CN108415393A - A kind of GaAs product quality consistency control method and system - Google Patents
A kind of GaAs product quality consistency control method and system Download PDFInfo
- Publication number
- CN108415393A CN108415393A CN201810355693.4A CN201810355693A CN108415393A CN 108415393 A CN108415393 A CN 108415393A CN 201810355693 A CN201810355693 A CN 201810355693A CN 108415393 A CN108415393 A CN 108415393A
- Authority
- CN
- China
- Prior art keywords
- data
- product quality
- product
- neural network
- 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 111
- 229910001218 Gallium arsenide Inorganic materials 0.000 title claims abstract description 22
- 239000000047 product Substances 0.000 claims abstract description 83
- 230000008569 process Effects 0.000 claims abstract description 78
- 238000004519 manufacturing process Methods 0.000 claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 238000013178 mathematical model Methods 0.000 claims abstract description 9
- 239000007795 chemical reaction product Substances 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims 1
- 238000000151 deposition Methods 0.000 description 7
- 230000008021 deposition Effects 0.000 description 7
- 238000005245 sintering Methods 0.000 description 7
- 238000004544 sputter deposition Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000002946 Total quality control Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000001259 photo etching Methods 0.000 description 3
- 238000003326 Quality management system Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005530 etching Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010849 ion bombardment Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000012360 testing method 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
- G05B2219/32—Operator till task planning
- G05B2219/32368—Quality control
-
- 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of GaAs product quality consistency control method, is as follows:Step 1:Historical process data is arranged to form archetype sample database;Step 2:Mathematical modeling is carried out using artificial neural network to the process data in production process;Step 3:Product quality forecast, one of product sequence is specially often completed, end product quality prediction is carried out using mathematical model by the process data to the procedure, after the completion of product, the real data of product is compared with prediction result data, generates product quality models report.
Description
Technical field
The present invention relates to control of product quality technical fields, and in particular to GaAs product quality consistency 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.The product quality at existing GaAs Microwave Component Production scene
Final administration base be " total quality control " method.
The Fei Genbaomu of General Electric Company in 1961 is published《Total quality control》One book is emphasized to execute quality
Function is the responsibility of company personnel, it should which making personnel all has the concept of quality and undertake the responsibility of quality.By
Many country's utilization, summary and understanding in practice for many years, the meaning of total quality control, content and method are all richer
It is rich, substantial and perfect, a new, complete subject is formd, and form quality management system, newest fruits are international marks
Standard dissolves the military quality standard of ISO9001 family of standards and China of version《Quality management system requirement》(GJB9001A-2001).
Process management is carried out to product formation course through realizing, has accomplished to be defined in advance, has had record in thing, can trace afterwards.Together
When by carrying out control to product quality to the SPC of process results data analysis.
In recent years, with the large-scale application of the technologies such as cloud computing, Internet of Things, data mining, intelligent robot, the U.S.,
The country such as Europe takes the lead in proposing the intelligent Manufacturing Technology characterized by information physical merges, conventionally manufactured strong headed by Germany
State is determined as the fourth industrial revolution (industry 4.0), and is promoted to the height of national strategy to be implemented.
GaAs production line has had very strong automated and semi-automatic ability, but to the technical process number of magnanimity
According to, the excavation of process results data and environmental data, in terms of finding model Improving The Quality of Products consistency from process data and also
In the exploratory stage, there are no form a kind of feasible quality using creation data docking GaAs production to be controlled and commented
The method estimated.
Invention content
In view of the deficiencies of the prior art, the present invention proposes one kind with production process qualitative data automatic collection and data model
The quality control model calculated in real time controls and process control energy mainly for the quality risk in GaAs device production process
Power deficiency problem is established the mathematical model with self study, is transported by mathematical model based on the huge data being collected into
It calculates and carries out product quality consistency anticipation, having for quality risk control can be carried out in real time in process of production by, which building, prevents
Property quality control system, and then Instructing manufacture achieve the purpose that control quality conformance GaAs product quality consistency control
Method, specific technical solution are as follows:
A kind of GaAs product quality consistency control method, is as follows:
Step 1:Historical process data is arranged to form archetype sample database;
Step 2:Mathematical modeling is carried out using artificial neural network to the process data in production process;
Step 3:Product quality forecast specially often completes one of product sequence, passes through the process data to the procedure
Carry out end product quality prediction using mathematical model, after the completion of product, by the real data of product and prediction result data into
Row compares, and generates product quality models report.
