Metallurgy waste gas purification and recovery method based on particle swarm optimization algorithm

Abstract

The invention discloses a metallurgical waste gas purification and recovery method based on a particle swarm optimization algorithm, and the method comprises the following steps: S1, carrying out the pretreatment of metallurgical waste gas, monitoring the temperature, pressure, flow velocity and chemical components in real time, and inputting the temperature, pressure, flow velocity and chemical components into an optimization module; s2, key parameters in the purification and recovery process are analyzed through a recursive morphological coupling algorithm, a problem is decomposed into sub-problems, and operation parameters are determined; s3, performing global search through a morphological recombination particle swarm optimization algorithm to generate an optimization parameter set; s4, performing dynamic recombination on the potential optimal solution by applying an evolutionary form recombination algorithm, and improving a local solution; s5, the optimized parameter set is applied to the purification device, dynamic adjustment is conducted through a recursive morphological coupling algorithm, and recognition and recovery of rare components are achieved; s6, performing multi-stage detection on the purified and recycled waste gas, and feeding back to an optimization module for parameter adjustment; and S7, according to waste gas components and process requirements, operation parameters are adjusted in a self-adaptive mode.

Description

Technical Field

[0001] The present invention relates to the technical field of particle swarm optimization, and in particular to a metallurgical waste gas purification and recovery method based on a particle swarm optimization algorithm. Background Art

[0002] With the acceleration of industrialization, the metallurgical industry, as an important part of the industry, has generated a large amount of waste gas during the production process, which poses a severe challenge to the environment and resources. These waste gases contain a variety of harmful substances, including sulfur dioxide, nitrogen oxides, heavy metal particles, etc., as well as rare gases and other valuable components. How to efficiently purify these waste gases, reduce the emission of harmful substances, and maximize the recovery of valuable components has become an important issue that needs to be solved in the metallurgical industry.

[0003] First, the existing metallurgical waste gas purification technology mainly relies on traditional physical and chemical methods, such as dry dust removal, wet desulfurization, catalytic reduction, etc. These methods have certain effects in removing most of the harmful components in the waste gas, but when dealing with complex and changeable waste gas components, they often face problems such as low efficiency, high energy consumption, complex equipment, and high operating costs. Especially when the waste gas composition changes greatly, the purification effect of the existing technology is difficult to guarantee, resulting in the emission of harmful substances failing to meet environmental protection standards, which in turn aggravates environmental pollution.

[0004] Secondly, traditional waste gas treatment technology also has obvious deficiencies in resource recycling. Metallurgical waste gas often contains rare metals and precious gases. These components cannot be effectively recovered during the treatment process of existing technologies due to the limitations of the purification process, resulting in waste of resources. In addition, most existing resource recovery technologies are independent of the waste gas purification system. This separate process not only increases the complexity of the operation, but also reduces the overall resource recovery efficiency, affecting the improvement of economic benefits.

[0005] Third, with the development of computational intelligence and algorithm optimization technology, some advanced optimization algorithms have begun to be applied to the optimization of industrial processes, but in the field of metallurgical waste gas purification, the application of related technologies is still in its infancy. Existing technologies mainly focus on parameter adjustment and single-objective optimization, and lack the ability to globally optimize multi-objective, multi-dimensional complex systems. In addition, most of the existing optimization algorithms are traditional optimization methods, such as gradient descent method, genetic algorithm, etc. These algorithms are prone to fall into local optimal solutions when dealing with large-scale, multi-parameter optimization problems, and it is difficult to effectively solve complex waste gas purification and recovery problems.

[0006] In summary, the existing metallurgical waste gas purification and recovery technology has obvious defects in the following aspects: First, the existing technology has low purification efficiency when dealing with complex and changeable waste gas components, and it is difficult to meet environmental protection requirements; second, the resource recovery effect is poor, and the rare components in the waste gas cannot be fully recovered, resulting in resource waste; third, the existing optimization algorithm is prone to fall into local optimality when dealing with multi-objective optimization problems in complex industrial environments, lacks global optimization capabilities, and leads to low overall system operation efficiency. Therefore, how to provide a metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm is a problem that technicians in this field urgently need to solve. Summary of the invention

[0007] One object of the present invention is to propose a metallurgical waste gas purification and recovery method based on a particle swarm optimization algorithm. The present invention makes full use of the recursive morphological coupling algorithm and the morphological reorganization particle swarm optimization algorithm to perform hierarchical analysis and global optimization of key parameters in the metallurgical waste gas purification and recovery process, thereby improving the removal efficiency of harmful substances, reducing environmental pollution, and achieving the maximum recovery of valuable components in the waste gas, and has the advantages of high purification efficiency, high resource utilization and strong adaptability.

[0008] The metallurgical waste gas purification and recovery method based on the particle swarm optimization algorithm according to an embodiment of the present invention comprises the following steps:

[0009] S1. Perform preliminary pretreatment on the waste gas generated during the metallurgical production process, monitor the temperature, pressure, flow rate and chemical composition of the waste gas in real time through the sensor network, and input the collected data into the optimization module;

[0010] S2. In the optimization module, the key parameters in the exhaust gas purification and recovery process are analyzed hierarchically using the recursive morphological coupling algorithm, the optimization problem is decomposed into multiple sub-problems, and the preliminary operating parameter setting values ​​of each sub-problem are determined;

[0011] S3, based on the preliminary parameter setting values, performing a global search through a morphological reorganization particle swarm optimization algorithm, identifying a potential global optimal solution, and generating an optimized parameter set;

[0012] S4. In the particle swarm optimization process, the evolutionary morphological reorganization algorithm is applied to the identified potential optimal solution to improve the local solution and generate a new set of optimization parameters by dynamically reorganizing the morphological structure of the solution;

[0013] S5. Apply the optimized parameter set to the exhaust gas purification device, dynamically adjust the operating parameters of the purification device through the recursive morphological coupling algorithm, treat harmful substances in the exhaust gas, identify and recover valuable components in the purified exhaust gas, adjust the operating conditions of the recovery device, and realize the recovery of rare components;

[0014] S6. Perform multi-stage detection on the purified and recovered waste gas, record and analyze the emission data. If the emission does not meet the standard, feedback is given to the optimization module, and the parameters are readjusted and iteratively optimized through the morphological reorganization particle swarm optimization algorithm and the recursive morphological coupling algorithm until the waste gas emission meets the standard;

[0015] S7. According to the changes in the composition of metallurgical waste gas and process requirements, the operating parameters in the above steps S1 to S6 are adjusted by optimizing the adaptive function of the module to be suitable for different metallurgical production environments.

