CN114564884B - Design method for simultaneously optimizing multiple electric contact performances of electric contact material - Google Patents
Design method for simultaneously optimizing multiple electric contact performances of electric contact material Download PDFInfo
- Publication number
- CN114564884B CN114564884B CN202210139492.7A CN202210139492A CN114564884B CN 114564884 B CN114564884 B CN 114564884B CN 202210139492 A CN202210139492 A CN 202210139492A CN 114564884 B CN114564884 B CN 114564884B
- Authority
- CN
- China
- Prior art keywords
- electric contact
- performance
- machine learning
- performances
- test conditions
- 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.)
- Active
Links
- 239000000463 material Substances 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000013461 design Methods 0.000 title claims abstract description 24
- 238000012360 testing method Methods 0.000 claims abstract description 48
- 238000002360 preparation method Methods 0.000 claims abstract description 38
- 238000005457 optimization Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000010801 machine learning Methods 0.000 claims abstract description 28
- 239000000126 substance Substances 0.000 claims abstract description 21
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000003466 welding Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000002474 experimental method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 229910045601 alloy Inorganic materials 0.000 claims description 6
- 239000000956 alloy Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 12
- 238000011161 development Methods 0.000 abstract description 7
- 239000000654 additive Substances 0.000 description 4
- 230000000996 additive effect Effects 0.000 description 4
- 229910052802 copper Inorganic materials 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 229910001325 element alloy Inorganic materials 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910000510 noble metal Inorganic materials 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/26—Composites
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Manufacture Of Switches (AREA)
Abstract
The invention relates to a design method for simultaneously optimizing multiple electric contact performances of an electric contact material, which comprises the following steps: searching a plurality of electric contact performances such as chemical formula, preparation process, test conditions, arcing time, arcing energy, fusion welding force, contact resistance, quality change value and the like of the electric contact material, and taking the electric contact performances as a data set sample; randomly dividing a data set into a training set and a testing set, respectively modeling the electric contact performance by adopting a plurality of machine learning algorithms, and screening out the machine learning algorithms which have better performance on a plurality of electric contact performance models; performing multi-performance optimization on the established prediction model by adopting a multi-objective optimization algorithm, and improving the model through iterative optimization to finally realize development of a novel electric contact material with excellent comprehensive performance; the invention has the advantages of simplicity, convenience, rapidness, low cost, high accuracy and the like for optimizing the electrical contact performance of the multi-element electrical contact material based on reliable literature data and machine learning technology.
Description
Technical Field
The invention relates to the field of electric contact materials, in particular to a design method for simultaneously optimizing various electric contact performances of an electric contact material.
Technical Field
The electric contact material is a functional carrier for the electric appliance to complete the current connection, conduction and disconnection and signal generation and transmission, the electric contact performance is the key for influencing the reliability of electric and electronic engineering, and the electric contact material has praise of the heart of a low-voltage electric appliance in the field of the piezoelectric appliance and is widely applied to products such as relays, circuit breakers, contactors, sensors, industrial control and the like. With the development of the application field of the electric contact material, more severe requirements are put on the electric contact service performance of the electric contact material, and at present, a novel electric contact material is mainly developed by introducing a novel strengthening component, changing the content of an additive element, optimizing a preparation process and other methods. However, most of alloys in the modification process are quaternary or even other multi-element alloys, and the problems of large research and development workload and the like caused by component types, component content, preparation process and the like are faced during design and development. The traditional trial-and-error method searches for a new electric contact material in huge material components and preparation process space, and faces the problems of long development period, high cost (most of the electric contact materials are noble metal-based materials) and the like. Therefore, a new development method of the electrical contact material is urgently needed to solve the defects of the conventional development method.
Real-world engineering optimization problems typically require simultaneous optimization of multiple targets, and the evaluation of these objective functions is expensive due to the reliance on physical experimentation, which is referred to as an expensive multi-target optimization problem. For example, for electrical contact materials, when the three properties of arcing time, arcing energy and fusion welding force are optimally represented, the performance of both the contact resistance and the quality change value is not good, resulting in an unsatisfactory overall service condition of the final electrical contact material. The method has the characteristics of high cost, low efficiency, long period, wide scale and the like, and is difficult to find out the component materials with better performance of the 5 electric contact performances. Therefore, the design and research of materials with better performance and optimal comprehensive performance are always difficult problems in the field of materials.
