CN106777672A - Metal material forging microstructure flexible measurement method based on adaptive expert system - Google Patents
Metal material forging microstructure flexible measurement method based on adaptive expert system Download PDFInfo
- Publication number
- CN106777672A CN106777672A CN201611149220.6A CN201611149220A CN106777672A CN 106777672 A CN106777672 A CN 106777672A CN 201611149220 A CN201611149220 A CN 201611149220A CN 106777672 A CN106777672 A CN 106777672A
- Authority
- CN
- China
- Prior art keywords
- microstructure
- technological parameter
- metal material
- matching degree
- database
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Forging (AREA)
Abstract
Microstructure flexible measurement method is forged the invention provides a kind of metal material based on adaptive expert system.The method comprises the following steps:(1) smithing technological parameter and metal material microstructure data according to history sets up initial expert system, mainly including database, inference machine and learning machine;(2) actual comparing with the technological parameter in database for forging is obtained into technological parameter error vector, machine calculates processing parameter matching degree by inference;(3) using the microstructure that the microstructure data estimation in processing parameter matching degree and database is current;(4) expert system self study, if the current microstructure of estimation is new microstructure, new technological parameter and microstructure data is saved in database;Otherwise, terminate.The inventive method can forge microstructure by accurate measurement metal material online, solve the technical barrier that metal material forging microstructure is difficult to on-line measurement.
Description
Technical field:
The invention belongs to metal material processing field of engineering technology, it is related to a kind of metal material based on adaptive expert system
Material forging microstructure flexible measurement method.
Background technology:
Because the metal materials such as nickel base superalloy, aluminium alloy, magnesium alloy have excellent mechanical performance and other military services
Performance, has been widely used for space flight, aviation, navigation and nuclear energy field.Microstructure (the recrystallization crystal particle dimension of metal material
With recrystallization fraction) it is the key factor for influenceing its properties.How metal material is accurately measured in process
Microstructure is a problem urgently to be resolved hurrily.
Research shows that Microstructure evolution of the metal material in forging process is extremely complex, significantly by deformation temperature,
The combined influence of the technological parameter such as strain rate and strain.Additionally, in forging process, existing measuring apparatus cannot be surveyed in real time
Measure the microstructure of metal material.For this physical quantity for being difficult to and measuring, can be estimated using flexible measurement method.At present, often
Flexible measurement method mainly includes:Flexible measurement method based on data-driven modeling and Kernel-based methods modelling by mechanism.In forging
During, the Microstructure evolution of metal material is extremely complex, it is difficult to set up accurate mechanism model.With the hair of intelligent method
The methods such as exhibition, neutral net, fuzzy set and expert system are gradually introduced the prediction of multiple material microstructure and rheological behaviour
In modeling, and achieve good effect.Therefore, it can propose a kind of simple, fast and efficient metal material based on intelligent method
Material forging microstructure flexible measurement method.
The inventive method is based on adaptive expert system, with reference to fuzzy reasoning method, it is proposed that a kind of simple, quick, high
Effect metal material forging microstructure flexible measurement method, solve metal material forging microstructure cannot on-line measurement difficulty
Topic.
The content of the invention:
It is an object of the invention to provide a kind of metal material forging microstructure flexible measurement method, metal material is solved
Forging microstructure cannot on-line measurement problem.
The scheme that the present invention solves above-mentioned problem is:
Metal material forging microstructure flexible measurement method based on adaptive expert system, the method includes following step
Suddenly:
Step 1:Smithing technological parameter (mold speed and displacement, forging temperature) and metal material according to history is microcosmic
Tissue data (recrystallization fraction and recrystallization crystal particle dimension) set up initial expert system, mainly including database, inference machine
And learning machine;
Step 2:Actual comparing with the technological parameter in database for forging is obtained into technological parameter error vector, according to pushing away
Fuzzy reasoning method in reason machine calculates processing parameter matching degree;
Step 3:Using the current microstructure of the microstructure data estimation in processing parameter matching degree and database;
Step 4:Expert system self study, if the current microstructure of estimation is new microstructure, new technique
Parameter and microstructure data are saved in database;Otherwise, terminate.
