CN113642170B - Steel plant yield monitoring method based on thermal infrared remote sensing satellite data - Google Patents
Steel plant yield monitoring method based on thermal infrared remote sensing satellite data Download PDFInfo
- Publication number
- CN113642170B CN113642170B CN202110909812.8A CN202110909812A CN113642170B CN 113642170 B CN113642170 B CN 113642170B CN 202110909812 A CN202110909812 A CN 202110909812A CN 113642170 B CN113642170 B CN 113642170B
- Authority
- CN
- China
- Prior art keywords
- data
- area
- surface temperature
- steel
- plant
- 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
Images
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
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- 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
Abstract
The invention discloses a steel plant yield monitoring method based on thermal infrared remote sensing satellite data, belonging to the field of thermal infrared remote sensing image processing and analysis: firstly, acquiring monthly output and L1 level data corresponding to each month aiming at a steel plant area to be monitored; drawing a factory area range and an urban area range after the factory area is removed; then, performing inversion calculation on the L1-level data, performing mask processing according to the ranges of the factory area and the urban area, respectively extracting earth surface temperature data corresponding to each month of the factory area and the urban area, and deleting data with cloud; then, calculating the difference value T of high and low temperatures of the plant area by using the maximum value in the plant area earth surface temperature data in each month and the mean value of the urban area earth surface temperaturedAs an index of steel production; finally, based on the least square method, T is establisheddEstimating a production model between the model and the steel yield and carrying out precision verification; the next month T of the plantdAnd substituting the indexes into an estimated production model meeting the precision requirement, and monitoring the steel yield in the next month. The invention can effectively acquire the production state of an enterprise in time.
Description
Technical Field
The invention belongs to the technical field of thermal infrared remote sensing image processing and analysis, and particularly relates to a steel plant yield monitoring method based on thermal infrared remote sensing satellite data.
Background
The steel industry in China is an important prop industry of national economy, and plays an important role in the aspects of economic construction, social development, financial tax, national defense construction, stable employment and the like. According to statistics, the yield of crude steel in China in the first half of 2020 years reaches 4.99 hundred million tons, the yield is increased by 1.4 percent on year-by-year basis, and the global percentage of the crude steel reaches 57.2 percent.
In recent years, the production of Chinese steel is kept at a higher level, but the international overall economic development is slowed down, the international market demand is weak, the difficulty of steel export is increased, and the situation that the supply and demand of the Chinese steel market are larger is still difficult to reverse. On one hand, the raw materials produced by iron and steel enterprises are mainly iron ores, the price cost of the iron ores accounts for more than 40% of the cost of the iron and steel industry in China, and the iron and steel enterprises are the first major imports of iron ores in the world all the time, so that the production conditions of the iron and steel enterprises can be directly reflected to the demand and the imports of the iron ores, and the iron and steel enterprises have important influence on the price fluctuation of the iron ores in the international market. On the other hand, the yield condition of the iron and steel enterprises directly affects the market supply end, the steel price is affected, and the social and economic activities such as large-scale infrastructure construction, national investment and the like can be indirectly reflected. Meanwhile, in recent years, China always strengthens the requirements of the capacity and the environmental protection of the steel industry, and urgently needs to solve the problems of surplus capacity, serious pollution and the like of steel enterprises. Therefore, mastering the production condition and the yield information of the iron and steel enterprises has important significance for monitoring social and economic activities, analyzing the large commodity transactions of iron ores, steel materials and the like and protecting the environment.
The production process of a steel enterprise generally comprises the following steps: firstly, ore dressing and sintering iron ore to prepare pellets, then matching the pellets with coke and limestone, putting the pellets into an iron-making furnace (blast furnace) for heating, and refining to obtain pig iron; removing impurities from the pig iron in the high-temperature steel-making furnace again, and refining to obtain crude steel; finally, high-temperature pressure processing is carried out according to different requirements, and various steel products are rolled. High temperature is required to be provided in the processes of sintering, iron making and steel rolling, and the temperature of a plurality of links in the production process is over 1000 ℃. Therefore, obvious thermal effect is formed in the whole steel factory area, and obvious contrast is formed with the heat radiation of other areas in the periphery normally. Therefore, it is feasible that the thermal radiation information emitted from the terrestrial objects acquired by the thermal infrared sensor of the satellite is used for the yield change and prediction of the steel enterprises.
