CN112326540A - Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium - Google Patents
Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112326540A CN112326540A CN202011069396.7A CN202011069396A CN112326540A CN 112326540 A CN112326540 A CN 112326540A CN 202011069396 A CN202011069396 A CN 202011069396A CN 112326540 A CN112326540 A CN 112326540A
- Authority
- CN
- China
- Prior art keywords
- network model
- alloy
- zirconium
- corrosion
- corrosion resistance
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
- G01N17/006—Investigating resistance of materials to the weather, to corrosion, or to light of metals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N5/00—Analysing materials by weighing, e.g. weighing small particles separated from a gas or liquid
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental & Geological Engineering (AREA)
- Environmental Sciences (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention provides a nuclear zirconium-4 alloy corrosion resistance prediction method based on a BP network model, which comprises the following steps: obtaining an original data sample, extracting characteristic information, constructing a BP network model, and verifying the BP network model. The present invention relates to an electronic device and a storage medium for performing the above method. Aiming at the problem of influence prediction of different alloy components on the corrosion performance of the nuclear zirconium-4 alloy, the BP network model is taken as the center, the principal component analysis technology is combined to perform dimensionality reduction and denoising treatment on input variables, characteristic information is extracted, the prediction precision and generalization capability of the traditional BP network model are effectively improved, a nonlinear mapping relation model of the zirconium-4 alloy component content and the corrosion performance is constructed, the problems of long research and development period, low efficiency and cost waste caused by the fact that a large number of experimental methods are used for corrosion performance research at present are solved, and a new technical means is provided for research and development of novel zirconium alloys.
Description
Technical Field
The invention relates to the technical field of nuclear-grade zirconium materials, in particular to a method for predicting corrosion resistance of a nuclear zirconium-4 alloy based on a BP network model, electronic equipment and a storage medium.
Background
Zirconium-4 alloy has been used as a structural material for Pressurized Water Reactors (PWRS) and Boiling Water Reactors (BWRS), such as cladding tubes, end plugs, spacer grids, etc., due to its excellent nuclear properties. The corrosion resistance is the most critical one of the multi-core performance of the zirconium-4 alloy. In actual production, due to a long process chain, many factors affecting corrosion performance, such as alloy composition, hot working process, cumulative annealing parameter Σ a value, surface state, corrosion environment, and the like, are among the most important ones as compared with other factors, which are alloy compositions (including element types and addition amounts) as sources.
The corrosion performance of the zirconium-4 alloy sample is influenced by the contents of alloy and impurity elements, and foreign research work mainly relates to the alloy elements Sn, Fe and Cr and the impurity elements C, Si, P, Al and the like. Eucken et al found that by processing zirconium-4 alloy samples of small 1mm thickness in different compositional ratios of the plate, followed by autoclave corrosion: within the range of zirconium-4 composition required by ASTM standards, uniform corrosion performance at 400 ℃ becomes worse as the Sn content increases; the content of Fe and Cr is increased from 0.21 percent to 0.36 percent of the upper limit, and the corrosion can be obviously improved; the corrosion performance is continuously deteriorated when the element C is added to 283ppm from 40ppm which is extremely low; the corrosion performance is not obviously changed by increasing the contents of Si, P and Al. The microstructure analysis of Makoto Harada et al shows that if the surface oxide of the zirconium-4 alloy is converted from a monoclinic structure to a tetragonal or face-centered cubic structure, the 'stress relief' caused in the conversion process is likely to be beneficial to the improvement of uniform corrosion performance, and the increase of the Sn content is likely to accelerate the corrosion conversion due to the effect of stabilizing the monoclinic structure oxide. In China, a small rolling mill is mainly used by Yaomei and other people of Shanghai university to prepare plate samples in a laboratory, and the influence of different elements such as Sn, Cu, Nb, O and the like on the corrosion behavior of the zirconium alloy under different medium conditions is researched. The research work adopts a single-factor variable control method, so that the experimental amount is large, and the research and development cost is high; meanwhile, because the alloy components influencing the corrosion performance of the zirconium-4 alloy are various in types and the elements have interaction influence, the method is a multi-dimensional nonlinear mapping problem and is difficult to express the internal relation by establishing a simple mathematical model. Although the traditional experimental method plays a positive role in the development of corrosion technology, the research and development requirements of the zirconium-4 alloy in the aspect of predicting the corrosion performance of the zirconium-4 alloy are far from being met. Therefore, if a mathematical model between different alloy components and corrosion performance can be constructed by means of a novel technical means under the condition of as few experiments as possible, the model is utilized to realize rapid prediction and analysis of the influence of different components on the corrosion performance, and the method has an important role in promoting the research and development of novel zirconium alloys in China.