Disclosure of Invention
The invention aims to overcome the defects of long experimental period, high experimental cost and the like in the prior art for simultaneously optimizing various electric contact performances of four or more electric contact materials, and provides a method for simultaneously optimizing the various electric contact performances of the electric contact materials based on a machine learning technology, which is simple, convenient, low in cost and labor-saving. The present invention attempts to achieve such multi-performance simultaneous optimization using machine-learned multi-objective optimization strategies.
The aim of the invention is achieved by the following technical scheme:
A design method for simultaneously optimizing a plurality of electrical contact properties of an electrical contact material, comprising the steps of:
1) Searching chemical formulas, preparation processes, test conditions, arcing time, arcing energy, fusion welding force, contact resistance and quality change values of the electric contact materials from the channels of literature, public databases, self-contained databases and the like, taking the chemical formulas, the preparation processes and the electric contact experimental test conditions as data set samples, wherein the chemical formulas, the preparation processes and the electric contact experimental test conditions are taken as inputs, and the arcing time, the arcing energy, the fusion welding force, the contact resistance and the quality change values are predicted target values of a machine learning model;
2) Randomly dividing the data set into a training set (80-90%) and a test set (10-20%);
3) The method comprises the steps of adopting an integration algorithm Xgboost, K nearest neighbor, an artificial neural network, support vector regression, naive Bayes, random forest and other machine learning algorithms to respectively model arcing time, arcing energy, fusion welding force, contact resistance and quality change values, and respectively adopting the effects of comprehensively analyzing and modeling parameters such as mean square error MSE, mean absolute error MAE, root mean square error RMSE and the like. Finally screening out machine learning algorithms with better performance on 5 electric contact performance models;
4) For a specific preparation process and electric contact experimental test conditions, a component space is established by selecting an element type search range and the minimum variation of each element, performance prediction is carried out, and the performance of the electric contact material is rapidly and comprehensively optimized by combining a multi-objective optimization algorithm-non-dominant genetic algorithm (NSGA-II). The electrical contact performance at the Pareto front was chosen from the predicted results to be relatively good data for the new design alloy. For sample data of different preparation processes and electric contact experiment test conditions, selecting search ranges of preparation process types, electric contact experiment test conditions and element types, and search conditions of preparation process screening types, electric contact experiment test condition screening conditions and minimum element variation, establishing preparation, test and component search spaces, performing performance prediction, and performing multi-objective performance rapid comprehensive optimization on the performance of an electric contact material by combining a multi-objective optimization algorithm-non-dominant genetic algorithm (NSGA-II). Based on the thought, the chemical composition, the preparation process and the electrical contact experiment test conditions are optimized simultaneously;
5) For optimized chemical components, preparation process and electric contact experimental test conditions, selecting several components, processes or test conditions with the largest uncertainty of a predicted result, performing experimental synthesis preparation and electric contact performance measurement, expanding the components, the processes or the test conditions to an initial data set, and iteratively improving a machine learning model;
6) Based on a final optimized and improved machine learning model, a novel electric contact material with excellent performances such as arcing time, arcing energy, fusion welding force, contact resistance, quality change value and the like is designed and developed according to the requirements of chemical components, a preparation process and electric contact experimental test conditions.
Compared with the prior art, the invention has the following beneficial effects:
1. the method has better effect on optimizing various electric contact performances of the four-element to multi-element electric contact material at the same time, and has universality;
2. the method can limit the preparation process conditions, the actual industrial use conditions (namely the experimental test conditions mentioned above) and the types and the ranges of the elements of the electric contact materials according to the use requirements of the electric contact performance, and finally gives candidate chemical formulas meeting the design requirements and the limit conditions. The method effectively accelerates the design efficiency of the new material and overcomes the defects of the traditional trial-and-error method.
