponding parameter values of each product in the equipment through the system interface program.
- the data association module 2 is used to perform data association on each product name, process name, equipment name, production parameter item name, and parameter value.
- the database module 3 is used to generate a corresponding database from the associated data.
- the data summary display module 4 uses the PCA algorithm to summarize the associated data selected by the user from the database, and summarizes the data to obtain sample scores for graphic display.
- the PCA algorithm sample score graph is shown in Figure 2.
- t[1] represents the sample value after the first dimensionality reduction transformation of the PCA algorithm
- t[2] represents the sample value after the second dimensionality reduction transformation of the PCA algorithm
- CVDC23 and CVDC22 is the name of the production equipment, which are two different production units of the same type of equipment.
- the difference impact proportion sorting module 5 sorts the production parameter items according to the proportion of impact difference from large to small.
- Figure 3 illustrates the difference in influence of each production parameter item in this embodiment. The proportions of are sorted from large to small.
- the abscissa in the figure represents the production parameter items, and the ordinate represents the impact difference value.
- the key parameter item number setting module 6 is used by the user to set several parameter items at the top of the ranking results of the difference impact proportion sorting module as key parameter items that affect the difference. For example, the user can set the top eight parameter items as key parameter items, which can be set according to the actual situation.
- the key parameter item data display module 7 displays the data of key parameter items that affect the difference.
- the key parameter item data display module 7 uses the PCA model curve model to display the data of the key parameter item in a curve graphic.
- the differential data and the undifferentiated data in the curve graphic are displayed in different colors.
- Figure 4 is the data display of the first key parameter item;
- Figure 5 is the data display of the third key parameter item;
- Figure 6 is the data display of the fifth key parameter item;
- Figure 7 is the data display of the eighth key parameter item.
- the abscissa is the product name, and the ordinate is the parameter value data of the parameter item. Different colors are used in the figure to represent differential data and undifferentiated data.
- the system of the present invention uses the PCA algorithm to calculate the characteristic values of different groups of data and analyze the proportions of various factors, consider the characteristics of data differences from the data level, analyze the key parameters that affect equipment differences, and quickly lock machine differences for the manufacturing department. Root causes enable efficient traceability analysis of production data.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Manufacturing & Machinery (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Provided in the present invention is a system for rapidly analyzing equipment difference root causes in semiconductor manufacturing. The system comprises: a production parameter acquisition module, a data association module, a database module, a data summarization and display module, a difference impact proportion sorting module and a key parameter item data display module. The production parameter acquisition module is used for acquiring production parameter items and parameter values thereof of products in the equipment. The data association module is used for associating product names, process names, equipment names, production parameter item names and parameter values. The database module is used for generating a corresponding database for the associated data. The data summarization and display module is used for summarizing the associated data selected from the database by the user by means of a PCA algorithm, and carrying out graphic display on summarized sample scores. The difference impact proportion sorting module sorts the production parameter items from high to low according to difference impact proportions. The key parameter item data display module displays data of key parameter items affecting the difference.
Description
本发明涉及半导体生产技术领域,具体涉及一种快速分析半导体制造中设备差异根因的系统。The invention relates to the technical field of semiconductor production, and in particular to a system for quickly analyzing root causes of equipment differences in semiconductor manufacturing.
在半导体集成电路制造过程中,相同工艺条件下的同类型设备间的个体设备差异分析对于半导体生产是极其重要的。该条件下设备差异越大,对于工艺转移就越困难,同样也比较难以控制产品质量的一致性。半导体生产设备众多,快速精确的寻找相同或相似工艺条件下设备差异的根本原因占据了工程师近一半的工作内容,对半导体制造效率的提升是一个重大挑战,也影响着半导体制造的成本和利润的关键指标。In the semiconductor integrated circuit manufacturing process, the analysis of individual device differences between the same type of equipment under the same process conditions is extremely important for semiconductor production. The greater the difference in equipment under this condition, the more difficult it is to transfer the process, and it is also more difficult to control the consistency of product quality. There are many semiconductor production equipments. Quickly and accurately finding the root causes of equipment differences under the same or similar process conditions takes up nearly half of the work of engineers. It is a major challenge to improve the efficiency of semiconductor manufacturing and also affects the cost and profit of semiconductor manufacturing. Key indicators.
