Method, system, device and medium for predicting temperature field of concrete hydrothermalization

Abstract

The application belongs to the technical field of mass concrete quality control, and discloses a concrete hydrothermal temperature field prediction method, system, device and medium, which comprises the following steps: inputting external environment data around a formal construction section of mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model to obtain a concrete hydrothermal temperature field prediction result; wherein, based on the RBF proxy model-particle swarm algorithm, key calculation parameters in a hydrothermal temperature field calculation model are calibrated according to external environment data around a preset test section of mass concrete and temperature data of preset monitoring points, the calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model, and the pre-constructed mass concrete construction hydrothermal temperature field prediction model is obtained; and the application carries out inversion analysis based on external environment data of the preset test section of mass concrete and temperature data of the preset monitoring points, so that the accuracy and effectiveness of the prediction result are effectively ensured.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of mass concrete quality control, and particularly relates to a concrete water-heat temperature field prediction method, system, device and medium. BACKGROUND

[0002] Mass concrete is a common construction structure in civil engineering, which generally refers to mass concrete with a minimum size of not less than 1m or concrete that is expected to cause harmful cracks due to temperature changes and shrinkage caused by hydration of cementitious materials in the concrete. Due to the large block volume and complex temperature control requirements, the construction of mass concrete is difficult. If the temperature control is not proper during construction, significant temperature gradient may be generated due to hydration heat of cementitious materials, which may cause uneven internal temperature stress and further cause temperature cracks. Temperature cracks not only affect the appearance of the structure, but also greatly reduce the overall strength and durability of the structure, causing great safety hazards.

[0003] In order to improve the crack resistance of mass concrete, the mix proportion of concrete or the construction parameters are usually adjusted to achieve the purpose. When the construction parameters are optimized, the hydration heat simulation analysis of mass concrete is needed, and the construction parameters are adjusted or anti-cracking measures are added according to the simulation analysis results. In the hydration heat simulation analysis, the temperature distribution of mass concrete needs to be accurately predicted to achieve the purpose of accurate simulation analysis.

[0004] At present, in order to accurately predict the temperature distribution of mass concrete, the calculation parameters used for temperature distribution prediction are directly obtained by querying relevant specifications or indoor tests. The relevant specifications are, for example, "Mass Concrete Construction Standard" (GB50496-2018). However, the directly obtained calculation parameters lack consideration of the uncertainty factors of the construction site, resulting in low accuracy and effectiveness of the temperature distribution prediction results. In addition, the indoor construction is difficult, and the required parameters cannot be accurately obtained on the construction site. SUMMARY

[0005] In view of the technical problems in the prior art, the present application provides a concrete water-heat temperature field prediction method, system, device and medium to solve the technical problem that the accuracy and effectiveness of the temperature distribution prediction results are low due to the lack of consideration of the uncertainty factors of the construction site in the calculation parameters in the process of predicting the temperature distribution of mass concrete.

[0006] To achieve the above purpose, the technical solution adopted by the present application is as follows:

[0007] The present application provides a concrete water-heat temperature field prediction method, which comprises:

[0008] Collect the external environment data around the formal construction section of the mass concrete;

[0009] Input the external environment data around the formal construction section of the mass concrete into the pre-constructed mass concrete construction hydrothermal temperature field prediction model, and output to obtain the mass concrete hydrothermal temperature field prediction result;

[0010] The construction process of the pre-constructed mass concrete construction hydrothermal temperature field prediction model is as follows:

[0011] Collect the external environment data around the preset test section of the mass concrete and the temperature data of the preset monitoring points in the preset test section of the mass concrete;

[0012] Carry out finite element modeling on the preset test section of the mass concrete to obtain a hydrothermal temperature field calculation model;

[0013] According to the external environment data around the preset test section of the mass concrete and the temperature data of the preset monitoring points in the preset test section of the mass concrete, the key calculation parameters in the hydrothermal temperature field calculation model are calibrated based on the RBF proxy model-particle swarm algorithm, and the calibrated calculation parameters are obtained;

[0014] The calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model to obtain the pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0015] Further, the external environment data around the formal construction section of the mass concrete includes the ambient temperature data, humidity data and wind speed data around the formal construction section of the mass concrete.

[0016] Further, the external environment data around the preset test section of the mass concrete includes the ambient temperature change curve with time, the humidity change curve with time and the wind speed change curve with time around the preset test section of the mass concrete.