The artificial neural network technology is a super-large-scale nonlinear continuous time self-adaptive information processing technology, and has the advantages of few training samples, fast data processing, comprehensive information search, strong learning capacity, fast convergence modeling and the like, so that the artificial neural network technology is widely popularized and applied in the field of domestic processing and manufacturing in recent years. Among them, the BP (Back Propagation) neural network technology is most successfully and widely applied. The BP network is also called a feedforward neural network, is an algorithm for training error back propagation, has a simple principle and higher calculation accuracy, and is applied to a plurality of fields at present. The invention patent (CN 107609647A) discloses a roller alloy mechanical property prediction method based on a BP neural network, and the inventor realizes the screening of the optimal parameter combination by constructing a BP network model among the components, the heat treatment process parameters and the mechanical property of the roller alloy. The invention patent (CN 111241750A) discloses a BP network cold-rolled strip steel mechanical property prediction method combined with a genetic algorithm, and the inventor takes a BP network as a center, improves the BP network by using the genetic algorithm, establishes a prediction model of the cold-rolled strip steel mechanical property and improves the production efficiency. However, for a long time, the nuclear grade zirconium material has high production cost and great technical difficulty, and domestic research work is still at the beginning stage. Therefore, a method for applying the BP neural network technology to the prediction of the corrosion performance of the nuclear-grade zirconium material is urgently needed to solve the problems that the existing research work adopts a single-factor control variable method, the experimental amount is large, the research and development cost is high, and the internal relation of different alloy components is difficult to express by establishing a simple mathematical model.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a nuclear zirconium-4 alloy corrosion resistance prediction method based on a BP network model, which is used for predicting the nuclear zirconium-4 alloy corrosion resistance under different alloy components, so that the influence analysis of the corrosion resistance of the alloy under the action of single elements and interaction is realized, and a new efficient technical means is provided for optimizing the optimal alloy component combination and preparing the zirconium-4 alloy with excellent corrosion resistance.
The invention provides a nuclear zirconium-4 alloy corrosion resistance prediction method based on a BP network model, which comprises the following steps:
obtaining an original data sample, taking corrosion weight gain of a nuclear zirconium-4 alloy plate sample as a research object, determining an input variable and an output variable, and carrying out corrosion detection to obtain the original data sample;
constructing a BP network model, determining a BP network topological structure, setting a training function, a learning rate, a transfer function, training steps and a maximum allowable error, and constructing the BP network model with different alloy components and corrosion weight gain through a training sample selected from the original data sample;
and verifying the BP network model, namely verifying the constructed BP network model through a test sample selected from the original data samples.
Further, in the step of obtaining the original data sample, the input variables include mass percentage of Sn, mass percentage of Fe + Cr, mass percentage of C, mass percentage of Si, mass percentage of X, and corrosion period, and the output variable is corrosion gain of the sample.
Further, in the step of obtaining the original data sample, the size of the plate sample is 20mm × 20mm × 2mm, and the plate sample is subjected to a 400 ℃/10.3MPa 300-day corrosion test in a reaction kettle, wherein the weight increment period of the sampling test is 10 th, 30 th, 60 th, 80 th, 100 th, 130 th, 150 th, 180 th, 210 th, 240 th, 270 th and 300 th days respectively.
Further, extracting characteristic information between the step of obtaining the original data sample and the step of constructing the BP network model, performing principal component analysis on the input variable, and extracting the characteristic information to form a new low-dimensional input variable.
Further, in the step of extracting the characteristic information, SPSS-13.0 software is used for carrying out principal component analysis, and 6 component input variables with certain correlation are recombined into 3 new independent comprehensive variables.