To better implement the present invention, further for:
The step 1 is specially:
1.1 combine historical process process data, process results data, product quality information, arrange as structure
The data of change form archetype sample database;
1.2 pairs of archetype sample databases pre-process, and sample data is made to have integrality, consistency and retrospect
Property, reduced data meets data claimed below and does not repeat, be no different regular data, can trace back to technique from product quality information
Process data and process results data.
The step 1.2 is specially:
1.2.1 processing empty value can capture field null value, be loaded or replaced with other meaning data;
1.2.2 standardize data format, field format constraint definition is realized, for time, numerical value, character etc. in data source
Data can customize load format;
1.2.3 data are split, field can be decomposed according to business demand;
1.2.4 data replace the replacement, it can be achieved that invalid data, missing data;
1.2.5 it establishes with product identification as main foreign key constraint, it is replaceable or export to mistake to the invalid data of no dependence
Accidentally in data file, ensure the load that major key uniquely records.
The step 2 specifically,
Process data pass through Principal Component Analysis or Fisher face or Factor minute in 2.1 pairs of production processes
Analysis method carries out dimension-reduction treatment;
Data in 2.2 pairs of production processes carry out unified dimension, data are normalized;
2.3 carry out mathematical modeling using the artificial neural network ANN connected entirely, in training process, be all made of tutor or
Person has the learning method of supervision to be trained artificial neural network, in the training process, is made using sensu lato energy function
For evaluation index, wherein sensu lato energy function E is as follows:
Wherein yiIt is exported for sample, fnnIt is exported for neural network;
In the training process, the gradient descent method used trains artificial neural network, so that neural network is optimal, i.e.,
Energy function E reaches minimum, and specific weighed value adjusting formula is as follows:
Wherein, λ is material calculation, wijIt is neural network weight, netjIt is wijThe output of place layer, xijIt is sample components,
ΔwijIt is the adjustment amount of weights;
Weights it is as follows with new formula, k is iterations:
wij(k+1)=wij(k)+Δwij
According to above-mentioned formula, the approximate error of system can gradually restrain, when training error reaches acceptable precision, artificial god
It can use as preliminary mathematical model through network, optimized according to the data acquired in real time in subsequent use.
A kind of GaAs product quality consistency control system, is provided with homogeneity of product prediction module, is used for per pass work
After sequence completion, parameters of technique process and process results data are obtained and in this, as the defeated of product quality consistency prediction module
Enter;
Product quality consistency forecast database, the prediction result data for receiving homogeneity of product prediction module;
Model parameter module is adjusted, for being adjusted into Mobile state to product quality consistency prediction model, in actual life
As production is more and more in production, model can be automatically tended to perfect by the adjustment of parameter;
Product quality models report generation module, for after product is finally completed, model predictive error module will be practical
Product quality data and the product quality data of prediction compared, form product quality models report and be used for assistant analysis.
Beneficial effects of the present invention are:GaAs production line has had very strong automated and semi-automatic ability, still
Excavation to the technical process data, process results data and environmental data of magnanimity, the present invention rigidly implement total quality pipe
The requirement of reason carries out " record, subsequent retrospect in definition, thing in advance " manufacturing process with digitizing means;Pass through automation
Data collection mode, can be widely by the requirement in GaAs production line, technical process data, process results data, ring
Border tidal data recovering gets up, and meaning does not lie in the collection to data, and is have to product quality from huge extracting data
Rule, pattern and the model of meaning;Centered on model, preventive quality management and control is carried out, prevents batch quality accident from occurring;
It realizes manufacturing process science decision, in each stage of manufacturing process, optimal realizing route is selected to being not carried out manufacturing process.
