CN108510615A - A kind of control system of semiconductor manufacturing facility and technique - Google Patents
A kind of control system of semiconductor manufacturing facility and technique Download PDFInfo
- Publication number
- CN108510615A CN108510615A CN201810284488.3A CN201810284488A CN108510615A CN 108510615 A CN108510615 A CN 108510615A CN 201810284488 A CN201810284488 A CN 201810284488A CN 108510615 A CN108510615 A CN 108510615A
- Authority
- CN
- China
- Prior art keywords
- data
- semiconductor manufacturing
- similarity distance
- manufacturing facility
- central point
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 239000004065 semiconductor Substances 0.000 title claims abstract description 50
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 32
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000012706 support-vector machine Methods 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 238000013450 outlier detection Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 claims description 7
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 3
- 238000001311 chemical methods and process Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000000547 structure data Methods 0.000 claims description 2
- 238000006467 substitution reaction Methods 0.000 claims description 2
- 230000002547 anomalous effect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000001427 coherent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/146—Quality control systems during manufacturing process
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- General Factory Administration (AREA)
Abstract
The present invention provides the control systems of a kind of semiconductor manufacturing facility and technique, including data pre-processing unit, outlier detection unit, support vector machines training unit, intelligent monitoring unit and continuous learning unit；Wherein data pre-processing unit includes preprocessing module and clustering processing module, and preprocessing module is used to pre-process the data that semiconductor manufacturing facility and technique acquire, and clustering processing module carries out clustering processing to the pretreated data of preprocessing module；Outlier detection unit carries out outlier detection to the data after clustering processing, obtains abnormal point set.
Description
Technical field
The present invention relates to semiconductor manufacturing facilities and process control technology field, and in particular to a kind of semiconductor manufacturing facility
With the control system of technique.
Background technology
In semiconductor manufacturing and production process, the exceptional quality problem of semiconductor devices is difficult and semiconductor manufacturing facility
Contact is directly established in behavior with technique, in the prior art, is typically only capable to after exception occurs in the quality of semiconductor devices by skill
The treatment measures that next step is formulated after art personnel inspection and judgement, check each time and judge that the exception of semiconductor devices is all one
A supposition, the iterative process verified, and technical staff only just consult when the quality of semiconductor devices is abnormal related
Semiconductor manufacturing facility and technique measurement data, find out questions and prospect, this pattern causes problems with：
(1) human factor influences big：Under above-mentioned pattern, the application method of the detection data of conductor manufacturing equipment and technique
It is determined by the well known experience of technical staff itself and judgement with effect, therefore causes the process results after anomalous event generation
Difference is very big, and also to there is different difference, especially experience each other shallower with the deeper engineering of experience by different engineers
Process results difference between teacher is very big；
(2) lack the study mechanism that links up：The processing of anomalous event each time is also an opportunity to study, can be at future
Reason dependent event provides help, but is supported due to lacking system, the historical data of anomalous event processing each time, including exception
Event phenomenon analysis, handling suggestion and implementation effect are dispersed in different spaces, cannot form the mechanism of continuous learning；
(3) it is long to expend the time for manual handle data：Technical staff may take up in the decision of a suitable control parameter
The time of a few hours, seriously reduce production capacity；
(4) there is no abnormal behaviour forecast function：Only just start when semi-conducting material and device go wrong and deviate
Problem detection pattern at the initial stage that cannot occur in problem, takes prevention, to avoid product quality problem.
Invention content
In view of the above-mentioned problems, the present invention provides a kind of control system of semiconductor manufacturing facility and technique.
The purpose of the present invention is realized using following technical scheme：
Provide a kind of control system of semiconductor manufacturing facility and technique, including data pre-processing unit, abnormal point
Survey unit, support vector machines training unit, intelligent monitoring unit and continuous learning unit；
Data pre-processing unit includes preprocessing module and clustering processing module, and preprocessing module is used for semiconductor manufacturing
Equipment and the data of technique acquisition are pre-processed, and clustering processing module clusters the pretreated data of preprocessing module
Processing；
Outlier detection unit carries out outlier detection to the data after clustering processing, obtains abnormal point set；
Abnormal point set is divided into training sample set and test sample collection by support vector machines training unit, and utilizes training sample
This set pair support vector machines is trained, and completes to support by checking the result of test sample set pair support vector machines verification
The training of vector machine is verified with test；If verification result is undesirable, support vector machines parameter is adjusted, then pass through iteration meter
It calculates, until verification result meets the requirements, exports final data training parameter to intelligent monitoring unit；
The intelligent monitoring unit is used to monitor using the final data training parameter of support vector machines training unit output
With control semiconductor manufacturing facility and technique；
The continuous learning unit is used to monitor that semiconductor manufacturing facility and technique are abnormal when intelligent monitoring unit
When behavior, newfound abnormal behaviour data and its front and back adjacent normal data are formed into new training sample data collection and are carried out
Mark, is trained support vector machines using new samples data set, exports new training parameter to intelligent monitoring unit, to intelligence
Monitoring unit carries out parameter update.
