Concrete hydration heat prediction system based on internet of things and multi-source data fusion

Abstract

The application relates to the technical field of concrete detection, in particular to a concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion, which comprises a data acquisition module, a space division module, a point distribution determination module, a data mapping module, a space discrimination module, an environment verification module and a prediction output module. The data acquisition module is used to acquire structure drawings, material attributes and construction parameters of concrete structures to be poured. The space division module is used to divide a plurality of space units. The point distribution determination module is used to determine the types of the plurality of space units. The data mapping module is used to map temperature data to corresponding space units. The space discrimination module is used to perform space consistency verification and correct temperature data that fails to pass the verification to obtain effective temperature data. The environment verification module is used to determine whether the space units have hydration heat reaction representation capabilities. The prediction output module is used to output prediction results. The application improves the accuracy of concrete hydration heat prediction.

Description

Technical Field

[0001] This invention relates to the field of concrete testing technology, and in particular to a concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion. Background Technology

[0002] With the rapid development of the construction industry, concrete is increasingly widely used in building engineering. However, the environmental impact of concrete construction processes and performance changes is receiving increasing attention. Among these factors, the heat of hydration in concrete is a key one, affecting not only the setting time but also potentially causing structural temperature fluctuations. This can lead to uneven internal temperatures within buildings, resulting in various problems such as cracking and expansion. Current technologies for anomaly handling of collected data typically focus on detecting outliers in the temperature values ​​themselves, lacking effective judgment of the spatial correspondence of the data. Even when monitoring data values ​​are within the normal range, if their actual spatial location is incorrect, they may still be input into the heat of hydration analysis model as normal data. This causes aliasing of temperature change characteristics at different spatial locations, resulting in a temperature field that fails to accurately reflect the actual temperature distribution within the concrete.

[0003] Chinese Patent Publication No. CN120706128A discloses a method, system, and equipment for predicting the heat of hydration and adiabatic temperature of concrete mixed with slag powder. The system includes: a hydration heat prediction model construction unit, configured to express the total heat release of the silicate cement-slag system as the sum of the heat release of hydration of silicate cement and the heat release of hydration of slag, thus obtaining a silicate cement-slag hydration heat release prediction model; and an adiabatic temperature prediction unit, configured to multiply the total heat release of the silicate cement-slag system calculated by the silicate cement-slag hydration heat release prediction model by the amount of cementitious material used per cubic meter, as the internal heat source term in the concrete heat conduction differential equation, and solve the concrete heat conduction differential equation using the finite difference method to obtain the temperature field distribution of the concrete under adiabatic conditions; wherein, the heat release of hydration of silicate cement is calculated based on the degree of hydration of silicate cement, and the degree of hydration of silicate cement is predicted by a silicate cement hydration degree prediction model.

[0004] Therefore, it can be seen that the method, system and equipment for predicting the hydration heat and adiabatic temperature of concrete with slag powder have the problem of low reliability in predicting the hydration heat due to insufficient integration of the prediction process with actual construction monitoring data and the inability to effectively eliminate abnormal data, which leads to insufficient adaptability of the prediction results to actual concrete temperature changes. Summary of the Invention

[0005] To address this, the present invention provides a concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion, which overcomes the problems in the prior art where it is difficult to accurately establish the correspondence between multi-source monitoring data and concrete spatial units, and where abnormal monitoring data is easily transmitted to the hydration heat prediction process, resulting in low reliability of the hydration heat prediction results.

[0006] To achieve the above objectives, the present invention provides a concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion, comprising: The data acquisition module is used to acquire structural drawings, material properties, and construction parameters of the concrete structure to be poured. The spatial division module is used to determine the pouring benchmark of the concrete structure to be poured according to the structural drawings and the construction parameters to divide it into several spatial units, and bind the material properties and benchmark coordinates to the corresponding spatial units. The placement determination module is used to determine the types of the several spatial units and, based on the determination results and the reference coordinates, determine the sensor placement scheme to deploy the temperature sensor. The data mapping module is used to acquire the temperature data collected by the temperature sensor and map the temperature data to the corresponding spatial unit according to the reference coordinates. The spatial discrimination module is used to perform spatial consistency verification on the spatial units represented by the temperature data and the mapped spatial units, and to correct the temperature data that fails the verification to obtain valid temperature data. An environmental verification module is used to perform environmental coupling verification on the space unit based on the effective temperature data, and to determine whether the space unit has the ability to characterize the heat of hydration reaction. The prediction output module is used to input the effective temperature data into the concrete hydration heat prediction model to participate in the hydration heat prediction and output the prediction result when the hydration heat reaction characterization capability verification is passed.