Description of the drawings
Fig. 1 is the structural schematic diagram of mathematical model in the present invention;
Fig. 2 is the structural schematic diagram of control system in the present invention;
Fig. 3 is the structural schematic diagram of prediction of quality in the present invention;
Fig. 4 is the structural schematic diagram of Sample Data Collection in the present invention;
Fig. 5 is the structural schematic diagram of neural network model in the present invention;
Fig. 6 is the overall structure diagram of prediction of quality 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.
In the present embodiment, the processes such as dielectric deposition, sputtering, sintering of GaAs production line are their direct shadows of critical process
Final product quality is rung, by prediction to critical process and feedback control, to ensure the final consistency of product quality.It is situated between
Matter deposition parameters of technique process be:Temperature, pressure, gas flow, power.The parameters of technique process of sputtering process is:Material
Purity, ion bombardment power, sputtering time, operating air pressure, quality characteristic value are coating film thickness;The technique mistake of sintering circuit
Journey parameter is:Temperature, time, gas flow, quality characteristic value are hardness.
As shown in Figures 1 to 6:A kind of GaAs product quality consistency control method, is as follows:
Step 1:Historical process data is arranged to form archetype sample database;
1.1 combine historical process process data, process results data, product quality information, arrange as structure
The data of change form archetype sample database;
1.2 pairs of archetype sample databases pre-process, and sample data is made to have integrality, consistency and retrospect
Property, reduced data meets data claimed below and does not repeat, be no different regular data, can trace back to technique from product quality information
Process data and process results data.
The step 1.2 is specially:
1.2.1 processing empty value can capture field null value, be loaded or replaced with other meaning data;
1.2.2 standardize data format, field format constraint definition is realized, for time, numerical value, character etc. in data source
Data can customize load format;
1.2.3 data are split, field can be decomposed according to business demand;
1.2.4 data replace the replacement, it can be achieved that invalid data, missing data;
1.2.5 it establishes with product identification as main foreign key constraint, it is replaceable or export to mistake to the invalid data of no dependence
Accidentally in data file, ensure the load that major key uniquely records.
Historical process process in trapping medium deposition, sputtering, sintering, plated film, photoetching, six key production equipments of etching
The business datum of data, historical process result data and product.Product business datum is stored in operation system, data collection journey
Sequence obtains product essential information and product quality information from business system database, and stores into sample database.History
Technical process data with document form be stored in equipment control computer and filing database in, data collection program parse work
Skill procedure file is converted to partly-structured data in structural data storage raw sample data library.Produce result data
It is stored in operation system by the form of electronic document, data collection program obtains electronic document from operation system, by technique
Result data is converted in structural data storage to raw sample data library.Technical process data are judged during collection
Whether incidence relation can be determined with process results data with product information, if lacking incidence relation thinks that data are endless
Whole, data are rejected.
After collecting end data, related personnel is by the analysis to data to the technique mistake of dielectric deposition and sintering circuit
Number of passes carries out dimensionality reduction according to a liter dimension is carried out, to the technical process data of sputtering process.Simultaneously because dimension difference is to relevant parameter
It is normalized.
Step 2:Mathematical modeling is carried out using artificial neural network to the process data in production process;
Process data pass through Principal Component Analysis or Fisher face or Factor minute in 2.1 pairs of production processes
Analysis method carries out dimension-reduction treatment;
Data in 2.2 pairs of production processes carry out unified dimension, data are normalized;
2.3 carry out mathematical modeling using the artificial neural network ANN connected entirely, in training process, be all made of tutor or
Person has the learning method of supervision to be trained artificial neural network, in the training process, is made using sensu lato energy function
For evaluation index, wherein sensu lato energy function E is as follows:
Wherein yiIt is exported for sample, fnnIt is exported for neural network;
In the training process, the gradient descent method used trains artificial neural network, so that neural network is optimal, i.e.,
Energy function E reaches minimum, and specific weighed value adjusting formula is as follows:
Wherein, λ is material calculation, wijIt is neural network weight, netjIt is wijThe output of place layer, xijIt is sample components,
ΔwijIt is the adjustment amount of weights;
Weights it is as follows with new formula, k is iterations:
wij(k+1)=wij(k)+Δwij
According to above-mentioned formula, the approximate error of system can gradually restrain, when training error reaches acceptable precision, artificial god
It can use as preliminary mathematical model through network, optimized according to the data acquired in real time in subsequent use.