Preferably, the data that the semiconductor manufacturing facility and technique acquire are included in semi-conducting material and device manufactured
The macroparameter and micro-parameter that semiconductor manufacturing facility detects and controls in journey.
Preferably, the macroparameter includes temperature, pressure, flow, chemical composition parameter, and the micro-parameter includes object
The parameter of reason process and chemical process.
Beneficial effects of the present invention are：The mass data that the present invention acquires semiconductor manufacturing facility and technique is dug
Pick makes full use of the data resource to realize and carries out intelligent control to semiconductor equipment and technique, ensure that semi-conducting material and
Device production quality, higher efficiency is capable of when the quality of semi-conducting material and device is abnormal finds the original occurred extremely
Cause, and the mechanism with continuous learning solve the process results caused by technical staff's experience limits in the prior art
Difference；And it using the continuous learning function of the intelligence control system, also solves in the prior art due to a lack of coherent study
The loss of anomalous event process experience caused by mechanism；Anomalous event treatment effeciency is also improved, production capacity is improved.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the system structure schematic block diagram of an illustrative embodiment of the invention；
Fig. 2 is the structural schematic block diagram of the data pre-processing unit of an illustrative embodiment of the invention.
Reference numeral：
Data pre-processing unit 10, outlier detection unit 20, support vector machines training unit 30, intelligent monitoring unit
40, continuous learning unit 50, preprocessing module 100, clustering processing module 200.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, Fig. 2, a kind of control system of semiconductor manufacturing facility and technique provided in this embodiment, including data
Pretreatment unit 10, outlier detection unit 20, support vector machines training unit 30, intelligent monitoring unit 40 and continuous learning list
Member 50；
Data pre-processing unit 10 includes preprocessing module 100 and clustering processing module 200, and preprocessing module 100 is used for
The data acquired to semiconductor manufacturing facility and technique pre-process, and clustering processing module 200 locates preprocessing module 100 in advance
Data after reason carry out clustering processing；
Outlier detection unit 20 carries out outlier detection to the data after clustering processing, obtains abnormal point set；
Abnormal point set is divided into training sample set and test sample collection by support vector machines training unit 30, and utilizes training
Sample set is trained support vector machines, and completes to prop up by checking the result of test sample set pair support vector machines verification
The training and test for holding vector machine are verified；If verification result is undesirable, support vector machines parameter is adjusted, then pass through iteration
It calculates, until verification result meets the requirements, exports final data training parameter to intelligent monitoring unit 40；
The intelligent monitoring unit 40 is used to supervise using the final data training parameter of support vector machines training unit output
Survey and control semiconductor manufacturing facility and technique；
The continuous learning unit 50 is used to monitor that semiconductor manufacturing facility and technique occur when intelligent monitoring unit 40
When abnormal behaviour, newfound abnormal behaviour data and its front and back adjacent normal data are formed into new training sample data collection simultaneously
It is labeled, support vector machines is trained using new samples data set, export new training parameter to intelligent monitoring unit 40,
Parameter update is carried out to intelligent monitoring unit 40.
Preferably, the data that the semiconductor manufacturing facility and technique acquire are included in semi-conducting material and device manufactured
The macroparameter and micro-parameter that semiconductor manufacturing facility detects and controls in journey.
Preferably, the macroparameter includes temperature, pressure, flow, chemical composition parameter, and the micro-parameter includes object
The parameter of reason process and chemical process.