According to such scheme, expert system described in step 1 mainly includes database, inference machine and learning machine, its effect
Respectively:
Database:For storing smithing technological parameter and metal material microstructure data, for inference machine provides technique ginseng
Number error vector, and then estimate metal material microstructure;
Inference machine:Based on fuzzy inference system, according to technological parameter error vector calculate actual smithing technological parameter
With degree, for hard measurement metal material microstructure;
Learning machine:Judge whether hard measurement microstructure is new microstructure, and by new microstructure and right
The smithing technological parameter answered is added in database, to improve database, improves hard measurement precision.
According to such scheme, database described in step 1 is according to history smithing technological parameter (mold speed and position
Move) and microstructure data (recrystallization crystal particle dimension and recrystallization fraction) set up, the database includes precondition and micro-
Tissue two parts are seen, wherein, precondition is 4 technological parameters, i.e. the mold speed and displacement of kth step and k+1 steps;It is microcosmic
It is organized as the recrystallization crystal particle dimension and recrystallization fraction of the step of kth+1.
According to such scheme, technological parameter error vector described in step 2 be actual smithing technological parameter with database in
The difference of technological parameter (precondition), can be expressed as:
Ei=[sp(k)-se(k),sp(k+1)-se(k+1),vp(k)-ve(k),vp(k+1)-ve(k+1)] i=1,2 ...,
m (1)
Wherein, spAnd vpActual smithing technological parameter (displacement of mold and speed), s are represented respectivelyeAnd veRepresent respectively
Technological parameter (displacement of mold and speed) in database, EiIt is i-th technological parameter error vector, m is technological parameter
The number of error vector.
According to such scheme, fuzzy reasoning method described in step 2 is the core of flexible measurement method, and its process is:
If all errors are all 0 in technological parameter error vector, illustrate that the smithing technological parameter is a certain with database
The matching degree of individual technological parameter is 1, then the corresponding microstructure of the technological parameter is the result of hard measurement;
If all errors are not all 0 in technological parameter error vector, illustrate to need to calculate technique with fuzzy reasoning method
The matching degree of parameter, the error of mold speed and mold displacement, the two operating modes are included due to technological parameter error vector
The order of magnitude of parameter is differed, it is therefore desirable to which duty parameter error vector is normalized, and normalization formula is:
Wherein, x is the value before normalization, xnIt is the value after normalization, xminAnd xmaxIt is maximum and minimum value.
The matching degree of each technological parameter is calculated with Triangleshape grade of membership function in technological parameter error vector, its
Expression formula is:
Wherein, p is the matching degree of technological parameter, and e is normalized error, Triangleshape grade of membership function parameter b=0.05.
After 4 matching degrees of technological parameter are calculated, the matching degree of technological parameter error vector is this 4 matchings
The product of degree:
pv=p1×p2×p3×p4 (4)
Wherein, pvThe matching degree of technological parameter error vector, p1、p2、p3And p4It is 4 matching degrees of technological parameter.
After all of error vector matching degree is obtained, in order to ensure total matching degree sum for 1, it is necessary to all of
Error vector matching degree is normalized, and normalization formula is:
Wherein, piIt is i-th matching degree before normalization, pinIt is i-th matching degree after normalization, m is technique
The number of parameter error vector.
According to such scheme, estimated using the microstructure data in processing parameter matching degree and database described in step 3
Calculating microstructure can be described as:By the microstructure in all of technological parameter error vector matching degree and database all with to
Amount form is represented:
P=[p1n,p2n,……,pmn], G=[g1,g2,……,gm], F=[f1,f2,……,fm] (6)
Wherein, P is technological parameter error vector matching degree, and G is recrystallization crystal particle dimension vector, and F is recrystallization scores vector, then
Microstructure (the recrystallization crystal particle dimension g of hard measurementm, recrystallization fraction fm) can be expressed as:
gm=PGT (7)
fm=PFT (8)
According to such scheme, the process of expert system self study described in step 4 can be described as:Judge microcosmic group of estimation
Whether be new microstructure, if new microstructure, then new technological parameter and microstructure data are saved in data if knitting
In storehouse;Otherwise, terminate.
