A mass concrete pouring temperature control method, system, device and medium

Abstract

The application discloses a mass concrete pouring temperature control method, system, device and medium, relates to the technical field of mass concrete pouring, and comprises the following steps: constructing a pouring structure layer of mass concrete; applying a temperature boundary condition to the pouring structure layer, simulating a temperature field of the pouring structure layer based on the temperature boundary condition, and obtaining temperature distribution characteristics in the pouring structure layer; determining crack characteristics of the pouring structure layer under the action of temperature based on the temperature distribution characteristics in the pouring structure layer; adopting a pre-constructed bidirectional long-short time neural network to construct a functional relationship between the crack characteristics and the temperature distribution characteristics and pouring parameters; inputting the functional relationship, real-time temperature information and real-time crack information into an improved particle swarm algorithm for optimization; when an iteration condition is reached, outputting optimal pouring parameters of the functional relationship, and pouring the mass concrete based on the optimal pouring parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mass concrete pouring, and more particularly to a mass concrete pouring temperature control method, system, device and medium. BACKGROUND

[0002] According to the Specification for Construction of Mass Concrete GB50496-2009, mass concrete refers to mass concrete with a minimum geometric 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.

[0003] During mass concrete pouring construction, mass concrete has the characteristics of large volume, concentrated cement hydration heat release, small heat dissipation area, and rapid internal temperature rise. Therefore, during the hardening process of mass concrete, temperature cracks are likely to occur due to a large temperature difference between the inside and outside of the mass concrete. Currently, mass concrete is poured in multiple times. When the time interval between each two pouring times is long, the shrinkage of the first poured concrete structure, including temperature shrinkage and dry shrinkage, has basically been completed, and the shrinkage of the later poured concrete is strongly constrained by the first poured concrete. When the constrained concrete shrinkage exceeds the ultimate tensile stretch of the concrete, the concrete cracks. The shrinkage of mass concrete is mainly temperature shrinkage. Therefore, the current related technology mainly uses methods such as embedding cooling water pipes in the interior of the later poured concrete structure and reducing the pouring temperature of the concrete to reduce temperature shrinkage, but this method is limited by the construction conditions and environmental conditions of the construction site. It is not possible to determine the optimal pouring parameters of the circulating water pipe control system arranged in the mass concrete, which results in poor crack control effect of the mass concrete. SUMMARY

[0004] The purpose of the present application is to provide a mass concrete pouring temperature control method, system, device and medium. The present application solves the problem of poor crack control effect of the mass concrete interior provided by the conventional pouring method of the related art.

[0005] The above technical purpose of the present application is achieved by the following technical solution:

[0006] In a first aspect of the present application, a mass concrete pouring temperature control method is provided. The method comprises:

[0007] Obtaining pouring structure data of mass concrete, and constructing a pouring structure layer of the mass concrete according to the pouring structure data;

[0008] A temperature boundary condition is applied to the pouring structure layer, and a temperature field simulation of the pouring structure layer is performed based on the temperature boundary condition to obtain temperature distribution characteristics in the pouring structure layer.

[0009] Based on the temperature distribution characteristics in the pouring structure layer, the crack characteristics of the pouring structure layer under the action of temperature are determined in combination with the pouring structure layer.

[0010] A function relationship between the crack characteristics and the temperature distribution characteristics and the pouring parameters is constructed by using a pre-constructed bidirectional long-short time neural network.

[0011] The function relationship, real-time temperature information, and real-time crack information are input into an improved particle swarm algorithm for optimization, and when the iteration condition is reached, the optimal pouring parameters of the function relationship are output, and the mass concrete is poured based on the optimal pouring parameters. The improved particle swarm algorithm is obtained by optimizing the initial solution of the particle swarm algorithm by using a chaotic search strategy, and introducing an update strategy based on a normal distribution to dynamically update the particle properties of the optimized particle swarm algorithm.

[0012] In one implementation scheme, the temperature boundary condition is applied to the pouring structure layer, specifically including:

[0013] Temperature data of at least one pouring structure layer are obtained;

[0014] The temperature data are cleaned;

[0015] Temperature characteristics are extracted based on the cleaned temperature data; wherein the temperature characteristics include the average temperature of the layer, the temperature gradient of the layer, and the rate of change of temperature with time;

[0016] Based on the temperature characteristics, a measured temperature boundary of the pouring structure layer is obtained.

