An online calculation method, device and computer-readable storage medium for the slag tapping speed of a blast furnace

Abstract

The present invention relates to an online calculation method, device and computer-readable storage medium for the slag tapping speed of a blast furnace, belonging to the technical field of blast furnace ironmaking, and comprising the following steps: S1: Collect the real-time current data of the blast furnace slag water belt to form the original time series data of the belt current; S2: Collect the actual tapping data of the blast furnace, including the opening time of the taphole, the slag tapping time of the blast furnace, and the plugging time of the taphole; S3: Perform threshold filtering on the blast furnace slag water belt current data; S4: Fill in the missing data in the actual tapping data of the blast furnace and correct the incorrect data; S5: Perform clustering analysis on the slag water belt current data to obtain the motor current gears under different load conditions; S6: Combine the actual tapping performance and the historical data of the slag water belt current over a period of time to establish a slag tapping speed calculation model under different motor gears; S7: Combine the actual tapping performance and the real-time data of the slag water belt current, and online calculate the slag tapping speed based on the slag tapping speed model.

Description

Technical Field

[0001] The present invention belongs to the technical field of blast furnace ironmaking, and relates to an online calculation method, device and computer-readable storage medium for the slag tapping speed of a blast furnace. Background Art

[0002] The energy consumption of blast furnace ironmaking is huge, reaching 30-35% of the total energy consumption of iron and steel enterprises, and it is the energy consumption center and cost center of the metallurgical industry. Energy conservation and cost reduction in the blast furnace ironmaking process are currently the key tasks of iron and steel enterprises. The stable and smooth operation of the blast furnace is the basis for reducing the cost of hot metal, reducing fuel consumption and carbon dioxide emissions. The fluctuation of the molten slag and iron stored in the hearth has an important impact on the furnace condition fluctuation. The blast furnace operator needs to master the accurate situation of the stored molten slag and iron, and take corresponding measures in time to avoid affecting the furnace condition due to slag and iron discharge reasons, so as to achieve the purpose of long-term stable and smooth operation of the blast furnace.

[0003] At present, the total daily slag tapping volume has been obtained through algorithms such as material balance, but there is still a lack of reliable actual slag tapping speed for verification, resulting in the blast furnace operator not knowing the position of the molten slag and iron liquid level in the hearth, and only being able to tap iron regularly, rather than optimizing the iron tapping operation according to the situation of the stored molten slag and iron in the hearth. At present, there are three calculation methods for the blast furnace slag tapping speed: 1) Manual calculation: Manual estimation is carried out based on the experience of the blast furnace operator. The result of this method has large errors and is not timely, and cannot be used to guide the blast furnace iron tapping operation; 2) Belt scale: Weigh the slag conveying belt through a belt scale. This method cannot solve the problems that the belt scale is easily damaged and has low accuracy in a harsh production environment; 3) Rotary drum motor current: Calculate the slag tapping speed based on the current of the water slag rotary drum motor. Since the slag tapping speed and the current of the rotary drum motor are not a simple linear relationship due to the influence of water flow impact on the rotary drum, the result of this method has large errors. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an online calculation method for the slag tapping speed of a blast furnace.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] An online calculation method for the slag tapping speed of a blast furnace, comprising the following steps:

[0007] S1: Collect the real-time current data of the blast furnace water slag belt to form the original time series data of the belt current;

[0008] S2: Collect the actual iron tapping data of the blast furnace, including the iron notch opening time, the blast furnace slag tapping time, and the iron notch plugging time;

[0009] S3: Perform threshold filtering on the blast furnace water slag belt current data;

[0010] S4: Clean the actual tapping data of the blast furnace, fill in the missing data in the actual tapping data of the blast furnace, and correct the error data;

[0011] S5: Conduct cluster analysis on the water slag belt current data to obtain the motor current gears under different load conditions;

[0012] S6: Combine the historical data of the actual tapping and the water slag belt current over a period of time to establish a slag discharging speed calculation model under different motor gears;

[0013] S7: Combine the real-time data of the actual tapping and the water slag belt current, and calculate the slag discharging speed online based on the slag discharging speed model.

[0014] Furthermore, step S1 specifically includes: Set a current transformer on the motor of the blast furnace water slag belt, and convert the current signal into a digital signal through the analog module and A / D conversion module of the PLC and transmit it to the upper computer.

[0015] Furthermore, step S2 specifically includes: When issuing instructions to open the taphole, discharge slag, and plug the taphole in the industrial control computer in the blast furnace control room, obtain the current moment as the time corresponding to the event.