[0007] Furthermore, the space division module is used to determine the design space range of the concrete structure to be poured based on the structural drawings, and to modify the design space range based on the construction parameters to determine the pouring area, so as to divide the space into units.

[0008] Furthermore, the point determination module is used to determine the critical distance value between shallow and deep layers based on the casting reference. The point determination module is used to calculate the shortest distance from the center of the spatial unit to the outer surface of the concrete structure to be poured; The point determination module is used to determine that the spatial unit is a shallow spatial unit when the shortest distance is less than or equal to the shallow-deep critical distance value. The point determination module is used to determine that the spatial unit is a deep spatial unit when the shortest distance is greater than the critical distance between shallow and deep layers.

[0009] Furthermore, the sensor placement module is used to determine the sensor placement location of each spatial unit according to the type of the spatial unit and the temperature monitoring requirements of the concrete to be poured corresponding to the pouring reference, and to record the correspondence between the sensor and the spatial unit to form a sensor placement scheme for deploying temperature sensors.

[0010] Furthermore, the spatial discrimination module is used to obtain the actual installation location information of the temperature sensor corresponding to the temperature data, and to determine the actual spatial unit to which the temperature sensor belongs based on the actual installation location information and the pouring reference of the concrete structure to be poured. The spatial discrimination module is used to perform spatial consistency verification on the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit; The spatial discrimination module is used to determine that the spatial consistency verification is passed and generate valid temperature data based on the temperature data when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are consistent. The spatial discrimination module is used to determine that the spatial consistency verification has failed and obtain the temperature data that failed the verification when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are inconsistent.

[0011] Furthermore, the spatial discrimination module is used to determine the corresponding spatial unit based on the actual spatial location of the sensor when the spatial consistency verification fails, to deassociate the temperature data from the original spatial unit and reassociate the data to the spatial unit determined based on the actual spatial location, to update the association record between the sensor and the spatial unit and to perform consistency verification, and to generate corrected valid temperature data after the verification is passed.

[0012] Furthermore, the environmental verification module is used to calculate the temperature change based on temperature data over a continuous time period within the same spatial unit, and to determine the direction and rate of temperature change for the corresponding spatial unit based on the temperature change. The environmental verification module is used to determine that the temperature trend in the space unit is consistent when the direction of temperature change in the space unit is continuous and the rate of change conforms to the change law in the heat of hydration of concrete. The environmental verification module is used to determine that the temperature trend in the space unit is abnormal when the direction of temperature change in the space unit is discontinuous or the rate of change does not conform to the change law in the heat of hydration of concrete.

[0013] Furthermore, the environmental verification module is used to determine that the space unit has data representation capability when the temperature trend is consistent within the space unit; The environmental verification module is used to determine that the space unit does not have data representation capability when the temperature trend in the space unit is abnormal, and to mark the effective temperature data corresponding to the space unit as temperature data to be corrected.

[0014] Furthermore, the environmental verification module is used to acquire the temperature data to be corrected and to determine the temperature correction trajectory based on the temperature change trend of the adjacent time series of the temperature data to be corrected. The environmental verification module is used to determine the corrected temperature value of the time node corresponding to the temperature data to be corrected based on the temperature correction trajectory, and to adjust the corrected temperature value using the temperature change relationship between adjacent spatial units to obtain the corrected temperature data. The environmental verification module is used to re-verify the corrected temperature data using environmental coupling, and outputs the corrected temperature data as valid temperature data after the verification is passed.

[0015] Furthermore, the prediction output module is used to input the effective temperature data into the concrete hydration heat prediction model. The model combines the hydration heat release and the heat transfer relationship between different spatial units to calculate the temperature change of each spatial unit at future prediction time points, and forms the prediction trend of the internal temperature of concrete at future times based on the predicted temperature of each spatial unit.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the system of the present invention determines the sensor layout scheme according to the hierarchical attributes of the spatial unit, so that the temperature sensors can be reasonably arranged according to different depth areas of the concrete structure, improving the targeting of the sensor layout, and enabling the collected temperature data to more comprehensively reflect the spatial distribution and evolution process of the internal temperature field of the concrete. Through spatial consistency verification, it can identify inaccurate spatial attribution data caused by sensor data association errors, spatial mapping deviations, etc., avoiding erroneous spatial information from entering the subsequent hydration heat prediction process, improving the spatial accuracy of the prediction model input data. By judging the data representation capability of each spatial unit, it can determine whether the data collected by each spatial unit conforms to the actual law of temperature change over time and spatial transmission during the hydration heat process of concrete, so that the data input to the hydration heat prediction model has both spatial consistency and reasonable change, overcoming the problems of unclear correspondence between sensor data and actual spatial location, failure to identify and process abnormal temperature data in a timely manner, and invalid monitoring data participating in the prediction, which lead to large deviations in the hydration heat prediction results, thus improving the accuracy of concrete hydration heat prediction.