[0017] Further, the key calculation parameters in the hydrothermal temperature field calculation model include parameters related to the concrete heat release function and parameters affecting the concrete surface convective heat transfer coefficient.

[0018] Further, the parameters related to the concrete heat release function include the concrete adiabatic temperature rise value and the concrete heat release rate coefficient ; the parameters affecting the concrete surface convective heat transfer coefficient include the correction coefficient of the wind speed term in the surface convective heat transfer coefficient and the correction coefficient of the constant term in the surface convective heat transfer coefficient .

[0019] Further, according to the external environment data around the large-volume concrete preset test section and the temperature data of a plurality of preset monitoring points in the large-volume concrete preset test section, the key calculation parameters in the water-heat temperature field calculation model are calibrated based on the RBF proxy model-particle swarm algorithm, and the process of obtaining the calibrated calculation parameters is as follows:

[0020] A plurality of groups of key calculation parameters of the water-heat temperature field calculation model of the preset test section are randomly generated and substituted into the water-heat temperature field calculation model to obtain a plurality of initial calculation models;

[0021] The external environment data around the large-volume concrete preset test section are input into a plurality of initial calculation models, and a plurality of initial calculation modules are respectively run to predict the temperature data of the preset monitoring points, and a plurality of groups of temperature data calculation values of the preset monitoring points are obtained;

[0022] According to the temperature data calculation values of the plurality of groups of preset monitoring points and the temperature data of the preset monitoring points in the large-volume concrete preset test section, a plurality of groups of function values of preset objective functions are calculated;

[0023] The key calculation parameters of the water-heat temperature field calculation model of the plurality of groups of preset test sections and the function values of the plurality of groups of preset objective functions are substituted into the RBF radial basis function for training to obtain an RBF proxy model;

[0024] The RBF proxy model is optimized by using the particle swarm algorithm to obtain the optimal solution of the RBF proxy model;

[0025] The optimal solution of the RBF proxy model and the randomly generated solution around the optimal solution of the RBF proxy model are substituted into the water-heat temperature field calculation model of the preset test section to obtain a plurality of optimized calculation models; the plurality of optimized calculation models are re-run, and the RBF proxy model is updated according to the results of the plurality of optimized calculation models, and the iteration is repeated until convergence, and the calibrated calculation parameters are output.

[0026] Further, the preset objective function is specifically: the sum of the prediction surface deviations of all preset monitoring points.

[0027] The prediction surface deviation of the preset monitoring point is specifically:

[0028] According to the temperature data calculation value of the preset monitoring point, a prediction result curve is constructed; and according to the temperature data of the preset monitoring point in the large-volume concrete preset test section, a true result curve is constructed;

[0029] The area between the prediction result curve and the true result curve is calculated, that is, the prediction surface deviation of the preset monitoring point is obtained.

[0030] The application further provides a concrete hydrothermal temperature field prediction system, comprising:

[0031] A data acquisition module is configured to acquire external environment data around the formal construction section of the mass concrete.

[0032] A result prediction module is configured to input the external environment data around the formal construction section of the mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model, and output a concrete hydrothermal temperature field prediction result.

[0033] The pre-constructed mass concrete construction hydrothermal temperature field prediction model is constructed in the following manner:

[0034] Finite element modeling is performed on a preset test section of the mass concrete to obtain a hydrothermal temperature field calculation model of the preset test section.

[0035] External environment data around the preset test section of the mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of the mass concrete are acquired.

[0036] Based on the external environment data around the preset test section of the mass concrete and the temperature data of the preset monitoring points in the preset test section of the mass concrete, key calculation parameters in the hydrothermal temperature field calculation model of the preset test section are calibrated based on a RBF proxy model-particle swarm algorithm to obtain calibrated calculation parameters.

[0037] The calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model of the preset test section to obtain a pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0038] The application further provides a concrete hydrothermal temperature field prediction device, comprising:

[0039] A memory is configured to store a computer program.

[0040] A processor is configured to implement the steps of the concrete hydrothermal temperature field prediction method when the computer program is executed.

[0041] The application further provides a computer readable storage medium storing a computer program, wherein the computer program is configured to implement the steps of the concrete hydrothermal temperature field prediction method when executed by a processor.

