Method and device for obtaining endpoint information of sintering endpoint

Abstract

The present invention provides a method and device for obtaining endpoint information of a sintering endpoint. The method comprises the following steps: comparing the exhaust gas temperatures of each wind box at the same time to obtain the highest exhaust gas temperature of each wind box at each time; selecting the exhaust gas temperatures of each wind box at a first preset position at the time when the highest exhaust gas temperature of each wind box belongs to the wind box at a second preset position at the time when the highest exhaust gas temperature of each wind box belongs to the wind box at a second preset position at the time when the highest exhaust gas temperature of each wind box belongs to the wind box at a second preset position at the time as the second data set; correcting the exhaust gas temperature of the tail wind box at the current time based on the first data set and the second data set to obtain the corrected temperature of the tail wind box; comparing the corrected temperature of the tail wind box with the highest exhaust gas temperature of all wind boxes at the current time to obtain a comparison result; determining an information mode based on the comparison result; and determining the endpoint information of the sintering endpoint based on the information mode.

Description

Technical Field

[0001] The present invention relates to the technical field of sintering process, and in particular to a method and device for acquiring endpoint information of a sintering endpoint. Background Art

[0002] Sintering is an important part of the ironmaking process. The quality of sintered ore directly affects the stability and smoothness of the blast furnace. The endpoint information of sintering (such as sintering endpoint temperature and endpoint position) is directly related to the quality of sintered ore. During the sintering process, sintering endpoint information such as sintering endpoint temperature and endpoint position cannot be directly detected by equipment. On-site production personnel need to obtain it through experience or calculation. The results are inaccurate, the reaction speed is slow, the labor intensity of personnel is high, and the sintering endpoint fluctuates greatly, resulting in fluctuations in the quality of sintered ore.

[0003] Although some existing solutions can avoid technicians going to the site to obtain endpoint information, the existing solutions for obtaining endpoint information ignore the leakage of the tail wind box, resulting in errors in the obtained endpoint information. Alternatively, the existing solutions require the addition of some additional detection equipment to improve the accuracy of the endpoint information, which increases the equipment cost. Summary of the invention

[0004] The present invention provides a method and device for acquiring endpoint information of a sintering endpoint, so as to solve the technical problem of acquiring accurate endpoint information without increasing the cost of detection equipment.

[0005] In one aspect, the present invention provides a method for obtaining endpoint information of a sintering endpoint, comprising:

[0006] Obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment;

[0007] Comparing the windbox exhaust gas temperatures at the same time among the windbox exhaust gas temperatures to obtain the highest windbox exhaust gas temperature at each time;

[0008] Among the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the first preset position is located are selected as the first data set;

[0009] Among the wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the second preset position is located are selected as the second data set;

[0010] Correcting the exhaust gas temperature of the tail windbox at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail windbox;

[0011] Comparing the tail windbox correction temperature with the highest windbox exhaust gas temperature of all windboxes at the current moment to obtain a comparison result;

[0012] determining an information mode based on the comparison result;

[0013] End point information of a sintering endpoint is determined based on the information pattern.

[0014] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, the method corrects the exhaust gas temperature of the tail windbox at the current moment based on the first data set and the second data set to obtain the corrected temperature of the tail windbox, including:

[0015] Determine an average temperature difference between an average value of the windbox exhaust gas temperature of the windbox at the first preset position and an average value of the windbox exhaust gas temperature of the windbox at the second preset position in the first data set as a material layer temperature drop;

[0016] Determine a first average value of the windbox exhaust gas temperature of the tail windbox in the second data set, and a second average value of the windbox exhaust gas temperature of the windbox at the second preset position;

[0017] Determining a correction coefficient for the wind box exhaust gas temperature of the tail wind box based on the material layer temperature drop, the first average value, and the second average value;

[0018] The tail wind box exhaust gas temperature is corrected based on the correction coefficient to obtain the tail wind box correction temperature.

[0019] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, the correction coefficient of the wind box exhaust gas temperature of the tail wind box is determined based on the material layer temperature drop, the first average value and the second average value, including:

[0020] Calculate a first difference between the second average value and the temperature drop of the material layer;

[0021] The ratio of the first difference to the first average value is calculated to determine a correction coefficient of the wind box exhaust gas temperature of the tail wind box.

[0022] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, determining an information mode based on the comparison result includes:

[0023] When the comparison result is that the tail windbox correction temperature is less than or equal to the highest windbox exhaust gas temperature of all windboxes at the current moment, determining that the information mode is a non-hysteresis mode;

[0024] When the comparison result is that the tail windbox correction temperature is greater than the highest windbox exhaust gas temperature of all windboxes at the current moment, it is determined that the information mode is the hysteresis mode.

