Parameter inversion method and terminal equipment of mass concrete mechanism model

Abstract

The present invention belongs to the technical field of parameter inversion, and discloses a parameter inversion method and terminal equipment for a mechanism model of large-volume concrete, wherein the method comprises obtaining multiple sets of design parameter values ​​of thermal parameters to be inverted in the mechanism model of large-volume concrete; determining the design temperature value corresponding to each set of design parameter values ​​by using the mechanism model; determining the mapping relationship between the temperature of large-volume concrete and the thermal parameters to be inverted according to the multiple sets of design parameter values ​​and the corresponding design temperature values; and determining the inversion value of the thermal parameters to be inverted according to the measured temperature value and the mapping relationship. The inversion values ​​of the total adiabatic temperature rise and hydration heat coefficient of cement in the adiabatic temperature rise equation determined by the parameter inversion method for the mechanism model of large-volume concrete of the present invention can comprehensively, accurately and truly reflect the cement hydration heat process in the construction stage, ensuring that the predicted temperature of the large-volume concrete determined by the method is more accurate, thereby facilitating the adoption of corresponding temperature control measures and ensuring the construction quality of the large-volume concrete.

Description

Technical Field

[0001] The invention belongs to the technical field of parameter inversion, and specifically discloses a parameter inversion method of a large volume concrete mechanism model and a terminal device. Background Art

[0002] Mass concrete is a common structural form in modern engineering structures, and a large amount of hydration heat is generated during its pouring process. Due to the large size of the concrete structure, low thermal conductivity, construction constraints and temperature changes, temperature cracks usually appear during the construction process. Temperature cracks not only damage the beauty of the concrete structure, but also reduce the bearing capacity, safety and waterproof performance of the structure, thereby affecting its durability and service life. Effective temperature control of mass concrete is an important means to ensure the pouring quality, such as controlling temperature changes during construction to avoid large temperature changes or large temperature gradients during concrete construction. By predicting the temperature and its changes during the concrete pouring process in advance and taking corresponding temperature control measures, the construction quality of mass concrete can be guaranteed.

[0003] At present, the analytical methods for the study of temperature changes in large-volume concrete include numerical simulation methods. The large-volume concrete mechanism model constructed by numerical simulation methods reflects the temperature change law of concrete based on related heat conduction differential equations and other methods, but it simplifies the heat conduction equation, boundary conditions and external environment, and has a large deviation from the actual temperature change of concrete. In addition, there are problems such as complex model settings, huge calculation workload and long calculation running time, which makes it difficult to meet the needs of dynamic prediction of concrete temperature. In order to accurately predict the temperature change of large-volume concrete during the construction period, it is necessary to clarify the change law of hydration heat. Therefore, the selection of adiabatic temperature rise parameters of concrete is particularly critical. However, due to the influence of test conditions, construction technology, construction environment and other factors, the adiabatic temperature rise parameters selected in the design stage test have certain errors, which fail to fully, accurately and truly reflect the cement hydration heat process in the construction stage, resulting in deviations in the numerical simulation results of the temperature field and may even deviate from the actual situation. Summary of the invention

[0004] The purpose of the present invention is to provide a parameter inversion method and terminal equipment for a large-volume concrete mechanism model, so as to solve the technical problem that the adiabatic temperature rise parameters of concrete determined by the existing method are inaccurate, resulting in deviations in the numerical simulation results of the temperature field or even deviations from the actual situation.

[0005] The first aspect of the present invention discloses a parameter inversion method for a mass concrete mechanism model, comprising: obtaining multiple groups of design parameter values ​​of thermal parameters to be inverted in the mass concrete mechanism model; using the mechanism model to determine the design temperature value corresponding to each group of design parameter values; determining the mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted according to the multiple groups of design parameter values ​​and the corresponding design temperature values; and determining the inversion value of the thermal parameter to be inverted according to the measured temperature value and the mapping relationship.

[0006] Preferably, determining the mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted according to the multiple groups of design parameter values ​​and the corresponding design temperature values ​​specifically includes: constructing an inversion proxy model composed of a neural network model and a regression prediction model; taking the design temperature value as input and the design parameter value as output, training the inversion proxy model, and obtaining the mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted.