半导体制造设备差异分析传统方法依赖于手动获取设备生产日志,通过对日志中各生产参数进行逐个的手动筛选和分析,依靠生产经验对个别参数进行逐个画图比对,最终获得设备差异的相关参数项,其分析效率完全依赖工程师的生产经验,经验丰富的工程师分析时长比一般工程师分析时长短。但是遇到设备参数过多的设备类型,有可能因为参数过多造成个别参数在分析时候被遗漏,最终有些设备的差异找不到根本原因,成为无解之谜。繁琐的传统分析方法耗费大量的人工分析时间,随着半导体制造自动化程度越来越高,生产中的数据量越来越大,传统的分析方法已经无法满足快速的寻找设备差异
原因的场景需求。The traditional method of semiconductor manufacturing equipment difference analysis relies on manually obtaining equipment production logs. By manually screening and analyzing each production parameter in the log one by one, and relying on production experience to compare individual parameters one by one, the relevant parameter items of equipment differences are finally obtained. , its analysis efficiency completely depends on the production experience of engineers, and the analysis time of experienced engineers is shorter than that of ordinary engineers. However, when encountering a device type with too many device parameters, it is possible that individual parameters may be missed during analysis due to too many parameters. In the end, the root cause of the differences in some devices cannot be found and become an unsolvable mystery. Cumbersome traditional analysis methods consume a lot of manual analysis time. As semiconductor manufacturing becomes more and more automated and the amount of data in production becomes larger and larger, traditional analysis methods are no longer able to quickly find equipment differences. Reason scene requirements.
发明内容Contents of the invention
本发明是为了解决上述问题而进行的,目的在于提供一种快速分析半导体制造中设备差异根因的系统。The present invention is made to solve the above problems, and aims to provide a system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing.
本发明提供了一种快速分析半导体制造中设备差异根因的系统,其特征在于,包括:生产参数获取模块、数据关联模块、数据库模块、数据汇总展示模块、差异影响比重排序模块、关键参数项数据展示模块;其中,生产参数获取模块用于获取各产品在设备中生产参数项及其对应的参数值;数据关联模块用于将各产品名称、工艺名称、设备名称、生产参数项名称、参数值进行数据关联;数据库模块用于将关联后的数据生产对应的数据库;数据汇总展示模块通过PCA算法用于对用户从数据库所选中的关联数据进行汇总,并将汇总得到的样本得分进行图形展示;差异影响比重排序模块按照影响差异的比重由大至小对生产参数项进行排序;关键参数项数据展示模块将影响差异的关键参数项的数据进行展示。The invention provides a system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing, which is characterized by including: a production parameter acquisition module, a data association module, a database module, a data summary display module, a difference impact proportion ranking module, and key parameter items Data display module; among them, the production parameter acquisition module is used to obtain the production parameter items of each product in the equipment and their corresponding parameter values; the data association module is used to obtain each product name, process name, equipment name, production parameter item name, parameter value for data association; the database module is used to produce the corresponding database from the associated data; the data summary display module is used to summarize the associated data selected by the user from the database through the PCA algorithm, and graphically display the summarized sample scores. ; The difference impact proportion sorting module sorts the production parameter items according to the proportion that affects the difference from large to small; the key parameter item data display module displays the data of key parameter items that affect the difference.
进一步,在本发明提供的快速分析半导体制造中设备差异根因的系统中,其特征在于,还包括:关键参数项数量设定模块,其中,关键参数项数量设定模块用于用户将差异影响比重排序模块的排序结果中前列的若干个参数项设定为影响差异的关键参数项。Further, in the system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing provided by the present invention, it is characterized in that it also includes: a key parameter item number setting module, wherein the key parameter item number setting module is used by the user to determine the impact of the difference. Several parameter items at the top of the sorting results of the proportion sorting module are set as key parameter items that affect the difference.