In recent years, the thermal infrared remote sensing satellite technology is gradually applied to the research of thermal effects of urban heat island effect, forest fire, earthquake and heat energy related industries and the like at home and abroad. At present, in the mesoscale remote sensing data, a thermal infrared sensor (TIRS) carried by a Landsat8 satellite has the characteristics of strong sensitivity to a thermal infrared band and high spatial resolution, and can perform accurate inversion analysis on the surface temperature and thermal spatial distribution. The earth surface temperature is an important parameter in the interaction process of the atmosphere and the land, an algorithm for inverting the earth surface temperature by utilizing thermal infrared remote sensing data is mature, and typically comprises an atmosphere correction method (also called a Radiative Transfer Equation-RTE), a single-channel algorithm and a split window algorithm. According to the previous research results, the surface temperature inverted by the thermal infrared remote sensing data can reflect the actual production condition of the steel plant. Such as: meng Qing rock (2018) proposes that the Landsat8 satellite data is utilized to carry out temperature inversion, an index system suitable for small-scale ground object thermal environment monitoring is established, and the side face reflects the production change condition of a steel plant through thermal environment indexes such as different area temperature average value differences and high temperature area ratio values of each time phase. Lijing (2019) divides a low-temperature area and a high-temperature area from inverted surface temperature by adopting a threshold method, interprets the production state of a steel enterprise by constructing a thermal radiation model, and preliminarily verifies the monitoring result by combining the spatial structure change information of the enterprise with a high-resolution remote sensing satellite. However, in the process of temperature inversion and monitoring analysis of long-sequence multi-temporal thermal infrared data, the influence of thermal infrared remote sensing ground temperature inversion accuracy and seasonal climate temperature change cannot be fully considered, so that the correlation between the ground temperature value parameters acquired based on thermal infrared remote sensing and the yield is not high within a period of one year or more.
Disclosure of Invention
The invention provides a method for monitoring the yield of an iron and steel plant based on thermal infrared remote sensing satellite data, aiming at the problem that current parties urgently need to master the yield information of the iron and steel production industry in time and the monthly capacity data of the iron and steel enterprise cannot be quickly acquired by means of the prior art.
The invention relates to a method for monitoring the yield of a steel plant based on thermal infrared remote sensing satellite data, which comprises the following steps:
the method comprises the steps of firstly, acquiring monthly output of pig iron of the steel plant in a historical time period and L1 level data of LANDSAT8/TIRS corresponding to the monthly output aiming at a steel plant area to be monitored; the factory area range is sketched through the remote sensing image, and the urban area range of the steel factory area is excluded;
step two, respectively carrying out earth surface temperature inversion calculation on the L1-grade data of each month, carrying out mask processing according to vector data of factory area and urban area ranges, and respectively extracting earth surface temperature data corresponding to each month of the factory area and the urban area;
the method specifically comprises the following steps: firstly, performing surface temperature inversion calculation on the acquired L1-grade data by an atmospheric correction method aiming at the current month to generate surface temperature data; then, performing mask processing on the surface temperature data according to the vector data of the factory area and the urban area, respectively reserving the surface temperature data of the factory area and the urban area, and removing the surface temperature data outside the area;
deleting the surface temperature data with the cloud through direct observation and screening;
and step four, extracting the maximum value in the plant area ground surface temperature data in each month and the urban ground surface temperature mean value, and calculating the remote sensing monitoring index plant area high-low temperature difference value used for generating the steel yield in the current month.
