Modified red mud proportioning optimization method and system based on strength, cost and carbon emission

Abstract

The invention belongs to the crossing field of carbon emission and red mud resource utilization technologies, and discloses a modified red mud proportion optimization method and system based on strength, cost and carbon emission. The method comprises the following steps: establishing a modified red mud road material proportioning multi-objective optimization model; obtaining an optimal set of the mix proportion schemes of the modified red mud road material needing to be evaluated; determining weights of three evaluation indexes, namely strength, cost and carbon emission in the optimal set of the scheme by adopting an entropy weight method; a TOPSIS decision-making method is adopted to evaluate the relative sequence of all the schemes in the scheme optimal set, and the optimal mix proportion scheme is selected.

Description

Technical Field

[0001] The present invention belongs to the cross-field of carbon emission and red mud resource utilization technology, and in particular relates to a modified red mud ratio optimization method and system based on strength, cost and carbon emission. Background Art

[0002] Red mud is an industrial solid waste discharged when the aluminum industry extracts alumina. With the development of the aluminum industry and the reduction of the grade of bauxite ore, the stock of red mud is increasing. Therefore, the comprehensive utilization of red mud is becoming an increasingly important research topic. Red mud modification and solidification can be used for projects such as roadbed filling and road base stabilization gravel. These engineering applications have corresponding technical requirements for the strength of modified red mud road materials. However, there are many factors that affect the strength of red mud road materials, including the amount of curing agent, moisture content, and curing age. Conducting physical tests to determine the strength corresponding to each mix ratio scheme will consume a lot of manpower, material resources and time. At the same time, cost control is also a crucial link in the process of engineering design and implementation. Reasonable cost budgeting and effective cost management can significantly improve the economic benefits of the project. While pursuing cost-effectiveness, engineering applications must also ensure that the quality and safety standards of the project are not affected. This requires finding an appropriate balance between cost control and quality assurance, that is, cost and strength. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the disclosed embodiments of the present invention provide a modified red mud ratio optimization method and system based on strength, cost and carbon emissions. The purpose of the present invention is to comprehensively consider the cost, strength and carbon emissions, establish the calculation function of cost, strength and carbon emissions, and establish a three-objective optimization model; establish a multi-objective optimization system through NSGA-Ⅱ global optimization, and seek the Pareto optimal frontier solution set of the modified red mud road material ratio; use the TOPSIS solution evaluation method based on entropy weight to establish a comprehensive evaluation system for the Pareto optimal frontier solution set, and select the optimal solution of the modified red mud road material ratio according to the relative closeness ranking.

[0004] The technical solution is as follows: A modified red mud ratio optimization method based on strength, cost and carbon emissions, comprising: S1, establish the solution function of the three evaluation indicators of strength, cost and carbon emissions, take the maximization of compressive strength, the minimization of economic cost and carbon emissions as the optimization goals, and establish a multi-objective optimization model for the proportion of modified red mud road materials; S2, the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution solves the multi-objective optimization model and obtains the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix proportion schemes to be evaluated; the proportions of each group of modified red mud road material mix proportion schemes to be evaluated are different, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; S3, using the entropy weight method to determine the weights of the three evaluation indicators of intensity, cost and carbon emissions in the optimal set of solutions; S4, use the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes and select the optimal mix ratio scheme.

[0005] In step S1, a solution function for the three evaluation indicators of intensity, cost and carbon emissions is established, including: establishing an intensity function , using the unconfined compressive strength prediction function ,According to the test data of red mud road material projects implemented in many places, a sample data set was obtained and a function was established using a deep learning method; Cost Function The expression is: ; In the formula, The proportion of polymer composite solidified materials in red mud road materials. is the proportion of fly ash in red mud road materials, is the proportion of cement in red mud road materials, is the proportion of rapid hardening cement in red mud road materials, is the maintenance age of red mud road materials, The moisture content of red mud for red mud road materials; Carbon emissions function The expression is: ; Taking maximizing compressive strength, minimizing economic cost and carbon emission as optimization goals, a multi-objective optimization model was established to solve the problem of maximizing and minimize The trade-off between ; the expression is: ; In the formula, It is the negative value of the strength function. The greater the compressive strength, the smaller the negative value of the compressive strength.