进一步,在本发明提供的快速分析半导体制造中设备差异根因的系统中,还可以具有这样的特征:其中,关键参数项数据展示模块以
PCA模型曲线模型对关键参数项的数据进行曲线图形展示,该曲线图形中有差异数据与无差异数据采用不同的颜色分别显示。Furthermore, the system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing provided by the present invention can also have the following features: wherein the key parameter item data display module is The PCA model curve model displays the data of key parameter items in a curve graphic. The differential data and the undifferentiated data in the curve graphic are displayed in different colors.
本发明的作用与效果:Functions and effects of the present invention:
本发明的快速分析半导体制造中设备差异根因的系统通过数据源选择和数据缺失值的处理,在保证数据完整性的基础上建立产品信息、设备信息及生产参数的关联数据库,通过PCA算法分析出同类工艺条件在同类设备中不同个体设备差异的根本原因和关键生产参数,还可以实现设备差异关键生产参数的比重排名。本发明可以快速锁定设备差异的关键生产参数,比传统人工分析方法节省10倍以上的分析时间。The system of the present invention for quickly analyzing the root causes of equipment differences in semiconductor manufacturing establishes an associated database of product information, equipment information and production parameters on the basis of ensuring data integrity through data source selection and processing of missing data values, and analyzes through the PCA algorithm The root causes and key production parameters of different individual equipment differences in similar process conditions among similar equipment can also be identified, and the proportion of key production parameters of equipment differences can also be ranked. This invention can quickly lock the key production parameters of equipment differences and save more than 10 times the analysis time than the traditional manual analysis method.
图1是本发明的实施例中快速分析半导体制造中设备差异根因的系统的框图;1 is a block diagram of a system for quickly analyzing root causes of equipment differences in semiconductor manufacturing in an embodiment of the present invention;
图2是本发明的实施例中PCA算法样本得分图形展示图;Figure 2 is a graphical display of PCA algorithm sample scores in an embodiment of the present invention;
图3是本发明的实施例中生产参数项按影响差异的比重由大至小排序的示意图;Figure 3 is a schematic diagram illustrating production parameter items sorted from large to small according to the proportion of influencing differences in the embodiment of the present invention;
图4是本发明的实施例中第一关键参数项的数据展示曲线图;Figure 4 is a data display curve chart of the first key parameter item in the embodiment of the present invention;
图5是本发明的实施例中第三关键参数项的数据展示曲线图;Figure 5 is a data display curve chart of the third key parameter item in the embodiment of the present invention;
图6是本发明的实施例中第五关键参数项的数据展示曲线图;Figure 6 is a data display curve chart of the fifth key parameter item in the embodiment of the present invention;
图7是本发明的实施例中第八关键参数项的数据展示曲线图。
Figure 7 is a data display curve chart of the eighth key parameter item in the embodiment of the present invention.
为了使本发明实现的技术手段、创作特征、达成目的与功效易于明白了解,以下实施例结合附图对本发明的技术方案作具体阐述。In order to make it easy to understand the technical means, creative features, objectives and effects achieved by the present invention, the following embodiments specifically describe the technical solutions of the present invention in conjunction with the accompanying drawings.
<实施例><Example>
参阅图1,本实施例提供一种快速分析半导体制造中设备差异根因的系统100,该系统包括以下功能模块:生产参数获取模块1、数据关联模块2、数据库模块3、数据汇总展示模块4、差异影响比重排序模块5、关键参数项数量设定模块6、关键参数项数据展示模块7。各功能模块通过运行相应的计算机算法实现对应的功能。Referring to Figure 1, this embodiment provides a system 100 for quickly analyzing the root causes of equipment differences in semiconductor manufacturing. The system includes the following functional modules: production parameter acquisition module 1, data association module 2, database module 3, and data summary display module 4 , Difference impact proportion sorting module 5, key parameter item quantity setting module 6, key parameter item data display module 7. Each functional module implements the corresponding function by running the corresponding computer algorithm.
