Optimization method of concrete water reducing agent formula
Optimizing the concrete water reducer formula through multi-dimensional nonlinear response surface model and adaptive network simulation annealing algorithm, solving the problem of inaccurate formulation optimization and inconsistent environmental regulations in the existing technology, achieving the best balance of concrete performance and flexible production reduces costs.
Patent Information
- Application Number
- CN202410865636.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-06-28
AI Technical Summary
The existing technology cannot effectively understand and predict the impact of the complex factors (component interactions and environmental factors) on concrete performance, resulting in insufficient precision in formula optimization and inability to meet environmental regulations and market changes, limiting production flexibility and possibly increasing costs.
The multi-dimensional nonlinear response surface model and adaptive network simulation annealing algorithm are used, combined with environmental sensors and material analysis equipment, and the concrete water reducing agent formula parameters are optimized, and the production process is adjusted through experimental verification to achieve accurate and dynamic adjustment of the formula.
The optimal balance of concrete performance is achieved, the cost efficiency and environmental protection of the formula is improved, the optimal performance under different application conditions is ensured, the flexibility and prediction capabilities of formula design are enhanced, and the production costs are reduced.
Smart Images

Figure CN118673563B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of computer-aided engineering, and in particular to a method for optimizing a concrete water reducing agent formula. Background Art
[0002] As a widely used building material, the performance of concrete is significantly affected by the proportion of its components. In the construction industry, researchers and engineers continue to explore the optimal formula of various additives to improve the performance of concrete, extend its service life, and reduce manufacturing costs. Concrete water reducer is one of the important additives that can significantly improve the working performance and mechanical strength of concrete while reducing the amount of cement, thereby achieving both economic and environmental benefits.
[0003] With the increasingly stringent environmental regulations and the rapid development of building materials technology, the requirements for concrete water reducer formulations are also increasing. This requires concrete water reducers to not only meet performance standards, but also consider cost efficiency and environmental protection during the production process. Therefore, it is particularly important to develop an efficient formulation optimization method that can comprehensively consider these factors. In addition, the performance of concrete is greatly affected by the construction environment, such as temperature, humidity and other on-site conditions, which need to be fully considered in the formulation design of water reducers.
[0004] The existing technology has at least the following technical problems: the existing technology limits the understanding and prediction of complex factors affecting concrete performance (such as interactions between components and the influence of environmental factors), resulting in imprecise formula optimization and failure to guarantee optimal performance under all practical application conditions. The water-reducing agent ingredients used may burden the environment and fail to comply with increasingly stringent environmental regulations. The formula cannot be dynamically adjusted to adapt to changes in the market and raw material prices, which limits production flexibility and may increase costs. Summary of the invention
[0005] The present invention provides a method for optimizing a concrete water reducing agent formula to solve the technical problems that the prior art limits the understanding and prediction of complex factors affecting concrete performance (such as interactions between components and the influence of environmental factors), resulting in insufficient precision in formula optimization, inability to guarantee optimal performance under all practical application conditions, the water reducing agent ingredients used may burden the environment, fail to comply with increasingly stringent environmental regulations, and cannot dynamically adjust the formula to adapt to changes in the market and raw material prices, which limits production flexibility and may increase costs.
[0006] The concrete water reducing agent formula optimization method of the present invention specifically includes the following technical solutions:
[0007] The method for optimizing the formula of concrete water reducing agent comprises the following steps:
[0008] S1. Deploy environmental sensors, material analysis equipment and engineering data input interfaces to collect data and form data vectors; construct a multi-dimensional nonlinear response curve model and describe the relationship between formulation parameters and concrete performance; optimize formulation parameters through adaptive network simulated annealing algorithm to obtain the optimal formulation parameters;
[0009] S2. Convert the optimal formula parameters into the actual addition amount of each formula component, verify through experiments, evaluate the comprehensive performance of the formula, and adjust the production process according to the experimental results.
