Cement raw material ratio optimization method and system

Abstract

The invention relates to the technical field of cement chemical component analysis, and discloses a cement raw material proportion optimization method and system, and the method comprises the steps: determining a target compressive strength value based on the chemical component proportion of a cement raw material; obtaining a first chemical component combination before optimization of the cement clinker matched with the target compressive strength value from a preset cement ratio database; according to the first chemical component proportion combination, the preset value range of different chemical components of the cement clinker and the preset constraint condition, iterative optimization is conducted through the genetic algorithm, and an optimized second chemical component combination is obtained. The method has the advantages that data deviation between laboratory conditions and actual production is avoided by optimizing the clinker component proportion combination through the cement proportion and the genetic algorithm, the optimal cement clinker component combination is found under the constraint of a plurality of performance indexes, and during the application process, when the cement raw material proportion is analyzed on the basis of the optimized cement clinker proportion, the optimal cement clinker component combination is obtained. And the accuracy of component analysis of the cement raw material is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of cement chemical composition analysis, and in particular to a cement raw material ratio optimization method and system. Background Art

[0002] As the core basic raw material for national economic construction, cement plays a vital role in various infrastructure and construction projects. How to effectively improve the performance of cement clinker is not only a key research direction in the field of cement science, but also an effective way to increase the amount of admixtures and reduce carbon emissions in the cement production process.

[0003] The existing technology mainly evaluates cement components through a large number of experimental designs and adjusts the ratio of raw materials to achieve the adjustment of the chemical composition of cement clinker and the ratio of key components. Although certain effects can be obtained in the laboratory, there is a certain disconnect between the experimental design and the actual production process. The cement clinker in the production process contains multiple chemical composition indicators. The final analysis of the cement raw material results based on the clinker ratio is not accurate. Different production scenarios lead to different indicator requirements, which leads to the lack of consistency between experimental data and production practice results. Summary of the invention

[0004] In view of this, the present invention provides a cement raw meal ratio optimization method and system to solve how to improve the accuracy of the cement clinker chemical composition ratio under multiple performance indicators in the actual production process, so as to use the optimized clinker composition to infer the cement raw meal ratio, and further improve the accuracy of the component analysis of the cement raw meal.

[0005] In a first aspect, the present invention provides a method for optimizing cement raw material ratio, the method comprising:

[0006] Determine the target compressive strength value based on the chemical composition ratio of the cement raw material;

[0007] Obtaining a first chemical component combination of cement clinker matching the target compressive strength value from a preset cement ratio database; the first chemical component combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical component types and corresponding proportions;

[0008] According to the first chemical component proportion combination, the preset value range of different chemical components in cement clinker and the preset constraints, a genetic algorithm is used to perform iterative optimization to obtain a second chemical component combination, which represents the optimized chemical component proportion combination corresponding to the first chemical component combination.

[0009] In the embodiment of the present invention, an initial first chemical component combination is determined in a preset cement ratio database by determining the target compressive strength value in advance, and the first chemical component combination is optimized by using a genetic algorithm in combination with the value ranges of different chemical components in cement clinker and preset constraints. The deviation from the actual production data during the iterative optimization of the genetic algorithm is reduced by optimizing the cement ratio in the database and the genetic algorithm based on the value ranges of different chemical components in cement clinker in the actual production process and the preset constraints. The genetic algorithm is further introduced based on the existing chemical component combination data to find the best component combination based on the constraints of multiple performance indicators on the basis of ensuring that the chemical component combination can basically meet the compressive strength requirements, ensuring that the optimized component combination can meet the production practice results, and finding the optimal ratio under the constraints, so that the chemical component combination is more in line with the actual production needs, avoiding the problem of inconsistency between experimental data and actual production results, thereby improving the accuracy of the chemical component ratio of cement clinker under multiple performance indicators. In the actual application process, when analyzing the cement raw material ratio based on the optimized cement clinker ratio, the accuracy of the component analysis of the cement raw material can be effectively improved.

[0010] In an optional embodiment, according to the first chemical component ratio combination, the preset value range of different chemical components in the cement clinker and the preset constraint conditions, a second chemical component combination is optimized by using a genetic algorithm, and the second chemical component combination represents the optimized chemical component ratio combination corresponding to the first chemical component combination, specifically including:

[0011] According to the preset value ranges of different chemical components in cement clinker and preset constraints, an initial chemical proportion population is randomly generated; wherein the initial chemical proportion population includes multiple chemical proportion individuals, and one chemical proportion individual represents the proportion combination information of multiple different chemical components;

[0012] Adding the chemical ratio individuals corresponding to the first chemical component combination to the initial chemical ratio population to obtain a first iterative population;

[0013] According to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population, according to the preset cement performance prediction function, the predicted compressive strength value corresponding to each chemical ratio individual is calculated;

[0014] According to the predicted compressive strength value and the target compressive strength value corresponding to each chemical ratio individual, the absolute difference corresponding to each chemical ratio individual is calculated according to the preset absolute difference function;

[0015] According to the corresponding absolute difference of each chemical ratio individual, the fitness value corresponding to each chemical ratio individual is calculated;

[0016] The selection probability is calculated according to the fitness value of each chemical ratio individual, and one or more target parent individuals are selected;

[0017] Performing a gene crossover operation or a gene mutation operation on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals, wherein all target child individuals constitute a second iterative population;

[0018] Determine whether the current number of iterations reaches the target number of iterations. If not, replace the second iteration population with the first iteration population for the next round of iterations. If the target number of iterations is reached, select the chemical ratio individual with the highest fitness value among all chemical ratio individuals in the last round of iterations as the optimized chemical ratio individual, and output the corresponding second chemical composition combination, which represents the proportion combination of the optimized chemical components corresponding to the target compressive strength value.

[0019] The embodiment of the present invention generates a random initial population according to the preset value range and constraints of the chemical composition of cement clinker, and adds the first chemical composition combination in the preset database to the initial population, which not only ensures that the diversity of solutions is effectively increased, but also can effectively narrow the search space of solutions based on the initial first chemical composition combination, calculates the compressive strength of each chemical ratio individual according to the preset prediction function, and compares it with the target value, calculates the absolute difference and the fitness value, and generates new combinations by simulating the biological evolution process, thereby retaining combinations with high fitness and determining new potential combinations, avoiding local optimality, and improving the degree of global optimization. By judging whether the number of iterations reaches the preset target, the algorithm obtains the optimal solution after a sufficient number of cycles. If the set termination condition is met, the individual with the highest fitness is selected from the population of the final iteration as the optimized chemical composition combination, to ensure that the obtained combination is the optimal solution after iterative optimization and is more in line with the target compressive strength requirement.

[0020] In an optional implementation, according to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population, according to the preset cement performance prediction function, the predicted compressive strength value corresponding to each chemical ratio individual is calculated, specifically including:

[0021] Input the proportion of different chemical components corresponding to each chemical ratio individual into a preset cement performance prediction function constructed based on the empirical data relationship between chemical composition and compressive strength, and predict the predicted compressive strength value corresponding to each chemical ratio individual;

[0022] The cement performance prediction function is expressed by the following formula:

[0023]

[0024] Where f1[j] represents the predicted compressive strength value corresponding to the jth chemical ratio individual, N represents the number of chemical components, and x i represents the proportion of the i-th chemical component in the current chemical ratio individual, y i Represents the weight of the i-th chemical component in the current chemical ratio individual when calculating the predicted compressive strength value.

[0025] The embodiment of the present invention inputs the proportions of different chemical components, and the prediction function constructed based on the empirical data relationship is faster than the actual experimental test speed in the prior art. The prediction function can calculate the compressive strength value of each chemical ratio individual, quickly evaluate the compressive strength of multiple chemical ratios, reduce the waste of computing resources, speed up the optimization process, and provide a data basis for the subsequent calculation of absolute differences.

[0026] In an optional implementation, the preset absolute difference function is expressed by the following formula:

[0027] f2[j]=|target_strength-f1[j]|;

[0028] Among them, f2[j] represents the absolute difference corresponding to the j-th chemical ratio individual, f1[j] represents the predicted compressive strength value corresponding to the j-th chemical ratio individual, and target_strength represents the target compressive strength value;

[0029] According to the corresponding absolute difference of each chemical ratio individual, the fitness value corresponding to each chemical ratio individual is calculated, including:

[0030] The absolute difference corresponding to each chemical ratio individual is input into the fitness calculation function to calculate the fitness value corresponding to each chemical ratio individual; the fitness calculation function is expressed by the following formula:

[0031]

[0032] Among them, f3[j] represents the fitness value corresponding to the jth chemical ratio individual.

[0033] The embodiment of the present invention determines the degree of deviation between the predicted compressive strength value and the target compressive strength value of each chemical component combination by calculating the absolute difference. At the same time, by calculating the fitness value, it is ensured that the combination with high fitness can be preferentially selected for the next round of crossover or mutation operation in each subsequent round of iteration, thereby improving the accuracy of the optimization process and providing a data basis for the subsequent selection process.

[0034] In an optional implementation, the selection probability is calculated according to the fitness value of each chemical ratio individual, and one or more target parent individuals are selected, specifically including:

[0035] The fitness value corresponding to each chemical ratio individual is input into the roulette probability calculation function to calculate the selection probability corresponding to each chemical ratio individual; the roulette probability calculation function is expressed by the following formula:

[0036]

[0037] Among them, f4[j] represents the selection probability corresponding to the jth chemical ratio individual, and M represents the number of chemical ratio individuals in the first iteration population;

[0038] The selection probability corresponding to each chemical ratio individual is compared with a preset selection probability threshold, and one or more chemical ratio individuals corresponding to a selection probability greater than the selection probability threshold are selected as the target parent individual.

[0039] The embodiment of the present invention calculates the fitness value of each chemical ratio individual and inputs it into the roulette probability calculation function to ensure that individuals with high fitness have a greater probability of being selected as the target parent individual. The reason why the individual with the highest fitness is not directly selected but the parent individual is selected according to probability is to ensure the diversity of solutions and further expand the number of individuals in the iterative population, thereby ensuring that the iterative result can be globally optimal.

[0040] In an optional implementation, if the number of target parent individuals is greater than or equal to two, a gene crossover operation is performed on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals, specifically including:

[0041] Selecting two target parent individuals to be crossed from two or more target parent individuals, and randomly determining the positions of the crossover points in the two target parent individuals to be crossed;

[0042] The chemical component gene fragments are exchanged at the crossover point positions of the target parent individuals to be crossed to obtain two target child individuals, wherein the chemical component gene fragments represent the proportion of a chemical component in the target parent individual; when all the target parent individuals are subjected to gene crossover operations, target child individuals corresponding to multiple target parent individuals are obtained.

[0043] In the embodiment of the present invention, the characteristics of the two parent individuals are combined into new child individuals by randomly selecting the intersection position of the target parent individual and exchanging the gene fragments. Since the number of child individuals will not decrease, the diversity of the population is improved, the search accuracy of the genetic algorithm is guaranteed, and the optimization process will not fall into the local optimal solution, so as to more accurately find the global optimal solution of the chemical composition ratio individual.

[0044] In an optional implementation, performing a gene crossover operation on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals specifically includes:

[0045] The mutation point position in each target parent individual is randomly determined according to the preset mutation probability;

[0046] The chemical composition gene fragments at the mutation point of the target parent individual are numerically transformed according to the preset value range of different chemical components in cement clinker and preset constraints to obtain the target child individuals corresponding to each target parent individual.

[0047] In the embodiment of the present invention, the random bits of the gene encoding of the individual are mutated according to the setting of the mutation probability, and different genes are introduced in each iteration to ensure that the number of sub-individuals will not decrease. In some cases, it will be further expanded, so that the generated chemical component combinations are more diverse, thereby more accurately finding the global optimal solution of the chemical component ratio individual.

[0048] In a second aspect, the present invention provides a cement raw material ratio optimization system, the system comprising:

[0049] A target compressive strength setting module is used to determine a target compressive strength value based on the chemical composition ratio of the cement raw material;

[0050] A matching chemical composition combination extraction module is used to obtain a first chemical composition combination of cement clinker that matches the target compressive strength value from a preset cement ratio database; the first chemical composition combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical composition types and corresponding proportions;

[0051] The chemical composition combination optimization module is used to perform iterative optimization using a genetic algorithm according to the first chemical composition proportion combination, the preset value range of different chemical components in the cement clinker, and the preset constraints to obtain a second chemical composition combination, where the second chemical composition combination represents the optimized chemical composition proportion combination corresponding to the first chemical composition combination.

[0052] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the cement raw material ratio optimization method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for optimizing cement raw material ratio according to the first aspect or any corresponding embodiment thereof.

[0054] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for optimizing cement raw material ratio according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 is a schematic flow chart of a method for optimizing cement raw material ratio according to an embodiment of the present invention;

[0057] Figure 2 is a schematic flow chart of another cement raw material ratio optimization method according to an embodiment of the present invention;

[0058] Figure 3 is a schematic flow chart of another method for optimizing cement raw material ratio according to an embodiment of the present invention;

[0059] Figure 4 is a structural block diagram of a cement raw material ratio optimization system according to an embodiment of the present invention;

[0060] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0062] In the prior art, when calculating the cement clinker composition ratio, the cement clinker ratio experiment conducted in the laboratory is carried out under relatively stable and controlled conditions. In actual production, the cement production line will be affected by many factors, which will cause the actual performance of the clinker composition to be inconsistent with the experimental results. The laboratory may use a specific raw material ratio to increase the content of tricalcium silicate to improve the strength of cement. In actual production, due to the instability of equipment temperature control, the content of tricalcium silicate may be reduced, affecting the target cement strength.

[0063] In addition, cement clinker is mainly made of raw materials containing CaO, SiO2, Al2O3, and Fe2O3 in appropriate proportions, ground and calcined at high temperature, and finally forms four main minerals: tricalcium silicate (C3S), dicalcium silicate (C2S), tricalcium aluminate (C3A), and tetracalcium aluminoferrite (C4AF). C3S accounts for about 55-65%, C2S accounts for 15-20%, C3A accounts for 5-10%, and C4AF accounts for 8-12%. The type and content of minerals in clinker have a decisive influence on the performance of clinker. The laboratory mainly sets the proportion of a specific component, but ignores the interaction between the components. While increasing the C3S content, it may lead to a decrease in the C2S or C3A content. Although the adjustment of a single component has achieved the experimental effect, the overall cement strength performance has not been improved.

[0064] The embodiment of the present invention provides a method for optimizing the ratio of cement raw materials, which is applied to the clinker component ratio scenario in the actual cement production process, and solves the problem of inconsistent components in the laboratory and in actual production. Through the optimization of cement ratios in the database and genetic algorithms, data deviations caused by factors such as unstable temperature control in actual production while laboratory conditions are stable are avoided. By using genetic algorithms to iteratively optimize the combination of component ratios, the best combination of components can be found under the constraints of multiple performance indicators, making the optimization results more in line with actual production, thereby applying the optimized clinker components to infer the ratio of cement raw materials, and further improving the accuracy of the component analysis of cement raw materials.

[0065] According to an embodiment of the present invention, an embodiment of a method for optimizing the proportion of cement raw materials is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] In this embodiment, a method for optimizing the ratio of cement raw materials is provided, which can be used in the above-mentioned computer. Figure 1 : is a flow chart of a method for optimizing cement raw material ratio according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0067] Step S101, determining a target compressive strength value based on the chemical composition ratio of cement raw material.

[0068] It should be noted that cement raw material refers to lime raw materials, clay raw materials and a small amount of correction raw materials. In the actual production process, the type of cement raw material is often fixed. Therefore, when the composition of cement raw material is determined, the target compressive strength value to be achieved can be determined.

[0069] Specifically, it can be queried through a preset cement compressive strength database, which contains different cement raw material ratios and their corresponding compressive strength data. By finding the compressive strength values ​​related to similar lime raw materials, clay raw materials and a small amount of correction raw materials, the target compressive strength is preliminarily determined. In actual application, the setting of the target compressive strength value needs to be adjusted according to the intended use of the cement product. For example, if a higher compressive strength is required in a building structure, it is increased based on the target compressive strength in the database, while in some common uses, the requirements can be appropriately lowered, and it is reduced based on the target compressive strength in the database.

[0070] It is understandable that when optimizing the chemical composition ratio of cement clinker, it is necessary to first set a reasonable compressive strength value and use the determined target compressive strength value as the objective function parameter of the optimization algorithm in subsequent steps, so as to achieve targeted optimization.

[0071] Step S102, obtaining a first chemical composition combination of cement clinker matching the target compressive strength value from a preset cement mix database; the first chemical composition combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical composition types and corresponding proportions.

[0072] Specifically, a preset database of different cement clinker chemical composition ratio combinations can be used for query, and the database of different cement clinker chemical composition ratio combinations contains the proportion of each component and its corresponding compressive strength value. According to the target compressive strength value, the chemical composition combination close to the database is screened out. It can ensure further optimization on the existing pre-optimization ratio without having to find a matching ratio from scratch. Once the preliminary matching combination is determined, the corresponding chemical component type and proportion are extracted, for example, SiO2 may account for 30%, Al2O3 may account for 10%, etc.

[0073] For example, the target compressive strength is set to 50 MPa. After querying the database of different cement clinker chemical composition ratio combinations, a ratio combination is found: SiO2 is 30%, Al2O3 is 8%, Fe2O3 is 6%, CaO is 50%, and MgO is 6%, which is used as the first chemical composition combination to provide basic data for the optimization process. At this time, the combination has not reached the optimal state for actual production application, which meets the initial optimization goal of this embodiment.

[0074] Step S103, according to the first chemical component proportion combination, the preset value range of different chemical components in the cement clinker and the preset constraint conditions, iterative optimization is performed using a genetic algorithm to obtain a second chemical component combination, where the second chemical component combination represents the optimized chemical component proportion combination corresponding to the first chemical component combination.

[0075] It should be noted that the preset value ranges and preset constraints of different chemical components in cement clinker are set according to the actual production scenario requirements. Unlike the single constraint restrictions in the laboratory, this embodiment can flexibly adjust the preset value ranges of different chemical components in cement clinker according to the changes in the actual production scenario, for example, the proportion of SiO2 is lower than 30% and higher than 20%. The constraint conditions represent the restriction conditions of the sum of the proportions of different chemical components. In this embodiment, the preset constraint conditions can also be adjusted, which is represented by the following constraint formula:

[0076] SiO2_percentage+Al2O3_percentage+Fe2O3_percentage+CaO_percentage+Mg O_percentage<=100;

[0077] The above constraint formula indicates that the sum of the proportions of SiO2, Al2O3, Fe2O3, CaO, and MgO is less than or equal to 100%.

[0078] Specifically, the genetic algorithm is introduced into the optimization process of chemical component ratio, including: representing the ratio of each component of the first chemical component combination through binary coding, converting different component ratios into binary strings of 0 and 1 to form the binary coding of cement clinker components, and similarly converting the preset value ranges of different chemical components in cement clinker and the numerical contents in the constraint formula into binary strings of 0 and 1 to form the constraint binary coding; using the binary coding of cement clinker components and the constraint binary coding to generate a population, calculating the fitness of individuals in the population according to a preset fitness function, and continuously optimizing the cement clinker ratio combination through selection, crossover and mutation operations in the genetic algorithm, wherein, in the selection operation, the combination with high fitness is preferentially selected to enter the next generation; in the crossover operation, the combination of the parent generation generates a new offspring; the mutation operation generates a new offspring by randomly changing part of the bit string; and judging the termination condition according to the set number of iterations or fitness threshold. When the termination condition is reached, the optimized second chemical component combination can be obtained as the final cement clinker chemical component ratio.

[0079] For example, after several generations of iterations, a new generation of cement clinker chemical composition combination is obtained, in which the proportions of each component are 32% SiO2, 7% Al2O3, 6% Fe2O3, 1% CaO, and 4% MgO. This combination is close to the target compressive strength value under the evaluation of the fitness function and meets the preset constraints.

[0080] In the embodiment of the present invention, an initial first chemical component combination is determined in a preset cement ratio database by determining the target compressive strength value in advance, and the first chemical component combination is optimized by using a genetic algorithm in combination with the value ranges of different chemical components in cement clinker and preset constraints. The deviation from the actual production data during the iterative optimization of the genetic algorithm is reduced by optimizing the cement ratio in the database and the genetic algorithm based on the value ranges of different chemical components in cement clinker in the actual production process and the preset constraints. The genetic algorithm is further introduced based on the existing chemical component combination data to find the best component combination based on the constraints of multiple performance indicators on the basis of ensuring that the chemical component combination can basically meet the compressive strength requirements, ensuring that the optimized component combination can meet the production practice results, and finding the optimal ratio under the constraints, so that the chemical component combination is more in line with the actual production needs, avoiding the problem of inconsistency between experimental data and actual production results, thereby improving the accuracy of the chemical component ratio of cement clinker under multiple performance indicators. In the actual application process, when analyzing the cement raw material ratio based on the optimized cement clinker ratio, the accuracy of the component analysis of the cement raw material can be effectively improved.

[0081] In this embodiment, a method for optimizing the ratio of cement raw materials is provided, which can be used in the above-mentioned computer. Figure 2 : is a flow chart of a method for optimizing cement raw material ratio according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0082] Step S201, determine the target compressive strength value based on the chemical composition ratio of the cement raw material. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0083] Step S202, obtaining a first chemical component combination of cement clinker that matches the target compressive strength value from a preset cement ratio database; the first chemical component combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical component types and corresponding proportions. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0084] Step S203, based on the first chemical component proportion combination, the preset value range of different chemical components in the cement clinker and the preset constraint conditions, an iterative optimization is performed using a genetic algorithm to obtain a second chemical component combination, where the second chemical component combination represents the optimized chemical component proportion combination corresponding to the first chemical component combination.

[0085] Specifically, step S203 includes:

[0086] Step S2031, randomly generating an initial chemical proportion population according to the preset value range of different chemical components in cement clinker and preset constraints; wherein the initial chemical proportion population includes multiple chemical proportion individuals, and one chemical proportion individual represents the proportion combination information of multiple different chemical components.

[0087] It should be noted that the initial chemical ratio population refers to an initial set consisting of multiple cement clinker chemical component ratio individuals. Each individual represents a specific chemical component combination, including the proportion combination information of different components. The generated initial chemical ratio population is the initial search space of the genetic algorithm in this embodiment.

[0088] Specifically, define the preset value range of each chemical component. For example, if the preset range of the proportion of SiO2 is 20%-30%, then when generating the initial individual, randomly set a value between 20% and 30% for the proportion of SiO2. The proportions of other chemical components Al2O3, Fe2O3, CaO and MgO are also set within their respective ranges, and the sum of the proportions of SiO2, Al2O3, Fe2O3, CaO and MgO is less than or equal to 100%. The discrete results of each of the above numerical parameters are represented by binary coding to form a binary string consisting of 0 and 1. The length of the string is mainly composed of the following factors: the number of different chemical components in cement clinker, the preset value range of different chemical components in cement clinker, and the constraints. The binary codes of each of the above numerical parameters are randomly matched to form an individual, and the matching process is repeated to obtain multiple individuals to form an initial chemical ratio population.

[0089] Step S2032, adding the chemical ratio individuals corresponding to the first chemical component combination to the initial chemical ratio population to obtain a first iterative population.

[0090] It is understandable that the purpose of adding the first chemical composition combination is to provide a basic initial solution for the algorithm, so that subsequent iterations can start with a better solution, reduce the low fitness individuals that may be caused by random generation, and improve the optimization efficiency of subsequent iterations. Similarly, the discrete results of each numerical parameter in the first chemical composition combination are represented by binary coding and added to the initial chemical ratio population.

[0091] Step S2033, according to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population, according to the preset cement performance prediction function, calculate the predicted compressive strength value corresponding to each chemical ratio individual.

[0092] The purpose of calculating the predicted compressive strength value in this embodiment is to determine the compressive strength performance of each chemical ratio individual and whether the combination can reach the target compressive strength. In the iterative process of the algorithm, the combination with the compressive strength closer to the target value is preferentially selected, thereby improving the optimization speed of the algorithm.

[0093] Specifically, the above step S2033 includes: inputting the proportion of different chemical components corresponding to each chemical ratio individual into a preset cement performance prediction function constructed based on the empirical data relationship between chemical composition and compressive strength, and predicting the predicted compressive strength value corresponding to each chemical ratio individual;

[0094] The cement performance prediction function is expressed by the following formula:

[0095]

[0096] Where f1[j] represents the predicted compressive strength value corresponding to the jth chemical ratio individual, N represents the number of chemical components, and x i represents the proportion of the i-th chemical component in the current chemical ratio individual, y i Represents the weight of the i-th chemical component in the current chemical ratio individual when calculating the predicted compressive strength value.

[0097] For example, when the chemical composition type is determined to be SiO2, Al2O3, Fe2O3, CaO, and MgO, the corresponding cement performance prediction function is as follows:

[0098] f=x1y1+x2y2+x3y3+x4y4+x5y5;

[0099] Among them, x1, x2, x3, x4, and x5 respectively represent the proportion of SiO2, Al2O3, Fe2O3, CaO, and MgO in the chemical proportion; y1, y2, y3, y4, and y5 respectively represent the weights of SiO2, Al2O3, Fe2O3, CaO, and MgO in the predicted compressive strength value.

[0100] The embodiment of the present invention inputs the proportions of different chemical components, and the prediction function constructed based on the empirical data relationship is faster than the actual experimental test speed in the prior art. The prediction function can calculate the compressive strength value of each chemical ratio individual, quickly evaluate the compressive strength of multiple chemical ratios, reduce the waste of computing resources, speed up the optimization process, and provide a data basis for the subsequent calculation of absolute differences.

[0101] Step S2034, according to the predicted compressive strength value and the target compressive strength value corresponding to each chemical ratio individual, according to the preset absolute difference function, calculate the absolute difference corresponding to each chemical ratio individual.

[0102] It should be noted that the calculation of the absolute difference function is to evaluate the difference between each individual and the target value. The smaller the difference, the closer the performance of the individual is to the expected target. In genetic algorithms, the absolute difference will directly affect the fitness function, thereby determining the probability of the individual being selected in the next generation.

[0103] Specifically, the above step S2034 includes: presetting the absolute difference function to be expressed by the following formula:

[0104] f2[j]=|target_strength-f1[j]|;

[0105] Among them, f2[j] represents the absolute difference corresponding to the j-th chemical ratio individual, f1[j] represents the predicted compressive strength value corresponding to the j-th chemical ratio individual, and target_strength represents the target compressive strength value;

[0106] For example, the target compressive strength value is 50 MPa. For each individual, the predicted compressive strength value is subtracted from the target compressive strength value and the absolute value is taken. For example, for an individual with a predicted strength of 48 MPa, the absolute difference is 2 MPa. In this way, the absolute difference of each individual is calculated for the next step of fitness value calculation.

[0107] Step S2035, calculating the fitness value corresponding to each chemical ratio individual according to the corresponding absolute difference value of each chemical ratio individual.

[0108] Specifically, the above step S2035 includes: inputting the absolute difference corresponding to each chemical ratio individual into the fitness calculation function to calculate the fitness value corresponding to each chemical ratio individual;

[0109] The fitness calculation function is expressed by the following formula:

[0110]

[0111] Among them, f3[j] represents the fitness value corresponding to the jth chemical ratio individual.

[0112] It is understandable that the purpose of calculating the fitness value is to select individuals with a smaller gap with the target value to enter the next generation, thereby gradually approaching the optimal solution. The size of the fitness value directly affects the priority of the individual in the selection operation. The individual with a smaller difference usually has a higher fitness value. For example, the absolute difference is 2 calculated in the previous step, then the fitness value calculation result of the individual is 0.5. Individuals with high fitness values ​​will be retained in the next generation.

[0113] The embodiment of the present invention determines the degree of deviation between the predicted compressive strength value and the target compressive strength value of each chemical component combination by calculating the absolute difference. At the same time, by calculating the fitness value, it is ensured that the combination with high fitness can be preferentially selected for the next round of crossover or mutation operation in each subsequent round of iteration, thereby improving the accuracy of the optimization process and providing a data basis for the subsequent selection process.

[0114] Step S2036, calculate the selection probability according to the fitness value of each chemical ratio individual, and select one or more target parent individuals.

[0115] The selection probability in the embodiment of the present invention is used to control the retention of individuals, ensuring that individuals with high fitness are given priority in entering the next generation. Through such a selection method, the inheritance opportunity of individuals with high fitness is increased, thereby improving the optimization efficiency.

[0116] Specifically, the above step S2036 includes:

[0117] Step a1, input the fitness value corresponding to each chemical ratio individual into the roulette probability calculation function, and calculate the selection probability corresponding to each chemical ratio individual; the roulette probability calculation function is represented by the following formula:

[0118]

[0119] Among them, f4[j] represents the selection probability corresponding to the jth chemical ratio individual, and M represents the number of chemical ratio individuals in the first iteration population;

[0120] Step a2, comparing the selection probability corresponding to each chemical ratio individual with a preset selection probability threshold, and selecting one or more chemical ratio individuals corresponding to a selection probability greater than the selection probability threshold as the target parent individual.

[0121] For example, through the roulette wheel selection method, individuals with higher fitness values ​​are given a higher selection probability. Assuming that the sum of the fitness values ​​of all individuals in the population is 2, if the fitness of one of the chemical ratio individuals is 0.5, then its selection probability is 25%. In this embodiment, individuals with chemical ratios higher than 10% can be selected according to the preset selection probability threshold of 10%.

[0122] The embodiment of the present invention calculates the fitness value of each chemical ratio individual and inputs it into the roulette probability calculation function to ensure that individuals with high fitness have a greater probability of being selected as the target parent individual. The reason why the individual with the highest fitness is not directly selected but the parent individual is selected according to probability is to ensure the diversity of solutions and further expand the number of individuals in the iterative population, thereby ensuring that the iterative result can be globally optimal.

[0123] Step S2037, performing a gene crossover operation or a gene mutation operation on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals, wherein all target child individuals constitute a second iterative population.

[0124] In this embodiment, the gene crossover and mutation operations generate new target offspring individuals by combining or mutating the parent genes, thereby forming a new population. The crossover operation exchanges some genes of the parent individuals, and the mutation operation randomly changes some genes of the individuals. This enables the algorithm to explore a wider solution space and avoid local optimal solutions caused by early convergence. The crossover operation retains the excellent gene combinations of the parent individuals, and the mutation operation introduces randomness to prevent the algorithm from falling into the local optimum.

[0125] In an optional implementation, if the number of target parent individuals is greater than or equal to two, step S2037 specifically includes:

[0126] Step b1, selecting two target parent individuals to be crossed from two or more target parent individuals, and randomly determining the intersection positions of the two target parent individuals to be crossed;

[0127] Step b2, exchanging the chemical component gene fragments at the intersection position of each of the target parent individuals to be crossed to obtain two target child individuals, wherein the chemical component gene fragment represents the proportion of a chemical component in the target parent individual; when all the target parent individuals are subjected to gene crossover operations, target child individuals corresponding to multiple target parent individuals are obtained.

[0128] It should be noted that in genetic algorithms, gene crossover operation refers to exchanging gene fragments between parent individuals to generate new offspring individuals and expand the search space for solutions.

[0129] Specifically, two individuals are randomly selected as the parents to be crossed, and one or more positions are randomly selected as crossover points on the gene sequences of the two selected parent individuals. In this embodiment, each individual represents a ratio combination of chemical components of cement clinker, and the gene sequence of each ratio combination is represented by binary code. The method of selecting the crossover point can be: single-point crossover, i.e., randomly selecting a position in the gene sequence as the crossover point; multi-point crossover, i.e., randomly selecting multiple positions in the gene sequence as the crossover points; uniform crossover, i.e., randomly deciding whether to exchange each gene.

[0130] For example, there are two parent individuals, and their gene sequences are:

[0131] Parent 1: 1100 1100 1111 0001;

[0132] Parent 2: 1100 1010 1111 1011;

[0133] Among them, "1100" and "1111" represent two different chemical components A and chemical component B respectively. "1100" represents the proportion of chemical component A in parent 1, "0001" represents the proportion of chemical component B in parent 1, "1010" represents the proportion of chemical component A in parent 2, and "1011" represents the proportion of chemical component B in parent 2. If the crossover position is selected as 5-8, "1100" and "1010" are exchanged to obtain two offspring, and the gene sequences are:

[0134] Offspring 1: 1100 1010 1111 0001;

[0135] Offspring 2: 1100 1100 1111 1011;

[0136] In this embodiment, by randomly selecting parent individuals and crossover points, the diversity of the population is increased, which is conducive to searching for the optimal solution in a larger solution space.

[0137] In the embodiment of the present invention, the characteristics of the two parent individuals are combined into new child individuals by randomly selecting the intersection position of the target parent individual and exchanging the gene fragments. Since the number of child individuals will not decrease, the diversity of the population is improved, the search accuracy of the genetic algorithm is guaranteed, and the optimization process will not fall into the local optimal solution, so as to more accurately find the global optimal solution of the chemical composition ratio individual.

[0138] In another optional implementation, step S2037 specifically includes:

[0139] Step c1, randomly determining the position of the mutation point in each target parent individual according to a preset mutation probability;

[0140] Step c2, numerically transforming the chemical composition gene fragment at the mutation point position of the target parent individual according to the preset value range of different chemical components in cement clinker and preset constraints to obtain the target child individual corresponding to each target parent individual.

[0141] It should be noted that when the mutation probability is preset, it is necessary to combine the set factors, such as the optimization speed and the individual range of the population. When a larger population range is required, a higher mutation probability is selected, and when a faster optimization speed is required, a lower mutation probability is selected.

[0142] This embodiment continues to use the example of step b1 to step b2 above to illustrate, there is a parent individual, the gene sequence is as follows: parent 1: 1100 1100 1111 0001;

[0143] If the probability is set to 50% mutation probability, 4 binary bits will mutate among the 8 bits "1100" and "0001". For example, the gene sequence of the offspring after mutation is as follows: Offspring 1: 1100 1001 1111 0011.

[0144] In the embodiment of the present invention, the random bits of the gene encoding of the individual are mutated according to the setting of the mutation probability, and different genes are introduced in each iteration to ensure that the number of sub-individuals will not decrease. In some cases, it will be further expanded, so that the generated chemical component combinations are more diverse, thereby more accurately finding the global optimal solution of the chemical component ratio individual.

[0145] Step S2038, determine whether the current number of iterations reaches the target number of iterations. If not, replace the second iteration population with the first iteration population to perform the next round of iterations. If the target number of iterations is reached, select the chemical ratio individual with the highest fitness value among all chemical ratio individuals in the last round of iterations as the optimized chemical ratio individual, and output the corresponding second chemical composition combination, which represents the proportion combination of the optimized chemical components corresponding to the target compressive strength value.

[0146] Specifically, a counter is set to 0 initially to record the number of completed iterations. Each time an iteration is completed, the counter is incremented by 1, and the value of the counter is compared with the preset target number of iterations. For example, there are 100 chemical ratio individuals in the last round of iterations, and their fitness values ​​are 0.85, 0.92, 0.88...0.90 respectively. The system will select the individual with a fitness value of 0.92 as the final optimization result. The selected optimal individual is decoded and its gene sequence is converted into the actual chemical composition ratio value.

[0147] The embodiment of the present invention generates a random initial population according to the preset value range and constraints of the chemical composition of cement clinker, and adds the first chemical composition combination in the preset database to the initial population, which not only ensures that the diversity of solutions is effectively increased, but also can effectively narrow the search space of solutions based on the initial first chemical composition combination, calculates the compressive strength of each chemical ratio individual according to the preset prediction function, and compares it with the target value, calculates the absolute difference and the fitness value, and generates new combinations by simulating the biological evolution process, thereby retaining combinations with high fitness and determining new potential combinations, avoiding local optimality, and improving the degree of global optimization. By judging whether the number of iterations reaches the preset target, the algorithm obtains the optimal solution after a sufficient number of cycles. If the set termination condition is met, the individual with the highest fitness is selected from the population of the final iteration as the optimized chemical composition combination, to ensure that the obtained combination is the optimal solution after iterative optimization and is more in line with the target compressive strength requirement.

[0148] In the actual application process, the operation process of the present invention can refer to Figure 3 , establish a field matching database for cement, and predict the target compressive strength based on the historical data in the database and the chemical composition ratio of cement raw materials. Based on the predicted target compressive strength, the chemical composition of cement clinker in the database is matched through an improved genetic algorithm, and the relevant component ratios are optimized. This optimization process includes the steps of population initialization, definition of objective function f, calculation of fitness function, and judgment of whether the iteration termination conditions are met. If the number of iterations required is met, the optimized clinker composition is output; otherwise, the optimization is continued through roulette wheel selection, crossover and mutation operations until the specified target strength and component ratio are reached. Based on the optimized cement clinker composition, the raw material composition of cement raw materials can be further deduced.

[0149] Among them, the target compressive strength is not only a simple numerical setting. In the field of construction engineering, the compressive strength of cement clinker is the core indicator for evaluating the strength of concrete and the durability of the structure. Therefore, when optimizing the ratio of cement clinker components, it is very important to set a scientific and reasonable compressive strength target, which is directly related to whether the final optimization effect meets the actual engineering needs.

[0150] When optimizing the composition ratio of cement clinker, the optimal solution that meets the target compressive strength and composition constraints is gradually sought. The main method used is (1) roulette selection. The roulette selection method is used to select individuals in the population. Based on the fitness value of the individual, the individual with a higher fitness value is more likely to be selected. Through roulette selection, retaining individuals with higher fitness can improve the optimization efficiency, accelerate the convergence speed, and help to quickly find a solution close to the target. (2) Ordered crossover method is an operation of gene recombination based on the chromosome sequence of the parent generation, which retains the excellent characteristics of the parent generation individuals and increases new genetic diversity, thereby increasing the diversity of the population during the optimization process. Avoid the population from converging to the local optimal solution, but further explore the global optimal solution. (3) Two-point mutation method. In order to further increase the diversity of the population, combined with the two-point mutation method, during the mutation process, the chromosome sequence of the individual is randomly selected and locally changed to generate new individuals, expand the solution space, avoid the algorithm from falling into the local optimal solution, and improve the global search ability. The entire search process is iterated multiple times until the optimal solution that meets the target compressive strength and various constraints is found. Through continuous iterative optimization, the optimal solution can be gradually approached and the optimal cement clinker chemical composition ratio can be finally found.

[0151] Under the conditions of raw material oxide composition and ignition loss in Table 1, the target compressive strength of 28d = 47.6 MPa is taken as an example for explanation. As shown in Table 2, the main component data before and after optimization are compared:

[0152] Table 1 Oxide composition and ignition loss of cement raw materials

[0153] raw material Loss <![CDATA[SiO2]]> <![CDATA[Al2O3]]> <![CDATA[Fe2O3]]> CaO MgO limestone 41.30 4.40 0.64 0.32 52.41 0.47 Fly ash 0.92 46.34 44.77 2.29 2.55 0.37 Iron slag -2.10 33.3 7.48 38.56 12.34 2.44 sandstone 0.40 91.85 3.02 2.37 0.42 0.37

[0154] Table 2 Comparison values ​​of cement clinker before and after optimization

[0155] Compressive strength 28 days <![CDATA[SiO2(%)]]> <![CDATA[Al2O3(%)]]> <![CDATA[Fe2O3(%)]]> CaO(%) MgO(%) Before optimization 22.32 5.21 3.73 66.33 0.84 After optimization 23.56 6.12 5.29 62.24 0.90

[0156] Among them, taking CaO (calcium oxide) as an example: before optimization, the content of CaO was 66.33%, and after optimization it dropped to 62.24%. Since in actual industrial production environments, reducing the proportion of CaO can be used to reduce carbon emissions, the embodiment of the present invention successfully reduces the content of CaO through optimization of genetic algorithms while maintaining the compressive strength unchanged. Other cement clinker components can be compared to CaO (calcium oxide), which will not be repeated here.

[0157] Furthermore, after obtaining the main component data of the optimized cement clinker, the cement raw material ratio information is determined based on the main component data of the optimized cement clinker, specifically including: calculating the raw material ratio information using a preset raw material density calculation model, or determining the raw material ratio information based on a pre-stored cement clinker-cement raw material mapping relationship, etc. The embodiments of the present invention are not limited to this.

[0158] Exemplarily, the optimized raw material ratio obtained by the embodiment of the present invention based on the main component data of the optimized cement clinker is shown in Table 3:

[0159] Table 3 Comparison of cement raw material ratio before and after optimization

[0160] Cement raw material formula limestone Fly ash Iron slag sandstone Original recipe 82.167 5.173 4.930 7.730 Alternative recipes 78.260 6.327 7.803 7.611

[0161] Among them, the original formula represents the raw material ratio of cement before optimization, and the alternative formula represents the raw material ratio after optimization. It can be understood that by improving the genetic algorithm, the chemical composition of cement clinker is fine-tuned to meet specific material requirements or performance needs while keeping the same 28-day compressive strength value. This optimization may affect the preparation process and final performance of cement clinker, thus playing an important role in engineering or construction applications.

[0162] In the present embodiment, a cement raw material ratio optimization system is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0163] This embodiment provides a cement raw material ratio optimization system. Figure 4 As shown, including:

[0164] A target compressive strength setting module 401 is used to determine a target compressive strength value based on the chemical composition ratio of the cement raw material;

[0165] The matching chemical component combination extraction module 402 is used to obtain a first chemical component combination of cement clinker that matches the target compressive strength value from a preset cement ratio database; the first chemical component combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical component types and corresponding proportions;

[0166] The chemical composition combination optimization module 403 is used to perform iterative optimization using a genetic algorithm according to the first chemical composition proportion combination, the preset value range of different chemical components in the cement clinker, and the preset constraints to obtain a second chemical composition combination, where the second chemical composition combination represents the optimized chemical composition proportion combination corresponding to the first chemical composition combination.

[0167] In an optional embodiment, the chemical composition combination optimization module 403 includes:

[0168] The initialization population unit is used to randomly generate an initial chemical proportion population according to the preset value range of different chemical components in the cement clinker and the preset constraint conditions; wherein the initial chemical proportion population includes a plurality of chemical proportion individuals, and a chemical proportion individual represents the proportion combination information of a plurality of different chemical components;

[0169] A first iterative population unit, used for adding the chemical ratio individuals corresponding to the first chemical component combination to the initial chemical ratio population to obtain a first iterative population;

[0170] A compressive strength prediction unit is used to calculate the predicted compressive strength value corresponding to each chemical ratio individual according to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population and according to the preset cement performance prediction function;

[0171] An absolute difference calculation unit, used to calculate the absolute difference corresponding to each chemical ratio individual according to the predicted compressive strength value and the target compressive strength value corresponding to each chemical ratio individual and according to a preset absolute difference function;

[0172] A fitness calculation unit, used to calculate the fitness value corresponding to each chemical ratio individual according to the corresponding absolute difference value of each chemical ratio individual;

[0173] A selection probability calculation unit is used to calculate the selection probability according to the fitness value of each chemical ratio individual and select one or more target parent individuals;

[0174] A gene operation unit is used to perform a gene crossover operation or a gene mutation operation on one or more target parent individuals to obtain target child individuals corresponding to the multiple target parent individuals, wherein all target child individuals constitute a second iterative population;

[0175] The iteration judgment unit is used to judge whether the current number of iterations has reached the target number of iterations. If the target number of iterations has not been reached, the second iteration population is replaced by the first iteration population to perform the next round of iterations. If the target number of iterations has been reached, the chemical ratio individual with the highest fitness value among all chemical ratio individuals in the last round of iterations is selected as the optimized chemical ratio individual, and the corresponding second chemical composition combination is output. The second chemical composition combination represents the proportion combination of the optimized chemical components corresponding to the target compressive strength value.

[0176] In an optional implementation, according to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population, according to the preset cement performance prediction function, the predicted compressive strength value corresponding to each chemical ratio individual is calculated, specifically including:

[0177] Input the proportion of different chemical components corresponding to each chemical ratio individual into a preset cement performance prediction function constructed based on the empirical data relationship between chemical composition and compressive strength, and predict the predicted compressive strength value corresponding to each chemical ratio individual;

[0178] The cement performance prediction function is expressed by the following formula:

[0179]

[0180] Where f1[j] represents the predicted compressive strength value corresponding to the jth chemical ratio individual, N represents the number of chemical components, and x i represents the proportion of the i-th chemical component in the current chemical ratio individual, y i Represents the weight of the i-th chemical component in the current chemical ratio individual when calculating the predicted compressive strength value.

[0181] In an optional implementation, the preset absolute difference function is expressed by the following formula:

[0182] f2[j]=|target_strength-f1[j]|;

[0183] Among them, f2[j] represents the absolute difference corresponding to the j-th chemical ratio individual, f1[j] represents the predicted compressive strength value corresponding to the j-th chemical ratio individual, and target_strength represents the target compressive strength value;

[0184] According to the corresponding absolute difference of each chemical ratio individual, the fitness value corresponding to each chemical ratio individual is calculated, including:

[0185] The absolute difference corresponding to each chemical ratio individual is input into the fitness calculation function to calculate the fitness value corresponding to each chemical ratio individual; the fitness calculation function is expressed by the following formula:

[0186]

[0187] Among them, f3[j] represents the fitness value corresponding to the jth chemical ratio individual.

[0188] In an optional implementation, the selection probability is calculated according to the fitness value of each chemical ratio individual, and one or more target parent individuals are selected, specifically including:

[0189] The fitness value corresponding to each chemical ratio individual is input into the roulette probability calculation function to calculate the selection probability corresponding to each chemical ratio individual; the roulette probability calculation function is expressed by the following formula:

[0190]

[0191] Among them, f4[j] represents the selection probability corresponding to the jth chemical ratio individual, and M represents the number of chemical ratio individuals in the first iteration population;

[0192] The selection probability corresponding to each chemical ratio individual is compared with a preset selection probability threshold, and one or more chemical ratio individuals corresponding to a selection probability greater than the selection probability threshold are selected as the target parent individual.

[0193] In an optional embodiment, if the number of target parent individuals is greater than or equal to two, the gene operation unit specifically includes:

[0194] A crossover operation subunit, used for selecting two target parent individuals to be crossed from two or more target parent individuals, and randomly determining the positions of the crossover points in the two target parent individuals to be crossed;

[0195] The gene exchange subunit is used to exchange the chemical component gene fragments at the crossover point positions of the target parent individuals to be crossed, so as to obtain two target child individuals, wherein the chemical component gene fragment represents the proportion of a chemical component in the target parent individual; when all the target parent individuals are subjected to gene crossover operations, target child individuals corresponding to multiple target parent individuals are obtained.

[0196] In an optional embodiment, the gene manipulation unit specifically includes:

[0197] A mutation point selection subunit is used to randomly determine the mutation point position in each target parent individual according to a preset mutation probability;

[0198] The mutation processing subunit is used to perform numerical transformation on the chemical composition gene fragment at the mutation point of the target parent individual according to the preset value range of different chemical components in cement clinker and preset constraints to obtain the target child individual corresponding to each target parent individual.

[0199] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0200] The cement raw material ratio optimization system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0201] The embodiment of the present invention also provides a computer device having the above Figure 4 The cement raw material ratio optimization system shown.

[0202] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0203] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0204] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0205] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0206] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0207] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0208] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0209] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0210] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the defined scope.

Claims

1. A method for optimizing cement raw material ratio, characterized in that: The method comprises: Determine the target compressive strength value based on the chemical composition ratio of the cement raw material; Obtaining a first chemical component combination of cement clinker matching the target compressive strength value from a preset cement ratio database; the first chemical component combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical component types and corresponding proportions; According to the first chemical component proportion combination, the preset value range of different chemical components in cement clinker and the preset constraints, a genetic algorithm is used to perform iterative optimization to obtain a second chemical component combination, which represents the optimized chemical component proportion combination corresponding to the first chemical component combination.

2. The method according to claim 1, characterized in that The second chemical component combination is obtained by optimizing using a genetic algorithm according to the first chemical component proportion combination, the preset value range of different chemical components in the cement clinker, and the preset constraint conditions. The second chemical component combination represents the optimized chemical component proportion combination corresponding to the first chemical component combination, and specifically includes: According to the preset value ranges of different chemical components in cement clinker and preset constraints, an initial chemical proportion population is randomly generated; wherein the initial chemical proportion population includes a plurality of chemical proportion individuals, and a chemical proportion individual represents the proportion combination information of a plurality of different chemical components; Adding the chemical ratio individuals corresponding to the first chemical component combination to the initial chemical ratio population to obtain a first iterative population; According to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population, according to the preset cement performance prediction function, the predicted compressive strength value corresponding to each chemical ratio individual is calculated; According to the predicted compressive strength value and the target compressive strength value corresponding to each chemical ratio individual, the absolute difference corresponding to each chemical ratio individual is calculated according to the preset absolute difference function; According to the corresponding absolute difference of each chemical ratio individual, the fitness value corresponding to each chemical ratio individual is calculated; The selection probability is calculated according to the fitness value of each chemical ratio individual, and one or more target parent individuals are selected; Performing a gene crossover operation or a gene mutation operation on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals, wherein all target child individuals constitute a second iterative population; It is determined whether the current number of iterations reaches the target number of iterations. If not, the second iteration population is replaced by the first iteration population to perform the next round of iterations. If the target number of iterations is reached, the chemical ratio individual with the highest fitness value among all chemical ratio individuals in the last round of iterations is selected as the optimized chemical ratio individual, and the corresponding second chemical composition combination is output, wherein the second chemical composition combination represents the proportion combination of the optimized chemical components corresponding to the target compressive strength value.

3. The method according to claim 2, characterized in that The method of calculating the predicted compressive strength value corresponding to each chemical ratio individual according to the proportion combination information of different chemical components corresponding to each chemical ratio individual in the first iteration population and according to the preset cement performance prediction function specifically includes: Input the proportion of different chemical components corresponding to each chemical ratio individual into a preset cement performance prediction function constructed based on the empirical data relationship between chemical composition and compressive strength, and predict the predicted compressive strength value corresponding to each chemical ratio individual; The cement performance prediction function is expressed by the following formula: Where f1[j] represents the predicted compressive strength value corresponding to the jth chemical ratio individual, N represents the number of chemical components, and x i represents the proportion of the i-th chemical component in the current chemical ratio individual, y i Represents the weight of the i-th chemical component in the current chemical ratio individual when calculating the predicted compressive strength value.

4. The method according to claim 2 or 3, characterized in that: The preset absolute difference function is expressed by the following formula: f2[j]=|target_strength-f1[j]|; Among them, f2[j] represents the absolute difference corresponding to the j-th chemical ratio individual, f1[j] represents the predicted compressive strength value corresponding to the j-th chemical ratio individual, and target_strength represents the target compressive strength value; The step of calculating the fitness value corresponding to each chemical ratio individual according to the corresponding absolute difference value of each chemical ratio individual specifically includes: The absolute difference corresponding to each chemical ratio individual is input into the fitness calculation function to calculate the fitness value corresponding to each chemical ratio individual; the fitness calculation function is represented by the following formula: Among them, f3[j] represents the fitness value corresponding to the jth chemical ratio individual.

5. The method according to claim 4, characterized in that The method of calculating the selection probability according to the fitness value of each chemical ratio individual and selecting one or more target parent individuals specifically includes: The fitness value corresponding to each chemical ratio individual is input into the roulette probability calculation function to calculate the selection probability corresponding to each chemical ratio individual; the roulette probability calculation function is represented by the following formula: Among them, f4[j] represents the selection probability corresponding to the jth chemical ratio individual, and M represents the number of chemical ratio individuals in the first iteration population; The selection probability corresponding to each chemical ratio individual is compared with a preset selection probability threshold, and one or more chemical ratio individuals corresponding to a selection probability greater than the selection probability threshold are selected as the target parent individual.

6. The method according to claim 5, characterized in that If the number of target parent individuals is greater than or equal to two, a gene crossover operation is performed on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals, specifically including Selecting two target parent individuals to be crossed from two or more target parent individuals, and randomly determining the positions of the crossover points in the two target parent individuals to be crossed; The chemical component gene fragments are exchanged at the crossover point positions of the target parent individuals to be crossed to obtain two target child individuals, wherein the chemical component gene fragments represent the proportion of a chemical component in the target parent individual; when all the target parent individuals are subjected to gene crossover operations, target child individuals corresponding to multiple target parent individuals are obtained.

7. The method according to claim 6, characterized in that Performing a gene crossover operation on one or more target parent individuals to obtain target child individuals corresponding to multiple target parent individuals includes: The mutation point position in each target parent individual is randomly determined according to the preset mutation probability; The chemical component gene fragment at the mutation point position of the target parent individual is numerically transformed according to the preset value range of different chemical components in cement clinker and preset constraints to obtain the target child individual corresponding to each target parent individual.

8. A cement raw material ratio optimization system, characterized in that: The system comprises: A target compressive strength setting module is used to determine a target compressive strength value based on the chemical composition ratio of the cement raw material; A matching chemical composition combination extraction module is used to obtain a first chemical composition combination of cement clinker that matches the target compressive strength value from a preset cement ratio database; the first chemical composition combination represents a proportion combination of chemical components before optimization corresponding to the target compressive strength value, and the proportion combination includes multiple chemical composition types and corresponding proportions; The chemical composition combination optimization module is used to perform iterative optimization using a genetic algorithm according to the first chemical composition proportion combination, the preset value range of different chemical components in the cement clinker and the preset constraints to obtain a second chemical composition combination, wherein the second chemical composition combination represents the optimized chemical composition proportion combination corresponding to the first chemical composition combination.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the cement raw material ratio optimization method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the cement raw material ratio optimization method according to any one of claims 1 to 7.

Images