The mass data that the above embodiment of the present invention acquires semiconductor manufacturing facility and technique is excavated, and is made full use of
The data resource is realized carries out intelligent control to semiconductor equipment and technique, ensure that semi-conducting material and device production matter
Amount, higher efficiency is capable of when the quality of semi-conducting material and device is abnormal finds abnormal the reason of occurring, and has
The mechanism of continuous learning solves the process results difference caused by technical staff's experience limits in the prior art；And
Using the continuous learning function of the intelligence control system, also solve in the prior art due to a lack of caused by coherent study mechanism
The loss of anomalous event process experience；Anomalous event treatment effeciency is also improved, production capacity is improved.
In one embodiment, the data acquired to semiconductor manufacturing facility and technique pre-process, specially：
To there are the data of 0 value or negative value to pre-process, 0 value or negative value are replaced with into preset substitution value.
The present embodiment can prevent 0 value in data or negative value from being impacted to the processing of subsequent data clusters.
In one embodiment, clustering processing is carried out to 100 pretreated data of preprocessing module, specifically included：
(1) data of pretreated set period of time are extracted as a data set, X is set as, builds each data
Arest neighbors set：To the arbitrary data x in data set Xi, calculate xiWith the similarity of remainder data in data set X, according to similar
It spends ascending sequence to be ranked up, μ data are as x before selectingiArest neighbors, structure data xiArest neighbors setArest neighbors setDescribed in μ data be ranked up according to the ascending sequence of Euclidean distance, will sequence in ρ
The data of position are assigned a value of ρ；
(2) in first time iteration, select first unlabelled data in data set X as first cluster central point
O1, calculate remainder data and cluster central point O1Between similarity distance, according to similarity distance distribution principle to data xiDivided
With operation；
Wherein, similarity distance distribution principle is：If data xiIt is little with the similarity distance between the cluster central point that newly selects
In the similarity distance threshold value D of settingT, not to data xiIt is allocated operation；If data xiWith between the cluster central point that newly selects
Similarity distance is more than the similarity distance threshold value D of settingT, continue to calculate data xiWith the number in the arest neighbors set of the cluster central point
Similarity distance between, if data xiBetween a data in the arest neighbors set of the cluster central point, meet it is similar away from
From the similarity distance threshold value D more than settingT, then by data xiIt is assigned to the cluster central point, and is marked；
Wherein, set the calculation formula of the similarity distance between two data as：
In formula, D (xi,xl) indicate data xiWith xlBetween similarity distance,Indicate xiIn xlArest neighbors setIn position assignment, ifThen assignment Indicate xlIn xiArest neighbors setIn
Position assignment, ifThen assignment
(3) it enables iterations λ add 1, selects first unlabelled data in data set X as another cluster central point
Oλ+1, calculate remainder data and cluster central point Oλ+1Between similarity distance, if data xjIt is unmarked, it is distributed according to similarity distance
Principle is to data xjIt is allocated operation；If data xjIt is marked and can be assigned to cluster central point according to similarity distance distribution principle
Oλ+1, compare cluster central point, the cluster central point O of itself and original distributionλ+1Between similarity distance, select similarity distance bigger cluster in
Cluster is added in heart point；
(4) (3) are repeated until iterations λ reaches the threshold value of setting or all data have all been labeled.
The present embodiment sets the specific mechanism that pretreated data are carried out with clustering processing, which can be simply fast
The cluster of data is completed promptly, need not preassign the number of cluster, wherein similarity distance distribution principle is innovatively set,
When so that one or more of arest neighbors set only similar when data to cluster central point and to cluster central point data are similar, number
According to that could be located at the same cluster with cluster central point, thus relative to traditional clustering algorithm based on similarity, the present embodiment is adopted
With stronger restrictive condition, more suitable for detecting any shape cluster, cluster is efficiently and quality is high；Two are weighed in the prior art
When the distance between a data, most common metric form is absolute distance, such as Euclidean distance, manhatton distance.This implementation
Example innovatively sets a kind of new similarity distance measure formulas, the calculated similarity distance of the formula relative to absolutely away from
From the variable density in data set can be adapted to automatically so that cluster operation can adapt to the cluster in different densities and scale.
Wherein, the similarity between two data may be used existing similarity function and be calculated, for example, by using remaining
String similitude, Pearson correlation coefficient etc. are measured.