生产参数获取模块1通过系统接口程序获取各产品在设备中生产参数项及其对应的参数值。The production parameter acquisition module 1 acquires the production parameter items and corresponding parameter values of each product in the equipment through the system interface program.
数据关联模块2用于将各产品名称、工艺名称、设备名称、生产参数项名称、参数值进行数据关联。The data association module 2 is used to perform data association on each product name, process name, equipment name, production parameter item name, and parameter value.
数据库模块3用于将关联后的数据生产对应的数据库。The database module 3 is used to generate a corresponding database from the associated data.
数据汇总展示模块4通过PCA算法用于对用户从数据库所选中的关联数据进行汇总,并将数据汇总得到样本得分进行图形展示。PCA算法样本得分图形如图2所示,图中t[1]表示PCA算法进行一次降维转换后的样本值,t[2]表示PCA算法进行二次降维转换后的样本值,CVDC23和CVDC22是生产设备名称,分别为同一类型设备的两个不同生产单元。The data summary display module 4 uses the PCA algorithm to summarize the associated data selected by the user from the database, and summarizes the data to obtain sample scores for graphic display. The PCA algorithm sample score graph is shown in Figure 2. In the figure, t[1] represents the sample value after the first dimensionality reduction transformation of the PCA algorithm, t[2] represents the sample value after the second dimensionality reduction transformation of the PCA algorithm, CVDC23 and CVDC22 is the name of the production equipment, which are two different production units of the same type of equipment.
差异影响比重排序模块5按照影响差异的比重由大至小对生产参数项进行排序。图3示意了本实施例中各生产参数项按照影响差异
的比重由大至小排序,图中横坐标表示生产参数项,纵坐标表示影响差异值。The difference impact proportion sorting module 5 sorts the production parameter items according to the proportion of impact difference from large to small. Figure 3 illustrates the difference in influence of each production parameter item in this embodiment. The proportions of are sorted from large to small. The abscissa in the figure represents the production parameter items, and the ordinate represents the impact difference value.
关键参数项数量设定模块6用于用户将差异影响比重排序模块的排序结果中前列的若干个参数项设定为影响差异的关键参数项。例如,用户可以将排序前八的参数项设定为关键参数项,具体可根据实际情况进行设定。The key parameter item number setting module 6 is used by the user to set several parameter items at the top of the ranking results of the difference impact proportion sorting module as key parameter items that affect the difference. For example, the user can set the top eight parameter items as key parameter items, which can be set according to the actual situation.
关键参数项数据展示模块7将影响差异的关键参数项的数据进行展示。关键参数项数据展示模块7以PCA模型曲线模型对关键参数项的数据进行曲线图形展示,该曲线图形中有差异数据与无差异数据采用不同的颜色分别显示。图4为第一关键参数项的数据展示;图5为第三关键参数项的数据展示;图6为第五关键参数项的数据展示;图7为第八关键参数项的数据展示。在图4至图7数据展示曲线图中,横坐标为产品名称,纵坐标为该参数项的参数值数据,图中用不同颜色表示了有差异数据和无差异数据。The key parameter item data display module 7 displays the data of key parameter items that affect the difference. The key parameter item data display module 7 uses the PCA model curve model to display the data of the key parameter item in a curve graphic. The differential data and the undifferentiated data in the curve graphic are displayed in different colors. Figure 4 is the data display of the first key parameter item; Figure 5 is the data display of the third key parameter item; Figure 6 is the data display of the fifth key parameter item; Figure 7 is the data display of the eighth key parameter item. In the data display curve graphs in Figures 4 to 7, the abscissa is the product name, and the ordinate is the parameter value data of the parameter item. Different colors are used in the figure to represent differential data and undifferentiated data.
