CN112348264A - Carbon steel corrosion rate prediction method based on random forest algorithm - Google Patents
Carbon steel corrosion rate prediction method based on random forest algorithm Download PDFInfo
- Publication number
- CN112348264A CN112348264A CN202011246916.7A CN202011246916A CN112348264A CN 112348264 A CN112348264 A CN 112348264A CN 202011246916 A CN202011246916 A CN 202011246916A CN 112348264 A CN112348264 A CN 112348264A
- Authority
- CN
- China
- Prior art keywords
- corrosion
- data
- model
- random forest
- corrosion rate
- 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
- 238000005260 corrosion Methods 0.000 title claims abstract description 90
- 230000007797 corrosion Effects 0.000 title claims abstract description 85
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 34
- 229910000975 Carbon steel Inorganic materials 0.000 title claims abstract description 28
- 239000010962 carbon steel Substances 0.000 title claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000000523 sample Substances 0.000 claims abstract description 27
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 238000003066 decision tree Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 239000007769 metal material Substances 0.000 abstract 1
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002436 steel type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention discloses a carbon steel corrosion rate prediction method based on a random forest algorithm, belongs to the technical field of corrosion prediction of metal materials, and collects main factors SO influencing carbon steel corrosion2Temperature, humidity and rainfall, a high-flux corrosion monitoring probe is utilized, one temperature, humidity and corrosion current data point is collected every minute, and a test site collects data volume of one year; establishing SO by using random forest algorithm2And the relation model of temperature, humidity and corrosion current can greatly reduce the test cost and shorten the test period.
Description
Technical Field
The invention belongs to the technical field of steel manufacturing, and particularly relates to a carbon steel corrosion rate prediction method based on a random forest algorithm.
Background
China is wide in breadth, spans five climatic zones, has a plurality of atmospheric environment types such as coastal environment, inland environment, damp and hot environment, drought environment, urban environment, rural environment, industrial environment and the like, has complex environmental factors influencing material corrosion, has different atmospheric corrosivity in different regions, has unrepresentative corrosion rate in only one region, and in the popularization process of steel products, users hope to obtain the corrosion rate of target steel types in the local area.
The traditional method for obtaining the corrosion rate is through on-site hanging, but the hanging cost is high, the period is long, and especially the hanging of remote areas is limited by the dual conditions of climate and traffic whether sample hanging or sampling.
The random forest is based on a bagging (bagging) method and decision tree integrated algorithm, and the generalization capability of the model is improved through random sampling, so that the prediction accuracy is improved.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a carbon steel corrosion rate prediction method based on a random forest algorithm, which is established by combining a computer technology and utilizing the random forest algorithm.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the following technical scheme:
a carbon steel corrosion rate prediction method based on a random forest algorithm comprises the following steps:
1) collecting data: collecting main factors SO influencing carbon steel corrosion2Temperature, humidity and rainfall, a high-flux corrosion monitoring probe is utilized, one temperature, humidity and corrosion current data point is collected every minute, and a test site collects data volume of one year;
2) data preprocessing: screening abnormal values of the collected data points and deleting the abnormal values;
3) establishing a corrosion prediction model: establishing SO by using random forest algorithm2A model of the relationship of temperature, humidity and corrosion current;
4) and (3) verifying the model: the corrosion rate accuracy calculated by the traditional coupon corrosion rate verification model is utilized;
a(x)=(1-|v1-v2|/v2)*100%
in the formula, a(x) Indicating corrosion accuracy, v1Represents the conventional coupon corrosion rate, v2Representing the corrosion rate calculated by the model;
5) predicting the corrosion rate of carbon steel: collected SO2And the information such as temperature, humidity, rainfall and the like, and the corrosion rate of the carbon steel is predicted by utilizing the established corrosion prediction model.
Further, in step 1), the data collection is to collect one data point per minute, and the collected data item includes SO2Temperature, humidity, rainfall and corrosion current, the data volume of one year (about 50 ten thousand) was collected.
Further, in the step 2), the data preprocessing specifically includes dividing the data into two sections of data in rainy season and dry season according to rainfall conditions after completely repeated data is deleted; in the step 2), the rainfall information is uniformly set to be a numerical value 1 no matter the rainfall is in the case of rain; dividing data points without rainfall into data grades according to the humidity, wherein the specific division principle is shown in a table 1; and (3) taking the rainfall information and the division value of the humidity level as factors influencing the corrosion rate of the carbon steel, and participating in model calculation.
Further, in the step 3), the SO of the test site is used2The temperature, the humidity and the numerical grade division value are used as independent variables x, the corrosion current numerical value is used as a dependent variable y, and a random forest algorithm is utilized to establish a relation model between x and y, namely a corrosion prediction model.