In a preferred embodiment, set the calculation formula of the similarity between two data as：
In formula, S (xi,xj) indicate data xiWith data xjBetween similarity, xiαIndicate data xiα dimension attribute values,
xjαIndicate data xjα dimension attribute values, β be data dimension, f1(xiα,xjα) be setting be minimized function, work as xiα≤
xjα, f1(xiα,xjα)=xiα, work as xiα>xjα, f1(xiα,xjα)=xjα；f2(xiα,xjα) be setting be maximized function, work as xiα<
xjα, f2(xiα,xjα)=xjα, work as xiα≥xjα, f2(xiα,xjα)=xiα。
The present embodiment innovatively sets the calculation formula of similarity, it is proposed that a kind of new measuring similarity mechanism,
The similarity obtained by the calculation formula weighs the similitude between two data, enable to the calculating of similarity not by
Dimension to data influences, to avoid any unnecessary data conversion so that simpler to the cluster of data quick.
In one embodiment, outlier detection is carried out to the data after clustering processing, specifically included：
(1) if there are the number threshold value that the data amount check of a cluster is less than setting after cluster, which is considered as abnormal clusters,
All data in abnormal clusters are considered as abnormal data；
(2) similarity distance between the cluster central point of other normal clusters and the cluster central point of abnormal clusters is calculated；
(3) it is set if being not more than there are the similarity distance between the cluster central point and the cluster central point of normal clusters of an abnormal clusters
Fixed cluster similarity distance threshold value then using the normal clusters as cluster to be detected, and is detected using the data of the abnormal clusters to be detected
Data in cluster, if the data acquisition system of the abnormal clusters is Xδ={ x1,x2,..,x0, the data in cluster to be detectedUnder satisfaction
When row exceptional condition, by dataIt is considered as abnormal data：
In formula,For dataArest neighbors set,For data X0Arest neighbors set, xθ∈Xδ,
It indicatesWithIntersection in data amount check, M be setting number threshold value.
Due to comparatively loose and more lonely relative to other data between the data in the smaller cluster of scale
It is vertical, therefore the data in the cluster of scale is smaller are usually considered as abnormal data in the prior art.Based on this, the present embodiment is to cluster
Data that treated carry out outlier detection, therefrom innovatively propose for whether detection data to be abnormal abnormal item
Part, the exceptional condition judge the data according to the data intersection quantity of the arest neighbors set between data and the data of abnormal clusters
Whether it is abnormal data, has certain accuracy of detection, detection mode is simple and effective and is not influenced by data dimension.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. the control system of a kind of semiconductor manufacturing facility and technique, characterized in that including data pre-processing unit, abnormal point
Survey unit, support vector machines training unit, intelligent monitoring unit and continuous learning unit；
Data pre-processing unit includes preprocessing module and clustering processing module, and preprocessing module is used for semiconductor manufacturing facility
It is pre-processed with the data of technique acquisition, clustering processing module carries out at cluster the pretreated data of preprocessing module
Reason；
Outlier detection unit carries out outlier detection to the data after clustering processing, obtains abnormal point set；
Abnormal point set is divided into training sample set and test sample collection by support vector machines training unit, and utilizes training sample set
Support vector machines is trained, and supporting vector is completed by checking the result of test sample set pair support vector machines verification
The training of machine is verified with test；If verification result is undesirable, support vector machines parameter is adjusted, then by iterating to calculate,
Until verification result meets the requirements, final data training parameter is exported to intelligent monitoring unit；
The intelligent monitoring unit is used for the monitoring of final data training parameter and control using the output of support vector machines training unit
Semiconductor manufacturing facility processed and technique；
The continuous learning unit is used to monitor that semiconductor manufacturing facility and technique are abnormal behavior when intelligent monitoring unit
When, newfound abnormal behaviour data and its front and back adjacent normal data are formed into new training sample data collection and are gone forward side by side rower
Note, is trained support vector machines using new samples data set, exports new training parameter to intelligent monitoring unit, to intelligent prison
It controls unit and carries out parameter update.
2. the control system of a kind of semiconductor manufacturing facility and technique according to claim 1, characterized in that described partly to lead
System manufacturing apparatus and the data of technique acquisition are included in semi-conducting material and device manufacturing processes, semiconductor manufacturing facility detection
With the macroparameter and micro-parameter of control.
3. the control system of a kind of semiconductor manufacturing facility and technique according to claim 2, characterized in that the macroscopic view
Parameter includes temperature, pressure, flow, chemical composition parameter, and the micro-parameter includes the parameter of physical process and chemical process.
