A real-time measurement method for the blast furnace slag discharge

Abstract

The present invention relates to a method for real-time determination of the blast furnace slag discharge amount, belonging to the technical field of blast furnace ironmaking, and comprising the following steps: S1: Establish a fuzzy inference model for the blast furnace slag discharge amount; the actual slag discharge amount = K * (actual motor current - no-load motor current) + A, where K is a conversion coefficient; A is a correction constant; S2: Determine the conversion coefficient K of the fuzzy inference model; S3: Correct the constant A of the fuzzy inference model through machine learning. This method aims at the problem of the lack of accurate and effective slag discharge amount detection technology in blast furnace ironmaking, and has strong pertinence. The actual slag discharge amount is calculated through the optimized algorithm of the water slag conveyor belt current, and then the iron storage amount, slag storage amount and their distribution in the hearth are obtained to guide the iron tapping operation and reduce the consumption of drill pipes and mud plugs.

Description

Technical Field

[0001] The present invention belongs to the technical field of blast furnace ironmaking, and relates to a method for real-time measurement of the blast furnace slag discharge amount. Background Art

[0002] At present, there is no technology that can accurately and effectively detect the actual slag discharge amount, and there is a lack of an accurate measurement method for the slag storage amount in the furnace. During the process of blast furnace slag and iron discharge management, it is difficult to ensure the real-time grasp of the positions of the molten iron surface and the slag surface, which affects the feeding speed and the stability of the original coal gas flow in the hearth, and further affects the long-term stable operation of the blast furnace. During the blast furnace ironmaking process, if the real-time distribution of the slag discharge amount and the slag-iron composition in the furnace can be grasped in a timely and accurate manner, the operation management of blast furnace slag and iron discharge can be effectively optimized, which helps the safe production of the blast furnace and increases production and reduces consumption. At present, there are usually three methods for calculating the blast furnace slag discharge amount: 1) Estimation by an experienced blast furnace foreman. This manual estimation method has large errors and poor real-time performance, which is not conducive to the refined and standardized management of blast furnace production; 2) A belt scale is set on the water slag conveyor belt. This method has the following problems: The belt scale has high requirements for the working environment. The production site environment is harsh, the weighing equipment is easily damaged, and the maintenance cost is high; 3) Calculating the slag amount based on the current of the water slag drum motor. Since there is no linear relationship between the slag amount and the current of the drum motor, this method cannot effectively detect the blast furnace slag discharge amount under the condition of drastic changes in working conditions. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method for real-time measurement of the blast furnace slag discharge amount.

[0004] To achieve the above purpose, the present invention provides the following technical solutions:

[0005] A method for real-time measurement of the blast furnace slag discharge amount includes the following steps:

[0006] S1: Establish a fuzzy inference model for the blast furnace slag discharge amount;

[0007] Actual slag discharge amount = K * (actual motor current - no-load motor current) + A

[0008] Where K is a conversion coefficient; A is a correction constant;

[0009] S2: Determine the conversion coefficient K of the fuzzy inference model;

[0010] S3: Correct the constant A of the fuzzy inference model through machine learning.

[0011] Further, step S2 specifically includes:

[0012] According to the motor voltage, motor current, motor usage factor, and motor power factor, calculate the relationship between the current and the motor power by using the motor power formula:

[0013]

[0014] Where P is the three-phase motor power; U is the rated voltage of the motor; I is the actual current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate.

[0015] According to the formula of motor power and belt tension:

[0016] P=FV

[0017] Where P is the three-phase motor power; F is the belt tension; V is the belt running speed.

[0018] Combined with the relationship between belt tension and belt load:

[0019] F=u*m*g*cosα

[0020] Where F is the belt tension; u is the belt friction coefficient; m is the belt load mass; g is the gravity constant 9.8; cosα is the belt inclination angle.

[0021] Combining the above two equations, we can calculate the relationship between belt load, friction coefficient and motor power:

[0022] P=u*m*g*cosα*V

[0023] Calculate the belt conveyor power through the relationship between horizontal load power, inclined load power and no-load power:

[0024] P a =P h +P v +P e

[0025] Where P a P is the belt transmission power; h is the belt horizontal load power; P v P is the belt tilt load power; e is the belt no-load power;

[0026] The belt horizontal load power and the inclined load power are the total mechanical decomposition of the belt according to the belt inclination angle. After combining, we can get:

[0027] P h +P v =u*m*g*cosα*V

[0028] Where u is the belt friction coefficient; m is the belt load mass; g is the gravity constant 9.8; cosα is the belt inclination angle; V is the belt running speed.