[0017] Furthermore, the system of the present invention determines the layered attributes of spatial units, enabling different spatial locations to correspond to different temperature change characteristics. Since the internal areas of concrete are significantly affected by the heat of hydration, their temperature changes slowly, while areas near the outer surface are more significantly affected by environmental heat dissipation, resulting in faster temperature changes. Layered determination of spatial units can differentiate temperature monitoring needs under different heat transfer conditions, improving the targeting of sensor placement. This allows temperature sensors to be rationally configured for deep areas, shallow areas, and key temperature change areas, avoiding the problems of insufficient monitoring in some key areas and repeated monitoring in others caused by fixed spacing or random point placement in traditional methods. This improves the matching degree between the temperature monitoring scheme and the actual concrete structure, overcoming the problems of incomplete temperature acquisition, insufficient accuracy of spatial temperature distribution analysis, and large deviations in hydration heat prediction results caused by the inability of traditional sensor placement methods to adapt to differences in heat transfer in different areas. This further improves the accuracy of concrete hydration heat prediction.

[0018] Furthermore, the system of the present invention can determine whether the correlation between the temperature sensor data and its mapped spatial unit is accurate by performing spatial consistency verification between the temperature data and the actual corresponding spatial location. This avoids the problem of temperature data being incorrectly associated with non-corresponding spatial areas due to factors such as changes in sensor installation location, data mapping errors, or spatial correlation recording deviations. When the spatial consistency verification fails, the incorrect association between the temperature data and the original spatial unit is released, and it is remapped to the correct spatial unit. This achieves automatic correction of spatially correlated erroneous data, improves data utilization, avoids the loss of effective monitoring data due to local spatial correlation anomalies, and prevents erroneous associations from re-entering the subsequent analysis process. It overcomes the problem of distorted input data for the hydration heat prediction model due to sensor data spatial mapping errors and inaccurate spatial assignment of temperature data, which in turn causes large deviations in the predicted results of the internal temperature field of concrete. This further improves the accuracy of concrete hydration heat prediction.

[0019] Furthermore, the system described in this invention, by verifying the temperature trend within a spatial unit, can determine whether the temperature change in a single monitoring area conforms to its own hydration heat development characteristics, judge the continuity of the temperature change direction and the rate of change, distinguish between normal temperature fluctuations and abnormal temperature changes, avoid misjudgments caused by relying solely on a single temperature value, overcome the problem of erroneous temperature data participating in subsequent predictions due to sensor acquisition fluctuations, abnormal data transmission, or local data mutations, improve the ability of temperature monitoring data to represent the actual temperature field distribution, comprehensively judge the data representation capability of spatial units, establish a temperature correction trajectory for temperature data to be corrected that lacks representation capability, and adjust the correction results in conjunction with spatial temperature correlation, so that the corrected temperature data simultaneously meets the requirements of temporal continuity and spatial distribution rationality, improve the ability of temperature monitoring data to truly represent the concrete hydration heat process, enhance the accuracy and stability of the input prediction model data, overcome the problem that the hydration heat prediction results are greatly biased due to local fluctuations, single-point anomalies, and unclear spatial temperature change relationships in temperature sensor acquisition data, and cannot accurately reflect the evolution process of the internal temperature field of concrete, further improving the accuracy of concrete hydration heat prediction. Attached Figure Description

[0020] Figure 1 This is an overall structural block diagram of the concrete hydration heat prediction system based on the fusion of Internet of Things and multi-source data according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of determining the types of several spatial units in a concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating the spatial consistency verification process of the concrete hydration heat prediction system based on the fusion of Internet of Things and multi-source data in an embodiment of the present invention. Figure 4 This is a flowchart illustrating the process by which the concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion determines whether a spatial unit has the ability to characterize hydration heat reaction, according to an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0022] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0024] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] Please see Figure 1 The diagram shown is an overall structural block diagram of a concrete hydration heat prediction system based on the fusion of Internet of Things and multi-source data according to an embodiment of the present invention. The system described in this embodiment includes: The data acquisition module is used to acquire structural drawings, material properties, and construction parameters of the concrete structure to be poured. A spatial division module, which is connected to the data acquisition module, is used to determine the pouring benchmark of the concrete structure to be poured according to the structural drawings and the construction parameters to divide it into several spatial units, and bind the material properties and benchmark coordinates to the corresponding spatial units. The placement determination module, which is connected to the space division module, is used to determine the types of the several spatial units and determine the sensor placement scheme based on the determination result and the reference coordinates to deploy the temperature sensor. A data mapping module, which is connected to the point determination module, is used to acquire temperature data collected by the temperature sensor and map the temperature data to the corresponding spatial unit according to the reference coordinates. A spatial discrimination module, which is connected to the data mapping module, is used to perform spatial consistency verification on the spatial unit represented by the temperature data and the mapped spatial unit, and to correct the temperature data that fails the verification to obtain valid temperature data. An environmental verification module, which is connected to the space discrimination module, is used to perform environmental coupling verification on the space unit based on the effective temperature data, and to determine whether the space unit has the ability to characterize the heat of hydration reaction. The prediction output module, which is connected to the environmental verification module, is used to input the effective temperature data into the concrete hydration heat prediction model to participate in the hydration heat prediction and output the prediction result when the hydration heat reaction characterization capability verification is passed.