[0016] Optionally, S2 includes the following steps:

[0017] S21, classify the key parameter set P involved in the waste gas purification and recovery process according to physical and chemical properties to form multiple dimensional subsets P = {P1, P2, ..., P n}, where each subset P i Contains parameters under a specific dimension, such as temperature P T 、Pressure P P , flow rate P F And chemical composition P C ;

[0018] S22. For each dimension subset P i , using the recursive morphological coupling algorithm to construct a high-order nonlinear coupling tensor T i , where the tensor element T ijk Represents parameter P ij With P ik The multi-dimensional coupling relationship between:

[0019]

[0020] Among them, α im is the dynamic coupling coefficient, which is used to adjust the coupling strength between parameters; β im To adjust the coefficient of nonlinear coupling, it is used to control the decay rate of the exponential function; and They represent the second-order partial derivatives of the parameters, capturing high-order changes; t represents the number of recursive iterations, which is the time step used to update the tensor;

[0021] S23, the constructed high-order nonlinear coupling tensor T i Perform recursive morphological analysis to generate a multidimensional coupling state vector R i , each element Represents parameter P ij Recursive strength in multidimensional coupling state:

[0022]

[0023] Among them, Zi is the normalization factor, which is used to standardize the value of each element; ij is the coupling adjustment coefficient, which adjusts the time-recursive effect of the parameters;

[0024] S24, multi-dimensional coupling state vector R i Combined with the process requirements of metallurgical waste gas purification and recovery, the preliminary operating parameter tensor S is formed i ;

[0025] S25, the initial operation parameter tensor S i Perform multi-level analysis to construct a preliminary global optimization setting matrix M0, and further generate a preliminary operating parameter matrix M1;

[0026] S26, inputting the preliminary operation parameter matrix M1 into the morphological reorganization particle swarm optimization algorithm as the basic input for global search and optimization.

[0027] Optionally, S3 includes the following steps:

[0028] S31, in the initial stage of the morphological reorganization particle swarm optimization algorithm, based on the preliminary operation parameter matrix M1 generated by the recursive morphological coupling algorithm, initialize the particle swarm X = {x1, x2, ..., x N}, where each particle x i =x i1 ,x i2 ,...,x in} represents a possible solution vector, where x i is the position vector of particle i, which contains the values ​​of all dimensional parameters; N represents the number of particle swarms, that is, the total number of particles in the swarm; n is the dimension of the optimization problem, that is, the number of parameters contained in the position vector of each particle;

[0029] S32, the initial velocity of the particle V = {v1, v2, ..., v N} and the initial position P = {p1, p2, ..., p N} is also set to the value associated with the preliminary operating parameter matrix M1, where v i represents the velocity vector of particle i, which represents the velocity of particle i in each dimension; p i It represents the current best position of particle i, which is usually the best solution encountered by the particle so far; M1 is the preliminary operation parameter matrix, which contains the initial optimization parameter values ​​and is used to guide the initial position and speed setting of the particle swarm;

[0030] S33, based on the initial position of each particle, use the morphological reorganization operator to preprocess the position, and the reorganized position of the particle

[0031]

[0032] in, is the position of particle i after the t+1th iteration; is the initial perturbation value of the particle position, which increases the diversity of the search space by introducing randomness; θ ij is the recombination intensity coefficient, which regulates the mutual influence between particles i and j; κ is the recombination regulation coefficient, which is used to control the dynamic change intensity during the recombination process; M ij is an element in the preliminary operation parameter matrix, representing the coupling parameter between the i-th particle and the j-th particle; is the velocity of particle j at the tth iteration, which is used to adjust the position in combination with the velocity;

[0033] S34. In each iteration step, the particle swarm dynamically adapts according to the multi-objective optimization requirements of metallurgical waste gas purification and recovery. i The fitness function By combining multiple objective functions:

[0034]

[0035] in, is the fitness value of particle i at the tth iteration, reflecting the optimization performance of particle i in the current iteration; is the kth objective function, which is used to evaluate the optimization of the specific goal of particle i; w k is the weight of the kth objective function, which is used to balance the priorities between different objectives; is the objective function f k The derivative with respect to time t represents the rate of change of the target over time; is the norm of the recursive coupling vector, which indicates the magnitude of the change of the target under the current coupling state;

[0036] S35. According to the fitness function The results are combined with the iterative rules of the morphological reorganization particle swarm optimization algorithm to update the speed and position of each particle:

[0037]

[0038] in, is the velocity of particle i after the t+1th iteration; ζ is the velocity update coefficient, which controls the inertia weight of the particle and affects the stability of the particle's moving direction; η is the acceleration factor, which adjusts the particle's attraction to the global and local optimal solutions; is the recursive coupling state vector, which represents the response of the particle under different coupling states; is the rate of change of the particle's position with respect to time; is the new position of particle i after the t+1th iteration; σ is the morphological reorganization position adjustment coefficient, which affects the response intensity of the particle to the morphological change; is the individual optimal position of particle i, indicating the best solution of the particle so far; g(t) is the global optimal position of the particle swarm, indicating the current best solution of the entire particle swarm;

[0039] S36. In each iteration, a local optimization process of morphological reorganization is introduced to adaptively reorganize some particles in the particle swarm through nonlinear transformation to further optimize the local solution.

[0040] S37. During the global optimization process, after several iterations, multi-level morphological reorganization optimization is implemented, and multiple local adjustments are made to the particle swarm through coupling and reorganization methods at different levels:

[0041]

[0042] Among them, λ is the global adjustment coefficient of morphological reorganization, which controls the influence of multi-level reorganization; is the weight factor of hierarchical optimization, which adjusts the contribution of different hierarchies in the overall optimization; M 1ik is an element in the preliminary operation parameter matrix, indicating the strength of the morphological coupling relationship;

[0043] S38. After reaching the convergence condition, based on the final result of the morphological reorganization particle swarm optimization algorithm, identify the global optimal solution g(T), and use g(T) as the optimized parameter set S opt , used to guide the next stage of waste gas purification and recovery operations; g (T) It is the global optimal solution after all iterations, indicating the best parameter combination.