[0017] In one implementation scheme, the temperature field simulation of the pouring structure layer is performed based on the temperature boundary condition, specifically including:

[0018] The measured temperature boundary of the pouring structure layer is obtained, and grid processing is performed based on the measured temperature boundary to divide the pouring structure layer into a plurality of grid units;

[0019] A transient heat conduction equation of each grid unit is constructed by using a finite element method;

[0020] The transient heat conduction equation is solved to obtain the time and space distribution of the temperature field, and the temperature field simulation of the pouring structure layer is realized.

[0021] In one implementation scheme, based on the temperature distribution characteristics in the pouring structure layer, the crack characteristics of the pouring structure layer under the action of temperature are determined in combination with the pouring structure layer, specifically including:

[0022] Based on a plurality of network units of the pouring structure layer, a crack constraint model is constructed;

[0023] The temperature field is simulated to obtain the temperature distribution characteristics in the pouring structure layer as a thermal boundary condition, which is interpolated to the grid cells of the crack constraint model; if the temperature field and the crack field grid are consistent, the node temperature is directly read; if the grid is inconsistent, the bilinear interpolation is adopted to read the node temperature;

[0024] The time step of the node temperature is matched with the crack analysis time step to determine the crack characteristics of the pouring structure layer under the action of temperature.

[0025] In an implementation scheme, the expression of the function relationship is , wherein, represents the crack characteristics of the pouring structure layer, f represents the function mapping relationship, T represents the temperature distribution characteristics of the pouring structure layer, represents the flow rate of water in the circulating water pipeline, represents the water temperature of water in the circulating water pipeline.

[0026] In an implementation scheme, the expression for optimizing the inertia weight of the particle swarm algorithm by using the chaos search strategy is: ; wherein, k represents the current iteration number, K represents the maximum iteration number, represents the minimum inertia weight, represents the maximum inertia weight, represents the chaotic factor generated by the chaotic mapping function.

[0027] The second aspect of the present application provides a control system for mass concrete pouring, which comprises:

[0028] A structure data acquisition module is configured to acquire pouring structure data of the mass concrete, and construct a pouring structure layer of the mass concrete according to the pouring structure data.

[0029] A temperature distribution simulation module is configured to apply a temperature boundary condition to the pouring structure layer, and simulate a temperature field of the pouring structure layer based on the temperature boundary condition to obtain temperature distribution characteristics in the pouring structure layer.

[0030] A crack constraint determination module is configured to determine crack characteristics of the pouring structure layer under the action of temperature based on the temperature distribution characteristics in the pouring structure layer and the pouring structure layer.

[0031] A function relationship determination module is configured to construct a function relationship between the crack characteristics and the temperature distribution characteristics and the pouring parameters by using a pre-constructed bidirectional long-short term neural network.

[0032] The pouring control module is used for inputting the function relationship, real-time temperature information and real-time crack information into the improved particle swarm algorithm for optimization, and outputs the optimal pouring parameter of the function relationship when the iteration condition is reached, and pours the mass concrete based on the optimal pouring parameter.

[0033] In an implementation scheme, the temperature distribution simulation module is specifically further used for:

[0034] obtaining temperature data of at least one pouring structure layer;

[0035] performing data cleaning on the temperature data;

[0036] extracting temperature features based on the cleaned temperature data; wherein the temperature features include average temperature of the layer, temperature gradient of the layer and temperature change rate with time;

[0037] obtaining a measured temperature boundary of the pouring structure layer based on the temperature features.

[0038] The third aspect of the present application provides a computer device, comprising a processor and a memory storing a computer program, when the computer program is run by the processor, a mass concrete pouring temperature control method provided by the first aspect of the present application is executed.

[0039] The fourth aspect of the present application provides a computer readable storage medium, storing instructions, when the instructions are run on the computer, the computer executes a mass concrete pouring temperature control method provided by the first aspect of the present application.