The high and low temperature difference value calculation formula of the plant area is as follows:
Td＝Tfmax-Tcmean
wherein, TdRepresents the difference value of high and low temperatures of a plant area, TfmaxRepresenting the maximum value, T, in the plant surface temperature datacmeanRepresents the mean value of the urban surface temperature.
Step five, selecting a linear regression mode to establish T based on a least square methoddAnd (4) an estimated production model between the measured yield and the steel yield, and performing precision verification on the estimated production model of the steel.
The method comprises the following specific steps:
501, performing polynomial curve fitting according to a least square method by using monthly pig iron yield data of the steel plant in a historical time period and plant area high and low temperature difference indexes corresponding to each month;
step 502, selecting and (T) according to the principle of minimum deviation square sumd，TdCorresponding throughput) is established by TdAn estimation model with independent variable and dependent variable as yield;
the estimated model formula is as follows:
Y＝A0+A1X+...+AKXK
wherein A is0...AKFor each coefficient of the fitted curve, K is the corresponding number of curve fits, and X is the monthly T corresponding to the finally selected fitted curvedY is monthly estimated production data corresponding to the finally selected fitting curve;
step 503, compare the T of each monthdAnd substituting the estimated production data value into the estimated production model to calculate the estimated production data value corresponding to each month, comparing the estimated production data value with the actual historical data of each month, and calculating an error rate to carry out precision verification.
The error rate is calculated as follows:
E＝((Y-Yr)÷Yr)×100％
wherein E is the error rate, YrIs the actual historical production data acquired.
504. Judging whether the error rate meets the threshold limit, if so, outputting a final estimated production model, otherwise, returning to the step 501 for fitting again, if not, judging that the current estimated production model does not meet the error requirement;
sixthly, carrying out high-low temperature difference T on the plant area of the next month of the steel plantdThe indexes are substituted into the estimated production model meeting the precision requirement, and the steel plant is subjected to next monthThe steel production is monitored.
The invention has the advantages that:
1) the method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data calculates the earth surface temperature through the thermal infrared remote sensing satellite, constructs small-scale earth surface temperature quantitative index parameters and a yield estimation model, and solves the problem that the production state of an enterprise cannot be timely and effectively acquired. The steel yield data generated by the remote sensing monitoring index provides data support for obtaining the capacity information of the steel enterprises in a large range and knowing the development conditions of social economy in time.
2) The method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data provides basic guarantee for the steel industry to meet the requirements of capacity operation and environmental protection, solves the problems of excess capacity, serious pollution and the like of the steel enterprise and provides new objective and neutral heterogeneous data for related financial information service organizations.
Drawings
FIG. 1 is a flow chart of a method for monitoring the production of a steel plant based on thermal infrared remote sensing satellite data according to the present invention;
FIG. 2 shows monthly output of An steel pig iron and corresponding T in the example of the present inventiond(difference between high and low temperatures in the plant area) is shown.
Detailed Description
The present invention will be described in further detail and with reference to the accompanying drawings so that those skilled in the art can understand and practice the invention.
The invention aims at the characteristics of high-temperature operation of the steel plant, utilizes thermal infrared satellite remote sensing to monitor the thermal environment, constructs quantitative index parameters suitable for monitoring the surface temperature of the high-temperature steel plant, and can monitor the yield condition of the steel plant and timely master the production state of a target steel enterprise through the high correlation between the parameters and the yield of the steel plant, thereby serving the strategic decision and management of national industrial structure adjustment and optimization upgrading on one hand and providing objective and neutral heterogeneous data for related financial information service organizations on the other hand.