[0016] Furthermore, step S3 specifically includes: Set the upper and lower limit thresholds of the blast furnace water slag belt current in the upper computer, and filter the peak values in the belt current time series data caused by the peak current during motor startup, where the current upper limit threshold I t is the no-load current of the blast furnace water slag belt, and the lower limit threshold I b of the blast furnace water slag belt is the full-load current.

[0017] Furthermore, step S5 specifically includes: For the current time series data after threshold filtering, adopt a clustering analysis method of unsupervised learning based on the Manhattan distance, where the Manhattan distance is defined as shown in the following formula, which is a measure of the similarity between current data:

[0018]

[0019] where x and y each represent a set of current data, there are n current values in each set of current data, i represents the i-th current value, d(x,y) represents the Manhattan distance between point x and y, ||x i -y i || represents the absolute value of the difference between x i and y i ;

[0020] After clustering, the current intensity data shows a characteristic of being distributed according to gears. Thus, the current intensity data is mapped to several gears according to the load of the belt. The current intensity of the smallest gear is the no-load current, which is the current intensity of the belt under no-load conditions and is used to overcome the resistance during the operation of the belt. The current intensity of the largest gear is the full-load current, which is the current intensity of the belt under the maximum load. Take the no-load current as I t , and take the full-load current as I b , which are respectively used as the lower threshold and the upper threshold for current threshold filtering.

[0021] Furthermore, step S6 specifically includes: according to the recorded time of opening the iron notch, slag discharging, and plugging the opening in the actual tapping record of the blast furnace, take the time between slag discharging and plugging the opening as the normal working time of the belt; exclude the slag-grabbing behavior of the traveling crane when calculating the slag discharging speed and add it to the data of the belt working time through a compensation coefficient;

[0022] First, according to the slag discharging time and plugging time of the actual tapping record, take out the historical data of the sluice belt current during the normal working time of the belt in each tapping cycle, and count the working duration of the historical data of the belt current at different motor gears, denoted as T i , where i represents the current gear; set the effective load of the motor at different gears, denoted as W i , and get:

[0023]

[0024] where WS represents the total effective load of the belt within one tapping cycle;

[0025] Collect the actual tapping data of m times and the corresponding data of the current gear duration, and establish an overdetermined equation set as follows:

[0026]

[0027] The least squares solution of the above overdetermined equation set is the effective load of the belt at each gear;

[0028] Count the total slag volume Wt and the slag volume Wo entering the slag pool within a certain period, and get the compensation coefficient k = Wt / (Wt - Wo).

[0029] Furthermore, step S7 specifically includes: collecting the real-time data of the actual tapping record and the sluice belt current, determining the working gear i of the belt according to the current intensity, and obtaining the effective load Wi at this gear from the model established in step S6. Then the slag discharging speed at the current moment is Wr = Wi * k.

[0030] On the other hand, the present invention provides an on-line calculation device for the slag tapping speed of a blast furnace, comprising a memory and a processor; the memory is used for storing a computer program; the processor is used for implementing the on-line calculation method for the slag tapping speed of a blast furnace as described in any one of the above when executing the computer program.

[0031] In still another aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the on-line calculation method for the slag tapping speed of a blast furnace as described in any one of the above is implemented.

[0032] The beneficial effects of the present invention are as follows: Aiming at the problem that blast furnace operators lack reliable actual slag tapping speed data and cannot timely understand the amount of slag in the hearth, through a calculation model that combines the actual tapping performance and the water slag belt current data, the slag tapping speed is calculated on-line and then the amount of slag in the hearth is calculated, which changes the current situation that blast furnace operators can only tap iron regularly based on experience and transforms it into dynamically optimizing the iron tapping operation according to the slag and iron storage situation in the hearth.

[0033] Other advantages, objectives and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in detail preferably with reference to the accompanying drawings, wherein:

[0035] Figure 1 is a flow chart of the on-line calculation method for the slag tapping speed of the blast furnace described in the present invention;

[0036] Figure 2 is a schematic diagram of threshold filtering of the water slag belt current of the blast furnace described in the present invention;

[0037] Figure 3 is a schematic diagram of clustering of the water slag belt current of the blast furnace described in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The following specific examples illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the drawings provided in the following embodiments only schematically illustrate the basic concept of the present invention. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0039] Among them, the drawings are only for illustrative purposes, showing only schematic diagrams rather than physical diagrams, and should not be construed as a limitation to the present invention; in order to better illustrate the embodiments of the present invention, some components in the drawings will be omitted, enlarged or reduced, which do not represent the dimensions of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0040] In the drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only for illustrative purposes and should not be construed as a limitation to the present invention. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0041] Please refer to Figures 1 to 3 , which provides an online calculation method for the slag tapping speed of a blast furnace, including the following steps:

[0042] S1: Collect the real-time data of the blast furnace slag belt current. The real-time data of the current is collected through a periodic collection device on the blast furnace slag belt motor to form the original time series data of the belt current; specifically, a current transformer is set on the blast furnace slag belt motor, and through the analog module and A / D (analog / digital) module of the PLC, the current signal is converted into a digital signal and transmitted to the upper computer.