[0044] Optionally, S4 includes the following steps:

[0045] S41. In the particle swarm optimization process, from the optimization parameter set S opt The first M particles with the highest fitness values ​​are selected to form the potential optimal solution set G = {g1, g2, ..., g M}, and make a preliminary analysis of the morphological structures of these solutions and calculate the morphological similarity matrix S i ;

[0046] S42. Based on the potential optimal solution set G, the evolutionary morphological reorganization algorithm is used to dynamically reorganize the morphological structure of the solution:

[0047]

[0048] in, is the morphological vector of solution i after the t+1th iteration; α is the morphological recombination intensity coefficient, which adjusts the amplitude of morphological recombination; ω is the frequency adjustment coefficient, which is used to control the frequency of the sine function during the morphological recombination process; W ij is the weight matrix, reflecting the coupling relationship between solutions; It represents the rate of change of solution j with respect to dimension x, capturing the change in the shape of the solution; It is a perturbation term of the morphological structure, which increases the diversity of solutions;

[0049] S43. Based on the morphological reorganization, combined with the morphological reorganization process, the local dynamic coupling mechanism is further introduced to perform recursive optimization. The solution vector after recursive optimization is

[0050]

[0051] in, is the vector of solution i after recursive optimization; γ is the coupling strength coefficient, which regulates the dynamic coupling effect between solutions; is the recursive coupling state vector, which indicates the state of the kth dimension in the current iteration; κ is the coupling adjustment coefficient, which controls the strength of the coupling process; M ik is an element in the preliminary operation parameter matrix, representing the coupling relationship between solution i and the kth dimension;

[0052] S44, based on the recursive optimization, the local structure of the solution is deeply optimized through nonlinear transformation, and the optimized local solution vector

[0053]

[0054] in, is the vector of solution i after local depth optimization; δ is the local optimization intensity coefficient, which controls the amplitude of nonlinear transformation; tanh is the hyperbolic tangent function, which is used in the nonlinear optimization process; is the local optimization contribution coefficient, which regulates the mutual influence between local solutions; It is the local parameter set obtained by the previous optimization, which serves as the basis for guiding the deep optimization;

[0055] S45. After the local depth optimization is completed, the global structure of the entire solution is optimized by combining the multi-level morphological reorganization process. The final optimized solution vector

[0056]

[0057] in, is the optimization vector of solution i after the final morphological reorganization; ζ is the global morphological optimization coefficient, which adjusts the amplitude of multi-level optimization; ψp is the hierarchical optimization weight factor, which controls the contribution of different structural levels in the global optimization; M ip is the element in the preliminary operation parameter matrix, which represents the coupling relationship between solutions; β is the morphological reorganization adjustment coefficient, which affects the dynamic adjustment of the hierarchical structure;

[0058] S46. After the above multi-level morphological reorganization and global optimization, the final optimized parameter set S is generated. final Represents the optimal solution set obtained after all optimization steps; It is the optimization vector obtained after the final iteration of each solution, which is used to guide the process parameter setting in the next stage.

[0059] Optionally, S5 includes the following steps:

[0060] S51, generate the final optimization parameter set S final Mapped to the initial operating parameter set C of the exhaust gas purification device (0) The mapping process combines morphological reorganization with multi-dimensional coupling optimization to optimize the vector Conversion into control parameter sets for purification units

[0061] S52. In the exhaust gas purification process, the recursive morphological coupling algorithm is used to dynamically adjust the operating parameter set C(t) at multiple levels. By introducing nonlinear coupling and dynamic frequency regulation, the operating parameter set is updated over time:

[0062]

[0063] Among them, γ i is the recursive adjustment strength coefficient, which controls the amplitude of parameter adjustment; is the recursive coupling matrix, regulating the dynamic relationship between parameters; α ik is the nonlinear coupling coefficient; β i is the frequency adjustment coefficient, which controls the periodicity of dynamic adjustment; T ik (t) is a time-dependent phase shift function; S53, through the dynamically adjusted operating parameter set C(t), the exhaust gas purification device operates under optimized conditions to remove harmful substances. The optimization of the purification process is based on a high-order multi-objective function Maximization of the function Incorporating nonlinear and coupled effects:

[0064]

[0065] Among them, η j is the weight of the objective function, reflecting the priority of different hazardous substances; j is the nonlinear adjustment coefficient, which adjusts the amplitude during the purification process; ζj is the high-order coupling coefficient; G j (t) is a time-dependent gain function used to dynamically amplify the purification effect;

[0066] S54. During the purification process, based on the analysis of the recursive morphological coupling algorithm, the rare components in the purified exhaust gas are identified, and the operating parameters R(t) of the recovery device are dynamically adjusted. Multidimensional nonlinear optimization is introduced into the recovery process to achieve maximum recovery efficiency:

[0067]

[0068] Among them, R l (t) is the vector of the operating parameters of the recovery device at time t; θ is the dynamic adjustment coefficient of the recovery process; is the contribution coefficient of recycling optimization, which adjusts the recycling priority of rare components; ψ p is a nonlinear adjustment factor that controls the complexity of the recycling process; V p (t) is the concentration function of the rare component, which varies with time;

[0069] S55, using the above-mentioned dynamically adjusted recovery parameter R l (t), further optimize the recovery efficiency of rare components, and the final optimization objective function of the recovery process It is defined by a complex nonlinear combination as follows:

[0070]

[0071] in, is the optimization objective function of recovery efficiency; s is the weight of the objective function, which adjusts the priority of rare components; β s is the nonlinear regulation frequency, used to control the periodicity of the recovery efficiency; s is the gain adjustment coefficient, which amplifies the specific signal in the recycling process; s is a time-dependent nonlinear coefficient that controls the complexity of the recycling process;

[0072] S56. During the entire purification and recovery process, the emission concentration, energy consumption, and recovery rate are monitored in real time. The feedback data will be input into the recursive morphological coupling algorithm to dynamically adjust the operating parameters C(t) and R(t).

[0073] The beneficial effects of the present invention are:

[0074] (1) The present invention proposes a metallurgical waste gas purification and recovery method based on a particle swarm optimization algorithm. The metallurgical waste gas is pre-treated, and the physical and chemical parameters of the waste gas are monitored in real time. These data are input into the optimization module. Combined with the recursive morphological coupling algorithm, the key parameters in the waste gas purification and recovery process are analyzed hierarchically. During the optimization process, the morphological reorganization particle swarm optimization algorithm is used to perform a global search, identify potential global optimal solutions, and generate an optimized parameter set. This process effectively improves the removal rate of harmful substances in the waste gas, reduces the negative impact on the environment during the purification process, and ensures that the rare components in the waste gas can be efficiently identified and recovered, thereby improving resource utilization.