[0006] In step S2, the multi-objective optimization algorithm NSGA-II based on the concept of Pareto optimal solution solves the multi-objective optimization model, including: Generate the initial population according to the decision variable range and constraints of the problem, and the number of population solutions , the preset maximum genetic generation is 2000; the population is divided into different frontiers according to the non-dominated relationship, and the crowding distance is calculated for each modified red mud road material mix ratio scheme in the population. , crowding distance The calculation formula is: ; In the formula, is the number of objective functions, Proportion scheme for modified red mud road materials In the The value of the objective function, They are respectively the mixed ratio schemes of modified red mud road materials In the The values ​​of adjacent mix ratios on the objective function; Through the binary tournament selection method, the parent is selected based on the tournament and individual ranking of the modified red mud road material mix scheme and the crowding distance, and two mix schemes are randomly selected for comparison each time; when comparing two mix schemes, the non-dominated sorting Rank is first compared. If the Rank of one mix scheme is lower than that of the other, it will be selected as the better scheme; if the Rank of the two mix schemes is the same, their crowding distances are further compared; the crowding distance is used to measure the distribution density of the mix scheme in the objective function space; the larger the crowding distance, the more independent the mix scheme is in the objective function space; in the binary tournament, if the Rank of the two mix schemes is different, the scheme with the lower Rank is selected; if the Rank is the same, the scheme with the larger crowding distance is selected; if all comparisons are the same, one of them is randomly selected; NSGA-Ⅱ uses the crossover operator to generate offspring and mutate the offspring. A new generation of mix ratio schemes is generated through crossover and mutation operations. Crossover is to select two schemes from the current population as parents through the tournament selection method and randomly select a crossover point to determine which parts of the two parent schemes will be exchanged; the multi-objective optimization algorithm NSGA-Ⅱ is real number coded and uses Simulated Binary Crossover to simulate the binary crossover method. According to the crossover point, some mix ratio parameters of the two parent schemes are exchanged to generate two new offspring schemes; mutation is to randomly select a scheme from the offspring generated in the previous step for mutation, and randomly select one or more mix ratio parameter positions as mutation points. Mutation is performed by adding a small random perturbation to the mix ratio parameter value; mutation operation is performed on the selected mix ratio parameter position to generate the final mutated offspring scheme; Merge the parent and offspring into a temporary population and and progeny population Merge into a temporary population ,in The size is ; Select the best from the temporary population based on non-dominated sorting and crowding distance schemes as the new generation population; if the preset number of iterations is reached or other termination conditions are met, the tournament selection method stops, otherwise it returns to the non-dominated sorting step; the final non-dominated sorting population is output, and the non-dominated sorting population is the Pareto optimal solution set of the problem.

[0007] In step S3, the entropy weight method is used to determine the weights of the three evaluation indicators of intensity, cost and carbon emissions in the optimal set of solutions, including: S301, constructing an original decision matrix according to the evaluation index of the modified red mud road material ratio to be evaluated , and standardize the index parameters in the original decision matrix to construct a standardized decision matrix ; S302, calculate the original decision matrix The probability value of each indicator parameter in , construct a probability matrix based on each indicator parameter ; S303, according to the probability matrix , calculate the information entropy of each indicator parameter , using information entropy Calculate the information utility value of each indicator parameter , the entropy weight of each indicator parameter is calculated using the information utility value , the entropy weights of all indicator parameters form the entropy weight matrix .

[0008] In step S301, construct the original decision matrix , including: The number of optimization solutions is , the number of evaluation indicators is , and each index corresponding to each group of optimization solutions is expressed as OK The mathematical matrix form of the columns, the original decision matrix The form is: ; In the formula, called the Line The elements of the column, Indicates The element in the first column of the row means The first evaluation index of the target sample is , ; Standardized Decision Matrix Each element in The expression is: .

[0009] In step S302, the original decision matrix is ​​calculated The probability value of each indicator parameter in , the expression is: ; Probability Matrix The form is: ; In step S303, the information entropy of each indicator parameter is calculated , the expression is: ; Using information entropy Calculate the information utility value of each indicator parameter , the expression is: ; The entropy weight of each indicator parameter is calculated using the information utility value , the expression is: ; Entropy Weight The form is: ; The entropy weights of all indicator parameters form the entropy weight matrix , the expression is: ; In the formula, They are the weight values ​​of the three indicators: intensity, cost and carbon emission.