Drawings
FIG. 1 is a basic flow chart of the design method of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and a preferred embodiment.
Example 1: the optimized design of the novel Ag-Cu-Ni-V electric contact material.
The method comprises the following specific steps:
1) The design concept and flow of this embodiment are shown in fig. 1, and chemical formula, preparation process, test condition, arcing time, arcing energy, fusion welding force, contact resistance and quality change values of the electrical contact material are searched from the own database, and are used as data set samples, wherein the chemical formula, preparation process and electrical contact experimental test condition are used as inputs, and the arcing time, arcing energy, fusion welding force, contact resistance and quality change values are predicted target values of the machine learning model. In this example, the same preparation process (casting method) and test conditions (test using an electrical contact material comprehensive parameter tester, model: JF04C, specific test parameters are shown in Table 1) were adopted for the data obtained from the database, so that the input values only consider the chemical components, and the chemical formulas of part of the electrical contact materials and the experimental values of the properties of various electrical contact materials are shown in Table 2:
Table 1 electrical contact test parameters
| Test parameters | Setting value |
| Circuit parameters | DC, 24V,20A |
| Number of tests | 20000 Times |
| Contact force | 40cN |
| Contact spacing | 1mm |
| Frequency of | 2Hz(0.5s) |
| Atmosphere of | Air-conditioner |
Table 2 collects experimental values of the chemical formulas of the partial electric contact materials and the properties of various electric contact materials
2) Randomly dividing the data set into a training set (80-90%) and a test set (10-20%);
3) The method comprises the steps of adopting an integration algorithm Xgboost, K nearest neighbor, an artificial neural network, support vector regression, naive Bayes, random forest and other machine learning algorithms to respectively model arcing time, arcing energy, fusion welding force, contact resistance and quality change values, and respectively adopting the effects of comprehensively analyzing and modeling parameters such as mean square error MSE, mean absolute error MAE, root mean square error RMSE and the like. Finally, screening out a machine learning algorithm which has better performance on 5 electric contact performance models, aiming at the collected data, the model effect of support vector regression is best, the degree of overfitting is low, and the error of a test set is within 10%;
4) For this example, the preparation process and the electrical contact experimental test conditions were already fixed, so Cu, ni and V3 elements were taken as additive elements, and the search range (mass fraction) of each element was selected as Cu: 0-40%, ni: 0-10%, V: and 0-1.5%, wherein each element establishes a component space at a spacing of 0.1% (mass fraction) for performance prediction. And the performance of the electric contact material is subjected to multi-objective performance rapid comprehensive optimization by combining a multi-objective optimization algorithm, namely a non-dominant genetic algorithm (NSGA-II). The electrical contact performance at the Pareto front was chosen from the predicted results to be relatively good data for the new design alloy.
5) For the chemical components optimized under the specific preparation process and the electric contact experimental test conditions, selecting a plurality of components with the largest uncertainty of the prediction result, performing experimental synthesis preparation and electric contact performance measurement, expanding the components to an initial data set, and iteratively improving a machine learning model;
6) Based on a machine learning model of final optimization improvement, in the process of simultaneously optimizing the multi-objective performance of the electric contact performance of Ag-Cu-Ni-V, the final optimization components are as follows: ag-10.56Cu-0.42Ni-0.22V, and the corresponding electric contact performance is respectively as follows: arcing time: 4ms, arcing energy: 265mJ, fusion welding force: 14cN, contact resistance: 3.62mΩ and mass change value: 0.25mg, the optimization results of which are better than the performance of the component correspondence of the collected data. Experiments prove that the error of the predicted value and the experimental value of the multi-target performance of the electric contact material is less than 8%. Therefore, the method of the invention has better effect in optimizing the electrical contact performance of the electrical contact material at the same time.
Example 2: the optimized design of the novel Ag-Cu-Ni-Ce electric contact material.