[0042] Compared with the prior art, the application has the following advantages:

[0043] This invention provides a method for predicting the hydrothermal temperature field of concrete. Based on external environmental data and temperature data from pre-set monitoring points of a large-volume concrete test section, inversion analysis is performed to calibrate key calculation parameters in the hydrothermal temperature field calculation model. This ensures that the key calculation parameters fully consider the influence of environmental factors at the construction site, effectively guaranteeing the accuracy and validity of the predicted hydrothermal temperature field results. This improves the accuracy of the hydrothermal simulation analysis results for large-volume concrete, providing a basis for the design of construction parameters for large-volume concrete and ensuring its crack resistance. Secondly, the RBF surrogate model-particle swarm optimization algorithm is used for parameter calibration. This inversion analysis method, combining the RBF surrogate model and particle swarm optimization algorithm, enables rapid and efficient calibration of calculation parameters, greatly improving analysis efficiency and saving construction time. Furthermore, by obtaining the data required for the inversion analysis from the pre-set large-volume concrete test section, extensive indoor testing is unnecessary, significantly reducing the impact on the construction period. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of the concrete hydrothermal temperature field prediction method described in this invention;

[0046] Figure 2 This is a schematic diagram of the curing method for the pre-set test section of large-volume concrete in this invention;

[0047] Figure 3 This is a schematic diagram of the planar distribution of pre-set monitoring points within the pre-set test section of large-volume concrete in this invention;

[0048] Figure 4 This is a cross-sectional view of the preset monitoring points within the preset test section of the large-volume concrete in this invention;

[0049] Figure 5 This is a diagram illustrating the calculation principle of the preset objective function in this invention. Detailed Implementation

[0050] In order to make the technical problems, technical schemes and beneficial effects solved in the present application clearer, the technical schemes in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0051] As shown in the accompanying Figure 1 , the present application provides a concrete hydrothermal temperature field prediction method, comprising the following steps:

[0052] Step 1, collecting external environment data around a preset test section of mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of mass concrete; wherein the external environment data around the preset test section of mass concrete includes an environmental temperature change curve with time , a humidity change curve with time and a wind speed change curve with time ; the temperature data of a plurality of preset monitoring points of the preset test section of mass concrete includes temperature measured values of a plurality of preset monitoring points and corresponding monitoring point position information ; wherein, is the number of preset monitoring points.

[0053] In the present application, the preset test section of mass concrete is a part of the mass concrete to be constructed, and the size of the preset test section of mass concrete can be selected according to the actual situation on site; for example, for a raft foundation, a region of 3m×3m is selected as the preset test section; the position selection principle of the preset test section is as follows: a region with a large temperature change and a large risk of structural cracking, such as a variable cross-section region or a strong constraint region, is selected in the mass concrete to be constructed, but the weak link of the structure is avoided; the concrete type used in the preset test section is the same as or similar to the concrete type used in the formal construction section of the mass concrete, and the pouring and vibrating methods are the same as those in the formal construction section of the mass concrete.

[0054] The curing process of the preset test section of mass concrete is selected according to the construction conditions, such as plastic film curing, cotton felt film curing and water storage curing, and different curing methods are implemented in the preset test section according to the actual conditions; specifically, the curing process of the preset test section is as follows:

[0055] The preset test section is divided into 3×3=9 blocks according to the plane; wherein the first row of three blocks is cured by using a plastic film, the second row of three blocks is cured by using a cotton felt, and the third row of three blocks is cured by using water storage, as shown in the accompanyingFigure 2 As shown; specifically, the first block of the first row uses one layer of insulating plastic film for curing, the second block of the first row uses two layers of insulating plastic film for curing, and the third block of the first row uses three layers of insulating plastic film for curing; the first block of the second row uses one layer of insulating cotton felt for curing, the second block of the second row uses two layers of insulating cotton felt for curing, and the third block of the second row uses three layers of insulating cotton felt for curing; the first block of the third row uses 10cm of water for curing, the second block of the third row uses two layers of 15cm of water for curing, and the third block of the third row uses three layers of 20cm of water for curing.

[0056] Temperature sensors are installed at several pre-set monitoring points in the pre-set test section of the large-volume concrete to measure the change process of concrete hydration heat. Each temperature sensor serves as a pre-set monitoring point. At least three layers of temperature sensors are installed within each block: the uppermost layer is installed 10cm from the top surface of the concrete, the lowermost layer is installed 10cm from the bottom surface, and the middle layer is installed at the midpoint of the thickness direction of each block, as shown in the attached diagram. Figures 3-4 As shown; among them, attached Figure 3 , 4 Each black dot in the diagram represents one or a group of temperature sensors. It should be noted that, based on the above, additional temperature sensors can be added to each block, and the installation location of each temperature sensor can be recorded to increase the density of monitoring points for subsequent optimization and inversion analysis.

