Cement cost determination method, apparatus, electronic device, and medium

Abstract

The application provides a cement cost determination method and device, electronic equipment and medium, and relates to the field of cement.The method comprises the following steps: obtaining target proportions of component cement ingredients according to each proportion constraint interval of the component cement ingredients and a preset proportion target; and determining the cement cost according to the target proportions of all component cement ingredients and the unit price of each component cement ingredient, in the case that a target particle size distribution of the target proportions meets a preset particle size distribution constraint interval, a target cement fineness of the target proportions meets a preset cement fineness constraint interval, and a target cement strength of the target proportions meets a preset cement strength constraint interval.The application seeks an optimal cement grinding ingredient scheme by taking the following conditions as constraints: suitable cement particle size distribution composition, lowest cement comprehensive cost, and lowest cement quality meeting standard requirements, so as to reduce the cement cost while ensuring that the constraints are met.

Description

Technical Field

[0001] This invention relates to the field of cement, and more particularly to a method, apparatus, electronic device, and medium for determining cement costs. Background Technology

[0002] Currently, cement grinding systems and intelligent batching control still have certain lags and limitations in solving product fluctuations and multi-objective optimization. They cannot take into account cement particle size distribution, cost, and quality to determine the most suitable cement mix ratio to reduce cement costs. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and medium for determining cement costs, which addresses the shortcomings of existing technologies in ensuring cement particle size distribution, controlling costs, and guaranteeing cement quality. It provides a technical solution for determining the optimal solution of the component proportions of cement under various constraints.

[0004] In a first aspect, the present invention provides a method for determining cement costs, comprising:

[0005] Based on the proportion constraints of each component cement ingredient and the preset proportion target, obtain the target proportion of each component cement ingredient;

[0006] If the target particle size distribution of the target mix meets the preset particle size distribution constraint range, the target cement fineness of the target mix meets the preset cement fineness constraint range, and the target cement strength of the target mix meets the preset cement strength constraint range, the cement cost is determined based on the target mix proportions of all component cement ingredients and the unit price of each component cement ingredient.

[0007] According to the cement cost determination method provided by the present invention, the step of obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and a preset proportion target includes:

[0008] Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the lowest proportion cost of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined.

[0009] The proportion cost of all component cement ingredients is determined based on the sum of the costs of each component cement ingredient.

[0010] The cost of each component of the cement mix is ​​determined based on the proportion of each component and the unit price of each component.

[0011] The cement ingredients include at least one of limestone, coal gangue, fly ash, slag, clinker, and gypsum.

[0012] The sum of the target proportions of each component cement ingredient is a preset constant;

[0013] Each proportion constraint range of the cement ingredients includes:

[0014] The proportion of limestone is greater than or equal to the first lower limit and less than or equal to the first upper limit;

[0015] The proportion of coal gangue is greater than or equal to the second lower limit and less than or equal to the second upper limit;

[0016] The proportion of fly ash is greater than or equal to the third lower limit and less than or equal to the third upper limit;

[0017] The proportion of slag is greater than or equal to the fourth lower limit and less than or equal to the fourth upper limit;

[0018] The proportion of clinker is greater than or equal to the fifth lower limit and less than or equal to the fifth upper limit;

[0019] The proportion of gypsum is greater than or equal to the sixth lower limit and less than or equal to the sixth upper limit.

[0020] According to the cement cost determination method provided by the present invention, the step of obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and a preset proportion target includes:

[0021] Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the maximum sum of the proportions of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined.

[0022] The cement ingredients include at least one of limestone, coal gangue, fly ash, and slag.

[0023] The sum of the target proportions of each component of the cement mix is ​​a preset constant.

[0024] According to the cement cost determination method provided by the present invention, after obtaining the target proportions of each component cement ingredient, the method further includes:

[0025] Input the target proportions of each cement component into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model;

[0026] Input the target proportions of each cement component into the cement fineness model, and obtain the target cement fineness output by the cement fineness model;

[0027] Input the target proportions of each cement component into the cement strength model, and obtain the target cement strength output by the cement strength model.

[0028] The particle size distribution model was determined based on the sample proportions of each cement component and the linear fitting of the sample particle size distribution.

[0029] The cement fineness model was determined based on the sample proportions of each component cement ingredient and the linear fitting of the sample cement fineness.

[0030] The cement strength model was determined based on the sample proportions of each component cement mix and the linear fitting of the sample cement strength.

[0031] According to the cement cost determination method provided by the present invention, the target particle size distribution of the target mix proportion satisfies a preset particle size distribution constraint range, the target cement fineness of the target mix proportion satisfies a preset cement fineness constraint range, and the target cement strength of the target mix proportion satisfies a preset cement strength constraint range, including:

[0032] The target particle size distribution is greater than or equal to the seventh lower limit and less than or equal to the seventh upper limit;

[0033] The target cement fineness is greater than or equal to the eighth lower limit and less than or equal to the eighth upper limit;

[0034] The target cement strength is greater than or equal to the ninth lower limit and less than or equal to the ninth upper limit;

[0035] The target particle size distribution is greater than or equal to a first preset threshold, the target cement fineness is less than or equal to a second preset threshold, the target cement strength is greater than or equal to a third preset threshold, the first preset threshold is greater than the third preset threshold, and the third preset threshold is greater than the second preset threshold.

[0036] According to the cement cost determination method provided by the present invention, the step of determining the cement cost based on the target proportions of all component cement ingredients and the unit price of each component cement ingredient includes:

[0037] The target cost of each cement component is determined based on the target proportion of each component and the unit price of each component.

[0038] The cement cost is determined by the sum of the target costs of all cement components.

