A silicon steel annealing furnace combustion control system

Abstract

The application relates to the technical field of annealing furnace control, and discloses a silicon steel annealing furnace combustion control system which comprises the following steps: when M burners in an annealing furnace are used to carry out combustion processing on silicon steel to be processed according to ideal values of control parameters, if incomplete combustion is found in the furnace, actual values of the burners in the furnace about the control parameters are obtained; the control parameters include gas flow and combustion air flow; the ideal values and the actual values of the control parameters are compared in a numerical relationship, and according to the comparison result, an aging burner is screened out from the M burners in the furnace, and the actual values of the aging burner about the control parameters are extracted; the actual values of the aging burner about the control parameters are corrected by using a preconfigured genetic algorithm, and the correction values of the aging burner about the control parameters are obtained; the application is favorable for realizing precise combustion control by dynamically adjusting combustion parameters, intelligently identifying the aging burner and adjusting the combustion state in real time.

Description

Technical Field

[0001] This invention relates to the field of annealing furnace control technology, and more specifically, to a combustion control system for a silicon steel annealing furnace. Background Technology

[0002] The silicon steel annealing furnace plays a crucial role in the steel production process. Its main function is to improve the electromagnetic and mechanical properties of silicon steel through heating and annealing. Heating in the annealing furnace is achieved by multiple heating burners. These burners typically generate a high-temperature environment through the combustion of a mixture of fuel gas and air, thereby completing the annealing process of silicon steel. In existing technologies, the multiple burners in the annealing furnace are generally controlled synchronously, meaning that each burner operates simultaneously under the same combustion conditions to ensure the uniformity of the annealing temperature. However, with long-term use in high-temperature operating environments, the burners gradually age, leading to a decrease in combustion efficiency, a weakening of the injection effect, and even the possibility of incomplete combustion in some burners.

[0003] The aging of burners poses a serious challenge to the overall combustion control of silicon steel annealing furnaces. On the one hand, uneven combustion of aging burners may cause uneven temperature distribution within the annealing furnace, affecting the annealing quality of silicon steel. On the other hand, if aging burners still operate according to the synchronous control strategy, they cannot dynamically adjust combustion parameters based on their actual working conditions, leading to energy waste and increased equipment wear. This control method cannot reflect burner performance changes in a timely manner, thus affecting production efficiency and energy utilization.

[0004] To address the aforementioned issues, a novel combustion control system for silicon steel annealing furnaces is urgently needed. This system should be able to monitor and analyze the operating status of each burner, independently control and adjust burners with different aging levels to optimize the combustion process and improve the furnace's operating efficiency and product quality. Simultaneously, by automatically identifying and intelligently adjusting the burner's aging status, it should ensure a stable temperature distribution within the furnace even when different burners have inconsistent aging levels, thereby enhancing the reliability of the silicon steel annealing process. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a combustion control system for a silicon steel annealing furnace.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A combustion control system for a silicon steel annealing furnace, the system comprising:

[0008] The data acquisition module is used to acquire the actual values ​​of the burners in the furnace with respect to the control parameters when incomplete combustion is detected in the furnace during combustion processing of the silicon steel to be processed by the M burners in the annealing furnace according to the ideal values ​​of the control parameters; the control parameters include gas flow rate and combustion air flow rate, where M is an integer greater than zero;

[0009] The data analysis module is used to compare the ideal and actual values ​​of the control parameters, and based on the comparison results, to select the aged burners from the M burners in the furnace and extract the actual values ​​of the aged burners with respect to the control parameters.

[0010] The combustion control module is used to correct the actual values ​​of the control parameters of the aging burner using a pre-configured genetic algorithm, obtain the corrected values ​​of the control parameters of the aging burner, and adjust the control parameters of the aging burner in the furnace according to the corrected values.

[0011] Furthermore, the logic for obtaining the ideal value of the control parameter is as follows:

[0012] Obtain basic characteristic data of the silicon steel to be processed; the basic characteristic data includes the thickness, width, weight, silicon content, carbon content and surface roughness of the silicon steel to be processed;

[0013] The basic characteristic data of the silicon steel to be processed are input into a pre-constructed parametric regression model to obtain the combustion load requirement of the silicon steel to be processed; the combustion load requirement is the target annealing temperature.

[0014] Based on the preset relationship between the ideal values ​​of the control parameters and the combustion load requirements, the ideal values ​​of the control parameters for M burners in the annealing furnace are extracted.

[0015] Furthermore, the logic for obtaining the surface roughness of the silicon steel to be processed is as follows:

[0016] Obtain a surface image of the silicon steel to be processed, and after grayscale processing, obtain the grayscale values ​​of the pixels in the grayscale surface image.

[0017] The grayscale value of the pixel is input into the pre-constructed surface roughness calculation model to obtain the surface roughness of the silicon steel to be processed.

[0018] The expression for the pre-constructed surface roughness calculation model is as follows:

[0019]

[0020] In the formula: RA is the surface roughness. This represents the grayscale change in the i-th row direction. This represents the grayscale change in the j-th row direction, where P and Q represent the number of rows and columns of the image, respectively.

[0021] Furthermore, the generation logic of the pre-built parametric regression model is as follows:

[0022] Acquire historical control parameter training data, and divide the historical control parameter training data into parameter regression training set and parameter regression test set. The historical control parameter training data includes the basic characteristic data of the silicon steel to be processed and its corresponding combustion load requirements.

[0023] A regression network is constructed by using the basic characteristic data of the silicon steel to be processed in the parameter regression training set as the input of the regression network and the combustion load demand in the parameter regression training set as the output of the regression network. The regression network is then trained to obtain the initial parameter regression network.

[0024] The initial parametric regression network is validated using a parametric regression test set. The output of the initial parametric regression network that is less than or equal to the preset test error threshold is used as the pre-built parametric regression model.

[0025] Furthermore, the logic for determining the presence of incomplete combustion within the furnace is as follows:

[0026] Data on flue gas inside the annealing furnace is acquired within a predetermined time range. The flue gas data includes oxygen concentration, carbon monoxide concentration, hydrocarbon concentration, carbon dioxide concentration, and particulate matter concentration.

[0027] Input the flue gas data into the pre-built flue gas coefficient calculation model to obtain the flue gas coefficient inside the annealing furnace;

[0028] The expression for the pre-constructed flue gas coefficient calculation model is as follows:

[0029]

[0030] In the formula: GS is the flue gas coefficient, O2(t) is the oxygen concentration, CO2(t) is the carbon dioxide concentration, Co(t) is the carbon monoxide concentration, PM(t) is the particulate matter concentration, HC(t) is the hydrocarbon concentration, e is the natural constant, and T is the length of the given time range.

[0031] Furthermore, the numerical comparison of the ideal and actual values ​​of the control parameters includes:

[0032] Calculate the ratio between the ideal and actual values ​​of each burner control parameter;

[0033] Calculate the difference between the ideal and actual values ​​of the control parameters after the ratio calculation, and mark the difference between the ideal and actual values ​​of the control parameters after the ratio calculation as the control parameter difference;

[0034] Set the threshold for the first control parameter;

[0035] The difference in control parameters is compared with the first control parameter threshold. If the difference in control parameters is greater than or equal to the first control parameter threshold, the corresponding burner is determined to be an aged burner; if the difference in control parameters is less than the first control parameter threshold, the corresponding burner is determined to be a non-aged burner.

[0036] Furthermore, after screening out the aged burners, the process includes:

[0037] The control parameters of the aged burner were poor.

[0038] Set a second control parameter threshold, which is greater than the first control parameter threshold;

[0039] The control parameter difference is compared with the second control parameter threshold. If the control parameter difference is greater than or equal to the second control parameter threshold, the corresponding aging burner is marked as a burner to be replaced. If the control parameter difference is less than the second control parameter threshold but greater than the first control parameter threshold, the corresponding aging burner is marked as a burner not to be replaced.

[0040] Furthermore, the correction of the actual values ​​of the control parameters for the aging burner includes:

[0041] a1: Initialize the population: Randomly generate an original population containing Z chromosomes, each chromosome representing a set of random values ​​for control parameters, wherein each chromosome is represented as X = [X1, X2], where X1 represents the gas flow rate, X2 represents the combustion air flow rate, and Z is an integer greater than zero;

[0042] a2: Fitness assessment: Under each chromosome, obtain the flue gas coefficient, fuel consumption and actual annealing temperature in the annealing furnace, input the flue gas coefficient, fuel consumption and actual annealing temperature into the pre-constructed fitness function, and calculate the fitness of each chromosome.

[0043] a3: Selection: Two chromosomes with high fitness from the original population were selected as the father and mother using the roulette wheel method;

[0044] a4: Crossover: The process of crossing over the father and mother to produce new chromosomes;

[0045] a5: Mutation: Perform a mutation operation on the new chromosome to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2;

[0046] a6: Repeat steps a2 to a5 until the fitness of chromosomes in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the random value of the control parameter represented by the corresponding chromosome as the correction value of the control parameter.

[0047] Furthermore, the formula for calculating the pre-constructed fitness function is as follows: In the formula: Fitness is fitness, GS is flue gas coefficient, GS0 is the reference value of flue gas coefficient, WD is the actual annealing temperature, WD0 is the target annealing temperature, and E(x1) is the fuel consumption.

[0048] A combustion control method for a silicon steel annealing furnace, implemented based on the aforementioned combustion control system for a silicon steel annealing furnace, the method comprising:

[0049] When the M burners in the annealing furnace are burning the silicon steel to be processed according to the ideal values ​​of the control parameters, and incomplete combustion is found in the furnace, the actual values ​​of the burners in the furnace with respect to the control parameters are obtained; the control parameters include the gas flow rate and the combustion air flow rate, and M is an integer greater than zero;

[0050] The ideal and actual values ​​of the control parameters are compared numerically, and the aged burners are selected from the M burners in the furnace based on the comparison results. The actual values ​​of the aged burners with respect to the control parameters are then extracted.

[0051] A pre-configured genetic algorithm is used to correct the actual values ​​of the control parameters of the aging burner, thereby obtaining the corrected values ​​of the control parameters of the aging burner. The control parameters of the aging burner in the furnace are then adjusted according to the corrected values.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0053] This application discloses a combustion control system for a silicon steel annealing furnace, comprising: when M burners in the annealing furnace are performing combustion processing on the silicon steel to be processed according to ideal values ​​of control parameters, and incomplete combustion is found in the furnace, the actual values ​​of the burners in the furnace with respect to the control parameters are obtained; the control parameters include gas flow rate and combustion air flow rate; the ideal and actual values ​​of the control parameters are compared numerically, and aging burners are selected from the M burners in the furnace according to the comparison results, and the actual values ​​of the aging burners with respect to the control parameters are extracted; the actual values ​​of the aging burners with respect to the control parameters are corrected using a pre-configured genetic algorithm to obtain the corrected values ​​of the aging burners with respect to the control parameters; based on the above technical features, this invention dynamically adjusts each burner by analyzing the characteristic data of silicon steel. The gas flow rate and combustion air flow rate of the burners ensure temperature uniformity during the annealing process, solving the problem of uneven combustion caused by aging burners that traditional synchronous control methods cannot handle. The system can intelligently identify the aging status of the burners and avoid energy waste and equipment wear by independently adjusting the combustion parameters of burners with different aging levels. At the same time, the introduction of genetic algorithms to optimize and adjust the control parameters of aging burners further improves combustion efficiency, reduces energy consumption, and ensures that the temperature distribution in the furnace remains stable even when different burners have inconsistent aging levels, thereby improving the annealing quality of silicon steel and the reliability of the process. It effectively reduces maintenance costs and production interruptions caused by aging burners and significantly improves the production efficiency and energy utilization rate of the annealing furnace. Attached Figure Description

[0054] Figure 1 A modular structure diagram of a combustion control system for a silicon steel annealing furnace provided by the present invention;

[0055] Figure 2 A flowchart of the combustion control method for silicon steel annealing furnace provided by the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example 1

[0058] Please see Figure 1 As shown in the figure, this embodiment discloses a combustion control system for a silicon steel annealing furnace, the system comprising:

[0059] The data acquisition module 101 is used to acquire the actual values ​​of the burners in the furnace with respect to the control parameters when the silicon steel to be processed is burned by the M burners in the annealing furnace according to the ideal values ​​of the control parameters and incomplete combustion is found in the furnace; the control parameters include gas flow rate and combustion air flow rate, and M is an integer greater than zero;

[0060] In implementation, the logic for obtaining the ideal value of the control parameter is as follows:

[0061] Obtain basic characteristic data of the silicon steel to be processed; the basic characteristic data includes the thickness, width, weight, silicon content, carbon content and surface roughness of the silicon steel to be processed;

[0062] The thickness, width, weight, silicon content, and carbon content of the silicon steel to be processed are obtained manually by technicians or directly extracted from a pre-built system database according to the model of the silicon steel to be processed. In the system database, technicians have pre-recorded basic characteristic data such as thickness, width, weight, silicon content, and carbon content of the silicon steel model.

[0063] The logic for obtaining the surface roughness of the silicon steel to be processed is as follows:

[0064] Obtain a surface image of the silicon steel to be processed, and after grayscale processing, obtain the grayscale values ​​of the pixels in the grayscale surface image.

[0065] The grayscale value of the pixel is input into the pre-constructed surface roughness calculation model to obtain the surface roughness of the silicon steel to be processed.

[0066] The expression for the pre-constructed surface roughness calculation model is as follows:

[0067]

[0068] In the formula: RA is the surface roughness. This represents the grayscale change in the i-th row direction. This represents the grayscale change in the j-th row direction, where P and Q represent the number of rows and columns of the image, respectively.

[0069] The basic characteristic data of the silicon steel to be processed are input into a pre-constructed parametric regression model to obtain the combustion load requirement of the silicon steel to be processed; the combustion load requirement is the target annealing temperature.

[0070] It should be understood that the target annealing temperature of the annealing process will vary depending on the metal specifications and materials; each metal has its specific physical properties and target performance during the annealing process, therefore, the target annealing temperature is set differently by technicians based on the actual characteristics of the material.

[0071] Based on the preset relationship between the ideal values ​​of the control parameters and the combustion load requirements, the ideal values ​​of the control parameters for M burners in the annealing furnace are extracted.

[0072] It should be noted that: the system database pre-stores the ideal values ​​of multiple control parameters and their mapping relationships with combustion load requirements. In each mapping relationship, technicians associate and bind the ideal value of a control parameter with the combustion load requirement. Each mapping relationship reveals the ideal values ​​of the gas flow rate and the combustion air flow rate that should be output when the silicon steel to be processed is to reach the target annealing temperature. These ideal values ​​of gas flow rate and combustion air flow rate are determined manually based on the actual situation.

[0073] The generation logic of the pre-built parametric regression model is as follows:

[0074] Acquire historical control parameter training data, and divide the historical control parameter training data into parameter regression training set and parameter regression test set. The historical control parameter training data includes the basic characteristic data of the silicon steel to be processed and its corresponding combustion load requirements.

[0075] It should be noted that the basic characteristic data of the silicon steel to be processed and its corresponding combustion load requirements (i.e., target annealing temperature) in the historical control parameter training data were all collected by technicians based on the actual experimental conditions.

[0076] A regression network is constructed by using the basic characteristic data of the silicon steel to be processed in the parameter regression training set as the input of the regression network and the combustion load demand in the parameter regression training set as the output of the regression network. The regression network is then trained to obtain the initial parameter regression network.

[0077] The initial parametric regression network is validated using a parametric regression test set. The output of the initial parametric regression network that is less than or equal to the preset test error threshold is used as the pre-built parametric regression model.

[0078] Specifically, the regression network is one of the following regression algorithms: decision tree, random forest, support vector machine, multinomial regression, LSTM, CNN, or RNN.

[0079] Specifically, the logic for determining the presence of incomplete combustion within the furnace is as follows:

[0080] Data on flue gas inside the annealing furnace is acquired within a predetermined time range. The flue gas data includes oxygen concentration, carbon monoxide concentration, hydrocarbon concentration, carbon dioxide concentration, and particulate matter concentration.

[0081] The flue gas data is obtained through various sensors, including but not limited to oxygen sensors, carbon monoxide sensors, hydrocarbon sensors, carbon dioxide sensors, and particulate matter sensors.

[0082] Input the flue gas data into the pre-built flue gas coefficient calculation model to obtain the flue gas coefficient inside the annealing furnace;

[0083] The expression for the pre-constructed flue gas coefficient calculation model is as follows:

[0084]

[0085] In the formula: GS is the flue gas coefficient, O2(t) is the oxygen concentration, CO2(t) is the carbon dioxide concentration, Co(t) is the carbon monoxide concentration, PM(t) is the particulate matter concentration, HC(t) is the hydrocarbon concentration, e is the natural constant, and T is the length of a given time range in seconds (s).

[0086] The data analysis module 102 is used to compare the ideal and actual values ​​of the control parameters, and to select the aged burners from the M burners in the furnace based on the comparison results, and to extract the actual values ​​of the aged burners with respect to the control parameters.

[0087] In implementation, the comparison of the numerical relationship between the ideal and actual values ​​of the control parameters includes:

[0088] Calculate the ratio between the ideal and actual values ​​of each burner control parameter;

[0089] It should be understood that the control parameters include the gas flow rate and the combustion air flow rate. Therefore, the ideal value of the control parameters includes the ideal value of the gas flow rate and the ideal value of the combustion air flow rate. Calculating the ratio between the two will yield the ratio of the ideal value of the combustion air flow rate to the ideal value of the gas flow rate, which is the ideal value of the air-fuel ratio. Similarly, the logic for the actual value of the control parameters is the same, and will not be repeated here.

[0090] Calculate the difference between the ideal and actual values ​​of the control parameters after the ratio calculation, and mark the difference between the ideal and actual values ​​of the control parameters after the ratio calculation as the control parameter difference;

[0091] Set the threshold for the first control parameter;

[0092] The control parameter difference is compared with the first control parameter threshold. If the control parameter difference is greater than or equal to the first control parameter threshold, the corresponding burner is determined to be an aged burner; if the control parameter difference is less than the first control parameter threshold, the corresponding burner is determined to be a non-aged burner.

[0093] In one specific implementation, after screening out the aged burners, the process includes:

[0094] The control parameters of the aged burner were poor.

[0095] Set a second control parameter threshold, which is greater than the first control parameter threshold;

[0096] The control parameter difference is compared with the second control parameter threshold. If the control parameter difference is greater than or equal to the second control parameter threshold, the corresponding aging burner is marked as a burner to be replaced. If the control parameter difference is less than the second control parameter threshold but greater than the first control parameter threshold, the corresponding aging burner is marked as a burner not to be replaced.

[0097] It should be understood that when the corresponding aging burner is marked as a burner to be replaced, it means that the corresponding aging burner has reached a serious level of aging. The system maintenance personnel should be reminded to replace the corresponding aging burner urgently to avoid affecting the quality of metal processing and to avoid unnecessary fuel loss.

[0098] By comparing the ideal and actual values ​​of the control parameters, aging burners can be automatically identified, and it can be determined whether they need to be replaced based on the degree of aging. This not only effectively avoids the decline in combustion efficiency caused by burner aging, but also allows for personalized adjustments based on the actual working conditions of different burners, avoiding unnecessary fuel waste and equipment wear.

[0099] The combustion control module 103 is used to correct the actual values ​​of the control parameters of the aging burner using a pre-configured genetic algorithm, obtain the corrected values ​​of the control parameters of the aging burner, and adjust the control parameters of the aging burner in the furnace according to the corrected values.

[0100] The correction of the actual values ​​of the control parameters for the aging burner includes:

[0101] a1: Initialize the population: Randomly generate an original population containing Z chromosomes, each chromosome representing a set of random values ​​for control parameters, wherein each chromosome is represented as X = [X1, X2], where X1 represents the gas flow rate, X2 represents the combustion air flow rate, and Z is an integer greater than zero;

[0102] a2: Fitness assessment: Under each chromosome (i.e., the random value of each control parameter in the original population), the flue gas coefficient, fuel consumption and actual annealing temperature in the annealing furnace are obtained. The flue gas coefficient, fuel consumption and actual annealing temperature are input into the pre-constructed fitness function to calculate the fitness of each chromosome.

[0103] The formula for calculating the pre-constructed fitness function is as follows: Where: Fitness is fitness, GS is flue gas coefficient, GS0 is the reference value of flue gas coefficient, WD is the actual annealing temperature, WD0 is the target annealing temperature, and E(x1) is the fuel consumption.

[0104] It should be noted that the reference values ​​for flue gas coefficients and other values ​​are set in advance by technicians based on actual experimental conditions.

[0105] a3: Selection: Two chromosomes with high fitness from the original population were selected as the father and mother using the roulette wheel method;

[0106] Roulette wheel selection is a commonly used selection method in genetic algorithms to select chromosomes with higher fitness to enter the next generation. It simulates the process of roulette wheel selection, where each chromosome receives a corresponding "roulette" area based on its fitness. The higher the fitness of a chromosome, the larger its corresponding area and the higher its probability of being selected.

[0107] a4: Crossover: The process of crossing over the father and mother to produce new chromosomes;

[0108] It should be noted that the crossover operation between the parent and mother lines is based on the crossover operation, which includes, but is not limited to, one of the following: single-point crossover, uniform crossover, or sequential crossover.

[0109] a5: Mutation: Perform a mutation operation on the new chromosome to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2;

[0110] In genetic algorithms, mutation is used to introduce gene diversity and prevent the algorithm from getting trapped in local optima; the mutation operation on new chromosomes is achieved through uniform mutation or Gaussian mutation, etc.

[0111] a6: Repeat steps a2 to a5 above until the fitness of chromosomes in the original population or new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the random value of the control parameter represented by the corresponding chromosome as the correction value of the control parameter.

[0112] For example: Assuming the maximum number of iterations is 100, after each iteration, record the chromosome with the highest fitness in the current population and its fitness value; if no significant change in fitness value is found in a certain generation, it is considered that the convergence condition has been met, the iteration stops, and the random value of the control parameter represented by the corresponding chromosome is output as the correction value of the control parameter;

[0113] By combining flue gas data acquired by sensors, the system can determine the combustion status inside the annealing furnace in real time and quickly adjust control parameters when incomplete combustion is detected. Unlike traditional synchronous control methods, this system can correct for the aging of individual burners, improving energy efficiency and reducing energy consumption in production. In addition, even when different burners have inconsistent aging levels, the system can still ensure uniform temperature distribution inside the furnace, avoiding problems such as local overheating or insufficient temperature. This makes the annealing process of silicon steel more stable, improves the electromagnetic and mechanical properties of the product, and thus improves the reliability of the production line and the quality of the final product.

[0114] Example 2

[0115] Please see Figure 2 As shown in the figure, this embodiment discloses a combustion control method for a silicon steel annealing furnace, the method comprising:

[0116] S201: When the M burners in the annealing furnace are burning the silicon steel to be processed according to the ideal values ​​of the control parameters, and incomplete combustion is found in the furnace, the actual values ​​of the burners in the furnace with respect to the control parameters are obtained; the control parameters include the gas flow rate and the combustion air flow rate, and M is an integer greater than zero;

[0117] S202: Compare the numerical relationship between the ideal and actual values ​​of the control parameters, and select aged burners from the M burners in the furnace based on the comparison results, and extract the actual values ​​of the aged burners with respect to the control parameters.

[0118] S203: Use a pre-configured genetic algorithm to correct the actual values ​​of the control parameters of the aging burner, obtain the corrected values ​​of the control parameters of the aging burner, and adjust the control parameters of the aging burner in the furnace according to the corrected values.

[0119] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters, weights, and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0120] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0122] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0123] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0124] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0126] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0127] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A combustion control system for a silicon steel annealing furnace, characterized in that, The system includes: The data acquisition module is used to acquire the actual values ​​of the burners in the furnace with respect to the control parameters when incomplete combustion is detected in the furnace during combustion processing of the silicon steel to be processed by the M burners in the annealing furnace according to the ideal values ​​of the control parameters; the control parameters include gas flow rate and combustion air flow rate, where M is an integer greater than zero; The data analysis module is used to compare the ideal and actual values ​​of the control parameters, and based on the comparison results, to select the aged burners from the M burners in the furnace and extract the actual values ​​of the aged burners with respect to the control parameters. The comparison of the numerical relationship between the ideal and actual values ​​of the control parameters includes: Calculate the ratio between the ideal and actual values ​​of each burner control parameter; Calculate the difference between the ideal and actual values ​​of the control parameters after the ratio calculation, and mark the difference between the ideal and actual values ​​of the control parameters after the ratio calculation as the control parameter difference; Set the threshold for the first control parameter; The difference in control parameters is compared with a first control parameter threshold. If the difference is greater than or equal to the first control parameter threshold, the corresponding burner is determined to be an aged burner; if the difference is less than the first control parameter threshold, the corresponding burner is determined to be a non-aged burner. The combustion control module is used to correct the actual values ​​of the control parameters of the aging burner using a pre-configured genetic algorithm, obtain the corrected values ​​of the control parameters of the aging burner, and adjust the control parameters of the aging burner in the furnace according to the corrected values.

2. The combustion control system for a silicon steel annealing furnace according to claim 1, characterized in that, The logic for obtaining the ideal value of the control parameter is as follows: Obtain basic characteristic data of the silicon steel to be processed; the basic characteristic data includes the thickness, width, weight, silicon content, carbon content and surface roughness of the silicon steel to be processed; The basic characteristic data of the silicon steel to be processed are input into a pre-constructed parametric regression model to obtain the combustion load requirement of the silicon steel to be processed; the combustion load requirement is the target annealing temperature. Based on the preset relationship between the ideal values ​​of the control parameters and the combustion load requirements, the ideal values ​​of the control parameters for M burners in the annealing furnace are extracted.

3. The combustion control system for a silicon steel annealing furnace according to claim 2, characterized in that, The logic for obtaining the surface roughness of the silicon steel to be processed is as follows: Obtain a surface image of the silicon steel to be processed, and after grayscale processing, obtain the grayscale values ​​of the pixels in the grayscale surface image. The grayscale value of the pixel is input into the pre-constructed surface roughness calculation model to obtain the surface roughness of the silicon steel to be processed. The expression for the pre-constructed surface roughness calculation model is as follows: In the formula: RA is the surface roughness. This represents the grayscale change in the i-th row direction. This represents the grayscale change in the j-th row direction, where P and Q represent the number of rows and columns of the image, respectively.

4. The combustion control system for a silicon steel annealing furnace according to claim 3, characterized in that, The generation logic of the pre-built parametric regression model is as follows: Acquire historical control parameter training data, and divide the historical control parameter training data into parameter regression training set and parameter regression test set. The historical control parameter training data includes the basic characteristic data of the silicon steel to be processed and its corresponding combustion load requirements. A regression network is constructed by using the basic characteristic data of the silicon steel to be processed in the parameter regression training set as the input of the regression network and the combustion load demand in the parameter regression training set as the output of the regression network. The regression network is then trained to obtain the initial parameter regression network. The initial parametric regression network is validated using a parametric regression test set. The output of the initial parametric regression network that is less than or equal to the preset test error threshold is used as the pre-built parametric regression model.

5. The combustion control system for a silicon steel annealing furnace according to claim 4, characterized in that, The logic for determining the presence of incomplete combustion within the furnace is as follows: Data on flue gas inside the annealing furnace is acquired within a predetermined time range. The flue gas data includes oxygen concentration, carbon monoxide concentration, hydrocarbon concentration, carbon dioxide concentration, and particulate matter concentration. Input the flue gas data into the pre-built flue gas coefficient calculation model to obtain the flue gas coefficient inside the annealing furnace; The expression for the pre-constructed flue gas coefficient calculation model is as follows: In the formula: GS is the flue gas coefficient, O2(t) is the oxygen concentration, CO2(t) is the carbon dioxide concentration, Co(t) is the carbon monoxide concentration, PM(t) is the particulate matter concentration, HC(t) is the hydrocarbon concentration, e is the natural constant, and T is the length of the given time range.

6. The combustion control system for a silicon steel annealing furnace according to claim 5, characterized in that, After screening out aged burners, the following were included: The control parameters of the aged burner were poor. Set a second control parameter threshold, which is greater than the first control parameter threshold; The control parameter difference is compared with the second control parameter threshold. If the control parameter difference is greater than or equal to the second control parameter threshold, the corresponding aging burner is marked as a burner to be replaced. If the control parameter difference is less than the second control parameter threshold but greater than the first control parameter threshold, the corresponding aging burner is marked as a burner not to be replaced.

7. The combustion control system for a silicon steel annealing furnace according to claim 6, characterized in that, in, The correction of the actual values ​​of the control parameters for the aging burner includes: a1: Initialize the population: Randomly generate an original population containing Z chromosomes, each chromosome representing a set of random values ​​for control parameters, wherein each chromosome is represented as X = [X1, X2], where X1 represents the gas flow rate, X2 represents the combustion air flow rate, and Z is an integer greater than zero; a2: Fitness assessment: Under each chromosome, obtain the flue gas coefficient, fuel consumption and actual annealing temperature in the annealing furnace, input the flue gas coefficient, fuel consumption and actual annealing temperature into the pre-constructed fitness function, and calculate the fitness of each chromosome. a3: Selection: Two chromosomes with high fitness from the original population were selected as the father and mother using the roulette wheel method; a4: Crossover: The process of crossing over the father and mother to produce new chromosomes; a5: Mutation: Perform a mutation operation on the new chromosome to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 until the fitness of chromosomes in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the random value of the control parameter represented by the corresponding chromosome as the correction value of the control parameter.

8. The combustion control system for a silicon steel annealing furnace according to claim 7, characterized in that, The formula for calculating the pre-constructed fitness function is as follows: In the formula: Fitness is fitness, GS is flue gas coefficient, GS0 is the reference value of flue gas coefficient, WD is the actual annealing temperature, WD0 is the target annealing temperature, and E(x1) is the fuel consumption.

9. A method for controlling combustion in a silicon steel annealing furnace, characterized in that, It is implemented based on a silicon steel annealing furnace combustion control system according to any one of claims 1 to 8, the method comprising: When the M burners in the annealing furnace are burning the silicon steel to be processed according to the ideal values ​​of the control parameters, and incomplete combustion is found in the furnace, the actual values ​​of the burners in the furnace with respect to the control parameters are obtained. The control parameters include gas flow rate and combustion air flow rate, where M is a positive integer. The ideal and actual values ​​of the control parameters are compared numerically, and the aged burners are selected from the M burners in the furnace based on the comparison results. The actual values ​​of the aged burners with respect to the control parameters are then extracted. A pre-configured genetic algorithm is used to correct the actual values ​​of the control parameters of the aging burner, resulting in corrected values ​​of the control parameters of the aging burner. The control parameters of the aging burner in the furnace are then adjusted based on the corrected values.

Images