Self-compacting concrete construction quality control method, device and equipment based on machine learning

Abstract

The invention is suitable for the technical field of big data, and provides a self-compacting concrete construction quality control method, device and equipment based on machine learning, and the method comprises the steps: obtaining environment information corresponding to a target scene; generating a pouring simulation model corresponding to the self-compacting concrete according to the environment information; and importing preset construction behavior data into the pouring simulation model, and performing behavior control on the construction behavior data to obtain control behavior data. By the adoption of the method, the accuracy of performance prediction can be improved, under the condition that the performance data does not meet the performance indexes, behavior control is conducted on the expected construction behavior data, the accuracy of construction behaviors is improved, and the pouring quality of the self-compacting concrete is improved.

Description

Technical Field

[0001] This application belongs to the field of big data technology, and particularly relates to a method, device, and equipment for controlling the construction quality of self-compacting concrete based on machine learning. Background Art

[0002] Concrete, as one of the main building materials in current infrastructure construction and housing construction, how to make its indicators meet the construction requirements during the construction process directly affects the quality of the building. For self-compacting concrete, due to factors such as construction conditions and raw material fluctuations, there are large fluctuations in its actual pouring indicators. The existing use technologies of self-compacting concrete generally need to test its performance indicators after the self-compacting concrete is poured to determine whether it meets the quality requirements, which is difficult to ensure the construction quality. When its performance indicators do not meet the quality requirements, it often needs to be demolished, reinforced, and re-accepted, thus greatly prolonging the construction time required.

[0003] It can be seen that the existing use technologies of self-compacting concrete cannot accurately predict its pouring performance indicators in different pouring scenarios, are difficult to ensure the construction quality, and result in large fluctuations in the building construction period. Summary of the Invention

[0004] The embodiments of this application provide a method and an electronic device for controlling the construction quality of self-compacting concrete based on machine learning, which can solve the problem that the existing use technologies of self-compacting concrete cannot accurately determine its pouring performance indicators in different pouring scenarios, are difficult to ensure the construction quality, and result in large fluctuations in the building construction period.

[0005] In a first aspect, the embodiments of this application provide a method for controlling the construction quality of self-compacting concrete based on machine learning, including: Obtaining environmental information corresponding to a target scenario; the environmental information includes: pouring space size and scenario type; Generating a pouring simulation model corresponding to the self-compacting concrete according to the environmental information; the pouring simulation model is obtained through machine learning training based on preset historical valid data; the historical valid data is obtained after data cleaning of all historical engineering data; Importing preset construction behavior data into the pouring simulation model, performing behavior control on the construction behavior data, and obtaining control behavior data; the control behavior data is the behavior data when the performance data of the self-compacting concrete meets the performance indicators corresponding to the target scenario.

[0006] In a possible implementation of the first aspect, importing the preset construction behavior data into the pouring simulation model and performing behavior control on the construction behavior data to obtain control behavior data includes: Creating a simulated construction object in the pouring simulation model according to the construction behavior data; the construction behavior data includes: at least one construction device and at least one construction worker; Controlling the simulated construction object to sequentially execute each of the construction steps in the pouring simulation model according to a plurality of construction steps determined according to the construction behavior data; During the execution of the construction steps, determining the state data of the simulated concrete in the pouring simulation model in real time; the state data includes: mechanical property parameters, durability property parameters, and carbon emission parameters; If it is detected that any state data at any moment does not meet the performance index, generating behavior control data according to the performance deviation corresponding to any state data and the associated construction step; Adjusting the construction behavior data based on the behavior control data, and based on the adjusted construction behavior data, returning to execute the operation of creating a simulated construction object in the pouring simulation model according to the construction behavior data until the state data meets the performance index after all the construction steps are completed.

[0007] In a possible implementation of the first aspect, during the execution of the construction steps, determining the state data of the simulated concrete in the pouring simulation model in real time includes: During the execution of the construction steps, collecting the real-time data of the simulated concrete in the pouring simulation model in real time; Determining the scene influence factor corresponding to the state data according to the scene type; the scene type includes: environmental temperature, environmental humidity, and position slope; Constructing a state prediction curve corresponding to the simulated concrete based on the real-time data and the scene influence factor; Determining the state data in the state prediction curve according to the predicted completion time corresponding to the completion of all the construction steps; the state data is the data corresponding to the predicted completion time in the state prediction curve; Correspondingly, if it is detected that any state data at any moment does not meet the performance index, generating behavior control data according to the performance deviation corresponding to any state data and the associated construction step includes: Calculating the curve deviation area between the state prediction curve and the standard state curve; Calculate the deviation index corresponding to the state data according to the weight values corresponding to each time series partition in the curve deviation area; the weight values are determined based on the length of the time interval between each time series partition and the execution time of the current construction behavior; If the deviation index is greater than a preset deviation threshold, generate behavior control data according to the performance deviation corresponding to any of the state data and the associated construction steps.

[0008] In a possible implementation manner of the first aspect, before generating the pouring simulation model corresponding to the self-compacting concrete according to the environmental information, it further includes: Obtain the historical valid data and the historical prediction data corresponding to each historical valid data; the historical environment corresponding to each historical valid data matches the environmental information; Determine the data confidence level of each historical valid data according to the data deviation corresponding to each historical valid data and the historical prediction data; Determine the historical feature index corresponding to each historical valid data according to multiple preset data feature dimensions; Calculate the index deviation coefficient corresponding to each data feature dimension according to the historical feature index and the data confidence level corresponding to each historical valid data; Based on the index deviation coefficient, determine the key feature dimension corresponding to the environmental information from all the data feature dimensions; Construct the pouring simulation model based on the historical feature indexes corresponding to the historical valid data in the key feature dimension.

[0009] In a possible implementation manner of the first aspect, the calculating the index deviation coefficient corresponding to each data feature dimension according to the historical feature index and the data confidence level corresponding to each historical valid data includes: For any historical valid data, calculate the index deviation factor between any historical valid data and other historical valid data according to the data confidence level; the index deviation factor is specifically:

[0010] where Devt(i) is the index deviation factor corresponding to the i-th historical valid data; ConLv(i) is the data confidence level corresponding to the i-th historical valid data; M is the total number of the historical valid data; is the historical feature index of the i-th historical valid data in the k-th data feature dimension; is the historical feature index of the j-th historical valid data in the k-th data feature dimension; Calculate the index deviation coefficient according to each of the index deviation factors and the collection time corresponding to the historical valid data; specifically, the index deviation coefficient is:

[0011] where DevtLv is the index deviation coefficient; Histime(i) is the collection time corresponding to the i-th historical valid data; Curtime is the current time; and α is a preset adjustment constant.