[0039] According to the cement cost determination method provided by the present invention, after determining the cement cost based on the sum of the target costs of all component cement ingredients, the method further includes:

[0040] The total cement time is determined based on the total amount of cement and the cement work hours.

[0041] The electricity cost is determined based on the total cement production time and the electricity consumption of cement.

[0042] The total cost of cement is determined based on the cement cost and the electricity cost.

[0043] Secondly, a cement cost determination device is provided, comprising:

[0044] Acquisition Unit: Used to acquire the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target;

[0045] Determining unit: used to determine cement cost based on the target proportions of all cement components and the unit price of each cement component, provided that the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range.

[0046] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the cement cost determination method.

[0047] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cement cost determination method as described above.

[0048] The cement cost determination method, apparatus, electronic device, and medium provided by this invention first use each proportion constraint range of each component cement batch as a constraint condition, and a preset proportion target as an optimization target to obtain the target proportion of each component cement batch. The obtained target proportion also needs to satisfy: the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range. By using the appropriate cement particle size distribution, the lowest comprehensive cement cost, and the lowest cement quality to meet the standard requirements as constraints, the optimal cement grinding batching scheme is recommended to reduce cement cost while ensuring compliance with the constraints. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0050] Figure 1 This is one of the flowcharts illustrating the cement cost determination method provided by the present invention;

[0051] Figure 2This is the second flowchart illustrating the cement cost determination method provided by the present invention;

[0052] Figure 3 This is a schematic diagram of the process for determining cement costs provided by the present invention;

[0053] Figure 4 This is the third flowchart illustrating the cement cost determination method provided by the present invention;

[0054] Figure 5 This is a schematic diagram of the cement cost determination device provided by the present invention;

[0055] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0057] In the traditional operation and management of cement grinding systems, quality managers or process engineers typically rely on past technical experience, actual quality analysis of inventory clinker and blended materials, cement company management procedures, and internal control standards to issue production ratios for various blended materials, clinker, and desulfurized gypsum according to the cement production plan. However, this production method often fails to guarantee optimal cement product quality and proportions. Currently, intelligent control of cement grinding systems and batching still has limitations in addressing issues such as lag, product fluctuations, and multi-objective optimization.

[0058] From the perspective of clinker conservation and environmental protection, it is necessary to fully utilize the chemical activity of cement clinker particles to maximize resource utilization, and to improve the performance of cement and the workability of concrete. However, as an intermediate product in the building materials industry chain, the specific characteristics of cement performance are reflected in concrete. With the continuous emergence of high-performance concrete, concrete has put forward more and more stringent and detailed requirements for cement performance, such as the compatibility of admixtures, concrete workability and durability. In the past, it was often thought that the silicate mineral content was the main issue affecting the performance of cement and concrete, but the correlation between the physical quantities that make up the gradation of cement particles and the performance of cement and concrete was ignored. The bulk density of cement particles has a great influence on the workability, strength and durability of the prepared concrete. Particle gradation is the performance system that comprehensively reflects the distribution of coarse and fine particles in cement.

[0059] However, currently there is no systematic solution for intelligent management and recommendation of cement batching optimization from the perspective of the industrial chain, based on meeting the performance requirements of concrete construction, such as cement particle size distribution, and with the constraints of lowest cost and suitable quality. Based on the above technical problems, this invention provides a method, apparatus, electronic device, and medium for determining cement costs. Figure 1 This is one of the flowcharts illustrating the cement cost determination method provided by the present invention, which provides a cement cost determination method, including:

[0060] Based on the proportion constraint range of each component cement ingredient and the preset proportion target, obtain the target proportion of each component cement ingredient;

[0061] If the target particle size distribution of the target mix meets the preset particle size distribution constraint range, the target cement fineness of the target mix meets the preset cement fineness constraint range, and the target cement strength of the target mix meets the preset cement strength constraint range, the cement cost is determined based on the target mix proportions of all component cement ingredients and the unit price of each component cement ingredient.

[0062] In step 101, the target proportion of each component cement ingredient is obtained according to each proportion constraint interval and the preset proportion target. The proportion constraint interval is the maximum and minimum input values ​​of the constraint configuration, so that the proportion of each component cement ingredient can only be selected from its corresponding maximum and minimum values. The purpose of setting each proportion constraint interval of each component cement ingredient is to ensure the quality of the finished cement product. The preset proportion target is the optimization direction, which can take cost reduction as the optimization target. The process of obtaining the target proportion with the lowest cost is the comprehensive optimization of the batching based on the low-cost cement batching optimization system for concrete function. This invention optimizes in real time under the constraint conditions corresponding to the target configuration and recommends the cement batching scheme that meets the lowest comprehensive cost of cement grinding.

[0063] In step 102, if the target particle size distribution of the target mix meets the preset particle size distribution constraint range, the target cement fineness of the target mix meets the preset cement fineness constraint range, and the target cement strength of the target mix meets the preset cement strength constraint range, the cement cost is determined based on the target mix proportions of all component cement ingredients and the unit price of each component cement ingredient.

[0064] Those skilled in the art will understand that the target proportion of each component cement ingredient obtained based on the constraint range of each proportion of each component cement ingredient and the preset proportion target is not a final configuration scheme. It still needs to be constrained by the next round of constraints, namely the constraints on the target particle size distribution, the target cement fineness and the target cement strength.

[0065] Based on the proportion constraints of each component of the cement mix and the preset proportion target, multiple target proportions can be obtained. The target particle size distribution, target cement fineness, and target cement strength are all determined based on the target proportions. Therefore, based on each target configuration, the corresponding target particle size distribution, target cement fineness, and target cement strength can be obtained. However, the target particle size distribution, target cement fineness, and target cement strength must meet their corresponding preset constraint ranges. Therefore, when the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range, it can be understood as a filtering process that can exclude target proportions that do not meet the preset constraint ranges.