The method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data, as shown in figure 1, comprises the following steps:
the method comprises the steps of firstly, acquiring historical data of monthly pig iron yield of the steel plant in a historical time period and L1-level data of LANDSAT8/TIRS corresponding to the month of the yield data aiming at a steel plant area to be monitored; vector data of a factory area range is sketched through a remote sensing image, and vector data of an urban area range of a steel factory area are excluded;
step two, respectively carrying out earth surface temperature inversion calculation on the L1-grade data of each month, carrying out mask processing according to the vector data of the factory area and the urban area, and respectively extracting earth surface temperature data corresponding to each month of the factory area and the urban area;
the method specifically comprises the following steps: firstly, performing surface temperature inversion calculation on the acquired L1-level data by an atmospheric correction method by using a Landsat 8LST expansion tool of ENVI software for the current month, calculating and acquiring surface temperature values of all pixels by using thermal infrared remote sensing data and information such as atmospheric profile parameters and thermal infrared load parameters acquired according to satellite imaging time, and generating surface temperature data;
then, the earth surface temperature data are masked according to the vector data of the factory area and the urban area, and the earth surface temperature data T in the steel factory area range and the urban area range are respectively reservedfAnd TcRemoving the surface temperature data outside the area;
step three, opening inverted surface temperature data, and screening the surface temperature data which is cloudless and has better quality through visual interpretation;
the method specifically comprises the following steps: firstly, simultaneously opening the earth surface temperature data of the factory area and urban area range vectors in ENVI software; judging whether clouds exist in the factory area and the urban area through direct observation, and deleting the surface temperature data of the day with the clouds;
and step four, extracting the maximum value in the plant area ground surface temperature data in each month and the urban ground surface temperature mean value, and calculating the remote sensing monitoring index plant area high-low temperature difference value used for generating the steel yield in the current month.
The method specifically comprises the following steps:
step 401, arranging the earth surface temperatures of all pixels in the factory floor range in a descending order, taking the average value of the largest N values in the factory floor temperature data as the highest value of the factory floor temperature, where N is usually 3, and the calculation formula is as follows:
wherein, TfiAnd the earth surface temperature value of the ith pixel arranged from high to low according to the temperature value in the factory area range is represented.
Step 402, calculating the average value of the surface temperature of all pixels in the urban area range, wherein the calculation formula is as follows:
wherein, TfjThe earth surface temperature value of the jth pixel in the urban area range is represented, and M represents the number of the earth surface temperature pixels obtained by inversion calculation in the urban area range;
step 403, calculating the difference value of high temperature and low temperature of the plant area, wherein the calculation formula is as follows:
Td＝Tfmax-Tcmean
wherein, TdRepresents the difference value of high and low temperatures of a plant area, TfmaxRepresenting the maximum value, T, in the plant surface temperature datacmeanRepresents the mean value of the urban surface temperature.
Step five, selecting a linear regression mode to establish T based on a least square methoddAnd (4) an estimated production model between the measured yield and the steel yield, and performing precision verification on the estimated production model of the steel.
The method comprises the following specific steps:
501, performing polynomial curve fitting according to a least square method by using monthly pig iron yield data of the steel plant in a historical time period and plant area high and low temperature difference indexes corresponding to each month;
502, selecting according to the principle of minimum deviation square sumAnd (T)d，TdCorresponding throughput) is established by TdAn estimation model with independent variable and dependent variable as yield;
the estimated model formula is as follows:
Y＝A0+A1X+...+AKXK
wherein A is0...AKFor each coefficient of the fitted curve, K is the corresponding number of curve fits, and X is the monthly T corresponding to the finally selected fitted curvedY is monthly estimated production data corresponding to the finally selected fitting curve;
step 503, compare the T of each monthdAnd substituting the estimated production data value into the estimated production model to calculate the estimated production data value corresponding to each month, comparing the estimated production data value with the actual historical data of each month, and calculating an error rate to carry out precision verification.
The error rate is calculated as follows:
E＝((Y-Yr)÷Yr)×100％
wherein E is the error rate, YrIs the actual historical production data acquired.
504. Judging whether the error rate meets the threshold limit, if so, outputting a final estimated production model, otherwise, returning to the step 501 for fitting again, if not, judging that the current estimated production model does not meet the error requirement;
sixthly, carrying out high-low temperature difference T on the plant area of the next month of the steel plantdAnd (5) substituting the indexes into an estimated production model meeting the precision requirement, and monitoring the steel output of the next month of the steel plant.