Further, in step 3), the establishing of the corrosion prediction model includes the following steps:
3.1) randomly and repeatedly selecting N (N < N) samples from N original training samples by using a Bootstrap method to generate m training subsets.
3.2) performing decision tree modeling on the m training subsets respectively: randomly selecting a part of sample characteristics from all sample characteristics on the nodes, dividing left and right subtrees of the decision tree according to the minimum mean square error, and recursively building the tree until a termination condition is met:
wherein, for the arbitrary dividing characteristic A, the data set D divided into two sides corresponding to the arbitrary dividing point a1And D2(ii) a In the formula, xiIs a sample value, yiIs with xiCorresponding true value, c1Is D1Sample output mean of data set, c2Is D2A sample output mean of the data set; each decision tree is composed of training subsets X and theta with sample size nk(random vector sequence { theta }kN, independently distributed equally, k 1,2.. n);
3.3) repeating the steps to form a random forest by a plurality of decision trees, namely a set of all decision trees { h (X, theta) }k) N, where each decision tree model h (X, θ)k) There is a vote weight to select the classification result for input variable x:
wherein H (x) represents the result of random forest classification, hi(x) Is a single decision tree classification result, Y represents a classification target, and I (is) is an indicative function;
and 3.4) inputting the test sample into a random forest regression model, adopting a simple voting mechanism, namely taking the most votes as a final prediction result, and comparing the final prediction result with an actual value to evaluate the fitting effect of the model.
Further, in step 5), SO is converted by using the relation model established in step 3)2And inputting the temperature, humidity and rainfall information into the model, calculating the corrosion current value, and further converting the corrosion current into the corrosion rate according to the Faraday's law.
Has the advantages that: compared with the traditional coupon method for obtaining the corrosion rate, the method collects the main factor SO influencing the carbon steel corrosion2Temperature, humidity and rainfall, a high-flux corrosion monitoring probe is utilized, one temperature, humidity and corrosion current data point is collected every minute, and a test site collects data volume of one year; by using a random forest algorithm, the method can be used,establishment of SO2And the relation model of temperature, humidity and corrosion current can greatly reduce the test cost and shorten the test period.
Drawings
FIG. 1 is a flow chart of carbon steel corrosion rate prediction data processing and modeling based on a random forest algorithm.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
As shown in FIG. 1, a carbon steel corrosion rate prediction method based on a random forest algorithm comprises the following steps:
1) collecting data: collecting main factors SO influencing carbon steel corrosion2Temperature, humidity and rainfall, a high-flux corrosion monitoring probe is utilized, one temperature, humidity and corrosion current data point is collected every minute, and a test site collects data volume of one year;
2) data preprocessing: screening abnormal values of the collected data points and deleting the abnormal values;
3) establishing a corrosion prediction model: establishing SO by using random forest algorithm2A model of the relationship of temperature, humidity and corrosion current; the steps of establishing the random forest decision tree model are as follows:
3.1) randomly and repeatedly selecting N (N < N) samples from N original training samples by using a Bootstrap method to generate m training subsets.
3.2) performing decision tree modeling on the m training subsets respectively: randomly selecting a part of sample characteristics from all sample characteristics on the nodes, dividing left and right subtrees of the decision tree according to the minimum mean square error, and recursively building the tree until a termination condition is met.
Wherein, for the arbitrary dividing characteristic A, the data set D divided into two sides corresponding to the arbitrary dividing point a1And D2. In the formula, xiIs a sample value, yiIs with xiCorresponding realityValue, c1Is D1Sample output mean of data set, c2Is D2The sample output mean of the data set.
Each decision tree is composed of training subsets X and theta with sample size nk(random vector sequence { theta }kN, independently distributed equally).
3.3) repeating the steps to form a random forest by a plurality of decision trees, namely a set of all decision trees { h (X, theta) }k) N, where each decision tree model h (X, θ)k) There is a vote weight to select the classification result for the input variable x.
Wherein H (x) represents the result of random forest classification, hi(x) Is a single decision tree classification result, Y represents a classification target, and I (is) is an indicative function.
And 3.4) inputting the test sample into a random forest regression model, adopting a simple voting mechanism, namely taking the most votes as a final prediction result, and comparing the final prediction result with an actual value to evaluate the fitting effect of the model.
4) And (3) verifying the model: the corrosion rate accuracy calculated by the traditional coupon corrosion rate verification model is utilized;
a(x)=(1-|v1-v2|/v2)*100%
wherein a (x) represents the corrosion accuracy, v1Represents the conventional coupon corrosion rate, v2Representing the corrosion rate calculated by the model.
5) Predicting the corrosion rate of carbon steel: collecting SO from major cities across the country2And the information such as temperature, humidity, rainfall and the like, and the established corrosion prediction model is utilized to predict the corrosion rate of the carbon steel in the main cities in China.
In step 1), one data point is collected every minute, and the collected data item includes SO2Temperature, humidity, rainfall and corrosion current, the data volume of one year (about 50 ten thousand) was collected.
In the step 2), after completely repeated data is deleted, the data is divided into two sections of data in rainy season and dry season according to the rainfall condition.
In the step 2), the rainfall information is uniformly set to be a numerical value 1 no matter the rainfall is in the case of raining.
In the step 2), data grades are divided according to the humidity of data points without rainfall, and the specific division principle is shown in table 1.
In the step 2), the rainfall information and the humidity grade are used as factors influencing the corrosion rate of the carbon steel and participate in model calculation.
TABLE 1 principle of data preprocessing
Humidity (H) and rainfall information | Numerical ranking |
Rainfall device | 1 |
No rainfall and H is less than or equal to 40 | 0 |
Does not rain, and 40<H≤60 | 2 |
Not raining, and 60<H≤80 | 3 |
Not raining, and 80<H≤90 | 4 |
Not raining, and 90<H≤98 | 5 |
Not raining, and H>98 | 6 |
In step 3), SO of the test site is measured2Temperature, humidity and numerical grade division values in table 1 are used as independent variables x, corrosion current numerical values are used as dependent variables y, and a relation model between x and y, namely a corrosion prediction model, is established by utilizing a random forest algorithm.
In step 5), the SO of the main cities in the country is converted by using the relation model established in the step 3)2And inputting the temperature, humidity and rainfall information into the model, calculating the corrosion current value, and further converting the corrosion current into the corrosion rate according to the Faraday's law.
Claims (6)
1. A carbon steel corrosion rate prediction method based on a random forest algorithm is characterized by comprising the following steps: the method comprises the following steps:
1) collecting data: collecting main factors SO influencing carbon steel corrosion2Temperature, humidity and rainfall, a high-flux corrosion monitoring probe is utilized, one temperature, humidity and corrosion current data point is collected every minute, and a test site collects data volume of one year;
2) data preprocessing: screening abnormal values of the collected data points and deleting the abnormal values;
3) establishing a corrosion prediction model: establishing SO by using random forest algorithm2A model of the relationship of temperature, humidity and corrosion current;
4) and (3) verifying the model: verifying the accuracy of the corrosion rate calculated by the model by using the coupon corrosion rate;
a(x)=(1-|v1-v2|/v2)*100%
wherein a (x) represents the corrosion accuracy, v1Represents the conventional coupon corrosion rate, v2Representing the corrosion rate calculated by the model;
5) predicting the corrosion rate of carbon steel: collected SO2And the information such as temperature, humidity, rainfall and the like, and the corrosion rate of the carbon steel is predicted by utilizing the established corrosion prediction model.
2. The carbon steel corrosion rate prediction method based on the random forest algorithm as recited in claim 1, wherein: in step 1), the data collection is to collect one data point per minute, and the collected data item includes SO2Temperature, humidity, rainfall and corrosion current, data volume of one year is collected.
3. The carbon steel corrosion rate prediction method based on the random forest algorithm as recited in claim 1, wherein: in the step 2), the data preprocessing specifically comprises the steps of dividing data into two sections of data in rainy season and dry season according to rainfall conditions after completely repeated data are deleted; setting the rainfall information as a value 1 uniformly no matter the rainfall is in the rain as long as the rainfall is rained; dividing data grades according to the humidity of data points without rainfall; and (3) taking the rainfall information and the division value of the humidity level as factors influencing the corrosion rate of the carbon steel, and participating in model calculation.
4. The carbon steel corrosion rate prediction method based on the random forest algorithm as recited in claim 1, wherein: in the step 3), SO of the test site is used2The temperature, the humidity and the numerical grade division value are used as independent variables x, the corrosion current numerical value is used as a dependent variable y, and a random forest algorithm is utilized to establish a relation model between x and y, namely a corrosion prediction model.
5. The carbon steel corrosion rate prediction method based on the random forest algorithm as claimed in claim 4, wherein the method comprises the following steps: in step 3), the establishing of the corrosion prediction model comprises the following steps:
3.1) randomly and repeatedly selecting N (N < N) samples from N original training samples by using a Bootstrap method to generate m training subsets.
3.2) performing decision tree modeling on the m training subsets respectively: randomly selecting a part of sample characteristics from all sample characteristics on the nodes, dividing left and right subtrees of the decision tree according to the minimum mean square error, and recursively building the tree until a termination condition is met:
wherein, for the arbitrary dividing characteristic A, the data set D divided into two sides corresponding to the arbitrary dividing point a1And D2(ii) a In the formula, xiIs a sample value, yiIs with xiCorresponding true value, c1Is D1Sample output mean of data set, c2Is D2A sample output mean of the data set; each decision tree is composed of training subsets X and theta with sample size nkGenerating; random vector sequence [ theta ]kN, wherein k is independently distributed in the same way as 1,2.. n;
3.3) repeating the steps to form a random forest by a plurality of decision trees, namely a set of all decision trees { h (X, theta) }k) N, where each decision tree model h (X, θ)k) There is a vote weight to select the classification result for input variable x:
wherein H (x) represents the result of random forest classification, hi(x) Is a single decision tree classification result, Y represents a classification target, and I (is) is an indicative function;
and 3.4) inputting the test sample into a random forest regression model, adopting a simple voting mechanism, namely taking the most votes as a final prediction result, and comparing the final prediction result with an actual value to evaluate the fitting effect of the model.
6. The carbon steel corrosion rate prediction method based on the random forest algorithm as recited in claim 1, wherein: in the step 5), the SO is processed by utilizing the relation model established in the step 3)2Temperature and humidityAnd inputting rainfall information into the model, calculating the corrosion current value, and further converting the corrosion current into the corrosion rate according to Faraday's law.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011246916.7A CN112348264A (en) | 2020-11-10 | 2020-11-10 | Carbon steel corrosion rate prediction method based on random forest algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011246916.7A CN112348264A (en) | 2020-11-10 | 2020-11-10 | Carbon steel corrosion rate prediction method based on random forest algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112348264A true CN112348264A (en) | 2021-02-09 |
Family
ID=74363262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011246916.7A Pending CN112348264A (en) | 2020-11-10 | 2020-11-10 | Carbon steel corrosion rate prediction method based on random forest algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112348264A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113591385A (en) * | 2021-08-03 | 2021-11-02 | 中国民航大学 | Carbon steel dynamic atmospheric corrosion influence factor mining and corrosion rate prediction method under actual vehicle service working condition, electronic equipment and storage medium |
CN113822334A (en) * | 2021-08-20 | 2021-12-21 | 南京钢铁股份有限公司 | Roller screening method, storage medium and system |
CN113902327A (en) * | 2021-10-21 | 2022-01-07 | 南京工程学院 | Evaluation method and system for corrosion health state of offshore wind plant foundation structure |
CN114121174A (en) * | 2021-11-19 | 2022-03-01 | 武汉材料保护研究所有限公司 | Carbon steel corrosion rate prediction method |
CN114565185A (en) * | 2022-03-28 | 2022-05-31 | 北京化工大学 | Corrosion rate prediction system based on multi-source data |
CN116563626A (en) * | 2023-05-06 | 2023-08-08 | 南京工业大学 | Prediction method for corrosion rate of steel bridge bolt |
CN116563626B (en) * | 2023-05-06 | 2024-07-26 | 南京工业大学 | Prediction method for corrosion rate of steel bridge bolt |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782499A (en) * | 2009-01-21 | 2010-07-21 | 中国科学院金属研究所 | Method for predicting atmospheric corrosion rate of metal material |
US20140163903A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | Real time numerical computation of corrosion rates from corrosion sensors |
CN109507535A (en) * | 2018-12-10 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | Grounding net of transformer substation operation phase and service life prediction technique and device |
CN110751339A (en) * | 2019-10-24 | 2020-02-04 | 北京化工大学 | Method and device for predicting corrosion rate of pipeline and computer equipment |
WO2020162098A1 (en) * | 2019-02-08 | 2020-08-13 | Jfeスチール株式会社 | Method for generating metallic material corrosion level prediction model, metallic material corrosion level predicting method, metallic material selecting method, metallic material corrosion level prediction program, and metallic material corrosion level prediction device |
-
2020
- 2020-11-10 CN CN202011246916.7A patent/CN112348264A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782499A (en) * | 2009-01-21 | 2010-07-21 | 中国科学院金属研究所 | Method for predicting atmospheric corrosion rate of metal material |
US20140163903A1 (en) * | 2012-12-11 | 2014-06-12 | International Business Machines Corporation | Real time numerical computation of corrosion rates from corrosion sensors |
CN109507535A (en) * | 2018-12-10 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | Grounding net of transformer substation operation phase and service life prediction technique and device |
WO2020162098A1 (en) * | 2019-02-08 | 2020-08-13 | Jfeスチール株式会社 | Method for generating metallic material corrosion level prediction model, metallic material corrosion level predicting method, metallic material selecting method, metallic material corrosion level prediction program, and metallic material corrosion level prediction device |
CN110751339A (en) * | 2019-10-24 | 2020-02-04 | 北京化工大学 | Method and device for predicting corrosion rate of pipeline and computer equipment |
Non-Patent Citations (2)
Title |
---|
LUCHUN YAN;YUPENG DIAO;KEWEI GAO: "Analysis of Environmental Factors Affecting the Atmospheric Corrosion Rate of Low-Alloy Steel Using Random Forest-Based Models", MATERIAS, vol. 13, no. 15, pages 1 - 13 * |
骆正山;宋莹莹;毕傲睿;: "基于GRA-RFR的油气集输管道内腐蚀速率预测", 材料保护, no. 03 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113591385A (en) * | 2021-08-03 | 2021-11-02 | 中国民航大学 | Carbon steel dynamic atmospheric corrosion influence factor mining and corrosion rate prediction method under actual vehicle service working condition, electronic equipment and storage medium |
CN113591385B (en) * | 2021-08-03 | 2024-03-26 | 中国民航大学 | Mining method for carbon steel dynamic atmospheric corrosion influence factors of actual vehicle service conditions, corrosion rate prediction method, electronic equipment and storage medium |
CN113822334A (en) * | 2021-08-20 | 2021-12-21 | 南京钢铁股份有限公司 | Roller screening method, storage medium and system |
CN113902327A (en) * | 2021-10-21 | 2022-01-07 | 南京工程学院 | Evaluation method and system for corrosion health state of offshore wind plant foundation structure |
CN114121174A (en) * | 2021-11-19 | 2022-03-01 | 武汉材料保护研究所有限公司 | Carbon steel corrosion rate prediction method |
CN114565185A (en) * | 2022-03-28 | 2022-05-31 | 北京化工大学 | Corrosion rate prediction system based on multi-source data |
CN116563626A (en) * | 2023-05-06 | 2023-08-08 | 南京工业大学 | Prediction method for corrosion rate of steel bridge bolt |
CN116563626B (en) * | 2023-05-06 | 2024-07-26 | 南京工业大学 | Prediction method for corrosion rate of steel bridge bolt |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112348264A (en) | Carbon steel corrosion rate prediction method based on random forest algorithm | |
CN109165693B (en) | Automatic identification method suitable for dew, frost and icing weather phenomena | |
CN105069537B (en) | A kind of construction method of combination type air Quality Prediction | |
CN105182450A (en) | Short-time early warning system for severe convection weather | |
CN107480698A (en) | Method of quality control based on multiple monitoring indexes | |
CN110210660B (en) | Ultra-short-term wind speed prediction method | |
CN110362886B (en) | Urban masonry residential safety assessment method based on uncertainty analysis | |
CN116340723B (en) | Rural water pollution quick tracing method and system based on big data | |
CN110261272B (en) | Method for screening key influence factors on PM2.5 concentration distribution based on geographic detection and PCA (principal component analysis) | |
CN106845080B (en) | Based on the modified Scene Tourist meteorological disaster intelligent Forecasting of difference | |
CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
CN111126511A (en) | Vegetation index fusion-based LAI quantitative model establishment method | |
CN105259318A (en) | Foul smell OU value prediction method and system based on meteorological parameters | |
CN108615054B (en) | Method for constructing comprehensive index for measuring similarity between drainage pipe network nodes | |
CN103257000B (en) | Temperature extreme-value prediction method for bridge structure sunshine effect analysis | |
Pegion et al. | Understanding predictability of daily southeast US precipitation using explainable machine learning | |
CN113537336A (en) | XGboost-based short-term thunderstorm and strong wind forecasting method | |
CN117541095A (en) | Agricultural land soil environment quality classification method | |
CN113281229A (en) | Multi-model self-adaptive atmosphere PM based on small samples2.5Concentration prediction method | |
Gan et al. | Prediction of air pollutant concentration based on luong attention mechanism Seq2Seq model | |
CN116662935A (en) | Atmospheric pollutant spatial distribution prediction method based on air quality monitoring network | |
Pei et al. | Analysis of spring drought in Northeast China from the perspective of atmosphere, snow cover, and soil | |
Saha et al. | Identification of Indian monsoon predictors using climate network and density-based spatial clustering | |
CN113960700B (en) | Objective inspection, statistics and analysis system for regional numerical forecasting result | |
CN114529035A (en) | CART-based wind speed forecasting method of multi-mode integrated model |
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 |