[0010] Preferably, the S1 specifically includes:
[0011] In the multidimensional nonlinear response surface model, the collected data is converted into a form suitable for the multidimensional nonlinear response surface model; and a nonlinear transformation function is applied to each data in the data vector for data conversion.
[0012] Preferably, the S1 specifically includes:
[0013] After data transformation, a response surface is constructed to describe the relationship between recipe parameters and data vectors, and the expected performance corresponding to the current recipe is calculated.
[0014] Preferably, the S1 specifically includes:
[0015] The adaptive network simulated annealing algorithm is used to optimize the recipe parameters. During the optimization process, the recipe parameters are continuously adjusted according to the current state of the multidimensional nonlinear response surface model and the preset goals to obtain the optimal recipe parameters.
[0016] Preferably, the S2 specifically includes:
[0017] The optimal formula parameters are converted into an actual executable concrete water-reducing agent formula, and the formula component ratio represented by the optimal formula parameters is converted into a specific weight or volume ratio.
[0018] Preferably, the S2 specifically includes:
[0019] Based on the optimal formula parameters, nonlinear influencing factors and correction coefficients are introduced to quantify the formula and obtain the actual addition amount of each formula component in the optimal formula parameters.
[0020] Preferably, the S2 specifically includes:
[0021] Based on the actual addition amount of each formula component, experimental verification of the formula is carried out to test whether the performance of the concrete meets expectations.
[0022] Preferably, the S2 specifically includes:
[0023] Use the actual addition amount of each formula component to prepare concrete samples, determine the proportion of each formula component in the concrete samples, and conduct performance tests on each prepared concrete sample; after experimental verification, when there is a deviation between the actual performance and the experimentally predicted performance, the formula needs to be adjusted or re-optimized.
[0024] The beneficial effects of the technical solution of the present invention are:
[0025] 1. The present invention, through the application of a multi-dimensional nonlinear response surface model, can simultaneously consider the cost efficiency, performance optimization and environmental protection goals of the concrete water-reducing agent formula, achieve the best balance between these goals, and accurately adjust the formula to optimize the comprehensive performance of concrete, including its mechanical strength, durability and environmental impact;
[0026] 2. The present invention deploys environmental sensors, material analysis equipment and engineering data input interfaces to collect comprehensive data about the concrete pouring site, such as temperature, humidity, wind speed and the chemical and physical properties of raw materials. Combined with data conversion and enhancement technology, it can more accurately predict the effects of different formulations;
[0027] 3. The response surface model used in the present invention is combined with nonlinear transformation, which can effectively capture the complex relationship between input data and formulation parameters, which not only enhances the prediction ability of the response surface model, but also provides a flexible and powerful tool for the formulation design of concrete water reducing agent;
[0028] 4. The application of the adaptive network simulated annealing algorithm combines the global search capability of simulated annealing with the adaptive learning capability of artificial neural networks, effectively finding the optimal formula between cost, performance and environmental protection. It not only improves the search efficiency, but also ensures that the global optimal solution can be found in the complex formula design space. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 This is a flow chart of the concrete water reducing agent formula optimization method of the present invention; DETAILED DESCRIPTION
[0030] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0031] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0032] The specific scheme of the method for optimizing the concrete water reducing agent formula provided by the present invention is described in detail below with reference to the accompanying drawings.
[0033] Refer to the attached Figure 1 , which shows a flow chart of a method for optimizing a concrete water reducing agent formula provided by an embodiment of the present invention, the method comprising the following steps:
[0034] S 1. Deploy environmental sensors, material analysis equipment and engineering data input interfaces to collect data and form data vectors; construct a multi-dimensional nonlinear response curve model and describe the relationship between formulation parameters and concrete performance; optimize formulation parameters through adaptive network simulated annealing algorithm to obtain the optimal formulation parameters;
[0035] In order to solve the multi-objective optimization problem of cost efficiency, performance optimization and environmental protection goals of concrete water reducing agent formulation, a multidimensional nonlinear response surface model was constructed to describe the complex relationship between formulation parameters and final concrete performance, so as to predict the effects of different formulations.