[0026] Specifically, the concrete structure to be poured is the target structural entity that has not yet been poured during the construction process and needs to be formed by concrete construction.

[0027] Specifically, structural drawings include the structural shape information of the concrete structure to be poured, the dimensional information of the concrete structure to be poured, and the elevation information of the concrete structure to be poured.

[0028] Specifically, material properties include cementitious material properties, thermal properties, and hydration characteristic parameters.

[0029] Specifically, construction parameters are data that reflect the actual concrete construction process and environmental conditions.

[0030] Specifically, the reference coordinates are unified spatial reference coordinates used to describe the spatial positions and their relative positions in the concrete structure to be poured.

[0031] Specifically, the casting reference includes reference coordinates, reference axis, and reference surface.

[0032] In this embodiment, the system determines the sensor placement scheme based on the hierarchical attributes of spatial units, enabling temperature sensors to be rationally arranged according to different depth regions of the concrete structure. This improves the targeting of sensor placement and allows the collected temperature data to more comprehensively reflect the spatial distribution and evolution of the internal temperature field of the concrete. Through spatial consistency verification, inaccurate spatial attribution data caused by sensor data association errors, spatial mapping deviations, etc., can be identified, preventing erroneous spatial information from entering the subsequent hydration heat prediction process and improving the spatial accuracy of the prediction model input data. By judging the data representation capability of each spatial unit, it can be determined whether the data collected by each spatial unit conforms to the actual laws of temperature change over time and spatial transmission during the concrete hydration heat process. This ensures that the data input to the hydration heat prediction model has both spatial consistency and reasonable variation, overcoming the problems of unclear correspondence between sensor data and actual spatial location, failure to promptly identify and process abnormal temperature data, and the participation of invalid monitoring data in prediction, which lead to large deviations in hydration heat prediction results. This improves the accuracy of concrete hydration heat prediction.

[0033] Please see Figure 2 As shown, it is a logical flowchart of the process of determining the types of the plurality of spatial units in an embodiment of the present invention.

[0034] Specifically, the space division module is used to determine the design space range of the concrete structure to be poured based on the structural drawings, and to modify the design space range based on the construction parameters to determine the pouring area, so as to divide the space into units.

[0035] Specifically, the point determination module is used to determine the critical distance value between shallow and deep layers based on the pouring reference. The point determination module is used to calculate the shortest distance from the center of the spatial unit to the outer surface of the concrete structure to be poured; The point determination module is used to determine that the spatial unit is a shallow spatial unit when the shortest distance is less than or equal to the shallow-deep critical distance value. The point determination module is used to determine that the spatial unit is a deep spatial unit when the shortest distance is greater than the critical distance between shallow and deep layers.

[0036] Specifically, the sensor placement module is used to determine the sensor placement location of each spatial unit according to the type of the spatial unit and the temperature monitoring requirements of the concrete to be poured corresponding to the pouring reference, and to record the correspondence between the sensor and the spatial unit to form a sensor placement scheme for deploying temperature sensors.

[0037] Specifically, a spatial unit is a concrete area with a continuous spatial range, determined by the geometric boundaries, pouring zones, and material distribution of the concrete structure to be poured in space. It serves as the basic spatial object for spatial attribution of temperature monitoring data and prediction of hydration heat.

[0038] Specifically, the shallow spatial unit is a concrete spatial unit whose center is close to the pouring reference and is significantly affected by heat exchange from the external environment.

[0039] Specifically, a deep spatial unit is a concrete spatial unit whose center is far from the casting reference and is less affected by the external environment.

[0040] Specifically, the sensor placement scheme is a plan for the installation locations and corresponding relationships of temperature sensors.

[0041] Specifically, the process of calculating the shortest distance from the center of a spatial unit to the outer surface of the concrete structure to be poured is as follows: determine the outer surface boundary of the concrete structure to be poured based on the structural drawings, and determine the center position of each spatial unit based on the spatial division results. Taking the center position of the spatial unit as the starting point, calculate the spatial distance between that position and each outer surface of the concrete structure, and compare the obtained spatial distances. The minimum value among them is determined as the shortest distance from the center position of the spatial unit to the outer surface of the concrete structure to be poured.

[0042] Specifically, the correspondence between the sensor and the spatial unit is determined by the spatial coordinates of the temperature sensor in the concrete spatial reference based on the actual installation location information of the temperature sensor, and the spatial unit and spatial level to which the temperature sensor belongs are determined based on the spatial coordinates and the spatial boundary relationship of each spatial unit. The spatial affiliation relationship between the temperature sensor and the spatial unit is established to describe the spatial unit where the temperature sensor is located.

[0043] Specifically, the process of determining the critical distance values ​​between deep and shallow layers involves determining the distribution constraints of monitoring point locations based on the temperature field distribution, using the distance from the outer surface of the concrete to different internal locations as the dividing line, and combining the thickness of the concrete structure to be poured and the arrangement of temperature monitoring points to determine the critical distance values ​​between deep and shallow layers that characterize the difference between the temperature changes on the outer surface and the internal temperature changes.

[0044] Specifically, the critical distance between deep and shallow layers can be determined according to the surface temperature of the concrete pouring body specified in GB 50496-2018, preferably the temperature 50mm inside the surface of the concrete pouring body. In this embodiment, the critical distance between deep and shallow layers is set to 50mm. Those skilled in the art can dynamically adjust the critical distance between deep and shallow layers according to the actual parameters of the concrete pouring body, which will not be elaborated here.

[0045] Understandably, the design space range of the concrete structure to be poured is obtained from the structural drawings, and the design range is adjusted in combination with the actual construction parameters to determine the actual pouring area. The pouring area is then divided into multiple spatial units with independent spatial location information, providing a basis for the correspondence between temperature data and spatial location. A unified spatial reference system is established based on the pouring benchmark, and the critical distance values ​​for shallow and deep layers are determined by combining the dimensions of the concrete structure and the temperature transfer characteristics. For each spatial unit, the shortest distance from its center to the outer surface of the concrete is calculated, and this distance is compared with the critical distance values ​​for shallow and deep layers. When the shortest distance is less than or equal to the critical distance value, the spatial unit is determined to be a shallow spatial unit; when the shortest distance is greater than the critical distance value, the spatial unit is determined to be a deep spatial unit. The sensor placement locations are determined based on the hierarchical attributes of different spatial units and the requirements for hydration heat monitoring, and the correspondence between the sensors and spatial units is recorded to form a sensor placement scheme. This method enables the sensors to be rationally arranged for different temperature variation areas, improving the coverage of temperature acquisition data on the internal temperature field distribution of concrete, and providing an accurate data foundation for subsequent spatial mapping of temperature data, hydration heat analysis, and prediction.

[0046] In this embodiment, the system determines the layered attributes of spatial units, enabling different spatial locations to correspond to different temperature change characteristics. Since the internal areas of concrete are significantly affected by hydration heat, their temperature changes slowly, while areas near the outer surface are more significantly affected by environmental heat dissipation, resulting in faster temperature changes. Layering spatial units allows for differentiation of temperature monitoring needs under different heat transfer conditions, improving the targeting of sensor placement. This enables temperature sensors to be rationally configured for deep areas, shallow areas, and key temperature change areas, avoiding the problems of insufficient monitoring in some key areas and repeated monitoring in others caused by fixed spacing or random placement methods in traditional methods. This improves the matching degree between the temperature monitoring scheme and the actual concrete structure, overcoming the problems of incomplete temperature acquisition, insufficient accuracy of spatial temperature distribution analysis, and large deviations in hydration heat prediction results caused by the inability of traditional sensor placement methods to adapt to differences in heat transfer in different areas. This further improves the accuracy of concrete hydration heat prediction.

[0047] Please see Figure 3 The diagram shown is a logical flowchart of the spatial consistency verification process according to an embodiment of the present invention.

[0048] Specifically, the spatial discrimination module is used to obtain the actual installation location information of the temperature sensor corresponding to the temperature data, and to determine the actual spatial unit to which the temperature sensor belongs based on the actual installation location information and the pouring reference of the concrete structure to be poured. The spatial discrimination module is used to perform spatial consistency verification on the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit; The spatial discrimination module is used to determine that the spatial consistency verification is passed and generate valid temperature data based on the temperature data when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are consistent. The spatial discrimination module is used to determine that the spatial consistency verification has failed and obtain the temperature data that failed the verification when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are inconsistent.

[0049] Specifically, the spatial discrimination module is used to determine the corresponding spatial unit based on the actual spatial location of the sensor when the spatial consistency verification fails, to deassociate the temperature data with the original spatial unit and reassociate the data with the spatial unit determined based on the actual spatial location, to update the association record between the sensor and the spatial unit and to perform consistency verification, and to generate corrected valid temperature data after the verification is passed.

[0050] Specifically, spatial consistency refers to the consistency between the spatial unit represented by the temperature sensor and the actual spatial unit corresponding to the temperature sensor.

[0051] It is understandable that the actual installation location information of the temperature sensor is obtained according to the temperature sensor identifier corresponding to the temperature data, and the spatial unit where the actual installation location is located is determined with reference to the pouring benchmark of the concrete structure to be poured, as the actual representation spatial unit of the temperature data. Obtain the mapping space unit corresponding to the temperature data in the data mapping process, and compare whether the actual representation space unit is consistent with the mapping space unit. If the actual representation space unit is consistent with the mapping space unit, the temperature data is consistent with the spatial assignment of its actual collection location, the spatial consistency check is passed, and the temperature data is determined to be valid temperature data. If the actual representation space unit is inconsistent with the mapped space unit, the temperature data has a spatial association error. The spatial unit to which the temperature sensor belongs is re-determined based on the actual installation location of the temperature sensor, the association between the temperature data and the original mapped space unit is released, and the temperature data is re-associated to the actual spatial unit. At the same time, the association record between the temperature sensor and the space unit is updated. After the re-association is completed, the spatial unit to which the temperature sensor belongs is determined again based on the actual installation location of the temperature sensor and compared with the updated mapping result. If the comparison is consistent again, the correction is determined to be successful and the corresponding temperature data is output as valid temperature data, thereby ensuring that the temperature data entering the subsequent processing process has the correct spatial assignment.

[0052] In this embodiment, the system performs spatial consistency verification between temperature data and its mapped spatial units. This allows the system to determine the accuracy of the correlation between the temperature sensor data and the actual corresponding spatial location. This avoids the problem of temperature data being incorrectly associated with non-corresponding spatial areas due to factors such as changes in sensor installation location, data mapping errors, or spatial correlation recording deviations. When the spatial consistency verification fails, the system removes the erroneous association between the temperature data and the original spatial unit and remaps it to the correct spatial unit. This achieves automatic correction of spatially correlated erroneous data, improves data utilization, avoids the loss of effective monitoring data due to local spatial correlation anomalies, and prevents erroneous associations from re-entering the subsequent analysis process. This overcomes the problem of distorted input data for the hydration heat prediction model due to incorrect spatial mapping of sensor data and inaccurate spatial attribution of temperature data, which in turn causes large deviations in the predicted results of the internal temperature field of concrete. This further improves the accuracy of concrete hydration heat prediction.

[0053] Please see Figure 4 The diagram shown is a logical flowchart of the process for determining whether the spatial unit has the ability to characterize the heat of hydration reaction according to an embodiment of the present invention.

[0054] Specifically, the environmental verification module is used to calculate the temperature change based on temperature data over a continuous time period within the same spatial unit, and to determine the direction and rate of temperature change for the corresponding spatial unit based on the temperature change. The environmental verification module is used to determine that the temperature trend in the space unit is consistent when the direction of temperature change in the space unit is continuous and the rate of change conforms to the change law in the heat of hydration of concrete. The environmental verification module is used to determine that the temperature trend in the space unit is abnormal when the direction of temperature change in the space unit is discontinuous or the rate of change does not conform to the change law in the heat of hydration of concrete.

[0055] Specifically, the environmental verification module is used to determine that the space unit has data representation capability when the temperature trend is consistent within the space unit; The environmental verification module is used to determine that the space unit does not have data representation capability when the temperature trend in the space unit is abnormal, and to mark the effective temperature data corresponding to the space unit as temperature data to be corrected.

[0056] Specifically, the environmental verification module is used to acquire the temperature data to be corrected and to determine the temperature correction trajectory based on the temperature change trend of the temperature data in adjacent time periods. The environmental verification module is used to determine the corrected temperature value of the time node corresponding to the temperature data to be corrected based on the temperature correction trajectory, and to adjust the corrected temperature value using the temperature change relationship between adjacent spatial units to obtain the corrected temperature data. The environmental verification module is used to re-verify the corrected temperature data using environmental coupling, and outputs the corrected temperature data as valid temperature data after the verification is passed.

[0057] Specifically, the prediction output module is used to input the effective temperature data into the concrete hydration heat prediction model. The model combines the hydration heat release and the heat transfer relationship between different spatial units to calculate the temperature change of each spatial unit at a future prediction time node, and forms the prediction trend of the internal temperature of concrete at future times based on the predicted temperature of each spatial unit.

[0058] Specifically, the temperature data to be corrected is the temperature data that, after being verified for validity, was determined to be unable to accurately reflect the actual temperature change status of the corresponding space unit and requires further adjustment.

[0059] Specifically, the temperature change trend refers to the pattern of concrete temperature change over time, which reflects the temperature evolution during the heat of hydration release process.

[0060] Specifically, data representation capability refers to the ability of temperature data in a space cell to accurately reflect the actual temperature state and its change process of the space cell.

[0061] Specifically, the concrete hydration heat prediction model can be a hydration heat mechanism model, a heat conduction model, or a machine learning regression model. In this embodiment, the concrete hydration heat prediction model is a hydration heat mechanism model.

[0062] Understandably, the continuous temperature data of the same spatial unit are sorted according to the acquisition time, the temperature change between adjacent time nodes is calculated, and the direction and rate of temperature change are determined by combining the time interval between adjacent time nodes. The continuity analysis of temperature changes within a continuous time period is performed to determine whether there are frequent reversals in the direction of temperature change, and whether there are abrupt changes in the rate of change that are inconsistent with the normal hydration temperature evolution process. If the direction of temperature change can remain continuous and the rate of change changes reasonably with the temperature evolution process, then the temperature data of the spatial unit is considered to have formed a continuous and stable change process, and the temperature trend is determined to be consistent. If the direction of temperature change reverses abnormally, or the rate of change changes significantly and cannot be explained by the normal hydration process, the temperature trend is determined to be abnormal, indicating that the current data cannot truly reflect the actual temperature state of the space region. Therefore, the corresponding temperature data is marked as temperature data to be corrected. For data entering the correction process, a continuous change trajectory is established based on normal data before and after the anomaly, and a reasonable temperature range for the anomaly time node is determined. Then, the reasonable temperature is corrected using the temperature changes of the surrounding spatial location during the same period. After the correction is completed, the continuity relationship between the correction point and the data before and after, as well as the surrounding data, is rechecked. Once the requirements are met, the data is restored to usable data. Subsequently, the usable temperature data of each spatial unit is used as the current state and input into the prediction model. The model calculates the temperature of each location in the future hourly based on the process of heat generation inside the concrete and heat transfer to the surrounding area, and restores the overall future temperature distribution of the concrete according to the spatial location.

[0063] In this embodiment, the system verifies the temperature trend within a spatial unit to determine whether the temperature change in a single monitoring area conforms to its own hydration heat development characteristics. This avoids erroneous temperature data from sensor fluctuations, abnormal data transmission, or sudden local data mutations from being used in subsequent predictions. By comparing the temperature change trends between adjacent spatial units and combining the heat transfer laws between different spatial locations, the system determines whether the temperature changes in different areas have spatial correlations. This ensures that the temperature data not only meets the requirements of temporal continuity but also the laws governing the temperature field changes within the concrete, improving the ability of temperature monitoring data to represent the actual temperature field distribution. By comprehensively judging the data representation capabilities of spatial units, a temperature correction trajectory is established for temperature data that lacks representation capabilities. The correction results are then adjusted based on spatial temperature correlations, ensuring that the corrected temperature data simultaneously meets the requirements of temporal continuity and spatial distribution rationality. This improves the ability of temperature monitoring data to accurately represent the concrete hydration heat process, enhances the accuracy and stability of the data input to the prediction model, and overcomes the problems of large deviations in hydration heat prediction results and inaccurate reflection of the internal temperature field evolution process due to local fluctuations, single-point anomalies, and unclear spatial temperature change relationships in temperature sensor data. This further improves the accuracy of concrete hydration heat prediction.

[0064] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A concrete hydration heat prediction system based on the Internet of Things and multi-source data fusion, characterized in that, include: The data acquisition module is used to acquire structural drawings, material properties, and construction parameters of the concrete structure to be poured. The spatial division module is used to determine the pouring benchmark of the concrete structure to be poured according to the structural drawings and the construction parameters to divide it into several spatial units, and bind the material properties and benchmark coordinates to the corresponding spatial units. The placement determination module is used to determine the types of the several spatial units and, based on the determination results and the reference coordinates, determine the sensor placement scheme to deploy the temperature sensor. The data mapping module is used to acquire the temperature data collected by the temperature sensor and map the temperature data to the corresponding spatial unit according to the reference coordinates. The spatial discrimination module is used to perform spatial consistency verification on the spatial units represented by the temperature data collected by the temperature sensor and the mapped spatial units, and to correct the temperature data that fails the verification to obtain valid temperature data. An environmental verification module is used to perform environmental coupling verification on the space unit based on the effective temperature data, and to determine whether the space unit has the ability to characterize the heat of hydration reaction. The prediction output module is used to input the effective temperature data into the concrete hydration heat prediction model to participate in the hydration heat prediction and output the prediction result when the hydration heat reaction characterization capability verification is passed.

2. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 1, characterized in that, The space division module is used to determine the design space range of the concrete structure to be poured according to the structural drawings, and to modify the design space range according to the construction parameters to determine the pouring area, so as to divide the space into units.

3. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 2, characterized in that, The point determination module is used to determine the critical distance values ​​between shallow and deep layers based on the pouring reference. The point determination module is used to calculate the shortest distance from the center of the spatial unit to the outer surface of the concrete structure to be poured; The point determination module is used to determine that the spatial unit is a shallow spatial unit when the shortest distance is less than or equal to the shallow-deep critical distance value. The point determination module is used to determine that the spatial unit is a deep spatial unit when the shortest distance is greater than the critical distance between shallow and deep layers.

4. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 3, characterized in that, The sensor placement module is used to determine the sensor placement location of each spatial unit according to the type of the spatial unit and the temperature monitoring requirements of the concrete to be poured corresponding to the pouring reference, and to record the correspondence between the sensor and the spatial unit to form a sensor placement scheme for deploying temperature sensors.

5. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 4, characterized in that, The spatial discrimination module is used to obtain the actual installation location information of the temperature sensor corresponding to the temperature data collected by the temperature sensor, and to determine the actual spatial unit to which the temperature sensor belongs based on the actual installation location information and the pouring reference of the concrete structure to be poured. The spatial discrimination module is used to perform spatial consistency verification on the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit; The spatial discrimination module is used to determine that the spatial consistency verification is passed and generate valid temperature data based on the temperature data collected by the temperature sensor when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are consistent. The spatial discrimination module is used to determine that the spatial consistency verification has failed and obtain the temperature data that failed the verification when the actual spatial unit to which the temperature sensor belongs and the mapped spatial unit are inconsistent.

6. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 5, characterized in that, The spatial discrimination module is used to determine the corresponding spatial unit based on the actual spatial location of the sensor when the spatial consistency verification fails. It then disconnects the temperature data that failed the verification from the original spatial unit and re-associates the temperature data that failed the verification to the spatial unit determined based on the actual spatial location. The module also updates the association record between the sensor and the spatial unit and performs consistency verification. After the verification is successful, it generates corrected valid temperature data.

7. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 6, characterized in that, The environmental verification module is used to calculate the temperature change based on temperature data over a continuous time period within the same spatial unit, and to determine the direction and rate of temperature change for the corresponding spatial unit based on the temperature change. The environmental verification module is used to determine that the temperature trend in the space unit is consistent when the direction of temperature change in the space unit is continuous and the rate of change conforms to the change law in the heat of hydration of concrete. The environmental verification module is used to determine that the temperature trend in the space unit is abnormal when the direction of temperature change in the space unit is discontinuous or the rate of change does not conform to the change law in the heat of hydration of concrete.

8. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 7, characterized in that, The environmental verification module is used to determine that the space unit has data representation capability when the temperature trend is consistent within the space unit. The environmental verification module is used to determine that the space unit does not have data representation capability when the temperature trend in the space unit is abnormal, and to mark the effective temperature data corresponding to the space unit as temperature data to be corrected.

9. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 8, characterized in that, The environmental verification module is used to acquire the temperature data to be corrected and to determine the temperature correction trajectory based on the temperature change trend of adjacent time series of the temperature data to be corrected. The environmental verification module is used to determine the corrected temperature value of the time node corresponding to the temperature data to be corrected based on the temperature correction trajectory, and to adjust the corrected temperature value using the temperature change relationship between adjacent spatial units to obtain the corrected temperature data. The environmental verification module is used to re-verify the corrected temperature data using environmental coupling, and outputs the corrected temperature data as valid temperature data after the verification is passed.

10. The concrete hydration heat prediction system based on Internet of Things and multi-source data fusion according to claim 9, characterized in that, The prediction output module is used to input the effective temperature data into the concrete hydration heat prediction model. The model combines the hydration heat release and the heat transfer relationship between different spatial units to calculate the temperature change of each spatial unit at the future prediction time node, and forms the prediction trend of the internal temperature of concrete at future time based on the predicted temperature of each spatial unit.

Images