[0007] Preferably, the inversion proxy model is a Stacking ensemble model; the base learners in the Stacking ensemble model are a neural network model and a regression prediction model; and the meta learner in the Stacking ensemble model is a linear regression model.

[0008] Preferably, the neural network model is a BP neural network model; the activation function of the BP neural network model includes a steepness factor.

[0009] Preferably, the steepness factor is greater than or equal to 1.

[0010] Preferably, the regression prediction model is a correlation vector regression model with multiple target outputs constructed by combining a correlation vector regression model and a regression chain.

[0011] Preferably, the mechanism model is an adiabatic temperature rise equation; and the thermal parameters to be inverted are the total adiabatic temperature rise and hydration heat coefficient of cement.

[0012] Preferably, obtaining multiple sets of design parameter values ​​of thermal parameters to be inverted in the mechanism model of mass concrete specifically includes: respectively obtaining the value ranges of the total adiabatic temperature rise and hydration heat coefficient of cement; and sampling from the value ranges using the Latin hypercube sampling method to obtain multiple sets of design parameter values ​​of thermal parameters to be inverted.

[0013] The second aspect of the present invention discloses a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned large volume concrete mechanism model parameter inversion method when executing the computer program.

[0014] Compared with the prior art, the mass concrete mechanism model parameter inversion method and terminal device of the present invention have the following beneficial effects:

[0015] The inversion values ​​of the total adiabatic temperature rise and hydration heat coefficient of cement in the adiabatic temperature rise equation determined by the parameter inversion method of the mass concrete mechanism model of the present invention can comprehensively, accurately and truly reflect the cement hydration heat process in the construction stage, ensuring that the predicted temperature of the mass concrete determined by it is more accurate, thereby facilitating the adoption of corresponding temperature control measures to ensure the construction quality of the mass concrete.

[0016] The parameter inversion method of the mass concrete mechanism model of the present invention has the advantages of solving problems such as small samples, nonlinearity, and high dimensions, and reduces calculation time and resource consumption while ensuring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flowchart of a method for inverting parameters of a mass concrete mechanism model according to an embodiment of the present invention.

[0018] Figure 2 This is a comparison diagram of the monitoring value and the inversion value output of point A on the water-facing surface in an embodiment of the present invention.

[0019] Figure 3 This is a comparison chart of predicted values ​​and designed values ​​based on different models of total adiabatic temperature rise of cement in an embodiment of the present invention.

[0020] Figure 4 The hydration heat coefficient in the embodiment of the present invention is Comparison chart of predicted values ​​and designed values ​​of different models.

[0021] Figure 5 The hydration heat coefficient in the embodiment of the present invention is Comparison chart of predicted values ​​and designed values ​​of different models. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0023] The first aspect of the present invention provides a method for inversion of parameters of a concrete mechanism model, such as Figure 1 As shown, including:

[0024] Step 1: Obtain multiple sets of design parameter values ​​of thermal parameters to be inverted in the mass concrete mechanism model.

[0025] The mechanism model in the embodiment of the present invention is the adiabatic temperature rise equation.

[0026] The release of hydration heat is a key characteristic in the concrete curing process and is also the main cause of the formation of temperature stress cracks. There are many variables that affect the rate of hydration heat release, including the type and grade of cement, the mix ratio of concrete, and the temperature of the concrete itself. The hydration heat of cement is dependent on the age. In the early stage of concrete pouring, its change is relatively large. However, with the increase of age, the rate of change will gradually decrease. Therefore, in order to accurately predict the temperature changes during the construction period of large-volume concrete, it is necessary to clarify the change law of hydration heat. Studies have shown that the calculation results of the double exponential adiabatic temperature rise equation are consistent with the actual monitoring results. Therefore, the embodiment of the present invention uses it as the concrete adiabatic temperature rise equation, as shown in formula (1):

[0027] (1)

[0028] In the formula, for The temperature of the mass concrete at the moment; is the total adiabatic temperature rise of cement; and Both are hydration heat coefficients, which are related to the type of cement.