By dielectric deposition, sputtering, sintering, plated film, photoetching, the dielectric deposition temperature for etching six critical processes, pressure, gas
Body flow, coating film thickness, resistance, electric current, gas flow, evaporation thickness, sputter rate, vacuum degree, sintering temperature, photoetching ruler
Very little, etch rate, deposition rate, plated film rate, sintering time, leak rate, material purity, ion bombardment power, sputtering time 20
A key parameter, while new parameter is formed to thickness and etch rate parameter progress average value, variance, very poor processing.It will close
Parameter merges the input as input layer to key process parameter with treated.Predict the final power of product, phase, leakage
4 electricity, frequency index values.
Final neural network model is divided into three layers after modeling, and input layer is with 28 nodes, middle layer with 5251, output
Layer has 4 nodes.Wherein population sample data are 5300, and wherein 4600 samples are carried out to the training of model, in addition 700
Bar sample is as test sample.
Step 3:The current sample processed, after finishing a procedure, product quality consistency model system is certainly
Dynamic collection technology process data and process results data from equipment and operation system, and process is completed in current sample
All data formation process data packets give product quality consistency model module, the final mass of sample is predicted,
And it is directly checked in the system page.Prediction data and real data are compared and analyzed after sample completion simultaneously.
A kind of GaAs product quality consistency control system, is provided with homogeneity of product prediction module, is used for per pass work
After sequence completion, parameters of technique process and process results data are obtained and in this, as the defeated of product quality consistency prediction module
Enter;
Product quality consistency forecast database, the prediction result data for receiving homogeneity of product prediction module;
Model parameter module is adjusted, for being adjusted into Mobile state to product quality consistency prediction model, in actual life
As production is more and more in production, model can be automatically tended to perfect by the adjustment of parameter;
Product quality models report generation module, for after product is finally completed, model predictive error module will be practical
Product quality data and the product quality data of prediction compared, form product quality models report and be used for assistant analysis.
Claims (5)
1. a kind of GaAs product quality consistency control method, which is characterized in that be as follows:
Step 1:Historical process data is arranged to form archetype sample database;
Step 2:Mathematical modeling is carried out using artificial neural network to the process data in production process;
Step 3:Product quality forecast specially often completes one of product sequence, passes through the process data utilization to the procedure
Mathematical model carries out end product quality prediction, and after the completion of product, the real data of product and prediction result data are compared
It is right, generate product quality models report.
2. GaAs product quality consistency control method according to claim 1, it is characterised in that:The step 1 is specific
For:
1.1 combine historical process process data, process results data, product quality information, arrange as structuring
Data form archetype sample database;
1.2 pairs of archetype sample databases pre-process, and sample data is made to have integrality, consistency and retrospective, whole
Data after reason meet data claimed below and do not repeat, be no different regular data, can trace back to technical process from product quality information
Data and process results data.
3. GaAs product quality consistency control method according to claim 2, it is characterised in that:Step 1.2 tool
Body is:
1.2.1 processing empty value can capture field null value, be loaded or replaced with other meaning data;
1.2.2 standardize data format, realize field format constraint definition, for the number such as time, numerical value, character in data source
According to can customize load format;
1.2.3 data are split, field can be decomposed according to business demand;
1.2.4 data replace the replacement, it can be achieved that invalid data, missing data;
1.2.5 it establishes with product identification as main foreign key constraint, it is replaceable or export to error number to the invalid data of no dependence
According to the load that in file, guarantee major key uniquely records.