[0043] S2: Collect the actual iron tapping data of the blast furnace, including the iron notch opening time, the blast furnace slag tapping time, and the iron notch plugging time; specifically: a human-computer interaction interface program is set in the industrial control computer in the blast furnace central control room, and the blast furnace operator triggers the corresponding buttons at the moments of opening the iron notch, tapping slag, and plugging the iron notch, and the computer program automatically records the triggered event types and times.

[0044] S3: Perform threshold filtering on the water slag belt current data to filter out the peaks in the belt current time series data caused by the peak current during motor startup. Since there is a peak current during motor startup, there are peaks in the belt current time series data collected in step S1 that deviate from the normal range. Therefore, set the upper and lower current threshold values in the computer program and perform threshold filtering on them, as shown in the appendix. Figure 2 shown. Among them, the upper current threshold value I t and the lower threshold value I b are obtained by statistical calculation in step S5.

[0045] S4: Since the actual blast furnace tapping data is collected in a combination of manual triggering and program recording, there are a small number of data errors or omissions. Therefore, during the data preprocessing stage, fill in the missing data in the actual blast furnace tapping data and correct the incorrect data.

[0046] S5: Perform clustering analysis on the water slag belt current data to obtain the motor current gears under different load conditions. The water slag belt corresponds to different motor operating gears under different loads, and each operating gear corresponds to a current intensity. However, there are certain errors in the current intensity due to the accuracy of the acquisition equipment. Therefore, perform clustering analysis on the water slag belt current data to obtain the motor current gears under different load conditions.

[0047] For the current time series data after threshold filtering, use the clustering analysis method of unsupervised learning based on the Manhattan distance. The Manhattan distance is defined as shown in the following formula and is a measure of the similarity between current data.

[0048]

[0049] The current intensity data after clustering shows the characteristic of being distributed according to gears, as shown in the appendix. Figure 3 shown. Thus, map the current intensity data to several gears according to the load size of the belt. Among them, the current intensity of the smallest gear is the no-load current, which is the current intensity of the belt under no-load conditions and is used to overcome the friction and other resistances during the operation of the belt; the current intensity of the largest gear is the full-load current, which is the current intensity of the belt under the maximum load. Take the no-load current as I t and the full-load current as I b and use them as the lower and upper threshold values for current threshold filtering respectively.

[0050] S6: Combine the historical data of the actual tapping performance and the sluice belt current over a period of time to establish a calculation model for the slag discharging speed at different motor gears. Since after the blast furnace slag passes through the revolving drum, part of it is directly conveyed by the granulated slag belt, and part enters the slag pond. The granulated slag that enters the slag pond is grabbed by the slag crane onto the belt when there is no tapping in the blast furnace. According to the recorded time of opening the taphole, discharging slag, and stopping the taphole in the actual tapping performance of the blast furnace, the time between slag discharging and stopping the taphole is used as the normal working time of the belt. The slag-grabbing behavior of the crane has the characteristics of uncertainty in time and quantity. When calculating the slag discharging speed, this part of the data needs to be excluded and added to the data of the belt working time through a compensation coefficient.

[0051] First, according to the slag discharging time and the stopping taphole time of the actual tapping performance, extract the historical data of the sluice belt current during the normal working time of the belt in each tapping cycle, and count the working duration of the historical data of the belt current at different motor gears, denoted as T i , where i represents the current gear. Set the effective load of the motor at different gears, denoted as W i , and we can get:

[0052]

[0053] where WS represents the total effective load of the belt during one tapping cycle.

[0054] Collect the actual tapping performance data of m times and the corresponding current gear duration data, and establish the following overdetermined equations:

[0055]

[0056] The least-squares solution of the above overdetermined equations is the effective load of the belt at each gear.

[0057] Statistical total slag volume Wt and the slag volume Wo entering the slag pond over a period of time, the compensation coefficient k = Wt / (Wt - Wo) can be obtained.