[0066] In one optional embodiment, after obtaining all target proportions in step 101, the first target proportion that meets the standard of "the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range" can be determined as the target proportion for calculating cement cost according to step 102. In another optional embodiment, all target configurations can be displayed in a list, and the target proportion for calculating cement cost can be determined according to the received user input instructions.

[0067] Optionally, the present invention can not only calculate the target proportions of all cement components to achieve a suitable cement particle size distribution, the lowest overall cement cost, and cement quality that meets standard requirements, but also calculate the cement cost under the current proportion based on the target proportions of the component cement components. The cement cost is determined based on the target proportions of all component cement components and the unit price of each component cement component. Those skilled in the art will understand that in another optional embodiment, the present invention can also calculate the cement cost corresponding to the target proportions of all component cement components, and use the target proportion with the lowest cement cost as the final cement proportion, which is then put into actual production.

[0068] This invention provides an intelligent analysis method for a low-cost cement batching optimization system based on concrete functionality. This method can be applied to execution software. Through dynamic monitoring of incoming material components, process control of the grinding system, real-time prediction of cement product output, and pre-control of cement particle size distribution based on concrete construction performance, it aggregates and analyzes indicators and paths related to the entire process of the cement grinding system and concrete performance functions. This provides cement companies' quality managers with decision support for proactive and precise cement formulation design, periodic cement product prediction, cost optimization assessment, and matching of concrete construction performance. This enables intelligent management and control of cement batching scheme design, lean, digital, and service-oriented production, including quality and cost optimization.

[0069] Optionally, obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target includes:

[0070] Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the lowest proportion cost of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined.

[0071] The proportion cost of all component cement ingredients is determined based on the sum of the costs of each component cement ingredient.

[0072] The cost of each component of the cement mix is ​​determined based on the proportion of each component and the unit price of each component.

[0073] The cement ingredients include at least one of limestone, coal gangue, fly ash, slag, clinker, and gypsum.

[0074] The sum of the target proportions of each component cement ingredient is a preset constant;

[0075] Each proportion constraint range of the cement ingredients includes:

[0076] The proportion of limestone is greater than or equal to the first lower limit and less than or equal to the first upper limit;

[0077] The proportion of coal gangue is greater than or equal to the second lower limit and less than or equal to the second upper limit;

[0078] The proportion of fly ash is greater than or equal to the third lower limit and less than or equal to the third upper limit;

[0079] The proportion of slag is greater than or equal to the fourth lower limit and less than or equal to the fourth upper limit;

[0080] The proportion of clinker is greater than or equal to the fifth lower limit and less than or equal to the fifth upper limit;

[0081] The proportion of gypsum is greater than or equal to the sixth lower limit and less than or equal to the sixth upper limit.

[0082] Optionally, as a first optional embodiment of the present invention, the minimum proportion cost of all cement components is taken as the preset proportion target, as shown in the table below:

[0083]

[0084]

[0085] Based on the table above, the optimization objective is:

[0086] minT=P1*X1+P2*X2+P3*X3+P4*X4+P5*X5+P6*X6;

[0087] The constraints are:

[0088] X1+X2+X3+X4+X5+X6=1;

[0089] a1≤X1≤a2 (Limestone proportioning process constraint);

[0090] b1≤X2≤b2 (coal gangue proportioning process constraint);

[0091] c1≤X3≤c2 (Fly ash proportioning process constraint);

[0092] d1≤X4≤d2 (slag proportioning process constraint);

[0093] e1≤X5≤e2 (clinker proportioning process constraint);

[0094] f1≤X6≤f2 (gypsum mixing process constraints);

[0095] Where a1 is the first lower limit, a2 is the first upper limit, b1 is the second lower limit, b2 is the second upper limit, c1 is the third lower limit, c2 is the third upper limit, d1 is the fourth lower limit, d2 is the fourth upper limit, e1 is the fifth lower limit, e2 is the fifth upper limit, f1 is the sixth lower limit, and f2 is the sixth upper limit.

[0096] Optionally, the target particle size distribution of the target mix proportion satisfies a preset particle size distribution constraint range, the target cement fineness of the target mix proportion satisfies a preset cement fineness constraint range, and the target cement strength of the target mix proportion satisfies a preset cement strength constraint range, including:

[0097] The target particle size distribution is greater than or equal to the seventh lower limit and less than or equal to the seventh upper limit;

[0098] The target cement fineness is greater than or equal to the eighth lower limit and less than or equal to the eighth upper limit;

[0099] The target cement strength is greater than or equal to the ninth lower limit and less than or equal to the ninth upper limit;

[0100] The target particle size distribution is greater than or equal to a first preset threshold, the target cement fineness is less than or equal to a second preset threshold, the target cement strength is greater than or equal to a third preset threshold, the first preset threshold is greater than the third preset threshold, and the third preset threshold is greater than the second preset threshold.

[0101] As shown in the table below:

[0102]

[0103]

[0104] Optionally, the output variables must satisfy the following constraints:

[0105] u1≤Y1=f(X1,X2,X3,X4,X5,X6)≤u2(particle size distribution constraint);

[0106] v1≤Y2=g(X1,X2,X3,X4,X5,X6)≤v2(cement fineness constraint);

[0107] w1≤Y3=h(X1,X2,X3,X4,X5,X6)≤w2(three-day strength constraint);

[0108] Where u1 is the seventh lower limit, u2 is the seventh upper limit, v1 is the eighth lower limit, v2 is the eighth upper limit, w1 is the ninth lower limit, w2 is the ninth upper limit, Y1 is the target particle size distribution, Y2 is the target cement fineness, and Y3 is the target cement strength.

