Blast furnace coal injection quantity intelligent control method based on fuzzy self-adaption and genetic algorithm optimization

Abstract

The invention discloses a blast furnace coal injection quantity intelligent control method based on fuzzy self-adaption and genetic algorithm optimization. Comprising the following steps: S1, initializing a fuzzy adaptive control system, and setting an initial coal injection quantity set value; s2, monitoring the real-time working condition of the blast furnace through a sensor, and transmitting data to a control system; s3, inputting the acquired data into a fuzzy control system, and preliminarily adjusting the coal injection quantity according to a set value; s4, performing dynamic optimization on the fuzzy control parameters through a genetic algorithm optimization module; and S5, the coal injection execution module adjusts the coal injection rate in real time according to the optimization result, and closed-loop control is achieved. The intelligent control system for the coal injection amount of the blast furnace is constructed through related technologies such as machine learning and fuzzy control, self-adaptive intelligent control over the coal injection amount of the blast furnace is achieved, intelligent and green production of the blast furnace process is further achieved, and enterprise cost and energy consumption are reduced.

Description

Technical Field

[0001] The present invention relates to an intelligent control method for the coal injection amount in a blast furnace optimized based on fuzzy self - adaptation and genetic algorithm. Background Technique

[0002] In the process of coal injection in a blast furnace, the technology of injecting pulverized coal has become one of the important auxiliary means in blast furnace ironmaking. By injecting pulverized coal into the blast furnace tuyere to replace part of the coke, energy conservation, consumption reduction and emission reduction can be achieved. However, the coal injection process involves complex heat transfer and chemical reactions, belonging to a typical multi - variable coupling "black box" control system, and the process control is difficult. Traditional coal injection control relies on manual operation and fixed parameter adjustment, with problems such as slow response speed, low control accuracy and poor adaptability, and it is difficult to meet the dynamic requirements of variable working conditions in blast furnace ironmaking. In order to improve the stability of the coal injection process, reduce the coke ratio and enhance the production efficiency, it is necessary to realize the intelligent control of the coal injection amount and key process parameters.

[0003] In recent years, intelligent control technology has made remarkable progress in the field of industrial automation. Especially the introduction of technologies such as fuzzy control and genetic algorithm has provided new solutions for the intelligent control of coal injection in blast furnaces. Fuzzy control can effectively control the process without relying on an accurate mathematical model by fuzzifying complex process parameters, and is suitable for non - linear and uncertain systems in coal injection in blast furnaces. As a global optimization algorithm, the genetic algorithm optimizes the parameters of the fuzzy control system by simulating the biological evolution process, making the control of the coal injection amount more accurate and with a faster response. Through the intelligent control method of coal injection in a blast furnace combining fuzzy control and genetic algorithm, the stability, response speed and control accuracy of the coal injection process can be greatly improved, and the adaptive adjustment to complex and variable working conditions can be realized. The innovative application of this intelligent control technology not only helps to optimize the coal injection process in the blast furnace, improve the output and economic benefits of the blast furnace, but also conforms to the trend of low - carbon environmental protection and meets the green transformation needs of the iron and steel industry. Summary of the Invention

[0004] Aiming at the defects and deficiencies existing in the prior art, the purpose of the present invention is to provide an intelligent control method for the coal injection amount in a blast furnace optimized based on fuzzy self - adaptation and genetic algorithm.

[0005] To achieve the above - mentioned purpose, the intelligent control method for the coal injection amount in a blast furnace optimized based on fuzzy self - adaptation and genetic algorithm of the present invention includes the following steps:

[0006] S1: Initialize the fuzzy self - adaptation control system and set the initial coal injection amount set value;

[0007] S2: Monitor the real - time working conditions of the blast furnace through sensors and transmit the data to the control system;

[0008] S3: Input the collected data into the fuzzy control system and make a preliminary adjustment of the coal injection amount according to the set value;

[0009] S4: Dynamically optimize the fuzzy control parameters through the genetic algorithm optimization module;

[0010] S5: The coal injection execution module adjusts the coal injection rate in real time according to the optimization result to achieve closed-loop control.

[0011] Further, the specific step S1 is as follows:

[0012] S11: Set the target coal injection amount and control requirements for blast furnace production. According to these requirements, initialize the fuzzy rule base of the fuzzy adaptive control system and preset the initial value of the coal injection amount;

[0013] S12: Select key working condition parameters as control variables, set fuzzy control rules for each variable, divide the control range, and set the fuzzy membership function.

[0014] Further, the specific step S2 is as follows:

[0015] S21: The data acquisition module includes a variety of sensors, which are installed at the blast furnace tuyere, injection pipeline, temperature and pressure monitoring points, and are used to monitor the working condition parameters in the blast furnace in real time;

[0016] S22: After starting the acquisition module, the system collects the data recorded per second or per minute to the control system, including: blast furnace tuyere temperature, gas content, furnace pressure, coal powder supply rate data;

[0017] S23: The data acquisition module transmits the real-time data to the input end of the fuzzy adaptive control system through the Internet of Things or the factory local area network to ensure the real-time and accuracy of the data.

[0018] Further, the specific step S3 is as follows:

[0019] S31: Input the real-time data obtained by the data acquisition module into the fuzzy adaptive control system and compare it with the target coal injection amount set value;

[0020] S32: The fuzzy control system makes inferences based on the set fuzzy rule base and automatically judges whether the current coal injection amount needs to be adjusted; if the current coal injection amount deviates from the target, the fuzzy system generates an adjustment strategy according to the magnitude and direction of the deviation;

[0021] S33: The adjustment strategy is generated by fuzzy logic reasoning; if the deviation is large, the system will increase the adjustment amplitude of the coal injection amount; if the deviation is small, the adjustment amplitude will also be reduced accordingly to achieve refined control of the coal injection amount;

[0022] Further, the specific step S4 is as follows:

[0023] S41: The genetic algorithm optimization module performs real-time optimization on the parameters of the fuzzy control system to improve the response speed and accuracy of the control system under different working conditions;

[0024] S42: Through continuous iteration of the genetic algorithm, the overall fitness of the population is improved until the control accuracy requirement is met;

[0025] S43: After the optimal fuzzy parameter combination is generated, it is updated to the fuzzy control system to improve the real-time responsiveness of the coal injection volume adjustment.

[0026] Furthermore, the specific steps of step S5 are as follows:

[0027] S51: The coal injection execution module receives the adjustment instruction of the fuzzy adaptive control system and adjusts the pulverized coal injection volume in real time;

[0028] S52: The execution module acts on the coal injection system by adjusting the injection speed, adjusting the air volume, and the pulverized coal concentration parameters to ensure the precise control of the coal injection volume and the coal injection rate;

[0029] S53: After the execution module completes the adjustment, the result is fed back to the control system to achieve closed-loop control and verify the adjustment effect. If the deviation continues to exist, the fuzzy control system will recalculate a new adjustment strategy and execute it in a loop until the coal injection volume reaches the set stable range.

[0030] Furthermore, the specific establishment method of the fuzzy rule base is as follows: First, establish the input and output variables of the fuzzy control. The input variables are the working condition parameters of the blast furnace, including the tuyere temperature, pressure, oxygen content, gas content, coal injection rate, etc., and the output variable is the adjusted value of the coal injection volume. Then divide the fuzzy levels of the variables. For example, the tuyere temperature can be divided into "low", "moderate", and "high", and the adjusted value of the coal injection volume can be set to "decrease", "maintain", "increase". Then define the fuzzy rules. For example: If the tuyere temperature is "high" and the pressure is "normal", then the coal injection volume is adjusted to "decrease slightly"; if the tuyere temperature is "moderate" and the oxygen content is "high", then the coal injection volume is adjusted to "maintain", etc. Finally, determine the fuzzy inference mechanism and use fuzzy inference methods such as "max-min method" or "weighted average method" to map multiple input fuzzy quantities to the output adjusted value of the coal injection.

[0031] Furthermore, the fuzzy membership function is a mathematical tool in the fuzzy control system to describe the degree of fuzzy variables, which is used to convert the specific numerical values of the input and output variables into fuzzy values in the fuzzy set (such as "high", "low"). For example, for the tuyere temperature variable, a triangular membership function can be used for description:

[0032]

[0033] Among them, a and c are the starting and ending points of the function, b is the vertex. The triangular membership function has a peak at a certain central value, decreasing to zero on both the left and right, presenting a symmetric triangular shape.

[0034] Furthermore, the data acquisition module mainly uses sensors for various working conditions, specifically including temperature sensors, pressure sensors, flow sensors, gas composition detectors, level sensors, etc. The temperature sensor is mainly used to measure the real-time temperature of the tuyere and the combustion furnace, the pressure sensor is used to measure the tuyere pressure and the coal injection pipeline pressure, the flow sensor is used to measure the gas flow, the pulverized coal flow, etc., the gas composition detector mainly detects the oxygen content during the combustion process, and the level sensor is used to detect the stock of pulverized coal in the coal injection tank. The data of these sensors will be transmitted to the control system in real time.

[0035] Furthermore, the optimization of the genetic algorithm is to optimize the parameters of the fuzzy control system in real time, improving the response speed and accuracy of the control system under different working conditions. The specific steps are as follows:

[0036] 1) Initialize the population: Set the initial population for each fuzzy parameter of the control system.

[0037] 2) Fitness evaluation: Calculate the fitness of the current parameter combination according to the actual working condition performance of the coal injection system. The higher the fitness, the closer the current combination is to the target value.

[0038] 3) Selection, crossover, and mutation: Select individuals with higher fitness from the population for crossover and mutation operations to generate new parameter combinations.

[0039] 4) Iterative optimization: The genetic algorithm iterates continuously to improve the overall fitness of the population until the control accuracy requirement is met.

[0040] Furthermore, the initial population refers to multiple different initial settings used to optimize the control parameters; the initial population contains multiple individuals, one individual contains several parameter values of the fuzzy control system, and the parameter combinations of each individual are encoded in a predetermined manner.

[0041] Furthermore, the calculation of the fitness is used to measure the achievement of each coal injection parameter combination for the target control effect, so as to screen out the optimal solution. The specific implementation steps are as follows:

[0042] 1) Determine the fitness function, which is set according to the control target and used to evaluate the coal injection effect of each parameter combination.

[0043] 2) Define the evaluation index, and set specific evaluation indexes according to the target to quantify the performance of each parameter combination.

[0044] 3) Calculate the fitness of each individual and normalize the fitness values. After normalization, the genetic algorithm can select better individuals according to the fitness values to enter the next generation.

[0045] Further, the crossover and mutation operations are used to generate a new generation of individuals;

[0046] The crossover operation generates "offspring" individuals by exchanging partial gene information of two "parent" individuals, thus combining new control parameter combinations. The specific operation steps are as follows:

[0047] 1) Select two individuals with higher fitness as parents according to the fitness values;

[0048] 2) Randomly select a crossover point in the individual gene sequence;

[0049] 3) Swap the gene segments of the two parent individuals at the crossover point to generate two new offspring individuals;

[0050] 4) Check the legality of the generated offspring individuals to ensure that the generated control parameters are within the actual process range;

[0051] The mutation operation improves the diversity of the population by randomly changing some gene positions in the individuals, avoiding the algorithm falling into local optimality. The specific steps are as follows:

[0052] 1) Randomly select some individuals from the population for mutation according to the set mutation probability;

[0053] 2) Randomly select one or more gene positions as mutation positions in the selected mutated individuals;

[0054] 3) Randomly change the gene values at the mutation positions;

[0055] 4) The mutated gene combination needs to be within the reasonable range of the control system parameters;

[0056] Through the crossover and mutation operations, the genetic algorithm can effectively explore different parameter combinations and finally find the optimal solution suitable for the control of the blast furnace coal injection volume to improve the adaptability and efficiency of the system.

[0057] The present invention provides an intelligent control method for the coal injection volume in a blast furnace optimized based on fuzzy self - adaptation and genetic algorithm. By combining fuzzy self - adaptation control and genetic algorithm, the concentrations of components such as oxygen and gas in the blast furnace are converted into fuzzy membership values, a fuzzy control rule base with multiple inputs and a single output is established, and the genetic algorithm is used to optimize the control parameters. This method constructs an adaptive and dynamic coal injection volume adjustment system, which can automatically adjust the coal injection volume according to real - time data to meet the requirements of the blast furnace at different times and loads, ensuring sufficient combustion and efficient utilization of gas resources. Traditional coal injection control usually relies on manual adjustment or fixed parameters, making it difficult to quickly respond to changes in the blast furnace working conditions, and prone to problems such as low gas utilization rate, high energy consumption, and poor control accuracy. Through the method of the present invention, the intelligent and automated level of the coal injection process in the blast furnace is significantly improved, which not only ensures the stability of production and sufficient combustion of gas, but also reduces resource waste and carbon emissions, improves energy utilization rate and economic benefits. At the same time, this solution plays an important role in promoting the goals of green manufacturing and energy conservation and emission reduction in the iron and steel industry, and provides a reliable technical support for the intelligent transformation of blast furnace production. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flowchart of the present invention.

[0059] Figure 2 It is a schematic diagram of crossover of the genetic algorithm in the present invention.

[0060] Figure 3 It is a schematic diagram of mutation of the genetic algorithm in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0062] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and 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, and thus cannot be understood as a limitation of the present invention.

[0063] The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0064] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Embodiment 1

[0066] An intelligent control method for the pulverized coal injection amount in a blast furnace based on fuzzy self - adaptation and genetic algorithm optimization in this embodiment includes the overall design of the self - adaptation control system, the establishment of fuzzy rules, the optimization of pulverized coal injection parameters by the genetic algorithm, etc. to achieve the intelligent control of the pulverized coal injection amount in the blast furnace. The steps are as follows:

[0067] Step 1: Set the target pulverized coal injection amount and control requirements for blast furnace production, such as the pulverized coal injection rate, the temperature stability range, and the gas content. According to these requirements, initialize the fuzzy rule base of the fuzzy self - adaptation control system, and preset the initial value of the pulverized coal injection amount. The fuzzy rule base is shown in Table 1 below.

[0068] For the described fuzzy rule base, the specific method is to first establish the input and output variables of the fuzzy control. The input variables are the operating parameters of the blast furnace, including the tuyere temperature, pressure, oxygen content, gas content, pulverized coal injection rate, etc., and the output variable is the adjustment value of the pulverized coal injection amount. Then divide the fuzzy levels of the variables. For example, the tuyere temperature can be divided into "low", "moderate", and "high", and the adjustment value of the pulverized coal injection amount can be set as "decrease", "maintain", "increase". Then define the fuzzy rules. For example: if the tuyere temperature is "high" and the pressure is "normal", then the pulverized coal injection amount is adjusted to "decrease slightly"; if the tuyere temperature is "moderate" and the oxygen content is "high", then the pulverized coal injection amount is adjusted to "maintain", etc. Finally, determine the fuzzy inference mechanism, and use fuzzy inference methods such as the "max - min method" or the "weighted average method" to map the fuzzy quantities of multiple inputs to the output pulverized coal adjustment value.

[0069] Table 1 Fuzzy rule base for pulverized coal injection in blast furnace

[0070]

[0071] The fuzzy membership function is a mathematical tool in the fuzzy control system to describe the degree of fuzzy variables, and is used to convert the specific numerical values of the input and output variables into fuzzy values (such as "high", "low") in the fuzzy set. For example, for the tuyere temperature variable, a triangular membership function can be used for description:

[0072]

[0073] Among them, a and c are the starting and ending points of the function, b is the vertex. The triangular membership function has a peak at a certain central value, decreasing to zero on both the left and right sides, presenting a symmetric triangular shape.

[0074] Step 2: Divide the control range for different working condition parameters, and set the fuzzy membership function. In this embodiment, for the working condition parameters, the triangular membership function is used for description:

[0075]

[0076] a and c are the starting and ending points of the function, b is the vertex. The triangular membership function has a peak at a certain central value, decreasing to zero on both the left and right sides, presenting a symmetric triangular shape.

[0077] Step 3: Use a variety of sensors, installed at key positions such as blast furnace tuyeres, injection pipes, temperature and pressure monitoring points, etc., to monitor the working condition parameters in the blast furnace in real time. The system collects the data recorded per second or per minute to the control system, mainly including: data such as blast furnace tuyere temperature, gas content, furnace pressure, coal powder supply rate, etc.

[0078] Step 4: Use the genetic algorithm to generate the initial population, taking the coal injection amount, oxygen content, and gas content as the parameters of the individual. Calculate the fitness value for each individual. The fitness function is set according to indicators such as combustion efficiency, energy consumption, and pollution emissions. The fitness calculation method adopted in this embodiment is as follows:

[0079]

[0080] Step 5: Iteratively update the population through crossover and mutation operations to find the optimal coal injection amount setting. After several generations of iteration, take the individual with the highest fitness as the output of the coal injection control model. The crossover schematic diagram is as Figure 2 shown, and the mutation schematic diagram is as Figure 3 shown.

[0081] Step 6: Use the optimized coal injection amount setting value, and through control devices such as PLC controllers and solenoid valves, adjust the coal powder injection amount to the optimal state in real time. The system uses closed-loop control to monitor and adjust parameters such as oxygen, gas content, and furnace temperature in real time. When the parameters deviate, the system will automatically adjust the coal injection amount according to the fuzzy rule base to make it stable within the set range.

[0082] Step 7: Feed back the real-time blast furnace operation state and combustion efficiency to the control system, compare the deviation between the actual coal injection amount and the optimized value. After each coal injection adjustment cycle ends, the system automatically updates the fuzzy rule base and genetic algorithm parameters to improve the self-adaptability and optimization effect of the model.

[0083] The specific content of the above-mentioned Step 1 is:

[0084] S11: Set the target coal injection rate and control requirements for blast furnace production, such as coal injection rate, temperature stability range, and gas content. According to these requirements, initialize the fuzzy rule base of the fuzzy adaptive control system and preset the initial value of the coal injection rate.

[0085] S12: Select key operating condition parameters (such as tuyere temperature, pressure, oxygen content, etc.) as control variables, set fuzzy control rules for each variable, divide the control range, and set the fuzzy membership function.

[0086] The specific steps of step two are as follows:

[0087] S21: The data acquisition module includes a variety of sensors installed at key positions such as blast furnace tuyeres, injection pipes, temperature and pressure monitoring points, etc., for real-time monitoring of the operating condition parameters in the blast furnace. Through the sensors of each operating condition, specifically, temperature sensors, pressure sensors, flow sensors, gas composition detectors, level sensors, etc. The temperature sensors are mainly used to measure the real-time temperature of the tuyere and the combustion furnace, the pressure sensors are used to measure the tuyere pressure and the coal injection pipe pressure, the flow sensors are used to measure the gas flow and the pulverized coal flow, etc., the gas composition detector mainly detects the oxygen content during the combustion process, and the level sensor is used to detect the stock of pulverized coal in the coal injection tank. The data of these sensors will be transmitted to the control system in real time.

[0088] S22: After starting the acquisition module, the system will collect the data recorded per second or per minute into the control system, mainly including: data such as blast furnace tuyere temperature, gas content, furnace pressure, and pulverized coal supply rate.

[0089] S23: The data acquisition module transmits the real-time data to the input end of the fuzzy adaptive control system through the Internet of Things or the factory local area network to ensure the real-time and accuracy of the data.

[0090] The specific steps of step three are as follows:

[0091] S31: Input the real-time data obtained by the data acquisition module into the fuzzy adaptive control system and compare it with the set value of the target coal injection rate.

[0092] S32: The fuzzy control system makes inferences based on the set fuzzy rule base and automatically judges whether the current coal injection rate needs to be adjusted. If the current coal injection rate deviates from the target, the fuzzy system generates an adjustment strategy according to the magnitude and direction of the deviation.

[0093] S33: The adjustment strategy is generated by fuzzy logic inference. If the deviation is large, the system will increase the adjustment amplitude of the coal injection rate; if the deviation is small, the adjustment amplitude will also be reduced accordingly to achieve refined control of the coal injection rate.

[0094] The specific steps of step four are as follows:

[0095] S41: The genetic algorithm optimization module performs real-time optimization on the parameters of the fuzzy control system to improve the response speed and accuracy of the control system under different working conditions.

[0096] S42: Through continuous iteration of the genetic algorithm, the overall fitness of the population is improved until the control accuracy requirement is met.

[0097] S43: After the optimal fuzzy parameter combination is generated, it is updated to the fuzzy control system to improve the real-time responsiveness of the coal injection volume adjustment.

[0098] The specific steps of step five are as follows:

[0099] S51: The coal injection execution module receives the adjustment instruction of the fuzzy adaptive control system and adjusts the pulverized coal injection volume in real time.

[0100] S52: The execution module acts on the coal injection system by adjusting parameters such as the injection speed, air volume, and pulverized coal concentration to ensure the precise control of the coal injection volume and rate.

[0101] S53: After the execution module completes the adjustment, it feeds back the result to the control system to achieve closed-loop control and verify the adjustment effect. If the deviation continues to exist, the fuzzy control system will calculate a new adjustment strategy again and execute it in a loop until the coal injection volume reaches the set stable range.

[0102] The genetic algorithm optimization mainly performs real-time optimization on the parameters of the fuzzy control system to improve the response speed and accuracy of the control system under different working conditions. The specific steps are as follows:

[0103] 1) Initialize the population: Set the initial population for each fuzzy parameter (such as the shape of the membership function and the priority of the fuzzy rule) of the control system.

[0104] 2) Fitness evaluation: Calculate the fitness of the current parameter combination based on the actual working condition performance of the coal injection system (such as the accuracy of the coal injection volume, temperature fluctuation, reaction speed, etc.). The higher the fitness, the closer the current combination is to the target value.

[0105] 3) Selection, crossover, and mutation: Select individuals with higher fitness from the population for crossover and mutation operations to generate new parameter combinations.

[0106] 4) Iterative optimization: The genetic algorithm iterates continuously to improve the overall fitness of the population until the control accuracy requirement is met.

[0107] The initial population mentioned refers to multiple different initial settings used to optimize control parameters. The initial population contains multiple individuals. For the pulverized coal injection control system, an individual may contain several parameter values of the fuzzy control system, such as the fuzzy rule boundaries of the tuyere temperature and the adjustment range of the pulverized coal injection volume. The parameter combinations of each individual need to be encoded in a certain way. Commonly used are binary encoding, real number encoding, or symbolic encoding. The initial population can be randomly generated so that the parameter values cover a relatively wide range, increasing the exploration ability of the algorithm for different parameter combinations.

[0108] The fitness calculation mentioned is used to measure the achievement of each pulverized coal injection parameter combination for the target control effect, so as to screen out the optimal solution. The specific implementation steps are as follows:

[0109] 1) Determine the fitness function, which is set according to the control target and used to evaluate the pulverized coal injection effect of each parameter combination. For example, the fitness functions of the pulverized coal injection rate error, temperature deviation value, and gas consumption can be defined as:

[0110]

[0111] 2) Define evaluation indicators, and set specific evaluation indicators according to the target to quantify the performance of each parameter combination.

[0112] 3) Calculate the fitness of each individual and normalize the fitness value. After normalization, the genetic algorithm can select better individuals according to the fitness value to enter the next generation.

[0113] The crossover and mutation operations mentioned are mainly used to generate new individuals. The crossover operation generates "offspring" individuals by exchanging partial gene information of two "parent" individuals, thus combining new control parameter combinations. The specific operation steps are as follows:

[0114] 1) Select two individuals with higher fitness values as parents according to the fitness value.

[0115] 2) Randomly select a crossover point in the individual gene sequence.

[0116] 3) Exchange the gene segments of the two parent individuals at the crossover point to generate two new offspring individuals.

[0117] 4) Conduct a legality check on the generated offspring individuals to ensure that the generated control parameters conform to the actual process range (such as pulverized coal injection volume, temperature, etc.)

[0118] The mutation operation improves the diversity of the population by randomly changing some gene positions in the individual, avoiding the algorithm falling into local optima. The specific steps are as follows:

[0119] 1) Randomly select some individuals from the population for mutation according to the set mutation probability.

[0120] 2) Randomly select one or more gene positions as mutation positions among the selected mutated individuals.

[0121] 3) Randomly change the gene values at the mutation positions.

[0122] 4) The gene combination after mutation needs to conform to the reasonable range of the control system parameters. For example, parameters such as coal injection volume and temperature need to be within the allowable range of the equipment.

[0123] Through crossover and mutation operations, the genetic algorithm can effectively explore different parameter combinations and finally find the optimal solution suitable for the control of the coal injection volume in the blast furnace, thereby improving the adaptability and efficiency of the system.

[0124] The present invention provides an intelligent control method for the coal injection volume in the blast furnace optimized based on fuzzy self - adaptation and genetic algorithm, which combines fuzzy self - adaptation control and genetic algorithm. By converting the concentrations of components such as oxygen and gas in the blast furnace into fuzzy membership values, a fuzzy control rule base with multiple inputs and a single output is established, and the genetic algorithm is used to optimize the control parameters. This method constructs an adaptive and dynamic coal injection volume adjustment system, which can automatically adjust the coal injection volume according to real - time data to meet the requirements of the blast furnace at different times and loads, ensuring sufficient combustion and efficient utilization of gas resources. Traditional coal injection control usually relies on manual adjustment or fixed parameters, which is difficult to quickly respond to changes in the blast furnace working conditions and is prone to problems such as low gas utilization rate, high energy consumption, and poor control accuracy. Through the method of the present invention, the intelligent and automated level of the coal injection process in the blast furnace is significantly improved, which not only ensures the stability of production and the full combustion of gas, but also reduces resource waste and carbon emissions, improves energy utilization rate and economic benefits. At the same time, this solution plays an important role in promoting the goals of green manufacturing and energy conservation and emission reduction in the iron and steel industry, and provides a reliable technical support for the intelligent transformation of blast furnace production.

[0125] The above has described the present invention in detail with reference to the accompanying drawings. However, the present invention is not limited to the above - mentioned embodiments. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can be made without departing from the gist of the present invention. Many other changes and modifications made without departing from the concept and scope of the present invention should be regarded as within the protection scope of the present invention.

[0126] In the description of this specification, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0127] The above - mentioned are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for intelligent control of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization, characterized in that: The method comprises the following steps: S1: Initialize the fuzzy adaptive control system and set the initial coal injection amount setting value; S2: Monitor the real-time working conditions of the blast furnace through sensors and transmit the data to the control system; S3: input the collected data into the fuzzy control system and make preliminary adjustments to the coal injection amount according to the set value; S4: Dynamically optimize the fuzzy control parameters through the genetic algorithm optimization module; S5: The coal injection execution module adjusts the coal injection rate in real time according to the optimization results to achieve closed-loop control.

2. The intelligent control method for blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 1, characterized in that: The step S1 is specifically as follows: S11: setting the target coal injection amount and control requirements for blast furnace production, initializing the fuzzy rule base of the fuzzy adaptive control system according to these requirements, and presetting the initial value of the coal injection amount; S12: Select key operating parameters as control variables, set fuzzy control rules for each variable, divide the control range, and set the fuzzy membership function.

3. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 1, characterized in that: The step S2 is specifically as follows: S21: The data acquisition module includes a variety of sensors installed at the blast furnace tuyere, injection pipe, temperature and pressure monitoring points to monitor the working parameters in the blast furnace in real time; S22: After starting the acquisition module, the system collects the data recorded every second or every minute to the control system, including: blast furnace tuyere temperature, gas content, furnace pressure, and coal powder supply rate data; S23: The data acquisition module transmits real-time data to the input end of the fuzzy adaptive control system through the Internet of Things or the factory local area network to ensure the real-time and accuracy of the data.

4. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 1, characterized in that: The step S3 is specifically as follows: S31: input the real-time data acquired by the data acquisition module into the fuzzy adaptive control system and compare it with the target coal injection amount setting value; S32: The fuzzy control system performs reasoning based on the set fuzzy rule base to automatically determine whether the current coal injection amount needs to be adjusted; if the current coal injection amount deviates from the target, the fuzzy system generates an adjustment strategy based on the deviation size and direction; S33: The adjustment strategy is generated by fuzzy logic reasoning; if the deviation is large, the system will increase the adjustment range of the coal injection amount; if the deviation is small, the adjustment range will be reduced accordingly to achieve detailed control of the coal injection amount.

5. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 1, characterized in that: The step S4 is specifically as follows: S41: The genetic algorithm optimization module optimizes the parameters of the fuzzy control system in real time to improve the response speed and accuracy of the control system under different working conditions; S42: Improve the overall fitness of the population through continuous iteration of the genetic algorithm until the control accuracy requirement is met; S43: After the optimal fuzzy parameter combination is generated, it is updated to the fuzzy control system to improve the real-time responsiveness of the coal injection amount adjustment.

6. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 1, characterized in that: The step S5 is specifically as follows: S51: The coal injection execution module receives the adjustment instruction of the fuzzy adaptive control system and adjusts the coal powder injection amount in real time; S52: The execution module applies control instructions to the coal injection system by adjusting the injection speed, air volume, and coal powder concentration parameters to ensure accurate control of the coal injection amount and coal injection rate; S53: After the execution module completes the adjustment, the result is fed back to the control system to implement closed-loop control and verify the adjustment effect. If the deviation continues to exist, the fuzzy control system will calculate a new adjustment strategy again and execute it cyclically until the coal injection amount reaches the set stable range.

7. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 5, characterized in that: The genetic algorithm optimization is to optimize the parameters of the fuzzy control system in real time to improve the response speed and accuracy of the control system under different working conditions. The specific steps are as follows: 1) Initialize the population: set the initial population for each fuzzy parameter of the control system; 2) Fitness evaluation: Calculate the fitness of the current parameter combination based on the actual operating performance of the coal injection system. The higher the fitness, the closer the current combination is to the target value; 3) Selection, crossover and mutation: select individuals with higher fitness from the population for crossover and mutation operations to generate new parameter combinations; 4) Iterative optimization: The genetic algorithm is continuously iterated to improve the overall fitness of the population until the control accuracy requirement is met.

8. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 7, characterized in that: The initial population refers to a plurality of different initial settings for optimizing control parameters; the initial population includes a plurality of individuals, one individual includes a number of parameter values ​​of the fuzzy control system, and the parameter combination of each individual is encoded in a predetermined manner.

9. The intelligent control method of blast furnace coal injection amount based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 7, characterized in that: The fitness calculation is used to measure the achievement of the target control effect of each coal injection parameter combination, so as to select the best performing solution. The specific implementation steps are as follows: 1) Determine the fitness function, which is set according to the control target, to evaluate the coal injection effect of each parameter combination; 2) Define evaluation indicators and set specific evaluation indicators according to the goals to quantify the performance of each parameter combination; 3) Calculate the fitness of each individual and normalize the fitness value. After normalization, the genetic algorithm can select better individuals to enter the next generation based on the fitness value.

10. The intelligent control method of coal injection amount in a blast furnace based on fuzzy self-adaptation and genetic algorithm optimization as claimed in claim 7, characterized in that: The crossover and mutation operations are used to generate a new generation of individuals; The crossover operation generates a "child" individual by exchanging part of the genetic information of two "parent" individuals, thereby combining a new control parameter combination. The specific operation steps are: 1) Select two individuals with higher fitness as parents according to their fitness values; 2) Randomly select a crossover point in the individual gene sequence; 3) Swap the gene fragments of the two parent individuals at the crossover point to generate two new offspring individuals; 4) Check the legality of the generated offspring individuals to ensure that the generated control parameters are in line with the actual process range; The mutation operation improves the diversity of the population by randomly changing certain gene positions in individuals and avoids the algorithm from falling into the local optimum. The specific steps are: 1) According to the set mutation probability, some individuals are randomly selected from the population for mutation; 2) Randomly select one or more gene loci as variant loci in the selected variant individuals; 3) Randomly change the gene value at the variant position; 4) The mutated gene combination must be within the reasonable range of control system parameters; Through crossover and mutation operations, the genetic algorithm can effectively explore different parameter combinations and ultimately find the optimal solution for blast furnace coal injection control to improve the adaptability and efficiency of the system.

Images