4. according to a kind of control system of semiconductor manufacturing facility and technique of claim 1-3 any one of them, characterized in that
The data acquired to semiconductor manufacturing facility and technique pre-process, specially：To there are the data of 0 value or negative value into
Row pretreatment, preset substitution value is replaced with by 0 value or negative value.
5. the control system of a kind of semiconductor manufacturing facility and technique according to claim 4, characterized in that pretreatment
The pretreated data of module carry out clustering processing, specifically include：
(1) data of pretreated set period of time are extracted as a data set, X is set as, builds the nearest of each data
Neighbour's set：To the arbitrary data x in data set Xi, calculate xiWith the similarity of remainder data in data set X, according to similarity by
Small to be ranked up to big sequence, μ data are as x before selectingiArest neighbors, structure data xiArest neighbors setMost
Neighbour gathersDescribed in μ data be ranked up according to the ascending sequence of Euclidean distance, will sort the ρ position
Data be assigned a value of ρ；
(2) in first time iteration, select first unlabelled data in data set X as first cluster central point O1, meter
Calculate remainder data and cluster central point O1Between similarity distance, according to similarity distance distribution principle to data xiIt is allocated behaviour
Make；
Wherein, similarity distance distribution principle is：If data xiWith the similarity distance between the cluster central point that newly selects no more than setting
Similarity distance threshold value DT, not to data xiIt is allocated operation；If data xiBetween the cluster central point newly selected it is similar away from
From the similarity distance threshold value D more than settingT, continue to calculate data xiBetween the data in the arest neighbors set of the cluster central point
Similarity distance, if data xiBetween a data in the arest neighbors set of the cluster central point, meets similarity distance and be more than
The similarity distance threshold value D of settingT, then by data xiIt is assigned to the cluster central point, and is marked；
(3) it enables iterations λ add 1, selects first unlabelled data in data set X as another cluster central point Oλ+1,
Calculate remainder data and cluster central point Oλ+1Between similarity distance, if data xjIt is unmarked, according to similarity distance distribution principle
To data xjIt is allocated operation；If data xjIt is marked and can be assigned to cluster central point O according to similarity distance distribution principleλ+1,
Compare cluster central point, the cluster central point O of itself and original distributionλ+1Between similarity distance, select similarity distance bigger cluster central point
Cluster is added；
(4) (3) are repeated until iterations λ reaches the threshold value of setting or all data have all been labeled.
6. the control system of a kind of semiconductor manufacturing facility and technique according to claim 5, characterized in that setting two
The calculation formula of similarity distance between data is：
In formula, D (xi,xl) indicate data xiWith xlBetween similarity distance,Indicate xiIn xlArest neighbors setIn
Position assignment, ifThen assignment Indicate xlIn xiArest neighbors setIn position assign
Value, ifThen assignment
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810284488.3A CN108510615A (en) | 2018-04-02 | 2018-04-02 | A kind of control system of semiconductor manufacturing facility and technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810284488.3A CN108510615A (en) | 2018-04-02 | 2018-04-02 | A kind of control system of semiconductor manufacturing facility and technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108510615A true CN108510615A (en) | 2018-09-07 |
Family
ID=63379974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810284488.3A Pending CN108510615A (en) | 2018-04-02 | 2018-04-02 | A kind of control system of semiconductor manufacturing facility and technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108510615A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910021A (en) * | 2019-11-26 | 2020-03-24 | 上海华力集成电路制造有限公司 | Method for monitoring online defects based on support vector machine |
| CN112801497A (en) * | 2021-01-26 | 2021-05-14 | 上海华力微电子有限公司 | Anomaly detection method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561878A (en) * | 2009-05-31 | 2009-10-21 | 河海大学 | Unsupervised anomaly detection method and system based on improved CURE clustering algorithm |
| CN103020642A (en) * | 2012-10-08 | 2013-04-03 | 江苏省环境监测中心 | Water environment monitoring and quality-control data analysis method |
| CN104217015A (en) * | 2014-09-22 | 2014-12-17 | 西安理工大学 | Hierarchical clustering method based on mutual shared nearest neighbors |