Examples
The experiment of monthly pig iron productivity monitoring of Anyang iron and steel products Limited is explained.
Firstly, downloading L1 level data of LANDSAT8/TIRS corresponding to each month in the 1 st month of 2017 to the 3 rd month of 2021 from an official network of the United states geological exploration bureau; acquiring monthly pig iron yield information of the enterprise in the time period from related websites; meanwhile, the vector range of a factory area is sketched through the remote sensing image, and the urban vector range of the steel factory area is excluded.
And then, performing earth surface temperature inversion calculation on the L1-grade data of each month, performing mask extraction according to the vector data of the factory area and the urban area, and acquiring earth surface temperature data in the area ranges of the factory area and the urban area.
Data which pass the screening are interpreted by human eyes, and data with better quality in 21 stages, such as 20170223, 20170327, 20170428, 20170701, 20171122, 20171224, 20180109, 20180226, 20180330, 20180720, 20180922, 20181125, 20191027, 20191128, 20191230, 20200131, 20200216, 20200319, 20200522, 20200826, 20210117 and the like, are reserved.
Then, respectively extracting the maximum value in the plant area ground surface temperature data of the 21-period data and the mean value of the urban area ground surface temperature data, and calculating the high-low temperature difference value T of the plant aread。
And finally, based on the least square principle, taking the data in the period 21 from 20170223 to 20210117 as modeling basic sample data, carrying out yield prediction on the data in the period 20191027, taking all the data before the current period as samples, and respectively establishing the difference value T between the high temperature and the low temperature of the plant areadAnd predicting the current output of the steel plant by using a regression model between the current output of the steel plant and the monthly output of pig iron of the steel plant, and evaluating the precision of the estimation model. The results are shown in Table 1.
TABLE 1
| Date of sample | Monthly output (ten thousand tons) | Model estimation yield (ten thousand tons) | Error rate (%) |
| 20191027 | 49.98 | 52.13 | 4.30％ |
| 20191128 | 48.86 | 45.63 | -6.61％ |
| 20191230 | 47.09 | 43.81 | -6.96％ |
| 20200131 | 54.19 | 47.54 | -12.27％ |
| 20200216 | 47.7 | 48.73 | 2.16％ |
| 20200319 | 49.56 | 50.32 | 1.54％ |
| 20200522 | 70.98 | 61.61 | -13.20％ |
| 20200826 | 71.23 | 62.96 | -11.60％ |
| 20210117 | 47.25 | 48.36 | 2.34％ |
As can be seen from Table 1: and (3) inverting the earth surface temperature by using a thermal infrared remote sensing satellite, and estimating the monthly output of the steel plant by using an estimation model to obtain an average absolute error rate of 6.78%, wherein the absolute error rate of 6 samples is less than 10%, and the absolute error rate of 3 samples is more than 10% but less than 15%.
Monthly output of An steel and pig iron and corresponding TdThe variation trend chart of (difference between high and low temperatures in plant) is shown in FIG. 2, and it can be seen from the chart that the variation trend of monthly pig iron output and the corresponding T are shown except for 20170701, 20180109, 20191027 and other individual periodsdThe variation trends are basically consistent, and the correlation is high. Therefore, the method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data is feasible. Monitoring the indicator T by remote sensingdThe method can effectively acquire the productivity information of the iron and steel enterprises in a large range at a high speed (the difference value of high and low temperatures in a factory area), and provides data support for solving the development condition of social economy.
The results of the above examples show that the method is based on thermal infrared satellite remote sensing, the quantitative index parameters suitable for monitoring the earth surface temperature of the high-temperature steel plant and the yield estimation model for monitoring the yield of the steel plant are constructed with higher precision, objective and effective information can be provided for small-scale steel plant capacity monitoring, objective and neutral data services can be provided for government environmental protection and related financial information service institutions, and the method has better practical application value.
