Optimization production method of high-performance waterproof concrete

Abstract

The invention relates to the technical field of high-performance waterproof concrete production, and discloses a high-performance waterproof concrete optimizing production method which comprises the following steps: establishing a digital twinborn model for high-performance waterproof concrete production: collecting parameters in a high-performance waterproof concrete production process in real time; obtaining constraint conditions of the parameters; setting an optimization target for producing the high-performance waterproof concrete, wherein the optimization target comprises impermeability, strength and compactness; executing the optimization target model prediction strategy, and establishing a prediction model of the optimization target; calculating an optimal solution of parameters for the prediction model of the optimization target by adopting an Adam optimization algorithm; obtaining all optimal solutions, executing a nonlinear dynamic steady-state analysis strategy, obtaining a steady-state solution with the highest stability, and recording the steady-state solution as a target solution; a parameter feedback control strategy is executed, parameters in the high-performance waterproof concrete production process are adjusted, and an efficient, stable and sustainable solution is provided for concrete production.

Description

Technical Field

[0001] The invention relates to the technical field of high-performance waterproof concrete production, and in particular to a method for optimizing the production of high-performance waterproof concrete. Background Art

[0002] As an important building material, high-performance waterproof concrete is widely used in underground engineering, water conservancy facilities and high-strength construction. High-performance waterproof concrete is an important technological innovation in the field of modern building materials. Compared with traditional concrete, it has significant advantages in impermeability, strength, durability, etc., and can meet the high-standard requirements of complex projects and harsh environments.

[0003] Traditional concrete production methods mainly rely on empirical formulas and single performance optimization, which has the following problems: (1) There is a lack of comprehensive optimization strategies for impermeability, strength and density, which leads to contradictions between concrete properties; (2) The impact of dynamic conditions such as ambient temperature and humidity on concrete performance is ignored during the production process, making it difficult to ensure stability and consistency under actual construction conditions; (3) There is a lack of intelligent tuning methods, resulting in low optimization efficiency and high manual adjustment costs.

[0004] The present invention proposes a tuning production method for high-performance waterproof concrete, which integrates digital twin modeling, intelligent optimization algorithm and dynamic feedback adjustment technology, providing an efficient, stable and sustainable solution for concrete production. Summary of the invention

[0005] The present invention provides a method for optimizing the production of high-performance waterproof concrete, which helps solve the problems mentioned in the above background technology.

[0006] In the first aspect, the present application provides a method for optimizing the production of high-performance waterproof concrete, which adopts the following technical scheme: A method for optimizing the production of high-performance waterproof concrete, comprising: establishing a digital twin model for the production of high-performance waterproof concrete: Real-time collection of parameters during the production of high-performance waterproof concrete, including water-cement ratio , sand rate , admixture dosage , slump , Ambient temperature and ambient humidity ; By collecting key parameters for the production of high-performance waterproof concrete (such as water-cement ratio, sand ratio, admixture dosage, slump, ambient temperature and humidity) in real time, this method ensures the real-time and comprehensiveness of the data, and provides accurate basic data support for the construction of the digital twin model. The real-time collection process can reflect the dynamic changes of production conditions and avoid the lag problem caused by relying on offline test data in traditional methods. At the same time, the complete parameter collection covers the factors that have a greater impact on concrete performance in the production process, ensuring the accuracy of the prediction model and optimization algorithm. The acquisition of real-time data can also timely discover abnormal situations in production through systematic analysis, providing key feedback information for subsequent optimization processes. Therefore, real-time collection of parameters not only improves the controllability of the production process, but also significantly enhances the adaptability of the production system to changes in the environment and working conditions.