[0012] In a possible implementation manner of the first aspect, before generating the pouring simulation model corresponding to the self-compacting concrete according to the environmental information, it further includes: Construct Gaussian distribution curves corresponding to each of the data feature dimensions according to the existing feature values corresponding to each of the historical engineering data in each data feature dimension; Determine the abnormal distribution boundary according to the total amount of the data engineering data; Identify the historical engineering data within the abnormal distribution boundary in the Gaussian distribution curve as abnormal historical data, and identify the historical engineering data within the abnormal distribution boundary in the Gaussian distribution curve as legal historical data; Perform data calibration processing on the abnormal historical data according to the data calibration algorithm to obtain the primary calibration data; Obtain the historical valid data based on the primary calibration data and the legal historical data.

[0013] In a possible implementation manner of the first aspect, generating the pouring simulation model corresponding to the self-compacting concrete according to the environmental information includes: Obtain the standard pouring model associated with the scenario type according to the scenario type; Generate a simulated pouring space in the standard pouring model according to the pouring space size; Generate the pouring simulation model based on the simulated pouring space.

[0014] In a second aspect, an embodiment of the present application provides a self-compacting concrete construction quality control device based on machine learning, and the device includes: An environmental information acquisition unit, configured to acquire environmental information corresponding to a target scenario; the environmental information includes: pouring space size and scenario type; A pouring simulation model generation unit, configured to generate a pouring simulation model corresponding to the self-compacting concrete according to the environmental information; the pouring simulation model is obtained through machine learning training based on preset historical valid data; the historical valid data is obtained after data cleaning of all historical engineering data; A behavior control unit, configured to import preset construction behavior data into the pouring simulation model, perform behavior control on the construction behavior data, and obtain control behavior data; the control behavior data is the behavior data when the performance data of the self-compacting concrete meets the corresponding performance indicators of the target scenario.

[0015] In a third aspect, an embodiment of the present application provides an electronic 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 method described in any one of the above first aspects is implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method described in any one of the above first aspects is implemented.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a drone, the drone is enabled to execute the method described in any one of the above first aspects.

[0018] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: When self-compacting concrete needs to be used for pouring, the electronic device can obtain the environmental information corresponding to the target scenario of pouring, and generate a matching pouring simulation model according to the environmental information, so that the subsequent pouring simulation operations of the pouring simulation model can be adapted to the target scenario of pouring, improving the accuracy of pouring simulation; after constructing the corresponding pouring simulation model, various construction processes during construction can be simulated in the pouring simulation model according to the construction behavior data, so as to be able to judge whether the self-compacting concrete poured through the above construction behavior data meets the performance index requirements, and perform behavior control when the performance index is not met to obtain the corresponding control behavior data, realizing the construction guidance for concrete pouring. Compared with the existing concrete use technology, the embodiments of the present application do not need to test the performance index of the concrete until after construction is completed, but can perform performance prediction through the pouring simulation model. Since the pouring simulation model is constructed according to the environmental information of the target scenario, the accuracy of performance prediction can be improved, and when the performance data does not meet the performance index, the desired construction behavior data is behaviorally controlled, improving the accuracy of construction behavior and reducing the difficulty of using self-compacting concrete. Description of the Drawings

[0019] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 is a schematic structural diagram of a concrete construction management system provided by an embodiment of the present application; Figure 2 is a schematic implementation diagram of a self-compacting concrete construction quality control method based on machine learning provided by an embodiment of the present application; Figure 3 is a specific implementation flowchart before S203 in a self-compacting concrete construction quality control method based on machine learning provided by the second embodiment of the present application; Figure 4 is a specific implementation flowchart of S2033 and S2034 in a self-compacting concrete construction quality control method based on machine learning provided by the third embodiment of the present application; Figure 5 is a schematic application diagram of a state prediction curve provided by an embodiment of the present application; Figure 6 is a specific implementation flowchart before S202 in a self-compacting concrete construction quality control method based on machine learning provided by the fourth embodiment of the present application; Figure 7 is a specific implementation flowchart before S202 in a self-compacting concrete construction quality control method based on machine learning provided by the fifth embodiment of the present application; Figure 8 is a specific implementation flowchart of S202 in a self-compacting concrete construction quality control method based on machine learning provided by the sixth embodiment of the present application; Figure 9 is a schematic structural diagram of a self-compacting concrete construction quality control device based on machine learning provided by an embodiment of the present application; Figure 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0021] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also 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 avoid unnecessary details from interfering with the description of the present application.

[0022] It should be understood that when used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0023] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for differential description and should not be construed as indicating or implying relative importance.

[0024] A method for controlling the construction quality of self-compacting concrete based on machine learning provided by an embodiment of this application can be applied to a control device for controlling the construction quality of self-compacting concrete based on machine learning. Exemplarily, Figure 1 The schematic structural diagram of a concrete construction management system provided by an embodiment of this application is shown. Refer to Figure 1 As described, the concrete construction management system includes a control device 11 and a feedback terminal 12 for environmental information. Among them, the above-mentioned feedback terminal 12 can be set at a target scene 13 where concrete pouring is required. In this target scene, a groove for concrete pouring, such as groove 131, can be excavated. The environmental information in the above-mentioned target scene 13 can be obtained through the above-mentioned feedback terminal 12, and the collected environmental information is fed back to the control device 11. The control device 11 can determine control behavior data matching the target scene 13, so that after self-compacting concrete is poured according to the above-mentioned control behavior data, the self-compacting concrete can meet the performance requirements, reducing the difficulty of using self-compacting concrete and improving the construction efficiency.

[0025] Compared with conventional concrete, self-compacting concrete is affected by environmental factors during pouring, and its performance data generally needs to be determined after the self-compacting concrete has solidified, and the measurement is difficult, thus increasing the difficulty of using self-compacting concrete. However, the embodiment of this application can calibrate the construction behavior data by constructing a pouring simulation model matching the target scene before using self-compacting concrete for pouring, so as to improve the performance stability of self-compacting concrete pouring and increase the probability that the performance data after self-compacting concrete pouring meets the performance indicators.

[0026] Please refer to Figure 2 , Figure 2The figure shows a schematic implementation diagram of a self-compacting concrete construction quality control method provided by an embodiment of the present application. This self-compacting concrete construction quality control method based on machine learning is applied to the above control device 11. That is, the execution subject of the embodiment of the present application can be the above control device 11. Among them, the control device 11 is specifically an electronic device, and this electronic device can be an electronic device such as a computer, a laptop, a server, and a smart phone. For the convenience of description, the execution subject will be described by taking the electronic device as an example hereinafter. Specifically, the method includes the following steps: In S201, obtain the environmental information corresponding to the target scenario; the environmental information includes: the pouring space size and the scenario type.

[0027] In this embodiment, the electronic device can first determine the target scenario where self-compacting concrete needs to be poured. The target scenario can be a specific location, or a building corresponding to the concrete to be poured, etc., which can be specifically determined according to the actual situation.