[0058] S7: Collect the real-time data of the actual tapping performance and the sluice belt current, determine the working gear i of the belt according to the current intensity, and obtain the effective load Wi at this gear from the above model. Then the slag discharging speed at the current moment is Wr = Wi * k.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the purpose and scope of the present technical solution, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An on-line calculation method for the slag tapping speed of a blast furnace, characterized in that: It includes the following steps: S1: Collect the real-time current data of the blast furnace slag belt to form the original time-series data of the belt current; S2: Collect the actual tapping data of the blast furnace, including the iron notch opening time, the blast furnace slag tapping time, and the iron notch plugging time; S3: Perform threshold filtering on the blast furnace slag belt current data; S4: Clean the actual tapping data of the blast furnace, fill in the missing data in the actual tapping data of the blast furnace, and correct the error data; S5: Perform clustering analysis on the slag belt current data to obtain the motor current gears under different load conditions; S6: Combine the actual tapping performance and the historical data of the slag belt current over a period of time to establish a slag tapping speed calculation model under different motor gears; S7: Combine the actual tapping performance and the real-time data of the slag belt current, and online calculate the slag tapping speed based on the slag tapping speed model; Specifically included in step S5: For the current time-series data after threshold filtering, adopt an unsupervised learning clustering analysis method based on the Manhattan distance, where the Manhattan distance is defined as shown in the following formula, which is a measure of the similarity between current data: Among them, x and y each represent a set of current data, and there are n current values in each set of current data. i represents the i-th current value, d(x, y) represents the Manhattan distance between points x and y, and ||x i -y i || represents the absolute value of the difference between x i and y i ; After clustering, the current intensity data presents the characteristic of being distributed according to gears. Therefore, the current intensity data is mapped to several gears according to the load size of the belt. Among them, the current intensity of the smallest gear is the no-load current, which is the current intensity of the belt under no-load conditions and is used to overcome the resistance during the operation of the belt. The current intensity of the largest gear is the full-load current, which is the current intensity of the belt under the maximum load. Take the no-load current as I t , and take the full-load current as I b , which are respectively used as the lower threshold and the upper threshold for current threshold filtering; Specifically included in step S6: According to the recorded iron notch opening, slag tapping, and plugging times in the actual tapping performance of the blast furnace, take the time between slag tapping and plugging as the normal working time of the belt; When calculating the slag tapping speed, exclude the slag grabbing behavior of the traveling crane and add it to the data of the belt working time through a compensation coefficient; First, according to the slag tapping time and taphole stopping time of the actual tapping performance, the historical data of the sluice belt current during the normal working time of the belt in each tapping cycle is taken, and the working duration of the belt current historical data at different motor gears is counted, denoted as T i , where i represents the current gear; the effective load of the motor at different gears is set, denoted as W i , and we get: Where WS represents the total effective load of the belt within one tapping cycle; Collect m times of actual tapping data and the corresponding current gear duration data, and establish an overdetermined equation set as follows: The least squares solution of the above overdetermined equation set is the effective load of the belt under each gear; Statistical total slag volume Wt and slag volume Wo entering the slag pool over a period of time, and obtain the compensation coefficient k = Wt / (Wt - Wo); Specifically included in step S7: Collect the real-time data of the actual tapping performance and the sluice belt current, determine the working gear i of the belt according to the current intensity, and obtain the effective load Wi under this gear from the model established in step S6, then the slag tapping speed at the current moment is Wr = Wi * k.

2. The on-line calculation method of the blast furnace slag tapping speed according to claim 1, characterized in that: Specifically included in step S1: Set a current transformer on the blast furnace slag belt motor, and through the analog module and A / D conversion module of the PLC, convert the current signal into a digital signal and transmit it to the upper computer.

3. The online calculation method of the slag tapping speed of a blast furnace according to claim 1, characterized in that: Specifically included in step S2: When issuing instructions to open the iron notch, tap slag, and plug the iron notch in the industrial control computer in the blast furnace central control room, obtain the current moment as the time of the corresponding event.

4. The online calculation method of the slag tapping speed of the blast furnace according to claim 1, characterized in that: Specifically included in step S3 are: setting the upper and lower limit thresholds of the blast furnace slag belt current in the host computer, and filtering the peak values in the belt current time series data caused by the peak current during motor startup, where the upper current limit threshold I t is the no-load current of the blast furnace slag belt, and the lower limit threshold I of the blast furnace slag belt b is the full-load current.

5. An on-line calculation device for the slag tapping speed of a blast furnace, characterized in that, It includes a memory and a processor; The memory is used to store computer programs; The processor is used to, when executing the computer program, implement the online calculation method of the blast furnace slag tapping speed as described in any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by the processor, the online calculation method of the blast furnace slag tapping speed as described in any one of claims 1-4 is implemented.

Images