[0025] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, when the information mode is a non-hysteresis mode, determining the endpoint information of the sintering endpoint based on the information mode includes:

[0026] Obtaining the current maximum wind box exhaust gas temperature and the position of the wind box thermocouple of the target wind box to which the current maximum wind box exhaust gas temperature belongs as the first parameter;

[0027] Obtaining the windbox exhaust gas temperature at the previous moment before the current moment of the target windbox and the position of the windbox thermocouple as the second parameter;

[0028] Obtaining the windbox exhaust gas temperature at the next moment of the target windbox and the position of the windbox thermocouple as the third parameter;

[0029] End point information of a sintering end point is determined based on the first parameter, the second parameter, and the third parameter.

[0030] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, the endpoint information of the sintering endpoint is determined based on the first parameter, the second parameter and the third parameter, including:

[0031] Fitting a quadratic curve based on the first parameter, the second parameter and the third parameter;

[0032] The vertex parameter of the quadratic curve is determined as the endpoint information of the sintering endpoint.

[0033] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, when the information mode is a hysteresis mode, determining the endpoint information of the sintering endpoint based on the information mode includes:

[0034] Acquiring historical parameter information during the sintering process, wherein the historical parameter information includes historical endpoint information of the sintering endpoint;

[0035] Determine the relevance between the historical endpoint information and the remaining historical information in the historical parameter information excluding the historical endpoint information;

[0036] Retaining the remaining historical information whose relevance satisfies a preset relevance threshold and the historical endpoint information as a training sample set;

[0037] Establishing an endpoint information prediction model for sintering endpoint based on the training sample set and machine learning;

[0038] The endpoint information of the sintering endpoint is predicted based on the endpoint information prediction model.

[0039] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, before obtaining the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment, the method further includes:

[0040] Real-time acquisition of time series data during sintering process;

[0041] identifying outliers in each of the time series data;

[0042] Determine the missing value at the time when the outlier value is located;

[0043] The missing values ​​are replaced by the outliers.

[0044] According to a method for obtaining endpoint information of a sintering endpoint provided by the present invention, the step of identifying abnormal values ​​in each of the time series data comprises:

[0045] Identify outliers in each of the time series data using the 3σ method;

[0046] The determining of the missing value at the time when the abnormal value is located includes:

[0047] The missing value at the time when the outlier is located is determined by nearest neighbor filling.

[0048] On the other hand, the present invention also provides a device for obtaining endpoint information of a sintering endpoint, comprising:

[0049] A data acquisition module, used to obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment;

[0050] A maximum temperature determination module, used for comparing the bellows exhaust gas temperatures at the same time among the bellows exhaust gas temperatures, to obtain the maximum bellows exhaust gas temperature at each time;

[0051] A first screening module, used for screening out, from the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the first preset position is located as the first data set;

[0052] A second screening module is used to screen out, from the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the second preset position is located as the second data set;

[0053] a temperature correction module, configured to correct the exhaust temperature of the tail wind box at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail wind box;

[0054] A temperature comparison module, used to compare the tail windbox correction temperature with the highest windbox exhaust gas temperature of all windboxes at the current moment, and obtain a comparison result;

[0055] a mode determination module, configured to determine an information mode based on the comparison result;

[0056] The endpoint information determination module is used to determine the endpoint information of the sintering endpoint based on the information pattern.

[0057] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for obtaining endpoint information of the sintering endpoint as described in any one of the above is implemented.

[0058] The method and device for obtaining endpoint information of the sintering endpoint provided by the present invention compare the bellows exhaust gas temperatures at the same time among the bellows exhaust gas temperatures to obtain the highest bellows exhaust gas temperature at each moment, and among the bellows exhaust gas temperatures, screen out the bellows exhaust gas temperatures at the moment when the highest bellows exhaust gas temperature of the bellows at the first preset position is located as the first data set, and screen out the bellows exhaust gas temperatures at the moment when the highest bellows exhaust gas temperature of the bellows at the second preset position is located as the second data set, and correct the tail bellows exhaust gas temperature of the tail bellows at the current moment based on the first data set and the second data set to obtain the corrected temperature of the tail bellows, thereby reducing the influence of the air leakage of the tail bellows on the tail bellows exhaust temperature at the current moment, and the corrected temperature of the tail bellows can more accurately reflect the temperature of the tail bellows. Compare the corrected temperature of the tail wind box with the highest wind box exhaust gas temperature of all the wind boxes at the current moment to obtain a comparison result, determine the information mode based on the comparison result, and determine the endpoint information of the sintering end point based on the information mode. In this way, more accurate endpoint information can be obtained without adding additional equipment, and the quality and output of sintered ore can be improved without increasing equipment costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 It is a schematic flow chart of a method for obtaining endpoint information of a sintering endpoint provided in an embodiment of the present invention;