[0040] Compared with the prior art, the present application has the following beneficial effects:

[0041] In the temperature control method for large-volume concrete pouring provided by this invention, the invention, combined with the actual situation of current layered pouring of large-volume concrete, applies temperature boundary conditions to the pouring structural layer, simulates the temperature field of the pouring structural layer based on the temperature boundary conditions, and obtains the temperature distribution characteristics within the pouring structural layer; based on the temperature distribution characteristics within the pouring structural layer, and combined with the pouring structural layer, the crack characteristics of the pouring structural layer under temperature action are determined, and a pre-constructed bidirectional long-short-time neural network is used to construct the functional relationship between crack characteristics, temperature distribution characteristics, and pouring parameters, establishing a mapping relationship between the two characteristics and the pouring parameters, which refer to the flow rate and temperature of circulating water. Thus, when each pouring structural layer is at different temperatures, the internal temperature of the large-volume concrete can be reduced by changing the flow rate and temperature of circulating water, thereby preventing the depth and width of cracks from increasing and temperature cracks from occurring. The improved particle swarm optimization (PSO) algorithm is input with functional relationships, real-time temperature information, and real-time crack information for optimization. When the iteration condition is met, the optimal pouring parameters of the functional relationship are output. Based on the optimal pouring parameters, large-volume concrete is poured. However, traditional PSO algorithms are prone to getting stuck in local optima during optimization. As a result, the final output pouring parameters cannot minimize the internal and external temperature difference and internal cracks of the large-volume concrete, thus affecting the final pouring result. Therefore, this invention uses a chaotic search strategy to optimize the initial solution of the PSO algorithm and introduces a normal distribution-based update strategy to dynamically update the particle attributes of the optimized PSO algorithm, thereby avoiding the algorithm getting stuck in local optima. Thus, the crack characteristics of the large-volume concrete under different temperature distributions can be determined. Therefore, this invention solves the problem that the conventional pouring methods provided by current related technologies have poor control effects on internal cracks in large-volume concrete. Attached Figure Description

[0042] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0043] Figure 1 A schematic flowchart of a method for controlling the temperature of large-volume concrete pouring, provided in an embodiment of the present invention;

[0044] Figure 2 This is a system block diagram of a control system for large-volume concrete pouring provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0046] It is noted that the term "include" or "may include" used in various embodiments of the present application indicates the existence of the applied function, operation, or element, and does not limit one or more functions, operations, or elements from being added. Also, as used in various embodiments of the present application, the terms "include", "have", and their conjugates merely indicate the presence of specific features, numbers, steps, operations, elements, components, or combinations thereof, and should not be construed as excluding the presence or addition of one or more other features, numbers, steps, operations, elements, components, or combinations thereof.

[0047] It is to be understood that terms such as "first", "second", etc. are used only for the purpose of description and should not be understood as indicating or implying relative importance or implying the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0048] Reference is made to Figure 1 , Figure 1 A flowchart of a large-volume concrete pouring temperature control method provided by an embodiment of the present application is shown in FIG. 1, which includes the following steps. Figure 1

[0049] S101, obtaining pouring structure data of the large-volume concrete, and constructing a pouring structure layer of the large-volume concrete according to the pouring structure data.

[0050] In the present embodiment, first, a steel reinforcement framework of the large-volume concrete pouring structure to be constructed is laid, and temperature sensors and circulation pipelines are arranged on the steel reinforcement framework. For example, a temperature sensor is arranged in a first concrete pouring structure to be poured first in the large-volume concrete pouring structure to be constructed, for detecting the temperature inside the first concrete pouring structure; a temperature sensor is arranged in a second concrete pouring structure to be poured later in the large-volume concrete pouring structure to be constructed, for detecting the temperature inside the second concrete pouring structure. Of course, as can be understood by those skilled in the art, there can also be a third concrete pouring structure, and accordingly, temperature sensors and circulation pipelines are arranged in the pouring structure layer.

[0051] S102, applying a temperature boundary condition to the pouring structure layer, and simulating a temperature field of the pouring structure layer based on the temperature boundary condition to obtain temperature distribution characteristics in the pouring structure layer.

[0052] ​In the embodiment, the temperature boundary condition refers to the internal and external temperature difference, which has two, one is the difference between the concrete center temperature and the concrete surface temperature, and the other is the difference between the concrete surface temperature and the atmospheric temperature. Therefore, by applying the temperature boundary condition to each pouring structure layer for temperature field simulation, the temperature distribution characteristics in the obtained pouring structure layer can be ensured to guarantee that the internal and external temperature difference of the concrete during pouring meets the standard, and the pouring effect is achieved.

[0053] Therefore, the temperature boundary condition is applied to the pouring structure layer, specifically: obtaining temperature data of at least one pouring structure layer; performing data cleaning on the temperature data; extracting temperature features based on the cleaned temperature data; wherein the temperature features include the average temperature of the layer, the temperature gradient of the layer, and the rate of change of temperature over time; and obtaining the measured temperature boundary of the pouring structure layer based on the temperature features.

[0054] In some embodiments, the temperature field simulation of the pouring structure layer based on the temperature boundary condition specifically includes: obtaining the measured temperature boundary of the pouring structure layer, performing grid processing based on the measured temperature boundary, dividing the pouring structure layer into a plurality of grid units; constructing a transient heat conduction equation for each grid unit using the finite element method; solving the transient heat conduction equation to obtain the spatio-temporal distribution of the temperature field, and realizing the temperature field simulation of the pouring structure layer.

[0055] S103, based on the temperature distribution characteristics in the pouring structure layer, in combination with the pouring structure layer, determining the crack characteristics of the pouring structure layer under the action of temperature.

[0056] In the embodiment, the crack characteristics of the pouring structure layer under the action of temperature mainly include the following aspects:

[0057] Surface temperature cracks are caused by the release of hydration heat in the concrete, the internal temperature rises, and the surface heat dissipation is relatively fast, forming a large internal and external temperature difference, resulting in tensile stress in the surface layer of the concrete and cracking. Such cracks are generally shallow and often occur on the surface of the concrete.

[0058] Deep or penetrating temperature cracks usually occur several months or even longer after pouring, mainly due to the existence of a large temperature difference inside the building and external restrictions, such as rigid structures of large-volume concrete foundation and wall body, etc. When the temperature decreases and shrinks, it is affected by external structural factors such as foundation and cushion, etc., resulting in a large tensile stress, which causes deep or penetrating cracks in the concrete.

[0059] The crack direction is divided into irregular direction and parallel to the short side, wherein the irregular direction refers to that the temperature crack direction is generally irregular, and the structural crack is often crisscrossed. The parallel to the short side refers to that in a beam slab structure with a large length size, cracks are mostly parallel to the short side; the temperature crack that is deep and penetrates is generally parallel or close to parallel to the short side direction, and the crack appears in sections along the long side, and is thicker in the middle.

[0060] The crack width change is obviously affected by temperature, for example, the crack width is not uniform, and is obviously affected by temperature change. The crack width is wider in winter and narrower in summer. For example, the temperature crack caused by high temperature expansion is usually thicker in the middle and thinner at both ends, and the thickness change of the cold shrinkage crack is not obvious.

[0061] The crack or the radial crack refers to that in the construction process of mass concrete or high-strength concrete, due to the large difference between the internal temperature and the surface temperature of the concrete and the external environment temperature caused by hydration heat, and the existence of constraints, the crack or the radial crack may appear. The horizontal crack, the vertical crack and the inclined crack refer to that according to different temperature field distribution and constraint conditions, the horizontal crack, the vertical crack and the inclined crack may also appear.

[0062] In some embodiments, based on the temperature distribution characteristics in the poured structure layer, the crack characteristics of the poured structure layer under the action of temperature are determined in combination with the poured structure layer, and specifically include:

[0063] Based on the plurality of network units of the poured structure layer, a crack constraint model is constructed;

[0064] The temperature distribution characteristics in the poured structure layer obtained by temperature field simulation are taken as thermal boundary conditions, and are interpolated to the grid units of the crack constraint model. If the temperature field and the crack field grid are consistent, the node temperature is directly read. If the grid is inconsistent, the node temperature is read by using bilinear interpolation;

[0065] The time step of the node temperature is matched with the crack analysis time step, and the crack characteristics of the poured structure layer under the action of temperature are determined.

[0066] In S104, a function relationship between the crack characteristics and the temperature distribution characteristics and the pouring parameters is constructed by using the bidirectional long-short time neural network constructed in advance.

[0067] In this embodiment, the bidirectional long short-term memory neural network is composed of a forward long short-term memory neural network and a backward long short-term memory neural network. The input is the input signal of the previous time, the current time and the next time, and the encoding hidden state vector of the previous time, the current time and the next time. The forward LSTM is a forward long short-term memory neural network, and the backward LSTM is a backward long short-term memory neural network. The neural network is composed of a forgetting gate, an input gate and an output gate. The bidirectional long short-term memory neural network can encode the information from backward to forward, and through the backward input of the forward sequence to the backward sequence, the simultaneous training of the two LSTMs is realized.

[0068] The expression of the function relationship is , wherein, represents the crack characteristics of the cast structure layer, f represents the function mapping relationship, T represents the temperature distribution characteristics of the cast structure layer, represents the flow rate of water in the circulating water pipeline, represents the water temperature of water in the circulating water pipeline.

