Method for low-carbon smelting of multi-source complex copper ore by using sulfo-carbon

Abstract

The invention provides a sulfur-substituted carbon low-carbon smelting method for multi-source complex copper ore, and belongs to the technical field of metallurgy, the method comprises the following steps: aiming at a multi-source copper concentrate phase to be fed into a furnace, constructing a batching model taking the Cu element content as a target function and the S-free phase content as a constraint condition, and calculating the components and content of the fed phase through a multi-target algorithm; performing material balance and heat balance prediction by using an XGBoost prediction model according to the in-furnace phase components and content; and a heat balance result is analyzed and fed back in real time, the real-time feedback operation is dynamically adjusted, and the low-carbon smelting optimal batching scheme with thiocarbon is obtained. According to the method, machine learning, an intelligent algorithm and a batching scheme are combined, the smelting process is simulated, carbonaceous fuel combustion is accurately mastered, the carbon emission is controlled, and compared with a traditional technology, the carbon emission is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of metallurgy, and in particular relates to a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon. Background Art

[0002] The existing copper smelting batching technology has significant defects: the manual experience method has inherent drawbacks such as poor ratio accuracy and low stability; although machine learning and intelligent algorithms have improved batching accuracy and production efficiency, they are limited by a single front-end static batching mode, which can neither build a dynamic feedback mechanism for smelting process parameters nor lead to inaccurate estimates of fuel addition, resulting in redundant carbon emissions. The fundamental crux of the problem lies in the fact that the existing technical system has failed to establish a closed-loop control batching model of raw material adaptation-smelting balance-feedback regulation, resulting in the thermal energy potential of the high-sulfur phase not being effectively tapped and over-reliance on heat compensation of carbonaceous fuels. For this reason, it is urgent to develop a dynamic batching method for low-carbon smelting using sulfur instead of carbon. By establishing a batching model of furnace batching-balance prediction-thermal balance feedback-dynamic adjustment, the source reduction of carbonaceous fuels can be achieved while ensuring smelting heat balance, thereby breaking through the bottleneck of traditional smelting process technology. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon.

[0004] To implement the above technology, the specific steps are as follows:

[0005] S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm;

[0006] The expression of the phase composition of multi-source copper concentrate is as follows:

[0007]

[0008] Where, M is the sum of all phase contents; M i represents the content of the i-th S-containing phase; M j represents the content of the jth sulfur-free phase; l represents the total number of sulfur-containing substances; n represents the total number of sulfur-free substances;

[0009] The expression with Cu element content as the target is constructed as follows:

[0010]

[0011] In the formula, m Cu is the total content of element Cu in all phases; a i is the content of element Cu in the i-th S-containing phase; b jThe content of element Cu in the jth S-free phase;

[0012] The constraint expressions are as follows:

[0013]

[0014] Where, d j is the limit value of the content of the j-th phase that does not contain S; c is the limit value of the element Cu content in all phases;

[0015] Initialize the multi-objective gray wolf algorithm, where the initial parameters include: maximum number of iterations, number of gray wolves, variable dimension (dim), set search upper and lower spaces, initialize position, initialize speed, set target conditions, and set constraints;

[0016] The phase and content of the copper concentrate before entering the furnace are input into the initialized multi-objective grey wolf algorithm to obtain the phase and content of the copper concentrate entering the furnace.

[0017] S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results;

[0018] The copper concentrate phase and content obtained by S1 are input into the initialized XGBoost prediction model to obtain the material balance prediction result; wherein, the parameters of the initialized XGBoost prediction model include: the number of trees (n_estimators); learning rate (learning_rate); maximum depth of a single tree (max_depth); random sampling ratio of samples (subsample); random sampling ratio of features (colsample_bytree); minimum loss reduction threshold for node splitting (gamma); L1 regularization term (alpha), default 0; L2 regularization term (lambda), default 1 and objective function (objective);

[0019] Based on the material balance prediction results and the Gibbs free energy of chemical reactions in the material balance smelting process, the smelting heat balance is predicted;

[0020] The XGBoost prediction model achieves prediction by constructing a loss function and minimizing it;

[0021] The loss function expression is as follows:

[0022] L(y,f)=(yf) 2

[0023] Where y is the predicted value of the model and f is the actual label.

[0024] S3, performing real-time feedback operation on the thermal balance prediction results;

[0025] The real-time feedback operation is: by judging whether the heat balance prediction result meets the expected conditions, if not, the copper concentrate phase and content obtained by S2 entering the furnace are optimized and adjusted using the method of S1;

[0026] The expected conditions include: whether the total heat income of the process is greater than the total heat expenditure of the smelting process and whether carbonaceous fuel is added to provide heat;

[0027] The expected conditional expressions are as follows:

[0028] Q I =Q S +Q FS +Q C +Q T

[0029] Q I ≥Q O

[0030] In the formula, Q I is the total heat income of the smelting process; Q S Q is the total heat input and output of the sulfur-containing phase reaction during the smelting process; FS Q is the total heat output of the sulfur-free phase reaction during the smelting process; C Q is the heat of combustion of carbonaceous fuel; T Other heat input during the smelting process; Q O It is the total heat expenditure of the smelting process.

[0031] S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon;

[0032] The optimal batching condition for low-carbon smelting with sulfur replacing carbon is expressed as follows:

[0033] r 1 M 1 +r 2 M 1 +…+r l M l +Q FS +minQ C +Q T ≥Q O

[0034] Where M l Indicates the percentage of the total content of the first type of sulfur; r l Indicates the total amount of the first type of sulfur corresponding to the heat released during the smelting process; minQ C It means that the combustion of carbonaceous fuel provides the least heat;

[0035] That is, when the total heat income of the smelting process is greater than or equal to the total heat expenditure of the smelting process, the heat released by smelting the sulfide ore is used to adjust the percentage of the sulfur-containing phase in the phase, increase the sulfur-containing phase and replace the carbonaceous fuel in the raw material, thereby generating the optimal batching scheme in which sulfur is used instead of carbon to reduce the addition of carbonaceous fuel.

[0036] A system for low-carbon smelting of multi-source complex copper ore using sulfur instead of carbon, comprising: a phase batching module, a smelting balance prediction module, a real-time feedback module and a dynamic adjustment module;

[0037] The phase batching module is used to perform:

[0038] S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm;

[0039] The smelting balance prediction module is used to perform:

[0040] S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results;

[0041] The real-time feedback module is used to perform:

[0042] S3, performing real-time feedback operation on the thermal balance prediction results;

[0043] The dynamic adjustment module is used to perform:

[0044] S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a low-carbon smelting method for multi-source complex copper ores using sulfur instead of carbon.

[0046] Beneficial effects of the present invention:

[0047] 1. Closed-loop dynamic control mechanism: Compared with traditional technologies, the present invention breaks through the traditional static batching mode and constructs a closed-loop control system of "furnace batching-balance prediction-heat balance feedback-dynamic regulation". By monitoring the heat balance and fuel addition during the smelting process, the batching ratio and fuel addition amount are dynamically adjusted to achieve an adjustable closed-loop batching mechanism.

[0048] 2. Synergistic substitution effect of sulfur for carbon: quantitative analysis of the heat release of sulfide phase oxidation, by maximizing the utilization of sulfide phase (such as CuFeS 2 , FeS 2)’s oxidation thermal effect, improves the contribution of sulfur thermal conversion, and significantly reduces the amount of carbonaceous fuels such as pulverized coal.

[0049] 3. Combined with intelligent algorithms and machine learning: perform large amounts of data processing and calculation in a short period of time, handle multi-objective optimization problems through intelligent algorithms, and quickly derive the best batching solution; the system uses a sulfur-carbon dynamic calculation module that can adapt to a variety of different furnace processes, and uses machine learning to perform heat balance prediction models, providing a scalable technical path for the low-carbon transformation of smelting enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon according to the present invention;

[0051] Figure 2 This is the system interface diagram for low-carbon smelting using sulfur instead of carbon. DETAILED DESCRIPTION

[0052] In order to better illustrate the purpose, technical solutions and advantages of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, a low-carbon smelting method of multi-source complex copper ore using sulfur instead of carbon comprises the following steps:

[0054] S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm;

[0055] The expression of the phase composition of multi-source copper concentrate is as follows:

[0056]

[0057] Where, M is the sum of all phase contents; M i represents the content of the i-th S-containing phase; M j represents the content of the jth sulfur-free phase; l represents the total number of sulfur-containing substances; n represents the total number of sulfur-free substances;

[0058] The expression with Cu element content as the target is constructed as follows:

[0059]

[0060] In the formula, m Cuis the total content of element Cu in all phases; a i is the content of element Cu in the i-th S-containing phase; b j The content of element Cu in the jth S-free phase;

[0061] The constraint expressions are as follows:

[0062]

[0063] Where, d j is the limit value of the content of the j-th phase that does not contain S; c is the limit value of the element Cu content in all phases;

[0064] In this embodiment, d j set to 4%; l to 7; n to 3; c to 30%;

[0065] Initialize the multi-objective gray wolf algorithm, where the initial parameters include: maximum number of iterations, number of gray wolves, variable dimension (dim), set search upper and lower spaces, initialize position, initialize speed, set target conditions, and set constraints;

[0066] In this embodiment, the maximum number of iterations is set to 100; the number of gray wolves is set to 50; the variable dimension dim is set to 10;

[0067] The search space is set to:

[0068] lower_bound=-10*ones(1,dim);

[0069] upper_bound=10*ones(1,dim);

[0070] In the formula, lower_bound represents the lower bound; upper_bound represents the upper bound; ones(1,dim) represents a vector of all 1s with a length of dim;

[0071] That is, the code for searching the upper and lower spaces is: [-10*ones(1,dim); 10*ones(1,dim)];

[0072] The initialization position setting uses the random initialization method, the code is:

[0073] wolves_pos=lower_bound+(upper_bound-lower_bound).*rand(n_wolves,dim);

[0074] Among them, n_wolves is the number of gray wolves; rand(n_wolves,dim) generates a random matrix of size n_wolves,dim;

[0075] The initialization speed code is:

[0076] wolves_vel=zeros(n_wolves,dim);

[0077] This means setting the initial speed of all gray wolves to zero;

[0078] The target conditions are:

[0079] The constraints are:

[0080] The phase and content of the copper concentrate before entering the furnace are input into the initialized multi-objective grey wolf algorithm to obtain the phase and content of the copper concentrate entering the furnace; the phase and content of the copper concentrate before entering the furnace are input as shown in Table 1, and the phase and content of the copper concentrate entering the furnace are shown in Table 2;

[0081] Table 1: Copper concentrate phase and content before entering the furnace

[0082]

[0083] Table 2: Phase and content of copper concentrate entering the furnace

[0084]

[0085] S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results;

[0086] The copper concentrate phase and content obtained by S1 are input into the initialized XGBoost prediction model to obtain the material balance prediction result; wherein, the parameters of the initialized XGBoost prediction model include: the number of trees (n_estimators); learning rate (learning_rate); maximum depth of a single tree (max_depth); random sampling ratio of samples (subsample); random sampling ratio of features (colsample_bytree); minimum loss reduction threshold for node splitting (gamma); L1 regularization term (alpha), default 0; L2 regularization term (lambda), default 1 and objective function (objective);

[0087] In this embodiment, n_estimators = 100; learning_rate = 0.1; max_depth = 3; subsample = 0.8; colsample_bytree = 0.8; gamma = 0; alpha = 0; lambda = 1; objective = 'reg: squarederror' (the task type of the objective function is mean square error);

[0088] Based on the material balance prediction results and the Gibbs free energy of chemical reactions in the material balance smelting process, the smelting heat balance is predicted;

[0089] The XGBoost prediction model achieves prediction by constructing a loss function and minimizing it;

[0090] The loss function expression is as follows:

[0091] L(y,f)=(yf) 2

[0092] In the formula, y is the predicted value of the model, and f is the actual label;

[0093] The material balance prediction results and heat balance prediction results are shown in Table 3:

[0094] Table 3: Material balance and heat balance prediction results

[0095]

[0096] S3, performing real-time feedback operation on the thermal balance prediction results;

[0097] The real-time feedback operation is: by judging whether the heat balance prediction result meets the expected conditions, if not, the copper concentrate phase and content obtained by S2 entering the furnace are optimized and adjusted using the method of S1;

[0098] The expected conditions include: whether the total heat income of the process is greater than the total heat expenditure of the smelting process and whether carbonaceous fuel is added to provide heat;

[0099] The expected conditional expressions are as follows:

[0100] Q I =Q S +Q FS +Q C +Q T

[0101] Q I ≥Q O

[0102] In the formula, Q I is the total heat income of the smelting process; QS Q is the total heat input and output of the sulfur-containing phase reaction during the smelting process; FS Q is the total heat output of the sulfur-free phase reaction during the smelting process; C Q is the heat of combustion of carbonaceous fuel; T Other heat input during the smelting process; Q O It is the total heat expenditure of the smelting process.

[0103] S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon;

[0104] The optimal batching condition for low-carbon smelting with sulfur replacing carbon is expressed as follows:

[0105] r 1 M 1 +r 2 M 1 +…+r l M l +Q FS +minQ C +Q T ≥Q O

[0106] Where M l Indicates the percentage of the total content of the first type of sulfur; r l Indicates the total amount of the first type of sulfur corresponding to the heat released during the smelting process; minQ C It means that the combustion of carbonaceous fuel provides the least heat;

[0107] That is, when the total heat income of the smelting process is greater than or equal to the total heat expenditure of the smelting process, the heat released by smelting the sulfide ore is used to adjust the percentage of the sulfur-containing phase in the phase, increase the sulfur-containing phase and replace the carbonaceous fuel in the raw material, thereby generating the optimal batching scheme in which sulfur is used instead of carbon to reduce the addition of carbonaceous fuel.

[0108] Low carbon smelting system using sulfur instead of carbon Figure 2 As shown;

[0109] The heat absorption and release per unit mass (KJ / kg) of the phases are shown in Table 4, and the optimal batching scheme is shown in Table 5;

[0110] Table 4: Heat absorption and release per unit mass (KJ / kg) of the adjusted phase

[0111]

[0112] Table 5: Optimal ingredients

[0113] phase of matter content(%) <![CDATA[CuFeS 2 ]]> 69.344 <![CDATA[Cu 5 FeS 4 ]]> 3.12 <![CDATA[Cu 2 S]]> 2.01 <![CDATA[Cu 12 As 4 S 13 ]]> 0.416 <![CDATA[FeS 2 ]]> 16.24 FeS 1.95 ZnS 2.88 <![CDATA[CuCO 3 ·Cu(OH) 2 ]]> 0.46 <![CDATA[Cu 2 Cl(OH) 3 ]]> 0.72 <![CDATA[Fe 3 THE 4 ]]> 2.86

[0114] The obtained phase content is the optimal ingredient scheme for generating sulfur-substituted carbon to reduce the addition of carbonaceous fuel. Under this content ratio, the carbonaceous fuel is reduced from 0.31% to 0.221%, a decrease of 28.7%, which significantly reduces the use of carbonaceous fuel.

[0115] A system for low-carbon smelting of multi-source complex copper ore using sulfur instead of carbon, comprising: a phase batching module, a smelting balance prediction module, a real-time feedback module and a dynamic adjustment module;

[0116] The phase batching module is used to perform:

[0117] S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm;

[0118] The smelting balance prediction module is used to perform:

[0119] S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results;

[0120] The real-time feedback module is used to perform:

[0121] S3, performing real-time feedback operation on the thermal balance prediction results;

[0122] The dynamic adjustment module is used to perform:

[0123] S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon.

[0124] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a low-carbon smelting method for multi-source complex copper ores using sulfur instead of carbon.

[0125] Furthermore, based on the raw materials obtained by the present invention and the proposed optimization method, the differences in carbon emissions and fuel consumption between the unoptimized and optimized batching schemes are compared to further verify the low-carbon advantage of the method of the present invention.

[0126] Multiple batches of production data from a copper smelter were selected for analysis, and the specific conditions are as follows:

[0127] Processing capacity: 100 tons of copper ore / batch;

[0128] Smelting process: oxygen-enriched smelting;

[0129] Carbon emission factor: pulverized coal 2.7 tons CO 2 / ton of coal; sulfur oxidation 0.5 tons of CO 2 / ton of sulfur.

[0130] The amount of carbonaceous fuel added: before optimization: 0.5%; after optimization: 0.221%.

[0131] Carbon emissions calculations include:

[0132] 1. Sulfide carbon dioxide emissions:

[0133] The sulfur content calculation is shown in Table 6;

[0134] Table 6: Sulfur content calculation

[0135]

[0136] The calculation of carbon emissions using the optimization of the present invention and not using the optimization of the present invention is as follows:

[0137] Unoptimized solution:

[0138] 35.26 tons of sulfur × 0.5 tons of CO 2 / ton of sulfur = 17.63 tons of CO 2 ;

[0139] Optimized solution:

[0140] 34.65 tons of sulfur × 0.5 tons of CO 2 / ton of sulfur = 17.33 tons of CO 2 ;

[0141] 2. Carbon emissions from carbon fuel combustion are calculated as follows:

[0142] The calculation is based on the coal powder consumption. The coal powder consumption is calculated as follows:

[0143] Unoptimized solution:

[0144] 100 tons x 0.5% = 0.5 tons of coal;

[0145] 0.5×2.7=1.35 tons of CO 2 ;

[0146] Optimized solution:

[0147] 100 tons x 0.221% = 0.221 tons of coal;

[0148] 0.221×2.7=0.596 tons of CO 2 ;

[0149] 3. The comparison of total carbon emissions is shown in Table 7;

[0150] Table 7: Comparison of total carbon emissions

[0151]

[0152] If combined with flue gas desulfurization (desulfurization efficiency 90%), the total carbon emissions can be further reduced to:

[0153] 17.33×0.1+0.596=2.329 tons of CO 2

[0154] The optimized batching scheme reduces carbon fuel consumption by 55.9% and carbon emissions by 0.754 tons of CO by replacing carbon with sulfur and dynamically closed-loop regulation. 2 / batch; if combined with flue gas desulfurization technology (desulfurization efficiency 90%), the total carbon emissions will be 18.98 tons CO 2 Down to 2.329 tons of CO 2 / batch, the comprehensive emission reduction rate reached 87.7%, breaking through the bottleneck of high carbon emissions of traditional processes. In addition, the sulfide phase (CuFeS 2 , FeS 2 ) ratio is optimized, the heat release potential of sulfide oxidation is further tapped, replacing 55.9% of the heat of carbonaceous fuel and forming a low-carbon smelting core path; at the same time, the copper recovery rate is correspondingly improved, the content of other impurities is reduced, and the amount of waste slag generated is reduced.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present invention.

Claims

1. A low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon, characterized in that: The following steps are involved: S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm; S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results; S3, performing real-time feedback operation on the thermal balance prediction results; S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon.

2. According to claim 1, a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon is characterized by: The expression of the phase composition of the multi-source copper concentrate is as follows: Where, M is the sum of all phase contents; M i represents the content of the i-th S-containing phase; M j represents the content of the jth sulfur-free phase; l represents the total number of sulfur-containing substances; n represents the total number of sulfur-free substances; The expression for constructing the Cu element content as the target is as follows: In the formula, m Cu is the total content of element Cu in all phases; a i is the content of element Cu in the i-th S-containing phase; b j The content of element Cu in the jth S-free phase; The expression for the constraint condition of the non-S phase content is as follows: Where, d j is the limit value of the content of the jth phase that does not contain S; c is the limit value of the element Cu content in all phases.

3. According to claim 1, a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon is characterized by: According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction result. Specifically, the phase and content of the copper concentrate entering the furnace obtained in S1 are input into the initialized XGBoost prediction model to obtain the material balance prediction result; Predict the smelting heat balance based on the material balance prediction results and the Gibbs free energy of chemical reactions in the smelting process; The XGBoost prediction model achieves prediction by constructing a loss function and minimizing it; The loss function expression is as follows: L(y,f)=(y-f) 2 Where y is the predicted value of the model and f is the actual label.

4. According to claim 1, a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon is characterized by: In the real-time feedback operation of the heat balance prediction result, the real-time feedback operation is: by judging whether the heat balance prediction result meets the expected conditions, if it does not meet the expectations, the copper concentrate phase and content obtained in S2 entering the furnace are optimized and adjusted using the method of S1; The expected conditions include: whether the total heat income of the process is greater than the total heat expenditure of the smelting process and whether carbonaceous fuel is added to provide heat; The expected conditional expressions are as follows: Q I =Q S +Q FS +Q C +Q T Q I ≥Q O In the formula, Q I is the total heat income of the smelting process; Q S Q is the total heat input and output of the sulfur-containing phase reaction during the smelting process; FS Q is the total heat output of the sulfur-free phase reaction during the smelting process; C Q is the heat of combustion of carbonaceous fuel; T Other heat input during the smelting process; Q O is the total heat expenditure of the smelting process.

5. According to claim 1, a low-carbon smelting method for multi-source complex copper ore using sulfur instead of carbon is characterized by: The real-time feedback operation is dynamically adjusted to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon; The optimal batching condition for low-carbon smelting with sulfur replacing carbon is expressed as follows: r1M1+r2M1+…+r l M l +Q FS +minQ C +Q T ≥Q O Where M l Indicates the percentage of the total content of the first type of sulfur; r l Indicates the total amount of the first type of sulfur corresponding to the heat released during the smelting process; minQ C Indicates that carbonaceous fuel combustion provides the least heat.

6. A system for low-carbon smelting of multi-source complex copper ores using sulfur instead of carbon, characterized in that: include: Phase batching module, smelting equilibrium prediction module, real-time feedback module and dynamic adjustment module; The phase batching module is used to perform: S1. Based on the phase composition of multi-source copper concentrate, a batching model with Cu element content as the target and S-free phase content as the constraint condition is constructed, and the phase and content of copper concentrate entering the furnace are calculated by the multi-objective grey wolf algorithm; The smelting balance prediction module is used to perform: S2. According to the phase and content of the copper concentrate entering the furnace, the XGBoost prediction model is used to perform material balance prediction, and the heat balance prediction is performed based on the material balance prediction results; The real-time feedback module is used to perform: S3, performing real-time feedback operation on the thermal balance prediction results; The dynamic adjustment module is used to perform: S4. Dynamically adjust the real-time feedback operation to obtain the optimal batching scheme for low-carbon smelting using sulfur instead of carbon.

7. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements a low-carbon smelting method of multi-source complex copper ore using sulfur instead of carbon as described in any one of claims 1-5.

Images