Concrete hydration heat self-adaptive control method and system based on digital twinning

Abstract

The invention discloses the technical field of constructional engineering and intelligent control, and relates to a concrete hydration heat self-adaptive control method and system based on digital twinning. The method comprises the following steps: S1, constructing a concrete finite element model, simulating a hydration heat process, and outputting simulation data of temperature and temperature stress; s2, based on the analog data, optimizing the arrangement scheme of the cooling water pipe and the sensor through a composite convolutional neural network; s3, arranging and collecting real-time temperature and temperature stress data according to the scheme; s4, in combination with simulation and real-time data, predicting temperature change by adopting a BP neural network and a long-short term memory network, and constructing a dynamic prediction model; s5, based on the prediction result and the real-time data, constructing a WebGL digital twinborn platform, visualizing the data and correcting a prediction model; and S6, dynamically adjusting parameters of the cooling water pipe according to a correction result to realize hydration heat self-adaptive control. The invention further provides a system for realizing the method, the concrete temperature and the temperature stress can be accurately controlled, and the engineering structure safety and the quality control efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of construction engineering and intelligent control, and particularly relates to a method and system for adaptive control of concrete hydration heat based on digital twin. Background Art

[0002] As an indispensable basic material in modern engineering construction, concrete plays a crucial role in quality control and temperature control management during the construction process. With the increasingly strict construction requirements, how to improve the quality of concrete pouring, especially to avoid temperature-induced structural problems through precise temperature control, has become the core topic of current research and application. However, existing temperature control technologies face many challenges in practical applications. First of all, the acquisition of temperature control information often has problems of lag and inaccuracy, which leads to phenomena such as excessive temperature difference, too fast cooling rate and cooling amplitude, and uneven temperature gradient, and may ultimately cause concrete cracks. Secondly, the deviation of operators during the construction process is also an important factor leading to the failure of temperature control, resulting in limitations in temperature control.

[0003] Currently, many units have developed temperature control systems that automatically control the opening and closing of water-cooled pipes, and some systems can monitor the hydration heat of concrete. However, existing technologies still have deficiencies, especially in the experimental research on the mechanism of hydration heat. In the face of the adoption of new admixtures, existing systems are difficult to accurately predict the temperature development of concrete hydration heat. Most systems can still only provide passive control methods and are difficult to achieve active optimization of temperature control. In addition, the data monitoring and display methods are too single, and the deep integration of virtual and actual spaces cannot be fully realized, and accurate decision-making cannot be effectively supported.

[0004] With the development of the construction industry towards intelligence and digitization, how to combine the automation and intelligence of concrete temperature control has become a key problem to be solved urgently. Therefore, how to improve the data processing speed, optimize the data display platform, improve the data utilization efficiency, and dynamically adjust the temperature control parameters according to real-time data has become an important challenge for realizing the intelligence of concrete temperature control. Summary of the Invention

[0005] The present application provides a method and system for adaptive control of concrete hydration heat based on digital twin, which can accurately control the temperature and temperature stress of concrete, and obtain the technical effects of improving the safety of engineering structures and the quality control efficiency. During the concrete construction process, temperature control adjustments can be made according to real-time monitoring data. By using integrated learning and composite convolutional neural networks to optimize the simulation and prediction accuracy, dynamic temperature management can be achieved, thereby reducing temperature-related structural defects to achieve the technical effects.

[0006] In a first aspect, an embodiment of the present application provides a method for adaptive control of concrete hydration heat based on digital twin, and the method may include:

[0007] S1. Construct a finite element model of concrete according to preset parameters, conduct simulation prediction of concrete hydration heat, and output simulation data of temperature and temperature stress;

[0008] S2. According to the simulation data, preset the layout optimization objectives of cooling water pipes and sensors, and generate the layout schemes of cooling water pipes and sensors through a composite convolutional neural network based on the layout optimization objectives;

[0009] S3. According to the layout scheme, arrange cooling water pipes and sensors and collect real-time data; the real-time data includes temperature data and temperature stress data;

[0010] S4. According to the simulation data and the real-time data, use a BP neural network and a long short-term memory network to predict the concrete temperature change trend, construct a dynamic prediction model of concrete temperature and temperature stress, and output a dynamic prediction result;

[0011] S5. Based on the dynamic prediction result and the real-time data, construct a digital twin platform based on WebGL technology; the digital twin platform is used to visualize the temperature and temperature stress changes inside and on the surface of the concrete, and correct the dynamic prediction model, and output a corrected prediction result;

[0012] S6. According to the corrected prediction result output by the digital twin platform, dynamically adjust the water flow rate, water flow direction and water temperature of the cooling water pipes to achieve adaptive control of concrete hydration heat.

[0013] In some embodiments, the preset parameters include concrete mix ratio, environmental parameters, condition parameters of concrete construction and maintenance, physical parameters and layout parameters of cooling water pipes; the environmental parameters include temperature, humidity and wind speed.

[0014] In the above implementation process, by considering preset parameters such as concrete mix ratio, environmental parameters and construction conditions, the adaptability and accuracy of simulation prediction are enhanced, and the effect of optimizing the construction environment response ability is achieved.

[0015] In some embodiments, step S1 includes constructing a concrete model using WebGL technology, and on this basis, establishing a finite element simulation to simulate and analyze the change trends of the simulated temperature and temperature stress of concrete hydration heat.

[0016] In the above implementation process, through the entity modeling using WebGL technology and the establishment of a finite element model, the continuity, accuracy of data and the reliability of simulation analysis are improved, thereby achieving the effect of enhancing the practicality of simulation results.