本发明的系统通过PCA算法通过对不同组数据的特征值进行计算和各项因子的比重分析,从数据层面考虑数据差异的特征,分析出影响设备差异的关键参数,为制造部门快速锁定机差根因,实现对生产数据进行高效的追溯分析。The system of the present invention uses the PCA algorithm to calculate the characteristic values of different groups of data and analyze the proportions of various factors, consider the characteristics of data differences from the data level, analyze the key parameters that affect equipment differences, and quickly lock machine differences for the manufacturing department. Root causes enable efficient traceability analysis of production data.
上述实施例为本发明的具体案例,并不用来限制本发明的保护范围。凡在本发明的精神和原则之内所作的任何修改、等同替换、改进等,均包含在本发明的保护范围内。
The above embodiments are specific examples of the present invention and are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the protection scope of the present invention.
Claims (3)
- 一种快速分析半导体制造中设备差异根因的系统,其特征在于,包括:生产参数获取模块、数据关联模块、数据库模块、数据汇总展示模块、差异影响比重排序模块、关键参数项数据展示模块;A system for quickly analyzing the root causes of equipment differences in semiconductor manufacturing, which is characterized by including: a production parameter acquisition module, a data association module, a database module, a data summary display module, a difference impact proportion sorting module, and a key parameter item data display module;其中,所述生产参数获取模块用于获取各产品在设备中生产参数项及其对应的参数值;Wherein, the production parameter acquisition module is used to obtain the production parameter items of each product in the equipment and their corresponding parameter values;所述数据关联模块用于将各产品名称、工艺名称、设备名称、生产参数项名称、参数值进行数据关联;The data association module is used to perform data association on each product name, process name, equipment name, production parameter item name, and parameter value;所述数据库模块用于将关联后的数据生产对应的数据库;The database module is used to produce a corresponding database from the associated data;所述数据汇总展示模块通过PCA算法用于对用户从数据库所选中的关联数据进行汇总,并将汇总得到的样本得分进行图形展示;The data summary display module uses the PCA algorithm to summarize the associated data selected by the user from the database, and graphically displays the summarized sample scores;所述差异影响比重排序模块按照影响差异的比重由大至小对生产参数项进行排序;The difference impact proportion sorting module sorts the production parameter items according to the proportion of impact difference from large to small;所述关键参数项数据展示模块将影响差异的关键参数项的数据进行展示。The key parameter item data display module displays the data of key parameter items that affect the difference.
- 根据权利要求1所述的快速分析半导体制造中设备差异根因的系统,其特征在于,还包括:关键参数项数量设定模块,The system for quickly analyzing root causes of equipment differences in semiconductor manufacturing according to claim 1, further comprising: a key parameter item quantity setting module,其中,所述关键参数项数量设定模块用于用户将所述差异影响比重排序模块的排序结果中前列的若干个参数项设定为影响差异的关键参数项。Wherein, the key parameter item number setting module is used by the user to set several parameter items at the top of the sorting result of the difference impact proportion sorting module as key parameter items that affect the difference.