[0028] In this embodiment, in order to be able to reproduce the scenario in the pouring simulation model, the electronic device can obtain the environmental information corresponding to the target scenario. Among them, the environmental information can include two types of information: the pouring space size and the scenario type. Among them, the above-mentioned pouring space size is specifically the spatial information corresponding to the groove for pouring self-compacting concrete. For example, the groove depth, groove width, and groove length, etc. In the scenario where the groove is a complex cube, the above information can include multiple cross-sectional schematic diagrams, etc., which can be specifically obtained according to the actual situation.

[0029] In this embodiment, the above scenario type can be used to determine the scenario attribute information of the target scenario. For example, the above scenario type can be determined according to the attribute of the horizontal plane where the groove is located, such as the flat type and the slope type, or it can be determined according to the location attribute of the groove, such as the building foundation type, the driving road surface type, the pedestrian road surface type, etc. The above scenario type can include multiple types, that is, the scenario type of the target scenario is described through the attributes of multiple dimensions, so as to improve the accuracy of subsequent scenario simulation.

[0030] In a possible implementation manner, the above environmental information can be collected by a feedback terminal in the target scenario. The collection terminal can include multiple sensors. Through the sensors, the environmental information of the target scenario can be obtained and the environmental information can be fed back to the electronic device.

[0031] Exemplarily, the above feedback terminal can include a temperature and humidity sensor, an anemometer, and a barometer, etc., to obtain environmental information related to meteorology such as air humidity information, wind speed, and atmospheric pressure.

[0032] Exemplarily, the above feedback terminal may include a ground temperature probe, a soil moisture detector, and a groundwater monitoring float ball to obtain geological-related environmental information such as the ground temperature range, soil information, and groundwater information in the target scenario.

[0033] Based on this, the above environmental information may further include: information such as air humidity information, wind speed, atmospheric pressure, ground temperature range, soil information, and groundwater information. The specific environmental information can be selected according to the actual situation and is not limited herein.

[0034] In a possible implementation manner, the above environmental information may be obtained based on the design document corresponding to the target scenario. Since in the design stage, the relevant parameters for pouring corresponding to the target scenario can be determined, such as determining the groove position, groove depth, and soil texture structure at the groove, etc., the above relevant information can be recorded in the above design document. The electronic device can extract the key information related to the target scenario from the design document and perform feature data extraction on the key information, so as to obtain the above environmental information.

[0035] In S202, according to the environmental information, a pouring simulation model corresponding to the self-compacting concrete is generated; the pouring simulation model is obtained through machine learning training based on preset historical valid data; the historical valid data is obtained after data cleaning of all historical engineering data.

[0036] In this embodiment, the electronic device may be provided with a scenario simulation model. After collecting the environmental information corresponding to the target scenario, a corresponding scenario object can be constructed in the scenario simulation model. For example, a three-dimensional model matching the groove can be established in the scenario simulation model, and according to the soil information corresponding to the target scenario, the model attributes of the above three-dimensional model can be adjusted to simulate the material matching the soil information. Another example is that if the above environmental information includes groundwater information, a corresponding groundwater model can be established in the scenario simulation model, and according to the water level depth in the groundwater information, a seepage model corresponding to the groundwater model can be established to simulate the influence of groundwater on the groove. The specific type and quantity of the constructed three-dimensional models can be determined according to the environmental information and are not limited herein.

[0037] In this embodiment, the three-dimensional models created in the above pouring simulation model are specifically objects related to self-compacting concrete, such as the above groove model, groundwater model, and seepage model, etc., and may further include a solidification model and a mechanical model of self-compacting concrete. The establishment of the above models can be generated from the historical valid data collected during a large number of historical pouring processes. Through machine learning, the model data of each three-dimensional model is adjusted to make the three-dimensional model match the measurement data during the historical use process.

[0038] In this embodiment, since the amount of historical engineering data collected is large, which contains a large number of abnormal data or there are some missing data, etc., the electronic device can perform data cleaning on the historical engineering data, such as removing abnormal data and filling in the missing data, so as to obtain the corresponding historical valid data, improve the effectiveness of the data for training and learning, and then improve the accuracy of the simulation.

[0039] In some possible implementation manners, the process of performing data cleaning on the historical engineering data can be described as follows: First, remove noise and outliers through a data cleaning algorithm. For example, use the Z-score method to standardize the historical engineering data, set a threshold, and remove the historical engineering data that exceeds the range. Then, use the K-means clustering algorithm to group the cleaned data, set the number of clusters to 5, calculate the similarity between the data points and the cluster centers through the Euclidean distance, and finally divide the data into 5 clusters. Subsequently, use principal component analysis to reduce the dimension of each piece of historical engineering data after grouping, retain 95% of the variance information, and reduce the original data from 100 dimensions to 10 dimensions to reduce the computational complexity and retain the key features.

[0040] In S203, import the preset construction behavior data into the pouring simulation model, perform behavior control on the construction behavior data, and obtain control behavior data; the control behavior data is the behavior data when the performance data of the self-compacting concrete meets the performance indicators corresponding to the target scenario.

[0041] In this embodiment, the electronic device can store the standard construction process of self-compacting concrete and generate corresponding construction behavior data according to the standard construction process. Optionally, the electronic device can adjust the above standard construction process according to information such as the expected number of construction workers and the expected number of equipment corresponding to the target scenario, so as to obtain the construction behavior data corresponding to the target scenario.

[0042] In this embodiment, the above construction behavior data can include multiple construction steps, and each construction step can be limited with corresponding construction intervals, pouring volumes, pouring positions, etc. The characteristic data included in the specific construction steps can be determined according to the construction type corresponding to the construction step.

[0043] In this embodiment, the electronic device can import the above construction behavior data into the above constructed casting simulation model, so as to determine the performance data of the self-compacting concrete under the operation based on the construction behavior data. If the performance data does not meet the performance indicators corresponding to the target scenario, it means that the construction behavior data needs to be adjusted. Based on the adjusted construction behavior data, the operation of S203 is executed again. Through multiple iterations, until the performance data of the self-compacting concrete cast based on the adjusted construction behavior data meets the corresponding performance indicators, the adjusted construction behavior data is output, that is, the above control behavior data.

[0044] In this embodiment, the electronic device can generate a corresponding construction guidance document according to the control behavior data, and subsequently, the target scenario can be cast with self-compacting concrete according to the construction guidance document, so as to increase the probability that the actual performance of the self-compacting concrete meets the performance indicators.

[0045] In a possible implementation manner, the electronic device can collect the actual performance information corresponding to the target scenario, calculate the prediction deviation between the actual performance information and the performance data obtained based on the control behavior data, and calibrate the casting simulation model according to the prediction deviation, so as to enable model iteration and improve the accuracy of subsequent use.