| CN105791051A (en) * | 2016-03-25 | 2016-07-20 | 中国地质大学（武汉） | WSN (Wireless Sensor Network) abnormity detection method and system based on artificial immunization and k-means clustering |
| CN106483942A (en) * | 2016-09-20 | 2017-03-08 | 广东家易科技有限公司 | The intelligence control system of a kind of semiconductor manufacturing facility and technique and method |
| CN107528823A (en) * | 2017-07-03 | 2017-12-29 | 中山大学 | A kind of network anomaly detection method based on improved K Means clustering algorithms |
-
2018
- 2018-04-02 CN CN201810284488.3A patent/CN108510615A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561878A (en) * | 2009-05-31 | 2009-10-21 | 河海大学 | Unsupervised anomaly detection method and system based on improved CURE clustering algorithm |
| CN103020642A (en) * | 2012-10-08 | 2013-04-03 | 江苏省环境监测中心 | Water environment monitoring and quality-control data analysis method |
| CN104217015A (en) * | 2014-09-22 | 2014-12-17 | 西安理工大学 | Hierarchical clustering method based on mutual shared nearest neighbors |
| CN105791051A (en) * | 2016-03-25 | 2016-07-20 | 中国地质大学（武汉） | WSN (Wireless Sensor Network) abnormity detection method and system based on artificial immunization and k-means clustering |
| CN106483942A (en) * | 2016-09-20 | 2017-03-08 | 广东家易科技有限公司 | The intelligence control system of a kind of semiconductor manufacturing facility and technique and method |
| CN107528823A (en) * | 2017-07-03 | 2017-12-29 | 中山大学 | A kind of network anomaly detection method based on improved K Means clustering algorithms |
Non-Patent Citations (1)
| Title |
|---|
| 费欢，李光辉: "《基于K-means聚类的WSN异常数据检测算法》", 《计算机工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910021A (en) * | 2019-11-26 | 2020-03-24 | 上海华力集成电路制造有限公司 | Method for monitoring online defects based on support vector machine |
| CN112801497A (en) * | 2021-01-26 | 2021-05-14 | 上海华力微电子有限公司 | Anomaly detection method and device |
| CN112801497B (en) * | 2021-01-26 | 2024-04-30 | 上海华力微电子有限公司 | Abnormality detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102393882B (en) | Method for monitoring and diagnosing indoor air quality (IAQ) sensor on line | |
| CN106483942B (en) | A kind of intelligence control system and method for semiconductor manufacturing facility and technique | |
| CN109389145B (en) | Electric energy meter manufacturer evaluation method based on metering big data clustering model | |
| CN105468907B (en) | One kind accelerates degraded data validity check and model selection method | |
| CN108536971A (en) | A kind of Structural Damage Identification based on Bayesian model | |
| CN104221475B (en) | Fault detection, localization and performance monitoring of photosensors for lighting controls | |
| CN108520267B (en) | Hydrological telemetering data anomaly detection method based on space-time characteristics | |
| CN110400231B (en) | Failure rate estimation method for electric energy metering equipment based on weighted nonlinear Bayes | |
| CN104166718B (en) | A kind of bad data detection and identification method suitable for bulk power grid | |
| CN107679089A (en) | A kind of cleaning method for electric power sensing data, device and system | |
| CN116400126B (en) | Low-voltage power box with data processing system | |
| CN108510615A (en) | A kind of control system of semiconductor manufacturing facility and technique | |
| CN106595788B (en) | Based on the modified large pumping station flow monitoring method of Multi-parameter coupling | |
| CN113340598A (en) | Rolling bearing intelligent fault diagnosis method based on regularization sparse model | |
| CN108154271A (en) | A kind of surface air temperature method of quality control based on spatial coherence and surface fitting | |
| CN109190184A (en) | A kind of heating system historical data preprocess method | |
| CN113076834A (en) | Rotating machine fault information processing method, processing system, processing terminal, and medium | |
| CN109617526A (en) | A method of photovoltaic power generation array fault diagnosis and classification based on wavelet multiresolution analysis and SVM | |
| CN106407555A (en) | Accelerated degradation data analysis method based on principle of invariance of accelerating factor | |
| CN108470699A (en) | A kind of intelligence control system of semiconductor manufacturing facility and technique | |
| CN113486950B (en) | Intelligent pipe network water leakage detection method and system | |
| CN110096723B (en) | High-voltage switch cabinet insulation state analysis method based on operation and maintenance detection big data | |
| CN112780953B (en) | Independent metering area pipe network leakage detection method based on mode detection | |
| CN109375143A (en) | A kind of method of determining intelligent electric energy meter remaining life | |
| CN106444578B (en) | A kind of fault detection method based on isomery geodesic curve distance SVDD |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180907 |