Method and system for solving multiphase equilibrium of titanium slag in electric furnace smelting based on genetic algorithm

Abstract

The present invention provides a method and system for solving the multiphase equilibrium of electric furnace smelting titanium slag based on a genetic algorithm, which relates to the technical field of electric furnace smelting titanium slag, including: obtaining basic data in the electric furnace smelting titanium slag scenario; performing model construction processing based on phase composition data and thermodynamic property parameters to obtain a thermodynamic equilibrium constraint model; performing high-dimensional solution space generation processing based on phase composition data and smelting environment parameters to obtain a multidimensional equilibrium solution space; performing population encoding processing based on the multidimensional equilibrium solution space to obtain an initial population; performing fitness fusion processing based on the thermodynamic equilibrium constraint model to obtain a fitness index; performing evolution processing based on the fitness index and the convergence condition of the thermodynamic equilibrium constraint model to obtain an equilibrium solution set. The present invention embeds temperature and pressure parameters into the thermodynamic equilibrium constraint model, adjusts the Gibbs free energy weight through the temperature gradient, and controls the phase stability of the complex through the pressure gradient, so that the calculation results are more in line with actual smelting conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of electric furnace smelting titanium slag, and in particular to a method and system for solving multiphase equilibrium of electric furnace smelting titanium slag based on a genetic algorithm. Background Art

[0002] Electric furnace smelting of titanium slag is a core process for efficient titanium resource extraction. This process separates the iron and titanium oxides from ilmenite through a high-temperature reduction reaction, forming titanium-rich slag and pig iron. This process involves complex multiphase equilibrium processes, including the dynamic interaction of gas, slag, and metal phases, as well as phase transition reactions of the FeO-TiO2 complex. Accurately calculating this multiphase equilibrium state is crucial for optimizing smelting process parameters (such as temperature and carbon content), directly impacting titanium recovery and energy efficiency.

[0003] However, the high-temperature, multiphase coupling characteristics of titanium slag systems make it difficult for traditional thermodynamic models to accurately describe their dynamic equilibrium. Existing methods often rely on simplifying assumptions, such as ignoring the phase competition between Fe₃O₄ and FeO·TiO₂, fixing environmental parameters, and constructing static mass conservation equations, resulting in predictions that deviate from actual operating conditions. Some improved techniques employ staged linear programming or empirically adjusted model parameters. While these can mitigate single-constraint biases, they cannot address the global convergence problem in high-dimensional, non-convex solution spaces. Furthermore, the computational complexity increases exponentially with the number of phases, making it difficult to meet the demands of real-time process control.

[0004] Based on the above shortcomings of the prior art, there is an urgent need for a method and system for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on genetic algorithm. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on genetic algorithm to improve the above-mentioned problem. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present application provides a method for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm, comprising:

[0007] Obtain basic data for the electric furnace titanium slag smelting scenario, including phase composition data, thermodynamic property parameters of each phase chemical component, and smelting environment parameters;

[0008] Performing model construction processing based on the phase composition data and the thermodynamic property parameters, and obtaining a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation;

[0009] A high-dimensional solution space is generated based on the phase composition data and the smelting environment parameters, and a multi-dimensional equilibrium solution space is obtained by nonlinearly coupling mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters;

[0010] Performing population coding processing according to the multidimensional equilibrium solution space to obtain an initial population;

[0011] Performing fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index;

[0012] An evolutionary process is performed according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, and a temperature-pressure gradient-guided crossover and mutation operation is performed based on the initial population to obtain an equilibrium solution set.

[0013] In a second aspect, the present application also provides a system for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm, comprising:

[0014] An acquisition module is used to obtain basic data in the electric furnace titanium slag smelting scenario, wherein the basic data includes phase composition data, thermodynamic property parameters of each phase chemical component, and smelting environment parameters;

[0015] A construction module is used to perform model construction processing based on the phase composition data and the thermodynamic property parameters, and obtain a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation;

[0016] A generation module is used to generate a high-dimensional solution space based on the phase composition data and the smelting environment parameters, and obtain a multi-dimensional equilibrium solution space by nonlinearly coupling and mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters;

[0017] An encoding module, configured to perform population encoding processing according to the multidimensional equilibrium solution space to obtain an initial population;

[0018] A fusion module, configured to perform fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index;

[0019] The output module is used to perform evolutionary processing according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, and perform a temperature-pressure gradient-guided crossover and mutation operation based on the initial population to obtain an equilibrium solution set.

[0020] The beneficial effects of the present invention are:

[0021] This method deeply embeds temperature and pressure parameters into the thermodynamic equilibrium constraint model, regulating the Gibbs free energy weight through temperature gradients and controlling the phase stability of the complex through pressure gradients. This overcomes the limitation of traditional models that ignore the dynamic influence of environmental parameters, making the calculation results more consistent with actual smelting conditions. A normalized mandatory encoding rule is used to generate the initial population, ensuring that individuals strictly meet the total molar conservation and phase composition constraints, avoiding the ineffective search caused by traditional random encoding. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic flow chart of a method for solving the multiphase equilibrium of titanium slag in an electric furnace smelting process based on a genetic algorithm according to an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of the structure of a system for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm according to an embodiment of the present invention;

[0025] Figure 3 This is a schematic structural diagram of a device for solving multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm, as described in an embodiment of the present invention.

[0026] Markings in the figure: 800, a device for solving multiphase equilibrium of electric furnace smelting titanium slag based on genetic algorithm; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, construction module; 903, generation module; 904, encoding module; 905, fusion module; 906, output module. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, 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 part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides a method for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm.

