CN108594776A - A kind of GaAs quality conformance control method and system based on critical process - Google Patents
A kind of GaAs quality conformance control method and system based on critical process Download PDFInfo
- Publication number
- CN108594776A CN108594776A CN201810356299.2A CN201810356299A CN108594776A CN 108594776 A CN108594776 A CN 108594776A CN 201810356299 A CN201810356299 A CN 201810356299A CN 108594776 A CN108594776 A CN 108594776A
- Authority
- CN
- China
- Prior art keywords
- data
- critical
- parameters
- sample
- gaas
- 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 173
- 229910001218 Gallium arsenide Inorganic materials 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 239000006227 byproduct Substances 0.000 claims abstract description 4
- 239000000047 product Substances 0.000 claims description 16
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000000750 progressive effect Effects 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 23
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000000151 deposition Methods 0.000 description 18
- 230000008021 deposition Effects 0.000 description 17
- 238000002474 experimental method Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000005137 deposition process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 239000013049 sediment Substances 0.000 description 3
- 238000004886 process control Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012936 correction and preventive action Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011058 failure modes and effects analysis Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31395—Process management, specification, process and production data, middle level
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
A kind of GaAs quality conformance control method based on critical process, using steps are as follows, step 1:By the correlation of parameters of technique process and process results data, quantify the parameters of technique process weight for critical process;Step 2:Processing quality consistency model is built up using artificial neural network to the procedure parameter of critical process;Step 3:The process results data that critical process is completed by product are used as input, and the parameters of technique process and process results data of this procedure are predicted using processing quality consistency model.The present invention can carry out comprehensive analysis to multiple parameters, and data-handling capacity is powerful, as a result more precisely;Can before manufacture look-ahead production result and fed back, ensure production quality, reduce production risk;Can be forward-looking according to the suitable technological parameter of expected production prediction of result, simplify production technology.
Description
Technical field
The present invention relates to control of product quality technical fields, and in particular to the GaAs quality conformance based on critical process
Control method and system.
Background technology
GaAs microwave device and integrated circuit production are with complex technical process, Multi-varieties and Small-batch Production, consistency
It is required that the features such as high, product Lead Time is short and credit rating requirement is high.
It is at present to pass through reality to the means of Process Quality Control in GaAs microwave device and integrated circuit production process
The method for testing result deduction, substantially with the following method:
1. orthogonal experiment method, basic thought is the influence relationship by experimental verification correlation factor (parameters of technique process).
Since the factor is excessive, if tested to all changes of each factor, experimental amount is very huge, and orthogonal experiment method is logical
Cross the method for designing effective orthogonal arrage significantly and reducing test number (TN) and experiment Feasible degree can't be reduced.
2.PFMEA (processing procedure failure modes and effects analysis), basic step is as follows,
(1) it determines and technique productions or the relevant potential failure mode of manufacture course of products and cause;
(2) potential impact of the evaluation failure to product quality and customer;
(3) process control variable for reducing failure generation or failure condition is found out, and formulates Corrective and preventive action;
(4) potential failure mode hierarchical table is worked out, it is ensured that serious failure mode obtains priority acccess control;
(5) performance of tracing control measure updates failure mode hierarchical table.
The prior art is very efficiently and stable when debugging test to new producing line, but in GaAs microwave device sum aggregate
After the long-term operation of circuit production line, a large amount of technical process data and process results data are produced, are utilizing these numbers
Then exist in terms of according to being advanced optimized to technique it is clearly disadvantageous, above two method be suitable for experiment and theoretical side.
Invention content
In view of the deficiencies of the prior art, the present invention proposes one kind to being produced using GaAs microwave device and integrated circuit
The critical process of journey influences the emphasis technical process of product quality by studying GaAs production line, finds critical control point, grind
Study carefully the correlation between technical process operating parameter and process test result parameter, is built on this basis according to practical working procedure feature
The mathematical model of vertical processing quality consistency control, crosses the parameters of technique process of model adjustment critical process, reduces processing quality
Deviation to achieve the purpose that process optimization, effectively improve the CPK and CA of process results data, improve the ability of process
Index, specific technical solution are as follows:
A kind of GaAs quality conformance control method based on critical process, using steps are as follows,
Step 1:By the correlation of parameters of technique process and process results data, quantify the technique mistake for critical process
Journey parameters weighting;
Step 2:Processing quality consistency model is built up using artificial neural network to the procedure parameter of critical process;
Step 3:The process results data that critical process is completed by product are used as input, consistent using processing quality
The parameters of technique process and process results data of this procedure of property model prediction.