Further, in the step of constructing the BP network model, the BP network topology is three layers, namely an input layer, a hidden layer and an output layer, the number of nodes of the input layer is 3, the number of nodes of the output layer is 1, and the value range of the number of nodes of the hidden layer is [2-10 ].
Further, in the step of constructing the BP network model, the training function is tranlm, the learning function is LEARGDM, the transfer functions are Tansig and Purelin, the learning rate is set to 0.1, the maximum iteration number is 2000, and the target error isE is 1x10-2。
Furthermore, in the step of verifying the BP network model, samples which do not participate in the training of the BP network model are selected from the new samples, the constructed BP network model is subjected to prediction inspection, and the generalization capability of the model is evaluated through comparison of relative errors between actual measurement and predicted values.
An electronic device, comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for executing a nuclear zirconium-4 alloy corrosion resistance prediction method based on a BP network model.
A computer-readable storage medium having stored thereon a computer program for executing, by a processor, a method for predicting corrosion resistance of a zirconium-4 alloy for a core based on a BP network model.
Compared with the prior art, the invention has the beneficial effects that:
aiming at the problem of influence prediction of different alloy components on the corrosion performance of the nuclear zirconium-4 alloy, the BP network model is taken as the center, the principal component analysis technology is combined to perform dimensionality reduction and denoising treatment on input variables, characteristic information is extracted, the problems of overfitting, slow convergence speed, poor generalization capability and the like commonly existing in the application of the traditional BP network method in forecasting are solved, the prediction precision and generalization capability of the traditional BP network model are effectively improved, the nonlinear mapping relation model of the zirconium-4 alloy component content and the corrosion performance is constructed, the problems of long research and development period, low efficiency and cost waste caused by the fact that a large number of experimental methods are used for corrosion performance research at present are solved, and a new technical means is provided for research and development of novel zirconium alloys.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings. The detailed description of the present invention is given in detail by the following examples and the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flowchart of a nuclear zirconium-4 alloy corrosion resistance prediction method based on a BP network model according to the present invention;
FIG. 2 is a schematic diagram of the topology of the BP network model of the present invention;
FIG. 3 is a schematic diagram of a 3-5-1 three-layer BP neural network model according to the present invention;
FIG. 4 is a schematic diagram of the mean square error of the present invention as a function of the training step;
FIG. 5 is a comparison graph of predicted values and actual values of a corrosion gain BP network model of 110 training samples according to an embodiment of the present invention;
FIG. 6 is a comparison graph of predicted values and actual values of corrosion gain BP network models of 10 groups of detection samples in the embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
The method for predicting the corrosion resistance of the nuclear zirconium-4 alloy based on the BP network model, as shown in figure 1, comprises the following steps:
obtaining an original data sample, taking the corrosion weight gain data of a nuclear zirconium-4 alloy plate sample with the size of 20mm multiplied by 2mm under different alloy components at 400 ℃/10.3MPa for 300 days as a training sample, as shown in table 1, selecting Sn content, Fe + Cr content, C content, Si content, X content and corrosion period T as input variables, and selecting corrosion weight gain (mg/dm) of the plate sample as an output variable2)。
TABLE 1 input variable types and levels
Table 2 lists 120 groups of actually measured raw data samples, 110 groups of the raw data samples are taken as training samples, and 10 groups of data in total of S6, S18, S30, S42, S54, S66, S78, S90, S102 and S114 are taken as test samples of the model, as shown in Table 2.
Table 2 original training and testing samples
And extracting characteristic information, performing Principal Component Analysis (PCA) on the input variable, and extracting the characteristic information to form a new low-dimensional input variable. In this embodiment, the original 6 component input variables with a certain correlation are recombined into 3 new independent comprehensive variables by using the principal component analysis function of the SPSS-13.0 statistical software, and the original 6-h-1 three-layer network is simplified into a 3-h-1 network by performing the dimensionality reduction and denoising process, where the new input variables are shown in table 3. And the principal component analysis method is adopted to perform dimensionality reduction processing on the input variable, so that the structural scale of the traditional BP network is reduced, and the generalization performance of the model is improved.
TABLE 3 New 3-dimensional input variables after principal component analysis
Constructing a BP network model, as shown in FIG. 2, determining a BP network topological structure, setting a training function, a learning rate, a transfer function, training steps and a maximum allowable error, and constructing the BP network model with different alloy components and corrosion weight gain through a training sample selected from original data samples.