This embodiment is substantially identical to steps 1), 2), 3) and 5) of embodiment 1 above, with the exception of steps 4) and 6):
for this example, the preparation process and the test conditions of the electrical contact experiment have been fixed, so Cu, ni and Ce 3 elements are taken as additive elements, and the search range (mass fraction) of each element is selected as Cu: 0-40%, ni: 0-10%, ce: and 0-1.5%, wherein each element establishes a component space at a spacing of 0.1% (mass fraction) for performance prediction. And the performance of the electric contact material is subjected to multi-objective performance rapid comprehensive optimization by combining a multi-objective optimization algorithm, namely a non-dominant genetic algorithm (NSGA-II). The electrical contact performance at the Pareto front was chosen from the predicted results to be relatively good data for the new design alloy.
Based on a machine learning model of final optimization improvement, in the process of simultaneously optimizing the multi-target performance of the electric contact performance of Ag-Cu-Ni-Ce, the final optimization components are as follows: ag-9.98Cu-0.79Ni-0.11Ce, and the corresponding electric contact performance is respectively as follows: arcing time: 4ms, arcing energy: 243mJ, fusion welding force: 13cN, contact resistance: 3.44mΩ and mass change value: 0.21mg, the optimization results of which are better than the performance of the component correspondence of the collected data. Experiments prove that the error of the predicted value and the experimental value of the multi-target performance of the electric contact material is less than 8%.
Example 3: the optimized design of the novel Ag-Cu-Ni-V-Y electric contact material.
This embodiment is substantially identical to steps 1), 2), 3) and 5) of embodiment 1 above, with the exception of steps 4) and 6):
for this example, the preparation process and the electrical contact experimental test conditions have been fixed, so Cu, ni, V and Y4 elements were taken as additive elements, and the search range (mass fraction) of each element was selected as Cu: 0-40%, ni: 0-10%, V:0 to 1.5 percent, Y: and 0-1.5%, wherein each element establishes a component space at a spacing of 0.1% (mass fraction) for performance prediction. And the performance of the electric contact material is subjected to multi-objective performance rapid comprehensive optimization by combining a multi-objective optimization algorithm, namely a non-dominant genetic algorithm (NSGA-II). The electrical contact performance at the Pareto front was chosen from the predicted results to be relatively good data for the new design alloy.
Based on a final optimized and improved machine learning model, in the process of optimizing the multi-target performance of the electric contact performance of Ag-Cu-Ni-V-Y, the final optimized components are as follows: ag-10.45Cu-0.29Ni-0.21V-0.13Y, and the corresponding electrical contact properties are respectively as follows: arcing time: 4ms, arcing energy: 213mJ, fusion welding force: 12cN, contact resistance: 3.50mΩ and mass change value: 0.18mg, the optimization results of which are better than the performance of the component correspondence of the collected data. Experiments prove that the error of the predicted value and the experimental value of the multi-target performance of the electric contact material is less than 8%.
In summary, the above embodiment is based on the machine learning technology, and is directed to a method for optimizing multiple performances of a multi-element electrical contact material simultaneously according to the design requirement of multiple performances of the electrical contact material, and firstly, searching chemical formulas, preparation processes, test conditions, arcing time, arcing energy, fusion welding force, contact resistance and quality variation values of the electrical contact material from the channels of literature, public databases, self-contained databases and the like, and taking the chemical formulas, the preparation processes, the test conditions, the arcing time, the arcing energy, the fusion welding force, the contact resistance and the quality variation values as data set samples; randomly dividing a data set into a training set and a testing set, respectively modeling the electric contact performance by adopting a plurality of machine learning algorithms, and screening out the machine learning algorithms which have better performance on 5 electric contact performance models; performing multi-performance optimization on the established prediction model by adopting a multi-objective optimization algorithm, and improving the model through iterative optimization to finally realize development of a novel electric contact material with excellent comprehensive performance; the invention has the advantages of simplicity, convenience, rapidness, low cost, high accuracy and the like for optimizing the electrical contact performance of the quaternary or even multi-element electrical contact material based on reliable literature data and machine learning technology.
The above embodiments are only examples of the present invention, and the above embodiments may be changed without departing from the scope of the present invention, and are not to be considered as illustrative, and not limiting the scope of the present invention.