To better implement the present invention, further for:
Also set up step 4, product after processing is completed, by the parameters of technique process of prediction and process results data and reality
The parameters of technique process and process results comparing, error in judgement on border, readjust processing quality consistency Controlling model
Parameter reaches the ability of self study.
The step 2 specifically,
2.1 carry out dimensionality reduction according to principal component analysis (PCA) method before modeling to parameters of technique process;
The control parameter of 2.2 pairs of critical processes does normalized, and formula is as follows:
Wherein x is to need normalized sample, xmaxFor the maximum value of all samples, xminFor the minimum value of all samples, y
For the output valve for normalizing later;
2.3 use reduced data as training sample, and clustering processing is carried out to data, and the scale of cluster passes through European
Range estimation, cluster formula are as follows:
WhereinIt is class centerEach component, x is sample, d be sample x distance centers it is European away from
From;
Need progressive alternate that could finally converge to center in cluster process, the formula per single-step iteration centering is as follows
It is shown:
Wherein N is the number of samples of the i-th class during current iteration, ciIndicate the i-th class;
The artificial neural network is radial base neural net, and following formula is used when solving, solves wiIt can build
Vertical neural network;
WhereinFor cluster centre, x1,x2,…,xnFor sample, S1(·),S2(·),…,Sl() is base
Function, w1,w2,…,wlFor neural network weight, y1,y2,…,yiFor the corresponding output of sample.
A kind of GaAs quality conformance control system based on critical process, is provided with sample data library module, is used for
Collect historical process procedure parameter, the historical process result data of critical process;
Processing quality consistency model carries out calculating analysis for the data to critical process, predicts product quality;
Model predictive error module, for prediction result data to be compared with actual result data, error in judgement is big
It is small;
Model parameter module is adjusted, for after prediction result data and actual result data error are greater than the set value, adjusting
Whole processing quality consistency model data, reach the ability of self study.
Beneficial effects of the present invention are:GaAs production line is relied on, GaAs microwave device and integrated circuit life are studied
The critical process of producing line is excavated critical process process operation parameter by the existing a large amount of creation data of production line and is examined with technique
The correlation between result parameter is tested, the control of processing quality consistency is established by the characteristic parameter of critical process on this basis
Mathematical model, processing quality consistency is improved by mathematical model;
On the basis of existing experiment and theoretical method analysis, GaAs microwave device and integrated electricity are utilized
The mass data formed after the production line longtime running of road advanced optimizes technique, in turn by data mining model by model
Reduce the deviation of processing quality;
The present invention can carry out comprehensive analysis to multiple parameters, and data-handling capacity is powerful, as a result more precisely;It can be
The result of the preceding look-ahead production of production is simultaneously fed back, and is ensured the quality of production, is reduced production risk;It can be according to expection
The suitable technological parameter of production prediction of result, it is forward-looking, simplify production technology;To the requirement of Field Force's know-how
Low, automatic running is not necessarily to overstaffed participation, and operating cost is cheap, the application and popularization of the present invention being convenient for.
Description of the drawings
Fig. 1 is flowage structure schematic diagram in the present invention;
Fig. 2 is the structural schematic diagram of neural network in the present invention;
Fig. 3 is the structural schematic diagram of control module in the present invention.
Specific implementation mode
The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
The dielectric deposition of GaAs production line is the vital procedure of GaAs production line, passes through dielectric deposition work
Sequence ensures the thickness of medium finally in the range of properties of product require.Use effective, high quality a prediction model
The consistency of the final lifting process quality of parameters of technique process by predicting and controlling dielectric deposition process.Key procedure is situated between
Matter depositing operation implementing process quality conformance control technology, procedure technology Capability index Cpk are promoted.
As shown in Figure 1 to Figure 3:A kind of GaAs quality conformance control method based on critical process, such as using step
Under,
Step 1:By the correlation of parameters of technique process and process results data, quantify the technique mistake for critical process
Journey parameters weighting;
Specially historical process procedure parameter, the historical process result data of trapping medium deposition critical process.History work
Skill procedure parameter and historical process result data are stored in equipment control computer and filing database with document form,
Data collection program parses document, and semi-structured data format conversion is arrived original sample for storage after the data format after format
In database.The parameters of technique process of dielectric deposition process includes temperature, pressure, flow, power, deposition time, deposition location.