- 根据权利要求1所述的快速分析半导体制造中设备差异根因的 系统,其特征在于:Method for quickly analyzing root causes of equipment differences in semiconductor manufacturing according to claim 1 system, characterized by:其中,所述关键参数项数据展示模块以PCA模型曲线模型对关键参数项的数据进行曲线图形展示,该曲线图形中有差异数据与无差异数据采用不同的颜色分别显示。 Wherein, the key parameter item data display module uses a PCA model curve model to display the data of the key parameter item in a curve graphic, and the differential data and the undifferentiated data in the curve graphic are displayed in different colors.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210593693.4A CN114912898A (en) | 2022-05-27 | 2022-05-27 | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing |
CN202210593693.4 | 2022-05-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023226675A1 true WO2023226675A1 (en) | 2023-11-30 |
Family
ID=82768499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/091120 WO2023226675A1 (en) | 2022-05-27 | 2023-04-27 | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114912898A (en) |
WO (1) | WO2023226675A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114912898A (en) * | 2022-05-27 | 2022-08-16 | 上海哥瑞利软件股份有限公司 | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679163A (en) * | 2017-09-28 | 2018-02-09 | 成都海威华芯科技有限公司 | A kind of one step process manufacture factor significant difference analysis system and analysis method |
CN108257248A (en) * | 2018-02-23 | 2018-07-06 | 英特尔产品(成都)有限公司 | For monitoring the method and apparatus of production equipment and analytical equipment |
CN110276410A (en) * | 2019-06-27 | 2019-09-24 | 京东方科技集团股份有限公司 | Determine method, apparatus, electronic equipment and the storage medium of poor prognostic cause |
CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
CN114912898A (en) * | 2022-05-27 | 2022-08-16 | 上海哥瑞利软件股份有限公司 | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing |
-
2022
- 2022-05-27 CN CN202210593693.4A patent/CN114912898A/en active Pending
-
2023
- 2023-04-27 WO PCT/CN2023/091120 patent/WO2023226675A1/en unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679163A (en) * | 2017-09-28 | 2018-02-09 | 成都海威华芯科技有限公司 | A kind of one step process manufacture factor significant difference analysis system and analysis method |
CN108257248A (en) * | 2018-02-23 | 2018-07-06 | 英特尔产品(成都)有限公司 | For monitoring the method and apparatus of production equipment and analytical equipment |
CN110276410A (en) * | 2019-06-27 | 2019-09-24 | 京东方科技集团股份有限公司 | Determine method, apparatus, electronic equipment and the storage medium of poor prognostic cause |
CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
CN114912898A (en) * | 2022-05-27 | 2022-08-16 | 上海哥瑞利软件股份有限公司 | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing |
Also Published As
Publication number | Publication date |
---|---|
CN114912898A (en) | 2022-08-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109711659B (en) | Yield improvement management system and method for industrial production | |
CN107368700A (en) | Based on the microbial diversity interaction analysis system and method for calculating cloud platform | |
WO2023226675A1 (en) | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing | |
CN110309807A (en) | CAD diagram paper intelligent identification Method | |
CN101414183B (en) | Cigarette working procedure quality overall evaluation system and method based on gray correlation analysis | |
CN111159645B (en) | Bad root cause positioning method based on product production histories and parameters | |
CN106404441B (en) | A kind of failure modes diagnostic method based on non-linear similarity index | |
WO2007078814A2 (en) | Apparatus and method for strategy map validation and visualization | |
EP4080429A1 (en) | Technology readiness level determination method and system based on science and technology big data | |
CN104796282A (en) | Evaluating system and evaluating method for deep packet inspection product | |
Zhang et al. | A generic data analytics system for manufacturing production | |
CN113409555A (en) | Real-time alarm linkage method and system based on Internet of things | |
WO2021142622A1 (en) | Method for determining cause of defect, and electronic device, storage medium, and system | |
CN106680693A (en) | Batch test method for semiconductor chips based on grayscale map of fault data | |
CN112231971A (en) | Blast furnace fault diagnosis method based on relative integral trend diffusion fault sample generation | |
CN112598142B (en) | Wind turbine maintenance working quality inspection auxiliary method and system | |
CN117592656A (en) | Carbon footprint monitoring method and system based on carbon data accounting | |
CN111290969B (en) | Software quality analysis method based on characteristic frequency statistics | |
CN115905802A (en) | Semiconductor wafer test yield analysis method based on thermodynamic diagram | |
Riege et al. | Displaying data effectively using an automated process dashboard | |
CN116150989A (en) | Photovoltaic module manufacturing method and photovoltaic module | |
US6766265B2 (en) | Processing tester information by trellising in integrated circuit technology development | |
CN111461471A (en) | Method for analyzing and dynamically identifying company strategic environment trend | |
CN110262973B (en) | Data maintenance method, device, equipment and computer storage medium | |
CN111932279A (en) | Traditional Chinese medicine quality safety tracing and supervising method based on block chain technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23810748 Country of ref document: EP Kind code of ref document: A1 |