Claims (5)
1. A design method for simultaneously optimizing a plurality of electrical contact properties of an electrical contact material, comprising the steps of:
1) Searching the chemical formula, the preparation process, the test conditions and various electric contact performances of the electric contact material, and taking the chemical formula, the preparation process, the test conditions and various electric contact performances as data set samples; wherein the plurality of electrical contact properties includes arcing time, arcing energy, fusion welding force, contact resistance, and mass variance;
2) Taking chemical formulas, a preparation process and electric contact experimental test conditions as inputs, and taking various electric contact performances as predicted target values of a machine learning model;
3) Randomly dividing the data set into a training set and a testing set;
4) Modeling a plurality of electric contact performances by adopting a plurality of machine learning algorithms, and screening out the machine learning algorithms which have better performances on the plurality of electric contact performance models;
5) The adopted machine learning algorithm is the machine learning algorithm with good performance of the model screened in the step 4), for specific preparation process and electric contact experiment test conditions, a component space is established by selecting element type search range and minimum variation of each element, performance prediction is carried out, and multi-objective performance rapid comprehensive optimization is carried out on the performance of the electric contact material by combining a multi-objective optimization algorithm; wherein the multi-objective optimization algorithm adopts a non-dominant genetic algorithm NSGA-II to carry out multi-objective performance rapid comprehensive optimization on 5 electrical contact performances of the electrical contact material;
6) For sample data of different preparation processes and electric contact experiment test conditions, selecting a preparation process type, an electric contact experiment test condition, a search range of element types, a preparation process screening type, an electric contact experiment test condition screening condition and a search condition of minimum element variation, establishing preparation, test and component search spaces, performing performance prediction, and performing multi-objective performance rapid comprehensive optimization on the performance of an electric contact material by combining a multi-objective optimization algorithm;
7) For optimized chemical components, preparation process and electric contact experimental test conditions, selecting several components, processes or test conditions with the largest uncertainty of a predicted result, performing experimental synthesis preparation and electric contact performance measurement, expanding the components, the processes or the test conditions to an initial data set, and iteratively improving a machine learning model; based on the final optimized and improved machine learning model, various novel electric contact materials with excellent electric contact performance are designed according to the requirements of chemical components, preparation process and electric contact experimental test conditions.
2. The design method according to claim 1, wherein in the performance model modeling process in the step 4), the plurality of machine learning algorithms selected include an integration algorithm Xgboost, K nearest neighbor, artificial neural network, support vector regression, naive bayes and random forest.
3. The design method according to claim 1, wherein in the step 4), the effects of modeling are comprehensively analyzed by mean square error MSE, mean absolute error MAE and root mean square error RMSE parameters, respectively.
4. The design method according to claim 1, wherein the step 5) selects the data of relatively good electrical contact performance at the Pareto front from the predicted results obtained in the electrical contact performance prediction as the new design alloy.
5. The method of any one of claims 1-4, wherein in step 3), the training set is 80-90% and the test set is 10-20%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210139492.7A CN114564884B (en) | 2022-02-16 | 2022-02-16 | Design method for simultaneously optimizing multiple electric contact performances of electric contact material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210139492.7A CN114564884B (en) | 2022-02-16 | 2022-02-16 | Design method for simultaneously optimizing multiple electric contact performances of electric contact material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114564884A CN114564884A (en) | 2022-05-31 |
| CN114564884B true CN114564884B (en) | 2024-04-19 |
Family
ID=81714377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210139492.7A Active CN114564884B (en) | 2022-02-16 | 2022-02-16 | Design method for simultaneously optimizing multiple electric contact performances of electric contact material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114564884B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103348416A (en) * | 2011-02-09 | 2013-10-09 | 因派科特涂料公司 | Material for providing an electrically conducting contact layer, a contact element with such layer, method for providing the contact element, and uses of the material |
| CN105385877A (en) * | 2015-11-09 | 2016-03-09 | 昆明贵金属研究所 | Novel silver-based electrical contact composite material and preparing method thereof |
| CN110428876A (en) * | 2019-07-31 | 2019-11-08 | 东北大学 | A kind of steel material design method of the machine learning algorithm based on physical instruction |
| AU2020101453A4 (en) * | 2020-07-23 | 2020-08-27 | China Communications Construction Co., Ltd. | An Intelligent Optimization Method of Durable Concrete Mix Proportion Based on Data mining |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020114686A1 (en) * | 2018-12-03 | 2020-06-11 | Asml Netherlands B.V. | Method to predict yield of a semiconductor manufacturing process |
-
2022
- 2022-02-16 CN CN202210139492.7A patent/CN114564884B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103348416A (en) * | 2011-02-09 | 2013-10-09 | 因派科特涂料公司 | Material for providing an electrically conducting contact layer, a contact element with such layer, method for providing the contact element, and uses of the material |
| CN105385877A (en) * | 2015-11-09 | 2016-03-09 | 昆明贵金属研究所 | Novel silver-based electrical contact composite material and preparing method thereof |
| CN110428876A (en) * | 2019-07-31 | 2019-11-08 | 东北大学 | A kind of steel material design method of the machine learning algorithm based on physical instruction |
| AU2020101453A4 (en) * | 2020-07-23 | 2020-08-27 | China Communications Construction Co., Ltd. | An Intelligent Optimization Method of Durable Concrete Mix Proportion Based on Data mining |
Non-Patent Citations (2)
| Title |
|---|
| 基于集成学习的编译优化参数选择方法研究;刘慧;姚金阳;赵荣彩;;信息工程大学学报;20190615(第03期);全文 * |
| 昆明贵金属研究所计算材料学科的发展;陈松等;贵金属;20131130;第34卷(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114564884A (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114219147A (en) | Power distribution station fault prediction method based on federal learning | |
| Bernard et al. | Forest-RK: A new random forest induction method | |
| CN114580272A (en) | Design method for simultaneously optimizing conductivity and hardness of multi-element electric contact alloy | |
| CN114564884B (en) | Design method for simultaneously optimizing multiple electric contact performances of electric contact material | |
| CN106991074B (en) | Accelerated degradation test optimization design method based on principle of acceleration factor invariance | |
| CN113627672A (en) | Circuit breaker dynamic contact resistance prediction method based on partial least square estimation | |
| CN116720058A (en) | Method for realizing key feature combination screening of machine learning candidate features | |
| CN116028871A (en) | GIS equipment PD type judging method adopting improved marine predator algorithm to optimize SVM | |
| CN114021474B (en) | Relay service life prediction method based on improved gray wolf algorithm optimization | |
| CN115831263A (en) | Method and system for optimizing qualification rate of electrolytic refining high-purity indium product | |
| CN113222145B (en) | MODTT-EMD-based time sequence hybrid prediction method | |
| Ćosović et al. | BGP anomaly detection with balanced datasets | |
| Todd et al. | Directed multiple objective search of design spaces using genetic algorithms and neural networks | |
| RU2703874C1 (en) | Method of monitoring and predicting operation of a gas turbine plant using a matrix of defects | |
| CN108319139A (en) | A kind of industrial process pivot analysis and Neural Network Optimization modeling method | |
| CN117275599A (en) | High-temperature alloy component and process design method | |
| CN114487805A (en) | Circuit breaker fault diagnosis method based on genetic algorithm and clustering algorithm | |
| CN118010614B (en) | Corrosion resistance detection method and system for blending type interpenetrating network thermoplastic elastomer | |
| Murphy et al. | Univariate vs multivariate time series forecasting with transformers | |
| Gilbert et al. | Genetic programming-based variable selection for high-dimensional data | |
| CN118395880B (en) | Intermittent process temperature prediction method of multi-stage fusion cyclic neural network | |
| CN111046606A (en) | Global time-varying sensitivity calculation method for electromagnetic relay life cycle | |
| CN112490516B (en) | Power battery maintenance mode generation system and method | |
| Meyer et al. | Analytics for the optimization of the soybean oil purification process | |
| CN111667153B (en) | Resident electricity consumption behavior analysis method based on gray correlation analysis method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |