A heating furnace energy consumption accounting method based on an XGBoost algorithm

Abstract

The application discloses a heating furnace energy consumption accounting method based on an XGBoost algorithm, which comprises the following steps: determining the influencing factors of slab energy consumption, and determining the weight coefficients of the factors based on the XGBoost algorithm; obtaining the material information of slabs in the heating furnace; dividing the time period during which the slabs stay in the heating furnace into multiple energy consumption accumulation sections, and calculating the energy consumption of each accumulation section; calculating the single-slab apportioning coefficients of each influencing factor in each accumulation section according to the material information in the accumulation section; taking the single slab as the energy consumption accounting object, and calculating the energy consumption of each slab based on the weight coefficients of the influencing factors, the single-slab apportioning coefficients of the influencing factors and the energy consumption of each accumulation section. The application can consider the influence of the slab differentiation factors such as the time in the furnace, the steel charging temperature, the slab specification size and the steel tapping temperature on the single-slab energy consumption accounting, and realizes the accurate accounting of the slab energy consumption in the heating furnace.

Description

Technical Field

[0001] This invention relates to the field of hot rolling production technology, and in particular to a method for calculating the energy consumption of heating furnaces based on the XGBoost algorithm. Background Technology

[0002] As a pillar industry of the national economy, the steel industry is a traditionally high-energy-consuming and high-polluting sector, heavily reliant on the consumption of energy sources such as water, electricity, gas, and steam during its production process. The steel industry consumes approximately 5% of global energy and accounts for about 7% of anthropogenic carbon dioxide emissions. With economic and social development, especially under the backdrop of carbon neutrality, steel companies face increasing pressure from energy costs and environmental constraints in meeting carbon emission standards. Therefore, accurate accounting and meticulous control of energy consumption have become key aspects of achieving continuous and effective energy conservation and emission reduction, realizing green manufacturing, and achieving sustainable development for steel companies.

[0003] As a crucial piece of equipment in the hot rolling process, the heating furnace accounts for 60%-70% of the total energy consumption. Current energy-saving research on heating furnaces primarily focuses on improving combustion process control to increase accuracy and enhancing thermal efficiency through mathematical modeling. However, individual slab variations, furnace dwell time, and charging temperature also significantly impact slab energy consumption. Therefore, accurately calculating the heating energy consumption of a single slab and using this data to develop production plans and energy consumption management and evaluation mechanisms is of great guiding significance for achieving further energy conservation and emission reduction.

[0004] A search revealed a patent application with publication number CN111159919A, which discloses a method for measuring the energy consumption allocation of a heating furnace. This method divides the time a slab spends in the furnace into multiple accumulation segments for energy consumption accumulation, performs discrete processing of the energy consumption accumulation, and calculates the energy consumption of a single slab. The calculation considers factors such as slab heat absorption and heat loss allocation. However, this application does not truly address how to consider the impact of slab-specific factors such as furnace dwell time, charging temperature, slab dimensions, and tapping temperature on the energy consumption calculation of a single slab.

[0005] Patent application CN108646637A discloses an energy-saving intelligent control system for heating furnaces. Its technical solution mainly focuses on strengthening energy consumption monitoring and improving automatic control of the heating furnace to reduce energy consumption. It consists of a power supply unit, a programmable logic controller, a video acquisition and storage unit, a network switching unit, a fiber optic transceiver, a power distribution wiring unit, a human-machine interaction unit, an energy-saving intelligent control system, and a client application. While this technical solution can optimize heating effects and improve heating quality, the energy-saving analysis of individual slabs within the furnace is a crucial way to achieve overall furnace energy conservation, which this application does not truly address.

[0006] Patent CN108062583A discloses a method for optimizing process parameters of heating furnaces for energy conservation and emission reduction. This method obtains the optimal process parameters of the heating furnace by constructing an energy consumption model of the heating furnace and configuring the range of process parameters. The algorithm is simple and reliable. However, this application does not truly address how to consider the impact of slab differentiation factors such as furnace time, charging temperature, slab size, and tapping temperature on the energy consumption calculation of a single slab.

[0007] In summary, existing technologies mainly focus on reducing energy consumption by strengthening the automatic control of heating furnaces, constructing mathematical models, and optimizing process parameters. However, they do not address how to consider the impact of slab differentiation factors such as furnace time, charging temperature, slab size, and tapping temperature on the energy consumption calculation of a single slab. Summary of the Invention

[0008] This invention provides a heating furnace energy consumption calculation method based on the XGBoost algorithm to solve the technical problems of inaccurate calculation of energy consumption and cost of producing a single slab in the existing heating furnace slab production process, which cannot reflect the impact of billet material, specifications and dimensions, charging temperature and tapping temperature on heating furnace energy consumption. It enables precise calculation of the energy consumption of a single billet under different factors during the heating furnace production process.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] On the one hand, this invention provides a method for calculating the energy consumption of a heating furnace based on the XGBoost algorithm, including:

[0011] The factors affecting slab energy consumption were identified, and the weight coefficients of each factor were determined based on the XGBoost algorithm.

[0012] Using a preset time as the starting point for calculation, material information of slabs in actual production within the heating furnace is obtained; wherein, the material information includes: slab number and the values ​​of each of the influencing factors corresponding to the slab;

[0013] The time period during which the slab stays in the heating furnace is divided into multiple energy consumption accumulation segments. The energy consumption of the slab in the heating furnace is discretized, and the energy consumption of each accumulation segment is calculated.

[0014] Calculate the single slab allocation coefficient for each influencing factor within each accumulation segment based on the material information within each accumulation segment;

[0015] Taking a single slab as the energy consumption accounting object, the energy consumption of each slab is calculated based on the weight coefficient of each influencing factor corresponding to the slab, the single slab allocation coefficient of each influencing factor, and the energy consumption of each cumulative segment.

[0016] Furthermore, the influencing factors include furnace time, charging temperature, tapping temperature, and slab specifications and dimensions; wherein, slab specifications and dimensions include slab length, slab width, slab thickness, and slab weight.

[0017] Furthermore, the determination of the weight coefficients of each influencing factor based on the XGBoost algorithm includes:

[0018] Obtain historical production sample data of the heating furnace that includes the aforementioned influencing factors;

[0019] Using slab energy consumption as the target parameter, an XGBoost mathematical model is established. The sample data is imported into the XGBoost mathematical model for sample training. The importance and corresponding predicted value of each influencing factor are obtained through the feature_importance_ function in the model, and the weight coefficient of each influencing factor is obtained after normalization.

[0020] Furthermore, before importing the sample data into the XGBoost mathematical model for sample training, the method further includes: using a box plot method to remove outlier data from the sample data.

[0021] Furthermore, when using the box plot method to remove outliers from the sample data, the sample data is divided into three quarter points based on its distribution: the lower quarter point P1, the middle quarter point MD, and the upper quarter point P3. The upper extreme outlier is P3 + 3IPR, and the lower extreme outlier is P1 - 3IPR, where IPR represents the box height. Data exceeding the upper or lower extreme outlier is considered outlier.

[0022] Furthermore, the process of dividing the time the slab spends in the heating furnace into multiple energy consumption accumulation segments, discretizing the energy consumption of the slab in the heating furnace, and calculating the energy consumption of each accumulation segment includes:

[0023] Each time period with a constant number of slabs in the heating furnace is recorded as an energy consumption accumulation segment. The energy consumption of the slabs in the heating furnace is discretized, and the energy consumption of each accumulation segment is calculated using the following formula:

[0024]

[0025] Where, q i Let be the energy consumption of the i-th accumulation segment, and n be the number of sampling periods in the i-th accumulation segment. EQ i,j Δt is the instantaneous flow rate measurement of fuel in the j-th sampling period within the i-th cumulative segment, where Δt is the sampling period time.

[0026] Furthermore, the calculation of the single slab allocation coefficient for each influencing factor within each accumulation segment based on material information within each accumulation segment includes:

[0027] The furnace time allocation coefficient λk for the kth slab is calculated using the following formula. time :

[0028]

[0029] Among them, Time k Let s be the furnace time of the kth slab, and s be the number of slabs in the furnace within the current cumulative segment; the furnace temperature distribution coefficient λk of the kth slab is calculated using the following formula. intep :

[0030]

[0031] Wherein, Δintep k The furnace inlet temperature difference, Δintep k =Standard furnace inlet temperature - Actual furnace inlet temperature;

[0032] The width allocation coefficient λk of the k-th slab is calculated using the following formula. width :

[0033]

[0034] Among them, width k Let be the width of the k-th slab.

[0035] The thickness distribution coefficient λk of the k-th slab is calculated using the following formula. thick :

[0036]

[0037] Thick k Let be the thickness of the k-th slab.

[0038] The length allocation coefficient λk of the kth slab is calculated using the following formula. length :

[0039]

[0040] Where, length k Let k be the length of the kth slab.

[0041] The weight allocation coefficient λk of the k-th slab is calculated using the following formula. weight :

[0042]

[0043] Where, weight k Let be the weight of the k-th slab.

[0044] The furnace temperature distribution coefficient λk of the kth slab is calculated using the following formula. extep :

[0045]

[0046] Wherein, Δextep k Δextep is the temperature difference at the furnace outlet. k = Actual tapping temperature - Target tapping temperature.

[0047] Furthermore, the formula for calculating the energy consumption of each slab is as follows:

[0048]

[0049] Among them, Q k Let ε represent the energy consumption of the k-th slab, m represent the number of cumulative energy consumption segments for the k-th slab, and ε represent the energy consumption of the slab. time ε represents the weighting coefficient for furnace time. intep ε represents the weighting coefficient for the furnace feed temperature. width ε represents the weighting factor for the slab width. thick ε represents the weighting factor for slab thickness. length ε represents the weighting coefficient for the slab length. weight ε represents the weighting factor of the slab weight. extep The weighting coefficient represents the temperature at which the furnace exits.

[0050] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.

[0051] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction that is loaded and executed by a processor to implement the above-described method.

[0052] The beneficial effects of the technical solution provided by this invention include at least the following:

[0053] 1. The heating furnace energy consumption calculation method based on the XGBoost algorithm provided by this invention can comprehensively consider the influence of multiple factors such as billet specifications, furnace time, charging temperature, and tapping temperature on heating furnace energy consumption, and realize the precise calculation of individual billet energy consumption under different factor conditions during the heating furnace production process.

[0054] 2. The heating furnace energy consumption calculation method based on the XGBoost algorithm provided by this invention helps enterprises formulate production plans, establish energy consumption management and evaluation mechanisms, and achieve refined management of heating furnace energy. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of the execution flow of the furnace energy consumption calculation method based on the XGBoost algorithm provided in the embodiments of the present invention;

[0057] Figure 2 This is a schematic diagram of the box plot model provided in an embodiment of the present invention;

[0058] Figure 3 This is a bar chart of the weight coefficients of energy consumption influencing factors provided in the embodiments of the present invention;

[0059] Figure 4 This is a schematic diagram of the energy consumption accumulation process of the heating furnace provided in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0061] First Embodiment

[0062] This embodiment provides a heating furnace energy consumption calculation method based on the XGBoost algorithm. This method can take into account the influence of multiple factors and accurately calculate the gas consumption for heating slabs in the heating furnace.

[0063] Specifically, the execution flow of the method in this embodiment is as follows: Figure 1 As shown, it includes the following steps:

[0064] S1. Determine the factors affecting the differentiated energy consumption of slabs, obtain production sample data of the heating furnace, and determine the weight coefficients of the factors affecting the differentiated fuel consumption of each slab based on the XGBoost algorithm.

[0065] It should be noted that, in this embodiment, based on the actual on-site conditions, the furnace time, charging temperature, tapping temperature, length, width, thickness, and weight of the billet are identified as important factors affecting billet energy consumption.

[0066] The process of determining the weight coefficients of the factors affecting the differentiated fuel consumption of each slab based on the XGBoost algorithm is as follows:

[0067] S11, Obtain historical production sample data of the heating furnace that includes the above-mentioned influencing factors;

[0068] S12, using slab energy consumption as the target parameter, an XGBoost mathematical model is established; sample data is imported into the XGBoost mathematical model for sample training; the importance of each influencing factor and its corresponding predicted value can be obtained through the feature_importance_ function in the model, and after normalization, the furnace time weight coefficient ε is obtained. time Furnace entry temperature weighting coefficient ε intep Width weighting coefficient ε width Thickness weighting coefficient ε thick Length weighting coefficient ε length Weighting coefficient ε weight And the weighting coefficient ε for furnace exit temperature extep .

[0069] It should be noted that, before importing the sample data into the XGBoost mathematical model for training, to avoid model distortion caused by outlier data, this embodiment uses a box plot method to remove outlier data from the sample data. Specifically, as follows... Figure 2 As shown, when using the box plot method to remove outliers from the sample data, this embodiment divides the sample data into three quarter points based on the distribution of the sample data: the lower quarter point P1, the middle quarter point MD, and the upper quarter point P3. The upper extreme outlier point = P3 + 3IPR, and the lower extreme outlier point = P1 - 3IPR, where IPR represents the height of the box. When removing outliers from the sample data, data exceeding the upper or lower extreme outlier point are considered outliers.

[0070] This embodiment acquires 500 sets of data from a steel rolling mill, removes 67 outlier sets, leaving 433 sets. The sample set is imported into the XGBoost algorithm, and the XGBRegressor function is used to train the model, adjusting the model parameters to build the model. The XGBoost model parameters are shown in Table 1, and the feature parameters selected based on actual production conditions are shown in Table 2.

[0071] Table 1 XGBoost Model Parameter Table

[0072] Formula parameters Model parameters meaning numerical values γ gamma Regularization parameters 0.1 λ lambda Regularization parameters 1 M n_estimator Number of trees 200 T T Number of leaf nodes 32 max_depth Maximum tree depth 6 eta Shrinking step size 0.3 objective Define loss function reg:linear Subsample Random sampling ratio 0.9

[0073] Table 2 Feature Parameters

[0074] Feature fields meaning numerical values CHARGETEMP Slab temperature upon entering the furnace / ℃ 0-800 SLABTHICK Slab thickness / mm 220-230 SLABWIDTH Slab width / mm 1000-1420 SLABLENGTH Actual furnace exit temperature of slab / ℃ 4000-7000 SLABWEIGHT Slab weight / kg 8000-16000 DCHG_TEMP 1220-1244 DIFFTIME Furnace time 190-245

[0075] After the model is built, the importance of each feature parameter and its corresponding predicted value can be obtained through the feature_importance_ function in the model. After normalization, the weight coefficients of each influencing factor can be obtained, such as... Figure 3 As shown.

[0076] S2, using a preset time as the calculation starting point, obtains material information of the slab in actual production in the heating furnace;

[0077] Specifically, in this embodiment, at the starting point of the calculation, the billet number, specifications, tapping temperature, charging temperature, and furnace time of the steel billet are obtained through the material tracking system.

[0078] S3, divide the time period of the slab staying in the heating furnace into multiple energy consumption accumulation segments, perform discretization processing of the energy consumption of the slab in the heating furnace, and calculate the energy consumption of each accumulation segment.

[0079] Specifically, such as Figure 4 As shown, in this embodiment, each time period in which the number of steel billets in the heating furnace remains constant is recorded as an energy consumption accumulation segment. Thus, the time period in which the steel billets remain in the heating furnace is divided into m energy consumption accumulation segments. Discrete energy consumption accumulation is then performed, and the energy consumption of each energy consumption accumulation segment is calculated according to the following formula:

[0080]

[0081] Where, q i Let be the energy consumption of the i-th energy accumulation segment, in kgce, and n be the number of sampling periods for the i-th accumulation segment. EQ i,j Δt is the instantaneous flow rate of fuel in the j-th sampling period of the i-th accumulation segment, in kgce / h, where Δt is the sampling period time and j is the j-th sampling in the i-th energy consumption accumulation segment.

[0082] S4, based on the material information in each energy consumption accumulation segment, calculate the single slab allocation coefficient of each influencing factor in each energy consumption accumulation segment.

[0083] Specifically, the calculation method for the single slab allocation coefficient of each influencing factor is as follows:

[0084] The furnace time allocation coefficient for the kth slab is calculated using the following formula:

[0085]

[0086] Among them, Time k λk represents the furnace time of the kth slab in minutes. time The furnace time allocation coefficient is s, where s is the number of slabs in the furnace within the current cumulative segment;

[0087] The furnace temperature distribution coefficient for the kth slab is calculated using the following formula:

[0088]

[0089] Wherein, Δintep k The furnace temperature difference is expressed in °C, Δintep.k =Standard furnace inlet temperature - Actual furnace inlet temperature; λk intep This is the furnace temperature distribution coefficient;

[0090] The width allocation coefficient for the k-th slab is calculated using the following formula:

[0091]

[0092] Among them, width k λk represents the width of the k-th slab, in mm. width Let be the width allocation factor for the steel billet; the thickness allocation factor for the k-th slab is calculated using the following formula:

[0093]

[0094] Thick k λk represents the thickness of the k-th slab, in mm. thick The thickness allocation factor for the steel billet is given; the length allocation factor for the k-th slab is calculated using the following formula:

[0095]

[0096] Where, length k λk represents the length of the k-th slab, in mm. length Let be the billet length allocation factor; the weight allocation factor for the kth slab is calculated using the following formula:

[0097]

[0098] Where, weight k λk represents the weight of the k-th slab, in kg. weight The weight allocation factor for the steel billet is given; the furnace temperature allocation factor λk for the kth slab is calculated using the following formula. extep :

[0099]

[0100] Where, λk extep Δextep is the furnace temperature distribution coefficient. k The temperature difference at the furnace exit is expressed in °C, Δextep. k = Actual tapping temperature - Target tapping temperature.

[0101] In the above calculation formulas, s represents the number of steel billets in the furnace within a certain cumulative segment.

[0102] S5 takes a single slab as the energy consumption accounting object, and collects and calculates the fuel consumption of each slab based on the weight coefficient of each influencing factor, the single slab allocation coefficient of each influencing factor, and the cumulative energy consumption of the slab in the furnace.

[0103] Specifically, in this embodiment, the k-th billet within the i-th cumulative segment is taken as the calculation object. Taking into account the weight coefficients of each influencing factor and the single billet allocation coefficient of each influencing factor, the fuel consumption of the k-th billet within the i-th cumulative segment is calculated. The total fuel consumption of the k-th billet in the furnace is obtained by summing the m cumulative segments during the k-th billet's time in the furnace. The specific calculation formula is as follows:

[0104]

[0105] Among them, Q k Let m represent the energy consumption of the k-th slab, and m represent the number of cumulative energy consumption segments of the k-th slab.

[0106] In summary, the heating furnace energy consumption calculation method of this embodiment obtains a large amount of historical data on heating furnace gas consumption through a big data platform. By establishing an XGBoost mathematical model, the samples are imported into the model for training to obtain the importance and corresponding weight coefficients of each feature parameter. Based on a comprehensive consideration of the influence of multiple factors and the billet allocation coefficient, the gas consumption is discretized and accumulated using a single billet as the calculation object. This overcomes the inaccuracy of existing heating furnace production processes' energy consumption and cost calculation algorithms for producing a single billet, which cannot reflect the influence of billet material, specifications, charging temperature, and tapping temperature on heating furnace energy consumption. This method achieves precise calculation of individual billet energy consumption under different factor conditions during heating furnace production.

[0107] Second Embodiment

[0108] This embodiment provides an electronic device, which includes a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment.

[0109] The electronic device can vary considerably depending on its configuration or performance, and may include one or more processors (central processing units, CPUs) and one or more memories, wherein the memories store at least one instruction that is loaded by the processor and executed in accordance with the above method.

[0110] Third Embodiment

[0111] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0112] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0113] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0114] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0115] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0116] Finally, it should be noted that the above description represents a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A method for calculating the energy consumption of a heating furnace based on the XGBoost algorithm, characterized in that, include: The factors affecting slab energy consumption were identified, and the weight coefficients of each factor were determined based on the XGBoost algorithm. Using a preset time as the starting point for calculation, material information of slabs in actual production within the heating furnace is obtained; wherein, the material information includes: slab number and the values ​​of each of the influencing factors corresponding to the slab; The time period during which the slab stays in the heating furnace is divided into multiple energy consumption accumulation segments. The energy consumption of the slab in the heating furnace is discretized, and the energy consumption of each accumulation segment is calculated. Calculate the single slab allocation coefficient for each influencing factor within each accumulation segment based on the material information within each accumulation segment; Taking a single slab as the energy consumption accounting object, the energy consumption of each slab is calculated based on the weight coefficient of each influencing factor corresponding to the slab, the single slab allocation coefficient of each influencing factor, and the energy consumption of each cumulative segment. The influencing factors include: furnace time, charging temperature, tapping temperature, and slab dimensions; wherein, the slab dimensions include: slab length, slab width, slab thickness, and slab weight. The process of dividing the time the slab spends in the heating furnace into multiple energy consumption accumulation segments, discretizing the energy consumption of the slab in the heating furnace, and calculating the energy consumption of each accumulation segment includes: Each time period with a constant number of slabs in the heating furnace is recorded as an energy consumption accumulation segment. The energy consumption of the slabs in the heating furnace is discretized, and the energy consumption of each accumulation segment is calculated using the following formula: ； in, For the first i Energy consumption of each cumulative segment For the first i The number of sampling periods in each cumulative segment For the first i In the cumulative segment, the first j Instantaneous flow rate measurement of fuel within each sampling period The sampling period time; The calculation of the single slab allocation coefficient for each influencing factor within each accumulation segment based on material information within each accumulation segment includes: The first is calculated using the following formula. k Furnace time allocation coefficient for slab billets : ； in, For the first k The furnace dwell time of the slab, where s is the number of slabs in the furnace within the current cumulative segment; The first is calculated using the following formula. k Furnace temperature distribution coefficient for slab billets : ； in, For the temperature difference before entering the furnace, ; The first is calculated using the following formula. k Width allocation coefficient of slab blank : ； in, For the first k The width of the slab blank; The first is calculated using the following formula. k Thickness distribution coefficient of slab blank : ； in, For the first k The thickness of the slab blank; The first is calculated using the following formula. k Length allocation coefficient of slab blank : ； in, For the first k The length of the slab blank; The weight allocation coefficient of the kth slab is calculated using the following formula. : ； in, For the first k The weight of the slab blank; The first is calculated using the following formula. k Furnace temperature distribution coefficient for slab billets : ； in, For the temperature difference when exiting the furnace, ; The formula for calculating the energy consumption of each slab is as follows: ； in, Indicates the first k Energy consumption of slab blank, m represents the energy consumption of the first slab blank. k The number of energy consumption accumulation sections for slab blanks. This represents the weighting coefficient for furnace time. The weighting coefficient representing the furnace entry temperature. The weighting coefficient represents the width of the slab. The weighting coefficient representing the slab thickness. The weighting coefficient representing the slab length. The weighting coefficient representing the weight of the slab. The weighting coefficient represents the temperature at which the furnace exits.

2. The furnace energy consumption calculation method based on the XGBoost algorithm as described in claim 1, characterized in that, The determination of the weight coefficients of each influencing factor based on the XGBoost algorithm includes: Obtain historical production sample data of the heating furnace that includes the aforementioned influencing factors; Using slab energy consumption as the target parameter, an XGBoost mathematical model is established. The sample data is imported into the XGBoost mathematical model for sample training. The importance and corresponding predicted value of each influencing factor are obtained through the feature_importance_ function in the model, and the weight coefficient of each influencing factor is obtained after normalization.

3. The furnace energy consumption calculation method based on the XGBoost algorithm as described in claim 2, characterized in that, Before importing the sample data into the XGBoost mathematical model for sample training, the method further includes: using a box plot method to remove outlier data from the sample data.

4. The furnace energy consumption calculation method based on the XGBoost algorithm as described in claim 3, characterized in that, When using the box plot method to remove outliers from the sample data, the sample data is divided into three quarter points based on its distribution: the lower quarter point P1, the middle quarter point MD, and the upper quarter point P3. The upper extreme outlier is P3 + 3IPR, and the lower extreme outlier is P1 - 3IPR, where IPR represents the box height. Data exceeding the upper or lower extreme outlier is considered outlier.

Images