[0057] Step 2: Perform finite element modeling on the pre-set test section of large-volume concrete to obtain the finite element model of the test section; wherein, the finite element model of the test section includes the concrete structure of the pre-set test section, the existing structure around the pre-set test section and the foundation soil, and the existing structure around the pre-set test section includes pile foundation or pile cap; divide the finite element model of the test section into elements to obtain the hydrothermal temperature field calculation model; wherein, when dividing the elements, ensure that there is a node at each temperature sensor location.

[0058] Step 3: Based on the external environmental data around the pre-set test section of the large-volume concrete and the temperature data of the pre-set monitoring points within the pre-set test section of the large-volume concrete, the key calculation parameters in the hydrothermal temperature field calculation model are calibrated using the RBF proxy model-particle swarm algorithm to obtain the calibrated calculation parameters.

[0059] In this invention, the key calculation parameters in the hydrothermal temperature field calculation model include parameters related to the concrete heat release function and parameters affecting the convective heat transfer coefficient of the concrete surface; wherein, the parameters related to the concrete heat release function include the concrete adiabatic temperature rise value. and concrete heat release rate coefficient ; the parameters affecting the concrete surface heat transfer coefficient, including the correction coefficient of the wind speed term in the surface heat transfer coefficient and the correction coefficient of the constant term in the surface heat transfer coefficient .

[0060] It should be noted that the determination principle of the key calculation parameters in the hydrothermal temperature field calculation model is as follows:

[0061] The parameters affecting the calculation structure of the concrete hydration heat temperature field include the parameters related to the concrete heat release function, the parameters affecting the surface heat transfer, and the thermal parameters of the material; wherein the thermal parameters of the material mainly include the thermal conductivity and the specific heat capacity; since the thermal parameters of the material are relatively stable; therefore, the parameters related to the concrete heat release function and the parameters affecting the surface heat transfer are taken as the key calculation parameters in the hydrothermal temperature field calculation model.

[0062] When the concrete is taken as a heat source to release heat externally, the concrete adiabatic temperature rise value and the concrete heat release rate coefficient are two coefficients in the concrete heat source function; wherein the concrete heat source function is specifically:

[0063]

[0064] wherein, is the concrete heat source function.

[0065] Under different curing conditions, the concrete surface heat transfer coefficient is relatively complex, and is affected by factors such as material thickness and wind speed; in the application, the concrete surface heat transfer coefficient is designed by not considering the heat preservation and moisture retention of the concrete pile cap four around heat release coefficient, and considering the wind speed and curing measures; wherein the concrete surface heat transfer coefficient is specifically:

[0066]

[0067]

[0068] wherein, is the concrete surface heat transfer coefficient; is an intermediate variable; is the wind speed change curve with time; is the correction coefficient of the wind speed term in the surface heat transfer coefficient; is the correction coefficient of the constant term in the surface heat transfer coefficient; is the concrete pile cap four around heat release coefficient without considering heat preservation and moisture retention; is the thickness of the heat preservation material used in the curing. The thermal conductivity coefficient of the heat preservation material used for maintenance.

[0069] Specifically, based on the RBF proxy model-particle swarm algorithm, the key calculation parameters in the hydrothermal temperature field calculation model are calibrated, and the process of obtaining the calibrated calculation parameters is as follows:

[0070] Step 31, randomly generate several groups of key calculation parameters of the hydrothermal temperature field calculation model of the preset test section, and substitute them into the hydrothermal temperature field calculation model to obtain several initial calculation models.

[0071] Step 32, input the external environment data around the mass concrete preset test section as environmental parameters into the several initial calculation models, respectively run the several initial calculation modules to predict the temperature data of the preset monitoring points, and obtain several groups of temperature data calculation values of the preset monitoring points.

[0072] Step 33, according to the temperature data calculation values of the several groups of preset monitoring points and the temperature data of the preset monitoring points in the mass concrete preset test section, the function values of several groups of preset target functions are calculated; wherein the preset target function is specifically: the sum of the prediction surface deviations of all preset monitoring points.