[0075] (2) The present invention introduces a dynamic adaptive recursive morphological coupling algorithm. By applying the evolutionary morphological recombination algorithm to the identified potential optimal solution, the dynamic parameter adjustment of the purification and recovery device is realized, which can adapt to the changes in different metallurgical production environments. By real-time detection of the purified and recovered waste gas, the system can readjust parameters and iteratively optimize according to the feedback data to ensure that the waste gas emissions meet the standards and minimize the waste of resources. This process not only improves the adaptive ability of the system, but also reduces the operating cost, making waste gas purification and resource recovery more efficient and economical.

[0076] (3) The present invention adopts a combination of morphological reorganization particle swarm optimization algorithm and recursive morphological coupling algorithm to achieve global and local dual optimization for complex multi-objective optimization problems in metallurgical waste gas treatment by applying and adjusting the optimization parameter set. In this process, the system can effectively handle complex and variable waste gas components, improve purification efficiency and resource recovery rate, and show good adaptability and stability under different metallurgical production process conditions. Finally, through the multi-level and multi-stage optimization of the system, an efficient, environmentally friendly and economical metallurgical waste gas treatment effect is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0078] Figure 1 This is a flow chart of the metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm proposed by the present invention;

[0079] Figure 2 This is a schematic diagram of the hierarchical analysis of key parameters in the exhaust gas purification and recovery process by the recursive morphological coupling algorithm proposed in the present invention;

[0080] Figure 3 This is a flow chart of the morphological reorganization particle swarm optimization algorithm proposed in the present invention for global search and optimization. DETAILED DESCRIPTION

[0081] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0082] refer to Figure 1-3 , a metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm includes the following steps:

[0083] S1. Perform preliminary pretreatment on the waste gas generated during the metallurgical production process, monitor the temperature, pressure, flow rate and chemical composition of the waste gas in real time through the sensor network, and input the collected data into the optimization module;

[0084] S2. In the optimization module, the key parameters in the exhaust gas purification and recovery process are analyzed hierarchically using the recursive morphological coupling algorithm, the optimization problem is decomposed into multiple sub-problems, and the preliminary operating parameter setting values ​​of each sub-problem are determined;

[0085] S3, based on the preliminary parameter setting values, performing a global search through a morphological reorganization particle swarm optimization algorithm, identifying a potential global optimal solution, and generating an optimized parameter set;

[0086] S4. In the particle swarm optimization process, the evolutionary morphological reorganization algorithm is applied to the identified potential optimal solution to improve the local solution and generate a new set of optimization parameters by dynamically reorganizing the morphological structure of the solution;

[0087] S5. Apply the optimized parameter set to the exhaust gas purification device, dynamically adjust the operating parameters of the purification device through the recursive morphological coupling algorithm, treat harmful substances in the exhaust gas, identify and recover valuable components in the purified exhaust gas, adjust the operating conditions of the recovery device, and realize the recovery of rare components;

[0088] S6. Perform multi-stage detection on the purified and recovered waste gas, record and analyze the emission data. If the emission does not meet the standard, feedback is given to the optimization module, and the parameters are readjusted and iteratively optimized through the morphological reorganization particle swarm optimization algorithm and the recursive morphological coupling algorithm until the waste gas emission meets the standard;

[0089] S7. According to the changes in the composition of metallurgical waste gas and process requirements, the operating parameters in the above steps S1 to S6 are adjusted by optimizing the adaptive function of the module to be suitable for different metallurgical production environments.

[0090] In this implementation, S2 includes the following steps:

[0091] S21, classify the key parameter set P involved in the waste gas purification and recovery process according to physical and chemical properties to form multiple dimensional subsets P = {P1, P2, ..., P n}, where each subset P i Contains parameters under a specific dimension, such as temperature P T 、Pressure P P , flow rate P F And chemical composition P C ;

[0092] S22. For each dimension subset P i , using the recursive morphological coupling algorithm to construct a high-order nonlinear coupling tensor T i , where the tensor element T ijk Represents parameter P ij With P ik The multi-dimensional coupling relationship between:

[0093]

[0094] Among them, α im is the dynamic coupling coefficient, which is used to adjust the coupling strength between parameters; β im To adjust the coefficient of nonlinear coupling, it is used to control the decay rate of the exponential function; and They represent the second-order partial derivatives of the parameters, capturing high-order changes; t represents the number of recursive iterations, which is the time step used to update the tensor;

[0095] S23, the constructed high-order nonlinear coupling tensor T i Perform recursive morphological analysis to generate a multidimensional coupling state vector R i , each element Represents parameter P ij Recursive strength in multidimensional coupling state:

[0096]

[0097] Among them, Z i is the normalization factor, which is used to standardize the value of each element; ij is the coupling adjustment coefficient, which adjusts the time-recursive effect of the parameters;

[0098] S24, multi-dimensional coupling state vector R i Combined with the process requirements of metallurgical waste gas purification and recovery, the preliminary operating parameter tensor S is formed i ;

[0099] S25, the initial operation parameter tensor S iPerform multi-level analysis to construct a preliminary global optimization setting matrix M0, and further generate a preliminary operating parameter matrix M1;

[0100] S26, inputting the preliminary operation parameter matrix M1 into the morphological reorganization particle swarm optimization algorithm as the basic input for global search and optimization.