[0007] Obtaining constraints of the parameters; By obtaining the parameter constraints for producing high-performance waterproof concrete, this method can ensure that the optimization process is carried out within a reasonable range, thereby avoiding the occurrence of parameter combinations that do not meet engineering specifications or performance requirements in production. These constraints include the range of values ​​of water-cement ratio, sand ratio, admixture dosage and slump, as well as the influence limits of ambient temperature and humidity on performance. When optimizing the target model, the introduction of constraints makes the calculation results meaningful and can be directly used to guide production. Constraints can also filter out infeasible solutions, reduce the computational complexity of the optimization algorithm, and improve optimization efficiency. More importantly, this process provides quality assurance for production, ensuring that the high-performance waterproof concrete finally produced not only meets the performance requirements, but also meets the actual needs of construction.

[0008] Setting optimization goals for producing high-performance waterproof concrete, the optimization goals including impermeability, strength and density; Execute the prediction strategy of the optimization target model and establish the prediction model of the optimization target; The Adam optimization algorithm is used to calculate the optimal solution of the parameters of the prediction model of the optimization target; Obtain all optimal solutions, execute nonlinear dynamic steady-state analysis strategy, obtain the most stable steady-state solution, and record it as the target solution; Implement parameter feedback control strategy to adjust parameters in the process of producing high-performance waterproof concrete.

[0009] Preferably, the executing the optimization target model prediction strategy and establishing the prediction model of the optimization target includes: Collect historical parameters and apply multivariate regression model to fit the objective functions of impermeability, strength and density; The impermeability objective function is expressed as ; The intensity objective function is expressed as ; The density objective function is expressed as ; Obtaining the standard temperature for producing high-performance waterproof concrete and standard humidity ; Calculate the change results of the impermeability objective function under ambient temperature and ambient humidity ; Calculate the change of intensity objective function under ambient temperature and ambient humidity ; Calculate the change results of the density objective function under ambient temperature and ambient humidity , in, and All are objective function adjustment coefficients; The value range of the control parameter satisfies the parameter constraints.

[0010] By setting impermeability, strength and density as optimization targets, this method comprehensively considers the core performance requirements of high-performance waterproof concrete to ensure the diversity and comprehensiveness of the optimization results. Compared with the traditional single performance optimization method, multi-objective optimization can better meet the comprehensive requirements of complex engineering for material performance. By setting optimization targets, this method quantifies performance indicators into specific mathematical functions, providing a clear direction for subsequent model prediction and parameter optimization. The multidimensionality of the optimization target can also adjust the weight according to specific engineering needs to achieve a flexible balance between performance and economy. Therefore, the setting of optimization targets not only improves the pertinence and reliability of production, but also enhances the applicability and flexibility of the method.

[0011] Preferably, the prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: Calculating the objective function for producing high-performance waterproof concrete ; , in, and They are the weight of impermeability, strength and density respectively; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; Update Adam's momentum , , is the k-th step parameter The first-order momentum value of is the momentum coefficient, which determines the weight of the historical gradient, is the k+1th step parameter The first-order momentum value of Update the RMS term using the exponentially weighted moving average of the squared gradients , in, is the k-th step parameter The second-order momentum value of is the k+1th step parameter The second-order momentum value of is the smoothing coefficient, which controls the weight of the squared gradient history contribution.

[0012] By executing the prediction strategy of the optimized target model, this method constructs a multi-objective prediction model of impermeability, strength and density, which can accurately describe the relationship between production parameters and performance indicators. This process uses historical data and multivariate regression models to establish a high-precision objective function, which significantly improves the accuracy and robustness of the prediction performance. By adding the ambient temperature and humidity adjustment coefficient, the model can dynamically adapt to different working conditions and external environmental conditions, further enhancing the practicality of the model. In addition, this strategy can effectively reduce the dependence on test tuning, reduce test costs and time consumption, and provide a reliable data basis for subsequent parameter optimization. Therefore, the optimization target model prediction strategy has laid a solid foundation for the digitalization and intelligence of high-performance waterproof concrete production.