Based on 120 new groups of sample data after principal component analysis, 10 groups of data including NS6, NS18, NS30, NS42, NS54, NS66, NS78, NS90, NS102 and NS114 are selected as detection samples, and the remaining 110 groups of data are used as training samples, and a BP neural network model is programmed and constructed in MATLAB R2019a software.
Setting a hidden layer transfer function of the BP network model as Tansig, and comparing the number of hidden layer nodes by multiple times of training to obtain 5 with the minimum prediction error to obtain a 3-5-1 three-layer network model shown in figure 3; in addition, in order to make the BP network model converge quickly, the training function is set as the traincgb, the transfer function of the output layer is purelin, the learning rate is 0.1, the maximum training step number is 2000, and the target error range is 1x10-2(ii) a And (4) setting a for loop program to obtain the value which is the minimum relative error delta after 20 training comparisons and retaining the optimal initial weight and threshold. As shown in FIG. 4, after about 157 learning trainings, the relative error of the established network is substantially stabilized at 1x10-2。
Because the production flow of the nuclear zirconium-4 alloy is long, the detection cost is high, and the component influence factors are numerous, the influence of different alloy components on corrosion can be quickly and accurately predicted under the condition of as few experiments as possible by establishing a network model, so that the research work of the corrosion performance of the nuclear zirconium-4 alloy is greatly facilitated, and an efficient technical means is provided for the research and development of novel zirconium alloys.
And verifying the BP network model, namely verifying the constructed BP network model through a test sample selected from the original data sample.
The predicted and actual measurement data of 110 training samples were plotted using MATLAB R2019a software mapping function to obtain a simulation graph of actual measurement values and predicted values of BP network model, as shown in fig. 5. It can be seen that the predicted value of the network is basically consistent with the value measured by the experiment, which shows that the trained BP neural network model has stronger memory and induction capability and can be used as the basis of further prediction research.
And inputting 10 groups of detection samples into the established BP network model for simulation prediction so as to check the generalization capability of the model. Table 4 shows the results of the model prediction and the measured data, and as shown in fig. 6, the error comparison graph corresponding to the two is shown, and in combination, the maximum relative error δ of the model is 7.18%, which has reached a higher prediction accuracy, and the model can be used for further research work for predicting the corrosion performance of the nuclear zirconium-4 alloy.
TABLE 410 comparison of measured and model predicted results for test samples
An electronic device, comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for executing a nuclear zirconium-4 alloy corrosion resistance prediction method based on the BP network model.
A computer-readable storage medium having stored thereon a computer program for execution by a processor of a method for predicting corrosion resistance of a zirconium-4 alloy for a core based on a BP network model.
Aiming at the problem of influence prediction of different alloy components on the corrosion performance of the nuclear zirconium-4 alloy, the BP network model is taken as the center, the principal component analysis technology is combined to perform dimensionality reduction and denoising treatment on input variables, characteristic information is extracted, the problems of overfitting, slow convergence speed, poor generalization capability and the like commonly existing in the application of the traditional BP network method in forecasting are solved, the prediction precision and generalization capability of the traditional BP network model are effectively improved, the nonlinear mapping relation model of the zirconium-4 alloy component content and the corrosion performance is constructed, the problems of long research and development period, low efficiency and cost waste caused by the fact that a large number of experimental methods are used for corrosion performance research at present are solved, and a new technical means is provided for research and development of novel zirconium alloys.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner; those skilled in the art can readily practice the invention as shown and described in the drawings and detailed description herein; however, those skilled in the art should appreciate that they can readily use the disclosed conception and specific embodiments as a basis for designing or modifying other structures for carrying out the same purposes of the present invention without departing from the scope of the invention as defined by the appended claims; meanwhile, any changes, modifications, and evolutions of the equivalent changes of the above embodiments according to the actual techniques of the present invention are still within the protection scope of the technical solution of the present invention.