According to such scheme, the expert set up using history forging technology data and metal material microstructure data is
System, the smithing technological parameter gathered by industry spot can realize the on-line measurement of metal material microstructure.
Beneficial effects of the present invention:The present invention is difficult to online for metal material microstructure during actual industrial production
The problem of measurement, adaptive expert system is established according to history forging technology data and metal material microstructure data, essence
Standard rapidly realizes the hard measurement that metal material forges microstructure, is applicable to metal material die forging and flat-die forging adds
In work, for accurate measuring metallic materials microstructure provides new method.The invention and popularization and application of the method are to accurate measurement gold
Category Fine Texture of Material has important engineering significance.
Brief description of the drawings:
Fig. 1 is based on the metal material microstructure flexible measurement method flow chart of adaptive expert system;
Fig. 2 database structure figures;
Fig. 3 fuzzy reasoning flow charts;
Fig. 4 Triangleshape grade of membership function;
Nickel base superalloy microstructure hard measurement result before Fig. 5 expert system self studies;
Nickel base superalloy microstructure hard measurement result after Fig. 6 expert system self studies.
Specific embodiment:
The present invention will be described in detail with reference to the accompanying drawings and detailed description.
The present invention is a kind of metal material microstructure flexible measurement method, and its flow chart is as shown in Figure 1.It is described in detail below
The implementation detail of metal material microstructure flexible measurement method of the present invention, its method includes:
Step 1:Smithing technological parameter (mold speed and displacement, forging temperature) and metal material according to history is microcosmic
Tissue data (recrystallization fraction and recrystallization crystal particle dimension) set up initial expert system, mainly including database, inference machine
And learning machine;
Database is the smithing technological parameter (mold speed and displacement, forging temperature) and microstructure number according to history
Set up according to (recrystallization crystal particle dimension and recrystallization fraction), its structure is as shown in Fig. 2 the database includes precondition and micro-
Tissue two parts are seen, wherein, precondition is 4 technological parameters, i.e. the mold speed and displacement of kth step and k+1 steps;It is microcosmic
It is organized as the recrystallization crystal particle dimension and recrystallization fraction of the step of kth+1.
Step 2:Actual comparing with the technological parameter in database for forging is obtained into technological parameter error vector, according to pushing away
Fuzzy reasoning method in reason machine calculates processing parameter matching degree;
Technological parameter error vector is the difference of actual smithing technological parameter and technological parameter (precondition) in database,
Can be expressed as:
Ei=[sp(k)-se(k),sp(k+1)-se(k+1),vp(k)-ve(k),vp(k+1)-ve(k+1)] i=1,2 ...,
m (9)
Wherein, spAnd vpActual smithing technological parameter (displacement of mold and speed), s are represented respectivelyeAnd veRepresent respectively
Technological parameter (displacement of mold and speed) in database, EiIt is i-th technological parameter error vector, m is technological parameter
The number of error vector.
Fuzzy reasoning method in inference machine is the core of flexible measurement method, its flow as shown in figure 3, can be expressed as:
If all errors are all 0 in technological parameter error vector, illustrate the smithing technological parameter with some technique ginseng in database
Several matching degrees is 1, then the corresponding microstructure of the technological parameter is the result of hard measurement;If technological parameter error vector
In all errors be not all 0, illustrate to need the matching degree with fuzzy reasoning method calculating technological parameter, due to technological parameter error
Error of the vector including mold speed and mold displacement, the order of magnitude of the two duty parameters is differed, therefore is needed
Duty parameter error vector is normalized, normalization formula is:
Wherein, x is the value before normalization, xnIt is the value after normalization, xminAnd xmaxIt is maximum and minimum value.
The matching degree of each technological parameter is (such as Fig. 4 institutes with Triangleshape grade of membership function in technological parameter error vector
Show) calculate, its expression formula is:
Wherein, p is the matching degree of technological parameter, and e is normalized error, Triangleshape grade of membership function parameter b=0.05.