[0029] The adiabatic temperature rise equation in the embodiment of the present invention is run in the finite element software, so it is necessary to set the initial conditions and boundary conditions. The initial conditions involve the temperature distribution inside the mass concrete at the initial time. Generally, the temperature distribution at the initial time can be assumed to be a constant value, expressed as:

[0030] (2)

[0031] In the formula, Respectively represent the direction, Direction and direction; is the pouring temperature; is the temperature at the initial moment. In the temperature calculation process of concrete pouring block, the initial temperature is the pouring temperature; is a constant value.

[0032] The above boundary conditions involve the interaction between the surrounding environment and the concrete surface as well as the shape characteristics of the object, which can be divided into three categories.

[0033] The first type of boundary condition is that there is an accurate functional relationship between the boundary temperature of the concrete material and time, as shown in formula (3):

[0034] (3)

[0035] In the formula, for The temperature of mass concrete at all times; is the boundary temperature of concrete material and There is a functional relationship between them.

[0036] The second type of boundary condition, that is, the heat flux at the concrete material boundary can be expressed as a function of time, as shown in formula (4):

[0037] (4)

[0038] In the formula, is the pouring temperature; is the external normal direction of the concrete material boundary, and the direction of the heat flux is the same as the external normal direction; is the thermal conductivity; is the boundary temperature of concrete material and There is a functional relationship between them.

[0039] The third type of boundary condition, also known as the convection boundary condition, describes the heat transfer characteristics when a solid contacts a fluid (such as air). That is, when concrete contacts air, the heat flow on the concrete surface is proportional to its pouring temperature. and ambient temperature The difference is proportional to the mathematical expression:

[0040] (5)

[0041] In the formula, is the pouring temperature; is the external normal direction of the concrete material boundary, and the direction of the heat flux is the same as the external normal direction; is the thermal conductivity; is the heat release coefficient; when the heat release coefficient As it approaches infinity, , transformed into the first type of boundary conditions; when the heat release coefficient hour, , and then converted to adiabatic conditions. The heat release coefficient is related to the roughness of the concrete surface and the wind speed, as follows:

[0042] (6)

[0043] In the formula, The calculated wind speed.

[0044] The thermal parameter to be inverted determined in the embodiment of the present invention is the total adiabatic temperature rise of cement and hydration heat coefficient and , then multiple sets of design parameter values ​​of thermal parameters to be inverted in the mass concrete mechanism model are obtained, including:

[0045] Step 1.1: Obtain the total adiabatic temperature rise of cement and hydration heat coefficient and For example, based on engineering experience and combined with the trend of the temperature curve of the monitoring point, the value range is determined as shown in Table 1.

[0046] Table 1 Thermal parameters to be inverted and their value ranges

[0047]

[0048] Step 1.2: Use the Latin hypercube sampling method to sample from the value range to obtain multiple sets of design parameter values ​​for the thermal parameters to be inverted.

[0049] Latin Hypercube Sampling (LHS) is an efficient stratified sampling technique for generating approximately random sample points in a multidimensional parameter space. In the LHS method, the value range of each parameter is divided into several intervals of equal probability, a random value is selected in each sub-interval, and then these values ​​are combined into samples. This method achieves complete coverage of the parameter range by ensuring that the marginal distribution of each parameter is evenly stratified. The LHS method can obtain a sample set representing the entire parameter space with a small number of samples, thereby improving sampling efficiency. Therefore, the embodiment of the present invention uses the LHS method to extract parameter combination samples. Exemplarily, multiple sets of design parameter values ​​of thermal parameters to be inverted obtained using LHS are shown in Table 2.

[0050] Table 2 Design parameter values ​​of thermal parameters to be inverted

[0051]

[0052] Step 2: Use the mechanism model to determine the design temperature value corresponding to each set of design parameter values.

[0053] Based on the heat conduction theory of concrete, the "MODEL CHANGE" feature in ABAQUS software is used to simulate the layer-by-layer pouring process of concrete. In this process, all units are initially set to the "dead" state, and then the corresponding pouring layer units are gradually "activated" according to the actual order of concrete pouring. In addition, the UMATHT subroutine is secondary developed using the FORTRAN language to simulate the heat generation during cement hydration. At the same time, the FILM subroutine is used to set the heat transfer coefficient and the ambient temperature. Then, each set of design parameter values ​​in Table 2 is input into formula (1) in ABAQUS software to obtain the design temperature value corresponding to each set of design parameter values.

[0054] Step 3: According to multiple sets of design parameter values ​​and corresponding design temperature values, determine the mapping relationship between the temperature of the mass concrete and the thermal parameters to be inverted, specifically including:

[0055] Step 3.1: Construct an inversion proxy model consisting of a neural network model and a regression prediction model.

[0056] Due to its good material properties, mass concrete is widely used in construction projects. However, due to the influence of test conditions, construction technology, construction environment and other factors, the design parameter values ​​of the thermal parameters to be inverted selected in the design stage have certain errors, which fail to fully, accurately and truly reflect the cement hydration heat process in the construction stage, resulting in deviations in the numerical simulation calculation results of the temperature field, which may even deviate from the actual situation. In order to improve the accuracy of the prediction of the temperature field of mass concrete, the embodiment of the present invention constructs an inversion proxy model based on measured temperature data and a mechanism model to mine the complex nonlinear relationship between the thermal parameters to be inverted and the temperature field of mass concrete to invert and optimize the thermal parameters, thereby providing data support for the construction of subsequent fusion models.

[0057] The inversion proxy model used in the embodiment of the present invention is a Stacking ensemble model. The Stacking ensemble method is an ensemble method using a hierarchical structure, combining Boosting and Bagging. The principle is to select multiple algorithm models as base learners to mine and analyze the original data, and then output the prediction results to the meta learner for fitting.

[0058] The base learners in the Stacking ensemble model of the embodiment of the present invention are a neural network model and a regression prediction model; the meta learner in the Stacking ensemble model is a linear regression model. The embodiment of the present invention uses the neural network model to effectively handle complex nonlinear problems, and at the same time uses the robustness of the regression prediction model to improve the stability and generalization ability of the Stacking ensemble model.

[0059] The above neural network model is preferably a BP neural network model.

[0060] The advantage of BP neural network lies in its powerful nonlinear mapping ability and self-learning ability. It adjusts the network weights through the back propagation algorithm, so as to approximate any complex nonlinear relationship. However, the traditional BP neural network model also has some limitations, such as easy to fall into the local minimum, slow convergence speed, fixed learning rate and short learning memory cycle. In order to improve the accuracy, computational efficiency and stability of the algorithm, the embodiment of the present invention optimizes and improves the Sigmoid activation function of the BP neural network model.

[0061] The Sigmoid function is an S-shaped curve. There are saturation regions at both ends of its domain. In this region, the output of the network node is slow to respond to the weight adjustment. As a result, even if the network error is large, it is difficult to quickly reduce the error by adjusting the weight, thus falling into the flat area of ​​the error surface, affecting the convergence speed of the network. To solve this problem, the embodiment of the present invention uses the steepness factor , to adjust the shape of the Sigmoid function and expand the non-saturated region, as shown in formula (7). Before training begins, the steepness factor Initialized to 1, if the error value is still large but the error change is small during training, you can increase it appropriately value, such as 1.1, 1.2, etc., to leave the flat area; once you leave, you can The value is restored to the initial value. The improved method can significantly reduce the number of network iterations and improve training efficiency.

[0062] (7)

[0063] In the formula, is the input value, is the output value, is the steepness factor.

[0064] The regression prediction model in the embodiment of the present invention is a correlation vector regression model with multiple target outputs constructed by combining a correlation vector regression model and a regression chain.

[0065] Relevance Vector Machine Regression (RVR) is a model that applies Bayesian methods to statistical learning. It overcomes the shortcomings of the Support Vector Regression (SVR) model: (1) the kernel function selection must satisfy the Mercer condition; (2) the prediction results of SVM lack probabilistic expression; (3) the SVM model parameters are difficult to determine; (4) the sparsity is insufficient, etc. It also inherits the advantages of SVR in dealing with small samples, nonlinear and high-dimensional problems.

[0066] The relevant vector regression model can be expressed as follows: Assume that there is a training data set of ,in is the input vector, is the corresponding output, and both the input and output are independently distributed samples, and it is considered that for Regression function on input The noise output is:

[0067] (8)

[0068] In the formula The mean is 0 and the variance is Gaussian noise; Is the serial number.