[0031] See also Figure 1 , the figure shows that the method includes steps S100 to S600.

[0032] Step S100: Acquire basic data in the electric furnace titanium slag smelting scenario, the basic data including phase composition data, thermodynamic property parameters of each phase chemical component, and smelting environment parameters;

[0033] It can be understood that this step comprehensively obtains the multiphase composition data of the gaseous, slag and metal phases in the electric furnace smelting titanium slag scene, including components such as oxygen, carbon monoxide, carbon dioxide in the gas phase, key chemical components such as ferrous oxide, ferroferric oxide, titanium dioxide and titanium-iron complex in the slag state, as well as thermodynamic properties such as the standard formation free energy and activity coefficient of each phase, and combines the smelting temperature and system total pressure parameters collected in real time to construct the core data foundation for multiphase equilibrium calculation. In practical applications, the slag mineral phase composition is analyzed in real time by X-ray diffraction, the temperature distribution of the molten pool is synchronously monitored by high-temperature sensors, and the system pressure is collected by pressure transmitters to ensure that the data is strictly synchronized with the smelting process conditions. The chemical composition of each phase in the titanium smelting system of this embodiment is shown in the following table:

[0034] Table 1 Chemical composition of each phase in the titanium smelting system

[0035]

[0036] Step S200: constructing a model based on the phase composition data and thermodynamic property parameters, and obtaining a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation;

[0037] It should be noted that this step quantifies the cross-phase migration paths of elements such as iron, titanium, and oxygen into atomic conservation equations, ensuring that the elemental flow between the slag and metal phases satisfies mass balance (for example, the conversion ratio of iron between ferrous oxide and ferroferric oxide). Simultaneously, the equilibrium equations for the formation of complexes such as ilmenite and spinel are combined, and the reaction equilibrium constants are corrected by the activity coefficient to accurately describe the competitive relationship of the complex phase transitions at high temperatures. Furthermore, the extreme value of the Gibbs free energy is introduced as a global optimization objective, transforming the multiphase equilibrium problem into an energy minimization problem under dynamic constraints. This overcomes the limitation of traditional static models that cannot characterize the impact of environmental parameter changes on phase equilibrium paths. Specifically, according to the existing FeO-TiO2 slag phase diagram, FeO and TiO2 can form three solid-liquid compounds with the same composition: titanium spinel 2FeO•TiO2 (1395°C), ilmenite FeO•TiO2 (1400°C), and tantalum FeO•2TiO2 (1494°C); at the same time, FeO and Fe2O3 will form Fe3O4. Therefore, the structural unit of this system is Fe 2+ , O 3- ions and Fe2O3, TiO2, Fe3O4, 2FeO•TiO2, FeO•TiO, FeO •2TiO2 molecules. First, construct a chemical equilibrium equation from the reaction formula:

[0038]

[0039] Among them, Fe 2+ is ferrous ion; O 2- is oxygen ion; Fe2O3 is iron oxide; Fe3O4 is ferroferric oxide; subscripts (l) and (s) indicate liquid and solid, respectively; N1 is the molar amount of FeO in the slag phase; N2 is the molar amount of Fe2O3 in the slag phase; N3 is the molar amount of TiO2 in the slag phase; N4 is the molar amount of Fe3O4 in the slag phase; N3 is the molar amount of TiO2 in the slag phase; N5 is the molar amount of titanium spinel in the slag phase; N6 is the molar amount of ilmenite in the slag phase; N7 is the molar amount of tantalum in the slag phase.

[0040] Equations 1 to 4 use the activity coefficient to correct the equilibrium constant, accurately characterizing the competitive relationship of the complex phase transition at high temperature. Subsequently, based on the mass balance, we can obtain:

[0041]

[0042] Equations 3 to 5 quantify the distribution ratio of iron among FeO, Fe3O4, and the complex, and constrain the flow path of titanium in phases such as TiO2 and ilmenite. By eliminating redundant variables through simultaneous equations, we can further deduce:

[0043]

[0044] Where ∑x is the total mole fraction at equilibrium; b is the total mole fraction of FeO in the slag phase; a1 is the total mole fraction of Fe2O3 in the slag phase; a2 is the total mole fraction of TiO2 in the slag phase; N i is the molar amount of the i-th chemical component; i is the serial number of the chemical component.

[0045] Equations 8 and 9 couple the conservation relationships of iron and titanium with the chemical equilibrium equations to form a closed set of equations. Ultimately, the Gibbs free energy extremum equation serves as the global optimization objective, transforming the multiphase equilibrium problem into an energy minimization problem under dynamic constraints. The total Gibbs free energy of the system is expressed as:

[0046]

[0047] Among them, G 总 is the total Gibbs free energy of the system; represents the standard molar Gibbs free energy of formation of the i-th chemical component; R represents the ideal gas constant; T represents the system temperature. i is the activity of the i-th chemical component.

[0048] Step S300: generating a high-dimensional solution space based on the phase composition data and the smelting environment parameters, and obtaining a multi-dimensional equilibrium solution space by nonlinearly coupling mapping the ion concentration, the mole fraction of the composite molecule, and the environmental parameters;

[0049] Specifically, this step introduces temperature as a dynamic weight factor for ion diffusion rate and pressure as a probability adjustment coefficient for competition among complex phases, thereby converting the isolated chemical component distribution in the traditional low-dimensional solution space into a gradient field in a high-dimensional continuous space, thereby solving the problem of phase change path representation distortion caused by linear dimensionality reduction in the traditional model; at the same time, a hierarchical superposition of nonlinear mapping rules is designed based on the high-temperature characteristics of slag to make the solution space adapt to the multiphase coupling characteristics of the titanium slag system.