After 4 matching degrees of technological parameter are calculated, the matching degree of technological parameter error vector is this 4 matchings
The product of degree:
pv=p1×p2×p3×p4 (12)
Wherein, pvThe matching degree of technological parameter error vector, p1、p2、p3And p4It is 4 matching degrees of technological parameter.
After all of error vector matching degree is obtained, in order to ensure total matching degree sum for 1, it is necessary to all of
Error vector matching degree is normalized, and normalization formula is:
Wherein, piIt is i-th matching degree before normalization, pinIt is i-th matching degree after normalization, m is technique
The number of parameter error vector.
Step 3:Using the current microstructure of the microstructure data estimation in processing parameter matching degree and database;
Microstructure in all of technological parameter error vector matching degree and database is all represented with vector form:
P=[p1n,p2n,……,pmn], G=[g1,g2,……,gm], F=[f1,f2,……,fm] (14)
Wherein, P is technological parameter error vector matching degree, and G is recrystallization crystal particle dimension vector, F be recrystallization fraction to
Measure, then the current microstructure of hard measurement (recrystallization crystal particle dimension gm, recrystallization fraction fm) can be expressed as:
gm=PGT (15)
fm=PFT (16)
Step 4:Expert system self study, if the current microstructure of estimation is new microstructure, new technique
Parameter and microstructure data are saved in database;Otherwise, terminate.
Forging technology data according to online awareness, it is possible to use the adaptive expert system on-line measurement metal material of foundation
Material microstructure, hard measurement result is as shown in figure 5, it can be found that hard measurement results contrast is accurate, it is sufficient to reach industrial requirements;It is logical
Cross after expert system self study, hard measurement result is as shown in fig. 6, it can be found that hard measurement result is exactly accurate.This explanation is worked as
After expert system is by learning by oneself, can supplementary data storehouse well, be greatly enhanced hard measurement precision, therefore proposed by the present invention
Expert system is getting easier and easier to use more with more accurate.
From the above it can be found that method proposed by the present invention being capable of quickly and accurately gold in hard measurement forging process
Category Fine Texture of Material, for metal material microstructure provides reliable technological approaches in accurate description forging process.
Example of the invention is illustrated above in conjunction with accompanying drawing, but the present invention is not limited to above-mentioned specific embodiment party
Formula, above-mentioned specific embodiment is only exemplary.Any invention no more than the claims in the present invention, of the invention
Within protection domain.
Claims (3)
1. the metal material based on adaptive expert system forges microstructure flexible measurement method, it is characterised in that:For industry
Metal material microstructure is difficult to the problem of on-line measurement in forging process, is built based on forging technology data and microstructure data
Found adaptive expert system, can accurate hard measurement metal material microstructure, the method comprises the following steps:
Step 1:Smithing technological parameter (mold speed and displacement, forging temperature) and metal material microstructure according to history
Data (recrystallization fraction and recrystallization crystal particle dimension) set up initial expert system, mainly including database, inference machine and
Habit machine;
Step 2:Actual comparing with the technological parameter in database for forging is obtained into technological parameter error vector, by inference machine
In fuzzy reasoning method calculate processing parameter matching degree;
Step 3:Using the current microstructure of the microstructure data estimation in processing parameter matching degree and database;
Step 4:Expert system self study, if the current microstructure of estimation is new microstructure, new technological parameter
It is saved in database with microstructure data;Otherwise, terminate.
2. method as claimed in claim 1, it is characterised in that:Adaptive expert system described in step 1 solves metal material
Material microstructure is difficult to the problem of on-line measurement in forging process, it is characterised in that mainly include three below part:
(1) database, for storing smithing technological parameter and metal material microstructure data, for inference machine provides technological parameter
Error vector, and then estimate the current microstructure of metal material;
(2) inference machine:Based on fuzzy inference system, the matching of actual smithing technological parameter is calculated according to technological parameter error vector
Degree, for hard measurement metal material microstructure;
(3) learning machine:Whether the current microstructure for judging hard measurement is new microstructure, and by new microstructure
And during corresponding smithing technological parameter adds to database, to improve database, improve hard measurement precision.