[0036] Environmental sensors, material analysis equipment and engineering data input interfaces are deployed to collect data. Environmental sensors are responsible for measuring and recording environmental data such as temperature, humidity, wind speed, etc. at the concrete pouring site. The performance of concrete will vary under different environmental conditions. Material analysis equipment analyzes the chemical and physical properties of raw materials such as cement, sand, and stone. The chemical composition and physical properties of raw materials directly affect the quality and hardening performance of concrete. The engineering data input interface allows operators to input parameters such as concrete strength grade and setting time according to specific construction project requirements, which is a factor that must be considered in formula design.
[0037] The collected data forms a comprehensive data vector in is the ambient temperature, H is the ambient humidity, V is the wind speed, C chem It is the chemical composition of raw materials such as cement, sand, and stone. phys is the physical property of the raw material, S level is the strength grade of concrete, T set It is the setting time requirement for concrete.
[0038] In the multidimensional nonlinear response surface model, the collected data is first converted into a form that can be processed by the response surface model, and the data vector is transformed and enhanced. i , nonlinear function transformation is applied to improve the expression ability of response surface model. The transformation function is defined as:
[0039]
[0040] Among them, φ i (X) is the i-th input data X i The nonlinear transformation function applied is used to enhance the expressiveness of the response surface model, α 1i and α 2i It is the square coefficient of the sine transform coefficient and cosine transform coefficient of the i-th input data, which extracts the nonlinear and complex interaction effects of each input data, thereby providing a strong prediction basis for the response surface model.
[0041] After data conversion, a response surface is constructed to describe the relationship between the formulation parameters and the input data, and to calculate the expected performance corresponding to the current formulation, including cost, physical and chemical properties, and environmental impact; the response surface is defined by the formulation parameters of multiple component ratios, which determine the relative proportions of various components in the concrete water reducer. The adjustment of each formulation parameter will affect the final performance of the concrete, including its strength, durability, and environmental indicators; the response surface adopts a polynomial structure, which includes high-order terms and interaction terms of the input data, and the specific expression is:
[0042]
[0043] Where R(X, θ) is the response surface function, which is used to describe the relationship between the input data X and the recipe parameter θ. j represents the proportion of the jth ingredient in the recipe, γ ji is the weight that controls the influence of the i-th input data on the j-th recipe component, p ji is the polynomial order of adjusting the i-th input data in the j-th formulation component, m is the total number of input data, and n is the total number of formulation components. The response surface can capture the complex nonlinear relationship between different formulation components and concrete properties.
[0044] In order to find the optimal formula, the adaptive network simulated annealing algorithm is used to optimize the formula parameters, combining the global search ability of simulated annealing and the adaptive learning ability of artificial neural network to find the optimal formula; during the optimization process, the formula parameters are continuously adjusted according to the current state of the multi-dimensional nonlinear response surface model and the preset goals; in each iteration, the parameter update follows the following rules:
[0045]
[0046] Among them, θ (t+1) represents the value of the recipe parameter at step t+1 in the optimization process, θ (t) represents the value of the recipe parameter at step t in the optimization process, η represents the learning rate, Δθ (t)represents the gradient of the recipe parameter of the current iteration, ξ is the cooling coefficient, which is used to control the annealing rate in the adaptive network simulated annealing algorithm, is the current simulated annealing temperature, Φ is a random variable that conforms to the standard normal distribution to ensure that the adaptive network simulated annealing algorithm can jump out of the local minimum during the search process.
[0047] When the preset maximum number of iterations is reached or the performance improvement is lower than the preset threshold, the iteration is stopped. Thus, a set of potential optimal recipe parameters θ is obtained. * .
[0048] S2. Convert the optimal formula parameters into the actual addition amount of each formula component, verify through experiments, evaluate the comprehensive performance of the formula, and adjust the production process according to the experimental results.