4. GaAs product quality consistency control method according to claim 1, it is characterised in that:The step 2 is specific
For,
Process data pass through Principal Component Analysis or Fisher face or factor analysis in 2.1 pairs of production processes
Carry out dimension-reduction treatment;
Data in 2.2 pairs of production processes carry out unified dimension, data are normalized;
2.3 carry out mathematical modeling using the artificial neural network ANN connected entirely, in training process, have been all made of tutor or have had
The learning method of supervision is trained artificial neural network, in the training process, is used as and is commented using sensu lato energy function
Valence index, wherein sensu lato energy function E is as follows:
Wherein yiIt is exported for sample, fnnIt is exported for neural network;
In the training process, the gradient descent method used trains artificial neural network, so that neural network is optimal, i.e. energy
Function E reaches minimum, and specific weighed value adjusting formula is as follows:
Wherein, λ is material calculation, wijIt is neural network weight, netjIt is wijThe output of place layer, xijIt is sample components, Δ wij
It is the adjustment amount of weights;
Weights it is as follows with new formula, k is iterations:
wij(k+1)=wij(k)+Δwij
According to above-mentioned formula, the approximate error of system can gradually restrain, when training error reaches acceptable precision, artificial neural network
Network can be used as preliminary mathematical model, be optimized according to the data acquired in real time in subsequent use.
5. a kind of GaAs product quality consistency control system, it is characterised in that:It is provided with homogeneity of product prediction module, is used
After the completion of every procedure, obtains parameters of technique process and process results data and predict mould in this, as product quality consistency
The input of block;
Product quality consistency forecast database, the prediction result data for receiving homogeneity of product prediction module;
Model parameter module is adjusted, for being adjusted into Mobile state to product quality consistency prediction model, in actual production
As production is more and more, model can be automatically tended to perfect by the adjustment of parameter;
Product quality models report generation module, for after product is finally completed, model predictive error module is by actual production
Quality data and the product quality data of prediction are compared, and are formed product quality models report and are used for assistant analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810355693.4A CN108415393A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs product quality consistency control method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810355693.4A CN108415393A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs product quality consistency control method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108415393A true CN108415393A (en) | 2018-08-17 |
Family
ID=63135888
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810355693.4A Pending CN108415393A (en) | 2018-04-19 | 2018-04-19 | A kind of GaAs product quality consistency control method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108415393A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109767090A (en) * | 2018-12-27 | 2019-05-17 | 浙江省天正设计工程有限公司 | A kind of chemical hazard process risk intelligent control method |
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 |
CN112099460A (en) * | 2020-11-02 | 2020-12-18 | 常州微亿智造科技有限公司 | Quality characteristic processing method suitable for deep learning metal injection molding sintering product |
CN112116184A (en) * | 2019-06-21 | 2020-12-22 | 因斯派克托里奥股份有限公司 | Factory risk estimation using historical inspection data |
CN113256151A (en) * | 2021-06-15 | 2021-08-13 | 佛山绿色发展创新研究院 | Hydrogen quality detection method, system and computer storage medium using the same |
CN113537597A (en) * | 2021-07-16 | 2021-10-22 | 上海大学 | Privacy protection-based material performance prediction method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101403915A (en) * | 2008-11-07 | 2009-04-08 | 同济大学 | Product quality prediction technique for recombination assembly line |
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN105426394A (en) * | 2015-10-18 | 2016-03-23 | 广州赛意信息科技股份有限公司 | Mobile report generation method and system based on cross-platform |
CN105956330A (en) * | 2016-05-31 | 2016-09-21 | 山东中烟工业有限责任公司 | Method and system for establishing product process quality prediction model based on site data |