[0061] Figure 2 It is a schematic structural diagram of a device for acquiring endpoint information of a sintering endpoint provided in an embodiment of the present invention;

[0062] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Figure 1 It is a flow chart of a method for obtaining the endpoint information of the sintering endpoint provided by an embodiment of the present invention. The executor of the method may be a computer, a mobile phone, or a smart wearable device, etc. The method can be used to control the sintering system. The sintering system may mainly include a trolley, a mixer, a main exhaust fan, a ring cooler, and other equipment. The overall process flow may generally include various raw materials being proportioned in a batching chamber to form a mixed material, and then entering the mixer for mixing and balling, and then evenly spreading it on the trolley through a round roller feeder and a nine-roller feeder to form a material layer, and the ignition fan and the ignition fan ignite the material to start the sintering process. The sintered ore obtained after the sintering is completed is crushed by a single roller crusher and then cooled in a ring cooler, and finally sent to a blast furnace or a finished ore bin after screening and granulation. Among them, the oxygen required for the sintering process is provided by the main exhaust fan. There are multiple vertically arranged bellows under the trolley. Below the bellows is a horizontally placed large flue (or flue). The large flue is connected to the main exhaust fan. The negative pressure wind generated by the main exhaust fan through the large flue and the bellows passes through the trolley to provide combustion-supporting air for the sintering process.

[0065] Specifically, the method may include the following steps 101 to 108 .

[0066] 101. Obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment.

[0067] In this step, the temperature acquisition device can be used to collect the bellows exhaust gas temperature of all bellows at each moment in the sintering process and store it in a preset storage area, and then the bellows exhaust gas temperature of all bellows in the sintering process within the preset time before the current moment is obtained from the preset storage area. It can be understood that each stored bellows exhaust gas temperature corresponds to a collection moment and the bellows to which it belongs. The preset time can be set, for example, it can be set to any value between 12 and 36 hours, such as 24 hours. Of course, the preset time can also be adjusted according to actual conditions, and this embodiment does not make specific limitations. The bellows exhaust gas temperature of all bellows in the sintering process within the preset time before the current moment belongs to historical data.

[0068] 102. Compare the exhaust gas temperatures of the bellows at the same time among the exhaust gas temperatures of the bellows to obtain the highest exhaust gas temperature of the bellows at each time.

[0069] In this step, generally, the number of bellows may include multiple numbers, for example, 5, 6, 10 or other numbers, which is not specifically limited in this embodiment. Each bellows exhaust gas temperature has a corresponding collection time. For example, the collection time may include 1 o'clock, 2 o'clock, 3 o'clock and 4 o'clock, that is, it is necessary to compare the exhaust gas temperatures of each bellows at 1 o'clock, compare the exhaust gas temperatures of each bellows at 2 o'clock, compare the exhaust gas temperatures of each bellows at 3 o'clock, and compare the exhaust gas temperatures of each bellows at 4 o'clock to obtain the highest exhaust gas temperature of the bellows at 1 o'clock, the highest exhaust gas temperature of the bellows at 2 o'clock, the highest exhaust gas temperature of the bellows at 3 o'clock, and the highest exhaust gas temperature of the bellows at 4 o'clock.

[0070] 103. From the exhaust gas temperatures of the bellows, the exhaust gas temperatures of the bellows at the time when the highest exhaust gas temperature of the bellows at the first preset position is obtained are selected as the first data set.

[0071] In this step, it is assumed that the highest windbox exhaust gas temperature at point 1 and the highest windbox exhaust gas temperature at point 2 belong to the first preset position windbox, that is, the exhaust gas temperatures of each windbox at point 1 and the exhaust gas temperatures of each windbox at point 2 are taken as the first data set. The first preset position windbox can be set according to the actual situation, for example, set to the third-to-last windbox, or set to a windbox at other positions, which is not specifically limited in this embodiment. In general, the tail windbox can be regarded as the penultimate windbox, the windbox next to the tail windbox can be regarded as the second-to-last windbox, and the windbox next to the second-to-last windbox can be regarded as the third-to-last windbox. Of course, the windbox next to the tail windbox can also be regarded as the penultimate windbox, the windbox next to the penultimate windbox can be regarded as the second-to-last windbox, and the windbox next to the second-to-last windbox can be regarded as the third-to-last windbox. How to define the position of the windbox can be adjusted according to the actual situation.