[0050] Step S400: performing population coding processing according to the multidimensional equilibrium solution space to obtain an initial population;

[0051] It can be understood that this step first converts the coupling relationship between ion concentration, complex molar fraction and environmental parameters in the solution space into chromosome encoding rules, and ensures that each individual naturally satisfies the total molar conservation constraint through forced normalization processing, avoiding invalid solution redundancy caused by constraint conflicts in random encoding; secondly, the guiding effect of the temperature-pressure gradient field in the solution space on the phase transition path of the complex is utilized to dynamically adjust the distribution weights of different complex components in the chromosome (such as the high-temperature zone chromosomes preferentially carry the high proportion of ferroferric oxide), so that the initial population implicitly contains the phase competition law of actual smelting conditions; finally, based on the topological structure of the solution space (such as the strong correlation between iron ion concentration and ilmenite phase distribution), a partition sampling strategy is designed to generate a dense chromosome distribution in the high-probability equilibrium area, while covering the low-probability critical phase transition area, to ensure that the population has both global exploration and local refinement capabilities.

[0052] Step S500: Perform fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index;

[0053] It should be noted that this step normalizes the atomic conservation residuals of iron, titanium, and oxygen, the equilibrium deviations of key reactions such as ilmenite and spinel, and the difference in Gibbs free energy extremes. The weight ratio of these three factors is dynamically adjusted according to the smelting temperature to form a comprehensive fitness index that can quantify the equilibrium state of individual populations. This fitness index accurately quantifies the overall strengths and weaknesses of individual populations in multiphase equilibrium, particularly in the critical phase transition region generated by the competition between ilmenite and ferroferric oxide. It significantly improves the algorithm's ability to identify dominant solution domains, providing a highly discriminative optimization guide for subsequent evolutionary computations and ensuring that the population rapidly converges to a globally optimal solution set that meets actual smelting conditions.

[0054] Step S600: performing evolutionary processing according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, performing a temperature-pressure gradient-guided crossover and mutation operation based on the initial population, and obtaining an equilibrium solution set.

[0055] It can be understood that this step uses temperature parameters to control the search range of the crossover operation (e.g., expanding the crossover range in high-temperature zones to accelerate the global exploration of the Gibbs free energy downward trend) and pressure parameters to adjust the step length (e.g., reducing the step size under high-pressure conditions to finely approximate the ilmenite phase stability zone), allowing the evolutionary process to closely adapt to the dynamic changes in smelting environmental parameters. At the same time, the multi-criteria convergence conditions of mass conservation residuals, chemical equilibrium deviations, and Gibbs free energy change rates are integrated to ensure that the solution set simultaneously satisfies the requirements of atomic conservation, phase reaction equilibrium, and energy extrema. In the complex multi-phase coupled titanium slag smelting process, the evolutionary algorithm significantly improves the efficiency of locating the global optimal solution through the combined action of gradient-guided directional search and multi-objective convergence criteria. In particular, under the critical operating condition where ilmenite competes with ferroferric oxide, the solution set is more closely aligned with the actual process conditions, providing a high-confidence decision-making basis for dynamically controlling furnace temperature and optimizing the batch ratio.

[0056] Furthermore, step S200 includes steps S210 to S230.

[0057] Step S210: constructing multi-element atomic conservation equations based on the initial molar distribution and element conservation characteristics of the slag-state iron-titanium composite in the phase composition data, and obtaining a mass conservation equation group by establishing an atomic flow equilibrium relationship between iron, titanium, and oxygen elements in multiple phases;

[0058] Specifically, this step quantifies the migration paths of iron, titanium, and oxygen between the gas-slag-metal multiphase as atomic flow equilibrium relationships, such as the reduction reaction of iron between slag-state ferrous oxide and metallic-phase iron, and the solid solution transformation of titanium between slag-state titanium dioxide and ilmenite, forming a set of linear constrained equations with the mole fraction of the complex as the variable. By introducing multi-element joint conservation modeling, the interactive distribution of iron and titanium between the slag and metal phases is simultaneously considered, such as the dynamic transformation ratio of iron between ferrous oxide and ferroferric oxide, and the solid solution equilibrium of titanium in titanium dioxide and ilmenite, ensuring that the equations fully characterize the complexity of multiphase interactions.

[0059] Step S220: constructing a multiphase equilibrium equation based on the standard generation free energy and the activity dynamic correlation characteristics in the thermodynamic property parameters, and obtaining a chemical equilibrium equation group by dynamically coupling the thermodynamic equilibrium constant with the activity of the complex;

[0060] It should be noted that this step addresses the nonlinear variation of activity in high-temperature titanium slag with temperature and pressure. By embedding an activity coefficient correction mechanism into the equilibrium constant calculation, this method dynamically adjusts the phase stability thresholds for key reactions such as spinel and ilmenite. For example, as temperature rises, the increase in ferrous oxide activity directly affects the propensity for ferroferric oxide formation, enabling the model to accurately capture the dynamic laws of phase competition in actual smelting.

[0061] Step S230: Based on the mass conservation equations and the chemical equilibrium equations, a model is constructed to obtain a thermodynamic equilibrium constraint model that drives the evolution of the multiphase equilibrium state by constructing a dynamic optimization framework with minimization of Gibbs free energy as the goal and multiphase constraints as the boundaries.

[0062] As can be understood, this step introduces a temperature gradient-driven weight adjustment mechanism, prioritizing energy extremes in high-temperature regions and strengthening chemical equilibrium constraints in low-temperature regions, allowing the model to adapt to fluctuations in smelting conditions. This progressive modeling logic, from atomic conservation to phase transition equilibrium, ultimately achieves global energy optimization, providing a high-precision theoretical tool for solving multiphase equilibrium in titanium slag smelting.

[0063] Furthermore, step S300 includes steps S310 to S330.

[0064] Step S310: Based on the ion concentration distribution in the phase composition data and the temperature gradient characteristics of the smelting environment parameters, ion-environment coupling processing is performed to obtain an initial coupling space reflecting the ion migration characteristics of the high-temperature slag by mapping the iron ion and oxygen ion concentrations with the temperature parameters according to nonlinear weight association;

[0065] It can be understood that this step dynamically regulates the ion diffusion rate through temperature, quantifying the impact of temperature gradients on ion enrichment trends, allowing the initial coupled space to accurately characterize the driving effect of temperature fluctuations on ion migration paths. This initial space can map the regulatory effects of temperature changes on slag ion distribution in real time, providing a physical field-coupled ion migration benchmark for subsequent solution space expansion.

[0066] Step S320: performing a composite-pressure expansion based on the initial coupling space and the composite molecule mole fraction in the phase composition data. Utilizing the constraint relationship between the pressure parameter and the composite molecule generation reaction, the composite mole fraction and the pressure parameter are nonlinearly expanded to obtain a multidimensional correlation space containing the composite phase transition path.

[0067] It's important to note that this step leverages the effect of pressure on the free energy of complex formation (e.g., high pressure inhibits the decomposition of ferroferric oxide) to dynamically correlate the mole fractions of complexes like ilmenite and spinel with pressure gradients, creating an independent dimension to characterize changes in phase stability. This solution space transcends the traditional one-dimensional pressure simplification assumption and enables refined modeling of the competitive laws of phase transitions under multi-parameter coupling, such as the gradient characteristic of the dense distribution of ilmenite in high-pressure zones.

[0068] Step S330: construct a high-dimensional space topology based on the multi-dimensional correlation space, and obtain a multi-dimensional equilibrium solution space through multi-level nonlinear superposition and normalization constraints of ion-complex-environmental parameters.

[0069] It is understandable that by defining the topological structure based on the strong correlation between ion concentration and the distribution of the complex (for example, iron-rich regions correspond to a high probability distribution of the spinel phase), and by normalizing to eliminate dimensional differences, a continuous solution domain is formed. Through hierarchical topological optimization, the solution space globally covers the complex phase transition paths of the titanium slag system (such as the gradient transition in the critical phase transition zone of ilmenite to ferroferric oxide), providing a high-resolution search space for the genetic algorithm and significantly improving the efficiency of locating multiphase equilibrium solutions.

[0070] Furthermore, step S400 includes steps S410 to S430.

[0071] Step S410: performing normalized coding processing in the multidimensional equilibrium solution space, mapping the randomly generated complex distribution into a real-number coded chromosome satisfying a total molar fraction of 1, thereby obtaining a set of candidate individuals;

[0072] It should be noted that this step maps the distribution of randomly generated complexes to real-number coded chromosomes that satisfy a total mole fraction of 1, ensuring that each individual naturally meets the basic thermodynamic constraints. Preferably, the mole fractions of randomly generated complexes such as ilmenite and spinel are scaled and corrected by a normalization function to eliminate invalid solutions caused by excessive mole fractions. The technical effect of this step is that the feasibility ratio of the candidate individual set is significantly improved, avoiding invalid iterations caused by violating the total mole conservation in traditional random coding, and providing a high-quality initial data foundation for subsequent evolutionary calculations.

[0073] Step S420: Based on the candidate individual set and the temperature-pressure gradient distribution in the multidimensional equilibrium solution space, environmental parameter coupling processing is performed to generate a diverse population by dynamically adjusting the effect of temperature on the probability of dominant phase generation and the effect of pressure on the stability of the complex;

[0074] It's understandable that this step maps the temperature parameter into a dynamic regulator of the probability of formation of the dominant phase (e.g., ferroferric oxide), while simultaneously using the pressure parameter to control the stability threshold of the complex (e.g., ilmenite). The proportion of ferroferric oxide in individuals in the high-temperature zone increases with increasing temperature, while the distribution density of ilmenite increases under high-pressure conditions.

[0075] Step S430: Perform topological uniformity processing based on the topological correlation between the diverse population and the multidimensional equilibrium solution space, define the correlation partitions between ion concentration and complex distribution, and perform topological uniform sampling and reorganization on the chromosomes to generate an initial population.

[0076] It should be noted that this step divides the high-probability equilibrium region and the critical phase transition region according to the topological structure of the solution space, and uniformly extracts chromosomes in proportion within each partition to ensure that the population covers the potential solution domain of multiphase equilibrium. Preferably, dense sampling is implemented in the critical region of the ilmenite and ferroferric oxide phase transition, while the sampling density is reduced in the stable phase region. The generated initial population has a significantly enhanced global coverage capability of the complex solution domain, especially in the gradient transition region of the ilmenite-iron brookite phase transition path, where the population diversity is increased by more than 50% compared with traditional random sampling.

[0077] Furthermore, step S500 includes steps S510 to S530.

[0078] Step S510: Perform multi-element residual fusion processing according to the thermodynamic equilibrium constraint model, calculate the atomic conservation residuals of iron, titanium, and oxygen elements between the slag phases and perform weighted summation to generate a mass conservation fitness component;

[0079] Understandably, this step assigns weights to element conservation residuals based on smelting process priorities, forming a quantifiable indicator for assessing the degree of individual deviations from atomic conservation. By calculating multi-element joint residuals, we can accurately identify atomic distribution imbalances caused by complex phase transitions (such as titanium loss from solid solution due to ilmenite decomposition), providing a rigorous element conservation guide for subsequent optimization.

[0080] Step S520: performing dynamic deviation processing of equilibrium constants according to a thermodynamic equilibrium constraint model, dynamically correcting the equilibrium constants by introducing the activity coefficient of the complex, calculating the equilibrium deviations of key reactions of spinel and ilmenite, and generating a chemical equilibrium fitness component reflecting the interphase competition relationship;

[0081] It should be noted that, considering the inhibitory effect of increased ferrous oxide activity on spinel formation at high temperatures, this step introduces a dynamic correction mechanism for the activity coefficient with temperature and pressure, ensuring that the equilibrium deviation calculation is consistent with actual smelting conditions. This allows for precise quantification of the stability of the complex's phase transition pathways, resolving the problem of misjudging phase competition relationships caused by traditional models that ignore dynamic activity changes.

[0082] Step S530: performing optimization fusion processing according to the mass conservation fitness component and the chemical equilibrium fitness component, adjusting the optimization weight of the Gibbs free energy extreme value based on the temperature gradient, and generating a fitness index.

[0083] It should be noted that this step prioritizes the energy-optimal solution by assigning a higher weight to the Gibbs free energy in the high-temperature region, while strengthening the combined weight of mass conservation and chemical equilibrium in the low-temperature region. When the furnace temperature exceeds the critical value for the ilmenite phase transition, the mass conservation residual weight is reduced, focusing on energy-driven phase composition optimization. The generated fitness index can adapt to the dynamic changes in smelting conditions, guiding the genetic algorithm to rapidly converge to the global optimal solution set in complex multi-objective optimization, significantly improving the efficiency and accuracy of solving the multiphase equilibrium of titanium slag.

[0084] Furthermore, step S600 includes steps S610 to S630.

[0085] Step S610: Perform environmental parameter weighted parent selection based on the fitness index and the convergence conditions of the thermodynamic equilibrium constraint model. The fitness ranking weight is adjusted by the temperature gradient, and the population selection pressure is controlled by the pressure gradient to generate a parent population that is suitable for the smelting conditions.

[0086] Understandably, this step uses the temperature gradient to adjust the priority weights in the fitness ranking, while simultaneously utilizing the pressure gradient to control the population selection pressure, ensuring that the parent population distribution is strictly aligned with smelting parameters (such as real-time furnace temperature and pressure fluctuations). The environmentally biased characteristics of the parent population significantly improve the efficiency of subsequent evolutionary tracking of actual phase transition paths, avoiding the search direction deviation problems caused by traditional random selection.

[0087] Step S620: Perform gradient-guided crossover mutation processing on the parent population, control the crossover range through the temperature gradient, and adjust the mutation step length through the pressure gradient, to generate a daughter population that searches along the direction of decreasing Gibbs free energy;

[0088] It should be noted that, based on the parent population, this step converts physical field gradients (such as temperature-energy correlations and pressure-phase stability correlations) into the dynamic control logic of genetic operators. Preferably, as the temperature rises, the crossover operation favors chromosome combinations with a higher probability of producing ferroferric oxide, while the mutation operation under high-pressure conditions prioritizes fine-tuning the ilmenite mole fraction. This step ensures that the search path of the offspring population closely aligns with the thermodynamic evolution of actual smelting, significantly improving the algorithm's accuracy and convergence speed in locating complex phase equilibrium solutions.

[0089] Step S630: Perform multi-objective dynamic convergence processing based on the offspring population, and generate an equilibrium solution set by integrating the criteria of mass conservation residual threshold, chemical equilibrium deviation tolerance and Gibbs free energy extreme value change rate.

[0090] It is understood that this step sets the combined conditions of a mass conservation residual threshold (preferably, such as a deviation of ≤1% for inter-phase migration of iron and titanium elements), a chemical equilibrium tolerance (preferably, such as a deviation of ≤5% for the activity of the spinel formation reaction), and the Gibbs free energy change rate (preferably, such as a change rate of <0.1% over three consecutive generations) to ensure that the solution set simultaneously satisfies thermodynamic constraints and process feasibility. By integrating multiple criteria, the risk of local solution truncation caused by traditional single convergence criteria (such as relying solely on residuals or energy) is avoided, ensuring that the solution set fully covers feasible phase equilibrium states in titanium slag smelting and improving the reliability of process decisions.

[0091] Example 2:

[0092] like Figure 2 As shown, this embodiment provides a system for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on a genetic algorithm, and the system includes:

[0093] Acquisition module 901 is used to acquire basic data in the electric furnace smelting titanium slag scenario, the basic data including phase composition data, thermodynamic property parameters of each phase chemical component and smelting environment parameters;

[0094] A construction module 902 is used to construct a model based on the phase composition data and thermodynamic property parameters, and obtain a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation;

[0095] A generation module 903 is used to generate a high-dimensional solution space based on the phase composition data and the smelting environment parameters, and obtain a multi-dimensional equilibrium solution space by nonlinearly coupling and mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters;

[0096] The encoding module 904 is used to perform population encoding processing according to the multi-dimensional equilibrium solution space to obtain an initial population;

[0097] Fusion module 905, used to perform fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index;

[0098] The output module 906 is used to perform evolutionary processing according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, perform temperature-pressure gradient-guided crossover and mutation operations based on the initial population, and obtain an equilibrium solution set.

[0099] In some embodiments disclosed in this application, the building block 902 includes:

[0100] The first construction unit is used to construct multi-element atomic conservation equations based on the initial molar distribution of the slag-state iron-titanium composite and the element conservation characteristics in the phase composition data, and obtain the mass conservation equations by establishing the atomic flow equilibrium relationship between iron, titanium and oxygen elements in multiple phases;

[0101] The second construction unit is used to construct the multiphase equilibrium equation based on the standard generation free energy and activity dynamic correlation characteristics in the thermodynamic property parameters, and obtain the chemical equilibrium equation group by dynamically coupling the thermodynamic equilibrium constant and the activity of the complex;

[0102] The third construction unit is used to construct a model based on the mass conservation equations and the chemical equilibrium equations. By constructing a dynamic optimization framework with Gibbs free energy minimization as the goal and multiphase constraints as the boundaries, a thermodynamic equilibrium constraint model that drives the evolution of the multiphase equilibrium state is obtained.

[0103] In some embodiments disclosed in this application, the generation module 903 includes:

[0104] The first generation unit is used to perform ion-environment coupling processing based on the ion concentration distribution in the phase composition data and the temperature gradient characteristics of the smelting environment parameters. By mapping the iron ion and oxygen ion concentrations with the temperature parameters according to nonlinear weight association, an initial coupling space reflecting the ion migration characteristics of the high-temperature slag is obtained;

[0105] The second generation unit is used to perform a composite-pressure expansion based on the mole fraction of the composite molecules in the initial coupling space and the phase composition data, and to perform a nonlinear dimensional expansion of the composite mole fraction and the pressure parameter using the constraint relationship of the pressure parameter on the composite molecule generation reaction to obtain a multidimensional correlation space containing the phase transition path of the composite;

[0106] The third generation unit is used to construct a high-dimensional space topology based on the multidimensional correlation space, and obtain a multidimensional equilibrium solution space through multi-level nonlinear superposition and normalization constraints of ion-complex-environmental parameters.

[0107] In some embodiments disclosed in this application, the encoding module 904 includes:

[0108] A first encoding unit is configured to perform normalized encoding processing in a multidimensional equilibrium solution space, and obtain a set of candidate individuals by mapping the randomly generated complex distribution into a real-number coded chromosome satisfying a total molar fraction of 1;

[0109] The second coding unit is used to perform environmental parameter coupling processing based on the candidate individual set and the temperature-pressure gradient distribution in the multidimensional equilibrium solution space, and to generate a diverse population by dynamically adjusting the effect of temperature on the probability of dominant phase generation and the effect of pressure on the stability of the complex;

[0110] The third coding unit is used to perform topological uniformity processing based on the topological correlation of the diverse population and the multidimensional equilibrium solution space. The initial population is generated by defining the correlation partition between ion concentration and complex distribution, and performing topological uniform sampling and reorganization of chromosomes.

[0111] In some embodiments disclosed in this application, the fusion module 905 includes:

[0112] The first fusion unit is used to perform multi-element residual fusion processing according to the thermodynamic equilibrium constraint model. It calculates the atomic conservation residuals of iron, titanium, and oxygen elements between the slag phases and performs weighted summation to generate the mass conservation fitness component.

[0113] The second fusion unit is used to process the dynamic deviation of the equilibrium constant according to the thermodynamic equilibrium constraint model. By introducing the dynamic correction of the equilibrium constant by the activity coefficient of the complex, the equilibrium deviation of the key reactions of spinel and ilmenite is calculated to generate the chemical equilibrium fitness component reflecting the competition relationship between the phases;

[0114] The third fusion unit is used to perform optimization fusion processing according to the mass conservation fitness component and the chemical equilibrium fitness component, adjust the optimization weight of the Gibbs free energy extreme value based on the temperature gradient, and generate a fitness index.

[0115] In some embodiments disclosed in this application, the output module 906 includes:

[0116] The first output unit is used to perform environmental parameter weighted parent selection processing based on the fitness index and the convergence conditions of the thermodynamic equilibrium constraint model. The fitness ranking weight is adjusted by the temperature gradient, and the population selection pressure is controlled by the pressure gradient to generate a parent population adapted to the smelting conditions.

[0117] The second output unit uses gradient-guided crossover mutation processing based on the parent population, controls the crossover range through the temperature gradient, and adjusts the mutation step length through the pressure gradient, generating a progeny population that searches along the direction of decreasing Gibbs free energy;

[0118] The third output unit uses multi-objective dynamic convergence processing based on the offspring population to generate an equilibrium solution set by integrating the criteria of mass conservation residual threshold, chemical equilibrium deviation tolerance and Gibbs free energy extreme value change rate.

[0119] Example 3:

[0120] Corresponding to the above method embodiment, this embodiment also provides a multiphase equilibrium solution device for electric furnace smelting titanium slag based on genetic algorithm. The multiphase equilibrium solution device for electric furnace smelting titanium slag based on genetic algorithm described below and the multiphase equilibrium solution method for electric furnace smelting titanium slag based on genetic algorithm described above can be referenced to each other.

[0121] Figure 3 FIG. 8 is a block diagram of a device 800 for solving a multiphase equilibrium problem of titanium slag in an electric furnace based on a genetic algorithm according to an exemplary embodiment. Figure 3As shown, the device 800 for solving the multiphase equilibrium of titanium slag in an electric furnace based on a genetic algorithm may include: a processor 801 and a memory 802. The device 800 for solving the multiphase equilibrium of titanium slag in an electric furnace based on a genetic algorithm may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0122] The processor 801 is used to control the overall operation of the device 800 for solving the multiphase equilibrium of titanium slag in an electric furnace based on a genetic algorithm, so as to complete all or part of the steps of the method for solving the multiphase equilibrium of titanium slag in an electric furnace based on a genetic algorithm. The memory 802 is used to store various types of data to support the operation of the device 800 for solving the multiphase equilibrium of titanium slag in an electric furnace based on a genetic algorithm. Such data may include, for example, instructions for any application or method operating on the device 800, as well as application-related data, such as contact information, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electric furnace smelting titanium slag multiphase equilibrium solution device 800 based on genetic algorithm and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0123] In an exemplary embodiment, a device 800 for solving the multiphase equilibrium of titanium slag in an electric furnace smelting process based on a genetic algorithm can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned method for solving the multiphase equilibrium of titanium slag in an electric furnace smelting process based on a genetic algorithm.

[0124] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When executed by a processor, the program instructions implement the steps of the aforementioned method for solving the multiphase equilibrium of titanium slag in an electric furnace using a genetic algorithm. For example, the computer-readable storage medium may be the aforementioned memory 802 including the program instructions. The program instructions may be executed by the processor 801 of the apparatus 800 for solving the multiphase equilibrium of titanium slag in an electric furnace using a genetic algorithm to implement the aforementioned method for solving the multiphase equilibrium of titanium slag in an electric furnace using a genetic algorithm.

[0125] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on genetic algorithm, characterized in that: include: Obtain basic data for the electric furnace titanium slag smelting scenario, including phase composition data, thermodynamic property parameters of each phase chemical component, and smelting environment parameters; Performing model construction processing based on the phase composition data and the thermodynamic property parameters, and obtaining a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation; A high-dimensional solution space is generated based on the phase composition data and the smelting environment parameters, and a multi-dimensional equilibrium solution space is obtained by nonlinearly coupling mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters; Performing population coding processing according to the multidimensional equilibrium solution space to obtain an initial population; Performing fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index; An evolutionary process is performed according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, and a temperature-pressure gradient-guided crossover and mutation operation is performed based on the initial population to obtain an equilibrium solution set.

2. The method for solving the multiphase equilibrium of electric furnace smelting titanium slag based on genetic algorithm according to claim 1, characterized in that: A model is constructed based on the phase composition data and the thermodynamic property parameters, and a thermodynamic equilibrium constraint model is obtained by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation, including: Based on the initial molar distribution of the slag-state iron-titanium composite and the element conservation characteristics in the phase composition data, a multi-element atomic conservation equation is constructed, and a mass conservation equation group is obtained by establishing an atomic flow equilibrium relationship between iron, titanium, and oxygen elements in multiple phases; According to the standard free energy of formation and the dynamic correlation characteristics of the activity in the thermodynamic property parameters, a multiphase equilibrium equation is constructed, and a chemical equilibrium equation group is obtained by dynamically coupling the thermodynamic equilibrium constant and the activity of the complex; According to the mass conservation equations and the chemical equilibrium equations, a model construction process is performed, and by constructing a dynamic optimization framework with Gibbs free energy minimization as the goal and multiphase constraints as the boundaries, a thermodynamic equilibrium constraint model that drives the evolution of the multiphase equilibrium state is obtained.

3. The method for solving the multiphase equilibrium of titanium slag from electric furnace smelting based on genetic algorithm according to claim 1, characterized in that: A high-dimensional solution space is generated based on the phase composition data and the smelting environment parameters, and a multi-dimensional equilibrium solution space is obtained by nonlinearly coupling mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters, including: Based on the ion concentration distribution in the phase composition data and the temperature gradient characteristics of the smelting environment parameters, ion-environment coupling processing is performed to obtain an initial coupling space reflecting the ion migration characteristics of the high-temperature slag by mapping the iron ion and oxygen ion concentrations with the temperature parameters according to nonlinear weight association; Performing a complex-pressure expansion based on the mole fraction of the complex molecules in the initial coupling space and the phase composition data, and utilizing the constraint relationship of the pressure parameter on the complex molecule generation reaction to perform a nonlinear dimensional expansion on the mole fraction of the complex and the pressure parameter to obtain a multidimensional correlation space containing the phase transition path of the complex; A high-dimensional space topology is constructed according to the multi-dimensional correlation space, and a multi-dimensional equilibrium solution space is obtained through multi-level nonlinear superposition and normalization constraints of ion-complex-environmental parameters.

4. The method for solving the multiphase equilibrium of titanium slag in electric furnace smelting based on genetic algorithm according to claim 1, characterized in that: Performing population coding processing according to the multidimensional equilibrium solution space to obtain an initial population includes: According to the normalized coding process in the multidimensional equilibrium solution space, a candidate individual set is obtained by mapping the randomly generated complex distribution into a real-number coded chromosome satisfying a total molar fraction of 1; Performing environmental parameter coupling processing based on the candidate individual set and the temperature-pressure gradient distribution in the multidimensional equilibrium solution space, and generating a diverse population by dynamically adjusting the effect of temperature on the probability of dominant phase generation and the effect of pressure on the stability of the complex; According to the topological correlation between the diverse population and the multidimensional equilibrium solution space, topological uniformity processing is performed, and an initial population is generated by defining correlation partitions between ion concentration and complex distribution and performing topological uniform sampling and reorganization on chromosomes.

5. The method for solving the multiphase equilibrium of titanium slag from electric furnace smelting based on genetic algorithm according to claim 1, characterized in that: Fitness fusion processing is performed according to the thermodynamic equilibrium constraint model to obtain fitness indicators, including: Perform multi-element residual fusion processing according to the thermodynamic equilibrium constraint model, and generate mass conservation fitness components by calculating the atomic conservation residuals of iron, titanium, and oxygen elements between various phases in the slag state and performing weighted summation; According to the thermodynamic equilibrium constraint model, dynamic deviation processing of equilibrium constants is performed, and by introducing the complex activity coefficient to dynamically correct the equilibrium constants, the equilibrium deviations of key reactions of spinel and ilmenite are calculated to generate chemical equilibrium fitness components reflecting the competition relationship between phases; An optimization fusion process is performed according to the mass conservation fitness component and the chemical equilibrium fitness component, and an optimization weight of the Gibbs free energy extreme value is adjusted based on the temperature gradient to generate a fitness index.

6. A genetic algorithm-based multiphase equilibrium solution system for electric furnace titanium slag, characterized in that: include: An acquisition module is used to obtain basic data in the electric furnace titanium slag smelting scenario, wherein the basic data includes phase composition data, thermodynamic property parameters of each phase chemical component, and smelting environment parameters; A construction module is used to perform model construction processing based on the phase composition data and the thermodynamic property parameters, and obtain a thermodynamic equilibrium constraint model by simultaneously solving the mass conservation equation, the chemical equilibrium equation, and the Gibbs free energy extreme value equation; A generation module is used to generate a high-dimensional solution space based on the phase composition data and the smelting environment parameters, and obtain a multi-dimensional equilibrium solution space by nonlinearly coupling and mapping the ion concentration, the mole fraction of the composite molecule and the environmental parameters; An encoding module, configured to perform population encoding processing according to the multidimensional equilibrium solution space to obtain an initial population; A fusion module, configured to perform fitness fusion processing according to the thermodynamic equilibrium constraint model to obtain a fitness index; The output module is used to perform evolutionary processing according to the fitness index and the convergence condition of the thermodynamic equilibrium constraint model, and perform a temperature-pressure gradient-guided crossover and mutation operation based on the initial population to obtain an equilibrium solution set.

7. The electric furnace titanium slag multiphase equilibrium solution system based on genetic algorithm according to claim 6 is characterized in that: The building blocks include: The first construction unit is used to construct a multi-element atomic conservation equation based on the initial molar distribution and element conservation characteristics of the slag-state iron-titanium composite in the phase composition data, and obtain a mass conservation equation group by establishing an atomic flow equilibrium relationship between iron, titanium, and oxygen elements in multiple phases; The second construction unit is used to construct a multiphase equilibrium equation based on the standard generation free energy and activity dynamic correlation characteristics in the thermodynamic property parameters, and obtain a chemical equilibrium equation group by dynamically coupling the thermodynamic equilibrium constant and the activity of the complex; The third construction unit is used to perform model construction processing based on the mass conservation equations and the chemical equilibrium equations, and obtain a thermodynamic equilibrium constraint model that drives the evolution of the multiphase equilibrium state by constructing a dynamic optimization framework with Gibbs free energy minimization as the goal and multiphase constraints as the boundary.

8. The electric furnace titanium slag multiphase equilibrium solution system based on genetic algorithm according to claim 6 is characterized in that: The generation module includes: A first generating unit is configured to perform ion-environment coupling processing based on the ion concentration distribution in the phase composition data and the temperature gradient characteristics of the smelting environment parameters, and obtain an initial coupling space reflecting the ion migration characteristics of the high-temperature slag by mapping the iron ion and oxygen ion concentrations with the temperature parameters according to nonlinear weight association; a second generation unit, configured to perform a composite-pressure expansion based on the initial coupling space and the composite molecule mole fraction in the phase composition data, and to perform a nonlinear dimensional expansion on the composite mole fraction and the pressure parameter using a constraint relationship between the pressure parameter and the composite molecule generation reaction, thereby obtaining a multidimensional correlation space containing a phase transition path of the composite; The third generation unit is used to construct a high-dimensional space topology according to the multi-dimensional correlation space, and obtain a multi-dimensional equilibrium solution space through multi-level nonlinear superposition and normalization constraints of ion-complex-environmental parameters.

9. The electric furnace titanium slag multiphase equilibrium solution system based on genetic algorithm according to claim 6 is characterized in that: The encoding module includes: A first encoding unit is configured to perform normalized encoding processing in the multidimensional equilibrium solution space, and obtain a set of candidate individuals by mapping the randomly generated complex distribution into a real-number coded chromosome satisfying a total molar fraction of 1; A second encoding unit is configured to perform environmental parameter coupling processing based on the candidate individual set and the temperature-pressure gradient distribution in the multidimensional equilibrium solution space, and generate a diverse population by dynamically adjusting the effect of temperature on the probability of dominant phase generation and the effect of pressure on the stability of the complex; The third encoding unit is used to perform topological uniformity processing based on the topological correlation between the diverse population and the multidimensional equilibrium solution space, generate an initial population by defining the correlation partition between ion concentration and complex distribution, and performing topological uniform sampling and reorganization on chromosomes.

10. The electric furnace titanium slag multiphase equilibrium solution system based on genetic algorithm according to claim 6, characterized in that: The fusion module includes: The first fusion unit is used to perform multi-element residual fusion processing according to the thermodynamic equilibrium constraint model, and generate a mass conservation fitness component by calculating the atomic conservation residuals of iron, titanium, and oxygen elements between various phases in the slag state and performing weighted summation; The second fusion unit is used to perform dynamic deviation processing of equilibrium constants according to the thermodynamic equilibrium constraint model, calculate the equilibrium deviations of key reactions of spinel and ilmenite by introducing the complex activity coefficient to dynamically correct the equilibrium constants, and generate a chemical equilibrium fitness component reflecting the competition relationship between phases; The third fusion unit is used to perform optimization fusion processing according to the mass conservation fitness component and the chemical equilibrium fitness component, adjust the optimization weight of the Gibbs free energy extreme value based on the temperature gradient, and generate a fitness index.

Images