[0010] In step S4, the TOPSIS decision method is used to evaluate the relative ranking of each scheme in the optimal set of schemes, and the optimal mix ratio scheme is selected including: S401, using a standardized decision matrix Multiply the entropy weight matrix , construct a weighted decision matrix ; S402, according to the weighted decision matrix Calculate the maximum solution for each indicator parameter and the minimum solution ; S403, calculate the distance between each group of modified red mud road material mix ratio scheme and the maximum solution , the distance of the minimum solution , calculate the relative closeness of each group of modified red mud road material mix ratio scheme to the ideal scheme .

[0011] In step S401, the weighted decision matrix The calculation is: ; In step S402, the maximum value and minimum value The calculation is: ; ; in, , .

[0012] In step S403, the distance between each group of modified red mud road material mix ratio scheme and the maximum value , the minimum distance The calculation is as follows: Definition The distance between the evaluation object and the maximum value , the expression is: ; Definition The distance between the evaluation object and the minimum value : ; The relative closeness of each group of modified red mud road material mix ratio schemes to the ideal scheme The calculation method is as follows: ; For the The closer the value is to 1, the better the evaluation effect is.

[0013] Another object of the present invention is to provide a modified red mud ratio optimization system based on strength, cost and carbon emissions, the system implements any one of the modified red mud ratio optimization methods based on strength, cost and carbon emissions, the system comprising: The module for establishing a multi-objective optimization model for the ratio of modified red mud road materials is used to establish the solution functions of the three evaluation indicators of strength, cost and carbon emissions. The multi-objective optimization model for the ratio of modified red mud road materials is established with the optimization objectives of maximizing compressive strength, minimizing economic costs and carbon emissions. The module for obtaining the optimal set of modified red mud road material mix ratio schemes is used to solve the multi-objective optimization model based on the multi-objective optimization algorithm NSGA-Ⅱ of the Pareto optimal solution concept, and obtain the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix ratio schemes to be evaluated; each group of modified red mud road material mix ratio schemes to be evaluated has different proportions, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; The evaluation index weight determination module is used to determine the weights of the three evaluation indexes of intensity, cost and carbon emissions in the optimal set of solutions using the entropy weight method; The optimal mix ratio scheme selection module is used to evaluate the relative ranking of each scheme in the optimal set of schemes using the TOPSIS decision-making method and select the optimal mix ratio scheme.

[0014] In combination with all the above-mentioned technical solutions, the beneficial effects of the present invention are as follows: the modified red mud road material ratio evaluation method of the present invention is based on NSGA-Ⅱ global optimization and entropy weight TOPSIS method. By establishing strength function, cost function and carbon emission function, a multi-objective optimization model for modified red mud road material ratio with the goals of highest strength, lowest material cost and lowest total carbon emission is further constructed; the multi-objective optimization algorithm NSGA-Ⅱ based on the Pareto optimal frontier solution set is used to solve the multi-objective model of modified red mud road material ratio, and the strength, cost and carbon emission prediction and multi-objective optimization analysis of the modified red mud road material ratio scheme under various schemes are carried out to obtain the Pareto optimal frontier solution set of the modified red mud road material ratio; the TOPSIS scheme evaluation method based on entropy weight is used to establish a comprehensive evaluation system for the Pareto optimal frontier solution set, calculate the relative closeness of each group of schemes in the solution set to the ideal scheme and rank them, and finally obtain the optimal scheme for the modified red mud road material ratio according to the ranking. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure; Figure 1 is a flow chart of a modified red mud ratio optimization method based on strength, cost and carbon emission provided by an embodiment of the present invention; Figure 2 Schematic diagram of a modified red mud ratio optimization system based on strength, cost and carbon emission provided by an embodiment of the present invention; Figure 3 is a Pareto optimal frontier curve diagram provided by an embodiment of the present invention; In the figure: 1. Module for establishing a multi-objective optimization model for the proportion of modified red mud road materials; 2. Module for obtaining the optimal set of proportion schemes for modified red mud road materials; 3. Module for determining the weights of evaluation indicators; 4. Module for selecting the optimal proportion scheme. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific implementation disclosed below.

[0017] The innovation of the present invention lies in that: the present invention adopts a multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution to solve the multi-objective optimization model, and obtains the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix ratio schemes required to be evaluated; further adopts the entropy weight method to determine the weights of the three evaluation indicators of strength, cost and carbon emissions in the optimal set of schemes, adopts the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes, and selects the optimal mix ratio scheme.

[0018] Embodiment 1, as Figure 1 As shown, the modified red mud ratio optimization method based on strength, cost and carbon emission provided by the embodiment of the present invention comprises the following steps: S1, establish the solution function of the three evaluation indicators of strength, cost and carbon emissions, take the maximization of compressive strength, the minimization of economic cost and carbon emissions as the optimization goals, and establish a multi-objective optimization model for the proportion of modified red mud road materials; S2, the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution solves the multi-objective optimization model and obtains the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix proportion schemes to be evaluated; the proportions of each group of modified red mud road material mix proportion schemes to be evaluated are different, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; S3, using the entropy weight method to determine the weights of the three evaluation indicators of intensity, cost and carbon emissions in the optimal set of solutions; S4, use the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes and select the optimal mix ratio scheme.

[0019] Example 2, as another embodiment of the present invention, the modified red mud ratio optimization method based on strength, cost and carbon emission provided in the embodiment of the present invention comprises the following steps: Step 1: Establish the solution function of the three evaluation indicators of strength, cost and carbon emissions, and establish a multi-objective optimization model for the ratio of modified red mud road materials with the optimization objectives of maximizing compressive strength, minimizing economic cost and carbon emissions; In the second step, a multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution is used to solve the multi-objective optimization model and obtain the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix proportion schemes to be evaluated; the mix proportions of each group of modified red mud road material mix proportion schemes to be evaluated are different, and each group of proportions corresponds to a group of evaluation indicators; among them, exemplarily, the modified red mud road material mix proportion scheme to be evaluated consists of the content of polymer composite curing agent, the content of fly ash, the content of cement, the content of rapid hardening cement, the curing age and the moisture content.

[0020] Step 3: Construct the original decision matrix based on the evaluation index of the modified red mud road material ratio to be evaluated. X , and standardize the index parameters in the original decision matrix to construct a standardized decision matrix N .

[0021] Step 4: Calculate the original decision matrix X The probability value of each indicator parameter in the , and the probability matrix is ​​constructed according to each indicator parameter P .

[0022] Step 5: According to the probability matrix P Calculate the information entropy of each indicator parameter , using information entropy Calculate the information utility value of each indicator parameter , the entropy weight of each indicator parameter is calculated using the information utility value , the entropy weights of all indicator parameters form the entropy weight matrix .

[0023] Step 6: Use a standardized decision matrix N Multiply the entropy weight matrix , construct a weighted decision matrix V .

[0024] Step 7: Based on the weighted decision matrix V Calculate the maximum solution for each indicator parameter V + and the minimum solution V - .

[0025] Step 8: Calculate the distance between each group of modified red mud road material mix ratio schemes and the maximum solution , the distance of the minimum solution , calculate the relative closeness of each group of modified red mud road material mix ratio scheme to the ideal scheme .

[0026] Exemplarily, in step 1, the intensity function Y, the cost function Z and the carbon emission function W are established as follows: The strength function Y adopts the unconfined compressive strength prediction function Y, relies on the test data of red mud road material projects implemented in many places, obtains the sample data set, and uses the deep learning method in the prior art (based on experimental big data, using a model trained by a neural network) to establish the function.

[0027] For example, the cost function Assuming that the proportion of polymer composite solidified materials in red mud road materials , fly ash proportion , cement accounts for , rapid hardening cement accounts for The maintenance period is The moisture content of red mud is According to the prices of various raw materials for modified red mud road materials in Table 1, the cost function is set as for: ; Table 1 Prices of raw materials for modified red mud road materials

[0028] For example, the carbon emission function W assumes that the proportion of polymer composite solidified materials in red mud road materials is , fly ash proportion , cement accounts for , rapid hardening cement accounts for The maintenance period is The moisture content of red mud is According to the carbon emission of each raw material of the modified red mud road material in Table 2, the present invention innovatively proposes that the carbon emission function for: ; Table 2 Carbon emissions of raw materials for red mud road materials

[0029] Taking maximizing compressive strength, minimizing economic cost and carbon emission as optimization goals, the present invention innovatively proposes to establish a multi-objective optimization model: ; The meaning of this formula is that the solution to be found should be maximized (By minimizing ) and minimize and Provides a good balance between. It is the negative value of compressive strength. The greater the compressive strength, the smaller the negative value of compressive strength.

[0030] The constraints satisfied by the multi-objective optimization model are shown in Table 3: Table 3 Constraints

[0031] For example, in step 2, MATLAB software is used to solve the multi-objective optimization model using the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution. The specific solution process is as follows: an initial population is generated according to the decision variable range and constraint conditions of the problem, and the number of population solutions is N =100, and the preset maximum genetic generation is 2000. The population is divided into different frontiers (levels) according to the non-dominated relationship, and the crowding distance is calculated for each mix ratio scheme in the population to maintain population diversity; the parent is selected based on the ranking and crowding distance of the scheme through the tournament selection method, and the crossover operator is applied to generate offspring and perform mutation operations on the offspring. A new generation of schemes is generated through crossover and mutation operations, and the parents and offspring are merged into a temporary population. The best one is selected from the temporary population based on the non-dominated sorting and crowding distance. N The algorithm stops if the preset number of iterations is reached or other termination conditions are met, otherwise it returns to the non-dominated sorting step. The final non-dominated sorting population is output, which is the Pareto optimal solution set of the problem.

[0032] Among them, in solving the multi-objective optimization model based on the multi-objective optimization algorithm NSGA-Ⅱ of the Pareto optimal solution concept, the present invention innovatively establishes the objective function and constraint conditions according to the problem to be solved, and solves the problem of the present invention.

[0033] Exemplarily, in step 2, the evaluation index parameters include: intensity, cost, and carbon emissions.

[0034] For example, in step 3, the original decision matrix is ​​constructed , including: The number of optimization schemes is , the number of evaluation indicators is , and each index corresponding to each group of optimization solutions is expressed as OK The mathematical matrix form of the columns, where called the Line Elements of a column, such as Indicates The element in the first column of the row means The first evaluation index of the target sample is , ; The original decision matrix X is in the form of: ; Each element in the standardized decision matrix N .

[0035] For example, in step 4, the probability value of each indicator parameter in the original decision matrix X is calculated , the expression is: ; Probability Matrix The form is: ; In step S303, the information entropy of each indicator parameter is calculated , the expression is: ; Using information entropy Calculate the information utility value of each indicator parameter , the expression is: ; The entropy weight of each indicator parameter is calculated using the information utility value , the expression is: ; Entropy Weight The form is: ; The entropy weights of all indicator parameters form the entropy weight matrix , the expression is: ; In the formula, They are the weight values ​​of the three indicators: intensity, cost and carbon emission.

[0036] For example, in step 6, the weighted decision matrix The calculation is: ; For example, in step 7, the maximum value and minimum value The calculation is: ; ; in, , .

[0037] For example, in step 8, the distance between each group of modified red mud road material mix ratio scheme and the maximum value , the minimum distance The calculation is as follows: Definition The distance between the evaluation object and the maximum value , the expression is: ; Definition The distance between the evaluation object and the minimum value : ; The relative closeness of each group of modified red mud road material mix ratio schemes to the ideal scheme The calculation method is as follows: ; For the The closer the value is to 1, the better the evaluation effect is.

[0038] It can be seen from the above embodiments that the present invention regulates the mix ratio of red mud road materials based on strength, cost and carbon dioxide emissions, establishes a multi-objective optimization model for the ratio of modified red mud road materials with the optimization objectives of maximizing compressive strength and minimizing economic costs and carbon emissions, and adopts the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution to solve the multi-objective optimization model, and obtains the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix ratio schemes required for evaluation; further adopts the entropy weight method to determine the weights of the three evaluation indicators of strength, cost and carbon emissions in the optimal set of schemes, adopts the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes, selects the optimal mix ratio scheme, and realizes the multi-objective optimization design of its mix ratio.

[0039] The present invention improves a hybrid algorithm of non-dominated sorting genetics, solves the above model, and solves the problem that the initial solution quality of the basic NSGAII algorithm is poor and is prone to falling into the local optimum.

[0040] The multi-objective optimization problem of red mud road material mix ratio is solved in two steps by using NSGA-II and TOPSIS decision-making methods. First, the Pareto frontier solution is solved according to the constraints and three objectives to determine the optimal set of red mud road material mix ratio schemes. Then, the distance between the optimal set and the ideal scheme is calculated to sort and optimize the schemes.

[0041] Embodiment 2, as Figure 2As shown, the modified red mud ratio optimization system based on strength, cost and carbon emission provided by the embodiment of the present invention includes: Module 1 for establishing a multi-objective optimization model for the ratio of modified red mud road materials is used to establish a solution function for the three evaluation indicators of strength, cost and carbon emissions, and to establish a multi-objective optimization model for the ratio of modified red mud road materials with the optimization objectives of maximizing compressive strength, minimizing economic costs and carbon emissions; The optimal set acquisition module 2 of the modified red mud road material mix ratio scheme is used to solve the multi-objective optimization model based on the multi-objective optimization algorithm NSGA-Ⅱ of the Pareto optimal solution concept, and obtain the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix ratio schemes to be evaluated; each group of modified red mud road material mix ratio schemes to be evaluated has different proportions, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; Evaluation index weight determination module 3 is used to determine the weights of the three evaluation indexes of intensity, cost and carbon emissions in the optimal set of solutions by using the entropy weight method; The optimal mix ratio scheme selection module 4 is used to use the TOPSIS decision-making method to evaluate the relative ranking of each scheme in the optimal set of schemes and select the optimal mix ratio scheme.

[0042] Exemplarily, the evaluation index weight determination module 3 includes: The original decision matrix construction module is used to construct the original decision matrix according to the evaluation index of the modified red mud road material ratio to be evaluated. X , A standardized decision matrix construction module is used to standardize the indicator parameters in the original decision matrix and construct a standardized decision matrix N; The probability matrix construction module is used to calculate the probability value of each indicator parameter in the original decision matrix X and construct the probability matrix P according to each indicator parameter; The entropy weight matrix acquisition module is used to calculate the information entropy of each indicator parameter based on the probability matrix P , using information entropy Calculate the information utility value of each indicator parameter , the entropy weight of each indicator parameter is calculated using the information utility value , the entropy weights of all indicator parameters form the entropy weight matrix .

[0043] The optimal mix ratio selection module 4 includes: Weighted decision matrix building module for multiplying the entropy weight matrix by the normalized decision matrix N , construct the weighted decision matrix V; The maximum and minimum solution calculation module of the indicator parameter is used to calculate the maximum solution V+ and the minimum solution V- of each indicator parameter according to the weighted decision matrix V; Relative proximity calculation module, used to calculate the distance between each group of modified red mud road material mix scheme and the maximum solution , the distance of the minimum solution , calculate the relative closeness of each group of modified red mud road material mix ratio scheme to the ideal scheme .

[0044] To further illustrate the effects of the embodiments of the present invention, the following experiment was conducted.

[0045] The proportion of the modified red mud road material mix scheme in this embodiment is composed of: polymer composite curing material, fly ash, cement, rapid hardening cement, curing age (3-14 days) and moisture content. The experimental data range used to establish the compressive strength prediction model is as described in Table 4; Table 4 Influencing factors and their ranges of the mix ratio of modified red mud road materials

[0046] Building the intensity function Y , cost function Z Function of carbon emissions W : ; ; Taking maximizing the 7-day unconfined compressive strength, minimizing economic costs and carbon emissions as the optimization objectives, a multi-objective optimization model was established: ; The constraints are shown in Table 5; Table 5 Constraints

[0047] Using MATLAB software, the multi-objective optimization model was solved based on NSGA-Ⅱ. The algorithm operation parameters were set to 100 population schemes and 2000 maximum genetic generations. The Pareto optimal frontier curve was obtained. Figure 3 .

[0048] The multi-objective optimization model was solved by the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution to obtain 100 optimal sets of modified red mud road material mix ratio schemes for evaluation, and the minimum strength was set to 2.0 MPa, and 89 optimal sets of mix ratio schemes were screened out, as shown in Table 6. The evaluation indicators of each scheme are cost, strength and carbon emissions, as shown in Table 7.

[0049] Table 6 Optimal combination of modified red mud road material ratios

[0050] Table 7 Evaluation index parameters of modified red mud road material ratio

[0051] In this example, there are 89 optimal solutions for the ratio of modified red mud road materials and 3 evaluation indicators. The original decision matrix model .

[0052] Building the original decision matrix model See Table 8: Table 8 Original decision matrix model ;

[0053] Standardized Decision Matrix See Table 9: Table 9 Standardization decision matrix ;

[0054] Probability Matrix See Table 10: Table 10 Probability matrix ;

[0055] Entropy Weight The calculation results are shown in Table 11: Table 11 Entropy weight Calculation results

[0056] Weighted Decision Matrix The calculation results are shown in Table 12; Table 12 Weighted decision matrix ;

[0057] The distance between the modified red mud road material mix ratio and the maximum value , the minimum distance , relative proximity See Table 13 for the ranking of the solutions: Table 13 Maximum distance, minimum distance, relative closeness and ranking

[0058] By relative proximity The mix ratio schemes are sorted as shown in Table 14: Table 14: Ranking of mix ratios

[0059] Based on relative proximity Sorting shows that Scheme 25 is the optimal mix ratio scheme among the 89 selected modified red mud road material mix ratio schemes, with a polymer curing agent content of 0.209%, a fly ash content of 2.4%, a cement content of 5.468%, a quick-hardening cement content of 0.091%, a curing age of 7 days, a moisture content of 30.127%, a corresponding cost of 31.12 yuan / ton, a strength of 3.97Mpa, and a carbon emission of 44.42 kgCO2 / ton. This scheme takes into account the impact of cost, strength and carbon emissions, and realizes the comprehensive comparison of modified red mud road material mix ratio schemes.

[0060] 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 modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered within the protection scope of the present invention.

Claims

1. A modified red mud ratio optimization method based on strength, cost and carbon emissions, characterized in that: The method includes: S1, establish the solution function of the three evaluation indicators of strength, cost and carbon emissions, take the maximization of compressive strength, the minimization of economic cost and carbon emissions as the optimization goals, and establish a multi-objective optimization model for the proportion of modified red mud road materials; S2, the multi-objective optimization algorithm NSGA-Ⅱ based on the concept of Pareto optimal solution solves the multi-objective optimization model and obtains the Pareto optimal frontier to obtain the optimal set of modified red mud road material mix proportion schemes to be evaluated; the proportions of each group of modified red mud road material mix proportion schemes to be evaluated are different, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; S3, using the entropy weight method to determine the weights of the three evaluation indicators of intensity, cost and carbon emissions in the optimal set of solutions; S4, use the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes and select the optimal mix ratio scheme.

2. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 1 is characterized in that: In step S1, a solution function for the three evaluation indicators of intensity, cost and carbon emissions is established, including: establishing an intensity function , using the unconfined compressive strength prediction function ,According to the test data of red mud road material projects implemented in many places, a sample data set was obtained and a function was established using a deep learning method; Cost Function The expression is: ； In the formula, The proportion of polymer composite solidified materials in red mud road materials. is the proportion of fly ash in red mud road materials, is the proportion of cement in red mud road materials, is the proportion of rapid hardening cement in red mud road materials, is the maintenance age of red mud road materials, The moisture content of red mud for red mud road materials; Carbon emissions function The expression is: ； Taking maximizing compressive strength, minimizing economic cost and carbon emission as optimization goals, a multi-objective optimization model was established to solve the problem of maximizing and minimize The trade-off between ; the expression is: ； In the formula, It is the negative value of the strength function. The greater the compressive strength, the smaller the negative value of the compressive strength.

3. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 1 is characterized in that: In step S2, the multi-objective optimization algorithm NSGA-II based on the concept of Pareto optimal solution solves the multi-objective optimization model, including: Generate the initial population according to the decision variable range and constraints of the problem, and the number of population solutions , the preset maximum genetic generation is 2000; the population is divided into different frontiers according to the non-dominated relationship, and the crowding distance is calculated for each modified red mud road material mix ratio scheme in the population. , crowding distance The calculation formula is: ； In the formula, is the number of objective functions, Proportion scheme for modified red mud road materials In the The value of the objective function, They are respectively the mixed ratio schemes of modified red mud road materials In the The values ​​of adjacent mix ratios on the objective function; NSGA-Ⅱ uses the crossover operator to generate offspring and mutate the offspring, generating a new generation of mix ratio schemes through crossover and mutation operations. Crossover is to select two schemes from the current population as parents through the tournament selection method, and randomly select a crossover point to determine which schemes of the two parent schemes will be exchanged; the multi-objective optimization algorithm NSGA-Ⅱ is real number coding, and uses the Simulated Binary Crossover method to simulate the binary crossover method. According to the crossover point, some mix parameters of the two parent schemes are exchanged to generate two new offspring schemes; mutation is to randomly select a scheme from the offspring generated in the previous step for mutation, and randomly select one or more mix ratio parameter positions as mutation points, and perform mutation by adding a small random perturbation to the mix ratio parameter value; mutation operation is performed on the selected mix ratio parameter position to generate the final mutated offspring scheme; Merge the parent and offspring into a temporary population and and progeny population Merge into a temporary population ,in The size is ; Select the best from the temporary population based on non-dominated sorting and crowding distance schemes as the new generation population; if the preset number of iterations is reached or other termination conditions are met, the tournament selection method stops, otherwise it returns to the non-dominated sorting step; the final non-dominated sorting population is output, and the non-dominated sorting population is the Pareto optimal solution set of the problem.

4. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 1 is characterized in that: In step S3, the entropy weight method is used to determine the weights of the three evaluation indicators of intensity, cost and carbon emissions in the optimal set of solutions, including: S301, constructing an original decision matrix according to the evaluation index of the modified red mud road material ratio to be evaluated , and standardize the index parameters in the original decision matrix to construct a standardized decision matrix ; S302, calculate the original decision matrix The probability value of each indicator parameter in , construct a probability matrix based on each indicator parameter ; S303, according to the probability matrix , calculate the information entropy of each indicator parameter , using information entropy Calculate the information utility value of each indicator parameter , the entropy weight of each indicator parameter is calculated using the information utility value , the entropy weights of all indicator parameters form the entropy weight matrix .

5. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 4 is characterized in that: In step S301, construct the original decision matrix , including: The number of optimization solutions is , the number of evaluation indicators is , and each index corresponding to each group of optimization solutions is expressed as OK The mathematical matrix form of the columns, the original decision matrix The form is: ； In the formula, called the Line The elements of the column, Indicates The element in the first column of the row means The first evaluation index of the target sample is , ; Standardized Decision Matrix Each element in The expression is: 。 6. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 5 is characterized in that: In step S302, the original decision matrix is ​​calculated The probability value of each indicator parameter in , the expression is: ； Probability Matrix The form is: ； In step S303, the information entropy of each indicator parameter is calculated , the expression is: ； Using information entropy Calculate the information utility value of each indicator parameter , the expression is: ； The entropy weight of each indicator parameter is calculated using the information utility value , the expression is: ； Entropy Weight The form is: ; The entropy weights of all indicator parameters form the entropy weight matrix , the expression is: ； In the formula, They are the weight values ​​of the three indicators: intensity, cost and carbon emission.

7. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 1 is characterized in that: In step S4, the TOPSIS decision method is used to evaluate the relative ranking of each scheme in the optimal set of schemes, and the optimal mix ratio scheme is selected including: S401, using a standardized decision matrix Multiply the entropy weight matrix , construct a weighted decision matrix ; S402, according to the weighted decision matrix Calculate the maximum solution for each indicator parameter and the minimum solution ; S403, calculate the distance between each group of modified red mud road material mix ratio scheme and the maximum solution , the distance of the minimum solution , calculate the relative closeness of each group of modified red mud road material mix ratio scheme to the ideal scheme .

8. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 7 is characterized in that: In step S401, the weighted decision matrix The calculation is: ； In step S402, the maximum value and minimum value The calculation is: ； ； in, , .

9. The modified red mud ratio optimization method based on strength, cost and carbon emission according to claim 7, characterized in that: In step S403, the distance between each group of modified red mud road material mix ratio scheme and the maximum value , the minimum distance The calculation is as follows: Definition The distance between the evaluation object and the maximum value , the expression is: ； Definition The distance between the evaluation object and the minimum value : ； The relative closeness of each group of modified red mud road material mix ratio schemes to the ideal scheme The calculation method is as follows: ； For the The closer the value is to 1, the better the evaluation effect is.

10. A modified red mud ratio optimization system based on strength, cost and carbon emissions, characterized in that: Implementing the modified red mud ratio optimization method based on strength, cost and carbon emission as described in any one of claims 1 to 9, the system comprises: A module (1) for establishing a multi-objective optimization model for the ratio of modified red mud road materials is used to establish a solution function for the three evaluation indicators of strength, cost and carbon emissions, and to establish a multi-objective optimization model for the ratio of modified red mud road materials with the optimization objectives of maximizing compressive strength and minimizing economic costs and carbon emissions; The modified red mud road material mix ratio scheme optimal set acquisition module (2) is used to solve the multi-objective optimization model based on the Pareto optimal solution concept of the multi-objective optimization algorithm NSGA-II to obtain the Pareto optimal frontier, so as to obtain the optimal set of modified red mud road material mix ratio schemes to be evaluated; each group of modified red mud road material mix ratio schemes to be evaluated has different proportions, and each group of proportions corresponds to a group of evaluation indicators including strength, cost and carbon emissions; An evaluation index weight determination module (3) is used to determine the weights of the three evaluation indexes of intensity, cost and carbon emissions in the optimal set of solutions using an entropy weight method; The optimal mix ratio scheme selection module (4) is used to use the TOPSIS decision method to evaluate the relative ranking of each scheme in the optimal set of schemes and select the optimal mix ratio scheme.

Images