[0046] As can be seen from the above, for a method for controlling the construction quality of self-compacting concrete based on machine learning provided by an embodiment of the present application, when the electronic device needs to use self-compacting concrete for casting, it can obtain the environmental information corresponding to the target scenario of the casting, and generate a matching casting simulation model according to the environmental information, so that the subsequent casting simulation operation of the casting simulation model can be adapted to the target scenario of the casting, improving the accuracy of the casting simulation. After constructing the corresponding casting simulation model, it can simulate each construction process during construction in the casting simulation model according to the construction behavior data, so as to determine whether the self-compacting concrete cast through the above construction behavior data meets the performance indicator requirements, and perform behavior control when the performance indicators are not met to obtain the corresponding control behavior data, realizing the construction guidance for concrete casting. Compared with the existing concrete use technology, in the embodiment of the present application, it is not necessary to test the performance indicators of the concrete only after the construction is completed, but the performance can be predicted through the casting simulation model. Since the casting simulation model is constructed according to the environmental information of the target scenario, the accuracy of the performance prediction can be improved, and when the performance data does not meet the performance indicators, the desired construction behavior data is controlled, improving the accuracy of the construction behavior and reducing the difficulty of using self-compacting concrete.

[0047] Figure 3The figure shows a specific implementation flowchart of S203 in a self-compacting concrete construction quality control method based on machine learning provided in the second embodiment of the present application. Refer to Figure 3 As shown, relative to Figure 2 the embodiment, in S203 of a self-compacting concrete construction quality control method based on machine learning provided in the embodiment of the present application, it includes S2031 to S2035, and the specific description is as follows: In S2031, according to the construction behavior data, a simulated construction object is created in the pouring simulation model; the construction behavior data includes: at least one construction device and at least one construction worker.

[0048] In this embodiment, the pouring simulation model may store virtual models of different object types, including a concrete model for simulating self-compacting concrete, a device model for simulating construction devices, and a human operation model for simulating construction workers. The electronic device can create a simulated construction object that matches it in the above-mentioned pouring simulation model by reading the configuration data related to the construction device and the construction worker in the construction behavior data.

[0049] In this embodiment, the device type and the number of devices of the construction device may be recorded in the above-mentioned configuration data. The electronic device can extract the device model associated with the device type from the material library and create a plurality of device models corresponding to the above-mentioned number of devices in the pouring simulation model, that is, obtain the simulated construction object corresponding to the construction device.

[0050] In this embodiment, the above-mentioned construction worker is specifically used to simulate the construction behavior of the person during the construction process. For example, the number of devices that can be controlled in parallel, and the accuracy when controlling the device, etc. The electronic device can determine the control range corresponding to the above-mentioned simulated construction object according to the type, level, and number of the above-mentioned construction workers. Subsequently, when executing the construction steps, a random value can be determined from the above-mentioned construction range through a random number algorithm, and the random value is used as the operation characteristic value of the subsequent construction steps, so as to improve the accuracy of the subsequent simulation.

[0051] In S2032, according to the multiple construction steps determined by the construction behavior data, the simulated construction object is sequentially controlled in the pouring simulation model to execute each of the construction steps.

[0052] In this embodiment, the electronic device can determine the construction steps required for the self-compacting concrete pouring based on the construction behavior data. Each construction step can be set with a corresponding construction order and the dependency relationships among each construction step. The electronic device can sequentially control the simulated construction objects related to the construction steps in the pouring simulation model according to each construction order, so as to execute the corresponding construction steps through the simulated construction objects.

[0053] Exemplarily, the construction steps include: the mixing step of self-compacting concrete, the pouring step, and the groove pouring step. Among them, the mixing step of self-compacting concrete and the groove pouring step belong to two parallel steps, while the pouring step can only be implemented after these two steps are completed. Based on this, the electronic device can control the simulated construction objects related to the mixing of self-compacting concrete to execute the above mixing step, and at the same time control the simulated construction objects related to the groove pouring step to execute the above pouring step. Specifically, the parallel control or serial control of the above two steps can be determined according to the number of construction workers in the construction behavior data to determine the number of devices that can be simultaneously controlled in parallel.

[0054] In S2033, during the execution of the construction step, the state data of the simulated concrete in the pouring simulation model is determined in real time; the state data includes: mechanical property parameters, durability property parameters, and carbon emission parameters.

[0055] In this embodiment, during the process of the electronic device controlling each simulated construction object to execute any construction step, it continuously collects the real-time state of the simulated concrete in the pouring simulation model. Among them, the above simulated concrete is a simulation model based on self-compacting concrete to simulate the state of self-compacting concrete during use. Among them, in the stage of concrete mixing, the above simulated concrete model can be a mixture of material models corresponding to each raw material, and simulate the mixing process of each material model to obtain the corresponding simulated concrete.

[0056] In this embodiment, the electronic device can predict the state of the self-compacting concrete formed after pouring based on the real-time state of the simulated concrete in the pouring simulation model, so as to obtain the above-mentioned state data. That is, the above-mentioned state data is not determined based on the state of the model concrete during the execution of the construction steps, but is obtained by predicting the state after its formation. The pouring simulation model has a state prediction module. Importing the real-time state corresponding to the execution of the above-mentioned construction steps into the above-mentioned state prediction module can output the above-mentioned state data. Among them, according to the performance evaluation dimensions of the self-compacting concrete, the above-mentioned collected state data may include: mechanical property parameters, such as relevant data on the stiffness, hardness, and stress of the self-compacting concrete; the above-mentioned state data may also include durability property parameters, such as the degree of deformation under different pressures, wear resistance levels, etc.; the above-mentioned state data may also include carbon emission parameters, specifically, relevant data such as the total amount and rate of carbon dioxide generated during the pouring of the self-compacting concrete. Specifically, the data type of the above-mentioned state data can be determined according to actual index requirements and is not limited herein.

[0057] In S2034, if it is detected that any state data at any moment does not meet the performance index, behavior control data is generated according to the performance deviation corresponding to the any state data and the associated construction steps.

[0058] In this embodiment, the electronic device can perform index matching between the above-mentioned state data and the performance index corresponding to the target scenario. If the state data meets the performance index corresponding to the target scenario, the construction step can be continued, or after the current construction step is completed, the next construction step can be executed, and the operation of S2033 is repeated until all construction steps are completed. If, after all construction steps are completed, the state data of the simulated concrete all meet the above-mentioned performance index, the construction behavior data can be directly output without calibrating the construction behavior data.

[0059] In this embodiment, if the electronic device detects that a certain state data at any moment does not meet the performance index, it means that there may be abnormal behavior during the execution of the construction step, and the actual executed behavior does not match the target scenario. At this time, it is not necessary to execute the subsequent steps, but to perform behavior control on the already executed construction steps.