Claims (10)
1. The method for predicting the corrosion resistance of the nuclear zirconium-4 alloy based on the BP network model is characterized by comprising the following steps of:
obtaining an original data sample, taking corrosion weight gain of a nuclear zirconium-4 alloy plate sample as a research object, determining an input variable and an output variable, and carrying out corrosion detection to obtain the original data sample;
constructing a BP network model, determining a BP network topological structure, setting a training function, a learning rate, a transfer function, training steps and a maximum allowable error, and constructing the BP network model with different alloy components and corrosion weight gain through a training sample selected from the original data sample;
and verifying the BP network model, namely verifying the constructed BP network model through a test sample selected from the original data samples.
2. The BP network model-based method for predicting the corrosion resistance of the zirconium-4 alloy for a core according to claim 1, wherein: in the step of obtaining the original data sample, the input variables include mass percent of Sn, mass percent of Fe + Cr, mass percent of C, mass percent of Si, mass percent of X and corrosion period, and the output variables are corrosion gain of the sample.
3. The BP network model-based method for predicting the corrosion resistance of the zirconium-4 alloy for a core according to claim 1, wherein: in the step of obtaining the original data sample, the size of the plate sample is 20mm multiplied by 2mm, a 400 ℃/10.3MPa corrosion test is carried out in a reaction kettle for 300 days, and the weight increasing period of the sampling test is respectively 10 th, 30 th, 60 th, 80 th, 100 th, 130 th, 150 th, 180 th, 210 th, 240 th, 270 th and 300 th days.
4. The BP network model-based method for predicting the corrosion resistance of the zirconium-4 alloy for a core according to claim 2, wherein: and extracting characteristic information between the step of obtaining the original data sample and the step of constructing the BP network model, performing principal component analysis on the input variable, and extracting the characteristic information to form a new low-dimensional input variable.
5. The BP network model-based zirconium-4 alloy corrosion resistance prediction method of claim 4, wherein: in the step of extracting the characteristic information, SPSS-13.0 software is used for carrying out principal component analysis, and 6 component input variables with certain correlation are recombined into 3 new independent comprehensive variables.
6. The BP network model-based method for predicting the corrosion resistance of the zirconium-4 alloy for a core according to claim 1, wherein: in the step of constructing the BP network model, the BP network topology structure comprises three layers, namely an input layer, a hidden layer and an output layer, wherein the number of nodes of the input layer is 3, the number of nodes of the output layer is 1, and the value range of the number of nodes of the hidden layer is [2-10 ].
7. The BP network model-based method for predicting the corrosion resistance of the zirconium-4 alloy for a core according to claim 1, wherein: in the step of constructing the BP network model, a training function is TRAINLM, a learning function is LEARGDM, transfer functions are Tansig and Purelin, the learning rate is set to be 0.1, the maximum iteration time is 2000 times, and the target error E is 1x10-2。
8. The BP network model-based zirconium-4 alloy corrosion resistance prediction method of claim 4, wherein: in the step of verifying the BP network model, samples which do not participate in the training of the BP network model are selected from the new samples, the constructed BP network model is subjected to prediction inspection, and the generalization capability of the model is evaluated by comparing the relative error between actual measurement and a predicted value.