[0072] 104. From the exhaust gas temperatures of the bellows, the exhaust gas temperatures of the bellows at the time when the highest exhaust gas temperature of the bellows at the second preset position occurs are selected as the second data set.

[0073] In this step, it is assumed that the highest wind box exhaust gas temperature at point 3 and the highest wind box exhaust gas temperature at point 4 belong to the wind box at the second preset position, that is, the exhaust gas temperatures of each wind box at point 3 and the exhaust gas temperatures of each wind box at point 4 are taken as the second data set. The wind box at the second preset position can be set, and is not specifically limited here. Generally, the wind box at the second preset position is between the wind box at the first preset position and the tail wind box, and is adjacent to the wind box at the first preset position. For example, assuming that the wind box at the first preset position is the third to last wind box, the wind box at the second preset position is the second to last wind box.

[0074] 105. Correct the exhaust gas temperature of the tail windbox at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail windbox.

[0075] In this step, considering that there may be air leakage in the tail bellows, which may cause the measured tail bellows exhaust gas temperature to be inaccurate, the tail bellows exhaust gas temperature at the current moment is corrected based on the first data set and the second data set to obtain the tail bellows corrected temperature. The tail bellows corrected temperature can more accurately reflect the temperature of the tail bellows, thereby improving the accuracy of the obtained endpoint information.

[0076] 106. Compare the tail windbox correction temperature with the highest windbox exhaust gas temperature of all windboxes at the current moment to obtain a comparison result.

[0077] In this step, the corrected temperature of the tail windbox is compared with the highest windbox exhaust gas temperature of all windboxes at the current moment, rather than the current tail windbox exhaust gas temperature of the tail windbox, which is also beneficial to ensure the accuracy of the comparison result.

[0078] 107. Determine the information mode based on the comparison result.

[0079] In this step, the information mode may include a non-hysteresis mode and a hysteresis mode. The information mode may be used to indicate the magnitude relationship between the tail windbox correction temperature and the highest windbox exhaust gas temperature of all windboxes at the current moment.

[0080] 108. Determine endpoint information of a sintering endpoint based on the information pattern.

[0081] In this step, the endpoint information may include information such as the sintering endpoint temperature and the endpoint position.

[0082] In this embodiment, the exhaust gas temperatures of the windboxes at the same time are compared to obtain the highest exhaust gas temperature of the windboxes at each time. Among the exhaust gas temperatures of the windboxes, the exhaust gas temperatures of the windboxes at the time of the highest exhaust gas temperatures of the windboxes at the first preset position are screened out as the first data set, and the exhaust gas temperatures of the windboxes at the time of the highest exhaust gas temperatures of the windboxes at the second preset position are screened out as the second data set. The exhaust gas temperature of the tail windbox at the current time is corrected based on the first data set and the second data set to obtain the corrected temperature of the tail windbox, thereby reducing the influence of the leakage of the tail windbox on the exhaust gas temperature of the tail windbox at the current time. The corrected temperature of the tail windbox can more accurately reflect the temperature of the tail windbox. Compare the corrected temperature of the tail windbox with the highest exhaust gas temperature of all the windboxes at the current time to obtain a comparison result, determine the information mode based on the comparison result, and determine the endpoint information of the sintering endpoint based on the information mode. More accurate endpoint information can be obtained without adding additional equipment, and the output and quality of sintered ore can be improved without increasing equipment costs.

[0083] In one embodiment of the present specification, the exhaust temperature of the tail wind box at the current moment is corrected based on the first data set and the second data set to obtain the corrected temperature of the tail wind box, including:

[0084] Determine an average temperature difference between an average value of the windbox exhaust gas temperature of the windbox at the first preset position and an average value of the windbox exhaust gas temperature of the windbox at the second preset position in the first data set as a material layer temperature drop;

[0085] Determine a first average value of the windbox exhaust gas temperature of the tail windbox in the second data set, and a second average value of the windbox exhaust gas temperature of the windbox at the second preset position;

[0086] Determine a correction coefficient for the wind box exhaust gas temperature of the tail wind box based on the material layer temperature drop, the first average value, and the second average value;

[0087] The tail wind box exhaust gas temperature is corrected based on the correction coefficient to obtain the tail wind box correction temperature.

[0088] In this embodiment, in the process of determining the correction coefficient of the bellows exhaust gas temperature of the tail windbox, multiple data are used, such as the average value of the bellows exhaust gas temperature of the first preset position bellows in the first data set, the average value of the bellows exhaust gas temperature of the second preset position bellows in the first data set, the first average value of the bellows exhaust gas temperature of the tail windbox in the second data set, and the second average value of the bellows exhaust gas temperature of the second preset position bellows in the second data set. This can improve the rationality of the correction coefficient so as to obtain a more accurate corrected tail windbox temperature.

[0089] Moreover, in the present embodiment, the first preset position bellows may preferably be the third-to-last bellows, and the second preset position bellows may preferably be the second-to-last bellows. This allows the first preset position bellows and the second preset position bellows to more accurately reflect the endpoint information of the sintering endpoint, and also more accurately reflect the bellows exhaust gas temperature of the tail bellows, so as to further improve the accuracy of the correction coefficient obtained, thereby obtaining a more accurate tail bellows correction temperature.

[0090] In one embodiment of the present specification, the correction coefficient of the wind box exhaust gas temperature of the tail wind box is determined based on the material layer temperature drop, the first average value and the second average value, including:

[0091] Calculate a first difference between the second average value and the temperature drop of the material layer;

[0092] The ratio of the first difference to the first average value is calculated to determine a correction coefficient of the wind box exhaust gas temperature of the tail wind box.

[0093] In this embodiment, the first average value can be expressed as T1, the second average value can be expressed as T2, and the temperature drop of the material layer can be expressed as T. Calculating the first difference between the second average value T2 and the temperature drop of the material layer T, calculating the ratio of the first difference to the first average value T1, and determining the correction coefficient of the wind box exhaust gas temperature of the tail wind box is conducive to ensuring the rationality of the correction coefficient. The correction coefficient can be expressed as γ. Correction coefficient .

[0094] In one embodiment of the present specification, determining the information mode based on the comparison result includes:

[0095] When the comparison result is that the tail windbox correction temperature is less than or equal to the highest windbox exhaust gas temperature of all windboxes at the current moment, the information mode is determined to be the non-hysteresis mode;

[0096] When the comparison result is that the tail windbox correction temperature is greater than the highest windbox exhaust gas temperature of all windboxes at the current moment, it is determined that the information mode is the hysteresis mode.

[0097] In this embodiment, different information modes represent the temperature relationship between the corrected temperature of the tail windbox and the highest windbox exhaust gas temperature of all the windboxes at the current moment. When the temperature relationship is different, different methods are flexibly used to determine the endpoint information, which is conducive to ensuring the rationality and accuracy of the endpoint information.

[0098] In one embodiment of the present specification, when the information mode is a non-hysteresis mode, determining the endpoint information of the sintering endpoint based on the information mode includes:

[0099] The highest windbox exhaust gas temperature at the current moment and the orientation of the windbox thermocouple of the target windbox to which the highest windbox exhaust gas temperature at the current moment belongs are obtained as the first parameter. The target windbox is the windbox corresponding to the highest windbox exhaust gas temperature at the current moment. The first parameter can be expressed as (t1, a1), where t1 represents the highest windbox exhaust gas temperature at the current moment, and a1 represents the orientation of the windbox thermocouple of the target windbox to which the highest windbox exhaust gas temperature at the current moment belongs. The orientation can represent the direction and position of the windbox thermocouple.

[0100] The windbox exhaust gas temperature of the target windbox at the previous moment before the current moment and the orientation of the windbox thermocouple are obtained as the second parameter. The second parameter can be expressed as (t2, a2), t2 represents the windbox exhaust gas temperature of the target windbox at the previous moment before the current moment, and a2 represents the orientation of the windbox thermocouple of the target windbox at the previous moment before the current moment.

[0101] The windbox exhaust gas temperature at the next moment after the current moment of the target windbox and the position of the windbox thermocouple are obtained as the third parameter. The third parameter can be expressed as (t3, a3), t3 represents the windbox exhaust gas temperature at the next moment after the current moment of the target windbox, and a3 represents the position of the windbox thermocouple at the next moment after the current moment of the target windbox.

[0102] End point information of the sintering end point is determined based on the first parameter, the second parameter, and the third parameter.

[0103] Specifically, determining the endpoint information of the sintering endpoint based on the first parameter, the second parameter and the third parameter includes:

[0104] fitting a quadratic curve based on the first parameter, the second parameter, and the third parameter;

[0105] The vertex parameters of the quadratic curve are determined as the end point information of the sintering end point.

[0106] In this embodiment, in the non-hysteresis mode, the curve of the exhaust gas temperature of the last three wind boxes is more similar to a quadratic curve. Therefore, when the information mode is the non-hysteresis mode, the inflection point position of the quadratic curve can predict the sintering end point in real time, because the inflection point position represents the turning point of the temperature change, that is, the position where the temperature starts to drop after reaching the highest point in the sintering process. Therefore, it is very accurate to use the vertex parameter of the quadratic curve as the end point information of the sintering end point.

[0107] In one embodiment of the present specification, when the information mode is a hysteresis mode, determining the endpoint information of the sintering endpoint based on the information mode includes:

[0108] Acquire historical parameter information during the sintering process, wherein the historical parameter information includes historical endpoint information of the sintering endpoint;

[0109] Determine the relevance between the historical endpoint information and the remaining historical information in the historical parameter information excluding the historical endpoint information;

[0110] Retain the remaining historical information whose relevance meets the preset relevance threshold and the historical endpoint information as a training sample set;

[0111] Establish an endpoint information prediction model for sintering endpoint based on training sample set and machine learning;

[0112] The endpoint information of the sintering endpoint is predicted based on the endpoint information prediction model.

[0113] In this embodiment, the Pearson correlation analysis method can be used to determine the correlation between the historical endpoint information and the remaining historical information in the historical parameter information excluding the historical endpoint information. This method can obtain a relatively accurate correlation, which is conducive to retaining more reasonable and accurate remaining historical information. Machine learning can refer to multiple linear regression. When the information mode is a lag mode, an endpoint information prediction model for the sintering endpoint is established based on a training sample set and machine learning, and the endpoint information of the sintering endpoint is predicted based on the endpoint information prediction model, so that relatively accurate endpoint information can be obtained. In this embodiment, the endpoint information prediction model is used in the lag mode, rather than the endpoint information prediction model in any mode, so that the use of the endpoint information prediction model can be reduced, which is conducive to reducing the situation where the model occupies too many resources. Historical parameter information generally may include sintering process parameter time series data such as the collection of sintering raw material data, sintering silo equipment monitoring data, sintering mixing equipment monitoring data, and sintering machine equipment monitoring data, wherein the historical endpoint information of the sintering endpoint and the historical information of the non-sintering endpoint may also be included.

[0114] In one embodiment of the present specification, before obtaining the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time before the current moment, it also includes:

[0115] Real-time acquisition of time series data during sintering process;

[0116] Identify outliers in each time series data;

[0117] Determine the missing values ​​at the time when the outliers are present;

[0118] Replace outliers with missing values.

[0119] In this embodiment, the time series data represents data collected at different times. Missing values ​​can also be understood as estimated values ​​at the time when the outlier is located. Time series data generally may include sintering process parameter time series data such as sintering raw material data collected in real time, sintering silo equipment monitoring data, sintering mixing equipment monitoring data, and sintering machine equipment monitoring data, which may also include the wind box exhaust gas temperature of all wind boxes and the orientation of the wind box thermocouples. Identifying the outliers in each time series data, determining the missing values ​​at the time when the outliers are located, and replacing the outliers with the missing values ​​is conducive to improving the accuracy of the wind box exhaust gas temperature of all wind boxes in the sintering process within the preset time length obtained later, thereby improving the accuracy of the endpoint information.

[0120] In one embodiment of the present specification, identifying outliers in each of the time series data includes:

[0121] Identify outliers in each of the time series data using the 3σ method;

[0122] Determine the missing values ​​at the time when the outliers are present, including:

[0123] Missing values ​​at the moments where outliers are identified are filled in by nearest neighbors.

[0124] In this embodiment, the outliers in each of the time series data are identified by the 3σ method, and the outliers can be judged more accurately. In addition to the 3σ method, other methods can of course be used, which are not specifically limited here. By determining the missing value at the time when the outlier is located by nearest neighbor filling, the rationality of the missing value can be ensured. This embodiment can further improve the accuracy of the endpoint information. In addition to the nearest neighbor filling, other methods can also be used to determine the missing value, which are not specifically limited here.

[0125] Based on the same general inventive concept, the present invention also protects a device for obtaining endpoint information of a sintering endpoint, such as Figure 2 As shown. The following is a description of the device for acquiring the endpoint information of the sintering endpoint provided by the present invention. The device for acquiring the endpoint information of the sintering endpoint described below and the method for acquiring the endpoint information of the sintering endpoint described above can be referred to each other. The device may include a data acquisition module 201, a maximum temperature determination module 202, a first screening module 203, a second screening module 204, a temperature correction module 205, a temperature comparison module 206, a mode determination module 207 and an endpoint information determination module 208.

[0126] The data acquisition module 201 is used to obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment;

[0127] The maximum temperature determination module 202 is used to compare the wind box exhaust gas temperatures at the same time among the wind box exhaust gas temperatures to obtain the maximum wind box exhaust gas temperature at each time;

[0128] The first screening module 203 is used to screen out the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the first preset position is located from the wind box exhaust gas temperatures as the first data set;

[0129] The second screening module 204 is used to screen out the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the second preset position is located from the wind box exhaust gas temperatures as the second data set;

[0130] The temperature correction module 205 is used to correct the exhaust gas temperature of the tail wind box at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail wind box;

[0131] The temperature comparison module 206 is used to compare the tail wind box correction temperature with the highest wind box exhaust gas temperature of all wind boxes at the current moment to obtain a comparison result;

[0132] The mode determination module 207 is used to determine the information mode based on the comparison result;

[0133] The endpoint information determination module 208 is used to determine the endpoint information of the sintering endpoint based on the information pattern.

[0134] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0135] like Figure 3 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the method for obtaining the endpoint information of the sintering endpoint.

[0136] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0137] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for obtaining the endpoint information of the sintering endpoint provided by the above methods.

[0138] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the method for obtaining the endpoint information of the sintering endpoint provided by the above methods.

[0139] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for obtaining endpoint information of a sintering endpoint, characterized in that: include: Obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment; Comparing the windbox exhaust gas temperatures at the same time among the windbox exhaust gas temperatures to obtain the highest windbox exhaust gas temperature at each time; Among the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the first preset position is located are selected as the first data set; Among the wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the second preset position is located are selected as the second data set; Correcting the exhaust gas temperature of the tail windbox at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail windbox; Comparing the tail windbox correction temperature with the highest windbox exhaust gas temperature of all windboxes at the current moment to obtain a comparison result; determining an information mode based on the comparison result; Determining endpoint information of a sintering endpoint based on the information pattern; The method of correcting the exhaust gas temperature of the tail wind box at the current moment based on the first data set and the second data set to obtain the corrected temperature of the tail wind box includes: Determine an average temperature difference between an average value of the windbox exhaust gas temperature of the windbox at the first preset position and an average value of the windbox exhaust gas temperature of the windbox at the second preset position in the first data set as a material layer temperature drop; Determine a first average value of the windbox exhaust gas temperature of the tail windbox in the second data set, and a second average value of the windbox exhaust gas temperature of the windbox at the second preset position; Determining a correction coefficient for the wind box exhaust gas temperature of the tail wind box based on the material layer temperature drop, the first average value, and the second average value; Correcting the tail wind box exhaust temperature based on the correction coefficient to obtain a tail wind box correction temperature; Determining the information mode based on the comparison result includes: When the comparison result is that the tail windbox correction temperature is less than or equal to the highest windbox exhaust gas temperature of all windboxes at the current moment, determining that the information mode is a non-hysteresis mode; When the comparison result is that the tail windbox correction temperature is greater than the highest windbox exhaust gas temperature of all windboxes at the current moment, determining that the information mode is a hysteresis mode; When the information mode is a non-hysteresis mode, the endpoint information of determining the sintering endpoint based on the information mode includes: Obtaining the current maximum wind box exhaust gas temperature and the position of the wind box thermocouple of the target wind box to which the current maximum wind box exhaust gas temperature belongs as the first parameter; Obtaining the windbox exhaust gas temperature at the previous moment before the current moment of the target windbox and the position of the windbox thermocouple as the second parameter; Obtaining the windbox exhaust gas temperature at the next moment of the target windbox and the position of the windbox thermocouple as the third parameter; Determine endpoint information of a sintering endpoint based on the first parameter, the second parameter, and the third parameter; When the information mode is a hysteresis mode, the endpoint information of determining the sintering endpoint based on the information mode includes: Acquiring historical parameter information during the sintering process, wherein the historical parameter information includes historical endpoint information of the sintering endpoint; Determine the relevance between the historical endpoint information and the remaining historical information in the historical parameter information excluding the historical endpoint information; Retaining the remaining historical information whose relevance satisfies a preset relevance threshold and the historical endpoint information as a training sample set; Establishing an endpoint information prediction model for sintering endpoint based on the training sample set and machine learning; Predicting endpoint information of a sintering endpoint based on the endpoint information prediction model; Furthermore, determining the correction coefficient of the windbox exhaust gas temperature of the tail windbox based on the material layer temperature drop, the first average value and the second average value includes: Calculate a first difference between the second average value and the temperature drop of the material layer; Calculating a ratio of the first difference to the first average value to determine a correction coefficient of the wind box exhaust gas temperature of the tail wind box; The endpoint information of determining the sintering endpoint based on the first parameter, the second parameter and the third parameter includes: Fitting a quadratic curve based on the first parameter, the second parameter and the third parameter; The vertex parameter of the quadratic curve is determined as the endpoint information of the sintering endpoint.

2. The method for obtaining endpoint information of sintering endpoint according to claim 1, characterized in that: Before obtaining the wind box exhaust gas temperature of all wind boxes in the sintering process within the preset time before the current moment, it also includes: Real-time acquisition of time series data during sintering process; identifying outliers in each of the time series data; Determine the missing value at the time when the outlier value is located; The missing values ​​are replaced by the outliers.

3. The method for obtaining endpoint information of sintering endpoint according to claim 2, characterized in that: The identifying of outliers in each of the time series data comprises: Identify outliers in each of the time series data using the 3σ method; The determining of the missing value at the time when the abnormal value is located includes: The missing value at the time when the outlier is located is determined by nearest neighbor filling.

4. A device for obtaining endpoint information of sintering endpoint, characterized in that: include: A data acquisition module, used to obtain the wind box exhaust gas temperature of all wind boxes in the sintering process within a preset time period before the current moment; A maximum temperature determination module, used for comparing the bellows exhaust gas temperatures at the same time among the bellows exhaust gas temperatures, to obtain the maximum bellows exhaust gas temperature at each time; A first screening module, used for screening out, from the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the first preset position is located as the first data set; A second screening module is used to screen out, from the above-mentioned wind box exhaust gas temperatures, the wind box exhaust gas temperatures at the time when the highest wind box exhaust gas temperature of the wind box at the second preset position is located as the second data set; a temperature correction module, configured to correct the exhaust temperature of the tail wind box at the current moment based on the first data set and the second data set to obtain a corrected temperature of the tail wind box; A temperature comparison module, used to compare the tail windbox correction temperature with the highest windbox exhaust gas temperature of all windboxes at the current moment, and obtain a comparison result; a mode determination module, configured to determine an information mode based on the comparison result; An endpoint information determination module, used to determine the endpoint information of the sintering endpoint based on the information pattern; The method of correcting the exhaust gas temperature of the tail wind box at the current moment based on the first data set and the second data set to obtain the corrected temperature of the tail wind box includes: Determine an average temperature difference between an average value of the windbox exhaust gas temperature of the windbox at the first preset position and an average value of the windbox exhaust gas temperature of the windbox at the second preset position in the first data set as a material layer temperature drop; Determine a first average value of the windbox exhaust gas temperature of the tail windbox in the second data set, and a second average value of the windbox exhaust gas temperature of the windbox at the second preset position; Determining a correction coefficient for the wind box exhaust gas temperature of the tail wind box based on the material layer temperature drop, the first average value, and the second average value; Correcting the tail wind box exhaust temperature based on the correction coefficient to obtain a tail wind box correction temperature; Determining the information mode based on the comparison result includes: When the comparison result is that the tail windbox correction temperature is less than or equal to the highest windbox exhaust gas temperature of all windboxes at the current moment, determining that the information mode is a non-hysteresis mode; When the comparison result is that the tail windbox correction temperature is greater than the highest windbox exhaust gas temperature of all windboxes at the current moment, determining that the information mode is a hysteresis mode; When the information mode is a non-hysteresis mode, the endpoint information of determining the sintering endpoint based on the information mode includes: Obtaining the current maximum wind box exhaust gas temperature and the position of the wind box thermocouple of the target wind box to which the current maximum wind box exhaust gas temperature belongs as the first parameter; Obtaining the windbox exhaust gas temperature at the previous moment before the current moment of the target windbox and the position of the windbox thermocouple as the second parameter; Obtaining the windbox exhaust gas temperature at the next moment of the target windbox and the position of the windbox thermocouple as the third parameter; Determine endpoint information of a sintering endpoint based on the first parameter, the second parameter, and the third parameter; When the information mode is a hysteresis mode, the endpoint information of determining the sintering endpoint based on the information mode includes: Acquiring historical parameter information during the sintering process, wherein the historical parameter information includes historical endpoint information of the sintering endpoint; Determine the relevance between the historical endpoint information and the remaining historical information in the historical parameter information excluding the historical endpoint information; Retaining the remaining historical information whose relevance satisfies a preset relevance threshold and the historical endpoint information as a training sample set; Establishing an endpoint information prediction model for sintering endpoint based on the training sample set and machine learning; Predicting endpoint information of a sintering endpoint based on the endpoint information prediction model; Furthermore, determining a correction coefficient of the windbox exhaust gas temperature of the tail windbox based on the material layer temperature drop, the first average value, and the second average value includes: Calculate a first difference between the second average value and the temperature drop of the material layer; Calculating a ratio of the first difference to the first average value to determine a correction coefficient of the wind box exhaust gas temperature of the tail wind box; Determining endpoint information of a sintering endpoint based on the first parameter, the second parameter, and the third parameter includes: Fitting a quadratic curve based on the first parameter, the second parameter and the third parameter; The vertex parameter of the quadratic curve is determined as the endpoint information of the sintering endpoint.

Images