[0049] The obtained optimal formula parameters are converted into a practical and executable concrete water-reducing agent formula, including formula quantification, experimental verification and final production adjustment, and the formula component ratio represented by the optimal formula parameters is converted into a specific weight or volume ratio.
[0050] Set the optimal recipe parameter θ * Each recipe ingredient in The corresponding actual addition amount is M j , introducing nonlinear influencing factors and correction coefficients, taking into account the actual production situation and the variability of raw materials, the formula quantification formula is as follows:
[0051]
[0052] in, is the total volume of a given batch, ρ j is the density of the jth recipe ingredient, κ is the correction factor, σ j is the supply volatility of the jth recipe ingredient. The recipe quantification calculation takes into account the unstable factors in the supply chain, making the theoretical recipe closer to the actual production conditions.
[0053] Quantify the result according to the recipe M j , experimental verification of the formula is carried out in a laboratory environment. By preparing small batches of concrete samples and adding water reducers according to the quantitative formula, the performance of the concrete is tested to see if it meets expectations, including its strength, setting time and environmental protection indicators.
[0054] In the development process of concrete water reducers, quantified ingredient ratios are the basis for preparing experimental samples, which will then be used in experiments to measure their performance indicators (such as strength, environmental performance and cost-effectiveness), which directly affect the calculation of performance scores.
[0055] Use the M obtained from the recipe quantification phasej , that is, the actual amount of each formula component added, to prepare a series of concrete samples, M j It is directly used to determine the proportion of each formula component in the concrete sample. Each prepared sample is tested for performance, including its mechanical strength, environmental impact and production cost. The specific formula is:
[0056]
[0057] in, represents the performance score of the concrete sample obtained in the experiment, is the experimentally determined concrete strength, E exp is the environmental performance score, is the cost score, k1, k2, k3 are weight coefficients. The performance test formula increases the nonlinear characteristics of the calculation by introducing square, logarithm and square root operations, reflecting the comprehensive influence of different factors on concrete performance.
[0058] After experimental verification, if there is a deviation between the actual performance and the experimental predicted performance, the formula needs to be adjusted or re-optimized; adjust the formula parameters in production to optimize the large-scale production effect. Once the adjustment reaches a satisfactory accuracy, the new formula can be applied in a large-scale production environment. The dynamic adjustment formula is:
[0059]
[0060] Among them, Δθ (t+1) represents the gradient of the recipe parameter at step t+1, λ is the adjustment rate, θ (t) -θ * The term is the difference between the current recipe parameters and the optimal recipe parameters, θ (t) represents the value of the recipe parameter at step t in the optimization process, δ and is the amplitude and phase of the adjustment parameter, which is used to introduce periodic adjustment to adapt to possible periodic changes in the production process. T is the total duration of the adjustment cycle. ∈ is the performance feedback adjustment coefficient. is the target performance score, representing the ideal product performance, It is a performance feedback item, which is adjusted according to the difference between the predicted performance in the experiment and the target performance. If the actual performance does not meet expectations, the performance feedback item will positively adjust the recipe parameters; if it exceeds expectations, the opposite adjustment will be made.
[0061] The optimal formula parameters of concrete water reducer were determined by utilizing a multidimensional nonlinear response surface model and an adaptive network simulated annealing algorithm. The formula parameters were converted into specific addition amounts through an enhanced formula quantification formula, taking into account actual changes in raw material supply. The comprehensive performance of the formula was evaluated through experimental verification, and the production process was adjusted based on the experimental results to ensure that the performance, cost and environmental standards of the final product met the expected results.
[0062] In summary, the concrete water reducing agent formula optimization method is completed.
[0063] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0064] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0065] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. Concrete water reducing agent formula optimization method, It is characterized in that The following steps are involved: S1. Deploy environmental sensors, material analysis equipment, and engineering data input interfaces to collect data and form data vectors in is the ambient temperature; H is the ambient humidity; V is the wind speed; C chem It is the chemical composition of cement, sand and stone raw materials; phys is the physical property of the raw material; S level is the strength grade of concrete; T set It is the setting time requirement of concrete; A multidimensional nonlinear response curve model is constructed. In the multidimensional nonlinear response surface model, the collected data is converted into a form suitable for the multidimensional nonlinear response surface model; for each data in the data vector, a nonlinear transformation function is applied to perform data transformation, and the transformation function is defined as: Among them, φ i (X) is the i-th input data X i The nonlinear transformation function applied; α 1i and α 2i It is the square coefficient of the sine transform coefficient and cosine transform coefficient of the i-th input data; After data conversion, a response surface is constructed to describe the relationship between recipe parameters and data vectors, and the expected performance corresponding to the current recipe is calculated. The response curve adopts a polynomial structure, which includes high-order terms and interaction terms of the input data. The specific expression is: Where R(X,θ) is the response surface function; θ j Represents the proportion of the jth ingredient in the recipe; γ ji is the weight of controlling the influence of the i-th input data on the j-th recipe component; ji is the polynomial order of adjusting the i-th input data in the j-th recipe component; m is the total number of input data; n is the total number of recipe components; The recipe parameters are optimized by the adaptive network simulated annealing algorithm. During the optimization process, the recipe parameters are continuously adjusted according to the current state of the multi-dimensional nonlinear response surface model and the preset goals. In each iteration, the parameter update follows the following rules: Among them, θ (t+1) represents the value of the recipe parameter at step t+1 in the optimization process; θ (t) represents the value of the recipe parameter at step t in the optimization process; η represents the learning rate; Δθ (t) represents the gradient of the recipe parameter of the current iteration; ξ is the cooling coefficient; is the current simulated annealing temperature; Φ is a random variable; When the preset maximum number of iterations is reached or the performance improvement is lower than the preset threshold, the iteration is stopped to obtain the optimal recipe parameters; S2. Based on the optimal recipe parameters, set the optimal recipe parameters θ * Each recipe ingredient in The corresponding actual addition amount is M j , nonlinear influencing factors and correction coefficients are introduced to quantify the recipe. The recipe quantification formula is as follows: in, is the total volume of a given batch; ρ j is the density of the jth recipe ingredient; κ is the correction factor; σ j is the supply volatility of the jth recipe ingredient; According to the actual addition amount of each formula component, the formula is experimentally verified to test whether the performance of the concrete meets expectations; Use the actual addition amount of each formula component to prepare concrete samples, determine the proportion of each formula component in the concrete sample, and conduct performance tests on each prepared concrete sample. The specific formula is: in, represents the performance score of the concrete sample obtained in the experiment; is the experimentally determined concrete strength; E exp is the environmental performance score; is the cost score; k 1 , k 2 , k 3 is the weight coefficient; After experimental verification, when there is a deviation between the actual performance and the experimental predicted performance, the formula needs to be adjusted or re-optimized. The dynamic adjustment formula is: Among them, Δθ (t+1) represents the gradient of the recipe parameter at step t+1; λ is the adjustment rate; θ (t) -θ * The term is the difference between the current recipe parameters and the optimal recipe parameters; θ (t) represents the value of the recipe parameter at step t in the optimization process; δ and is the amplitude and phase of the adjustment parameter; T is the total duration of the adjustment cycle; ∈ is the performance feedback adjustment coefficient; is the target performance score; is the performance feedback item; Through experimental verification, the comprehensive performance of the formula was evaluated, and the production process was adjusted according to the experimental results.
2. The method for optimizing the concrete water reducing agent formula according to claim 1, It is characterized in that The S2 specifically includes: The optimal formula parameters are converted into an actual executable concrete water-reducing agent formula, and the formula component ratio represented by the optimal formula parameters is converted into a specific weight or volume ratio.
Citation Information
Cited By
Concrete preparation formula optimization design method
CN120895131A