The process results data of preceding working procedure include deposit 1 thickness of front position, deposit 2 thickness of front position, deposit 3 thickness of front position, form sediment
Product 4 thickness of front position, technological requirement is expectation thickness.Compile the data item of rear model altogether and include temperature, pressure, flow,
Power, deposition time, deposition location 1, deposition location 2, deposition location 3, deposition location 4, product deposit 1 thickness of front position, form sediment
Product 2 thickness of front position, deposit 3 thickness of front position, deposit 4 thickness of front position.
Step 2:Processing quality consistency model is built up using artificial neural network to the procedure parameter of critical process;
2.1 carry out dimensionality reduction according to principal component analysis (PCA) method before modeling to parameters of technique process;
The control parameter of 2.2 pairs of critical processes does normalized, and formula is as follows:
Wherein x is to need normalized sample, xmaxFor the maximum value of all samples, xminFor the minimum value of all samples, y
For the output valve for normalizing later;
2.3 use reduced data as training sample, and clustering processing is carried out to data, and the scale of cluster passes through European
Range estimation, cluster formula are as follows:
WhereinIt is class centerEach component, x is sample, d be sample x distance centers it is European away from
From;
Need progressive alternate that could finally converge to center in cluster process, the formula per single-step iteration centering is as follows
It is shown:
Wherein N is the number of samples of the i-th class during current iteration, ciIndicate the i-th class;
The artificial neural network is radial base neural net, and following formula is used when solving, solves wiIt can build
Vertical neural network;
WhereinFor cluster centre, x1,x2,…,xnFor sample, S1(·),S2(·),…,Sl() is base
Function, w1,w2,…,wlFor neural network weight, y1,y2,…,yiFor the corresponding output of sample.
In the present embodiment, wherein by deposition time temperature, pressure, flow, power, deposition location one, deposition location two,
Deposition location three, deposition location four, deposit one thickness of front position, deposit two thickness of front position, deposit three thickness of front position, deposit
Parameter of four thickness of front position as input layer.By position after position thickness, deposit after position thickness, deposit after the deposit of prediction
Output of the position thickness as output layer after thickness, deposit.
Sample is modeled by radial base neural net RBFNN, total number of samples is according to sharing 2000, wherein using
1600 sample datas carry out model training, remaining 400 sample data is tested.Input layer 13 nodes, middle layers
2109,4 nodes of output layer.
Step 3:The process results data that critical process is completed by product are used as input, consistent using processing quality
The parameters of technique process and process results data of this procedure of property model prediction.
Step 4:Product after processing is completed, by the parameters of technique process of prediction and process results data and actual work
Skill procedure parameter and process results comparing, error in judgement, readjust the parameter of processing quality consistency Controlling model, reach
To the ability of self study.
Processing quality consistency controls application system automatic acquisition product before GaAs dielectric deposition process is started to work
Preceding road sequence process results data, deposit one thickness of front position, deposit two thickness of front position, deposit three thickness of front position, form sediment
Product four thickness of front position predicts deposition time by processing quality consistency model, by parameters of technique process after prediction,
The deposition time of prediction in setting to system and starts to execute processing.The processing quality consistency control application after process finishing
System obtains process results data automatically, and by model predictive error module error in judgement, it is consistent to readjust processing quality
The parameter of property Controlling model, reaches the ability of self study.
A kind of GaAs quality conformance control system based on critical process, is provided with sample data library module, is used for
Collect historical process procedure parameter, the historical process result data of critical process;Processing quality consistency model, for key
The data of process carry out calculating analysis, predict product quality;Model predictive error module is used for prediction result data and reality
Border result data is compared, error in judgement size;Model parameter module is adjusted, in prediction result data and actual result
After data error is greater than the set value, adjusting process quality conformance model data reaches the ability of self study.
Claims (4)
1. a kind of GaAs quality conformance control method based on critical process, which is characterized in that using steps are as follows,
Step 1:By the correlation of parameters of technique process and process results data, quantify the technical process ginseng for critical process
Number weight;
Step 2:Processing quality consistency model is built up using artificial neural network to the procedure parameter of critical process;
Step 3:The process results data that critical process is completed by product are used as input, utilize processing quality consistency mould
Type predicts the parameters of technique process and process results data of this procedure.