[0109] Those skilled in the art will understand that model input variables, also known as operational variables of the production process, are the actual proportions of each raw material defined based on actual functions. These input variables include indicators such as cement particle size distribution, cement water requirement, cement fineness, cement rapid strength, clinker cost, fly ash price, limestone price, mineral powder price, electricity consumption per ton of cement, cement operating hours, and air classifier speed. After confirming the input and output model variables of the functional batching, several sets of relevant historical process data are collected. Then, the system autonomously recommends algorithms such as multiple regression and neural networks from the algorithm package (the algorithm package consists of multiple business processing algorithm classes, including modeling data filtering algorithm classes, modeling data standardization processing algorithm classes, basic statistical algorithm classes, variable correlation analysis algorithm classes, matrix calculation algorithm classes, multiple linear regression algorithm classes, real-time optimization control classes, and model adaptive adjustment classes) to fit the functional equation between the model input and output variables.

[0110] Optionally, the first preset threshold can be 75%, that is, the target particle size distribution is greater than or equal to 75%; the second preset threshold can be 6%, that is, the target cement fineness is less than or equal to 6%; and the third preset threshold can be 26%, that is, the target cement strength is greater than or equal to 26. The first preset threshold is greater than the third preset threshold, and the third preset threshold is greater than the second preset threshold.

[0111] Optionally, as a second optional embodiment of the present invention, the maximum sum of the proportions of all component cement ingredients is taken as the preset proportion target. In this case, obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target includes:

[0112] Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the maximum sum of the proportions of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined.

[0113] The cement ingredients include at least one of limestone, coal gangue, fly ash, and slag.

[0114] The sum of the target proportions of each component of the cement mix is ​​a preset constant.

[0115] Optionally, as a variation of this invention, the comprehensive optimization model for batching, after being abstracted by the above mathematical formulas, is transformed into an optimization problem in the field of operations research. Under the premise of satisfying all constraint inequalities, a set of optimal solutions is searched so that the objective function T can reach its minimum value. However, in actual production, because the price of clinker is significantly higher than that of other raw materials, while the prices of other mixed materials are similar, the price factor can be ignored. Moreover, the proportion of gypsum is generally constant. Therefore, when the value of X1+X2+X3+X4 is larger, since X1+X2+X3+X4+X5+X6=1, the value of X5+X6 is smaller. The smaller the value of X5+X6, the lower the cost. The above cement batching optimization model can be simplified to solving for the maximum value of the total amount of the four auxiliary materials.

[0116] It is worth noting that the constraints of the target optimization system for low-cost cement batching based on concrete function are the control objectives and adjustment ranges of each control variable that need to be met during the cement grinding production process. For example, the cement particle size distribution must be controlled within the range of [u1, u2], specifically defining the content of 32μm particle size distribution in the ground cement; the cement fineness must be controlled within the range of [v1, 1v2], specifically defining the 45μm sieve residue in the ground cement; and the three-day strength of the cement must be controlled within the range of [w1, w2], specifically defining the three-day strength of the ground cement. Therefore, the multi-objective optimization model for the cement process can be described as follows:

[0117] Optimization goal:

[0118] MaxT = X1 + X2 + X3 + X4;

[0119] Constraints:

[0120] X1+X2+X3+X4+X5+X6=1;

[0121] a1≤X1≤a2 (Limestone proportioning process constraint);

[0122] b1≤X2≤b2 (coal gangue proportioning process constraint);

[0123] c1≤X3≤c2 (Fly ash proportioning process constraint);

[0124] d1≤X4≤d2 (slag proportioning process constraint);

[0125] e1≤X5≤e2 (clinker proportioning process constraint);

[0126] f1≤X6≤f2 (gypsum mixing process constraints);

[0127] u1≤Y1=f(X1,X2,X3,X4,X5,X6)≤u2(particle size distribution constraint);

[0128] v1≤Y2=g(X1,X2,X3,X4,X5,X6)≤v2(cement fineness constraint);

[0129] w1≤Y3=h(X1,X2,X3,X4,X5,X6)≤w2(three-day strength constraint);

[0130] Y1≥75%;

[0131] Y2≤6%;

[0132] Y3≥26.

[0133] Where a1 is the first lower limit, a2 is the first upper limit, b1 is the second lower limit, b2 is the second upper limit, c1 is the third lower limit, c2 is the third upper limit, d1 is the fourth lower limit, d2 is the fourth upper limit, e1 is the fifth lower limit, e2 is the fifth upper limit, f1 is the sixth lower limit, f2 is the sixth upper limit, u1 is the seventh lower limit, u2 is the seventh upper limit, v1 is the eighth lower limit, v2 is the eighth upper limit, w1 is the ninth lower limit, w2 is the ninth upper limit, Y1 is the target particle size distribution, Y2 is the target cement fineness, and Y3 is the target cement strength. Thus, the optimization problem of cement batching ratio is finally transformed into a problem of solving: under the premise of satisfying all constraints, solve for X1, X2, X3, X4, X5, X6 so that the sum of X1, X2, X3, X4 is maximized.

[0134] Those skilled in the art will understand that once the objective function and constraints of the optimization model are determined, the above-mentioned batching optimization model can be transformed into a multivariate linear (nonlinear) optimization problem in the field of operations research. Based on the Matlab MCR real-time computing library and the C# optimization class library algorithm tools, the optimal solution of the above problem can be solved by suitable tools such as the conjugate gradient method or Newton's method.