[0029] P e is the motor power consumption when the belt runs without load. According to the motor power consumption formula, it can be obtained that:

[0030]

[0031] where P e is the no-load power of the belt; U is the rated voltage of the motor; I e is the no-load current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate.

[0032] Calculate the relationship f(I) between the current and the belt conveying capacity:

[0033]

[0034] After transformation, it can be obtained that:

[0035]

[0036] where m is the belt load mass, that is, the actual slag discharge amount; U is the rated voltage of the motor; I is the actual current of the motor; I e is the no-load current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate; u is the belt friction coefficient; m is the belt load mass; g is the gravitational constant 9.8; cosα is the belt inclination angle, and V is the belt running speed.

[0037] Simplify the above formula to obtain:

[0038] Actual slag discharge amount = K * (Actual motor current - No-load motor current) + A

[0039] where K is the conversion coefficient, A is the correction constant, which is the correction of the algorithm parameters according to the deviation between the theoretical slag production amount and the actual slag discharge amount per tapping, so as to obtain a more accurate actual slag discharge amount.

[0040] Calculate the relationship f(I) between the current and the belt conveying capacity:

[0041] f(I) = K * (I i - I e ) + A

[0042] where K is the conversion coefficient; I i is the actual current of the motor collected at the i-th second; I e is the no-load current of the motor; A is the correction constant.

[0043] Furthermore, collect the motor current I i per second, and calculate the total conveying amount M within the time period n:

[0044]

[0045] Obtain the total belt conveying volume M within the time period n, which is the actual slag discharge amount within this time period.

[0046] Further, specifically included in step S3 are:

[0047] Calculate the corresponding relationship through the relevant parameters of the water slag transportation belt motor, the speed reducer, and the relevant parameters of the belt, and correct the parameters through machine learning.

[0048] Calculate the theoretical slag production amount per minute according to the CaO balance method, and calculate the actual slag discharge amount per minute through an optimization algorithm based on the change of the current of the water slag transportation belt, so as to calculate the slag storage amount per minute.

[0049] Theoretical slag production amount per minute = ∑(CaO component × ore weight) ÷ (CaO) content in the slag ÷ number of minutes of batch interval

[0050] Learn the historical data calculated by the CaO balance method through machine learning, and correct the correction parameter A; during the smooth operation of the blast furnace, since the deviation between the theoretical slag production amount and the actual slag discharge amount is small within a relatively long period, and the deviation decreases as the cycle length increases, the balance relationship between the theoretical slag production amount and the actual slag discharge amount can be used as the basis for correcting the constant A. Since the blast furnace smelting cycle is generally about 6 hours, 10 days can cover 40 smelting cycles. The model statistically calculates the theoretical slag production amount and the actual slag discharge amount in a 10-day cycle in a rolling cumulative manner, and collects data for more than one month. Establish a regression model by the least square method, solve the positive definite matrix, and obtain a more accurate value of A. Feed back the parameters corrected by machine learning to the calculation model to gradually improve the accuracy of the calculation model.

[0051] The beneficial effects of the present invention are as follows: This method aims at the problem of the lack of accurate and effective slag discharge amount detection technology in blast furnace ironmaking, and has strong pertinence. Calculate the actual slag discharge amount through the optimization algorithm of the water slag transportation belt current, and then obtain the iron storage amount, slag storage amount and their distribution in the hearth, guide the iron tapping operation, and reduce the consumption of drill pipes and mud plugs.

[0052] 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 achieved and obtained through the following specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in detail with reference to the accompanying drawings as follows:

[0054] Figure 1 It is a schematic flow chart of a method for real-time measurement of the blast furnace slag discharge amount described in the present invention. Specific embodiments

[0055] The following uses specific specific examples to illustrate the embodiments 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 embodiments. 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 illustrate the basic concept of the present invention in a schematic manner. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0056] Among them, the drawings are only for illustrative purposes, showing only schematic diagrams, not physical diagrams, and should not be construed as a limitation on 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, and do not represent the dimensions of actual products; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0057] 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, and are 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 on 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.

[0058] Please refer to Figure 1 , the present invention provides a method for real-time measurement of the blast furnace slag discharge amount, including the following steps:

[0059] 1) Establish a fuzzy inference model for the blast furnace slag discharge amount:

[0060] Actual slag discharge amount = K * (actual motor current - no-load motor current) + A

[0061] Where K is the conversion coefficient; A is the correction constant.

[0062] The algorithm parameters are corrected according to the deviation between the theoretical slag amount and the actual slag amount for each tapping, so as to obtain a more accurate actual slag amount.

[0063] 2) Determine the conversion factor K:

[0064] According to the motor voltage, motor current, motor utilization factor, and motor power factor, the relationship between current and motor power is calculated using the motor power formula:

[0065]

[0066] Where P is the three-phase motor power; U is the rated voltage of the motor; I is the actual current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate.

[0067] According to the formula of motor power and belt tension:

[0068] P=FV

[0069] Where P is the three-phase motor power; F is the belt tension; V is the belt running speed.

[0070] Combined with the relationship between belt tension and belt load:

[0071] F=u*m*g*cosα

[0072] Where F is the belt tension; u is the belt friction coefficient; m is the belt load mass; g is the gravity constant 9.8; cosα is the belt inclination angle.

[0073] Combining the above two equations, we can calculate the relationship between belt load, friction coefficient and motor power:

[0074] P=u*m*g*cosα*V

[0075] Calculate the belt conveyor power through the relationship between horizontal load power, inclined load power and no-load power:

[0076] P a =P h +P v +P e

[0077] Where P a P is the belt transmission power; h is the belt horizontal load power; P v P is the belt tilt load power; e is the belt no-load power;

[0078] The belt horizontal load power and the inclined load power are the total mechanical decomposition of the belt according to the belt inclination angle. After combining, we can get:

[0079] P h +P v = u * m * g * cosα * V

[0080] Where u is the belt friction coefficient; m is the belt load mass; g is the gravitational constant 9.8; cosα is the belt inclination angle; V is the belt running speed.

[0081] P e is the motor work power when the belt runs without load. According to the motor work formula, it can be obtained that:

[0082]

[0083] Where P e is the no-load power of the belt; U is the rated voltage of the motor; I e is the no-load current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate.

[0084] Calculate the relationship f(I) between the current and the belt conveying capacity:

[0085]

[0086] After transformation, it can be obtained that:

[0087]

[0088] Where m is the belt load mass, that is, the actual slag discharge amount; U is the rated voltage of the motor; I is the actual current of the motor; I e is the no-load current of the motor; is the power factor, see the motor nameplate; e is the motor efficiency, see the motor nameplate; u is the belt friction coefficient; m is the belt load mass; g is the gravitational constant 9.8; cosα is the belt inclination angle, V is the belt running speed.

[0089] Simplify the above formula to obtain:

[0090] Actual slag discharge amount = K * (Actual motor current - No-load motor current) + A

[0091] Where K is the conversion coefficient, A is the correction constant, which is the correction of the algorithm parameters according to the deviation between the theoretical slag production amount and the actual slag discharge amount for each tapping, so as to obtain a more accurate actual slag discharge amount.

[0092] Calculate the relationship f(I) between the current and the belt conveying capacity:

[0093] f(I) = K * (I i - I e ) + A

[0094] where K is the conversion coefficient; I i is the actual current of the motor collected at the i-th second; I e is the no-load current of the motor; A is the correction constant.

[0095] Collect the motor current I every second i , and calculate the total conveying volume M within the time period n:

[0096]

[0097] Obtain the total conveying volume M of the belt within the time period n, which is the actual slag discharge amount within this time period.

[0098] 3) Correct the constant A through machine learning:

[0099] Calculate the corresponding relationship through the relevant parameters of the water slag transportation belt motor, the speed reducer, and the belt parameters, and correct the parameters through machine learning;

[0100] Calculate the theoretical slag production amount per minute according to the CaO balance method, calculate the actual slag discharge amount per minute through the optimization algorithm according to the change of the water slag transportation belt current, so as to calculate the slag storage amount per minute;

[0101] Theoretical slag production amount per minute = ∑(CaO component × ore weight) ÷ (CaO) content in the slag ÷ batch interval minutes

[0102] Through machine learning, learn the historical data calculated by the CaO balance method and correct the correction parameter A; during the smooth operation of the blast furnace, since the deviation between the theoretical slag production amount and the actual slag discharge amount is small within a long period, and the deviation decreases as the cycle length increases, the balance relationship between the theoretical slag production amount and the actual slag discharge amount can be used as the basis for correcting the constant A. Since the blast furnace smelting cycle is generally about 6 hours, 10 days can cover 40 smelting cycles. The model statistically calculates the theoretical slag production amount and the actual slag discharge amount in a 10-day cycle in a rolling cumulative manner, and collects data for more than one month. Establish a regression model by the least squares method, solve the positive definite matrix, and obtain a more accurate value of A. Apply the parameters corrected by machine learning to the calculation model to gradually improve the accuracy of the calculation model.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit. 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 within the scope of the claims of the present invention.

Claims

1. A real-time measurement method for the discharge amount of blast furnace slag, characterized in that: It includes the following steps: S1: Establish a fuzzy inference model for the blast furnace slag discharge amount; Actual slag discharge amount = K * (actual motor current - no-load motor current) + A where K is the conversion coefficient, U is the rated voltage of the motor, is the power factor, e is the motor efficiency, u is the belt friction coefficient, g is the gravitational constant, cosα is the belt inclination angle, V is the belt running speed; A is the correction constant; S2: Determine the conversion coefficient K of the fuzzy inference model; S3: Modify the constant A of the fuzzy inference model through machine learning. Specifically included in step S3: Calculate the corresponding relationship through the relevant parameters of the water slag conveyor belt motor, reducer, and belt, and modify the parameters through machine learning; Calculate the theoretical slag production amount per minute according to the CaO balance method, calculate the actual slag discharge amount per minute through the optimization algorithm according to the change of the water slag conveyor belt current, and thus calculate the slag storage amount per minute; Theoretical slag production amount per minute = ∑(CaO component × ore weight) ÷ CaO content in slag ÷ batch interval minutes The machine learning model learns the historical data calculated by the CaO balance method, modifies the corrected parameter A, uses the balance relationship between the theoretical slag production amount and the actual slag discharge amount as the basis for correcting the constant A. The machine learning model statistically accumulates the theoretical slag production amount and the actual slag discharge amount in a certain period in a rolling manner, establishes a regression model by the least squares method, solves the positive definite matrix, and obtains the value of A; Feed back the parameter A corrected by machine learning to the calculation model to gradually improve the accuracy of the calculation model.

2. The real-time measurement method of blast furnace slag discharge amount according to claim 1, characterized in that: Specifically included in step S2: According to the motor voltage, motor current, motor power factor, and motor efficiency, use the motor power formula to calculate the relationship between current and motor power: Where P is the power of the three-phase motor; U is the rated voltage of the motor; I is the actual current of the motor; is the power factor; e is the efficiency of the motor; According to the formula of motor power and belt tension: P = FV where P is the three-phase motor power; F is the belt tension; V is the belt running speed; Combine the relationship between belt tension and belt load: F = u * m * g * cosα where F is the belt tension; u is the belt friction coefficient; m is the belt load mass, that is, the actual slag discharge amount; g is the gravity constant; cosα is the belt inclination angle; Calculate the relationship between belt load, friction coefficient and motor power: P = u * m * g * cosα * V Calculate the belt conveying power through the relationship between horizontal load power, inclined load power, and no-load power: P a = P h + P v + P e Among which, P a is the belt conveying power; P h is the belt horizontal load power; P v is the belt inclined load power; P e is the motor work power when the belt runs without load; The horizontal load power and inclined load power of the belt are the mechanical decomposition of the total belt according to the belt inclination angle. After combination, it can be obtained: P h +P v = u * m * g * cosα * V According to the motor work formula, P is obtained e : where I e is the no-load current of the motor; Calculate the relationship f(I) between current and belt conveying capacity: After transformation, it can be obtained: Simplify the above formula to obtain: Actual slag discharge amount = K * (actual motor current - no-load motor current) + A where K is the conversion coefficient, A is the correction constant, which corrects the algorithm parameters according to the deviation between the theoretical slag production and the actual slag production per tapping.

3. The real-time measurement method of blast furnace slag discharge amount according to claim 2, characterized in that: Collect the motor current I per second i , and calculate the total conveying volume M within the time period n: where f(I i ) is the calculation formula for the belt conveying volume in the i-th second, that is: m = f(I i ) = K * (I i - I e ) + A where K is the conversion coefficient; I i is the actual current of the motor collected at the i-th second; I e is the no-load current of the motor; A is the correction constant; Obtain the total belt conveying amount M within the time period n, which is the actual slag discharge amount within this time period.

Images