[0073] It should be noted that the calculation process of the prediction surface deviation of each preset monitoring point is as follows: according to the temperature data calculation value of the preset monitoring point, a prediction result curve is constructed; according to the temperature data of the preset monitoring point in the mass concrete preset test section, a true result curve is constructed; wherein the construction process of the prediction result curve and the true result curve adopts to establish a rectangular coordinate system with time as the horizontal axis and temperature value as the vertical axis, and mark the temperature data calculation value or the temperature data of the preset monitoring point in the coordinate system, that is, the prediction result curve and the true result curve under the same coordinate system are obtained; according to the prediction result curve and the true result curve under the same coordinate system, the area between the prediction result curve and the true result curve is calculated, that is, the prediction surface deviation of the preset monitoring point is obtained, as shown in the accompanying drawings. Figure 5

[0074] Step 34, substitute the several groups of key calculation parameters of the hydrothermal temperature field calculation model of the preset test section and the function values of the several groups of preset target functions as training samples into the RBF radial basis function for training to obtain the RBF proxy model.

[0075] Step 35, use the particle swarm algorithm (Particle Swarm Optimization, PSO) to optimize the RBF proxy model to obtain the optimal solution of the RBF proxy model.

[0076] ​Step 36, the optimal solution of the RBF proxy model and the randomly generated solution around the optimal solution of the RBF proxy model are substituted into the hydrothermal temperature field calculation model of the preset test section to obtain a plurality of optimization calculation models; the operations of steps 32-34 are repeated, the plurality of optimization calculation models are re-run, and the RBF proxy model is updated according to the results of the plurality of optimization calculation models.

[0077] Step 37, the operations of steps 35-36 are repeated until the RBF proxy model converges, and the calibrated calculation parameters are output.

[0078] Step 4, the calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model in step 2 to obtain a pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0079] Step 5, external environment data around a formal construction section of mass concrete is collected; wherein the external environment data around the formal construction section of mass concrete includes environmental temperature data, humidity data and wind speed data around the formal construction section of mass concrete.

[0080] Step 6, the external environment data around the formal construction section of mass concrete is input into the pre-constructed mass concrete construction hydrothermal temperature field prediction model to output a concrete hydrothermal temperature field prediction result.

[0081] The concrete hydrothermal temperature field prediction method provided by the application, by constructing a numerical model of the test section through test section construction on site, taking the key calculation parameters in the hydrothermal temperature field calculation model as unknown quantities, and combining the RBF proxy model-particle swarm algorithm to optimize and calibrate the key calculation parameters in the hydrothermal temperature field calculation model, then substituting the calibrated calculation parameters into the hydrothermal temperature field calculation model to construct a pre-constructed mass concrete construction hydrothermal temperature field prediction model, finally, using the pre-constructed mass concrete construction hydrothermal temperature field prediction model to numerically simulate and predict the temperature field of the formal construction section of mass concrete; the application uses the monitoring data of the pre-set test section of mass concrete to perform inversion analysis to determine the calculation parameters, realizes accurate and efficient determination of the hydration heat analysis parameters of mass concrete, improves the accuracy of the simulation analysis results of the mass concrete hydrothermal analysis, and effectively guides the optimization of the construction scheme before mass concrete construction.

[0082] The application further provides a concrete hydrothermal temperature field prediction system, comprising a data acquisition module and a result prediction module; the data acquisition module is used for acquiring external environment data around an official construction section of mass concrete; the result prediction module is used for inputting the external environment data around the official construction section of mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model, and outputting to obtain a concrete hydrothermal temperature field prediction result; wherein, a construction process of the pre-constructed mass concrete construction hydrothermal temperature field prediction model is as follows: finite element modeling is performed on a preset test section of mass concrete to obtain a hydrothermal temperature field calculation model of the preset test section; external environment data around the preset test section of mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of mass concrete are acquired; based on the external environment data around the preset test section of mass concrete and the temperature data of the preset monitoring points in the preset test section of mass concrete, key calculation parameters in the hydrothermal temperature field calculation model of the preset test section are calibrated based on a RBF proxy model-particle swarm algorithm to obtain calibrated calculation parameters; and the calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model of the preset test section to obtain the pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0083] The application further provides a concrete hydrothermal temperature field prediction device, comprising a memory for storing a computer program and a processor for implementing steps of a concrete hydrothermal temperature field prediction method when executing the computer program.