[0013] Preferably, the prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: Correct the first-order momentum and second-order momentum values: , in, is the corrected first-order momentum estimate, is the bias correction factor for the first-order momentum value correction; , in, is the corrected second-order momentum estimate, is the bias correction factor for the second-order momentum value correction; , in, is the parameter value at the kth step, is the learning rate, which is used to control the step size of each update; Used to dynamically adjust the learning rate, is a smoothing term used to prevent the denominator from being zero; Setting the norm threshold ; Set parameter difference threshold ; and , then stop the iteration and get the optimal solution.

[0014] By adopting the Adam optimization algorithm, this method can quickly and stably calculate the optimal solution of the parameters, avoiding the problems caused by gradient oscillation or local optimality in traditional optimization methods. The Adam algorithm combines the advantages of momentum gradient descent and adaptive learning rate, and can dynamically adjust the update step size according to the historical gradient of each parameter, thereby improving the optimization efficiency and convergence speed. The algorithm has good adaptability to complex objective functions and is particularly suitable for high-dimensional and multi-objective optimization problems. In addition, the adaptive characteristics of the Adam algorithm enable it to operate stably in the face of uneven gradient changes, thereby ensuring the accuracy of the optimization results. Therefore, the introduction of the Adam optimization algorithm provides advanced computing support for the intelligent optimization of high-performance waterproof concrete production.

[0015] Preferably, the step of obtaining all optimal solutions and executing a nonlinear dynamic steady-state analysis strategy to obtain a steady-state solution with the highest stability includes: Get any optimal solution ; Compute the dynamic response of a parameter using nonlinear dynamic equations: , , , Among them, i=1,2,3,4, For parameters The dynamic rate of change, is the parameter value at time t, is the ambient temperature at time t, is the current ambient humidity value; judge of Is it satisfied at any time? ; If satisfied, then is a steady-state solution.

[0016] Preferably, the step of obtaining all optimal solutions and executing a nonlinear dynamic steady-state analysis strategy to obtain a steady-state solution with the highest stability includes: Calculate the Jacobian matrix J; ; in, Representation parameters right Partial derivatives, j=1,2,3,4,i=1,2,3,4,5,6; Find the eigenvalues ​​of the Jacobian matrix J Get the minimum value of the real part of each eigenvalue and record it as the marked value; Get the mark values ​​of all steady-state solutions, and record the steady-state solution corresponding to the minimum mark value as the target solution.

[0017] By executing a nonlinear dynamic steady-state analysis strategy, this method can select the solution with the highest stability from multiple optimal solutions to ensure the robustness and consistency of the production process under dynamic environmental conditions. The dynamic response of the parameters is simulated by nonlinear dynamic equations, and the eigenvalues ​​of the system are calculated by the Jacobian matrix, which can accurately determine the steady-state stability of each solution. The real part of the eigenvalue reflects the speed at which the system recovers after being disturbed. The solution with the most negative eigenvalue is selected to ensure the stability and rapid response capability of the production system under various disturbance conditions. Therefore, the nonlinear dynamic steady-state analysis strategy not only ensures the reliability of production, but also provides a scientific basis for the production of high-performance waterproof concrete in complex engineering environments.

[0018] Preferably, the execution parameter feedback control strategy to adjust the parameters in the process of producing high-performance waterproof concrete includes: Get the target solution ; For any parameter value at the current time t ; Calculate the parameter value at the next moment , in, is the feedback gain, i=1,2,3,4.

[0019] By executing the parameter feedback control strategy, this method can adjust the optimization process according to the parameters collected in real time during the production process, forming a closed-loop adjustment mechanism, which significantly improves the dynamic adaptability of production. The feedback control strategy ensures that the production parameters can be quickly restored to the vicinity of the target solution by calculating the dynamic change rate of each parameter and adjusting the gain. Even when the external environment (such as temperature and humidity) fluctuates, the system can remain stable. Compared with the traditional manual intervention method, the feedback control strategy realizes automated and intelligent adjustment, reducing the errors and costs of manual operation. Therefore, the parameter feedback control strategy effectively enhances the efficiency, stability and reliability of high-performance waterproof concrete production, laying the foundation for the realization of full automation and intelligence of production.

[0020] The present invention has the following beneficial effects: 1. The tuning production method of high-performance waterproof concrete, by establishing a digital twin model of high-performance waterproof concrete, combined with a multivariate regression model and the Adam optimization algorithm, jointly optimizes multiple performance targets such as impermeability, strength and density. By collecting real-time production parameters (such as water-cement ratio, sand ratio, admixture dosage, slump, temperature and humidity) and combining the regression model trained with historical data, the relationship between performance targets and parameters can be accurately predicted. The Adam algorithm is used to iteratively optimize the objective function, and the momentum and RMS terms are updated by calculating the gradient of each parameter to the objective function to accelerate convergence and avoid local optimality. The optimal parameter solution finally obtained not only ensures the performance of concrete, but also solves the performance contradiction problem caused by single performance optimization in traditional methods. As a result, this method significantly improves the impermeability and strength of concrete, while ensuring that the density meets the engineering requirements, providing a scientific and comprehensive concrete performance optimization solution for complex projects.

[0021] 2. The optimization production method of high-performance waterproof concrete significantly improves the stability of the concrete production system through nonlinear dynamic analysis and steady-state solution screening strategy. This method constructs nonlinear dynamic equations to dynamically simulate the changes of production parameters under environmental temperature and humidity disturbances, and uses the Jacobian matrix to calculate the stability index of the system. By solving the eigenvalues ​​corresponding to each optimal solution, the steady-state solution with the smallest eigenvalue real part is screened out to ensure that the system has the strongest stability and recovery ability when external fluctuations occur. Compared with traditional methods, this method can judge the dynamic response behavior of the steady-state solution in real time, and adjust the production parameters in combination with environmental conditions to ensure that the production process is always in a stable state. In addition, this method also uses a dynamic feedback control strategy to correct the production parameters in real time, effectively reducing the impact of external disturbances on concrete performance and ensuring the stability and consistency of production.

[0022] 3. The tuning production method of high-performance waterproof concrete significantly improves the efficiency of concrete production through the introduction of digital twin technology and intelligent optimization algorithm. Unlike the traditional method of relying on test tuning, this method is based on real-time collected production data and combines the multivariate regression model to predict the objective function, which greatly shortens the time for parameter optimization and performance verification. In addition, the Adam optimization algorithm quickly converges to the optimal solution by automatically updating the learning rate and iteration step size, avoiding the lengthy parameter adjustment process. After the optimization is completed, the steady-state solution screening and feedback control mechanism can adjust the production parameters in real time, and closed-loop optimization can be achieved without human intervention, which improves the automation level of the production process. Overall, this method simplifies the concrete production process, reduces the cost of manual testing and rework, and improves the overall production efficiency. It is particularly suitable for large-scale production and complex construction scenarios of high-performance waterproof concrete.

[0023] 4. The tuning production method of high-performance waterproof concrete reduces the excessive use of raw materials while ensuring the performance of concrete by accurately optimizing the water-cement ratio, sand ratio and admixture dosage, thereby reducing material costs. Secondly, the Adam optimization algorithm can converge to the optimal solution within a small number of iterations, reducing the time cost of experiments and debugging. In addition, through steady-state solution screening and feedback control mechanism, the rework rate in the production process has been greatly reduced, significantly reducing potential losses and maintenance costs in the project. More importantly, precise parameter control and efficient performance optimization have improved the service life and durability of concrete, bringing considerable economic returns to construction units in the long run. This method achieves efficient utilization of resources and maximizes economic benefits while meeting the quality requirements of high-performance waterproof concrete.

[0024] 5. The optimized production method of high-performance waterproof concrete effectively reduces carbon dioxide emissions by optimizing the use of raw materials, reducing cement content and energy consumption. In addition, the precise control of production parameters by the digital twin model greatly reduces resource waste and excessive material input, further improving resource utilization. At the same time, nonlinear dynamic analysis ensures the stability of the production system under different environmental conditions, avoiding material waste and performance loss due to external disturbances. While achieving improved production efficiency of high-performance concrete, this method combines environmental protection and economic benefits, providing an innovative technical path for the green development of the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the process of the present invention.

[0026] Figure 2 This is a schematic diagram of the Adam optimization algorithm flow of the present invention.

[0027] Figure 3It is a schematic diagram of the nonlinear dynamic steady-state analysis process of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Embodiment 1, refer to Figure 1 , a method for optimizing the production of high-performance waterproof concrete; Building a digital twin model for high-performance waterproof concrete production: Real-time collection of parameters during the production of high-performance waterproof concrete, including water-cement ratio , sand rate , admixture dosage , slump , Ambient temperature and ambient humidity ; By collecting key parameters (such as water-cement ratio, sand ratio, admixture dosage, slump, ambient temperature and humidity) in the production process of high-performance waterproof concrete in real time, the comprehensiveness and dynamic accuracy of data in the optimization process are ensured. These parameters can reflect real-time changes in the production process and provide basic support for the construction of digital twin models. Compared with the traditional method that relies on offline test data, the real-time collected data can capture the fluctuations of environmental and production conditions in a timely manner, making the prediction and optimization more in line with the actual working conditions. Through complete parameter collection, this method improves the accuracy of model fitting and provides high-quality input data for subsequent optimization algorithms, avoiding performance deviations caused by data errors. Therefore, through real-time parameter collection, this method realizes the precision and dynamic nature of production data, significantly improving the accuracy and reliability of concrete performance optimization.

[0030] Obtaining constraints of the parameters; By setting parameter constraints, this method ensures the rationality of variable values ​​in the optimization process, so that the parameter combination for producing high-performance waterproof concrete meets both engineering specifications and performance requirements. These constraints include the upper and lower limits of core variables such as water-cement ratio, sand ratio, admixture dosage and slump, which ensure the practical operability of the optimization results. In addition, the introduction of constraints reduces the search range of invalid solutions, improves the computational efficiency of the optimization algorithm, and ensures that the final optimized solution meets engineering requirements. For example, under strict requirements on impermeability and strength, a balance between performance and economy can be achieved through reasonable parameter constraints. By setting parameter constraints, this method achieves a smooth transition from the optimization model to actual production, effectively avoiding the performance deviation problem caused by parameter loss of control in the traditional optimization process.

[0031] Setting optimization goals for producing high-performance waterproof concrete, the optimization goals including impermeability, strength and density; Execute the prediction strategy of the optimization target model and establish the prediction model of the optimization target; The Adam optimization algorithm is used to calculate the optimal solution of the parameters of the prediction model of the optimization target; Obtain all optimal solutions, execute nonlinear dynamic steady-state analysis strategy, obtain the most stable steady-state solution, and record it as the target solution; Implement parameter feedback control strategy to adjust parameters in the process of producing high-performance waterproof concrete.

[0032] The execution of the optimization target model prediction strategy and establishment of the prediction model of the optimization target include: Collect historical parameters and apply multivariate regression model to fit the objective functions of impermeability, strength and density; The impermeability objective function is expressed as ; The intensity objective function is expressed as ; The density objective function is expressed as ; Obtaining the standard temperature for producing high-performance waterproof concrete and standard humidity ; Calculate the change results of the impermeability objective function under ambient temperature and ambient humidity ; Calculate the change of intensity objective function under ambient temperature and ambient humidity ; Calculate the change results of the density objective function under ambient temperature and ambient humidity , in, and All are objective function adjustment coefficients; The value range of the control parameter satisfies the parameter constraints.

[0033] By setting impermeability, strength and density as multi-objective optimization targets, this method comprehensively covers the core performance indicators of high-performance waterproof concrete. Compared with traditional single-objective optimization, multi-objective optimization can find the best balance between different performances, thereby meeting the needs of complex projects for diversified material performance. By assigning weights to the optimization targets, this method can flexibly adjust the optimization direction according to the actual requirements of the project, such as prioritizing the optimization of impermeability under certain conditions, while balancing strength and density under other conditions. This flexibility ensures the applicability of the optimization results, and at the same time, the overall performance of the material is further improved through the coordinated optimization of performance. Therefore, through multi-objective optimization, this method achieves comprehensive coverage of performance optimization and provides reliable support for the application of waterproof concrete in complex environments.

[0034] The prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: In this embodiment, refer to Figure 2 ; Calculating the objective function for producing high-performance waterproof concrete ; , in, and They are the weight of impermeability, strength and density respectively; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; Update Adam's momentum , , is the k-th step parameter The first-order momentum value of is the momentum coefficient, which determines the weight of the historical gradient, is the k+1th step parameter The first-order momentum value of Update the RMS term using the exponentially weighted moving average of the squared gradients , in, is the k-th step parameter The second-order momentum value of is the k+1th step parameter The second-order momentum value of is the smoothing coefficient, which controls the weight of the squared gradient history contribution.

[0035] The prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: Correct the first-order momentum and second-order momentum values: , in, is the corrected first-order momentum estimate, is the bias correction factor for the first-order momentum value correction; , in, is the corrected second-order momentum estimate, is the bias correction factor for the second-order momentum value correction; , in, is the parameter value at the kth step, is the learning rate, which is used to control the step size of each update; Used to dynamically adjust the learning rate, is a smoothing term used to prevent the denominator from being zero; Setting the norm threshold ; Set parameter difference threshold ; and , then stop the iteration and get the optimal solution.

[0036] By constructing a multivariate regression prediction model based on historical data, this method significantly improves the prediction accuracy and efficiency of the optimization target. The prediction model integrates the relationship between impermeability, strength and density and production parameters, and can quickly complete the fitting and updating of the objective function in a dynamic environment. Compared with the traditional method that relies on experimental tuning, the prediction model can significantly reduce the number and time of experimental verification, while improving the adaptability to environmental conditions (such as temperature and humidity changes). The temperature and humidity adjustment coefficients introduced in the model ensure accurate prediction under complex external conditions, thereby providing a reliable foundation for the optimization algorithm. Therefore, by optimizing the prediction of the target model, this method not only improves the performance prediction accuracy, but also greatly shortens the tuning process, bringing an efficient and accurate solution to the production of high-performance waterproof concrete.

[0037] By adopting the Adam optimization algorithm, this method achieves efficient and intelligent optimization of concrete production parameters. The Adam algorithm combines the advantages of momentum update and adaptive learning rate adjustment, and can quickly converge to the optimal solution while avoiding performance loss caused by local optimal points. The algorithm is sensitive to gradient changes and can dynamically adjust the learning rate of each parameter, and performs well in high-dimensional parameter space. Compared with the traditional gradient descent method, the Adam algorithm reduces the complexity of manually adjusting the learning rate and accelerates the optimization process. The optimal solution of parameters calculated by the Adam algorithm can meet the multi-objective requirements of impermeability, strength and density, and provide scientific guidance for the production of high-performance waterproof concrete. Therefore, the introduction of the Adam optimization algorithm not only improves the optimization efficiency, but also ensures the accuracy and applicability of the results.

[0038] The method of obtaining all optimal solutions and executing nonlinear dynamic steady-state analysis strategies to obtain the most stable steady-state solutions includes: In this embodiment, refer to Figure 3 ; Get any optimal solution ; Compute the dynamic response of a parameter using nonlinear dynamic equations: , , , Among them, i=1,2,3,4, For parameters The dynamic rate of change, is the parameter value at time t, is the ambient temperature at time t, is the current ambient humidity value; judge of Is it satisfied at any time? ; If satisfied, then is a steady-state solution.

[0039] The method of obtaining all optimal solutions and executing nonlinear dynamic steady-state analysis strategies to obtain the most stable steady-state solutions includes: Calculate the Jacobian matrix J; ; in, Representation parameters right Partial derivatives, j=1,2,3,4,i=1,2,3,4,5,6; Find the eigenvalues ​​of the Jacobian matrix J Get the minimum value of the real part of each eigenvalue and record it as the marked value; Get the mark values ​​of all steady-state solutions, and record the steady-state solution corresponding to the minimum mark value as the target solution.

[0040] By executing a nonlinear dynamic steady-state analysis strategy, this method can screen out the most stable combination of production parameters in a dynamic environment, thereby ensuring the robustness and consistency of the system. Steady-state analysis uses the Jacobian matrix to calculate the eigenvalues ​​of the optimization results, which can accurately determine the dynamic response behavior of the system. The real part of the eigenvalue reflects the speed at which the system recovers to a steady state. By selecting the solution with the most negative eigenvalue, it is ensured that the system can quickly stabilize under external disturbance conditions such as temperature and humidity fluctuations. Compared with the traditional method that ignores the defect of stability, the steady-state analysis strategy of this method significantly improves the reliability of the production process and provides a guarantee for the long-term use of concrete in complex engineering environments. Therefore, the nonlinear dynamic steady-state analysis strategy not only enhances the stability of concrete performance optimization, but also lays a scientific foundation for the stable operation of the production system.

[0041] The execution parameter feedback control strategy adjusts the parameters in the process of producing high-performance waterproof concrete, including: Get the target solution ; For any parameter value at the current time t ; Calculate the parameter value at the next moment , in, is the feedback gain, i=1,2,3,4.

[0042] By executing the parameter feedback control strategy, this method can quickly adjust the optimization process according to the dynamic changes of real-time production parameters to achieve closed-loop control. The feedback control strategy combines the nonlinear dynamic model to calculate the dynamic response rate of the production parameters in real time, and adjusts the gain coefficient according to the target solution to keep the production process in the optimal state. Compared with the traditional method that relies on manual adjustment, feedback control can significantly reduce human errors while improving production efficiency and stability. This strategy can also quickly respond to changes in ambient temperature and humidity to ensure that the performance of concrete is not affected by external disturbances, thereby achieving adaptive optimization of the system. Therefore, the parameter feedback control strategy effectively enhances the intelligent level of high-performance waterproof concrete production through a closed-loop adjustment mechanism, providing reliable guarantees for automated production.

[0043] The various technical parameters of the waterproof concrete mix ratio used in this embodiment are not composed of various technical parameter limit values, but are selected within the parameter limit range, and the best waterproof concrete mix ratio that meets the design requirements is obtained through trial mixing.

[0044] ① Water-cement ratio constraint ≦0.45 Determine the water-cement ratio based on the requirements of the bidding documents and previous construction experience, and strictly control the maximum water consumption.

[0045] ②Sand ratio limit 42%~44% Select an appropriate sand ratio to ensure the quantity and quality of cement mortar in concrete, reduce and change the pore structure, increase density and improve impermeability.

[0046] ③Slump constraint 150mm~200mm All engineering concrete is pumped commercial concrete, and the slump should not be too small. Therefore, during construction, the workability and pumpability of concrete are improved by adjusting the admixtures, and the slump of concrete is controlled within a reasonable range as much as possible.

[0047] ④ The dosage of admixture is limited to 20%~30%; The lime-sand ratio is selected based on the actual project conditions and previous construction experience.

[0048] ⑤ Temperature difference control: temperature difference ≤ 15℃; It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0049] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for optimizing the production of high-performance waterproof concrete, characterized in that: include: Establish a digital twin model for the production of high-performance waterproof concrete, specifically: Real-time collection of parameters during the production of high-performance waterproof concrete, including water-cement ratio , sand rate , admixture dosage , slump , Ambient temperature and ambient humidity ; Obtaining constraints of the parameters; Setting optimization goals for producing high-performance waterproof concrete, the optimization goals including impermeability, strength and density; Execute the prediction strategy of the optimization target model and establish the prediction model of the optimization target; The Adam optimization algorithm is used to calculate the optimal solution of the parameters of the prediction model of the optimization target; Obtain all optimal solutions, execute nonlinear dynamic steady-state analysis strategy, obtain the most stable steady-state solution, and record it as the target solution; Implement parameter feedback control strategy to adjust parameters in the process of producing high-performance waterproof concrete.

2. The method for optimizing and producing high-performance waterproof concrete according to claim 1, characterized in that: The method of executing the prediction strategy of the optimization target model and establishing the prediction model of the optimization target includes: Collect historical parameters and apply multivariate regression model to fit the objective functions of impermeability, strength and density; The impermeability objective function is expressed as ; The intensity objective function is expressed as ; The density objective function is expressed as ; Obtaining the standard temperature for producing high-performance waterproof concrete and standard humidity ; Calculate the change results of the impermeability objective function under ambient temperature and ambient humidity ； Calculate the change of intensity objective function under ambient temperature and ambient humidity ； Calculate the change results of the density objective function under ambient temperature and ambient humidity ， in, and All are objective function adjustment coefficients; The value range of the control parameter satisfies the parameter constraints.

3. The method for optimizing and producing high-performance waterproof concrete according to claim 2, characterized in that: The prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: Calculating the objective function for producing high-performance waterproof concrete ; ， in, and They are the weight of impermeability, strength and density respectively; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; The objective function right Find the partial derivative and get the gradient ; Update Adam's momentum , , is the k-th step parameter The first-order momentum value of is the momentum coefficient, which determines the weight of the historical gradient, is the k+1th step parameter The first-order momentum value of Update the RMS term using the exponentially weighted moving average of the squared gradients ， in, is the k-th step parameter The second-order momentum value of is the k+1th step parameter The second-order momentum value of is the smoothing coefficient, which controls the weight of the squared gradient history contribution.

4. The method for optimizing and producing high-performance waterproof concrete according to claim 3, characterized in that: The prediction model for the optimization target uses the Adam optimization algorithm to calculate the optimal solution of the parameters, including: Correct the first-order momentum and second-order momentum values: ， in, is the corrected first-order momentum estimate, is the bias correction factor for the first-order momentum value correction; ， in, is the corrected second-order momentum estimate, is the bias correction factor for the second-order momentum value correction; ， in, is the parameter value at the kth step, is the learning rate, which is used to control the step size of each update. Used to dynamically adjust the learning rate, is a smoothing term used to prevent the denominator from being zero; Setting the norm threshold ; Set parameter difference threshold ; and , then stop the iteration and get the optimal solution.

5. The method for optimizing and producing high-performance waterproof concrete according to claim 1, characterized in that: The method of obtaining all optimal solutions and executing nonlinear dynamic steady-state analysis strategies to obtain the most stable steady-state solutions includes: Get any optimal solution ; Compute the dynamic response of a parameter using nonlinear dynamic equations: ， ， ， Among them, i=1,2,3,4, For parameters The dynamic rate of change, is the parameter value at time t, is the ambient temperature at time t, is the ambient humidity value at time t; judge of Is it satisfied at any time? ; If satisfied, then is a steady-state solution.

6. The method for optimizing and producing high-performance waterproof concrete according to claim 5, characterized in that: The method of obtaining all optimal solutions and executing nonlinear dynamic steady-state analysis strategies to obtain the most stable steady-state solutions includes: Calculate the Jacobian matrix J; ； in, Representation parameters right Partial derivatives, j=1,2,3,4,i=1,2,3,4,5,6; Find the eigenvalues ​​of the Jacobian matrix J Get the minimum value of the real part of each eigenvalue and record it as the marked value; Get the mark values ​​of all steady-state solutions, and record the steady-state solution corresponding to the minimum mark value as the target solution.

7. The method for optimizing and producing high-performance waterproof concrete according to claim 6, characterized in that: The execution parameter feedback control strategy adjusts the parameters in the process of producing high-performance waterproof concrete, including: Get the target solution ; For any parameter value at the current time t ; Calculate the parameter value at the next moment ， in, is the feedback gain, i=1,2,3,4.

Images