2. the GaAs quality conformance control method based on critical process according to claim 1, it is characterised in that:Also set
Set step 4, product after processing is completed, by the parameters of technique process of prediction and process results data and actual technical process
Parameter and process results comparing, error in judgement, readjust the parameter of processing quality consistency Controlling model, reach self-study
The ability of habit.
3. the GaAs quality conformance control method based on critical process according to claim 1, it is characterised in that:It is described
Step 2 specifically,
2.1 carry out dimensionality reduction according to principal component analysis (PCA) method before modeling to parameters of technique process;
The control parameter of 2.2 pairs of critical processes does normalized, and formula is as follows:
Wherein x is to need normalized sample, xmaxFor the maximum value of all samples, xminFor the minimum value of all samples, y is to return
One changes later output valve;
2.3 use reduced data as training sample, carry out clustering processing to data, the scale of cluster passes through Euclidean distance
Judgement, cluster formula are as follows:
WhereinIt is class centerEach component, x is sample, and d is the Euclidean distance of sample x distance centers;
Need progressive alternate that could finally converge to center in cluster process, per the following institute of formula of single-step iteration centering
Show:
Wherein N is the number of samples of the i-th class during current iteration, ciIndicate the i-th class;
The artificial neural network is radial base neural net, and following formula is used when solving, solves wiNerve can be established
Network;
WhereinFor cluster centre, x1,x2,…,xnFor sample, S1(·),S2(·),…,Sl() is basic function,
w1,w2,…,wlFor neural network weight, y1,y2,…,yiFor the corresponding output of sample.
4. a kind of GaAs quality conformance control system based on critical process, it is characterised in that:It is provided with sample database
Module, historical process procedure parameter, historical process result data for collecting critical process;
Processing quality consistency model carries out calculating analysis for the data to critical process, predicts product quality;
Model predictive error module, for prediction result data to be compared with actual result data, error in judgement size;
Model parameter module is adjusted, for after prediction result data and actual result data error are greater than the set value, adjusting work
Skill quality conformance model data, reaches the ability of self study.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810356299.2A CN108594776A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs quality conformance control method and system based on critical process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810356299.2A CN108594776A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs quality conformance control method and system based on critical process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108594776A true CN108594776A (en) | 2018-09-28 |
Family
ID=63613275
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810356299.2A Pending CN108594776A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs quality conformance control method and system based on critical process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108594776A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110096041A (en) * | 2019-05-07 | 2019-08-06 | 中江联合(北京)科技有限公司 | Filter consistency method of quality control based on resonator assembly technology |
CN111209609A (en) * | 2018-11-21 | 2020-05-29 | 长鑫存储技术有限公司 | Production parameter determination method, device, system, storage medium and electronic equipment |
WO2022141759A1 (en) * | 2020-12-31 | 2022-07-07 | 杭州富加镓业科技有限公司 | Gallium oxide quality prediction method based on deep learning and czochralski method, and preparation method and system |
CN115258323A (en) * | 2021-04-29 | 2022-11-01 | 北京小米移动软件有限公司 | Film tearing control method and device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method using processing parameter to predict control indexes during tobacco processing procedures |
CN103676868A (en) * | 2013-12-09 | 2014-03-26 | 华南理工大学 | Automatic monitoring and intelligent analyzing system used in FPC manufacturing critical process |
CN106022636A (en) * | 2016-05-30 | 2016-10-12 | 北京航空航天大学 | Astronavigation component PID implementation effect evaluation method |
CN106950933A (en) * | 2017-05-02 | 2017-07-14 | 中江联合(北京)科技有限公司 | Quality conformance control method and device, computer-readable storage medium |
CN107042234A (en) * | 2017-03-15 | 2017-08-15 | 中冶华天工程技术有限公司 | The intelligent production line and production method gathered based on bar whole process big data |