9. An electronic device, characterized by comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for carrying out the method of any one of claims 1-8.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program is executed by a processor for performing the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069396.7A CN112326540A (en) | 2020-09-30 | 2020-09-30 | Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069396.7A CN112326540A (en) | 2020-09-30 | 2020-09-30 | Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112326540A true CN112326540A (en) | 2021-02-05 |
Family
ID=74314605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011069396.7A Pending CN112326540A (en) | 2020-09-30 | 2020-09-30 | Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112326540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116597923A (en) * | 2023-05-19 | 2023-08-15 | 小米汽车科技有限公司 | Model generation method, material information determination method, device, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106507845B (en) * | 2000-12-15 | 2016-10-05 | 西北有色金属研究院 | A kind of zirconium-base alloy |
| US10052026B1 (en) * | 2017-03-06 | 2018-08-21 | Bao Tran | Smart mirror |
| CN109255490A (en) * | 2018-09-28 | 2019-01-22 | 西安建筑科技大学 | Corrosion rate prediction technique outside a kind of buried pipeline based on KPCA-BAS-GRNN |
-
2020
- 2020-09-30 CN CN202011069396.7A patent/CN112326540A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106507845B (en) * | 2000-12-15 | 2016-10-05 | 西北有色金属研究院 | A kind of zirconium-base alloy |
| US10052026B1 (en) * | 2017-03-06 | 2018-08-21 | Bao Tran | Smart mirror |
| CN109255490A (en) * | 2018-09-28 | 2019-01-22 | 西安建筑科技大学 | Corrosion rate prediction technique outside a kind of buried pipeline based on KPCA-BAS-GRNN |
Non-Patent Citations (7)
| Title |
|---|
| 乌日根 等: "基于神经网络的RE-Ni-Cu合金铸铁腐蚀性能预测", 《兵器材料科学与工程》 * |
| 宣卫芳 等: "《装备与自然环境试验》", 30 November 2011, 航空工业出版社 * |
| 左羡第 等: "干湿交替环境中SO_2和H_2S混合气体对紫铜T2的腐蚀行为研究", 《腐蚀科学与防护技术》 * |
| 田文华 等: "《医疗联合体绩效评估》", 31 January 2019, 复旦大学出版社 * |
| 董艳艳 等: "不同配比Ni-Cr系涂层非线性动力学系统的抗腐蚀性能研究", 《材料导报》 * |
| 边伟 等: ""应用PCA和BP神经网络预测采出水对C20钢的腐蚀速率"", 《石油矿场机械》 * |
| 韩德盛 等: "用RBF人工神经网络构建铝合金大气腐蚀预测模型", 《腐蚀科学与防护技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116597923A (en) * | 2023-05-19 | 2023-08-15 | 小米汽车科技有限公司 | Model generation method, material information determination method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112836884A (en) | Copula-DBiLSTM-based method for accurately predicting multi-element load of comprehensive energy system | |
| CN112131785B (en) | Screening and optimizing method of methanation nickel-based catalyst formula based on ANN-NSGA-II | |
| CN110987436B (en) | Bearing fault diagnosis method based on excitation mechanism | |
| CN115847596B (en) | Production debugging control method and system for gypsum block | |
| CN113255206A (en) | Hydrological prediction model parameter calibration method based on deep reinforcement learning | |
| CN114580286A (en) | Neural network model optimization method based on stainless steel ultra-thin strip annealing process | |
| CN112326540A (en) | Nuclear zirconium-4 alloy corrosion resistance prediction method based on BP network model, electronic equipment and storage medium | |
| CN116520772A (en) | Sheet part numerical control machining quality prediction method based on multitasking transfer learning | |
| CN112800612A (en) | Dynamic evolution analysis method of nickel-based alloy corrosion layer based on cellular automaton | |
| CN114638164B (en) | Method for predicting high-temperature creep life of power station pressure pipeline | |
| CN114676814A (en) | Wind power ultra-short-term prediction method based on SATCN-LSTM | |
| CN113033105A (en) | Steel material fatigue performance prediction method based on mechanical theory guide transfer learning | |
| CN112668234A (en) | Intelligent control method for steelmaking endpoint of converter | |
| CN111798023B (en) | Comprehensive coke ratio prediction method in steelmaking sintering production | |
| CN110109904B (en) | Environment-friendly big data oriented water quality soft measurement method | |
| Zhang et al. | Predicting cement compressive strength using double-layer multi-expression Programming | |
| CN110415769B (en) | Low-activation steel design method based on machine learning under guidance of physical metallurgy | |
| CN116842834A (en) | Interpretable creep rupture life prediction method based on machine learning and SHAP value | |
| CN116484675A (en) | Crack propagation life prediction method and system for ship engine blade | |
| CN114118592B (en) | Smart power grids power consumption end short-term energy consumption prediction system | |
| CN114781250A (en) | Multi-factor influence environment fatigue life prediction method based on machine learning | |
| CN116307139A (en) | Wind power ultra-short-term prediction method for optimizing and improving extreme learning machine | |
| Yang et al. | Stress-assisted corrosion mechanism of 3Ni steel by using gradient boosting decision tree machining learning method | |
| CN114740713A (en) | Multi-objective optimization control method for wet flue gas desulfurization process | |
| CN112149260B (en) | Design method of three-dimensional impact-resistant negative Poisson's ratio structure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210205 |
|
| RJ01 | Rejection of invention patent application after publication |