CN109871937A - A kind of aluminium section mechanical performance prediction method based on RBF neural - Google Patents
A kind of aluminium section mechanical performance prediction method based on RBF neural Download PDFInfo
- Publication number
- CN109871937A CN109871937A CN201811352852.1A CN201811352852A CN109871937A CN 109871937 A CN109871937 A CN 109871937A CN 201811352852 A CN201811352852 A CN 201811352852A CN 109871937 A CN109871937 A CN 109871937A
- Authority
- CN
- China
- Prior art keywords
- mechanical performance
- aluminium section
- rbf neural
- network
- parameter
- 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
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 60
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000004411 aluminium Substances 0.000 title claims abstract description 44
- 230000001537 neural effect Effects 0.000 title claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 claims abstract description 44
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 230000008901 benefit Effects 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 7
- 239000002994 raw material Substances 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000004513 sizing Methods 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims 1
- 210000005036 nerve Anatomy 0.000 claims 1
- 238000011160 research Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 210000001044 sensory neuron Anatomy 0.000 description 1
Landscapes
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
A kind of aluminium section mechanical performance prediction method based on RBF neural, comprising the following steps: 1) survey the clustering of sample variable；2) direct mapping relations of the process parameters space to product mechanical performance index space in subspace；3) RBF neural network model of the technological parameter to product mechanical performance index in subspace and the total space；4) it is determined for the RBF neural parameter of aluminium section mechanical performance prediction；5) the production process of aluminium section intelligent optimization based on RBF neural.The present invention passes through clustering, the mapping relations in technological parameter to product mechanical performance space are analyzed in subspace, technological parameter is further analyzed in subspace and the total space to the RBF neural network model of product performance index, the RBF neural parameter for analyzing aluminium section mechanical performance prediction determines, and the production of intelligentization optimization of the aluminum profile based on RBF neural, this method is easy to use, it is easy to accomplish.
Description
Technical field
The present invention relates to a kind of profile prediction for mechanical performance method, especially a kind of aluminum profile based on RBF neural
Prediction for mechanical performance method.
Background technique
China is the higher country of aluminum profile yield accounting in the world, and aluminum profile output and usage amount be most in the world
More countries.Since aluminum profile has the characteristics that intensity height, good toughness, it is widely used in building and manufacturing industry, has been played huge
Effect, bring apparent Social benefit and economic benefit.
The production process of aluminum profile is a comprehensive complicated multifactor production process, and product quality is by many factors
Influence, performance (the mainly tensile strength sigma of chinese raw materials0) and Technical Parameters on Product Quality have very direct shadow
It rings.The optimum organization for determining raw material tensile strength and these technological parameters is the important link in aluminum profile production, to guarantee
Processing quality and reduction processing cost are of great significance.
The problems such as unstable, qualification rate is low for there are properties of product in aluminum profile production, pass through its production of analyzing and researching
Technical process, the author think, in order to improve the aluminium profile product quality of production, it is necessary to reinforce process study, specifically, need
Research work of both further carrying out: first is that being directed to the specific combination of technological parameter, aluminium profile product is relatively accurately predicted
Mechanical property；Second is that being directed to the mechanical property requirements of product, process parameter optimizing needed for determining production product is combined.
Evaluation and test aluminium profile product quality two important indicators be product tensile strength and elongation percentage, therefore, in order to compared with
Calculate to a nicety the mechanical property and Optimizing Process Parameters of product, needs to establish technological parameter and product tensile strength, elongation percentage
Between mapping relations.
Aluminum profile production process is an extremely complex physical process, and raw material are repeatedly rolled in process of production
Processing, the constraint type being subject to is comprehensive complicated, and rolled piece condition and state constantly change, and the process must keep each again
Metal mass flow is equal between rack and defers to law of conservation of energy, and process characteristic is more complicated and is difficult to grasp.It is embodied in:
1) there are many physical quantity involved in multivariable production process, they become with time course with spatial position change
Change, such as pressure, speed, flow, tension, and many physical quantitys be in the form of field existing for, such as stress field, strain
Field, velocity field etc..
2) in the above-mentioned variable of close coupling, any one variable, which changes, will all cause other multiple variables to become
Change.
3) many correlativities in nonlinear production process are nonlinear, here existing GEOMETRICALLY NONLINEAR,
There is physical nonlinearity problem.For example, stress-strain relation, mill stiffness curve, rolled piece plastic curve etc..
4) time variation production process can not maintain an ideal Best Point steadily in the long term, above-mentioned a large amount of non-thread
Property, close coupling variable vary at any time, and affect the variation of target control amount.
Therefore, directly from constraint condition and geometry deformation angle, technological parameter and the product for establishing aluminum profile are mechanical
Accurate Equations of Mathematical Physics are extremely difficult between performance indicator.
Determine that the conventional method of processing parameter has technological experiment method, theoretical calculation and limited in actual production at present
First method.
The advantages of technological experiment method is the rule for being able to reflect measured data in production or experiment, and resulting result accurately may be used
It leans on, the disadvantage is that higher cost, and experimental period is longer.
Theoretical calculation is by balance differential equation and condition of palsticity simultaneous, to find out the stress point when object plastic deformation
Cloth and strain regime, and then find out deformation force.Actually due to the complexity of production process, depth is non-linear, influence factor is many
It is more, have to introduce many simplification when being modeled and it is assumed that causing model accuracy lower, calculated result deviates practical work
Condition, even if using the parameter of measured data in production again correction model, due to the limitation of model structure itself, it is also difficult to adapt to
The requirement of production process.It is limited to the difficulty for modeling and solving, usual theoretical calculation can only solve some better simply two dimensions
Problem.
Though FInite Element can acquire the higher satisfactory solution of precision, needs iterate, and operation time is long, computational efficiency
It is low.The product mechanical performance parameter measured data that it is therefore necessary to process from processing parameter and accordingly, is researched and produced
Connection between technological parameter and product mechanical performance index.
Research achievement is less in terms of aluminum profile process optimization and performance prediction both at home and abroad, studies neither deep and incomplete
Qualitative analysis has only been made in face, without carrying out quantitative study, is far from satisfying that construction industry, manufacturing industry are fast-developing to be wanted
It asks.
Summary of the invention
In order to overcome the above-mentioned deficiency of the prior art, the present invention provides a kind of aluminium section mechanical based on RBF neural
Performance prediction method can establish the connection between production process of aluminium section parameter and product mechanical performance parameter, and method is simple,
It is easily achieved.
The technical solution used to solve the technical problems of the present invention is that: the following steps are included: 1) surveying the poly- of sample variable
Alanysis；2) direct mapping relations of the process parameters space to product mechanical performance index space in subspace；3) subspace and
RBF neural network model of the technological parameter to product mechanical performance index in the total space；4) it is directed to aluminium section mechanical performance prediction
RBF neural parameter determine；5) the production process of aluminium section intelligent optimization based on RBF neural.
Compared with prior art, a kind of aluminium section mechanical performance prediction method based on RBF neural of the invention, research
Affecting laws of the production technology to aluminium section mechanical performance, establish prediction and optimization system based on RBF neural, energy
Predict the mechanical performance of aluminum profile.It is for this complicated practical combinations optimization problem of aluminum profile process parameter optimizing, with aluminium
As final optimization pass target, the reasonable approach for the multiple-objection optimization found obtains the tensile strength and elongation percentage of product forms
Optimal procedure parameters combination was obtained, the mechanical performance of aluminum profile is improved.With saving material, cost is reduced, improves enterprise
Economic benefit, the good advantage of industrialization prospect.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the flow chart of one embodiment of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, belongs to protection scope of the present invention.
Referring to Fig. 1, a kind of aluminium section mechanical performance prediction method based on RBF neural of the present invention needs following step
It is rapid:
1) clustering of sample variable is surveyed
Using the method for clustering, centered on test samples variable, actual measurement known sample variable is handled, structure
The cluster most like with test samples variable is produced, to construct the subspace centered on test samples variable.
2) direct mapping relations of the process parameters space to product mechanical performance index space in subspace
According to the needs to study a question, variable X i has 5 components, respectively raw material tensile strength sigma in sample space0、
Sizing reduction △, drawing linear velocity v, idler wheel relief volume I and idler wheel distance s, are denoted as xi1, xi2, xi3, xi4, xi5 respectively.Xi pairs
The performance parameter variable Y i answered has 2 components, respectively the tensile strength sigma b of product and elongation percentage δ b, is denoted as yi1, yi2.If sub
In the Pk of space, xij is aki to the impact factor of yi1, and the impact factor to yi2 is bki.Within the scope of Pk, following relationship is utilized
XkAk=Yk1
XkBk=Yk2
Matrix A k and Bk are found out, later with the performance parameter of the mapping relations forecast test sample.
3) RBF neural network model of the technological parameter to product mechanical performance index in subspace and the total space
Radial primary function network is a kind of partial approximation network, and arbitrary continuation function can be theoretically approached with arbitrary accuracy.
Generally, RBF network, which can be considered, is made of n sensory neuron, h association's neuron and m reflection neuron for element
System.Due to the complexity of production process, directly from constraint condition and geometry deformation angle, aluminum profile is established
Accurate Equations of Mathematical Physics are extremely difficult between technological parameter and product mechanical performance index, even not possible with.So
The complex mapping relation between production process of aluminium section parameter and product mechanical performance is approached with RBF network.
4) it is determined for the RBF neural parameter of aluminium section mechanical performance prediction
RBF network neural member layer spread factor, network error and association's neuron number have the Approximation effect of network
It has a major impact.Spread factor wants sufficiently large, and the response range for enabling neuron to generate input covers sufficiently large region,
Simultaneously again cannot be too big, and making each neuron all has overlapped input vector response region；The value of network error is same
Sample can not be too big or too small, otherwise will have an adverse effect to RBF network performance.For association's neuron number, proposed adoption
Iterative manner determines that, when creating network, one RBF neuron of every addition calculates the error current of network.If network error
Less than desired value, stop iteration；Otherwise, neuron is continually added in network, until mean square error drops to desired mistake
Under difference or network neural member number reaches the maximum value of permission.In short, this project research is directed to aluminium profile product mechanicalness
Foreseeable RBF network parameter determines method.
5) the production process of aluminium section intelligent optimization based on RBF neural
The production process of aluminium profile product is extremely complex, it is impossible to directly establish the mathematical modulo of accurate description production process
Type.In this way, lacked the effective theory guidance of planning manufacturing condition, have in actual production using technological experiment method come
Determine manufacturing condition.For this problem, this project is quasi- carries out the production work based on genetic computation and radial primary function network
Skill optimizing research.Single-object problem is converted by multi-objective optimization question using unified objective function method；It is calculated using heredity
The global probabilistic search ability of method, carries out genetic search in entire processing parameter space；Utilize radial primary function network
Highly precise approach performance, establish the connection between production process of aluminium section parameter and product mechanical performance parameter, realize heredity
Individual fitness evaluation in calculating.
The application process of the embodiment of the present invention is as follows:
(1) acquisition of experimental design and known sample variable
Using conventional aluminium as research object, using orthogonal experiment design, one group of sample variable is designed；Produce this group of sample
The corresponding aluminium profile product sample of this variable, the mechanical performance of this group of sample is measured using WE-300 type universal testing machine,
As training sample.
(2) for the construction of the sample variable subspace of test samples prediction for mechanical performance
Known sample variable is handled using the method for clustering, constructs the cluster centered on each test samples,
Using each cluster member as the training sample of forecast test sample mechanical performance.When construction cluster, make each point of member of cluster
Measuring subspace made of envelope includes test samples.The determination of cluster scale and the construction of non-spherical cluster are ring collars herein
Section.
(3) determination of the foundation of prediction model and model parameter
The mechanical performance RBF network for establishing aluminium profile product in each subspace and the processing parameter total space respectively is pre-
Model is surveyed, research determines method for the RBF network parameter of aluminium profile product prediction for mechanical performance.
(4) model prediction accuracy and prediction stability analysis
It is divided to single output and two kinds of situations of dual output, in each subspace and the total space, research and training number of samples, training sample
This distribution form, RBF network parameter to the precision of prediction of aluminium profile product prediction for mechanical performance model and prediction stability influence,
Seek optimal model parameters combination.
(5) in aluminium profile product production technology Model for Multi-Objective Optimization each partial objectives for unitized processing
There are two the mechanical performance index of aluminium profile product product is main: tensile strength sigma b and elongation percentage δ b, the two are important
Degree is suitable, therefore the processing unitized to each partial objectives for of proposed adoption Objective Programming, it would be desirable to product mechanical performance as each
The optimal value of subhead scalar functions constructs unification according to sum of squares approach later according to the general requirement of multi-objective optimization question
Multi-objective optimization question is converted to single-object problem by objective function.
(6) solution of aluminium profile product production technology Model for Multi-Objective Optimization
Aluminium profile product production technology optimization problem is typical a higher-dimension, multi-peak, and objective function is unknown
Complex Constraints optimization problem.In view of genetic computation has extensive adaptability and global probabilistic search ability, this project proposed adoption
Genetic algorithm solves the aluminium profile product production technology optimization model based on RBF neural.
(7) verifying of aluminium profile product production technology optimization result
Using aluminium profile product production technology optimization the model calculation as process conditions, again with scheduled production base material
Sample is produced, its mechanical performance is measured, is made comparisons with desired performance indicator, the performance of technique Optimized model is examined.
The above is only presently preferred embodiments of the present invention, not does limitation in any form to the present invention, it is all according to
According to technical spirit of the invention, any simple modification and same variation are made to above embodiments, each fall within guarantor of the invention
Within the scope of shield.
Claims (6)
1. a kind of aluminium section mechanical performance prediction method based on RBF neural, characterized in that the following steps are included: 1) real
Survey the clustering of sample variable；2) the directly mapping in process parameters space to product mechanical performance index space is closed in subspace
System；3) RBF neural network model of the technological parameter to product mechanical performance index in subspace and the total space；4) it is directed to aluminum profile
The RBF neural parameter of prediction for mechanical performance determines；5) the production process of aluminium section intelligent optimization based on RBF neural.
2. a kind of aluminium section mechanical performance prediction method based on RBF neural according to claim 1, feature
It is that the process of the step 1) is as follows: using the method for clustering, centered on test samples variable, to the known sample of actual measurement
This variable is handled, and the cluster most like with test samples variable is constructed, thus in constructing with test samples variable and being
The subspace of the heart.
3. a kind of aluminium section mechanical performance prediction method based on RBF neural according to claim 1, feature
It is that the process of the step 2) is as follows:
According to the needs to study a question, variable X i has 5 components, respectively raw material tensile strength sigma in sample space0, sizing reduction
△, drawing linear velocity v, idler wheel relief volume I and idler wheel distance s, are denoted as xi1, xi2, xi3, xi4, xi5 respectively.The corresponding property of Xi
Energy parametric variable Yi has 2 components, respectively the tensile strength sigma b of product and elongation percentage δ b, is denoted as yi1, yi2；
If in the Pk of subspace, xij is aki to the impact factor of yi1, the impact factor to yi2 is bki.Within the scope of Pk, utilize
Relationship below
XkAk=Yk1
XkBk=Yk2
Matrix A k and Bk are found out, later with the performance parameter of the mapping relations forecast test sample.
4. a kind of aluminium section mechanical performance prediction method based on RBF neural according to claim 1, feature
It is that the process of the step 3) is as follows: is approached with RBF network between production process of aluminium section parameter and product mechanical performance
Complex mapping relation.
5. a kind of aluminium section mechanical performance prediction method based on RBF neural according to claim 1, feature
Be that the process of the step 4) is as follows: the spread factor of RBF network neural member layer wants sufficiently large, generates neuron to input
Response range can cover sufficiently large region, while again cannot be too big, and make each neuron all and have and is overlapped
Input vector response region；The value of its network error equally can not be too big or too small, otherwise will generate not to RBF network performance
Benefit influences；For association's neuron number, proposed adoption iterative manner is determined, when creating network, one RBF nerve of every addition
Member calculates the error current of network, if network error is less than desired value, stops iteration and otherwise continually adds neuron
In network, until mean square error drops under desired error or network neural member number reaches the maximum value of permission.