-
2018
- 2018-04-19 CN CN201810356299.2A patent/CN108594776A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567812A (en) * | 2012-01-09 | 2012-07-11 | 红云红河烟草(集团)有限责任公司 | Method using processing parameter to predict control indexes during tobacco processing procedures |
CN103676868A (en) * | 2013-12-09 | 2014-03-26 | 华南理工大学 | Automatic monitoring and intelligent analyzing system used in FPC manufacturing critical process |
CN106022636A (en) * | 2016-05-30 | 2016-10-12 | 北京航空航天大学 | Astronavigation component PID implementation effect evaluation method |
CN107042234A (en) * | 2017-03-15 | 2017-08-15 | 中冶华天工程技术有限公司 | The intelligent production line and production method gathered based on bar whole process big data |
CN106950933A (en) * | 2017-05-02 | 2017-07-14 | 中江联合(北京)科技有限公司 | Quality conformance control method and device, computer-readable storage medium |
Non-Patent Citations (5)
Title |
---|
KUNLIN ZHOU, RONGSHENG GUO: "Research on process monitoring method based on SPC and PCA technology", 《CONTROL AND DECISION CONFERENCE (CCDC),2011 CHINESE》 * |
MATLAB中文论坛: "《MATLAB神经网络的30个案例分析》", 30 April 2020 * |
商庆杰等: "实施统计过程控制(SPC)中常见问题的探讨", 《现代制造技术与装备》 * |
李保第等: "SPC参数控制限和规范限的定义", 《电子工艺技术》 * |
钟昕怡: "多品种小批量生产中关键工序识别与质量控制研究及应用", 《万方数据库》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111209609A (en) * | 2018-11-21 | 2020-05-29 | 长鑫存储技术有限公司 | Production parameter determination method, device, system, storage medium and electronic equipment |
CN110096041A (en) * | 2019-05-07 | 2019-08-06 | 中江联合(北京)科技有限公司 | Filter consistency method of quality control based on resonator assembly technology |
WO2022141759A1 (en) * | 2020-12-31 | 2022-07-07 | 杭州富加镓业科技有限公司 | Gallium oxide quality prediction method based on deep learning and czochralski method, and preparation method and system |
CN115258323A (en) * | 2021-04-29 | 2022-11-01 | 北京小米移动软件有限公司 | Film tearing control method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108594776A (en) | A kind of GaAs quality conformance control method and system based on critical process | |
CN108520357B (en) | Method and device for judging line loss abnormality reason and server | |
CN111861774B (en) | Oil reservoir production machine learning method based on parallel agent model | |
CN103745273B (en) | Semiconductor fabrication process multi-performance prediction method | |
CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
CN111476435B (en) | Charging pile load prediction method based on density peak value | |
CN105023042A (en) | User electricity stealing suspicion analyzing device and method based on big data neural network algorithm | |
CN103676881A (en) | Dynamic bottleneck analytical method of semiconductor production line | |
CN108287317A (en) | Power of battery prediction model generation method and system, power forecasting method and system | |
CN109740661A (en) | A kind of well fluid level adaptive forecasting method based on fuzzy evaluation | |
CN108520325A (en) | A kind of integral life prediction technique based on acceleration degraded data under changeable environment | |
CN108985577B (en) | Reservoir group real-time flood control dispatching significant reservoir intelligent identification method based on inference machine | |
CN108415393A (en) | A kind of GaAs product quality consistency control method and system | |
CN103983919A (en) | Battery life prediction method based on GM (1, N) gray model | |
CN110334879A (en) | Power grid bus reactive load forecasting method and device | |
CN110942084A (en) | Loss reduction measure making method based on synchronous line loss abnormity identification | |
CN112633556A (en) | Short-term power load prediction method based on hybrid model | |
CN110059938B (en) | Power distribution network planning method based on association rule driving | |
CN104794366A (en) | Full-factor experiment analysis method for oil nozzle abrasive flow machining | |
CN115271154B (en) | Nonlinear regression flood element prediction method based on polynomial and partial least square coupling | |
CN113821975B (en) | Method and system for predicting performance decay of fuel cell | |
Zhu et al. | Selection of criteria for multi-criteria decision making of reservoir flood control operation | |
CN114971092A (en) | Method and device for predicting concrete consumption of main control building of transformer substation | |
CN106570618A (en) | Cluster analysis and neutral network-based load simultaneous factor prediction method | |
Kong et al. | HACScale: Hardware-aware compound scaling for resource-efficient DNNs |
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 |
Application publication date: 20180928 |
|
RJ01 | Rejection of invention patent application after publication |