The acquisition of the thermal infrared remote sensing satellite data is influenced by the satellite orbit period and cloud and rain weather, the inverted earth surface temperature only reflects the geothermal condition of the steel plant area on the monitoring day, and the monthly output of the steel plant is the total value of the month, so that the two data are statistically different in period. Meanwhile, the steel plant can change equipment for a long time, so that the specific application of the method needs to be comprehensively analyzed by combining the capacity change of the steel plant.
Claims (3)
1. The method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data is characterized by comprising the following steps of:
firstly, acquiring monthly output of pig iron of an iron and steel plant in a historical time period and L1 level data of LANDSAT8/TIRS corresponding to monthly data aiming at the iron and steel plant to be monitored; the factory area range and the urban area range after the factory area is removed are sketched through the remote sensing image;
then, respectively carrying out earth surface temperature inversion calculation on the L1-grade data of each month, carrying out mask processing according to the ranges of the factory area and the urban area, respectively extracting earth surface temperature data corresponding to each month of the factory area and the urban area, and deleting the earth surface temperature data with cloud;
then, extracting the maximum value in the plant area earth surface temperature data and the urban area earth surface temperature mean value in each month, and calculating the remote sensing monitoring index plant area high-low temperature difference value T used for generating the steel yield in the current monthd；
Finally, based on the least square method, selecting a linear regression mode to establish TdThe estimated model is between the estimated model and the steel yield, and the estimated model of the steel is subjected to precision verification; the difference value T of high and low temperatures of the factory area of the next month of the steel plantdIndexes are substituted into the estimated production model meeting the precision requirement, and the steel output of the next month of the steel plant is monitored;
the method specifically comprises the following steps of calculating the difference value of high and low temperatures of a plant area:
firstly, arranging the earth surface temperatures of all pixels in the factory area range from big to small, taking the average value of the maximum N values in factory area temperature data as the highest value of the factory area temperature, and adopting the calculation formula as follows:
wherein, TfiIndicating the temperature values in the plant range from high to lowThe surface temperature value of the ith pixel of (1);
then, calculating the average value of the surface temperature of all pixels in the urban area range, wherein the calculation formula is as follows:
wherein, TfjThe earth surface temperature value of the jth pixel in the urban area range is represented, and M represents the number of the earth surface temperature pixels obtained by inversion calculation in the urban area range;
finally, the formula for calculating the difference value of the high temperature and the low temperature of the plant area is as follows:
Td＝Tfmax-Tcmean
wherein, TdRepresents the difference value of high and low temperatures of a plant area, TfmaxRepresenting the maximum value, T, in the plant surface temperature datacmeanRepresents the mean value of the urban surface temperature.
2. The method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data as claimed in claim 1, wherein the inversion calculation and the mask processing specifically comprise: firstly, performing surface temperature inversion calculation on the acquired L1-grade data by an atmospheric correction method aiming at the current month to generate surface temperature data; and then, carrying out mask processing on the earth surface temperature data according to the vector data of the factory area and the urban area, respectively reserving the earth surface temperature data of the factory area and the urban area, and removing the earth surface temperature data outside the area.