[0069] The neural network is trained using a training data set containing temperature distribution characteristics, crack characteristics and pouring parameters. During the training process, the model automatically learns the relationship between different characteristics and pouring parameters, and adjusts the hyperparameters of the model, such as learning rate, regularization term, etc., to optimize the performance of the model. Adaptive learning rate optimization algorithms such as Adam optimizer can be used to improve the training efficiency and convergence speed of the model.

[0070] The trained neural network is applied to the actual pouring process to monitor the temperature distribution and crack constraint in real time, and adjust the pouring parameters according to the mapping relationship output by the model to optimize the pouring process and reduce the generation of cracks.

[0071] According to the performance of the model in practical application, the model structure and parameters are continuously optimized. More data can be collected to enrich the training set, or the hyperparameters of the model can be adjusted to improve the accuracy and reliability of the model

[0072] S105, input the function relationship, real-time temperature information and real-time crack information into the improved particle swarm optimization algorithm for optimization, output the optimal pouring parameter of the function relationship when the iteration condition is reached, and pour the mass concrete based on the optimal pouring parameter; wherein the improved particle swarm optimization algorithm is to optimize the initial solution of the particle swarm optimization algorithm by using the chaos search strategy, and introduce the update strategy based on normal distribution to dynamically update the particle properties of the optimized particle swarm optimization algorithm.

[0073] In this embodiment, the particle swarm algorithm is a kind of optimization algorithm based on swarm intelligence, which simulates the foraging behavior of bird flocks, and finds the optimal solution of the problem through information sharing and cooperation between individuals in the group. In the particle swarm algorithm, each solution is regarded as a particle in the search space, and all particles have a fitness value, which is given by the optimization function and represents the quality of the solution. Each particle also has a speed, which determines the direction and distance of the particle in the search space. The particle swarm algorithm has the advantages of fast convergence speed, few parameters, and simple algorithm (faster convergence to the optimal solution than genetic algorithm for high-dimensional optimization problems), but it also has the problem of falling into local optimal solution, so it depends on good initialization. The optimization result of the particle swarm algorithm is affected by many factors, among which the initial value of the particle has a greater impact and is more difficult to control. If the initial value of the particle is randomly initialized, the optimization result may not always converge to a global or local optimal solution, but may also get an invalid solution without changing any parameters. Therefore, particle initialization is a very important step, which relates to the speed and direction of optimization convergence in the whole optimization process. If the initialization range of the particle is selected well, the convergence time of the optimization can be greatly shortened, and it is not easy to fall into a local optimal solution. According to the specific problem, if it is judged by experience that the optimal solution must be in a certain range, then initialize the particle in this range. If it cannot be determined, the boundary of the particle value is used as the initialization range.

[0074] The optimization process of the particle swarm algorithm is a conventional technical means in the technical field, and will not be described in detail in this embodiment.

[0075] Based on the disadvantages of the current particle swarm algorithm, the following improvements are made to the particle swarm algorithm in this embodiment: first, the inertia weight of the particle swarm algorithm is optimized using a chaotic search strategy to improve the diversity of the optimization process; second, an update strategy based on normal distribution is introduced, which can dynamically adjust the optimization direction according to the quality of the initial solution during the optimization process, thereby improving the efficiency and accuracy of the optimization.

[0076] Tent mapping is an ideal choice for initializing the population due to its simplicity and high efficiency in generating chaotic sequences. The mathematical model of Tent chaotic mapping is: , represents the current iteration value, represents the next iteration value.

[0077] The expression for optimizing the inertia weight of the particle swarm algorithm using the chaotic search strategy is: ; where k represents the current iteration number, K represents the maximum iteration number, represents the minimum inertia weight, represents the maximum inertia weight, Chaotic factor generated by chaotic mapping function.

[0078] The particle properties of the optimized particle swarm algorithm are dynamically updated by introducing a normal distribution-based update strategy, where the particle properties include velocity and position.

[0079] To guide the search direction by using this feature, a particle-dependent normal distribution optimization strategy is proposed. Here, is the preferred particle, and is an adjustable standard deviation that controls the optimization direction of the particle. According to the rules of normal distribution, interval contains most of the possible values of the random variable . By properly adjusting the size of , we can ensure that most of the generated random numbers are closely around . The new strategy enhances the utilization of the algorithm, while allowing a certain range of deviation, retaining more possibilities of optimization direction.

[0080] Specifically, the expression of the next velocity of the particle of the optimized particle swarm algorithm dynamically updated by the normal distribution-based update strategy is: where and are random numbers between 0 and 1, is the velocity of the i-th particle in the d-th dimension at the k-th iteration, is the velocity of the i-th particle in the d-th dimension at the k+1-th iteration, is the position of the i-th particle in the d-th dimension at the k-th iteration, is the historical optimal position of the i-th particle in the d-th dimension at the k-th iteration, is the historical optimal position of the group in the d-th dimension at the k-th iteration, k is the iteration number, and i is the particle number, is the inertia weight, is the individual learning factor, is the group learning factor, is the particle dimension number, is a constant.

[0081] The expression of the next position of the particle is: , is the position of the i-th particle in the d-th dimension at the k+1-th iteration.

[0082] According to the output of the optimal pouring parameters, adjust the flow rate and water temperature of the circulating water pipeline to ensure that the temperature difference and cracks of mass concrete are within the optimal pouring target.

[0083] Referring to Figure 2 , Figure 2 A system block diagram of a mass concrete pouring control system provided by an embodiment of the present application is shown in Figure 2 The system comprises:

[0084] A structure data acquisition module 210 is configured to acquire pouring structure data of the mass concrete, and construct a pouring structure layer of the mass concrete according to the pouring structure data.

[0085] A temperature distribution simulation module 220 is configured to apply a temperature boundary condition to the pouring structure layer, and simulate a temperature field of the pouring structure layer based on the temperature boundary condition to obtain a temperature distribution feature in the pouring structure layer.

[0086] A crack constraint determination module 230 is configured to determine a crack feature of the pouring structure layer under the temperature action in combination with the pouring structure layer based on the temperature distribution feature in the pouring structure layer.

[0087] A function relationship determination module 240 is configured to adopt a pre-constructed bidirectional long-short term neural network to construct a function relationship between the crack feature and the temperature distribution feature and the pouring parameter.

[0088] A pouring control module 250 is configured to input the function relationship, real-time temperature information and real-time crack information into an improved particle swarm algorithm for optimization, and output an optimal pouring parameter of the function relationship when an iteration condition is reached, and pour the mass concrete based on the optimal pouring parameter. The improved particle swarm algorithm is obtained by optimizing an initial solution of the particle swarm algorithm by adopting a chaotic search strategy, and introducing an updating strategy based on a normal distribution to dynamically update particle properties of the optimized particle swarm algorithm.

[0089] The temperature distribution simulation module 220 is specifically configured to:

[0090] acquire temperature data of at least one pouring structure layer;

[0091] perform data cleaning on the temperature data;

[0092] extract a temperature feature based on the cleaned temperature data; wherein the temperature feature comprises an average temperature of a layer, a temperature gradient of the layer and a temperature change rate over time;

[0093] obtain a measured temperature boundary of the pouring structure layer based on the temperature feature.

[0094] The mass concrete pouring control system in the embodiment of the present application is used for the mass concrete pouring control system as described above. Figure 1The mass concrete pouring temperature control method shown is a technical solution based on the same inventive concept. Through the detailed description of the mass concrete pouring temperature control method provided by the above embodiment, a person skilled in the art can clearly understand the implementation process of the mass concrete pouring control system in this embodiment. Therefore, in the interest of brevity of the specification, further description is omitted here.

[0095] Correspondingly, the mass concrete pouring control system provided by the embodiment, the present application combines the actual situation of the current mass concrete layer pouring, applies the temperature boundary condition to the pouring structure layer, simulates the temperature field of the pouring structure layer based on the temperature boundary condition, and obtains the temperature distribution characteristics in the pouring structure layer; based on the temperature distribution characteristics in the pouring structure layer, in combination with the pouring structure layer, the crack characteristics of the pouring structure layer under the action of temperature are determined, the function relationship between the crack characteristics and the temperature distribution characteristics, and the pouring parameters is constructed by using the pre-constructed bidirectional long-short time neural network, and the mapping relationship between the two characteristics and the pouring parameters is established. This pouring parameter refers to the flow rate and water temperature of the circulating water. Thus, when each pouring structure layer is at different temperatures, the internal temperature of the mass concrete can be reduced by changing the flow rate and water temperature of the circulating water, so as to prevent the depth and width of the crack from becoming larger and the temperature crack from occurring. The function relationship, real-time temperature information and real-time crack information are input into the improved particle swarm optimization algorithm for optimization. When the iteration condition is reached, the optimal pouring parameter of the function relationship is output, and the mass concrete is poured based on the optimal pouring parameter. Since the traditional particle swarm optimization algorithm is prone to local optimal solution during optimization, the finally output pouring parameter cannot minimize the internal and external temperature difference and internal crack of the mass concrete, thereby affecting the final pouring result of the mass concrete. Therefore, the present application optimizes the initial solution of the particle swarm optimization algorithm by using the chaos search strategy, and introduces the updating strategy based on the normal distribution to dynamically update the particle properties of the optimized particle swarm optimization algorithm, thereby avoiding the algorithm from falling into local optimum. Thus, the crack characteristics of the mass concrete under the action of different temperature distribution characteristics can be obtained, and the present application solves the problem of poor control effect of the conventional pouring method on the internal crack of the mass concrete.

[0096] The present application also provides a computer device. The computer device includes a processor, a memory, a communication interface, and at least one communication bus for connecting the processor, the memory, and the communication interface. The memory includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (PROM), or a portable read-only memory (CD-ROM), which is used for related instructions and data.

[0097] The communication interface is configured to receive and send data. The processor can be one or more CPUs, which can be a single-core CPU or a multi-core CPU when the processor is one CPU. The processor in the electronic device is configured to read one or more programs stored in the memory and perform the following operations: obtaining pouring structure data of the mass concrete, constructing a pouring structure layer of the mass concrete according to the pouring structure data; applying a temperature boundary condition to the pouring structure layer, simulating a temperature field of the pouring structure layer based on the temperature boundary condition, and obtaining temperature distribution characteristics in the pouring structure layer; determining crack characteristics of the pouring structure layer under the temperature action based on the temperature distribution characteristics in the pouring structure layer and in combination with the pouring structure layer; constructing a functional relationship between the crack characteristics and the temperature distribution characteristics and pouring parameters by using a pre-constructed bidirectional long-short term neural network; inputting the functional relationship, real-time temperature information and real-time crack information into an improved particle swarm optimization algorithm for optimization, and outputting optimal pouring parameters of the functional relationship when an iteration condition is reached, and pouring the mass concrete based on the optimal pouring parameters; wherein the improved particle swarm optimization algorithm is obtained by optimizing the inertia weight of the particle swarm optimization algorithm by using a chaotic search strategy and introducing a normal distribution-based update strategy to dynamically update the particle properties of the optimized particle swarm optimization algorithm.

[0098] It should be noted that the specific implementation of each operation can be described above Figure 1 It should be noted that the specific implementation of each operation can be described above

[0099] The embodiment of the present application further provides a computer readable storage medium, which is a memory device in a computer device and is used for storing programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, which stores an operating system of the terminal. Furthermore, one or more instructions suitable for being loaded and executed by the processor are stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory or a non-volatile memory, for example, at least one disk memory. The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the mass concrete pouring temperature control method in the above embodiment. It should be understood by those skilled in the art that the embodiment of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can adopt a computer program product implemented on one or more computer usable storage media (including but not limited to a disk memory, a CD-ROM, an optical memory, etc.) containing computer usable program codes.

[0100] The above detailed description is further used to explain the purpose, technical scheme and beneficial effects of the present application. It should be understood that the above detailed description is only a specific embodiment of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of controlling the temperature of mass concrete placement, characterized by, The method comprises: obtaining pouring structure data of mass concrete, and constructing a pouring structure layer of the mass concrete according to the pouring structure data; applying a temperature boundary condition to the pouring structure layer, and simulating a temperature field of the pouring structure layer based on the temperature boundary condition to obtain temperature distribution characteristics in the pouring structure layer; determining crack characteristics of the pouring structure layer under the action of temperature based on the temperature distribution characteristics in the pouring structure layer and in combination with the pouring structure layer; adopting a pre-constructed bidirectional long-short time neural network to construct a functional relationship between the crack characteristics, the temperature distribution characteristics, and pouring parameters; inputting the functional relationship, real-time temperature information, and real-time crack information into an improved particle swarm optimization algorithm for optimization, and outputting optimal pouring parameters of the functional relationship when an iteration condition is reached, and pouring the mass concrete based on the optimal pouring parameters; wherein the improved particle swarm optimization algorithm is obtained by optimizing an inertia weight of the particle swarm optimization algorithm by adopting a chaotic search strategy, and introducing a normal distribution-based updating strategy to dynamically update particle properties of the optimized particle swarm optimization algorithm.

2. The mass concrete placement temperature control method of claim 1, wherein The temperature boundary condition is applied to the pouring structure layer, and specifically comprises: obtaining temperature data of at least one pouring structure layer; performing data cleaning on the temperature data; extracting temperature characteristics based on the cleaned temperature data; wherein the temperature characteristics comprise an average temperature of a layer, a temperature gradient of the layer, and a temperature change rate over time; obtaining a measured temperature boundary of the pouring structure layer based on the temperature characteristics.

3. The mass concrete placement temperature control method of claim 2, wherein The temperature field simulation of the pouring structure layer based on the temperature boundary condition specifically comprises: obtaining the measured temperature boundary of the pouring structure layer, performing grid processing based on the measured temperature boundary, dividing the pouring structure layer into a plurality of grid units, and obtaining the plurality of grid units; adopting a finite element method to construct a transient heat conduction equation of each grid unit; solving the transient heat conduction equation to obtain a temperature field spatiotemporal distribution, and realizing the temperature field simulation of the pouring structure layer.

4. The mass concrete placement temperature control method of claim 1, wherein The crack characteristics of the pouring structure layer under the action of temperature are determined based on the temperature distribution characteristics in the pouring structure layer and in combination with the pouring structure layer, and specifically comprise: constructing a crack constraint model based on a plurality of network units of the pouring structure layer; inserting the temperature distribution characteristics in the pouring structure layer obtained by the temperature field simulation as a thermal boundary condition into grid units of the crack constraint model; if the temperature field and the crack field grids are consistent, the node temperature is directly read; if the grids are inconsistent, the node temperature is read by adopting bilinear interpolation; performing time step matching on the time step of the node temperature and the crack analysis time step to determine the crack characteristics of the pouring structure layer under the action of temperature.

5. The mass concrete placement temperature control method of claim 1, wherein The expression of the function relationship is , wherein, represents the crack feature of the cast structure layer, f represents the function mapping relationship, and T represents the temperature distribution feature of the cast structure layer, represents the flow rate of water in the circulating water pipeline, represents the water temperature of water in the circulating water pipeline.

6. The mass concrete placement temperature control method of claim 1, wherein The expression for optimizing the inertia weight of the particle swarm algorithm by using the chaos search strategy is: where k represents the current iteration number, K represents the maximum iteration number, represents the minimum inertia weight, represents the maximum inertia weight, represents a chaotic factor generated by a chaotic mapping function.

7. A mass concrete placement temperature control system characterized by, The system comprises: a structure data acquisition module configured to obtain pouring structure data of mass concrete, and construct a pouring structure layer of the mass concrete according to the pouring structure data; a temperature distribution simulation module configured to apply a temperature boundary condition to the pouring structure layer, and simulate a temperature field of the pouring structure layer based on the temperature boundary condition to obtain temperature distribution characteristics in the pouring structure layer; a crack constraint determination module configured to determine crack characteristics of the pouring structure layer under the action of temperature based on the temperature distribution characteristics in the pouring structure layer and in combination with the pouring structure layer. The function relationship determining module is configured to adopt a pre-constructed bidirectional long-short time neural network to construct a function relationship among the crack feature, the temperature distribution feature and the pouring parameter; The pouring control module is configured to input the function relationship, the real-time temperature information and the real-time crack information into the improved particle swarm algorithm for optimization, and output the optimal pouring parameter of the function relationship when an iteration condition is reached, and pour the mass concrete based on the optimal pouring parameter; wherein the improved particle swarm algorithm is obtained by optimizing the initial solution of the particle swarm algorithm by adopting a chaos search strategy, and introducing a normal distribution-based updating strategy to dynamically update the particle properties of the optimized particle swarm algorithm.

8. A mass concrete placement temperature control system according to claim 7, wherein, The temperature distribution simulation module is further configured to: obtain temperature data of at least one pouring structure layer; perform data cleaning on the temperature data; extract temperature features based on the cleaned temperature data; wherein the temperature features include the average temperature of the layer, the temperature gradient of the layer and the change rate of the temperature over time; obtain a measured temperature boundary of the pouring structure layer based on the temperature features.

9. A computer device, comprising: A computer program product is provided, which includes a processor and a memory storing the computer program, and when the computer program is run by the processor, the computer program product executes the mass concrete pouring temperature control method according to any one of claims 1 to 6.

10. A computer readable storage medium, characterized in that, An instruction is stored, and when the instruction is run on a computer, the instruction causes the computer to execute the mass concrete pouring temperature control method according to any one of claims 1 to 6.

Images