[0084] The processor implements steps of the above-mentioned concrete hydrothermal temperature field prediction method when executing the computer program, for example: acquiring external environment data around an official construction section of mass concrete; inputting the external environment data around the official construction section of mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model, and outputting to obtain a concrete hydrothermal temperature field prediction result; wherein, a construction process of the pre-constructed mass concrete construction hydrothermal temperature field prediction model is as follows: acquiring external environment data around a preset test section of mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of mass concrete; performing finite element modeling on the preset test section of mass concrete to obtain a hydrothermal temperature field calculation model; based on the external environment data around the preset test section of mass concrete and the temperature data of the preset monitoring points in the preset test section of mass concrete, calibrating key calculation parameters in the hydrothermal temperature field calculation model based on a RBF proxy model-particle swarm algorithm to obtain calibrated calculation parameters; and substituting the calibrated calculation parameters into the hydrothermal temperature field calculation model to obtain the pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0085] Or, the processor implements the functions of the modules in the above system when executing the computer program, for example: a data acquisition module, configured to acquire external environment data around the formal construction section of the mass concrete; a result prediction module, configured to input the external environment data around the formal construction section of the mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model, and output to obtain a mass concrete construction hydrothermal temperature field prediction result; wherein, the construction process of the pre-constructed mass concrete construction hydrothermal temperature field prediction model is as follows: finite element modeling is performed on a preset test section of the mass concrete to obtain a hydrothermal temperature field calculation model of the preset test section; external environment data around the preset test section of the mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of the mass concrete are acquired; according to the external environment data around the preset test section of the mass concrete and the temperature data of the preset monitoring points in the preset test section of the mass concrete, key calculation parameters in the hydrothermal temperature field calculation model of the preset test section are calibrated based on a RBF proxy model-particle swarm algorithm to obtain calibrated calculation parameters; and the calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model of the preset test section to obtain the pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0086] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing the preset functions, which are used to describe the execution process of the computer program in the mass concrete hydrothermal temperature field prediction device.

[0087] For example, the computer program can be divided into a data acquisition module and a result prediction module, and the specific functions of each module are as follows: the data acquisition module is used for acquiring external environment data around the formal construction section of the mass concrete; the result prediction module is used for inputting the external environment data around the formal construction section of the mass concrete into a pre-constructed mass concrete construction hydrothermal temperature field prediction model, and outputting to obtain a mass concrete hydrothermal temperature field prediction result; wherein the construction process of the pre-constructed mass concrete construction hydrothermal temperature field prediction model is as follows: finite element modeling is performed on a preset test section of the mass concrete to obtain a hydrothermal temperature field calculation model of the preset test section; external environment data around the preset test section of the mass concrete and temperature data of a plurality of preset monitoring points in the preset test section of the mass concrete are acquired; according to the external environment data around the preset test section of the mass concrete and the temperature data of the preset monitoring points in the preset test section of the mass concrete, the key calculation parameters in the hydrothermal temperature field calculation model of the preset test section are calibrated based on a RBF proxy model-particle swarm algorithm to obtain calibrated calculation parameters; and the calibrated calculation parameters are substituted into the hydrothermal temperature field calculation model of the preset test section to obtain the pre-constructed mass concrete construction hydrothermal temperature field prediction model.

[0088] The concrete hydrothermal temperature field prediction device can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The concrete hydrothermal temperature field prediction device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above is an example of the concrete hydrothermal temperature field prediction device, and does not constitute a limitation on the concrete hydrothermal temperature field prediction device, and can include more components than the above, or combine certain components, or different components, for example, the concrete hydrothermal temperature field prediction device can also include an input / output device, a network access device, a bus and the like.

[0089] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The processor is the control center of the concrete hydrothermal temperature field prediction device, and is connected to each part of the concrete hydrothermal temperature field prediction device through various interfaces and lines.

[0090] The memory can be configured to store the computer programs and / or modules, and the processor realizes various functions of the concrete hydrothermal temperature field prediction device by running or executing the computer programs and / or modules stored in the memory and calling data stored in the memory.

[0091] The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data (such as audio data, a phone book, etc.) created according to the use of the mobile phone, and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0092] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the concrete hydrothermal temperature field prediction method.

[0093] The modules / units integrated in the concrete hydrothermal temperature field prediction system can be stored in a computer readable storage medium if they are realized in the form of software function units and sold or used as independent products.

[0094] Based on such understanding, the application realizes all or part of the processes of the concrete hydrothermal temperature field prediction method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer readable storage medium, and the computer program can realize the steps of the concrete hydrothermal temperature field prediction method when executed by a processor. The computer program includes computer program codes, which can be in the form of source codes, object codes, executable files or preset intermediate forms, etc.

[0095] The computer readable storage medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. that can carry the computer program codes.

[0096] It should be noted that the contents contained in the computer readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable storage medium does not include electrical carrier signals and telecommunication signals.

[0097] The prediction method provided by the application realizes calibration of key calculation parameters in the water-heat temperature field calculation model based on inversion analysis of external environment data of a preset test section of mass concrete and temperature data of preset monitoring points, ensures that the key calculation parameters in the calculation model can fully consider the influence of environmental factors on the construction site, and effectively guarantees the accuracy and effectiveness of the prediction result of the water-heat temperature field.

[0098] In the application, the acquisition of the calculation parameters can be completed without a large number of indoor tests, only test section construction is needed, and the test section is part of the structure of the mass concrete to be constructed, so the influence on the total construction period is small; since the inversion analysis is performed on the data of the test section, only the test section needs to be implemented according to the formal construction scheme, so that the obtained calculation parameters can consider the influence of various site factors on the numerical simulation, which cannot be considered by indoor tests or formula calculation; secondly, the inversion analysis method combining the proxy model and the optimization algorithm can quickly and efficiently obtain the calculation parameters, thereby greatly improving the analysis efficiency and saving the construction period.

[0099] The above embodiment is only one of the implementation manners of the technical scheme of the application, and the scope of protection of the application is not limited to the above embodiment, but also includes any changes, substitutions and other implementation manners easily thought of by those skilled in the art within the technical scope disclosed by the application.

Claims

1. A method of predicting a temperature field of a concrete hydrothermalization, characterized by, The application relates to a method for predicting a water-heat temperature field of mass concrete, and belongs to the technical field of mass concrete construction. The method comprises the following steps: collecting external environment data around a formal construction section of mass concrete; inputting the external environment data around the formal construction section of mass concrete into a pre-constructed water-heat temperature field prediction model of mass concrete construction, and outputting a water-heat temperature field prediction result of the mass concrete; wherein the construction process of the pre-constructed water-heat temperature field prediction model of mass concrete construction is as follows: collecting external environment data around a preset test section of mass concrete and temperature data of preset monitoring points in the preset test section of mass concrete; carrying out finite element modeling on the preset test section of mass concrete, and obtaining a water-heat temperature field calculation model; based on an RBF proxy model-particle swarm algorithm, calibrating key calculation parameters in the water-heat temperature field calculation model according to the external environment data around the preset test section of mass concrete and the temperature data of the preset monitoring points in the preset test section of mass concrete, and obtaining calibrated calculation parameters; substituting the calibrated calculation parameters into the water-heat temperature field calculation model, and obtaining the pre-constructed water-heat temperature field prediction model of mass concrete construction; the process of calibrating the key calculation parameters in the water-heat temperature field calculation model based on the RBF proxy model-particle swarm algorithm according to the external environment data around the preset test section of mass concrete and the temperature data of the preset monitoring points in the preset test section of mass concrete, and obtaining the calibrated calculation parameters is as follows: randomly generating several groups of key calculation parameters of the water-heat temperature field calculation model of the preset test section, and substituting the key calculation parameters into the water-heat temperature field calculation model to obtain several initial calculation models; inputting the external environment data around the preset test section of mass concrete into the several initial calculation models, respectively running the several initial calculation models to predict the temperature data of the preset monitoring points, and obtaining several groups of calculated temperature data of the preset monitoring points; calculating function values of several groups of preset objective functions according to the several groups of calculated temperature data of the preset monitoring points and the temperature data of the preset monitoring points in the preset test section of mass concrete; substituting the several groups of key calculation parameters of the water-heat temperature field calculation model of the preset test section and the function values of the several groups of preset objective functions into an RBF radial basis function for training to obtain an RBF proxy model; optimizing the RBF proxy model by using a particle swarm algorithm to obtain an optimal solution of the RBF proxy model; 2. The method of claim 1, wherein substituting the optimal solution of the RBF proxy model and randomly generated solutions around the optimal solution of the RBF proxy model into the water-heat temperature field calculation model of the preset test section to obtain several optimized calculation models; re-running the several optimized calculation models, updating the RBF proxy model according to the results of the several optimized calculation models, and iteratively circulating until convergence is achieved, and outputting the calibrated calculation parameters. The external environment data around the formal construction section of mass concrete comprises environmental temperature data, humidity data and wind speed data around the formal construction section of mass concrete.

3. The method of claim 1, wherein, The external environment data around the mass concrete preset test section includes an ambient temperature change curve over time, a humidity change curve over time, and a wind speed change curve over time around the mass concrete preset test section.

4. The method of claim 1, wherein, The key calculation parameters in the water-heat temperature field calculation model include parameters related to a concrete heat release function and parameters affecting a concrete surface convective heat transfer coefficient.

5. The method of claim 4, wherein the temperature field is a hydrothermalization temperature field. The parameters related to the concrete heat release function include concrete adiabatic temperature rise value and concrete heat release rate coefficient ; The parameter affecting the heat transfer coefficient of the concrete surface includes a correction coefficient of a wind speed term in the heat transfer coefficient of the concrete surface and a correction coefficient of a constant term in the heat transfer coefficient of the concrete surface .

6. The method of claim 1, wherein, The preset target function is specifically a sum of predicted surface deviations of all preset monitoring points. The predicted surface deviation of the preset monitoring point is specifically: According to the temperature data calculation value of the preset monitoring point, a prediction result curve is constructed; and according to the temperature data of the preset monitoring point in the mass concrete preset test section, a true result curve is constructed; The area sandwiched by the prediction result curve and the true result curve is calculated, that is, the predicted surface deviation of the preset monitoring point is obtained.

7. A system for predicting a temperature field of a concrete hydrothermalization, characterized by, It comprises: The data acquisition module is configured to acquire external environment data around the mass concrete formal construction section. The result prediction module is configured to input the external environment data around the mass concrete formal construction section into a pre-constructed mass concrete construction water-heat temperature field prediction model, and output a concrete water-heat temperature field prediction result. The construction process of the pre-constructed mass concrete construction water-heat temperature field prediction model is specifically as follows: The mass concrete preset test section is subjected to finite element modeling to obtain a water-heat temperature field calculation model of the preset test section; The external environment data around the mass concrete preset test section and the temperature data of the preset monitoring point in the mass concrete preset test section are acquired. The key calculation parameters in the water-heat temperature field calculation model are calibrated based on the RBF proxy model-particle swarm algorithm according to the external environment data around the mass concrete preset test section and the temperature data of the preset monitoring point in the mass concrete preset test section, and calibrated calculation parameters are obtained. The calibrated calculation parameters are substituted into the water-heat temperature field calculation model of the preset test section to obtain the pre-constructed mass concrete construction water-heat temperature field prediction model. The process of calibrating the key calculation parameters in the water-heat temperature field calculation model based on the RBF proxy model-particle swarm algorithm according to the external environment data around the mass concrete preset test section and the temperature data of the preset monitoring point in the mass concrete preset test section to obtain the calibrated calculation parameters is specifically as follows: A plurality of sets of key calculation parameters of the water-heat temperature field calculation model of the preset test section are randomly generated and substituted into the water-heat temperature field calculation model to obtain a plurality of initial calculation models; The external environment data around the mass concrete preset test section are input into the plurality of initial calculation models, and the plurality of initial calculation models are respectively run to predict the temperature data of the preset monitoring point, and a plurality of sets of temperature data calculation values of the preset monitoring point are obtained; A plurality of sets of function values of the preset target function are calculated according to the plurality of sets of temperature data calculation values of the preset monitoring point and the temperature data of the preset monitoring point in the mass concrete preset test section. Key calculation parameters of a hydrothermal temperature field calculation model of a plurality of groups of preset test sections and function values of a plurality of groups of preset objective functions are taken as training samples, and are substituted into a RBF radial basis function for training, to obtain a RBF surrogate model; An optimal solution of the RBF surrogate model is obtained by using a particle swarm algorithm to optimize the RBF surrogate model; The optimal solution of the RBF surrogate model and randomly generated solutions around the optimal solution of the RBF surrogate model are substituted into the hydrothermal temperature field calculation model of the preset test section, to obtain a plurality of optimization calculation models; the optimization calculation models are re-run, and the RBF surrogate model is updated according to results of the optimization calculation models, and the iteration is circularly repeated until convergence, and the calibrated calculation parameters are output.

8. A concrete hydrothermal temperature field prediction device characterized by comprising: Comprise: a memory for storing a computer program; a processor for implementing the steps of the concrete hydrothermal temperature field prediction method according to any one of claims 1-6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the steps of the concrete hydrothermal temperature field prediction method according to any one of claims 1-6.

Images