[0017] In some embodiments, step S2 may further include:

[0018] S21. Preset the layout optimization objectives for the cooling water pipes and sensors according to the simulation data; the layout optimization objectives are to maximize the cooling effect and minimize the layout cost;

[0019] S22. Use a composite convolutional neural network to identify the temperature distribution, and generate the optimal layout plan for the cooling water pipes with the goal of maximizing the cooling effect;

[0020] S23. On the basis of the optimal layout of the cooling water pipes, use a composite convolutional neural network to generate the layout plan for the sensors.

[0021] In the above implementation, the automatic optimization of the layout of the cooling water pipes and sensors by the composite convolutional neural network realizes the maximization of the cooling effect and the minimization of the cost, and improves the construction efficiency and economy.

[0022] In some embodiments, step S23 of generating the layout plan for the sensors includes optimizing the number of sensors by using a master-slave composite convolutional neural network; wherein, the main path of the master-slave composite convolutional neural network processes the temperature change characteristics, and the slave path processes the humidity and concrete mix ratio changes.

[0023] In the above implementation, the optimization of the number and layout of the sensors by the master-slave composite convolutional neural network realizes the accuracy and efficiency of temperature and humidity monitoring, thereby improving the comprehensiveness and accuracy of data monitoring.

[0024] In some embodiments, step S3 may include:

[0025] S31. Arrange a wireless sensor network according to the layout plan;

[0026] S32. Collect the real-time data of the concrete through the wireless sensor network, and back up the real-time data in the local storage device; the real-time data includes temperature data and temperature stress data;

[0027] S33. Use the cyclic redundancy check method to check the real-time data, and transmit the checked real-time data to the cloud platform server.

[0028] In the above implementation, through the real-time data collection and cyclic redundancy check of the wireless sensor network, the accuracy and real-time nature of the data are ensured, and the effect of improving the reliability of data transmission is achieved.

[0029] In some embodiments, step S4 may include:

[0030] S41. Train a BP neural network according to the real-time data and the simulation data, and use the trained BP neural network to perform short-term prediction on the temperature of the concrete to obtain a short-term prediction result;

[0031] S42. Input the analog data, the real-time data, and the short-term prediction results into a long short-term memory network, and dynamically output the dynamic prediction results of the temperature change trend of the concrete hydration heat in real time.

[0032] In the above implementation, through the combined use of a BP neural network and a long short-term memory network, the accurate prediction of the concrete temperature change trend is realized, thus achieving the effects of optimizing the temperature control strategy and improving the structural safety.

[0033] In some embodiments, step S41 further includes optimizing the key parameters of the BP neural network by using a cross global artificial bee colony algorithm; the key parameters include input parameters, topological structure, and initial weights.

[0034] In the above implementation, by optimizing the key parameters of the BP neural network through a cross global artificial bee colony algorithm, the accuracy of temperature prediction is improved, thus realizing more refined temperature control management and reducing the structural risks caused by temperature.

[0035] In some embodiments, step S6 includes:

[0036] S61. Based on the real-time data and the dynamic prediction results, optimize the water flow rate, water flow direction, and water temperature of the cooling water pipes by using a non-dominated sorting genetic algorithm;

[0037] S62. Adjust the cold zone parameters of the concrete, including the temperature rise rate, the temperature drop rate, and the maximum temperature difference.

[0038] In the above implementation, by dynamically adjusting the parameters of the cooling water pipes through a non-dominated sorting genetic algorithm, the adaptive refinement of concrete temperature control is realized, achieving the effects of minimizing the risk of temperature cracks and improving the structural stability to the greatest extent.

[0039] In a second aspect, an embodiment of the present application provides a digital twin-based adaptive control system for concrete hydration heat, and the system may include:

[0040] A model construction unit, configured to construct a finite element model of concrete according to preset parameters and perform hydration heat simulation, and output simulation data of temperature and temperature stress;

[0041] An arrangement generation unit, configured to generate an arrangement plan of cooling water pipes and sensors according to the simulation data by using a composite convolutional neural network;

[0042] A real-time monitoring unit, responsible for arranging cooling water pipes and sensors according to the arrangement plan and collecting real-time data;

[0043] A prediction and analysis unit, configured to perform temperature trend prediction based on the simulation data and the real-time data by using a BP neural network and a long short-term memory network, and construct a dynamic prediction model;

[0044] The digital twin platform unit adopts a digital twin platform based on WebGL technology, which is used to visualize and correct the temperature and stress changes inside and on the surface of concrete, and output the corrected prediction results.

[0045] The control execution unit dynamically adjusts the water flow rate, water flow direction, and water temperature of the cooling water pipes according to the corrected prediction results to achieve the adaptive control of the hydration heat of concrete.

[0046] In the above implementation method, through the digital twin-based adaptive control system solution for the hydration heat of concrete, various technical effects are achieved. First of all, through the accurate finite element model and real-time data monitoring, the system can predict in advance and accurately grasp the temperature and temperature stress changes of concrete, avoiding the lag and inaccuracy in traditional temperature control systems. Secondly, the composite convolutional neural network optimizes the layout of cooling water pipes and sensors, improving the temperature control efficiency and system coverage, thus enhancing the uniformity of temperature control. Furthermore, the dynamic prediction model combining the BP neural network and the long short-term memory network effectively supports the active adjustment of the temperature control system, reducing the concrete cracks caused by excessive temperature differences. Finally, the real-time visualization and correction feedback mechanism of the digital twin platform ensure the accuracy and adaptive adjustment ability of the temperature control process, thereby improving the construction quality and engineering safety. This system significantly improves the accuracy, efficiency, and reliability of temperature control management, providing an intelligent solution for large-scale concrete construction.

[0047] Compared with the prior art, the beneficial effects of this application are:

[0048] Through the adaptive control solution for the hydration heat of concrete based on digital twin technology, this application achieves multi-level innovative effects. First of all, by constructing an accurate finite element model and simulating the hydration heat of concrete, the effect of accurately predicting the temperature and stress changes during the concrete construction process is achieved, thereby identifying potential structural risks in advance. Secondly, the composite convolutional neural network is used to optimize the layout of cooling water pipes and sensors according to the simulation data, realizing a more scientific and efficient resource allocation, and significantly improving the efficiency of the cooling system. Furthermore, by combining the BP neural network and the long short-term memory network, the dynamic prediction of the concrete temperature change trend is carried out and a prediction model is constructed, which makes the temperature control management more active and accurate, effectively preventing quality problems caused by abnormal temperatures. Finally, through the real-time data-driven digital twin platform, not only the changes in internal temperature and stress are visualized, but also the construction parameters can be adaptively adjusted according to the dynamic prediction results, ensuring the temperature control accuracy and construction safety during the construction process, and greatly reducing the structural problems caused by temperature. This all-round control strategy greatly improves the construction quality and ensures the long-term stability and safety of the structure. Description of the Drawings

[0049] Figure 1 Schematic diagram of the steps of a digital-twin-based self-adaptive control method for concrete hydration heat in Embodiment 1 of the present invention;

[0050] Figure 2 Schematic structural diagram of a digital-twin-based self-adaptive control method for concrete hydration heat in Embodiment 2 of the present invention;

[0051] Figure 3 Implementation flowchart of a digital-twin-based self-adaptive control method for concrete hydration heat in Embodiment 2 of the present invention;

[0052] Figure 4 System structure diagram of a digital-twin-based self-adaptive control system for concrete hydration heat in Embodiment 3 of the present invention;

[0053] Figure 5 Display interface of the cloud platform server in Embodiment 3 of the present invention. Specific implementation manners

[0054] The following combines the accompanying drawings and specific embodiments to detail the digital-twin-based self-adaptive control method and system for concrete hydration heat provided by the present invention. It should be emphasized that the embodiments are only for explaining and illustrating the technical content of the present invention and should not be construed as limiting the protection scope of the present invention. Any technical solution implemented based on the technical idea of the present invention falls within the protection scope of the present invention. In combination with the following description, the advantages and features of the present invention will be clearer. It should be noted that the accompanying drawings are in a simplified form and not to an accurate scale, only for the purpose of illustrating the embodiments of the present invention. In specific embodiments, how to implement an accurate concrete temperature control process through a digital-twin platform will be detailed according to actual construction conditions, cooling water pipe arrangements, and sensor arrangements.

[0055] Embodiment 1

[0056] During the research process, the applicant found that when using a traditional temperature control system, if one attempts to achieve immediate temperature control adjustment during concrete construction, it requires cumbersome steps such as manual monitoring and subsequent manual adjustment. When solving practical engineering problems, in order to achieve the technical purpose of efficient and accurate temperature management, the existing technologies cannot meet the requirements of real-time data processing and immediate feedback. Therefore, after researching this problem, the applicant proposed a self-adaptive control method based on digital twins. When addressing the technical problem of concrete temperature control, by integrating finite element models, neural network predictions, and digital twin technical solutions, high-precision temperature prediction and real-time self-adaptive adjustment are achieved, thereby achieving the technical effects of improving structural safety and construction efficiency.

[0057] Please refer to Figure 1 , Figure 1Schematic diagram of the steps of the concrete hydration heat adaptive control method based on digital twin provided by the embodiments of this application. The concrete hydration heat adaptive control method based on digital twin may include:

[0058] S1. Construct a finite element model of concrete according to preset parameters and conduct simulation prediction of concrete hydration heat, and output simulation data of temperature and temperature stress;

[0059] S2. According to the simulation data, preset the layout optimization objectives of cooling water pipes and sensors, and generate the layout schemes of cooling water pipes and sensors based on the layout optimization objectives through a composite convolutional neural network;

[0060] S3. Arrange cooling water pipes and sensors according to the layout scheme and collect real-time data; the real-time data includes temperature data and temperature stress data;

[0061] S4. According to the simulation data and the real-time data, use a BP neural network and a long short-term memory network to predict the concrete temperature change trend, and construct a dynamic prediction model of concrete temperature and temperature stress, and output a dynamic prediction result;

[0062] S5. Based on the dynamic prediction result and the real-time data, construct a digital twin platform based on WebGL technology; the digital twin platform is used to visualize the temperature and temperature stress changes inside and on the surface of the concrete, and correct the dynamic prediction model, and output a corrected prediction result;

[0063] S6. According to the corrected prediction result output by the digital twin platform, dynamically adjust the water flow rate, water flow direction and water temperature of the cooling water pipe to achieve the adaptive control of concrete hydration heat.

[0064] In some embodiments, the preset parameters include concrete mix ratio, environmental parameters, condition parameters of concrete construction and maintenance, physical parameters and layout parameters of cooling water pipes; the environmental parameters include temperature, humidity, and wind speed.

[0065] In the above implementation process, by considering preset parameters such as concrete mix ratio, environmental parameters and construction conditions, the adaptability and accuracy of simulation prediction are enhanced, and the effect of optimizing the construction environment response ability is achieved.

[0066] In some embodiments, step S1 includes constructing a concrete model using WebGL technology, and on this basis, establishing a finite element simulation to simulate and analyze the change trends of the simulated temperature and temperature stress of concrete hydration heat.

[0067] In the above implementation process, through the entity modeling using WebGL technology and the establishment of the finite element model, the continuity and accuracy of data and the reliability of simulation analysis are improved, thereby achieving the effect of enhancing the practicality of simulation results.

[0068] In some embodiments, step S2 may further include:

[0069] S21. According to the simulation data, preset the layout optimization objectives of the cooling water pipes and sensors; the layout optimization objectives are to maximize the cooling effect and minimize the layout cost;

[0070] S22. Use a composite convolutional neural network to identify the temperature distribution, and generate the optimal layout plan of the cooling water pipes with the goal of maximizing the cooling effect;

[0071] S23. On the basis of the optimal layout of the cooling water pipes, use a composite convolutional neural network to generate the layout plan of the sensors.

[0072] In the above implementation method, through the automatic optimization of the layout of the cooling water pipes and sensors by the composite convolutional neural network, the maximization of the cooling effect and the minimization of the cost are achieved, and the construction efficiency and economy are improved.

[0073] In some embodiments, step S23 generating the layout plan of the sensors includes optimizing the number of sensors using a master-slave composite convolutional neural network; wherein, the main path of the master-slave composite convolutional neural network processes the temperature change characteristics, and the slave path processes the humidity and concrete mix ratio changes.

[0074] In the above implementation method, through the optimization of the number and layout of sensors by the master-slave composite convolutional neural network, the accuracy and efficiency of temperature and humidity monitoring are achieved, thereby enhancing the comprehensiveness and accuracy of data monitoring.

[0075] In some embodiments, step S3 may include:

[0076] S31. According to the layout plan, arrange a wireless sensor network;

[0077] S32. Collect the real-time data of the concrete through the wireless sensor network, and back up the real-time data in the local storage device; the real-time data includes temperature data and temperature stress data;

[0078] S32. Use the cyclic redundancy check method to check the real-time data, and transmit the checked real-time data to the cloud platform server.

[0079] In the above implementation method, through the real-time data collection and cyclic redundancy check of the wireless sensor network, the accuracy and real-time performance of the data are ensured, achieving the effect of improving the reliability of data transmission.

[0080] In some embodiments, step S4 may include:

[0081] S41. Train a BP neural network based on the real-time data and the simulation data, and use the trained BP neural network to perform short-term prediction on the temperature of the concrete to obtain a short-term prediction result;

[0082] S42. Input the simulation data, the real-time data, and the short-term prediction result into a long short-term memory network, and dynamically output a dynamic prediction result of the temperature change trend of the concrete hydration heat.

[0083] In the above implementation, through the combination of the BP neural network and the long short-term memory network, accurate prediction of the concrete temperature change trend is achieved, thereby achieving the effects of optimizing the temperature control strategy and improving the structural safety.

[0084] In some embodiments, step S41 further includes optimizing the key parameters of the BP neural network by using a cross global artificial bee colony algorithm; the key parameters include input parameters, topological structure, and initial weights.

[0085] In the above implementation, by optimizing the key parameters of the BP neural network through the cross global artificial bee colony algorithm, the accuracy of temperature prediction is improved, thereby achieving more refined temperature control management and reducing the structural risks caused by temperature.

[0086] In some embodiments, step S6 includes:

[0087] S61. Based on the real-time data and the dynamic prediction result, optimize the water flow rate, water flow direction, and water temperature of the cooling water pipe by using a non-dominated sorting genetic algorithm;

[0088] S62. Adjust the cold zone parameters of the concrete, including the temperature rise rate, temperature drop rate, and maximum temperature difference.

[0089] In the above implementation, by dynamically adjusting the cooling water pipe parameters through the non-dominated sorting genetic algorithm, adaptive refinement of the concrete temperature control is achieved, reaching the effects of minimizing the risk of temperature cracks and improving the structural stability to the greatest extent.

[0090] The digital twin-based adaptive control method for concrete hydration heat provided by the embodiments of the present application can be widely applied to multiple technical fields, such as construction engineering, infrastructure construction, and temperature management of large structures, and is particularly suitable for the construction of key structures such as high-rise buildings and bridges. In the above implementation, when performing concrete temperature control, instant adjustment can be made according to the real-time collected temperature and stress data, and the control strategy is optimized through intelligent algorithms to achieve precise temperature adjustment, thereby effectively preventing structural cracks caused by temperature fluctuations and improving the engineering safety and construction quality.

[0091] Example 2

[0092] As an optimization of the foregoing embodiments, Example 2 provides a specific implementation manner of a digital-twin-based self-adaptive control method for concrete hydration heat.

[0093] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of the method according to the embodiments of the present application. As shown in the figure, the method includes a data acquisition layer, a data processing layer, and a control decision layer.

[0094] The data acquisition layer includes obtaining temperature and temperature stress data through on-site measurement by sensors and finite element data simulation, and uploading the data to the cloud platform server through wireless sensor network technology. During the data transmission process, the cyclic redundancy check method is used to verify the data.

[0095] The data processing layer includes analyzing the data obtained from the data acquisition layer, including using the cross-global artificial bee colony algorithm, BP neural network model, and long short-term memory network model, and constructing a digital twin modeling section using BIM technology, Unity3D technology, and WebGL technology for the analysis results.

[0096] The control decision layer includes transmitting the data in the digital twin modeling section to a temperature control execution module, a control signal transmission module, and a feedback adjustment module. Finally, the visualization of the entire process of self-adaptive control of concrete hydration heat can be achieved on the digital twin platform.

[0097] Please refer to Figure 3 , Figure 3 which is a flowchart of the implementation of a digital-twin-based self-adaptive control method for concrete hydration heat, specifically including:

[0098] S1. Construction of a finite element model of concrete and simulation prediction of hydration heat, including the following steps:

[0099] S11. First, set the concrete mix ratio, environmental parameters calibrated in the hydration heat test (including environmental temperature, humidity, and wind speed), and consider specific condition parameters during the concrete construction and curing processes. In addition, key parameters such as the boundary conditions and element division of the model also need to be set. These preset parameters provide the necessary data support and physical basis for subsequent modeling and simulation.

[0100] S12. Construct a finite element model of concrete according to the preset parameters in S11. The finite element model includes cooling water pipes and the physical parameters related to the cooling water pipes, such as shape and pipe diameter; it also includes the specific heat capacity of the cooling water, as well as the water flow rate, water flow direction, and water temperature flowing into the cooling water pipes, etc. This model is used to simulate the evolution of the temperature of hydration heat and the temperature stress during the concrete pouring process. Through finite element analysis, obtain the variation laws of temperature and temperature stress with time, and further provide reference data for temperature control management and optimization.

[0101] S13. On the basis of the finite element model, use the integrated learning method to correct the simulation data. By integrating the calculation results under different parameters and combining more factors that may affect the concrete hydration heat process (such as construction environment changes, material property differences, etc.), improve the accuracy and adaptability of the simulation.

[0102] S2. Optimize the layout of the cooling water pipes and sensors based on the composite convolutional neural network:

[0103] S21. Based on the simulation data in S1, use the composite convolutional neural network to automatically identify the distribution law of temperature, and take maximizing the cooling effect as the goal to adjust the layout parameters. The specific parameters include: pipe diameter, number of layers, layout direction, and horizontal and vertical spacings, etc. Through the calculation and optimization of the network, automatically screen and generate the optimal layout plan of the cooling water pipes, providing accurate guidance for subsequent construction.

[0104] S22. On the basis of the optimized layout of the cooling water pipes in S21, use the composite convolutional neural network to further optimize the layout of the sensors. This network can identify the key characteristic parameters to ensure that the layout of the sensors can comprehensively and accurately monitor the change trends of the temperature and temperature stress inside and on the surface of the concrete during the hydration heat process. Mainly optimize the number and position of the sensors to ensure that the real-time data covers the entire construction area and the data acquisition accuracy is high.

[0105] S3. Design a monitoring system based on the Internet of Things technology to transmit the temperature and temperature stress data to the cloud platform server in real time, including the following steps:

[0106] S31. According to the optimized plan generated in step S2, install the cooling water pipes and sensors in the actual structure to ensure that the pipe positions and parameters are consistent with the optimization results. Adopt the wireless sensor network (WSN) technology to collect and transmit the temperature and temperature stress data inside and on the surface of the concrete in real time. To ensure the efficiency and stability of data transmission, adopt an efficient data compression technology for transmission. The sensors automatically record the data and back it up in the local storage device to ensure the integrity of the data. At the same time, the sensor network is equipped with a backup power supply to ensure long-term stable operation.

[0107] S32. To ensure the accuracy and reliability of data, the cyclic redundancy check (CRC) method is used to perform integrity verification on the transmitted data. The verified data will be transmitted to the cloud platform server in real time, realizing the centralized management and real-time monitoring of large-scale data. This monitoring system provides reliable raw data support for subsequent dynamic prediction and adaptive control.

[0108] S4. Build a dynamic prediction model for the hydration heat temperature and temperature stress of concrete:

[0109] S41. Based on the temperature data, temperature stress data, and simulation data of concrete collected in real time in step S3, build a database of temperature and temperature stress for the training of the BP neural network. This database provides diverse and accurate data support for the network, helping to train a high-precision prediction model.

[0110] S42. By introducing the cross-global artificial bee colony algorithm, optimize the key parameters of the BP neural network, including input parameters, topological structure, and initial weight thresholds. This optimization process improves the efficiency and prediction accuracy of model training through global search and local adjustment.

[0111] S43. Build an optimized BP neural network, perform in-depth learning and short-term prediction, and obtain short-term prediction results. Through this model, the temperature and stress changes during the hydration heat process of concrete are predicted in real time, and the prediction results will be used as an important basis for issuing instructions in the automated control system.

[0112] S44. Collect the hydration heat temperature data of mass concrete and establish a concrete temperature change curve. Input the concrete temperature change curve, short-term prediction results, real-time data, and simulation data into the long short-term memory (LSTM) model to build a physical-data dual-driven dynamic prediction model for the hydration heat temperature of concrete. This dynamic prediction model continuously monitors the change trends of temperature and temperature stress during the hydration heat process of concrete in real time and outputs dynamic prediction results in real time. This model provides the core prediction ability for the digital twin platform and supports the optimization of subsequent control strategies.

[0113] S5. Build a digital twin platform for the hydration heat of concrete based on WebGL technology:

[0114] S51. Use Abaqus software to build a finite element model of concrete to simulate the temperature and temperature stress changes generated during the hydration heat process of concrete. This model provides basic data support for the subsequent digital twin platform.

[0115] S52. Import the finite element model information (geometry, node, and element information) and simulation data (node temperature field and stress field) generated by Abaqus into Unity3D to generate the corresponding 3D visual model. Use Unity3D to build the visualization interface of the digital twin platform to ensure that the digital twin platform can truly reflect the temperature and temperature stress distribution of concrete hydration heat.

[0116] S53. Based on WebGL technology, develop a digital twin monitoring platform that combines the dynamic prediction model with the monitored real-time data to achieve the following functions: comprehensively monitor the temperature and temperature stress changes inside and on the surface of the concrete; continuously correct the dynamic prediction model according to the monitored real-time data to improve the prediction accuracy and reliability. This platform can effectively ensure the consistency between the prediction results and the actual situation and provide a scientific basis for adaptive control. The built digital twin platform can realize the real-time display of the changes in hydration heat temperature and temperature stress. Based on WebGL technology, this platform combines technologies such as big data collection and analysis of concrete temperature control, artificial intelligence early warning, virtual reality interaction, and visualization, and transmits the real-time monitored data to the digital twin platform based on WebGL. In the digital twin platform, users can locate the positions of the sensors and view the temperature, stress historical information of various sensors, generate trend curves, inside-outside temperature difference distribution maps, inside-outside stress distribution maps, and other visualization charts.

[0117] S54. In addition, the real-time data is compared with the prediction results of the dynamic prediction model constructed in step S4 in real time, and the prediction model is corrected according to the real-time data, so that the temperature and temperature stress distribution states of the virtual model in the digital twin platform and the physical model of the actual concrete pouring are consistent. The so-called dynamic correction means adjusting and optimizing the digital model by comparing the real-time collected data with the prediction model to make it more accurately reflect the actual situation of concrete hydration heat. Through this correction process, the adaptive control of the physical model is realized to ensure the accuracy and stability of concrete temperature control.

[0118] S6. Dynamically control the parameters of the cooling water pipes to accurately adjust the concrete temperature.

[0119] S61. According to the monitoring and dynamic prediction results of the digital twin platform, combined with the measured data (concrete temperature, stress, temperature rise and fall rate, inside-outside temperature difference, maximum temperature difference, ambient temperature, inlet temperature, etc.), conduct comprehensive calculation and analysis. Through multi-parameter evaluation, comprehensively master the temperature change law during the hydration heat process to provide a basis for the optimization of subsequent control strategies.

[0120] S62. Adopt the Non-dominated Sorting Genetic Algorithm II (NSGA-II) optimization control method to dynamically adjust control parameters such as the water flow rate, water flow direction, water temperature, and pouring process parameters of the cooling water pipes according to the calculation and analysis results. Achieve precise control of the hydration heat of concrete, including: dynamically adjusting the flow rate, flow velocity, and water temperature of the cooling water to meet the temperature control requirements at different stages; optimizing the thickness and layout of the thermal insulation materials according to the prediction results; adjusting the pouring speed or sequence when necessary to ensure uniform temperature distribution. This optimization process will maximize the reduction of the temperature rise rate, ensure an appropriate cooling rate, and balance the temperature difference between the inside and the surface of the concrete to improve the temperature control accuracy. Through precise control, minimize the risk of temperature cracks and ensure the quality and long-term stability of the concrete structure.

[0121] Through the above steps, an adaptive and dynamically adjustable control system is formed, which can effectively respond to the temperature control requirements at different stages and achieve temperature control and stress optimization during the hydration heat process of concrete through fine adjustment.

[0122] In some embodiments, the method further includes measuring and analyzing the thermal physical property parameters of concrete at typical construction sites to effectively make up for the difference between the reference values in the current specifications and the actual situation. Select typical construction sites such as plain areas, plateaus, alpine regions, and coastal areas as the research objects to ensure that the popularization and application of this system can build a good experimental and theoretical foundation, and then improve its adaptability and practicability in different construction environments.

[0123] In some embodiments, in step S13, the embodiment of the present application adopts an integrated learning technique to optimize the finite element hydration heat analysis model. Most of the existing model correction methods are deterministic methods, which do not fully consider the uncertainty of structural parameters and responses, resulting in insufficient accuracy in actual engineering applications. In view of the widespread uncertainty during the concrete pouring process, especially in terms of structural parameters and responses, the finite element model correction method based on the meta-model and the base model selector can select the most suitable model through multi-model comparison for the numerical simulation analysis of hydration heat.

[0124] The specific process is as follows: First, organize and preprocess data such as construction environment conditions, concrete mix ratios, physical parameters and layout parameters of the cooling water pipes, and concrete physical parameters to ensure the accuracy of modeling. Then, input environmental parameters, material parameters, boundary conditions, etc. into the finite element software to obtain multiple base models. Optimize these base models through an integrated learning technique to form a meta-model and select the best model configuration. Finally, set the simulation parameters and run the simulation to predict the changing trends of the temperature and temperature stress of the hydration heat to evaluate the efficiency of the cooling system.

[0125] In some embodiments, in step S21, the embodiments of the present application use a composite convolutional neural network to predict the layout of the cooling water pipes. An optimization function is constructed to perform sequential iterative single-objective optimization for maximizing the cooling effect and minimizing the cost. First, taking maximizing the cooling effect as the optimization objective and the temperature peak and gradient as constraints, single-objective optimization is carried out to obtain an optimized layout of the cooling water pipes; then, on the premise of satisfying the local optimal solution of the cooling effect, taking minimizing the layout result as the optimization objective, the best number combination of the number of cooling water pipes or sensors is obtained while ensuring the monitoring accuracy.

[0126] By collecting parameters such as the layout density, length, and radial distribution of the water pipes, and combining the relevant data generated by simulation (such as the temperature distribution, cooling effect, and cost corresponding to different water pipe layouts), the water pipe layout parameters are used as the input of the neural network, and the corresponding cooling effect and cost are output.

[0127] By training the neural network, the network can learn the relationship between the water pipe layout and the cooling effect and cost. Finally, according to specific engineering requirements, the network structure or optimization algorithm parameters are adjusted to adapt to different engineering conditions and objectives, and finally the optimal solution between the cooling effect and cost is obtained. The multi-objective optimization method based on the composite convolutional neural network can not only achieve the best balance between cost and effect, but also flexibly cope with complex environments and provide an efficient and reliable optimization scheme.

[0128] In some embodiments, in step S21, the optimization of the number of sensors uses the network structure of the Primary and Secondary Convolutional Neural Networks (PasNet). The input features of the network include data such as ambient temperature, humidity, and concrete mix ratio. Through preprocessing (such as normalization), the data is split into a training set and a test set for the training and verification of the neural network.

[0129] The "primary" path in the network structure is dedicated to processing key features (such as temperature changes), while the "secondary" path processes auxiliary features (such as humidity or concrete mix ratio changes). Through convolutional operations, the network can extract and fuse these features, enhancing the learning ability for complex patterns in the data. Through model analysis, the sensor positions that have the greatest impact on the prediction results are identified, and the number and positions of the sensors are optimized accordingly, thereby improving the efficiency and economy of the monitoring system.

[0130] Finally, through training and verification, the network parameters (such as the learning rate and the size of the convolutional kernel) are adjusted to optimize the prediction accuracy of the model, ensuring the efficiency and reliability of the network during the optimization process of the number of sensors.

[0131] In some embodiments, in step S42, the embodiments of the present application introduce a cross global artificial bee colony algorithm to optimize the key parameters of the hydration heat model. This algorithm uses concrete temperature data, simulation data, and the numerical simulation data in step S1 as input features. Through the crossover operation, the population diversity is enhanced to avoid local optima, thereby improving the prediction accuracy of the model.

[0132] The optimized parameters will be used to run the hydration heat analysis model to simulate the effects of different environmental conditions and concrete ratios on the temperature drop process and temperature stress. According to the model analysis results, precise temperature control standards will be formulated, including the control of the basic temperature difference, the interlayer temperature difference, and the surface - interior temperature difference, to prevent the occurrence of structural problems such as concrete cracks. Through further data analysis, the ideal temperature drop curve will be determined, and measures such as adjusting the pouring time, modifying the ratio, or adopting specific cooling technologies will be proposed to ensure the project quality and reduce the environmental and economic costs.

[0133] In some embodiments, in step S43, a BP neural network is used for in - depth learning and short - term prediction. The BP neural network contains multiple hidden layers, and each layer can learn different abstraction levels of data, thus gradually constructing complex data representations. Especially in the prediction of concrete hydration heat, the deep learning network can outperform traditional statistical or machine learning methods and accurately predict the change trend of hydration temperature.

[0134] By collecting the concrete temperature change curve and combining simulation data, numerical simulation (physical model), and real - time data, a physical - data dual - driven dynamic prediction model is constructed using deep learning algorithms. Through a hierarchical feature extraction mechanism, this model automatically learns the advanced features of thermodynamics and chemical reactions during the concrete hydration process, accurately predicts the temperature change in real time, and serves as an important basis for issuing instructions in the automated control system, thereby realizing the transformation from passive control to active control.

[0135] In some embodiments, in step S5, the constructed digital twin platform is based on big data, cloud computing, the Internet of Things, and digital twin technology to build a virtual concrete digital twin platform that mimics the real situation. This platform uses simulation analysis data and a composite convolutional neural network to adjust the optimal layout of sensors and cooling water pipes in real time, and at the same time realizes functions such as intelligent diagnosis, control, and disposal of the operation of equipment and facilities. This digital twin platform can comprehensively monitor the construction process of mass concrete, provide monitoring, supervision, and intelligent decision - making support throughout the life cycle, and ensure the construction quality and project safety.

[0136] In some embodiments, in step S6, a temperature control solution is automatically generated by combining the monitoring and dynamic prediction results of the digital twin platform. Through the Latin Hypercube Sampling method (LHS), a temperature control sample database is constructed based on the real-time data of concrete mix proportions and hydration heat under different conditions, and a surrogate model is constructed to automatically generate the layout plan of cooling water pipes, the layout plan of sensors, and the water flow velocity control plan.

[0137] Combined with application cases under different environmental conditions, the model can provide a refined temperature control design solution and output the corresponding design diagrams, further optimizing the concrete temperature control effect and ensuring the temperature control accuracy and safety during the construction process.

[0138] Based on digital twin technology, the embodiments of this application perform adaptive control on the temperature control of the physical model through a virtual model, realizing the fusion and interaction between the virtual space and the physical space and among the various elements of concrete temperature control, promoting the implementation of advanced intelligent temperature control, directly serving the temperature control and crack prevention of concrete, and transforming the traditional passive management mode that relies on the subjective judgment and behavior of "people" for temperature control into an active management mode based on data mapping of digital twin technology to prevent the generation of temperature cracks. It enables all-weather and refined online monitoring and early warning during the concrete design and construction process, timely discovers and responds to temperature anomalies, and improves the informatization level of concrete curing work.

[0139] Embodiment 3

[0140] The embodiments of this application provide a digital twin-based concrete hydration heat adaptive control system, which is composed as Figure 4 shown, including:

[0141] A model construction unit, which is used to construct a finite element model of concrete according to preset parameters and perform hydration heat simulation, and output simulation data of temperature and temperature stress;

[0142] An arrangement generation unit, which uses a composite convolutional neural network to generate the layout plans of cooling water pipes and sensors according to the simulation data;

[0143] A real-time monitoring unit, which is responsible for arranging cooling water pipes and sensors according to the layout plan and collecting real-time data;

[0144] A prediction and analysis unit, which uses a BP neural network and a long short-term memory network to predict the temperature trend based on the simulation data and real-time data, and constructs a dynamic prediction model;

[0145] A digital twin platform unit, which uses a digital twin platform based on WebGL technology to visualize and correct the temperature and stress changes inside and on the surface of concrete, and output the corrected prediction results;

[0146] The control execution unit dynamically adjusts the water flow rate, water flow direction, and water temperature of the cooling water pipe according to the corrected prediction result to achieve the adaptive control of the hydration heat of concrete.

[0147] The composition of the system is as Figure 4 shown, including components such as a water pump, a high-power water temperature heating pipe, a wireless temperature receiving controller, a wireless temperature collector, a concrete temperature probe, and a cold water temperature probe. Through these key devices, information such as temperature data and stress data collected in real time will be automatically transmitted to the cloud platform server for centralized management and processing. Specifically, Figure 4 shows the collaborative working principle among various components - the water temperature heating pipe directly affects the hydration heat process of concrete by adjusting the water flow and temperature, while the layout scheme of the wireless temperature receiving controller and sensors ensures the comprehensiveness and accuracy of data collection.

[0148] After the data is processed by the cloud platform server, the display interface is as Figure 5 shown, which can present the temperature change trend, stress distribution map, and adjustment situation of the cooling water pipe parameters in each area in real time. Through this interface, users can visually monitor the system and correct the prediction model according to the real-time data to ensure the continuous optimization of the system. The real-time performance and intelligent decision-making ability of this platform not only improve the response speed of the temperature control system but also provide comprehensive data support for subsequent analysis and optimization, greatly enhancing the efficiency of large-scale data management.

[0149] Through Figure 4 the combination with Figure 5 , this system realizes the full-process management from data collection to real-time monitoring and then to intelligent optimization. The digital twin platform integrates physical data with the virtual space, realizes the efficient operation of the temperature control system, and provides intelligent and automated technical support for the control of the hydration heat of concrete.

[0150] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0151] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0152] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for adaptive control of concrete hydration heat based on digital twin, characterized in that: The following steps are involved: S1. Construct a finite element model of concrete according to preset parameters and perform concrete hydration heat simulation prediction, and output simulation data of temperature and temperature stress; S2. According to the simulation data, preset the layout optimization target of the cooling water pipes and sensors, and generate the layout scheme of the cooling water pipes and sensors through the composite convolutional neural network based on the layout optimization target; S3. Arrange cooling water pipes and sensors according to the arrangement scheme and collect real-time data; the real-time data includes temperature data and temperature stress data; S4. According to the simulation data and the real-time data, the BP neural network and the long short-term memory network are used to predict the temperature change trend of the concrete, and a dynamic prediction model of the concrete temperature and temperature stress is constructed to output the dynamic prediction results; S5. Based on the dynamic prediction results and the real-time data, construct a digital twin platform based on WebGL technology; The digital twin platform is used to visualize the temperature and temperature stress changes inside and on the surface of the concrete, and to correct the dynamic prediction model and output the corrected prediction results; S6. According to the corrected prediction results output by the digital twin platform, the water flow rate, water flow direction and water temperature of the cooling water pipe are dynamically adjusted to achieve adaptive control of the concrete hydration heat.

2. The method for adaptive control of concrete hydration heat based on digital twin according to claim 1, characterized in that: The preset parameters include concrete mix ratio, environmental parameters, condition parameters for concrete construction and maintenance, physical parameters and layout parameters of cooling water pipes; the environmental parameters include temperature, humidity, and wind speed.

3. The method for adaptive control of concrete hydration heat based on digital twin according to claim 2, characterized in that: Step S1 includes constructing a concrete model using WebGL technology, establishing a finite element simulation based on the model, and simulating and analyzing the change trend of the simulated temperature and temperature stress of the concrete hydration heat.

4. The method for adaptive control of concrete hydration heat based on digital twin according to claim 2, characterized in that: Step S2 includes: S21. According to the simulation data, preset the layout optimization target of the cooling water pipe and the sensor; the layout optimization target is to maximize the cooling effect and minimize the layout cost; S22. Using a composite convolutional neural network to identify the temperature distribution, with the goal of maximizing the cooling effect, generate the optimal layout of the cooling water pipes; S23. Based on the optimal layout of cooling water pipes, a composite convolutional neural network is used to generate a layout plan of sensors.

5. The method for adaptive control of concrete hydration heat based on digital twin according to claim 4 is characterized in that: Step S23 generates a sensor layout plan, including optimizing the number of sensors using a master-slave composite convolutional neural network; wherein the master path of the master-slave composite convolutional neural network processes temperature change characteristics, and the slave path processes humidity and concrete mix ratio changes.

6. The method for adaptive control of concrete hydration heat based on digital twin according to claim 5, characterized in that: Step S3 includes: S31. Arrange a wireless sensor network according to the arrangement scheme; S32. Collecting real-time data of concrete through the wireless sensor network and backing up the real-time data in a local storage device; the real-time data includes temperature data and temperature stress data; S33. Use a cyclic redundancy check method to verify the real-time data, and transmit the verified real-time data to the cloud platform server.

7. The method for adaptive control of concrete hydration heat based on digital twin according to claim 6, characterized in that: Step S4 includes: S41. Training a BP neural network according to the real-time data and the simulation data, and using the trained BP neural network to perform short-term prediction on the temperature of the concrete to obtain a short-term prediction result; S42. Input the simulation data, the real-time data and the short-term prediction results into a long short-term memory network, and output a dynamic prediction result of the temperature change trend of the concrete hydration heat in real time.

8. The method for adaptive control of concrete hydration heat based on digital twin according to claim 7, characterized in that: Step S41 also includes using a cross-global artificial bee colony algorithm to optimize key parameters of the BP neural network; the key parameters include input parameters, topological structure and initial weights.

9. A method for adaptively controlling concrete hydration heat based on digital twinning according to any one of claims 1 to 8, characterized in that: Step S6 includes: S61. Optimizing the water flow rate, water flow direction and water temperature of the cooling water pipe based on the non-dominated sorting genetic algorithm according to the real-time data and the dynamic prediction results; S62. Adjust the cold zone parameters of concrete, including temperature rise rate, temperature drop rate and maximum temperature difference.

10. A concrete hydration heat adaptive control system based on digital twin, characterized in that: When the system is running, the method described in any one of claims 1 to 9 can be implemented, including: A model building unit, used to build a finite element model of concrete according to preset parameters and perform hydration heat simulation, and output simulation data of temperature and temperature stress; A layout generation unit, which generates a layout plan of cooling water pipes and sensors according to simulation data using a composite convolutional neural network; The real-time monitoring unit is responsible for arranging cooling water pipes and sensors according to the layout plan and collecting real-time data; The prediction and analysis unit uses BP neural network and long short-term memory network to predict temperature trends based on simulation data and real-time data, and build a dynamic prediction model; The digital twin platform unit uses a digital twin platform based on WebGL technology to visualize and correct the temperature and stress changes inside and on the surface of the concrete, and output the corrected prediction results; The control execution unit dynamically adjusts the water flow rate, water flow direction and water temperature of the cooling water pipe according to the corrected prediction result to achieve adaptive control of the concrete hydration heat.

Images