3. method as claimed in claim 1, it is characterised in that:Fuzzy reasoning method described in step 2 realizes hard measurement
Core, it is characterised in that technological parameter vector includes 4 technological parameters (kth is walked and k+1 is walked mold speed and displacement),
If all errors are all 0 in technological parameter error vector, illustrate the smithing technological parameter with some technique ginseng in database
Several matching degrees is 1, then the corresponding microstructure of the technological parameter is the result of hard measurement;
If all errors are not all 0 in technological parameter error vector, because technological parameter error vector includes mold speed
With the error of mold displacement, the order of magnitude of the two duty parameters differs, it is therefore desirable to duty parameter error to
Amount is normalized, and normalization formula is:
Wherein, x is the value before normalization, xnIt is the value after normalization, xminAnd xmaxIt is maximum and minimum value;
The matching degree of each technological parameter is calculated with Triangleshape grade of membership function in technological parameter error vector, its expression
Formula is:
Wherein, p is the matching degree of technological parameter, and e is normalized error, Triangleshape grade of membership function parameter b=0.05;
After 4 matching degrees of technological parameter are calculated, the matching degree of technological parameter error vector is this 4 matching degrees
Product:
pv=p1×p2×p3×p4 (3)
Wherein, pvThe matching degree of technological parameter error vector, p1、p2、p3And p4It is 4 matching degrees of technological parameter;
After all of error vector matching degree is obtained, in order to ensure total matching degree sum for 1, it is necessary to all of error
Vectors matching degree is normalized, and normalization formula is:
Wherein, piIt is i-th matching degree before normalization, pinIt is i-th matching degree after normalization, m is technological parameter
The number of error vector;
Microstructure in all of technological parameter error vector matching degree and database is all represented with vector form:
P=[p1n,p2n,……,pmn], G=[g1,g2,……,gm], F=[f1,f2,……,fm] (5)
Wherein, P is technological parameter error vector matching degree, and G is recrystallization crystal particle dimension vector, and F is recrystallization scores vector, then
Microstructure (the recrystallization crystal particle dimension g of hard measurementm, recrystallization fraction fm) can be expressed as:
gm=PGT (6)
fm=PFT (7)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611149220.6A CN106777672A (en) | 2016-12-14 | 2016-12-14 | Metal material forging microstructure flexible measurement method based on adaptive expert system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611149220.6A CN106777672A (en) | 2016-12-14 | 2016-12-14 | Metal material forging microstructure flexible measurement method based on adaptive expert system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106777672A true CN106777672A (en) | 2017-05-31 |
Family
ID=58876836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611149220.6A Pending CN106777672A (en) | 2016-12-14 | 2016-12-14 | Metal material forging microstructure flexible measurement method based on adaptive expert system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106777672A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598096A (en) * | 2019-01-16 | 2019-04-09 | 中南大学 | A kind of online planing method of smithing technological parameter based on adaptive Dynamic Programming |
CN112765918A (en) * | 2021-01-22 | 2021-05-07 | 西安电子科技大学 | Fuzzy reasoning method for determining design parameters of integrated circuit |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1664500A (en) * | 2005-03-29 | 2005-09-07 | 东北大学 | Flexible measurement method for grain sizes of steel plate internal structure during rolling process |
CN102652925A (en) * | 2012-04-26 | 2012-09-05 | 中冶南方工程技术有限公司 | System for measuring granularity of pulverized coal of blast furnace coal powder injection middle-speed milling system |
US20170269559A1 (en) * | 2014-02-05 | 2017-09-21 | Yokogawa Corproation of America | System and Method for Online Measurement of Vapor Pressure in Hydrocarbon Process Streams |
-
2016
- 2016-12-14 CN CN201611149220.6A patent/CN106777672A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1664500A (en) * | 2005-03-29 | 2005-09-07 | 东北大学 | Flexible measurement method for grain sizes of steel plate internal structure during rolling process |