3. The method for monitoring the yield of the steel plant based on the thermal infrared remote sensing satellite data as claimed in claim 1, wherein the specific steps of establishing the estimated yield model and performing the precision verification are as follows:
501, performing polynomial curve fitting according to a least square method by using monthly pig iron yield data of the steel plant in a historical time period and plant area high and low temperature difference indexes corresponding to each month;
step 502, according to the principle of minimum deviation sum of squaresSelection and TdAnd TdThe closest fitting curve of each point of each corresponding yield is established by TdAn estimation model with independent variable and dependent variable as yield;
the estimated model formula is as follows:
Y＝A0+A1X+...+AKXK
wherein A is0...AKFor each coefficient of the fitted curve, K is the corresponding number of curve fits, and X is the monthly T corresponding to the finally selected fitted curvedY is monthly estimated production data corresponding to the finally selected fitting curve;
step 503, compare the T of each monthdSubstituting the estimated production data value into the estimated production model to calculate the estimated production data value corresponding to each month, comparing the estimated production data value with the actual historical data of each month, and calculating an error rate to carry out precision verification;
the error rate is calculated as follows:
E＝((Y-Yr)÷Yr)×100％
wherein E is the error rate, YrHistorical yield data for actual acquisition;
504. and judging whether the error rate meets the threshold limit, if so, outputting a final estimated model, otherwise, returning to the step 501 for fitting again when the current estimated model does not meet the error requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110909812.8A CN113642170B (en) | 2021-08-09 | 2021-08-09 | Steel plant yield monitoring method based on thermal infrared remote sensing satellite data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110909812.8A CN113642170B (en) | 2021-08-09 | 2021-08-09 | Steel plant yield monitoring method based on thermal infrared remote sensing satellite data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642170A CN113642170A (en) | 2021-11-12 |
| CN113642170B true CN113642170B (en) | 2022-04-05 |
Family
ID=78420317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110909812.8A Active CN113642170B (en) | 2021-08-09 | 2021-08-09 | Steel plant yield monitoring method based on thermal infrared remote sensing satellite data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642170B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107462331A (en) * | 2017-08-07 | 2017-12-12 | 中国科学院遥感与数字地球研究所 | Iron and steel enterprise's production history remote-sensing monitoring method and system |
| CN107490363A (en) * | 2017-07-19 | 2017-12-19 | 二十世纪空间技术应用股份有限公司 | A kind of heat production enterprise production intensity monitoring method based on surface temperature data |
| CN107941344A (en) * | 2017-11-15 | 2018-04-20 | 中国科学院遥感与数字地球研究所 | A kind of steel plant based on surface temperature remote-sensing inversion go formulation experiment method |
| CN111651856A (en) * | 2020-04-23 | 2020-09-11 | 中国科学院空天信息创新研究院 | Self-adaptive industrial heat anomaly detection method |
| CN112883568A (en) * | 2021-02-04 | 2021-06-01 | 中国地质调查局武汉地质调查中心 | Method, device and equipment for constructing monthly steel-making yield estimation model and storage medium |
| WO2021112756A1 (en) * | 2019-12-05 | 2021-06-10 | Agency For Science, Technology And Research | Method and apparatus for simulating a temperature distribution of a surface of a built environment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9996074B2 (en) * | 2016-09-21 | 2018-06-12 | International Business Machines Corporation | System and predictive modeling method for smelting process control based on multi-source information with heterogeneous relatedness |
| US11636672B2 (en) * | 2019-10-15 | 2023-04-25 | A.U.G. Signals Ltd. | Crop phenology estimation and tracking with remote sensing imagery |
| CN111487199B (en) * | 2020-04-23 | 2022-12-20 | 中国科学院空天信息创新研究院 | Steel plant remote sensing extraction method based on industrial production activity characteristics |
-
2021
- 2021-08-09 CN CN202110909812.8A patent/CN113642170B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107490363A (en) * | 2017-07-19 | 2017-12-19 | 二十世纪空间技术应用股份有限公司 | A kind of heat production enterprise production intensity monitoring method based on surface temperature data |
| CN107462331A (en) * | 2017-08-07 | 2017-12-12 | 中国科学院遥感与数字地球研究所 | Iron and steel enterprise's production history remote-sensing monitoring method and system |
| CN107941344A (en) * | 2017-11-15 | 2018-04-20 | 中国科学院遥感与数字地球研究所 | A kind of steel plant based on surface temperature remote-sensing inversion go formulation experiment method |
| WO2021112756A1 (en) * | 2019-12-05 | 2021-06-10 | Agency For Science, Technology And Research | Method and apparatus for simulating a temperature distribution of a surface of a built environment |
| CN111651856A (en) * | 2020-04-23 | 2020-09-11 | 中国科学院空天信息创新研究院 | Self-adaptive industrial heat anomaly detection method |
| CN112883568A (en) * | 2021-02-04 | 2021-06-01 | 中国地质调查局武汉地质调查中心 | Method, device and equipment for constructing monthly steel-making yield estimation model and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| "A Method for Monitoring Iron and Steel Factory Economic Activity Based on Satellites";Yi Zhou等;《Sustainability》;20180609;第10卷(第6期);第1-21页 * |
| "基于多时相热红外遥感的钢铁企业生产状态辅助监测";李静等;《国土资源遥感》;20190331;第31卷(第1期);第220-228页 * |
| 基于MODIS-NDVI的河南省冬小麦产量遥感估测;赵文亮等;《地理研究》;20121231;第31卷(第12期);第2310-2320页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642170A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Online cement clinker quality monitoring: A soft sensor model based on multivariate time series analysis and CNN | |
| Hengkai et al. | Remote sensing monitoring of land damage and restoration in rare earth mining areas in 6 counties in southern Jiangxi based on multisource sequential images | |
| CN107462331B (en) | Iron and steel enterprise's production history remote-sensing monitoring method and system | |
| CN104899388A (en) | Structure safety evaluation method under action of environmental loads of space steel structure | |
| CN101211383A (en) | Blast furnace molten iron silicon content feature analysis and prediction method | |
| CN110457867B (en) | Time sequence data filling and restoring method based on machine learning | |
| Chen et al. | LQD-RKHS-based distribution-to-distribution regression methodology for restoring the probability distributions of missing SHM data | |
| WO2020043028A1 (en) | Method for predicting air pollution using historical air quality data features | |
| Yue et al. | Mechanics-Guided optimization of an LSTM network for Real-Time modeling of Temperature-Induced deflection of a Cable-Stayed bridge | |
| CN107941344B (en) | Steel plant capacity-removing monitoring method based on surface temperature remote sensing inversion | |
| CN109443543B (en) | Infrared radiation quantitative characterization method for bearing coal rock damage evolution | |
| CN102033523A (en) | Strip steel quality forecasting, furnace condition early-warning and fault diagnosis method based on partial least square | |
| JP2012074007A (en) | Operation condition optimization system of plant, operation condition optimization method of plant and operation condition optimization program of plant | |
| CN112170501B (en) | Prediction method for wear crown and thermal crown of roller | |
| Feng et al. | Do anthropogenic factors affect the improvement of vegetation cover in resource-based region? | |
| CN110319938B (en) | High-spatial-resolution earth surface temperature generation method | |
| CN111046026B (en) | Constraint optimization-based missing energy consumption data filling method | |
| CN113592165B (en) | Sub-season climate prediction method and system based on ten-day trend and physical mode modeling | |
| Sun et al. | Variation of industrial air pollution emissions based on VIIRS thermal anomaly data | |
| CN104778361A (en) | Improved method for predicting hot-metal silicon content by EMD-Elman (empirical mode decomposition-Elman) neural network | |
| Guo et al. | A novel prediction model for the degree of rescue safety in mine thermal dynamic disasters based on fuzzy analytical hierarchy process and extreme learning machine | |
| CN113642170B (en) | Steel plant yield monitoring method based on thermal infrared remote sensing satellite data | |
| CN113177364B (en) | Soft measurement modeling method for temperature of blast furnace tuyere convolution zone | |
| Jiao et al. | Collaborative multiple rank regression for temperature prediction of blast furnace | |
| Li et al. | Identifying spatial patterns of synchronization between NDVI and climatic determinants using joint recurrence plots |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Production monitoring method for steel mills based on thermal infrared remote sensing satellite data Effective date of registration: 20230613 Granted publication date: 20220405 Pledgee: Beijing SME financing re Guarantee Co.,Ltd. Pledgor: Beijing Sixiang Aishu Technology Co.,Ltd. Registration number: Y2023990000293 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |