Method, device and equipment for predicting temperature of pouring area and medium

Abstract

The embodiment of the invention relates to a temperature prediction method and device for a pouring area, equipment and a medium. The method comprises the steps of obtaining sample data of a sample pouring area; training the initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used for predicting the temperature in the pouring area; obtaining index data of the to-be-detected pouring area; wherein the section of the to-be-measured pouring area is the same as that of the sample pouring area, and the index data comprises coordinates of a to-be-measured temperature measuring point in the to-be-measured pouring area after pouring, the surface temperature of the to-be-measured pouring area after pouring, material attribute data of target concrete for pouring the to-be-measured pouring area and environmental data of the to-be-measured pouring area; and inputting the index data into the temperature prediction model to obtain the predicted temperature of the to-be-measured temperature measurement point in the to-be-measured pouring area. According to the embodiment of the invention, the method achieves the automatic and intelligent prediction of the internal temperature of the pouring region, improves the prediction accuracy, and maintains the durability and stability of concrete.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, equipment and medium for predicting the temperature of a casting area. Background Art

[0002] Concrete will generate a large amount of hydration heat during the pouring process, causing the internal temperature of the concrete to rise quickly and be unevenly distributed, resulting in cracks in the concrete. Therefore, it is necessary to determine the internal temperature of the concrete during the pouring process.

[0003] In the related art, before pouring concrete, the temperature measuring points are manually determined and temperature measuring wires are buried at the temperature measuring points. After pouring, the temperature data inside the concrete is obtained through the temperature measuring wires using a thermometer. However, the deployment of the temperature measuring wires is affected by manual experience, and the accuracy of the final measured temperature is low. In addition, the temperature measuring wires are poured into the concrete and cannot be removed, which affects the durability and stability of the concrete. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a temperature prediction method, device, equipment and medium in a casting area.

[0005] The present disclosure provides a method for predicting the temperature of a casting area, comprising:

[0006] Acquire sample data of the sample pouring area; wherein the sample data includes the coordinates and internal temperature of the sample temperature measuring points in the sample pouring area after pouring, the surface temperature of the sample pouring area after pouring, the material property data of the sample concrete poured in the sample pouring area, and the environmental data of the sample pouring area;

[0007] Train the initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the pouring area;

[0008] Obtaining index data of the casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data include coordinates of the temperature measurement points to be tested in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, material property data of the target concrete cast in the casting area to be tested, and environmental data of the casting area to be tested;

[0009] The index data is input into the temperature prediction model to obtain the predicted temperature of the temperature measuring point to be measured in the casting area to be measured.

[0010] The present disclosure also provides a temperature prediction device for a casting area, comprising:

[0011] A first acquisition module is used to acquire sample data of a sample pouring area; wherein the sample data includes the coordinates and internal temperature of a sample temperature measurement point in the sample pouring area after pouring, the surface temperature of the sample pouring area after pouring, material property data of sample concrete poured in the sample pouring area, and environmental data of the sample pouring area;

[0012] A training module, used to train an initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the pouring area;

[0013] A second acquisition module is used to acquire index data of the casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data include coordinates of the temperature measurement points to be measured in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, material property data of the target concrete cast in the casting area to be tested, and environmental data of the casting area to be tested;

[0014] The prediction module is used to input the index data into the temperature prediction model to obtain the predicted temperature of the temperature measurement point to be measured in the casting area to be measured.

[0015] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the temperature prediction method of the casting area provided in the embodiment of the present disclosure.

[0016] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the temperature prediction method of the casting area provided by the embodiment of the present disclosure.

[0017] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: the temperature prediction solution for the casting area provided in the embodiments of the present disclosure, the method comprising: obtaining sample data of the sample casting area; wherein the sample data comprises the coordinates of the sample temperature measuring points in the sample casting area after casting and the internal temperature, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area; training an initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the casting area; obtaining index data of the casting area to be tested; wherein the cross-sections of the casting area to be tested and the sample casting area are the same, and the index data comprises the coordinates of the temperature measuring points in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, the material property data of the target concrete cast in the casting area to be tested, and the environmental data of the casting area to be tested; inputting the index data into the temperature prediction model to obtain the predicted temperature of the temperature measuring points in the casting area to be tested. By adopting the above technical scheme, the temperature, coordinates, material property data and environmental data of the pouring area of ​​the sample after pouring are collected, and a temperature prediction model is trained based on the above data. Based on the temperature prediction model, the temperature of the temperature measuring points in the pouring area after pouring can be predicted, thereby realizing automatic intelligent prediction of the internal temperature of the pouring area, avoiding the influence of manual experience on the predicted temperature, improving the accuracy of the prediction, and realizing temperature measurement in the pouring area without implanting temperature measuring wires, avoiding the influence of the temperature measuring wires on the concrete, and maintaining the durability and stability of the concrete. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 A schematic flow chart of a temperature prediction method for a casting area provided in an embodiment of the present disclosure;

[0021] Figure 2 A schematic diagram of the distribution of sample temperature measurement points provided in an embodiment of the present disclosure;

[0022] Figure 3 A schematic flow chart of another method for predicting temperature of a casting area provided in an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of temperature prediction of a casting area provided in an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of a temperature prediction device for a casting area provided in an embodiment of the present disclosure;

[0025] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0028] Temperature cracks will occur in concrete during the pouring process. Specifically, large-volume concrete will generate a large amount of hydration heat during the pouring process. The hydration heat causes the temperature inside the concrete to rise quickly and be unevenly distributed, resulting in a large temperature difference between the inside and outside of the concrete, causing large temperature tensile stress, and promoting the formation and development of concrete cracks. Therefore, it is of great research significance to monitor the internal temperature of large-volume concrete after pouring.

[0029] In the related art, the contact temperature measurement method is still used to obtain the internal temperature of concrete at the construction site. Specifically, before pouring concrete, the temperature measurement points are manually determined and the temperature measuring wires are manually buried at the temperature measurement points. After pouring is completed, the internal temperature data of the concrete is intermittently obtained by using a thermometer through the temperature measuring wires. However, this method of monitoring the temperature by arranging temperature measuring wires has limitations in the temperature measurement area, and the deployment of temperature measuring wires based on manual experience has a certain impact on the accuracy of the temperature, and cannot truly reflect the temperature change trend inside the overall concrete. In addition, in this type of temperature measurement method, the temperature measuring wire will be poured into the concrete together with the steel bars, and the temperature measuring wire cannot be removed. Since large-volume concrete mostly adopts a layered pouring construction method, a certain number of temperature measuring wires will be left inside each layer of concrete, which has a certain impact on the durability and stability of the concrete.

[0030] In order to solve the above problems, an embodiment of the present disclosure provides a temperature prediction method for a casting area, which is introduced below in conjunction with a specific embodiment.

[0031] Figure 1The present invention provides a flow chart of a method for predicting the temperature of a casting area according to an embodiment of the present invention. The method for predicting the temperature of a casting area can be applied to a temperature prediction device for a casting area. The temperature prediction device for a casting area can be implemented by software and / or hardware. The temperature prediction device for a casting area can generally be integrated into an electronic device. Figure 1 As shown, the temperature prediction method of the pouring area includes:

[0032] Step 101, obtaining sample data of a sample casting area; wherein the sample data includes the coordinates of a sample temperature measuring point in the sample casting area after casting and the internal temperature, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area.

[0033] Among them, the pouring area can be a range or space designated for concrete pouring operations in construction. The pouring area can be a pouring area in a preset foundation pit with a volume greater than a preset volume, and the preset foundation pit can be a foundation pit with a depth greater than a preset depth. The pouring area can be understood as a large-volume pouring area in a deep foundation pit. The sample pouring area can be used as a pouring area for obtaining sample data. The sample pouring area can be the first M pouring areas for pouring among multiple pouring areas. M can be a positive integer. The sample data can be a set of instances used to train and test the model, and the sample data can be data for which the corresponding output labels have been determined, that is, the sample data can be data containing the temperature in the pouring area.

[0034] The temperature measurement point may be a temperature measurement point. The sample temperature measurement point may be a temperature measurement point located inside the sample casting area after casting. The internal temperature may be the temperature inside the sample casting area. The surface temperature may be the temperature on the surface of the casting area, and the temperatures at different positions on the surface of the casting area may be considered to be the same surface temperature. The coordinate may be a spatial coordinate, and the coordinate may include three components, X, Y, and Z, wherein the X direction and the Y direction may be two directions on the concrete plane, and the Z direction may be a depth direction perpendicular to the concrete plane.

[0035] The sample concrete may be concrete poured in the sample pouring area. The material property data may be data characterizing the characteristics of the concrete material. The present embodiment does not limit the material property data. For example, the material property data may include but is not limited to at least one of density, specific heat capacity, and thermal conductivity. The environmental data may characterize the characteristics of the environment in which the pouring area is located. The present embodiment does not limit the environmental data. For example, the environmental data may include ambient temperature and / or humidity.

[0036] In some embodiments of the present disclosure, the sample casting area includes a sample surface area and a sample body area, and the sample temperature measuring points include a first sample temperature measuring point located in the sample surface area and a second sample temperature measuring point located in the sample body area, and the distribution density of the first sample temperature measuring point is greater than the distribution density of the second sample temperature measuring point. Among them, the sample surface area can be a portion of the sample casting area whose distance from the surface is not greater than a preset thickness, and the sample surface area can be a shell with a preset thickness. The sample body area can be a portion of the sample casting area whose distance from the surface is greater than a preset thickness, and the sample body area can be understood as the other sample casting areas except the sample surface area. The distribution density can be the number of temperature measuring points in a unit casting area.

[0037] In this embodiment, the sample casting area is divided into a shallow sample surface area and a deep sample main body area. The first sample temperature measuring points are arranged with a larger distribution density in the sample surface area, and the second sample temperature measuring points are arranged with a smaller distribution density in the sample main body area. Figure 2 A schematic diagram of the distribution of sample temperature measurement points provided in an embodiment of the present disclosure, Figure 2 In the figure, the solid rectangular box represents the sample casting area, and the dashed rectangular box inside the solid rectangular box divides the sample casting area into the sample surface area located in the shallow layer and the sample main body area located in the deep layer. The dashed unfilled circle is the first sample temperature measurement point, and the solid unfilled circle is the second sample temperature measurement point. The sample temperature measurement points can be arranged in layers according to the plane, Figure 2 The temperature measurement points of the samples arranged in one plane are shown in FIG. The first temperature measurement points of the samples are distributed in the surface area of ​​the samples, and the second temperature measurement points of the samples are distributed in the deep area of ​​the samples, and the first temperature measurement points of the samples are distributed more densely than the second temperature measurement points of the samples.

[0038] In the above scheme, the sample temperature measuring points are arranged mainly in the shallow layer and supplemented by the deep layer inside the sample pouring area. Under the same sample temperature measuring points, the temperature measurement of the shallow layer is more concentrated. After pouring, the concrete cracking in the pouring area is mostly concentrated in the shallow layer. The focus of this layout method is consistent with the concentrated cracking position of the concrete, which improves the accuracy of subsequent shallow position temperature prediction and can better avoid concrete cracking in the shallow layer.

[0039] In some embodiments of the present disclosure, the internal temperature is obtained by a contact thermometer, and the surface temperature of the sample casting area is obtained by a non-contact thermometer, and the origin position corresponding to the sample temperature measurement point is the temperature measurement point position of the non-contact thermometer. Among them, the contact thermometer can be in direct contact with the object to be measured, and measure the temperature of the object to be measured by the principle of heat conduction. The non-contact thermometer can measure the temperature of the object to be measured by measuring the thermal radiation emitted by the object to be measured without direct contact with the object to be measured. The non-contact thermometer can be an infrared thermometer.

[0040] In this embodiment, the temperature includes the internal temperature and surface temperature of the sample pouring area after the concrete is poured. The internal temperature can be obtained by using a contact thermometer. The surface temperature can be obtained by a non-contact thermometer. The non-contact thermometer can be installed at the edge of the pouring area and kept level with the concrete surface of the pouring area. The temperature acquisition frequency of the non-contact thermometer is consistent with that of the contact thermometer. In addition, the temperature measurement point position of the non-contact thermometer is used as the coordinate origin of the sample temperature measurement point to establish the spatial coordinates, and the coordinates of the sample temperature measurement point are marked in the spatial coordinate system. Figure 2 As shown in FIG. 1 , the black filled temperature measurement point is the temperature measurement point of the non-contact thermometer, and the temperature measurement point is used as the origin of the sample temperature measurement point. Thus, the calculation difficulty of subsequent coordinate-based calculation is reduced.

[0041] In the disclosed embodiments, in scenes such as underground space construction, it is necessary to cast large-volume concrete in deep foundation pits. Specifically, multiple identical casting objects in the construction area can be cast, and each casting object can be horizontally layered into multiple casting areas. In this embodiment, the first M casting areas that are cast first can be used as sample casting areas, and the material property data of the sample concrete cast in the sample casting areas can be obtained by conducting experiments on site in the construction area, and the environmental data of the environment in which the sample casting areas are located can be monitored. The temperature prediction device of the casting area obtains the material property data and the environmental data.

[0042] A temperature measuring wire is pre-arranged at the sample temperature measuring point in the sample casting area, and the internal temperature corresponding to the sample temperature measuring point is measured in a contact manner through the temperature measuring wire. The surface temperature of the sample casting area is measured by a non-contact thermometer to obtain the surface temperature of the sample casting area. The coordinates of the sample temperature measuring point are recorded with the temperature measuring point position of the non-contact thermometer as the origin.

[0043] Step 102, training an initial model based on sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the casting area.

[0044] The initial model may be a neural network model that has not been trained. The initial model may be a model with a regression prediction function, and the present embodiment does not limit the type of the initial model. For example, the initial model may be an eXtreme Gradient Boosting (XGBoost) model. The temperature prediction model may be a neural network model that has been trained.

[0045] In the disclosed embodiment, the temperature prediction device of the casting area can use the internal temperature in the sample data as the output data of the initial model, and use the other data in the sample data except the internal temperature as the input data of the initial model, train the initial model, and obtain the temperature prediction model.

[0046] Figure 3 A schematic flow chart of another method for predicting the temperature of a casting area provided in an embodiment of the present disclosure is shown in FIG. Figure 3 As shown, in some embodiments of the present disclosure, an initial model is trained according to sample data to obtain a temperature prediction model, including:

[0047] Step 301, perform stratified random sampling processing on sample data according to a preset division ratio to obtain a training data set and a test data set.

[0048] The division ratio may be a preset ratio for grouping sample data, and this embodiment does not limit the division ratio. For example, the division ratio may be 70% to 30% for the training data set and the test data set. The training data set may be a collection of sample data for training the model. The test data set may be a collection of sample data for testing the model.

[0049] In the embodiment of the present disclosure, the temperature prediction device of the pouring area can perform stratified random sampling processing on the sample data according to the pre-set division ratio according to the holdout method, and group them into a training data set and a test data set. For example, if the sample data is D, the training data set is S, and the test data set is T, then: D = S ∪ T, Therefore, the sample data is randomly divided into a training data set and a test data set, which avoids introducing additional bias in the data division process and affecting the temperature prediction model finally trained.

[0050] Step 302: Taking the initial model as the model to be processed, adjusting the model parameters of the model to be processed according to the training data set to obtain an intermediate model.

[0051] The model to be processed may be a model to be trained and tested. The intermediate model may be a model to be tested after the training of the training data set is completed.

[0052] In this embodiment, the initial model is used as the model to be processed, and the model parameters of the model to be processed are adjusted through the training data set, thereby completing the training of the model to be processed and obtaining an intermediate model to be error tested.

[0053] In some embodiments of the present disclosure, model parameters include adjustment parameters and fixed parameters. Adjustment parameters are model parameters that are dynamically adjusted during the training process of the model to be processed. Adjustment parameters include maximum tree depth layer, learning rate, number of learners, sample sub-sampling rate, column sub-sampling rate. Fixed parameters are model parameters that are fixed to default values ​​during the training process of the model to be processed. Among them, the adjustment parameters can be understood as model parameters that have a significant impact on the optimization of the model to be processed. Fixed parameters can be understood as model parameters that have a small impact on the optimization of the model to be processed.

[0054] The maximum tree depth layer can be the maximum depth that a decision tree can reach. The learning rate can be the adjustment step size of the model parameters each time the model is updated. The number of learners can be the number of decision trees contained in the model. The sample subsampling rate can represent the percentage of the training data set used to train the model to be processed in the overall training data set. For example, if the sample subsampling rate is 50%, 50% of the training data set is randomly selected from the overall training data set to train the model to be processed to establish a tree model. The column subsampling rate, also known as the column sampling rate or feature sampling rate, can represent the proportion of feature sampling when training the model to be processed.

[0055] In this embodiment, taking the extreme ladder boosting tree model as an example, in the process of training the model to be processed according to the training data set, the random search algorithm is used to optimize the adjustment parameters such as the maximum tree depth layer, learning rate, number of learners, sample subsampling rate, column subsampling rate, etc., so that the above adjustment parameters are determined to be appropriate values, and then the training of the model to be processed is completed. Specifically, the temperature prediction device of the casting area can call the random search algorithm from the function library. This embodiment does not limit the parameter setting of the random search function. For example, the number of jobs running in parallel (n_jobs) can be set to 8, the verboseness of the output information (verbose) can be set to 5, the cross-validation strategy (cv) can be set to 5 (i.e., five-fold cross validation), and the number of randomly selected parameter combinations (n_iter) can be set to 100. The initial value, end value and search step size of the adjustment parameter setting are randomly searched, and the optimal parameter search is performed. Five-fold cross validation is used by default. In addition, the fixed parameters are fixed to the default values ​​and are not adjusted with the training of the model to be processed. The model construction (xgb.XGBRegressor) module is called to build the intermediate model. In the above scheme, the adjustment parameters are adjusted while the fixed parameters are kept at the default values, which reduces the number of parameters adjusted during the model training process, improves the model training efficiency while having a smaller impact on the model performance.

[0056] Taking the extreme ladder boosting tree model as an example, the training process of the model to be processed is as follows.

[0057] The coordinates of the sample temperature measurement points in the training data set, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area are used as the characteristic values ​​of the input model to be processed, and the internal temperature in the training data set is used as the target value of the model to be processed to train the model to be processed. The extreme ladder boosting tree model can be regarded as an additive model composed of k base models. The prediction result of the internal temperature corresponding to the i-th sample data in the training data set after the t-th iteration is:

[0058]

[0059]

[0060] In the formula, k, t, and i can all be positive integers; represents the predicted value of the internal temperature of the model to be processed corresponding to the tth iteration of the i-th sample data; t represents the number of decision trees; x i represents the i-th sample data; f k (x i ) represents the kth function value of the i-th sample data in function F; f i (t-1) represents the predicted value of the first t-1 trees; f t (x i ) represents the base model of the tth iteration; Indicates the weight of the i-th sample data falling into the corresponding leaf node q.

[0061] The objective function of the model to be processed can be composed of an empirical loss term and a regularization term, so the objective function after the tth iteration can be:

[0062]

[0063] In the formula, Obj (t) represents the objective function value; P i Represents the characteristic value of the input model to be processed in the i-th sample data; It represents the predicted value of the internal temperature determined by the model to be processed corresponding to the i-th sample data iteration t times; represents the empirical loss term; T is the number of decision tree leaf nodes; γ is the penalty coefficient; λ is the regular term coefficient; is the L2 regularization term.

[0064] Step 303, input the coordinates of the sample temperature measurement points in the test data set, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area into the intermediate model to obtain the intermediate temperature output by the intermediate model.

[0065] The intermediate temperature may be the temperature of the sample temperature measurement point predicted by the intermediate model.

[0066] In this embodiment, the temperature prediction device of the pouring area can input the coordinates of the sample temperature measurement points in the test data set, the surface temperature of the sample pouring area after pouring, the material property data of the sample concrete poured in the sample pouring area, and the environmental data of the sample pouring area into the intermediate model to obtain the intermediate temperature predicted by the intermediate model based on the above data.

[0067] Step 304, calculating the evaluation index of the intermediate model according to the intermediate temperature and the internal temperature in the test data set, and if the evaluation index is within a preset index range, determining the intermediate model as a temperature prediction model.

[0068] Among them, the evaluation index can be a quantitative standard for evaluating the performance of the intermediate model. This embodiment does not limit the evaluation index. For example, the evaluation index can include one or more of the root mean square error (RMSE), the coefficient of determination (R2), and the mean absolute error (MAPE). The preset index interval can be a preset interval that characterizes the achievement of the evaluation index. The preset index area can be set according to user needs, etc., and this embodiment does not limit it.

[0069] In this embodiment, after determining the intermediate temperature, the intermediate temperature is used as the predicted value of the intermediate model, and the internal temperature in the test data set is used as the true value corresponding to the predicted value. The evaluation index of the intermediate model is calculated based on the predicted value and its corresponding true value, and it is determined whether the evaluation index is within the preset index range. If so, the intermediate model is determined as a temperature prediction model. If there is at least one evaluation index that is not within the preset index range, the intermediate model is determined as a new model to be processed, and the training of the model to be processed is continued to obtain a new intermediate model, and the evaluation index corresponding to the new intermediate model is calculated until the evaluation index is within the preset index range.

[0070] Specifically, the calculation formulas for the root mean square error, determination coefficient, and mean absolute error are as follows:

[0071]

[0072]

[0073]

[0074] Where n represents the amount of sample data in the test data set; yi Represents the internal temperature in the i-th sample data of the test data set, that is, the true value; Indicates the middle temperature corresponding to the i-th sample data of the test data set, that is, the predicted value; Represents the average value of the internal temperature in the test data set, that is, the sample mean.

[0075] In the above scheme, the sample data is divided into a training data set for training the initial model and a test data set for verifying the intermediate model that has completed the training. The generalization error of the intermediate model is estimated through the test, and the intermediate model that passes the test is determined as the temperature prediction model, thereby improving the accuracy of temperature prediction by the temperature prediction model.

[0076] Step 103, obtaining index data of the casting area to be tested; wherein the cross-sections of the casting area to be tested and the sample casting area are the same, and the index data include the coordinates of the temperature measurement points to be measured in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, the material property data of the target concrete cast in the casting area to be tested, and the environmental data of the casting area to be tested.

[0077] The pouring area to be tested may be a pouring area for which temperature prediction is to be performed. The sample pouring area may be a pouring area to be poured after the first M pouring areas among the multiple pouring areas. The index data may be data based on which the temperature prediction is performed inside the pouring area to be tested, and the index data may be data for which the output label is not determined. This embodiment does not limit the cross section, for example, the cross section may be a horizontal cross section, and the sample temperature measurement point may be a temperature measurement point located inside the pouring area to be tested after pouring. The target concrete may be the same as or different from the sample concrete.

[0078] In the disclosed embodiment, after collecting sample data from the first M pouring areas as sample pouring areas and training a temperature prediction model based on the sample data, the temperature prediction device of the pouring area can use the subsequent pouring areas as the pouring areas to be tested, and after the pouring of the pouring areas to be tested is completed, the coordinates of the temperature measurement points to be tested in the pouring areas to be tested, the surface temperature of the pouring areas to be tested, the material property data of the target concrete, the environmental data of the pouring areas to be tested and other parameters are obtained, and the above parameters are used as indicator data. Among them, the surface temperature of the pouring area to be tested can be obtained by a non-contact thermometer.

[0079] Step 104, input the index data into the temperature prediction model to obtain the predicted temperature of the temperature measuring point to be measured in the casting area to be measured.

[0080] The predicted temperature may be an estimated temperature of the pouring area to be tested at the temperature measuring point to be tested.

[0081] In the disclosed embodiment, the temperature prediction of the casting area inputs the index data of the casting area to be tested into the temperature prediction model, and the temperature prediction model performs neural network calculation to output the predicted temperature at the temperature measuring point to be tested in the casting area to be tested.

[0082] The temperature prediction method of a casting area provided by an embodiment of the present disclosure includes: obtaining sample data of a sample casting area; wherein the sample data includes the coordinates of a sample temperature measuring point in the sample casting area after casting and the internal temperature, the surface temperature of the sample casting area after casting, the material property data of a sample concrete cast in the sample casting area, and the environmental data of the sample casting area; training an initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the casting area; obtaining index data of a casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data includes the coordinates of a temperature measuring point in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, the material property data of a target concrete cast in the casting area to be tested, and the environmental data of the casting area to be tested; and inputting the index data into the temperature prediction model to obtain the predicted temperature of the temperature measuring point in the casting area to be tested. By adopting the above technical scheme, the temperature, coordinates, material property data and environmental data of the pouring area of ​​the sample after pouring are collected, and a temperature prediction model is trained based on the above data. Based on the temperature prediction model, the temperature of the temperature measuring points in the pouring area after pouring can be predicted, thereby realizing automatic intelligent prediction of the internal temperature of the pouring area, avoiding the influence of manual experience on the predicted temperature, improving the accuracy of the prediction, and realizing temperature measurement in the pouring area without implanting temperature measuring wires, avoiding the influence of the temperature measuring wires on the concrete, and maintaining the durability and stability of the concrete.

[0083] In some embodiments of the present disclosure, obtaining index data of the casting area to be tested includes: determining the accuracy of the temperature prediction model through sample data, and if the accuracy is verified, obtaining the index data of the casting area to be tested.

[0084] Specifically, in this embodiment, the temperature prediction model is verified by all the sample data. Specifically, the surface temperature of the sample casting area, the material property data of the sample concrete, the coordinates of the sample temperature measurement point, and the environmental data of the sample casting area in the sample data are used as input quantities and input into the temperature prediction model to obtain the predicted value at the coordinates of the sample temperature measurement point. The obtained predicted value is compared and analyzed with the corresponding internal temperature, and the two are compared and the deviation value is calculated. When the deviation value of more than 95% of the sample data is less than 3%, the temperature prediction model can be considered to be a valid model, and the index data of the area to be cast is obtained. Among them, the calculation formula of the deviation value is:

[0085]

[0086] Where D i Represents the deviation value of the i-th sample data, m i is the predicted value of the i-th sample data, n i Represents the internal temperature of the i-th sample data.

[0087] In the above scheme, after the temperature prediction model is obtained through sample data training, the temperature prediction model is verified through the overall sample data to ensure the accuracy of the temperature prediction model on the sample data.

[0088] In some embodiments of the present disclosure, before training the initial model according to the sample data to obtain the temperature prediction model, the temperature prediction method of the casting area further includes:

[0089] Determine the data mean and data standard deviation corresponding to each category of the sample data; take each category as a category to be processed, and for each sample data under the category to be processed, standardize the sample data according to the data mean and data standard deviation corresponding to the category to be processed to obtain standardized data, and use the standardized data to replace the sample data.

[0090] Among them, the category can be the basic data classification dimension in the sample data, and the category can include the surface temperature of the sample casting area, the material density of the sample concrete, the specific heat capacity of the sample concrete, the thermal conductivity of the sample concrete, the X coordinate of the sample temperature measurement point, the Y coordinate of the sample temperature measurement point, the Z coordinate of the sample temperature measurement point, the ambient temperature, the ambient humidity, and the internal temperature of the sample temperature measurement point. The data mean can be the average value of the data. The standard deviation can be used to characterize the degree of dispersion of the data.

[0091] In this embodiment, the temperature prediction device of the pouring area can pre-process the sample data, specifically, record the sample data in columns. Each column records the collection interval, the surface temperature of the sample pouring area, the material density of the sample concrete, the specific heat capacity of the sample concrete, the thermal conductivity of the sample concrete, the X coordinate of the sample temperature measurement point, the Y coordinate of the sample temperature measurement point, the Z coordinate of the sample temperature measurement point, the ambient temperature, the ambient humidity, and the internal temperature of the sample temperature measurement point.

[0092] Each column records a category of data. For each column of data, the corresponding data mean and data standard deviation are calculated. For each sample data in each column, the sample data is standardized according to the data mean and data standard deviation corresponding to the column where the sample data is located to obtain standardized data, and the standardized data is used to replace the sample data for subsequent processing.

[0093] The standardization method for sample data is as follows:

[0094]

[0095] In the formula, μ i With σ i As the data mean and data standard deviation of the category corresponding to the i-th sample data, x i is the value of the i-th sample data, x' i is the standardized data corresponding to the i-th sample data.

[0096] In the above scheme, the data is standardized to eliminate the impact caused by different value ranges of data of different categories, thereby improving the convergence efficiency of the subsequent temperature prediction model.

[0097] In some embodiments of the present disclosure, the temperature prediction method of the casting area further includes:

[0098] The outlet temperature of the next pouring area is determined according to the predicted temperature; wherein the next pouring area is the pouring area after the pouring area to be tested, and the next pouring area and the pouring area to be tested belong to the same pouring object; the outlet temperature is sent to the temperature control unit of the concrete conveying equipment, so that the temperature control unit controls the concrete conveying equipment to output concrete of the outlet temperature.

[0099] The outlet temperature is also called the discharge temperature, and the outlet temperature may be the temperature of concrete when it is output from the concrete conveying equipment. The outlet temperature is approximately the temperature of concrete for pouring the next pouring area. The pouring object may be an object to be poured with concrete, and this embodiment does not limit the pouring object, for example, the pouring object may be a column, etc. This embodiment does not limit the concrete conveying equipment, for example, the concrete conveying equipment may be a concrete delivery vehicle.

[0100] In the disclosed embodiment, a layered pouring method is used to construct the pouring object. A pouring object can be divided into multiple pouring areas. The pouring area that has completed pouring can be the pouring area to be tested, and the pouring area that is currently pouring can be the next pouring area. After determining the predicted temperature of the sample temperature measuring points of the pouring area to be tested, the temperature prediction of the pouring area can determine the average value of the predicted temperature, query the preset temperature relationship based on the average value, and determine the outlet temperature corresponding to the average value. Alternatively, the temperature prediction of the pouring area can determine the maximum value of the predicted temperature, query the preset temperature relationship based on the maximum value, and determine the outlet temperature corresponding to the average value. Among them, the temperature relationship can record the corresponding relationship between the average value of the predicted temperature and the outlet temperature, or the corresponding relationship between the maximum value of the predicted temperature and the outlet temperature.

[0101] After the outlet temperature is determined, the outlet temperature is fed back to the temperature control unit of the concrete conveying equipment. After receiving the outlet temperature, the temperature control unit controls the concrete temperature output by the concrete conveying equipment to be the outlet temperature.

[0102] In the above scheme, the subsequent concrete outlet temperature is automatically adjusted according to the predicted temperature of the pouring area to be tested, and the pouring area currently being poured is affected according to the pouring area that has completed pouring, thereby realizing closed-loop concrete temperature control and avoiding the formation of cracks due to large temperature differences inside the concrete.

[0103] In addition, the temperature prediction device of the pouring area can also construct a temperature field of the pouring area to be tested according to the predicted temperature, determine the temperature attenuation law inside the concrete according to the temperature field, or determine the part to be insulated in the pouring area to be tested according to the temperature field, generate reminder information according to the part to be insulated, and remind the user to construct corresponding insulation measures. Corresponding maintenance measures are formulated through the temperature field.

[0104] Figure 4 A schematic diagram of temperature prediction of a casting area provided by an embodiment of the present disclosure, such as Figure 4 As shown, in this implementation, sample data such as the internal temperature, the surface temperature of the casting area to be tested, the material property data of the target concrete, the coordinates of the sample temperature measurement points, and the environmental data of the casting area to be tested are obtained. The sample data is subjected to data standardization, and the sample data after standardization is divided into a training data set and a test data set. The model parameters are optimized based on the extreme ladder boosting tree model to obtain a temperature prediction model for the evaluation index test, and the accuracy of the temperature prediction model is verified. If the verification is passed, the predicted temperature of the casting area to be tested is determined by the temperature prediction model, and the temperature field of the casting area to be tested is determined according to the predicted temperature, and the construction control such as cooling of the unfinished unbuilt project is carried out according to the temperature field.

[0105] The temperature prediction method for the pouring area provided in the embodiment of the present disclosure performs temperature prediction and performs the same construction control based on the temperature prediction, thereby avoiding the formation of cracks due to large temperature differences inside the concrete, and performing temperature prediction by means of a neural network avoids the problem of the temperature measuring wire being buried inside the concrete and unable to be removed, thereby reducing the impact of uncontrollable factors on the construction quality. The quality of concrete pouring construction is effectively guaranteed, construction costs are further reduced, and construction efficiency is improved.

[0106] Figure 5 The present invention provides a schematic diagram of a device for predicting the temperature of a casting area according to an embodiment of the present invention. The device can be implemented by software and / or hardware, or integrated in an electronic device. Figure 5 As shown, the temperature prediction device of the pouring area includes:

[0107] The first acquisition module 501 is used to acquire sample data of a sample pouring area; wherein the sample data includes the coordinates and internal temperature of a sample temperature measurement point in the sample pouring area after pouring, the surface temperature of the sample pouring area after pouring, material property data of sample concrete poured in the sample pouring area, and environmental data of the sample pouring area;

[0108] A training module 502 is used to train an initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the pouring area;

[0109] The second acquisition module 503 is used to acquire index data of the casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data include the coordinates of the temperature measurement points to be measured in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, the material property data of the target concrete cast in the casting area to be tested, and the environmental data of the casting area to be tested;

[0110] The prediction module 504 is used to input the index data into the temperature prediction model to obtain the predicted temperature of the temperature measurement point to be measured in the casting area to be measured.

[0111] Optionally, the sample casting area includes a sample surface area and a sample main body area, the sample temperature measurement points include a first sample temperature measurement point located in the sample surface area and a second sample temperature measurement point located in the sample main body area, and the distribution density of the first sample temperature measurement points is greater than the distribution density of the second sample temperature measurement points.

[0112] Optionally, the internal temperature is obtained by a contact thermometer, the surface temperature of the sample casting area is obtained by a non-contact thermometer, and the origin position corresponding to the sample temperature measurement point is the temperature measurement point position of the non-contact thermometer.

[0113] Optionally, the temperature prediction device of the casting area further includes:

[0114] A determination module, used for determining a data mean and a data standard deviation corresponding to each category of the sample data before training an initial model according to the sample data to obtain a temperature prediction model;

[0115] The standardization module is used to treat each category as a category to be processed, and for each sample data under the category to be processed, the sample data is standardized according to the data mean and the data standard deviation corresponding to the category to be processed to obtain standardized data, and the standardized data is used to replace the sample data.

[0116] Optionally, the training module 502 is used to:

[0117] Performing stratified random sampling on the sample data according to a preset division ratio to obtain a training data set and a test data set;

[0118] Taking the initial model as the model to be processed, adjusting the model parameters of the model to be processed according to the training data set to obtain an intermediate model;

[0119] Input the coordinates of the sample temperature measurement points in the test data set, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area into the intermediate model to obtain the intermediate temperature output by the intermediate model;

[0120] An evaluation index of the intermediate model is calculated according to the intermediate temperature and the internal temperature in the test data set, and if the evaluation index is within a preset index range, the intermediate model is determined as the temperature prediction model.

[0121] Optionally, the model parameters include adjustment parameters and fixed parameters. The adjustment parameters are model parameters that are dynamically adjusted during the training process of the model to be processed. The adjustment parameters include the maximum tree depth layer, learning rate, number of learners, sample subsampling rate, and column subsampling rate. The fixed parameters are model parameters that are fixed to default values ​​during the training process of the model to be processed.

[0122] Optionally, the temperature prediction device of the casting area further includes:

[0123] A temperature module, used to determine the outlet temperature of the next pouring area according to the predicted temperature; wherein the next pouring area is the pouring area after the pouring area to be tested, and the next pouring area and the pouring area to be tested belong to the same pouring object;

[0124] The sending module is used to send the outlet temperature to the temperature control unit of the concrete conveying equipment, so that the temperature control unit controls the concrete conveying equipment to output concrete with the outlet temperature.

[0125] The temperature prediction device for the casting area provided in the embodiment of the present disclosure can execute the temperature prediction method for the casting area provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0126] Figure 6 The structure diagram of an electronic device provided by the embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the electronic device 600 includes one or more processors 601 and a memory 602 .

[0127] The processor 601 may be a central processing unit (CPU) or other forms of processing units having temperature prediction capability and / or instruction execution capability of a pouring area, and may control other components in the electronic device 600 to perform desired functions.

[0128] The memory 602 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 601 may run the program instructions to implement the temperature prediction method for the pouring area of ​​the embodiment of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0129] In one example, the electronic device 600 may further include: an input device 603 and an output device 604 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0130] In addition, the input device 603 may also include, for example, a keyboard, a mouse, and the like.

[0131] The output device 604 can output various information to the outside, including the determined distance information, direction information, etc. The output device 604 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0132] Of course, to simplify, Figure 6 Only some of the components related to the present disclosure in the electronic device 600 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 600 may also include any other appropriate components.

[0133] In addition to the above methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the temperature prediction method for the casting area provided by the embodiments of the present disclosure.

[0134] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0135] In addition, the embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the processor executes the temperature prediction method for the casting area provided by the embodiment of the present disclosure.

[0136] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0137] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0138] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting temperature in a casting area, characterized in that: include: Acquire sample data of the sample pouring area; wherein the sample data includes the coordinates and internal temperature of the sample temperature measuring points in the sample pouring area after pouring, the surface temperature of the sample pouring area after pouring, the material property data of the sample concrete poured in the sample pouring area, and the environmental data of the sample pouring area; Train the initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the pouring area; Obtaining index data of the casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data include coordinates of the temperature measurement points to be tested in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, material property data of the target concrete cast in the casting area to be tested, and environmental data of the casting area to be tested; The index data is input into the temperature prediction model to obtain the predicted temperature of the temperature measuring point to be measured in the casting area to be measured.

2. The method according to claim 1, characterized in that The sample casting area includes a sample surface area and a sample main body area, the sample temperature measuring points include a first sample temperature measuring point located in the sample surface area and a second sample temperature measuring point located in the sample main body area, and the distribution density of the first sample temperature measuring points is greater than the distribution density of the second sample temperature measuring points.

3. The method according to claim 1, characterized in that: The internal temperature is obtained by a contact thermometer, the surface temperature of the sample casting area is obtained by a non-contact thermometer, and the origin position corresponding to the sample temperature measurement point is the temperature measurement point position of the non-contact thermometer.

4. The method according to claim 1, characterized in that Before training the initial model according to the sample data to obtain the temperature prediction model, the method further includes: Determine the data mean and data standard deviation corresponding to each category of the sample data; Each category is taken as a category to be processed, and for each sample data under the category to be processed, the sample data is standardized according to the data mean and the data standard deviation corresponding to the category to be processed to obtain standardized data, and the standardized data is used to replace the sample data.

5. The method according to claim 1, characterized in that: The step of training an initial model according to the sample data to obtain a temperature prediction model comprises: Performing stratified random sampling on the sample data according to a preset division ratio to obtain a training data set and a test data set; Taking the initial model as the model to be processed, adjusting the model parameters of the model to be processed according to the training data set to obtain an intermediate model; Input the coordinates of the sample temperature measurement points in the test data set, the surface temperature of the sample casting area after casting, the material property data of the sample concrete cast in the sample casting area, and the environmental data of the sample casting area into the intermediate model to obtain the intermediate temperature output by the intermediate model; An evaluation index of the intermediate model is calculated according to the intermediate temperature and the internal temperature in the test data set, and if the evaluation index is within a preset index range, the intermediate model is determined as the temperature prediction model.

6. The method according to claim 5, characterized in that The model parameters include adjustment parameters and fixed parameters. The adjustment parameters are model parameters that are dynamically adjusted during the training process of the model to be processed. The adjustment parameters include the maximum tree depth layer, learning rate, number of learners, sample sub-sampling rate, and column sub-sampling rate. The fixed parameters are model parameters that are fixed to default values ​​during the training process of the model to be processed.

7. The method according to claim 1, characterized in that Also includes: Determine the outlet temperature of the next pouring area according to the predicted temperature; wherein the next pouring area is the pouring area after the pouring area to be tested, and the next pouring area and the pouring area to be tested belong to the same pouring object; The outlet temperature is sent to a temperature control unit of the concrete conveying equipment, so that the temperature control unit controls the concrete conveying equipment to output concrete of the outlet temperature.

8. A temperature prediction device for a casting area, characterized in that: include: A first acquisition module is used to acquire sample data of a sample pouring area; wherein the sample data includes the coordinates and internal temperature of a sample temperature measurement point in the sample pouring area after pouring, the surface temperature of the sample pouring area after pouring, material property data of sample concrete poured in the sample pouring area, and environmental data of the sample pouring area; A training module, used to train an initial model according to the sample data to obtain a temperature prediction model; wherein the temperature prediction model is used to predict the temperature in the pouring area; A second acquisition module is used to acquire index data of the casting area to be tested; wherein the casting area to be tested and the sample casting area have the same cross-section, and the index data include coordinates of the temperature measurement points to be measured in the casting area to be tested after casting, the surface temperature of the casting area to be tested after casting, material property data of the target concrete cast in the casting area to be tested, and environmental data of the casting area to be tested; The prediction module is used to input the index data into the temperature prediction model to obtain the predicted temperature of the temperature measurement point to be measured in the casting area to be measured.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the temperature prediction method of the casting area described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the temperature prediction method of the casting area described in any one of claims 1-7.

Images