6. a kind of aluminium section mechanical performance prediction method based on RBF neural according to claim 1, feature
It is that the process of the step 5) is as follows: converts single object optimization for multi-objective optimization question using unified objective function method and ask
Topic；Using the global probabilistic search ability of genetic algorithm, genetic search is carried out in entire processing parameter space；Utilize diameter
To the highly precise approach performance of primary function network, the connection between production process of aluminium section parameter and product mechanical performance parameter is established
System realizes fitness evaluation individual in genetic computation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811352852.1A CN109871937A (en) | 2018-11-14 | 2018-11-14 | A kind of aluminium section mechanical performance prediction method based on RBF neural |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811352852.1A CN109871937A (en) | 2018-11-14 | 2018-11-14 | A kind of aluminium section mechanical performance prediction method based on RBF neural |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109871937A true CN109871937A (en) | 2019-06-11 |
Family
ID=66916953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811352852.1A Pending CN109871937A (en) | 2018-11-14 | 2018-11-14 | A kind of aluminium section mechanical performance prediction method based on RBF neural |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871937A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704956A (en) * | 2019-08-09 | 2020-01-17 | 太原科技大学 | Cold rolling mill data-driven technological parameter optimization method |
| CN112241832A (en) * | 2020-09-28 | 2021-01-19 | 北京科技大学 | Product quality grading evaluation standard design method and system |
| CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
-
2018
- 2018-11-14 CN CN201811352852.1A patent/CN109871937A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 邢邦圣: "冷轧带肋钢筋机械性能的智能预测方法与工艺参数优化研究", 《中国博士学位论文全文数据库工程科技Ⅰ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704956A (en) * | 2019-08-09 | 2020-01-17 | 太原科技大学 | Cold rolling mill data-driven technological parameter optimization method |
| CN110704956B (en) * | 2019-08-09 | 2022-04-19 | 太原科技大学 | Cold rolling mill data-driven technological parameter optimization method |
| CN112241832A (en) * | 2020-09-28 | 2021-01-19 | 北京科技大学 | Product quality grading evaluation standard design method and system |
| CN112241832B (en) * | 2020-09-28 | 2024-03-05 | 北京科技大学 | Product quality grading evaluation standard design method and system |
| CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10814448B2 (en) | Comprehensive performance evaluation method for CNC machine tools based on improved pull-off grade method | |
| CN109871937A (en) | A kind of aluminium section mechanical performance prediction method based on RBF neural | |
| CN101863088B (en) | Method for forecasting Mooney viscosity in rubber mixing process | |
| CN104651559B (en) | Blast furnace liquid iron quality online forecasting system and method based on multivariable online sequential extreme learning machine | |
| CN104899425A (en) | Variable selection and forecast method of silicon content in molten iron of blast furnace | |
| CN102693452A (en) | Multiple-model soft-measuring method based on semi-supervised regression learning | |
| CN102324040B (en) | Methods for acquiring equivalent load spectrum and estimating residual fatigue life of bridge crane | |
| CN103514491A (en) | Power load forecasting method | |
| CN109255173A (en) | Consider the structural realism interval computation method of bounded-but-unknown uncertainty | |
| CN110135635A (en) | A kind of region electric power saturation load forecasting method and system | |
| CN111008870A (en) | Regional logistics demand prediction method based on PCA-BP neural network model | |
| Xiao et al. | The chaotic characteristic of the carbon-monoxide utilization ratio in the blast furnace | |
| CN114036452B (en) | Yield evaluation method applied to discrete production line | |
| CN103344740B (en) | Based on the glutamic acid production concentration online soft sensor method of multi input Wiener model | |
| CN102207474B (en) | Intelligent method for identifying alloy brand based on XRF (X-ray fluorescence) spectrometer | |
| CN110458479A (en) | A kind of new energy field technological achievement is converted into the potential evaluation method of technical standard | |
| CN105243608A (en) | Line project cost estimation method based on power transmission and transformation project cost design elements | |
| CN112330030B (en) | System and method for predicting requirements of expansion materials | |
| US11987855B2 (en) | Method and system for determining converter tapping quantity | |
| Kitsuregawa | Transformational Role of Big Data in Society 5.0 | |
| CN103543637B (en) | A kind of tool environment temperature Analytic modeling method | |
| CN112819354A (en) | Method and device for evaluating competitiveness of oversea mining project | |
| Chen-xu et al. | Auto regressive moving average (ARMA) prediction method of bank cash flow time series | |
| CN109635452A (en) | A kind of efficient multimodal stochastic uncertainty analysis method | |
| Wang et al. | Short-term prediction of power consumption for large-scale public buildings based on regression algorithm |
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: 20190611 |