[0060] In this embodiment, the way to perform behavior control on the construction step can be: according to the data type of the state data that does not meet the performance, determine multiple executed steps associated with this data type, and adjust the data in the construction behavior data related to the above-mentioned executed steps according to the preset adjustment step size to obtain the above-mentioned behavior control data.

[0061] In S2035, adjust the construction behavior data based on the behavior control data, and based on the adjusted construction behavior data, return to execute the operation of creating a simulated construction object in the pouring simulation model according to the construction behavior data until the state data meets the performance index after all the construction steps are completed.

[0062] In this embodiment, the electronic device can adjust the construction behavior data according to the behavior control data, for example, modify some parameters, and return to execute the operation of S2031 to perform the construction process simulation again. Through iteration, the state data of the simulated concrete can meet the performance index.

[0063] In the embodiment of the present application, during the process of simulating the self-compacting concrete pouring in the construction process through the construction behavior data, and continuously predicting the state data of the simulated concrete in the pouring simulation model, abnormal steps can be immediately discovered, and then the abnormal steps can be adjusted, which can improve the iteration speed of the control behavior data and the convergence speed of the results, thereby improving the user experience and avoiding the user waiting for a long time to obtain the corresponding control behavior data.

[0064] Figure 4 The specific implementation flowcharts of S2033 and S2034 in a method for controlling the construction quality of self-compacting concrete based on machine learning provided in the third embodiment of the present application are shown. Refer to Figure 4 as shown, relative to Figure 3 the above embodiment, S2033 in a method for controlling the construction quality of self-compacting concrete based on machine learning provided in the embodiment of the present application may include S401 to S404, and the above S2034 may include S405 to S407, which are specifically described as follows: During the process of executing the construction steps, real-time determination of the state data of the simulated concrete in the pouring simulation model includes: In S401, during the process of executing the construction steps, real-time data of the simulated concrete in the pouring simulation model is collected in real time.

[0065] In this embodiment, since the simulated concrete is a virtual object established in the pouring simulation model, the relevant parameters of the simulated concrete can be obtained. In the actual pouring process, the state of the self-compacting concrete cannot be collected at all times, and only the state can be predicted based on experience, resulting in a large state judgment error. And this embodiment can determine the real-time data through the simulated concrete, and the data type of the above real-time data can be data related to the performance index, so as to realize the prediction of the subsequent state data according to the real-time data, so as to compare the predicted state data with the performance index later to determine whether the state data meets the performance index.

[0066] In S402, according to the scene type, determine the scene impact factor corresponding to the state data; the scene type includes: ambient temperature, ambient humidity, and position slope.

[0067] In this embodiment, the electronic device can determine the scene impact factor that affects the state data according to the scene type corresponding to the target scene. It should be noted that the data type of the state data can include multiple dimensions, such as the mechanical property dimension, the durability dimension, and the concrete stability dimension, etc. The factors affected by the environment in different dimensions are different. The electronic device can also establish the corresponding relationship between different types of state data and the scene impact factor, so as to be able to determine the scene impact factor corresponding to different state data, so as to improve the accuracy of the subsequent state prediction curve.

[0068] In S403, based on the real-time data and the scene impact factor, construct the state prediction curve of the simulated concrete.

[0069] In S404, according to the predicted completion time corresponding to all the construction steps, determine the state data in the state prediction curve; the state data is the data corresponding to the predicted completion time in the state prediction curve.

[0070] In this embodiment, the electronic device can establish a corresponding real-time state curve according to all the real-time data collected during the execution of this construction step and the previous steps, and determine the influence coefficient of each scene impact factor according to the above real-time state curve. According to the influence coefficient corresponding to each scene impact factor and the above real-time state curve, establish the above state prediction curve. It should be noted that the real-time data includes data in multiple different dimensions, so the number of constructed state prediction curves can also be multiple, which can be specifically determined according to the data items included in the real-time data. When calculating the deviation index later, the corresponding deviation index can also be calculated according to different data items.

[0071] Exemplarily, Figure 5 shows an application schematic diagram of the state prediction curve provided by an embodiment of the present application. Refer to Figure 5 As shown, the curve 51 includes the curve segment 511 of the solid line part and the curve segment 512 of the curve part. Among them, the curve segment 511 is constructed according to the real-time data collected during the executed steps and the current execution steps. According to the curve segment 511, the influence coefficient corresponding to each scene impact factor can be determined, so as to be able to establish the corresponding state prediction function, and the state of the subsequent simulated concrete can be predicted according to the state prediction function, that is, the curve segment 512 can be obtained. Among them, the end time of the curve segment 512 is the time corresponding to the completion of all construction steps.

[0072] In this embodiment, the electronic device can determine the predicted completion time corresponding to all construction operations according to the state prediction curve, simulate the real-time data of the concrete, use the real-time data corresponding to the predicted completion time as the above-mentioned state data, and match the state data with the performance indicators to determine whether the construction requirements are met.

[0073] Correspondingly, if it is detected that any state data at any moment does not meet the performance indicators, behavior control data is generated according to the performance deviation corresponding to the any state data and the associated construction steps, including: In S405, calculate the curve deviation area between the state prediction curve and the standard state curve.

[0074] In this embodiment, the electronic device can generate a corresponding standard state curve in the target scenario in the coordinate system where the state prediction curve is located. The standard state curve is generated according to the performance indicators corresponding to the target scenario.

[0075] In this embodiment, the electronic device can calculate the deviation area between the above two curves to determine the deviation degree between the state of the simulated concrete and the expected state. Continuing with Figure 5 as an example for illustration, curve 52 is the standard state curve corresponding to the self-compacting concrete, and then the above-mentioned curve deviation area, that is, area 53, can be determined.

[0076] In S406, calculate the deviation index corresponding to the state data according to the weight values corresponding to each time series partition in the curve deviation area; the weight values are determined based on the time interval lengths between each time series partition and the execution time of the current construction behavior.

[0077] In this embodiment, the electronic device can divide the above-mentioned curve deviation area into regions according to the time series relationship to obtain multiple time series partitions. Each time series partition can correspond to a weight value. Among them, the longer the time interval length between the time series partition and the execution time of the current construction behavior, the lower the prediction confidence, so the corresponding weight value is smaller; on the contrary, the shorter the time interval between the time series partition and the execution time of the current construction behavior, the higher the prediction accuracy, the higher the confidence, and the corresponding weight value is larger. The electronic device can divide the curve deviation area into time series partitions, thereby improving the accuracy of the deviation index calculation. Among them, the above-mentioned deviation index can be expressed as:

[0078] Among them, EorroLv is the above-mentioned deviation index; Weight(p) is the weight value corresponding to the p-th time series partition; S(p) is the area of the region corresponding to the p-th time series partition, and P is the total number of time series partitions included in the curve deviation area.

[0079] In S407, if the deviation index is greater than a preset deviation threshold, behavior control data is generated according to the performance deviation corresponding to any one of the state data and the associated construction steps.

[0080] In this embodiment, when it is identified that the deviation index is greater than the deviation threshold, it means that the current state data does not meet the above performance index. According to the abnormal state data, the associated construction steps are determined, and according to the difference between the state data predicted based on the real-time data and the performance index, the performance deviation is obtained. The performance deviation is converted into a corresponding adjustment step size, and the behavior control data is obtained based on the adjustment step sizes corresponding to all the abnormal state data (one or more).

[0081] In the embodiment of the present application, by constructing a corresponding state prediction curve to determine the state data corresponding to the completion time according to the currently executed construction steps, and then identifying abnormal operations based on the state data, the accuracy of abnormal operation identification can be improved, and then the accuracy of behavior control can be improved.

[0082] Figure 6 The figure shows a specific implementation flowchart before S202 of a self-compacting concrete construction quality control method based on machine learning provided in the fourth embodiment of the present application. Refer to Figure 6 relative to Figure 2 In any one of the above embodiments, before S202 in a self-compacting concrete construction quality control method based on machine learning provided in this embodiment, it further includes: S601~S606, which are specifically described in detail as follows: In S601, the historical valid data and the historical prediction data corresponding to each historical valid data are obtained; the historical environment corresponding to each historical valid data matches the environmental information.

[0083] In this embodiment, when self-compacting concrete is poured, the project can be designed, and the corresponding performance requirements of the self-compacting concrete can be specified during the design. However, during the actual pouring, the actual usage amount and performance may deviate from the prediction during the design. Therefore, the electronic device can determine the influence degree of different construction processes on the concrete performance by obtaining the control groups of the above two data during the historical construction process, and then can realize the basic construction of the scenario simulation. Among them, the performance of the concrete and the relevant construction data during the actual pouring are the above-mentioned historical valid data, and the requirements recorded in the design document and the construction specifications during the pouring process are the above-mentioned historical prediction data.

[0084] In this embodiment, in order to improve the matching degree between the constructed pouring simulation model and the scenario, the historical environment corresponding to the collected historical valid data matches the environmental information corresponding to the target scenario. For example, the scenario type of the historical environment is the same as that of the target scenario, and / or the actual space size of the historical environment matches the pouring space size of the target scenario.

[0085] In S602, according to the data deviation corresponding to each historical valid data and the historical prediction data, determine the data confidence of each historical valid data.

[0086] In this embodiment, the electronic device can calculate the data deviation between each historical valid data and its corresponding historical prediction data respectively. Specifically, if the historical valid data contains multiple different data items, the deviation factors of different data items are calculated respectively, and the deviation factors corresponding to all data items are superimposed or weighted and superimposed to calculate the above data deviation.

[0087] In this embodiment, if there are multiple historical pouring events, then there are also multiple data groups for the historical valid data and the historical prediction data. Calculate the data deviation corresponding to each group of data respectively, and determine the corresponding data confidence according to the data deviation of each group of data. Among them, the larger the data deviation, the greater the error between the expected performance and the actual performance during the actual pouring of the self-compacting concrete, which may be caused by design mistakes or operation mistakes. At this time, there may be a certain abnormality, and the corresponding confidence is low, that is, there is an inverse relationship between the data deviation and the data confidence. The electronic device can convert the data deviation into the corresponding data confidence through a preset conversion function.

[0088] In S603, according to multiple preset data feature dimensions, determine the historical feature index corresponding to each historical valid data.

[0089] In S604, according to the historical characteristic indicators corresponding to each of the historical valid data and the data confidence level, calculate the index deviation coefficient corresponding to each data characteristic dimension.

[0090] In this embodiment, the historical valid data includes multiple data dimensions, such as the mechanical property dimension, the durability property dimension, and the carbon emission dimension, etc. The electronic device can extract the historical characteristic indicators corresponding to each data dimension from each historical valid data respectively.

[0091] In this embodiment, the electronic device can calculate the index mean of this data characteristic dimension according to the historical characteristic indicators corresponding to all historical valid data, then calculate the index deviation between the historical characteristic indicators of each historical valid data and this index mean, and superimpose the corresponding data confidence level on the basis of this index deviation, so as to be able to calculate the discrete contribution corresponding to this historical valid data. Based on the discrete contributions of all historical valid data, the index deviation coefficient corresponding to the corresponding data characteristic dimension can be calculated.

[0092] In a possible implementation manner, the calculation method of the above index deviation coefficient may include the following steps: In S604.1, for any historical valid data, calculate the index deviation factor between any historical valid data and other historical valid data according to the data confidence level; the index deviation factor is specifically:

[0093] where Devt(i) is the index deviation factor corresponding to the i-th historical valid data; ConLv(i) is the data confidence level corresponding to the i-th historical valid data; M is the total number of the historical valid data; is the historical characteristic indicator of the i-th historical valid data in the k-th data characteristic dimension; is the historical characteristic indicator of the j-th historical valid data in the k-th data characteristic dimension; In S604.2, calculate the index deviation coefficient according to each of the index deviation factors and the acquisition time corresponding to the historical valid data; the index deviation coefficient is specifically:

[0094] where DevtLv is the index deviation coefficient; Histime(i) is the acquisition time corresponding to the i-th historical valid data; Curtime is the current time; α is a preset adjustment constant.

[0095] In the embodiments of the present application, by calculating the index deviation factors corresponding to different historical valid data respectively, the deviation degree between each historical valid data and the mean value can be calculated, so as to determine the dispersion degree of the historical valid data among all historical pouring events (i.e., reflected by the index deviation factor). Moreover, the farther the historical pouring event is from the current time, the greater the difference between its pouring techniques and the smaller the corresponding reference contribution. Therefore, the time difference from the current time can be determined as its weight value, thereby improving the accuracy of the index deviation coefficient.

[0096] In S605, based on the index deviation coefficient, the key feature dimension corresponding to the environmental information is determined from all the data feature dimensions.

[0097] In this embodiment, the electronic device can select the data dimensions whose values are greater than a preset deviation threshold according to the index deviation coefficient as the key feature dimensions. That is, the above key feature dimensions have a large deviation in different pouring scenarios, which may be caused by the differences in construction techniques and need to be variables that are key monitored when constructing the model subsequently.

[0098] In S606, based on each historical feature index corresponding to the historical valid data in the key feature dimension, the pouring simulation model is constructed.

[0099] In this embodiment, each key feature dimension may correspond to one or more construction steps, and one or more construction simulation objects are determined according to the corresponding construction steps. The electronic device can determine the actual construction object associated with the key feature dimension and the process parameters of the actual construction object from the historical valid data, such as working hours, working intensity, and the personnel level of the operators, etc., so as to establish the association relationship between the key feature dimension and the construction simulation object. According to the association relationship between each key feature dimension and the construction simulation object, the above-mentioned pouring simulation model is generated.

[0100] In the embodiments of the present application, by obtaining historical valid data, the key feature dimensions affected by the process can be determined according to the dispersion degree of each data feature dimension in the historical valid data, and then the corresponding pouring simulation model is generated according to the key feature dimensions, improving the accuracy of the model.

[0101] Figure 7 Shows a specific implementation flowchart before S202 of a self-compacting concrete construction quality control method based on machine learning provided in the fifth embodiment of the present application. Refer to Figure 7 , relative to Figures 2 to 6For any of the above embodiments, before S202 in the self-compacting concrete construction quality control method based on machine learning provided in this embodiment, the following steps S701 to S705 are further included, which are specifically described as follows: In S701, according to the existing feature values corresponding to each data feature dimension in each piece of historical engineering data, Gaussian distribution curves corresponding to each data feature dimension are respectively constructed.

[0102] In S702, according to the total amount of data in the data engineering data, the abnormal distribution boundary is determined.

[0103] In S703, the historical engineering data within the abnormal distribution boundary in the Gaussian distribution curve is identified as abnormal historical data, and the historical engineering data within the abnormal distribution boundary in the Gaussian distribution curve is identified as legal historical data.

[0104] In this embodiment, the electronic device can perform data cleaning on the historical engineering data, and abnormal data with obvious construction behavior anomalies can be screened out. Among them, the screening method can be to construct a corresponding Gaussian distribution curve according to all historical engineering data, determine the abnormal distribution boundary, and the data outside the abnormal distribution boundary is far from the mean value, and it can be identified as abnormal data, that is, the data outside the abnormal distribution boundary of the above Gaussian distribution curve is used as abnormal historical data.

[0105] In S704, according to the data calibration algorithm, data calibration processing is performed on the abnormal historical data to obtain primary calibrated data.

[0106] In S705, based on the primary calibrated data and legal historical data, historical valid data is obtained.

[0107] In this embodiment, since the historical data of pouring records is limited, in order to increase the amount of training data that can be referenced, when abnormal historical data is identified, the historical abnormal data will not be directly discarded, but the historical abnormal data can be calibrated to obtain primary calibrated data, so as to increase the training data samples available for model construction and then improve the accuracy of simulation.

[0108] Figure 8 The specific implementation flowchart of a self-compacting concrete construction quality control method based on machine learning provided in the sixth embodiment of the present application at S202 is shown. Refer to Figure 8 , relative to Figures 2 to 6 For any of the above embodiments, in S202 of the self-compacting concrete construction quality control method based on machine learning provided in this embodiment, S2021 to S2023 are included, which are specifically described as follows: In S2021, according to the scene type, obtain a standard pouring model associated with the scene type.

[0109] In S2022, according to the pouring space size, generate a simulated pouring space in the standard pouring model.

[0110] In S2023, based on the simulated pouring space, generate the pouring simulation model.

[0111] In this embodiment, the electronic device can obtain different standard pouring models according to different scenarios. For example, for a road surface scenario, obtain a standard pouring model related to the road surface scenario; for a slope scenario, obtain a standard pouring model related to the slope scenario. The electronic device can construct different standard pouring models for different scene types, and generate corresponding simulated pouring spaces in the above standard pouring models according to the pouring space size. Among them, if the environmental information includes groundwater information, a groundwater environment model can also be created in the above standard pouring model, so as to improve the accuracy of the simulation.

[0112] In this embodiment, Figure 9 shows a structural block diagram of a self-compacting concrete construction quality control device based on machine learning provided by an embodiment of the present application. Each unit included in the self-compacting concrete construction quality control device based on machine learning is used to execute Figure 2 the respective steps implemented by the first device in the corresponding embodiment. For details, please refer to Figure 2 and Figure 2 the relevant descriptions in the corresponding embodiment. For the sake of convenience of description, only the parts related to this embodiment are shown.

[0113] See Figure 9 , the self-compacting concrete construction quality control device based on machine learning includes: An environmental information acquisition unit 91, configured to acquire environmental information corresponding to a target scene; the environmental information includes: pouring space size and scene type; A pouring simulation model generation unit 92, configured to generate a pouring simulation model corresponding to self-compacting concrete according to the environmental information; the pouring simulation model is obtained by performing machine learning training based on preset historical valid data; the historical valid data is obtained by performing data cleaning on all historical engineering data; A behavior control unit 93, configured to import preset construction behavior data into the pouring simulation model, perform behavior control on the construction behavior data, and obtain control behavior data; the control behavior data is the behavior data when the performance data of the self-compacting concrete satisfies the performance index corresponding to the target scene.

[0114] It should be understood that Figure 9In the structural block diagram of the shown device, each module is used to execute Figures 2 to 8 each step in the corresponding embodiment, and for Figures 2 to 8 each step in the corresponding embodiment has been explained in detail in the above embodiments. For details, please refer to Figures 2 to 8 and Figures 2 to 8 the relevant descriptions in the corresponding embodiments, which will not be elaborated here.

[0115] Figure 10 Figure 12 is a structural block diagram of an electronic device provided in another embodiment of the present application. As Figure 10 described, the electronic device 1000 of this embodiment includes: a processor 1010, a memory 1020, and a computer program 1030 stored in the memory 1020 and executable on the processor 1010, such as a program for the construction quality control method of self-compacting concrete based on machine learning. When the processor 1010 executes the computer program 1030, it implements the steps in each of the above embodiments of the construction quality control method of self-compacting concrete based on machine learning, such as Figure 2 the S201 to S203 described. Alternatively, when the processor 1010 executes the computer program 1030, it implements the functions of each module in the above Figure 9 corresponding embodiment. For example, Figure 9 the functions of the units 91 to 93 described. For details, please refer to Figure 9 the relevant descriptions in the corresponding embodiment.

[0116] Exemplarily, the computer program 1030 can be divided into one or more modules. One or more modules are stored in the memory 1020 and executed by the processor 1010 to complete the present application. One or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 1030 in the electronic device 1000. For example, the computer program 1030 can be divided into each unit module, and the specific functions of each module are as above.

[0117] The electronic device 1000 may include, but is not limited to, a processor 1010 and a memory 1020. Those skilled in the art can understand that Figure 10 this is only an example of the electronic device 1000 and does not constitute a limitation on the electronic device 1000. It may include more or fewer components than shown, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, buses, etc.

[0118] The so-called processor 1010 may be a central processing unit, or may also be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0119] The memory 1020 may be an internal storage unit of the electronic device 1000, such as the hard disk or memory of the electronic device 1000. The memory 1020 may also be an external storage device of the electronic device 1000, such as a plug-in hard disk, a smart memory card, a flash memory card, etc. equipped on the electronic device 1000. Further, the memory 1020 may also include both the internal storage unit of the electronic device 1000 and the external storage device.

[0120] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A self-compacting concrete construction quality control method based on machine learning, characterized in that: include: Obtain environmental information corresponding to the target scene; The environmental information includes: casting space size and scene type; Generate a pouring simulation model corresponding to the self-compacting concrete according to the environmental information; the pouring simulation model is obtained by machine learning training based on preset historical valid data; the historical valid data is obtained after data cleaning of all historical engineering data; Importing preset construction behavior data into the casting simulation model, performing behavior control on the construction behavior data to obtain control behavior data; the control behavior data is behavior data that makes the performance data of the self-compacting concrete meet the target scenario to the corresponding performance index.

2. The method according to claim 1, characterized in that The step of importing the preset construction behavior data into the casting simulation model and performing behavior control on the construction behavior data to obtain the controlled behavior data includes: Creating a simulated construction object in the casting simulation model according to the construction behavior data; the construction behavior data includes: at least one construction equipment and at least one construction worker; According to the multiple construction steps determined by the construction behavior data, sequentially controlling the simulated construction object in the casting simulation model to execute each of the construction steps; In the process of executing the construction steps, the state data of the simulated concrete in the casting simulation model is determined in real time; the state data includes: mechanical property parameters, durability performance parameters and carbon emission parameters; If it is detected that any item of status data at any time does not meet the performance index, then behavior control data is generated according to the performance deviation corresponding to any item of status data and the associated construction steps; The construction behavior data is adjusted based on the behavior control data, and based on the adjusted construction behavior data, the operation of creating a simulated construction object in the casting simulation model according to the construction behavior data is returned to be executed until the status data meets the performance indicator after all the construction steps are completed.

3. The method according to claim 2, characterized in that In the process of executing the construction step, determining the state data of the simulated concrete in the pouring simulation model in real time includes: In the process of executing the construction steps, real-time data of the simulated concrete in the pouring simulation model is collected in real time; Determine the scene influencing factor corresponding to the state data according to the scene type; the scene type includes: ambient temperature, ambient humidity and location slope; Based on the real-time data and the scene influencing factors, construct a state prediction curve corresponding to the simulated concrete; Determine the state data in the state prediction curve according to the predicted completion time corresponding to the completion of all the construction steps; the state data is the data corresponding to the predicted completion time in the state prediction curve; Correspondingly, if it is detected that any state data at any time does not meet the performance index, behavior control data is generated according to the performance deviation corresponding to any state data and the associated construction steps, including: Calculating the curve deviation area between the state prediction curve and the standard state curve; Calculate the deviation index corresponding to the state data according to the weight value corresponding to each time series partition in the curve deviation area; the weight value is determined based on the length of the time interval between each time series partition and the execution time of the current construction behavior; If the deviation index is greater than a preset deviation threshold, behavior control data is generated according to the performance deviation corresponding to any one of the status data and the associated construction steps.

4. The method according to claim 1, characterized in that: Before generating a pouring simulation model corresponding to the self-compacting concrete according to the environmental information, the method further includes: Acquire the historical valid data and the historical prediction data corresponding to each of the historical valid data; the historical environment corresponding to each of the historical valid data matches the environmental information; Determining the data confidence of each of the historical valid data according to the data deviation corresponding to each of the historical valid data and the historical prediction data; Determine, according to a plurality of preset data feature dimensions, a historical feature indicator corresponding to each of the historical valid data; Calculate the index deviation coefficient corresponding to each data feature dimension according to the historical feature index corresponding to each of the historical valid data and the data confidence; Based on the indicator deviation coefficient, determining the key feature dimension corresponding to the environmental information from all the data feature dimensions; The casting simulation model is constructed based on the historical feature indicators corresponding to the key feature dimensions of the historical valid data.

5. The method according to claim 4, characterized in that The calculating, according to the historical characteristic indicators and the data confidence corresponding to each of the historical valid data, the indicator deviation coefficient corresponding to each data characteristic dimension comprises: For any historical valid data, the index deviation factor between any historical valid data and other historical valid data is calculated according to the data confidence; the index deviation factor is specifically: Wherein, Devt(i) is the indicator deviation factor corresponding to the i-th historical valid data; ConLv(i) is the data confidence corresponding to the i-th historical valid data; M is the total number of data of the historical valid data; is the historical characteristic indicator of the i-th historical valid data in the k-th data characteristic dimension; is the historical characteristic indicator of the jth historical valid data in the kth data characteristic dimension; The indicator deviation coefficient is calculated according to each of the indicator deviation factors and the collection time corresponding to the historical valid data; the indicator deviation coefficient is specifically: Wherein, DevtLv is the indicator deviation coefficient; Histime(i) is the collection time corresponding to the i-th historical valid data; Curtime is the current time; α is the preset adjustment constant.

6. The method according to any one of claims 1 to 5, characterized in that: Before generating a pouring simulation model corresponding to the self-compacting concrete according to the environmental information, the method further includes: According to the existing characteristic values ​​corresponding to each data characteristic dimension of each historical engineering data, Gaussian distribution curves corresponding to each data characteristic dimension are respectively constructed; Determining an abnormal distribution boundary according to the total amount of data of the data engineering data; Identify the historical engineering data in the Gaussian distribution curve within the abnormal distribution boundary as abnormal historical data, and identify the historical engineering data in the Gaussian distribution curve within the abnormal distribution boundary as legal historical data; According to the data calibration algorithm, the abnormal historical data is subjected to data calibration processing to obtain primary calibration data; Based on the one-time calibration data and the legal historical data, historical valid data is obtained.

7. The method according to any one of claims 1 to 5, characterized in that: The step of generating a pouring simulation model corresponding to the self-compacting concrete according to the environmental information includes: According to the scene type, obtaining a standard casting model associated with the scene type; According to the casting space size, generating a simulated casting space in the standard casting model; The casting simulation model is generated based on the simulated casting space.

8. A self-compacting concrete construction quality control device based on machine learning, characterized in that: include: An environmental information acquisition unit, used to acquire environmental information corresponding to a target scene; The environmental information includes: casting space size and scene type; A pouring simulation model generating unit is used to generate a pouring simulation model corresponding to the self-compacting concrete according to the environmental information; the pouring simulation model is obtained by machine learning training based on preset historical valid data; the historical valid data is obtained after data cleaning of all historical engineering data; A behavior control unit is used to import preset construction behavior data into the casting simulation model, perform behavior control on the construction behavior data, and obtain control behavior data; the control behavior data is behavior data when the performance data of the self-compacting concrete meets the target scenario to the corresponding performance index.

9. An electronic 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 method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images