[0135] In addition, this invention can also combine genetic algorithms as the solution method for the model to solve the effective proportions of clinker, gypsum, and admixtures; by establishing a set of material balance equations and a batching calculation model, using linear algebra and matrix principles, and developing calculation software using a programming language, it can realize the calculation of batching for multiple groups; taking the proportion of admixtures as input and cement fineness, specific surface area, and CaO as output, a cement batching adjustment model is established using a neural network; an objective function is established to minimize the difference between actual strength and target strength, and the tabu search algorithm of LINGO optimization software is used to solve it to obtain the proportion adjustment value; a two-level intelligent optimization system is used to transform the batching model into a multi-objective model. A 0-1 combinatorial optimization method was used to solve the cement batching problem using an improved genetic algorithm. Based on the characteristics of online neutron analyzer detection, an optimization model was established with minimum cost as the objective function and the content of each cement component as a constraint. The SQP algorithm was used to solve the cement formula. A multi-objective optimization model for batching was established with minimum power consumption and maximum production capacity as objective functions. The NSGA-II algorithm was used to solve the model, and the algorithm and optimization model were verified. A prediction model for element content was established using support vector machines. A multi-objective optimization model for the cement batching system was established with minimum prediction error and minimum cost as objective functions, and a multi-objective particle swarm optimization algorithm was selected to solve it. These methods provide multifaceted support to production enterprises in solving the effective proportion of cement batching, realizing multi-component batching recommendations, improving the practicality of the scheme, seeking optimal formula solutions, adaptive adjustment, improving product qualification rate, and dividing operating conditions.

[0136] Due to the high energy consumption and wear of complex cement grinding systems, the level of automation control adopted in this invention has been gradually upgraded, directly improving the quality and output of cement products as well as system energy consumption. It integrates the characteristics of the system itself, such as large time delay, multiple constraints, multiple variables, and strong coupling between variables. Based on the continuous maturation of prediction, optimization, and control methods such as system control, energy consumption control, and product index recommendation, the goal of achieving system stability, product compliance, and energy consumption reduction is achieved.

[0137] To address the impact of cement hydration and particle size distribution on the workability, mechanical properties, and durability of cement and concrete, and to avoid resource and energy waste caused by using large-particle clinker as aggregate, from a process perspective, it is recommended to adopt high-efficiency multi-separation classifiers and separate grinding processes. This ensures reduced water demand, continuity of cement particle size distribution, and improved cement particle sphericity. Furthermore, based on Fuller curve analysis and the optimal particle size distribution requirements of cement products, the workability of concrete should be matched. The content of particles smaller than 32μm in the cement leaving the mill should be controlled to be ≥75%. From a holistic supply chain perspective, intelligent optimization and control of key indicators of cement particle size distribution at the mill should be implemented to match the functional properties of concrete. In particular, cement enterprises, under the constraints of strengthening process energy consumption control, ensuring appropriate quality, and meeting the basic performance requirements of concrete for cement particle size distribution, should systematically optimize and comprehensively utilize the best cement batching scheme to reduce operating costs and contribute to environmental protection and low-carbon development.

[0138] In this invention, optional constraints are employed, including those related to limestone proportioning, coal gangue proportioning, fly ash proportioning, slag proportioning, clinker proportioning, gypsum proportioning, particle size distribution, cement fineness, and three-day strength. In other embodiments, the constraints can be flexibly combined and customized according to customer needs, actual production, or the remaining quantities of raw materials in the raw material reserves. The advantages are highlighted in the following four aspects: integration of incoming material quality status, cement grinding process monitoring, and output product indicators across the entire cement grinding system; functional expansion, focusing on the function of concrete in matching cement, achieving service-oriented extended functions; real-time cost reduction recommendations: binding real-time on-site data for data-driven optimization of the entire system's cost indicators; and a comparison of cement formula optimization results, which can reduce the overall cost by more than 3% year-on-year and the system's carbon emissions by more than 6% year-on-year.

[0139] This invention provides an optimization scheme for low-cost cement batching for concrete applications. It focuses on the synergistic function of cement in concrete projects, using constraints such as suitable cement particle size distribution, lowest overall cement cost, and minimum cement quality compliance with standards. Leveraging the data fusion capabilities of an industrial big data platform, enterprises build a basic data system. Relying on platform data center technology, artificial intelligence and machine learning algorithms, and adaptive intelligent control technology, it precisely achieves platform tool support, parameter optimization and recommendation, and adaptive control. Business modeling and model training are performed for factors such as incoming material price, lag time, grinding system, product standards, and concrete functional adaptability. The system then provides online real-time optimization and recommendation of the best cement batching scheme, coordinating with cement grinding system model prediction, rolling optimization, and feedback correction closed-loop control to facilitate lean, digital, and service-oriented intelligent management and control of cement grinding production.

[0140] The cement cost determination method, apparatus, electronic device, and medium provided by this invention first use each proportion constraint range of each component cement batch as a constraint condition, and a preset proportion target as an optimization target to obtain the target proportion of each component cement batch. The obtained target proportion also needs to satisfy: the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range. By using the appropriate cement particle size distribution, the lowest comprehensive cement cost, and the lowest cement quality to meet the standard requirements as constraints, the optimal cement grinding batching scheme is recommended to reduce cement cost while ensuring compliance with the constraints.

[0141] Figure 2 This is a second schematic flowchart of the cement cost determination method provided by the present invention. After obtaining the target proportions of each component cement ingredient, it further includes:

[0142] Input the target proportions of each cement component into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model;

[0143] Input the target proportions of each cement component into the cement fineness model, and obtain the target cement fineness output by the cement fineness model;

[0144] Input the target proportions of each cement component into the cement strength model, and obtain the target cement strength output by the cement strength model.

[0145] The particle size distribution model was determined based on the sample proportions of each cement component and the linear fitting of the sample particle size distribution.

[0146] The cement fineness model was determined based on the sample proportions of each component cement ingredient and the linear fitting of the sample cement fineness.

[0147] The cement strength model was determined based on the sample proportions of each component cement mix and the linear fitting of the sample cement strength.

[0148] In step 201, the target proportions of each component cement ingredient are input into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model. The particle size distribution model is determined by linear fitting of the sample proportions of each component cement ingredient and the sample particle size distribution. This invention uses the proportions of different component cement ingredients and the historical particle size distribution under the proportion conditions of each component cement ingredient in historical production data as input for linear fitting, and then determines a particle size distribution model with the proportions of different component cement ingredients as independent variables and particle size distribution as dependent variable, so that the target proportions of each component cement ingredient are input into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model.

[0149] In step 202, the target proportions of each component cement ingredient are input into the cement fineness model, and the target cement fineness output by the cement fineness model is obtained. The cement fineness model is determined by linear fitting of the sample proportions of each component cement ingredient and the sample cement fineness. This invention uses the proportions of different component cement ingredients and the historical cement fineness under the condition of proportion of each component cement ingredient as input for linear fitting, and then determines the cement fineness model with the proportions of different component cement ingredients as independent variables and cement fineness as dependent variable, so that the target proportions of each component cement ingredient are input into the cement fineness model and the target cement fineness output by the cement fineness model is obtained.

[0150] In step 203, the target proportions of each component cement ingredient are input into the cement strength model to obtain the target cement strength output by the cement strength model. The cement strength model is determined by linear fitting of the sample proportions of each component cement ingredient and the sample cement strength. This invention uses the proportions of different components cement ingredients and the historical cement strength under the condition of each component cement ingredient proportion in historical production data as input for linear fitting, and then determines the cement strength model with the proportions of different components cement ingredients as independent variables and cement strength as dependent variable, so that the target proportions of each component cement ingredient are input into the cement strength model to obtain the target cement strength output by the cement strength model.

[0151] After the above-mentioned model of this invention is successfully created, it is required to quickly perform regression deviation analysis on the control models of each output control variable. Once the regression analysis deviations of all output variable control models meet the control deviation requirements of the optimization system, the established optimized control model is allowed to be saved to the database in the background of the optimized control system. After the multiple linear regression models of the process input and output variables are determined, model evaluation and judgment are required to determine whether the regressed model can be used as a real-time optimized control model. The reliability of the model is mainly determined by the residual analysis of the regression model, the R² exponent of the model regression, and the magnitude of the regression control threshold. The smaller the residual of the regression model, the smaller the regression deviation; conversely, the larger the residual, the greater the regression deviation. The closer the R² exponent of the regression model is to 1, the better the model's fit; conversely, the closer the R² exponent is to 0, the worse the model's fit.

[0152] In another alternative embodiment, in addition to using linear regression to determine particle size distribution, cement strength, and cement fineness, these can also be obtained by fitting historical production data with multiple regression, neural networks, or random forests.

[0153] Figure 3This is a schematic diagram of the process for determining cement cost provided by the present invention. The step of determining cement cost based on the target proportions of all cement components and the unit price of each cement component includes:

[0154] The target cost of each cement component is determined based on the target proportion of each component and the unit price of each component.

[0155] The cement cost is determined by the sum of the target costs of all cement components.

[0156] In step 1021, the target cost of each cement component is determined by multiplying the target proportion of each cement component with the unit price of each cement component.

[0157] In step 1022, the target costs of all component cement ingredients are added together, and the cement cost is determined based on the sum of the target costs of all component cement ingredients.

[0158] Figure 4 This is the third flowchart of the cement cost determination method provided by the present invention. After determining the cement cost based on the sum of the target costs of all component cement ingredients, it further includes:

[0159] The total cement time is determined based on the total amount of cement and the cement work hours.

[0160] The electricity cost is determined based on the total cement production time and the electricity consumption of cement.

[0161] The total cost of cement is determined based on the cement cost and the electricity cost.

[0162] In step 301, the total cement quantity is the total amount of cement to be produced in this production, and the cement production time is the cement output per hour. The total cement production time is determined based on the quotient of the total cement quantity and the cement production time.

[0163] In step 302, the cement power consumption is the power cost per hour, which is determined by multiplying the total cement time by the cement power consumption.

[0164] In step 303, the total cement cost is determined based on the sum of the cement cost and the electricity consumption cost.

[0165] Figure 5 This is a schematic diagram of the cement cost determination device provided by the present invention. The present invention provides a cement cost determination device, including an acquisition unit 1: used to acquire the target proportion of each component cement ingredient according to each proportion constraint range of each component cement ingredient and the preset proportion target. The working principle of the acquisition unit 1 can be referred to the aforementioned step 101, and will not be repeated here.

[0166] The cement cost determination device further includes a determination unit 2: used to determine the cement cost based on the target proportion of all component cement ingredients and the unit price of each component cement ingredient when the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range. The working principle of the determination unit 2 can be referred to the aforementioned step 102, and will not be repeated here.

[0167] This invention can construct a cement cost determination software platform based on the acquisition unit 1 and the determination unit 2, and construct a batching optimization system software platform based on low-cost concrete functional cement. It integrates the core functions of real-time data acquisition at the factory and workshop levels, data preprocessing, correlation analysis, dimensionality reduction analysis, cluster analysis, pattern recognition, causal analysis, data fusion, abnormal state prediction, security logic, and real-time predictive control and real-time optimization control of the production process into an industrial optimization control batching optimization system.

[0168] Accordingly, the batching optimization system also includes a data preprocessing module, which is used to optimize the time alignment, filtering and abnormal sampling point processing of the sample data for the control model modeling. This includes data preparation such as the time period when the clinker quality lags behind the clinker quality at the mill, the time period from the mixed material detection point to the mill entry point, key process variables in the production process, and the alignment rules for defining the cement mill exit detection time.

[0169] It also includes an import module, which is used to confirm the data source category of the data preprocessing page so that disk file import and database query import are possible. In disk file import, the module supports importing disk files in CSV format. In database query import, it queries data that meets the conditions from the data table (fusion data matrix) of the optimization control system's backend database model to build the optimization control model.

[0170] Optionally, the preprocessing methods for modeling sample data mainly include filtering of modeling sample data and processing of outlier sample values. The main data filtering methods include: amplitude limiting filtering, median filtering, arithmetic mean filtering, recursive mean filtering, median mean filtering, first-order lag filtering, and weighted recursive mean filtering.

[0171] This invention also includes an optimization control module, which performs variable correlation analysis to explore the correlation and importance among control variables in the production process. Based on the correlation analysis results, production experience, and mechanistic models, the module determines the input and output variables of the final optimization control model. Variable correlation analysis requires configuring a data standardization method for the model data. The main purpose of data standardization is to eliminate the influence of different dimensions of the modeling sample variables. The batching optimization system provides two commonly used data standardization methods: maximum-minimum standardization and normal distribution standardization. The modeling sample data correlation analysis page provides a data type selection interface, allowing users to choose between using raw sample data or filtered model data for variable correlation analysis. After the modeling sample data is standardized, the system automatically displays the standardized model data matrix, which can then be used to perform variable correlation analysis.

[0172] More specifically, the information that needs to be configured in the optimization control model of the ingredient optimization system includes: the type of modeling sample data, the training algorithm of the input and output variable control model, etc. Optionally, the original sample data or the filtered model data can be selected to create the control function equation between the input and output variables according to the requirements. The optimization model of the ingredient optimization system supports the input and output variable optimization control model, and the creation methods include, but are not limited to, multiple linear regression, neural network, and random forest methods.

[0173] This invention, after successfully creating an optimized control model, uses this model to perform real-time optimization control of the raw material formulation scheme that minimizes the overall product cost. First, it queries the database to retrieve the required optimized control model, then imports it. After configuring the parameters for real-time optimization control, it can then perform real-time optimization control of the raw material formulation scheme for the current production process. The real-time optimized control model query and import page allows users to search for qualified optimized control models by their start and end dates of creation, or quickly find qualified models using a fuzzy search method.

[0174] After successfully querying the optimized control model, users can click the checkboxes in front of each model to view its detailed information, including the regression model information for the input and output variables, details of the objective function, constraints on the input variables, and constraints on the output variables. Once the queried optimized control model is confirmed to be suitable for the current production conditions, users can click the "Import Optimized Model" button to load the current optimized control model into the optimized control system. After the system successfully loads the optimized control model selected by the real-time optimized control module, it will automatically display the detailed information of the currently used optimized control model on the real-time optimized control page.

[0175] After configuring the control mode for real-time optimization control, the user can activate the real-time optimization control service according to the instructions. Once the real-time optimization control service is fully activated, the system can automatically perform residual analysis and safety assessment on the real-time optimization control strategy of the current raw material formula, as well as the real-time predicted values ​​of particle size distribution, product fineness, and cement strength. Then, it can send these values ​​to the upstream process's OPC Server via the OPC communication protocol to assist the upstream process's APC pre-control system in real-time optimization control. The system can also send the real-time quality measurement values ​​of the current production process to the downstream process's client software via the communication protocol to assist the downstream process's APC pre-control system in real-time control of key indicators such as particle size distribution, mill fineness, and three-day strength of the mill cement.

[0176] After the optimized control model is loaded, the real-time optimization control function module needs to configure the control model for real-time process optimization control. Currently, the optimization control system provides two control modes: time-triggered control mode and timed control mode.

[0177] Event-triggered mode: In event-triggered mode, the current working condition is automatically judged by real-time monitoring of several key DCS status indicator variables during the production process, thereby realizing automatic optimization control. It is necessary to define and configure DCS event-triggered status variables in advance.

[0178] The timed control mode achieves real-time optimization control by configuring a real-time control cycle. The default control cycle for timed control mode is determined, specifying how often the optimization control system performs real-time optimization control calculations. In practical applications, users can modify the timed control cycle at any time based on actual business needs. Simply modify the control cycle for the timed control mode on the real-time optimization control page, and after restarting the optimization control service according to the newly set timed control cycle, it will perform real-time optimization control of the current production conditions' intensity and cost based on the user's newly set timed control cycle.

[0179] The cement cost determination method, apparatus, electronic device, and medium provided by this invention first use each proportion constraint range of each component cement batch as a constraint condition, and a preset proportion target as an optimization target to obtain the target proportion of each component cement batch. The obtained target proportion also needs to satisfy: the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range. By using the appropriate cement particle size distribution, the lowest comprehensive cement cost, and the lowest cement quality to meet the standard requirements as constraints, the optimal cement grinding batching scheme is recommended to reduce cement cost while ensuring compliance with the constraints.

[0180] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. For example... Figure 6 As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a cement cost determination method. The method includes: obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and a preset proportion target; and determining the cement cost based on the target proportion of all component cement ingredients and the unit price of each component cement ingredient, provided that the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range.

[0181] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0182] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a cement cost determination method provided by the above methods. The method includes: obtaining the target proportion of each component cement ingredient according to each proportion constraint range of each component cement ingredient and a preset proportion target; and determining the cement cost according to the target proportion of all component cement ingredients and the unit price of each component cement ingredient, provided that the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range.

[0183] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements a cement cost determination method provided by the above methods. The method includes: obtaining a target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and a preset proportion target; and determining the cement cost based on the target proportion of all component cement ingredients and the unit price of each component cement ingredient, provided that the target particle size distribution of the target proportion satisfies the preset particle size distribution constraint range, the target cement fineness of the target proportion satisfies the preset cement fineness constraint range, and the target cement strength of the target proportion satisfies the preset cement strength constraint range.

[0184] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0185] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining cement costs, characterized in that, include: Based on the proportion constraint range of each component cement ingredient and the preset proportion target, obtain the target proportion of each component cement ingredient; If the target particle size distribution of the target mix meets the preset particle size distribution constraint range, the target cement fineness of the target mix meets the preset cement fineness constraint range, and the target cement strength of the target mix meets the preset cement strength constraint range, the cement cost is determined based on the target mix proportions of all component cement ingredients and the unit price of each component cement ingredient. The step of obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target includes: Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the lowest proportion cost of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined. After obtaining the target proportions of each component of the cement mix, the following steps are also included: Input the target proportions of each cement component into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model; Input the target proportions of each cement component into the cement fineness model, and obtain the target cement fineness output by the cement fineness model; Input the target proportions of each cement component into the cement strength model, and obtain the target cement strength output by the cement strength model. The particle size distribution model was determined based on the sample proportions of each cement component and the linear fitting of the sample particle size distribution. The cement fineness model was determined based on the sample proportions of each component cement ingredient and the linear fitting of the sample cement fineness. The cement strength model was determined based on the sample proportions of each component cement mix and the linear fitting of the sample cement strength.

2. The method for determining cement cost according to claim 1, characterized in that, The proportioning cost of all cement components is determined based on the sum of the costs of each individual cement component; the cost of each individual cement component is determined based on its proportion and unit price; each cement component includes at least one of limestone, coal gangue, fly ash, slag, clinker, and gypsum; the sum of the target proportions of all cement components is a preset constant; each proportion constraint interval of each cement component includes: The proportion of limestone is greater than or equal to the first lower limit and less than or equal to the first upper limit; The proportion of coal gangue is greater than or equal to the second lower limit and less than or equal to the second upper limit; The proportion of fly ash is greater than or equal to the third lower limit and less than or equal to the third upper limit; The proportion of slag is greater than or equal to the fourth lower limit and less than or equal to the fourth upper limit; The proportion of clinker is greater than or equal to the fifth lower limit and less than or equal to the fifth upper limit; The proportion of gypsum is greater than or equal to the sixth lower limit and less than or equal to the sixth upper limit.

3. The method for determining cement cost according to claim 1, characterized in that, The step of obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target includes: Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the maximum sum of the proportions of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined. The cement ingredients include at least one of limestone, coal gangue, fly ash, and slag. The sum of the target proportions of each component of the cement mix is ​​a preset constant.

4. The method for determining cement cost according to any one of claims 1-3, characterized in that, The target particle size distribution of the target mix proportion meets a preset particle size distribution constraint range, the target cement fineness of the target mix proportion meets a preset cement fineness constraint range, and the target cement strength of the target mix proportion meets a preset cement strength constraint range, including: The target particle size distribution is greater than or equal to the seventh lower limit and less than or equal to the seventh upper limit; The target cement fineness is greater than or equal to the eighth lower limit and less than or equal to the eighth upper limit; The target cement strength is greater than or equal to the ninth lower limit and less than or equal to the ninth upper limit; The target particle size distribution is greater than or equal to a first preset threshold, the target cement fineness is less than or equal to a second preset threshold, the target cement strength is greater than or equal to a third preset threshold, the first preset threshold is greater than the third preset threshold, and the third preset threshold is greater than the second preset threshold.

5. The method for determining cement cost according to claim 1, characterized in that, The process of determining cement cost based on the target proportions of all cement components and the unit price of each cement component includes: The target cost of each cement component is determined based on the target proportion of each component and the unit price of each component. The cement cost is determined by the sum of the target costs of all cement components.

6. The method for determining cement cost according to claim 5, characterized in that, After determining the cement cost based on the sum of the target costs of all component cement ingredients, the following is also included: The total cement time is determined based on the total amount of cement and the cement work hours. The electricity cost is determined based on the total cement production time and the electricity consumption of cement. The total cost of cement is determined based on the cement cost and the electricity cost.

7. A cement cost determination device, characterized in that, include: Acquisition Unit: Used to acquire the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target; Determining unit: used to determine cement cost based on the target proportions of all cement ingredients and the unit price of each cement ingredient, provided that the target particle size distribution of the target proportion meets the preset particle size distribution constraint range, the target cement fineness of the target proportion meets the preset cement fineness constraint range, and the target cement strength of the target proportion meets the preset cement strength constraint range. The step of obtaining the target proportion of each component cement ingredient based on each proportion constraint range of each component cement ingredient and the preset proportion target includes: Using each proportion constraint range of each component cement ingredient as a constraint condition, and taking the lowest proportion cost of all component cement ingredients as the preset proportion target, the target proportion of each component cement ingredient is determined. After obtaining the target proportions of each component of the cement mix, the following steps are also included: Input the target proportions of each cement component into the particle size distribution model to obtain the target particle size distribution output by the particle size distribution model; Input the target proportions of each cement component into the cement fineness model, and obtain the target cement fineness output by the cement fineness model; Input the target proportions of each cement component into the cement strength model, and obtain the target cement strength output by the cement strength model. The particle size distribution model was determined based on the sample proportions of each cement component and the linear fitting of the sample particle size distribution. The cement fineness model was determined based on the sample proportions of each component cement ingredient and the linear fitting of the sample cement fineness. The cement strength model was determined based on the sample proportions of each component cement mix and the linear fitting of the sample cement strength.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the cement cost determination method as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the cement cost determination method as described in any one of claims 1-6.

Images