[0069] RVR only supports a single output, but considering that the three parameters in the adiabatic temperature rise inversion are closely related to each other, it is necessary to expand RVR into a prediction model that can handle multi-target outputs. RegressorChain is a method for solving multi-output regression problems. Its principle is to create a model for each output and use the output of the previous model as input to enhance the prediction of the next model during prediction, so as to capture the correlation between different output targets. When there is a dependency between output variables, using regression chains can provide better prediction performance, so RegressorChain is combined with RVR to construct a correlation vector regression prediction model (Multiple-RVR, Multi-RVR) for multi-target outputs.

[0070] The type of kernel function is a factor that has a greater impact on the RVR prediction accuracy, which determines the distribution of sample data mapped to high-dimensional space. Common kernel functions include linear kernel function, polynomial kernel function and radial basic function (RBF). Considering the prediction accuracy and convergence speed, the embodiment of the present invention selects the radial basis function as the kernel function of RVR.

[0071] The meta-learner used in the embodiment of the present invention is a linear regression (LR) model, which is a simple linear model and can avoid overfitting.

[0072] Step 3.2: Take the design temperature value as input and the design parameter value as output, train the inversion agent model, and obtain the mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted.

[0073] In the embodiment of the present invention, the design parameter values ​​and their corresponding design temperature values ​​are taken as a group to obtain multiple groups of values, which are then divided into a training set Train_set and a test set Test_set in a ratio of 8:2 to train and verify the inversion proxy model, and obtain the mapping relationship between the temperature of the mass concrete and the thermal parameters to be inverted.

[0074] During the training process, 5-fold cross validation was used to avoid overlapping of the training samples of the base learner and the meta-learner. In each cross validation, the training data was used to train the model, and the prediction results of the validation set and the test set were obtained. Subsequently, these prediction results were used as the training set and test set of the meta-learner, and then linear regression was used as the meta-learner to continue training. After the training was completed, the mapping relationship between the temperature of the mass concrete and the thermal parameters to be inverted was obtained.

[0075] Step 4: Determine the inversion value of the thermal parameter to be inverted according to the measured temperature value and the mapping relationship.

[0076] In the embodiment of the present invention, the measured temperature value is input into the mapping relationship to obtain the corresponding total adiabatic temperature rise of cement. The inversion value and hydration heat coefficient The inversion value and hydration heat coefficient The inversion value of .

[0077] The second aspect of the present invention discloses a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned parameter inversion method of the mechanism model of large-volume concrete are implemented.

[0078] The inversion values ​​of the total adiabatic temperature rise of cement and the hydration heat coefficient in the adiabatic temperature rise equation determined by the parameter inversion method of the mass concrete mechanism model of the present invention can comprehensively, accurately and truly reflect the cement hydration heat process in the construction stage, ensuring that the predicted temperature of the mass concrete determined by it is more accurate, thereby facilitating the adoption of corresponding temperature control measures to ensure the construction quality of the mass concrete.

[0079] The effectiveness of the method of the present invention will be verified by more specific examples below.

[0080] A case analysis is conducted by taking the arc semi-gravity retaining wall on the left bank of a reservoir inlet as an example.

[0081] The semi-gravity retaining wall finite element model was established, with a total of 660,652 units and 134,548 nodes in the dam body. The third type of boundary conditions were used on the contact surface between the bedrock and the retaining wall and the air. , the calculated heat release coefficient is 63.58. The annual average temperature is 16℃. The water-cement ratio of concrete is 0.40, the sand ratio is 37, and the 28-day compressive strength is 35.9MPa. The mix ratio parameters are shown in Table 3. Take the correction coefficient , the thermal performance index parameters of concrete are calculated using the percentage weighted method. The thermal performance parameters of concrete calculated in this way are shown in Table 4.

[0082] Table 3 Concrete mix parameters

[0083]

[0084] Table 4 Thermal performance parameters of concrete

[0085]

[0086] According to the adiabatic temperature rise equation (1), the total adiabatic temperature rise of cement is selected , Heat of hydration constant and As the thermal parameters to be inverted, the value range is determined based on engineering experience and combined with the trend of the temperature curve of the monitoring point as shown in Table 1 above. The LHS method is used to extract parameter combination samples, and a total of 50 sets of samples are extracted as shown in Table 2.

[0087] Parameter inversion calculation was performed on the first layer of cast-in-place where cooling water pipes were laid. The simulation was a monitoring analysis of the retaining wall from the beginning of the first layer casting to the 15th day. By using samples with different adiabatic temperature rise parameters, the time and value of the maximum temperature inside the concrete were basically different. Taking the sample {48.48, 1.40, 1.55} as an example, its maximum temperature was 58.22°C, which occurred 52.25h after the casting was completed.

[0088] After the Stacking integrated model is trained by constructing a training set with the extracted samples and obtaining the mapping relationship between the temperature of the mass concrete and the thermal parameters to be inverted, the measured temperature value is input into the Stacking integrated model to obtain The inversion values ​​of the three parameters are input into the established finite element model, and the predicted temperature value at the monitoring point is output. The predicted temperature value is compared with the measured value for verification. Monitoring points A, B and C are all located on the first layer of the first section of the retaining wall. Monitoring point A is 0.1m away from the foundation; monitoring point B is 1.5m away from the foundation; and monitoring point C is 2.9m away from the foundation. Point B, which is located at the core position, is selected as the feature point. The measured temperature value of monitoring point B is input into the Stacking integrated model, and the inversion value of the adiabatic temperature rise parameter is obtained as shown in Table 5. The inverted parameter value is substituted into formula (1), and the temperature of point A on the water surface is re-simulated. The simulation calculation value corresponding to the inversion value output is closer to the temperature monitoring value in the actual construction environment. Figure 2 As shown in the figure, it is feasible to use the tacking integrated model to invert the parameters of the adiabatic temperature rise equation. Figure 2 The test value output is the output corresponding to the design parameter value in the embodiment of the present invention.

[0089] Table 5 Inversion values ​​of adiabatic temperature rise parameters

[0090]

[0091] Furthermore, in order to evaluate the performance of the constructed Stacking integrated model, the single models (improved BP neural network, Multi-RVR model, SVR model) were used as controls, and the correlation coefficients were selected. , mean square error and mean absolute error As a performance evaluation indicator. The correlation coefficient indicates the degree to which the regression model fits the data, and can be used to compare different models. The closer its value is to 1, the better the model fits. The mean square error indicates the mean of the sum of squares of the difference between the predicted value and the actual value, reflecting the average difference between the predicted value and the actual value. The smaller its value is, the better the model prediction effect is. The mean absolute error indicates the average of the absolute value of the difference between the predicted value and the actual value, reflecting the average deviation between the predicted value and the actual value. When the predicted value is exactly the same as the actual value, it is 0. The larger the deviation, the larger the value.

[0092] Since the SVR model is also a single-target output regression algorithm, the same processing method as RVR is used to transform it into a multi-target output regression prediction (Multi-SVR) using RegressorChain. Based on Python language, Scikit-learn library and Keras framework, inversion proxy models based on improved BP neural network, Multi-RVR, Multi-SVR and Stacking integrated model are built respectively; the train_test_split method in the scikit-learn library is used to divide the 50 groups of inversion sample data into training set and test set. The initial parameter settings of each inversion proxy model are shown in Table 6.

[0093] Table 6 Initial parameter settings of different models

[0094]

[0095] The predicted value of the inversion surrogate model for the test set is compared with the sample design value. Figures 3 to 5 As shown, it can be seen that the prediction effect of the Multi-SVR model is the worst, especially in the parameter and Its prediction value is basically in an unchanged state, while Multi-RVR has better regression prediction effect than SVR due to its sparsity and the ability to automatically update hyperparameters. The Stacking integrated model established by the present invention is consistent with the prediction performance of the improved BP neural network, Multi-RVR, and Multi-SVR. It can maintain basically the same trend as the sample design value in the three inversion parameters, and it can be seen that after combining different types of algorithms using the Stacking integration method, the prediction results of the model are greatly improved, the residual becomes smaller, and the prediction accuracy is further improved. For example, in the second group of samples, the Stacking integrated model makes the absolute error closer to 0 by fusing the prediction results of the improved BP neural network and Multi-RVR.

[0096] The performance index comparison results of the improved BP neural network, Multi-RVR, Multi-SVR and Stacking integrated model are shown in Table 7. It can be seen that except for Multi-SVR, the accuracy of the mean square error and mean absolute error of the predicted values ​​and the designed values ​​of the other three models are at the same level, and the correlation coefficient are all greater than 0.9. In general, when When it is greater than 0.8, the model is considered effective. Therefore, it can be considered that except for Multi-SVR, the other models can make accurate predictions. Compared with the improved BP neural network and Multi-RVR, the Stacking ensemble model They are 3.45% and 1.35% higher respectively, the mean square error is reduced by 1.31% and 0.78% respectively, and the mean absolute error is reduced by 3.97% and 2.90% respectively, which shows the effectiveness of the model proposed in the present invention. It also shows that the Stacking ensemble model is superior to the other four models in accuracy and is more representative and superior.

[0097] Table 7 Comparison of performance indicators of different model test sets

[0098]

[0099] The inversion values ​​of the total adiabatic temperature rise of cement and the hydration heat coefficient in the adiabatic temperature rise equation determined by the parameter inversion method of the mass concrete mechanism model of the present invention can comprehensively, accurately and truly reflect the cement hydration heat process in the construction stage, ensuring that the predicted temperature of the mass concrete determined by it is more accurate, thereby facilitating the adoption of corresponding temperature control measures to ensure the construction quality of the mass concrete.

[0100] The above are only several embodiments of the present invention and are not intended to limit the present invention in any form. Although the present invention is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present invention. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention, using the above disclosed technical content to make slight changes or modifications are equivalent to equivalent implementation cases and fall within the scope of the technical solution.

Claims

1. A method for inversion of parameters of a mass concrete mechanism model, characterized in that: include: Obtain multiple sets of design parameter values ​​of thermal parameters to be inverted in the mass concrete mechanism model; Determine the design temperature value corresponding to each set of design parameter values ​​by using the mechanism model; Determining a mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted according to the multiple sets of design parameter values ​​and the corresponding design temperature values; Determining the inversion value of the thermal parameter to be inverted according to the measured temperature value and the mapping relationship; Determining the mapping relationship between the temperature of the mass concrete and the thermal parameters to be inverted according to the multiple sets of design parameter values ​​and the corresponding design temperature values ​​specifically includes: Construct an inversion proxy model consisting of a neural network model and a regression prediction model; Taking the design temperature value as input and the design parameter value as output, training the inversion agent model, and obtaining a mapping relationship between the temperature of the mass concrete and the thermal parameter to be inverted; The inversion proxy model is a Stacking ensemble model; the base learners in the Stacking ensemble model are a neural network model and a regression prediction model; the meta learner in the Stacking ensemble model is a linear regression model; The regression prediction model is a correlation vector regression model with multiple target outputs constructed by combining a correlation vector regression model and a regression chain.

2. The method for inversion of mass concrete mechanism model parameters according to claim 1 is characterized in that: The neural network model is a BP neural network model; The activation function of the BP neural network model includes a steepness factor.

3. The method for inversion of mass concrete mechanism model parameters according to claim 2 is characterized in that: The steepness factor is greater than or equal to 1.

4. The method for inversion of mass concrete mechanism model parameters according to any one of claims 1 to 3, characterized in that: The mechanism model is an adiabatic temperature rise equation; The thermal parameters to be inverted are the total adiabatic temperature rise and hydration heat coefficient of cement.

5. The method for inversion of mass concrete mechanism model parameters according to claim 4 is characterized in that: Obtain multiple sets of design parameter values ​​for thermal parameters to be inverted in the mass concrete mechanism model, including: Obtain the value ranges of cement total adiabatic temperature rise and hydration heat coefficient respectively; The Latin hypercube sampling method is used to sample from the value range to obtain multiple groups of design parameter values ​​of the thermal parameters to be inverted.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the mass concrete mechanism model parameter inversion method as claimed in any one of claims 1 to 5 are implemented.

Images