CN107479509A (en) * | 2008-03-06 | 2017-12-15 | 应用材料公司 | Yield prediction feedback for control device engineering system |
CN107562696A (en) * | 2017-09-12 | 2018-01-09 | 齐鲁工业大学 | Tire product quality on-line checking and control method |
-
2018
- 2018-04-19 CN CN201810355693.4A patent/CN108415393A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107479509A (en) * | 2008-03-06 | 2017-12-15 | 应用材料公司 | Yield prediction feedback for control device engineering system |
CN101403915A (en) * | 2008-11-07 | 2009-04-08 | 同济大学 | Product quality prediction technique for recombination assembly line |
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN105426394A (en) * | 2015-10-18 | 2016-03-23 | 广州赛意信息科技股份有限公司 | Mobile report generation method and system based on cross-platform |
CN105956330A (en) * | 2016-05-31 | 2016-09-21 | 山东中烟工业有限责任公司 | Method and system for establishing product process quality prediction model based on site data |
CN107562696A (en) * | 2017-09-12 | 2018-01-09 | 齐鲁工业大学 | Tire product quality on-line checking and control method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109767090A (en) * | 2018-12-27 | 2019-05-17 | 浙江省天正设计工程有限公司 | A kind of chemical hazard process risk intelligent control method |
CN109767090B (en) * | 2018-12-27 | 2020-09-29 | 浙江省天正设计工程有限公司 | Chemical dangerous process risk intelligent monitoring method |
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 |
CN112116184A (en) * | 2019-06-21 | 2020-12-22 | 因斯派克托里奥股份有限公司 | Factory risk estimation using historical inspection data |
CN112099460A (en) * | 2020-11-02 | 2020-12-18 | 常州微亿智造科技有限公司 | Quality characteristic processing method suitable for deep learning metal injection molding sintering product |
CN113256151A (en) * | 2021-06-15 | 2021-08-13 | 佛山绿色发展创新研究院 | Hydrogen quality detection method, system and computer storage medium using the same |
CN113537597A (en) * | 2021-07-16 | 2021-10-22 | 上海大学 | Privacy protection-based material performance prediction method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108415393A (en) | A kind of GaAs product quality consistency control method and system | |
CN107220734A (en) | CNC Lathe Turning process Energy Consumption Prediction System based on decision tree | |
CN113469241B (en) | Product quality control method based on process network model and machine learning algorithm | |
CN109800898A (en) | A kind of intelligence short-term load forecasting method and system | |
CN110232476B (en) | Micro-grid load prediction method based on deep learning | |
CN111178585A (en) | Fault reporting amount prediction method based on multi-algorithm model fusion | |
CN110689162A (en) | Bus load prediction method, device and system based on user side classification | |
CN106776316A (en) | A kind of power information software defect prevention method | |
CN111258984B (en) | Product quality end-edge-cloud collaborative forecasting method under industrial big data environment | |
CN112633556A (en) | Short-term power load prediction method based on hybrid model | |
CN108594776A (en) | A kind of GaAs quality conformance control method and system based on critical process | |
CN113722997A (en) | New well dynamic yield prediction method based on static oil and gas field data | |
Fang et al. | Adagrad gradient descent method for ai image management | |
CN115238573A (en) | Hydroelectric generating set performance degradation trend prediction method and system considering working condition parameters | |
CN113641733B (en) | Real-time intelligent estimation method for river cross section flow | |
CN109829246B (en) | Line parameter identification method based on parameter comprehensive suspicion | |
CN116956203B (en) | Method and system for measuring action characteristics of tapping switch of transformer | |
CN104460594A (en) | Dispatching optimization method based on two-layer nest structure | |
CN113705897A (en) | Product quality prediction method and system for industrial copper foil production | |
CN112700050A (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
CN116703254A (en) | Production information management system for mechanical parts of die | |
CN112949203B (en) | Board laser cutting quality judgment method based on electrical parameters and XGBOOST-NN algorithm | |
CN108596781A (en) | A kind of electric power system data excavates and prediction integration method | |
CN107169593A (en) | A kind of universities and colleges based on neutral net file line Forecasting Methodology | |
CN117709908B (en) | Intelligent auditing method and system for distribution rationality of power grid engineering personnel, materials and machines |
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: 20180817 |