[0101] In this implementation, S3 includes the following steps:

[0102] S31, in the initial stage of the morphological reorganization particle swarm optimization algorithm, based on the preliminary operation parameter matrix M1 generated by the recursive morphological coupling algorithm, initialize the particle swarm X = {x1, x2, ..., x N}, where each particle x i =x i1 ,x i2 ,...,x in} represents a possible solution vector, where x i is the position vector of particle i, which contains the values ​​of all dimensional parameters; N represents the number of particle swarms, that is, the total number of particles in the swarm; n is the dimension of the optimization problem, that is, the number of parameters contained in the position vector of each particle;

[0103] S32, the initial velocity of the particle V = {v1, v2, ..., v N} and the initial position P = {p1, p2, ..., p N} is also set to the value associated with the preliminary operating parameter matrix M1, where v i represents the velocity vector of particle i, which represents the velocity of particle i in each dimension; p i It represents the current best position of particle i, which is usually the best solution encountered by the particle so far; M1 is the preliminary operation parameter matrix, which contains the initial optimization parameter values ​​and is used to guide the initial position and speed setting of the particle swarm;

[0104] S33, based on the initial position of each particle, use the morphological reorganization operator to preprocess the position, and the reorganized position of the particle

[0105]

[0106] in, is the position of particle i after the t+1th iteration; is the initial perturbation value of the particle position, which increases the diversity of the search space by introducing randomness; θ ij is the recombination intensity coefficient, which regulates the mutual influence between particles i and j; κ is the recombination regulation coefficient, which is used to control the dynamic change intensity during the recombination process; M ijis an element in the preliminary operation parameter matrix, representing the coupling parameter between the i-th particle and the j-th particle; is the velocity of particle j at the tth iteration, which is used to adjust the position in combination with the velocity;

[0107] S34. In each iteration step, the particle swarm dynamically adapts according to the multi-objective optimization requirements of metallurgical waste gas purification and recovery. i The fitness function By combining multiple objective functions:

[0108]

[0109] in, is the fitness value of particle i at the tth iteration, reflecting the optimization performance of particle i in the current iteration; is the kth objective function, which is used to evaluate the optimization of the specific goal of particle i; w k is the weight of the kth objective function, which is used to balance the priorities between different objectives; is the objective function f k The derivative with respect to time t represents the rate of change of the target over time; is the norm of the recursive coupling vector, which indicates the magnitude of the change of the target under the current coupling state;

[0110] S35. According to the fitness function The results are combined with the iterative rules of the morphological reorganization particle swarm optimization algorithm to update the speed and position of each particle:

[0111]

[0112] in, is the velocity of particle i after the t+1th iteration; ζ is the velocity update coefficient, which controls the inertia weight of the particle and affects the stability of the particle's moving direction; η is the acceleration factor, which adjusts the particle's attraction to the global and local optimal solutions; is the recursive coupling state vector, which represents the response of the particle under different coupling states; is the rate of change of the particle's position with respect to time; is the new position of particle i after the t+1th iteration; σ is the morphological reorganization position adjustment coefficient, which affects the response intensity of the particle to the morphological change; is the individual optimal position of particle i, indicating the best solution of the particle so far; g (t) is the global optimal position of the particle swarm, indicating the current best solution of the entire particle swarm;

[0113] S36. In each iteration, a local optimization process of morphological reorganization is introduced to adaptively reorganize some particles in the particle swarm through nonlinear transformation to further optimize the local solution.

[0114] S37. During the global optimization process, after several iterations, multi-level morphological reorganization optimization is implemented, and multiple local adjustments are made to the particle swarm through coupling and reorganization methods at different levels:

[0115]

[0116] Among them, λ is the global adjustment coefficient of morphological reorganization, which controls the influence of multi-level reorganization; is the weight factor of hierarchical optimization, which adjusts the contribution of different hierarchies in the overall optimization; M 1ik is an element in the preliminary operation parameter matrix, indicating the strength of the morphological coupling relationship;

[0117] S38. After reaching the convergence condition, the global optimal solution g is identified based on the final result of the morphological reorganization particle swarm optimization algorithm. (T) , and g (T) As the optimized parameter set S opt , used to guide the next stage of waste gas purification and recovery operations; g (T) It is the global optimal solution after all iterations, indicating the best parameter combination.

[0118] In this implementation, S4 includes the following steps:

[0119] S41. In the particle swarm optimization process, from the optimization parameter set S opt The first M particles with the highest fitness values ​​are selected to form the potential optimal solution set G = {g1, g2, ..., g M}, and make a preliminary analysis of the morphological structures of these solutions and calculate the morphological similarity matrix S i ;

[0120] S42. Based on the potential optimal solution set G, the evolutionary morphological reorganization algorithm is used to dynamically reorganize the morphological structure of the solution:

[0121]

[0122] in, is the morphological vector of solution i after the t+1th iteration; α is the morphological recombination intensity coefficient, which adjusts the amplitude of morphological recombination; ω is the frequency adjustment coefficient, which is used to control the frequency of the sine function during the morphological recombination process; W ij is the weight matrix, reflecting the coupling relationship between solutions; It represents the rate of change of solution j with respect to dimension x, capturing the change in the shape of the solution; It is a perturbation term of the morphological structure, which increases the diversity of solutions;

[0123] S43. Based on the morphological reorganization, combined with the morphological reorganization process, the local dynamic coupling mechanism is further introduced to perform recursive optimization. The solution vector after recursive optimization is

[0124]

[0125] in, is the vector of solution i after recursive optimization; γ is the coupling strength coefficient, which regulates the dynamic coupling effect between solutions; is the recursive coupling state vector, which indicates the state of the kth dimension in the current iteration; κ is the coupling adjustment coefficient, which controls the strength of the coupling process; M ik is an element in the preliminary operation parameter matrix, representing the coupling relationship between solution i and the kth dimension;

[0126] S44, based on the recursive optimization, the local structure of the solution is deeply optimized through nonlinear transformation, and the optimized local solution vector

[0127]

[0128] in, is the vector of solution i after local depth optimization; δ is the local optimization intensity coefficient, which controls the amplitude of nonlinear transformation; tanh is the hyperbolic tangent function, which is used in the nonlinear optimization process; is the local optimization contribution coefficient, which regulates the mutual influence between local solutions; It is the local parameter set obtained by the previous optimization, which serves as the basis for guiding the deep optimization;

[0129] S45. After the local depth optimization is completed, the global structure of the entire solution is optimized by combining the multi-level morphological reorganization process. The final optimized solution vector

[0130]

[0131] in, is the optimization vector of solution i after the final morphological reorganization; ζ is the global morphological optimization coefficient, which adjusts the amplitude of multi-level optimization; ψ p is the hierarchical optimization weight factor, which controls the contribution of different structural levels in the global optimization; M ip is the element in the preliminary operation parameter matrix, which represents the coupling relationship between solutions; β is the morphological reorganization adjustment coefficient, which affects the dynamic adjustment of the hierarchical structure;

[0132] S46. After the above multi-level morphological reorganization and global optimization, the final optimized parameter set S is generated. final Represents the optimal solution set obtained after all optimization steps; It is the optimization vector obtained after the final iteration of each solution, which is used to guide the process parameter setting in the next stage.

[0133] In this implementation, S5 includes the following steps:

[0134] S51, generate the final optimization parameter set S final Mapped to the initial operating parameter set C(0) of the exhaust gas purification device, the mapping process combines morphological reorganization with multi-dimensional coupling optimization to optimize the vector Conversion into control parameter sets for purification units

[0135] S52. In the exhaust gas purification process, the recursive morphological coupling algorithm is used to dynamically adjust the operating parameter set C(t) at multiple levels. By introducing nonlinear coupling and dynamic frequency regulation, the operating parameter set is updated over time:

[0136]

[0137] Among them, γ i is the recursive adjustment strength coefficient, which controls the amplitude of parameter adjustment; is the recursive coupling matrix, regulating the dynamic relationship between parameters; α ik is the nonlinear coupling coefficient; β i is the frequency adjustment coefficient, which controls the periodicity of dynamic adjustment; T ik (t) is a time-dependent phase shift function; S53, through the dynamically adjusted operating parameter set C(t), the exhaust gas purification device operates under optimized conditions to remove harmful substances. The optimization of the purification process is based on a high-order multi-objective function Maximization of the function Incorporating nonlinear and coupled effects:

[0138]

[0139] Among them, η j is the weight of the objective function, reflecting the priority of different hazardous substances; j is the nonlinear adjustment coefficient, which adjusts the amplitude during the purification process; ζ j is the high-order coupling coefficient; G j (t) is a time-dependent gain function used to dynamically amplify the purification effect;

[0140] S54. During the purification process, based on the analysis of the recursive morphological coupling algorithm, the rare components in the purified exhaust gas are identified, and the operating parameters R(t) of the recovery device are dynamically adjusted. Multidimensional nonlinear optimization is introduced into the recovery process to achieve maximum recovery efficiency:

[0141]

[0142] Among them, R l (t) is the vector of the operating parameters of the recovery device at time t; θ is the dynamic adjustment coefficient of the recovery process; is the contribution coefficient of recycling optimization, which adjusts the recycling priority of rare components; ψ p is a nonlinear adjustment factor that controls the complexity of the recycling process; V p (t) is the concentration function of the rare component, which varies with time;

[0143] S55, using the above-mentioned dynamically adjusted recovery parameter R l (t), further optimize the recovery efficiency of rare components, and the final optimization objective function of the recovery process It is defined by a complex nonlinear combination as follows:

[0144]

[0145] in, is the optimization objective function of recovery efficiency; s is the weight of the objective function, which adjusts the priority of rare components; β s is the nonlinear regulation frequency, used to control the periodicity of the recovery efficiency; s is the gain adjustment coefficient, which amplifies the specific signal in the recycling process; s is a time-dependent nonlinear coefficient that controls the complexity of the recycling process;

[0146] S56. During the entire purification and recovery process, the emission concentration, energy consumption, and recovery rate are monitored in real time. The feedback data will be input into the recursive morphological coupling algorithm to dynamically adjust the operating parameters C(t) and R(t).

[0147] Embodiment 1:

[0148] In the production process of a large metallurgical plant, the waste gas generated during high-temperature smelting contains a large amount of harmful substances such as sulfur dioxide, nitrogen oxides and heavy metal particles. These waste gases not only cause serious pollution to the environment, but also contain rare gases and precious metal components such as argon, helium and palladium metal. If they are not effectively treated and recycled, they will not only aggravate environmental pollution, but also cause waste of resources. The metallurgical plant is located in an environmentally sensitive area surrounded by multiple residential areas, so the standards for waste gas emissions are very strict. Traditional waste gas treatment technology has been unable to meet the increasingly stringent emission standards and resource recovery requirements.

[0149] The metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm of the present invention is applied to the waste gas treatment system of the metallurgical plant. First, during the smelting process, the waste gas is collected and introduced into the pretreatment device, and the temperature, pressure, flow rate and chemical composition of the waste gas are monitored in real time through the sensor network, and these data are transmitted to the optimization module in real time. In the optimization module, the recursive morphological coupling algorithm is used to analyze and resolve these data, decomposing the complex waste gas treatment problem into multiple sub-problems, and each sub-problem sets preliminary operating parameters according to its physical and chemical properties.

[0150] Next, the morphological reorganization particle swarm optimization algorithm begins a global search within the initially set parameter range, identifies potential optimal solutions and generates optimized parameter sets. These parameter sets are applied to the exhaust gas purification device, and the operating parameters of the purification device are dynamically adjusted through the recursive morphological coupling algorithm, so that the purification device can efficiently remove harmful substances in the exhaust gas and identify and recover rare components in the exhaust gas.

[0151] During the entire purification process, the system will continuously monitor the purified waste gas and feed back the detected emission data to the optimization module. If it is found that the emission does not meet the standard, the system will immediately readjust the parameters and iterate the optimization through the morphological reorganization particle swarm optimization algorithm and the recursive morphological coupling algorithm until the waste gas emissions meet the environmental protection standards. At the same time, the system can dynamically adjust the operating parameters according to the changes in the composition of metallurgical waste gas and the production process requirements, so that the method can adapt to different metallurgical production environments.

[0152] Data Proof

[0153] Table 1 Performance data of metallurgical waste gas purification and recovery system

[0154]

[0155]

[0156] Through application in actual production environments, the metallurgical waste gas purification and recovery method of the present invention significantly improves waste gas treatment efficiency and resource recovery rate, and reduces energy consumption and operating costs. At the same time, the equipment operation is more stable, reducing downtime and maintenance costs, providing an efficient, economical and environmentally friendly waste gas treatment solution for the metallurgical industry.

[0157] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm, characterized in that: The steps include: S1. Perform preliminary pretreatment on the waste gas generated during the metallurgical production process, monitor the temperature, pressure, flow rate and chemical composition of the waste gas in real time through the sensor network, and input the collected data into the optimization module; S2. In the optimization module, the key parameters in the exhaust gas purification and recovery process are analyzed hierarchically using the recursive morphological coupling algorithm, the optimization problem is decomposed into multiple sub-problems, and the preliminary operating parameter setting values ​​of each sub-problem are determined; S3, based on the preliminary parameter setting values, performing a global search through a morphological reorganization particle swarm optimization algorithm, identifying a potential global optimal solution, and generating an optimized parameter set; S4. In the particle swarm optimization process, the evolutionary morphological reorganization algorithm is applied to the identified potential optimal solution to improve the local solution and generate a new set of optimization parameters by dynamically reorganizing the morphological structure of the solution; S5. Apply the optimized parameter set to the exhaust gas purification device, dynamically adjust the operating parameters of the purification device through the recursive morphological coupling algorithm, treat harmful substances in the exhaust gas, identify and recover valuable components in the purified exhaust gas, adjust the operating conditions of the recovery device, and realize the recovery of rare components; S6. Perform multi-stage detection on the purified and recovered waste gas, record and analyze the emission data. If the emission does not meet the standard, feedback is given to the optimization module, and the parameters are readjusted and iteratively optimized through the morphological reorganization particle swarm optimization algorithm and the recursive morphological coupling algorithm until the waste gas emission meets the standard; S7. According to the changes in the composition of metallurgical waste gas and process requirements, the operating parameters in the above steps S1 to S6 are adjusted by optimizing the adaptive function of the module to be suitable for different metallurgical production environments.

2. The metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm according to claim 1 is characterized in that: The S2 comprises the following steps: S21, classify the key parameter set P involved in the waste gas purification and recovery process according to physical and chemical properties to form multiple dimensional subsets P = {P1, P2, ..., P n }, where each subset P i Contains parameters under a specific dimension, such as temperature P T 、Pressure P P , flow rate P F And chemical composition P C ; S22. For each dimension subset P i , using the recursive morphological coupling algorithm to construct a high-order nonlinear coupling tensor T i , where the tensor element T ijk Represents parameter P ij With P ik The multi-dimensional coupling relationship between: Among them, α im is the dynamic coupling coefficient, which is used to adjust the coupling strength between parameters; β im To adjust the coefficient of nonlinear coupling, it is used to control the decay rate of the exponential function; and They represent the second-order partial derivatives of the parameters, capturing high-order changes; t represents the number of recursive iterations, which is the time step used to update the tensor; S23, the constructed high-order nonlinear coupling tensor T i Perform recursive morphological analysis to generate a multidimensional coupled state vector R i , each element Represents parameter P ij Recursive strength in multidimensional coupling state: Among them, Z i is the normalization factor, which is used to standardize the value of each element; ij is the coupling adjustment coefficient, which adjusts the time-recursive effect of the parameters; S24, multi-dimensional coupling state vector R i Combined with the process requirements of metallurgical waste gas purification and recovery, the preliminary operating parameter tensor S is formed i ; S25, the initial operation parameter tensor S i Perform multi-level analysis to construct a preliminary global optimization setting matrix M0, and further generate a preliminary operating parameter matrix M1; S26, inputting the preliminary operation parameter matrix M1 into the morphological reorganization particle swarm optimization algorithm as the basic input for global search and optimization.

3. The metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm according to claim 1 is characterized in that: The S3 comprises the following steps: S31, in the initial stage of the morphological reorganization particle swarm optimization algorithm, based on the preliminary operation parameter matrix M1 generated by the recursive morphological coupling algorithm, initialize the particle swarm X = {x1, x2, ..., x N }, where each particle x i =x i1 ,x i2 ,...,x in } represents a possible solution vector, where x i is the position vector of particle i, which contains the values ​​of all dimensional parameters; N represents the number of particle swarms, that is, the total number of particles in the swarm; n is the dimension of the optimization problem, that is, the number of parameters contained in the position vector of each particle; S32, the initial velocity of the particle V = {v1, v2, ..., v N } and the initial position P = {p1, p2, ..., p N } is also set to the value associated with the preliminary operating parameter matrix M1, where v i represents the velocity vector of particle i, which represents the velocity of particle i in each dimension; p i It represents the current best position of particle i, which is usually the best solution encountered by the particle so far; M1 is the preliminary operation parameter matrix, which contains the initial optimization parameter values ​​and is used to guide the initial position and speed setting of the particle swarm; S33, based on the initial position of each particle, use the morphological reorganization operator to preprocess the position, and the reorganized position of the particle in, is the position of particle i after the t+1th iteration; is the initial perturbation value of the particle position, which increases the diversity of the search space by introducing randomness; θ ij is the recombination intensity coefficient, which regulates the mutual influence between particles i and j; κ is the recombination regulation coefficient, which is used to control the dynamic change intensity during the recombination process; M ij is an element in the preliminary operation parameter matrix, representing the coupling parameter between the i-th particle and the j-th particle; is the velocity of particle j at the tth iteration, which is used to adjust the position in combination with the velocity; S34. In each iteration step, the particle swarm dynamically adapts according to the multi-objective optimization requirements of metallurgical waste gas purification and recovery. i The fitness function By combining multiple objective functions: in, is the fitness value of particle i at the tth iteration, reflecting the optimization performance of particle i in the current iteration; is the kth objective function, which is used to evaluate the optimization of the specific goal of particle i; w k is the weight of the kth objective function, which is used to balance the priorities between different objectives; is the objective function f k The derivative with respect to time t represents the rate of change of the target over time; is the norm of the recursive coupling vector, which indicates the magnitude of the change of the target under the current coupling state; S35. According to the fitness function The results are combined with the iterative rules of the morphological reorganization particle swarm optimization algorithm to update the speed and position of each particle: in, is the velocity of particle i after the t+1th iteration; ζ is the velocity update coefficient, which controls the inertia weight of the particle and affects the stability of the particle's moving direction; η is the acceleration factor, which adjusts the particle's attraction to the global and local optimal solutions; is the recursive coupling state vector, which represents the response of the particle under different coupling states; is the rate of change of the particle's position with respect to time; is the new position of particle i after the t+1th iteration; σ is the morphological reorganization position adjustment coefficient, which affects the response intensity of the particle to the morphological change; is the individual optimal position of particle i, indicating the best solution of the particle so far; g( t ) is the global optimal position of the particle swarm, indicating the current best solution of the entire particle swarm; S36. In each iteration, a local optimization process of morphological reorganization is introduced to adaptively reorganize some particles in the particle swarm through nonlinear transformation to further optimize the local solution. S37. During the global optimization process, after several iterations, multi-level morphological reorganization optimization is implemented, and multiple local adjustments are made to the particle swarm through coupling and reorganization methods at different levels: Among them, λ is the global adjustment coefficient of morphological reorganization, which controls the influence of multi-level reorganization; is the weight factor of hierarchical optimization, which adjusts the contribution of different hierarchies in the overall optimization; M 1ik is an element in the preliminary operation parameter matrix, indicating the strength of the morphological coupling relationship; S38. After reaching the convergence condition, based on the final result of the morphological reorganization particle swarm optimization algorithm, identify the global optimal solution g(T), and use g(T) as the optimized parameter set S opt , which is used to guide the next stage of exhaust gas purification and recovery operations; g(T) is the global optimal solution after all iterations, indicating the best parameter combination.

4. The metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm according to claim 1 is characterized in that: The S4 comprises the following steps: S41, in the particle swarm optimization process, from the optimization parameter set S opt The first M particles with the highest fitness values ​​are selected to form the potential optimal solution set G = {g1, g2, ..., g M }, and make a preliminary analysis of the morphological structures of these solutions and calculate the morphological similarity matrix S i ; S42. Based on the potential optimal solution set G, the evolutionary morphological reorganization algorithm is used to dynamically reorganize the morphological structure of the solution: in, is the morphological vector of solution i after the t+1th iteration; α is the morphological recombination intensity coefficient, which adjusts the amplitude of morphological recombination; ω is the frequency adjustment coefficient, which is used to control the frequency of the sine function during the morphological recombination process; W ij is the weight matrix, reflecting the coupling relationship between solutions; It represents the rate of change of solution j with respect to dimension x, capturing the change in the shape of the solution; It is a perturbation term of the morphological structure, which increases the diversity of solutions; S43. Based on the morphological reorganization, combined with the morphological reorganization process, the local dynamic coupling mechanism is further introduced to perform recursive optimization. The solution vector after recursive optimization is in, is the vector of solution i after recursive optimization; γ is the coupling strength coefficient, which regulates the dynamic coupling effect between solutions; is the recursive coupling state vector, which indicates the state of the kth dimension in the current iteration; κ is the coupling adjustment coefficient, which controls the strength of the coupling process; M ik is an element in the preliminary operation parameter matrix, representing the coupling relationship between solution i and the kth dimension; S44, based on the recursive optimization, the local structure of the solution is deeply optimized through nonlinear transformation, and the optimized local solution vector in, is the vector of solution i after local depth optimization; δ is the local optimization intensity coefficient, which controls the amplitude of nonlinear transformation; tanh is the hyperbolic tangent function, which is used in the nonlinear optimization process; It is the local optimization contribution coefficient, which regulates the mutual influence between local solutions; It is the local parameter set obtained by the previous optimization, which serves as the basis for guiding the deep optimization; S45. After the local depth optimization is completed, the global structure of the entire solution is optimized by combining the multi-level morphological reorganization process. The final optimized solution vector in, is the optimization vector of solution i after the final morphological reorganization; ζ is the global morphological optimization coefficient, which adjusts the amplitude of multi-level optimization; ψ p is the hierarchical optimization weight factor, which controls the contribution of different structural levels in the global optimization; M ip is the element in the preliminary operation parameter matrix, which represents the coupling relationship between solutions; β is the morphological reorganization adjustment coefficient, which affects the dynamic adjustment of the hierarchical structure; S46. After the above multi-level morphological reorganization and global optimization, the final optimized parameter set S is generated. final Represents the optimal solution set obtained after all optimization steps; It is the optimization vector obtained after the final iteration of each solution, which is used to guide the process parameter setting in the next stage.

5. The metallurgical waste gas purification and recovery method based on particle swarm optimization algorithm according to claim 1 is characterized in that: The S5 comprises the following steps: S51, generate the final optimization parameter set S final Mapped to the initial operating parameter set C(0) of the exhaust gas purification device, the mapping process combines morphological reorganization with multi-dimensional coupling optimization to optimize the vector Conversion into control parameter sets for purification units S52. In the exhaust gas purification process, the recursive morphological coupling algorithm is used to dynamically adjust the operating parameter set C(t) at multiple levels. By introducing nonlinear coupling and dynamic frequency regulation, the operating parameter set is updated over time: Among them, γ i is the recursive adjustment intensity coefficient, which controls the amplitude of parameter adjustment; is the recursive coupling matrix, regulating the dynamic relationship between parameters; α ik is the nonlinear coupling coefficient; β i is the frequency adjustment coefficient, which controls the periodicity of dynamic adjustment; T ik (t) is a time-dependent phase shift function; S53, through the dynamically adjusted operating parameter set C(t), the exhaust gas purification device operates under optimized conditions to remove harmful substances. The optimization of the purification process is based on a high-order multi-objective function Maximization of the function Incorporating nonlinear and coupled effects: Among them, η j is the weight of the objective function, reflecting the priority of different hazardous substances; j is the nonlinear adjustment coefficient, which adjusts the amplitude during the purification process; ζ j is the high-order coupling coefficient; G j (t) is a time-dependent gain function used to dynamically amplify the purification effect; S54. During the purification process, based on the analysis of the recursive morphological coupling algorithm, the rare components in the purified exhaust gas are identified, and the operating parameters R(t) of the recovery device are dynamically adjusted. Multidimensional nonlinear optimization is introduced into the recovery process to achieve maximum recovery efficiency: Among them, R l (t) is the vector of the operating parameters of the recovery device at time t; θ is the dynamic adjustment coefficient of the recovery process; is the contribution coefficient of recycling optimization, which adjusts the recycling priority of rare components; ψ p is a nonlinear adjustment factor that controls the complexity of the recycling process; V p (t) is the concentration function of the rare component, which varies with time; S55, using the above-mentioned dynamically adjusted recovery parameter R l (t), further optimize the recovery efficiency of rare components, and the final optimization objective function of the recovery process It is defined by a complex nonlinear combination as follows: in, is the optimization objective function of recovery efficiency; s is the weight of the objective function, which adjusts the priority of rare components; β s is the nonlinear regulation frequency, used to control the periodicity of the recovery efficiency; s is the gain adjustment coefficient, which amplifies the specific signal in the recycling process; s is a time-dependent nonlinear coefficient that controls the complexity of the recycling process; S56. During the entire purification and recovery process, the emission concentration, energy consumption, and recovery rate are monitored in real time. The feedback data will be input into the recursive morphological coupling algorithm to dynamically adjust the operating parameters C(t) and R(t).

Images