CN102652925A (en) * | 2012-04-26 | 2012-09-05 | 中冶南方工程技术有限公司 | System for measuring granularity of pulverized coal of blast furnace coal powder injection middle-speed milling system |
US20170269559A1 (en) * | 2014-02-05 | 2017-09-21 | Yokogawa Corproation of America | System and Method for Online Measurement of Vapor Pressure in Hydrocarbon Process Streams |
Non-Patent Citations (2)
Title |
---|
YAO WU等: "A Design of Soft Sensor based on Data Fusion", 《2009 INTERNATIONAL CONFERENCE ON INFORMATION ENGINEERING AND COMPUTER SCIENCE》 * |
周驰化: "模糊专家系统在高炉温度预测中的研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598096A (en) * | 2019-01-16 | 2019-04-09 | 中南大学 | A kind of online planing method of smithing technological parameter based on adaptive Dynamic Programming |
CN109598096B (en) * | 2019-01-16 | 2023-07-25 | 中南大学 | Forging process parameter online planning method based on self-adaptive dynamic planning |
CN112765918A (en) * | 2021-01-22 | 2021-05-07 | 西安电子科技大学 | Fuzzy reasoning method for determining design parameters of integrated circuit |
CN112765918B (en) * | 2021-01-22 | 2023-08-18 | 西安电子科技大学 | Fuzzy reasoning method for determining design parameters of integrated circuit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Majumder et al. | Application of GRNN and multivariate hybrid approach to predict and optimize WEDM responses for Ni-Ti shape memory alloy | |
Majumder et al. | Prediction and optimization of surface roughness and micro-hardness using grnn and MOORA-fuzzy-a MCDM approach for nitinol in WEDM | |
Mohanty et al. | An intelligent approach to optimize the EDM process parameters using utility concept and QPSO algorithm | |
Markopoulos et al. | Artificial neural network models for the prediction of surface roughness in electrical discharge machining | |
Hernandez et al. | A computational determination of the Cowper–Symonds parameters from a single Taylor test | |
Jiao et al. | Remaining useful life prediction for a roller in a hot strip mill based on deep recurrent neural networks | |
Majumder et al. | Predictive analysis on responses in WEDM of titanium grade 6 using general regression neural network (GRNN) and multiple regression analysis (MRA) | |
Inamdar et al. | Studies on the prediction of springback in air vee bending of metallic sheets using an artificial neural network | |
Senthilkumar et al. | Application of constitutive and neural network models for prediction of high temperature flow behavior of Al/Mg based nanocomposite | |
Quan et al. | Modeling the hot deformation behaviors of as-extruded 7075 aluminum alloy by an artificial neural network with back-propagation algorithm | |
Quan et al. | Artificial neural network modeling to evaluate the dynamic flow stress of 7050 aluminum alloy | |
CN114897227A (en) | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm | |
Anitha et al. | Multi-objective optimization of electrical discharge machining processes using artificial neural network. | |
CN106777672A (en) | Metal material forging microstructure flexible measurement method based on adaptive expert system | |
McBride et al. | Modelling tensile properties of gamma-based titanium aluminides using artificial neural network | |
Quan et al. | Modelling the hot flow behaviors of AZ80 alloy by BP-ANN and the applications in accuracy improvement of computations | |
Prabhu et al. | Adaptive neuro fuzzy inference system modelling of multi-objective optimisation of electrical discharge machining process using single-wall carbon nanotubes | |
CN112149896A (en) | Attention mechanism-based mechanical equipment multi-working-condition fault prediction method | |
ÇELİK et al. | Modelling of the clearance effects in the blanking process of CuZn30 sheet metal using neural network− a comparative study | |
Gao et al. | A 6-sigma robust optimization method for stamping forming of automobile covering parts based on residual error and radial basis interpolation | |
Wang et al. | Determination of temperature difference in squeeze casting hot work tool steel | |
Dong et al. | Just-in-time learning-based soft sensor for mechanical properties of strip steel via multi-block weighted semisupervised models | |
Nayak et al. | Taguchi integrated least square support vector machine an alternative to artificial neural network analysis of electrochemical machining process | |
CN105808949B (en) | Large-scale drop press upper beam speed on-line prediction method based on Taylor expansion | |
CN108873705A (en) | A kind of HH neuron synchronisation control means based on non-linearity PID |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |