Concrete strength prediction method based on multi-source data fusion

Abstract

The invention provides a concrete strength prediction method based on multi-source data fusion, and relates to the technical field of environmental monitoring, and the method comprises the following steps: based on real-time environmental parameters, calculating by using an empirical formula of a maturity method to obtain a first concrete strength value, and based on historical environmental parameters, calculating a second concrete strength value; calculating to obtain a second concrete strength value by utilizing an empirical formula of a maturity method; calculating a difference value between the first concrete strength value and the second concrete strength value to obtain a first concrete strength residual value, and training a machine learning model by taking the historical environmental parameter as an input feature and the first concrete strength residual value as a target variable to obtain a trained machine learning model; and inputting the real-time environmental parameters into the trained machine learning model to obtain a second concrete strength residual value, and obtaining a concrete strength predicted value based on the second concrete strength residual value and the first concrete strength value.

Description

Technical Field

[0001] The present application belongs to the field of environmental monitoring technology, and specifically relates to a concrete strength prediction method based on multi-source data fusion. Background Art

[0002] As the modern construction industry continues to demand higher quality concrete structures and higher efficiency, concrete strength prediction and maintenance control have become key technologies in construction management. Traditionally, concrete strength assessment has relied on laboratory test blocks. While this method offers a certain degree of accuracy, it suffers from long lead times, high costs, and a lack of real-time feedback. This makes it difficult to meet the demands of modern engineering for rapid decision-making and refined management.

[0003] In recent years, with the advancement of sensor technology, data analysis methods, and artificial intelligence algorithms, the "maturity method," a method for estimating concrete strength based on temperature history, has been widely used for on-site strength prediction. Furthermore, machine learning technology, with its powerful nonlinear modeling capabilities, has shown great potential in the field of intelligent building. However, how to organically combine these advanced technologies and effectively improve the accuracy and practicality of concrete strength prediction remains a pressing challenge in the industry.

[0004] Currently, common concrete strength prediction methods include the following: Estimating concrete strength based on temperature changes during concrete curing, using the relationship between maturity index and time integral, and combining empirical formulas. Simple regression models are built using historical data, inputting parameters such as temperature and humidity for prediction. These methods ignore the complex relationships between multiple factors, resulting in large prediction errors and failing to cope with changing construction scenarios.

[0005] Relying solely on empirical formulas or single-variable models makes it difficult to accurately reflect the true development trend of concrete strength, especially in complex and changing construction site environments, where errors are significant. Existing methods are mostly static calculations that do not combine historical and real-time data for error compensation, making it impossible to achieve continuous optimization of the prediction model. Most maintenance systems use fixed threshold control and lack the ability to make intelligent judgments and dynamic adjustments based on concrete strength development trends, which can easily lead to over- or under-maintenance. The data collected by the system has not been fully integrated into a unified platform, making it impossible to monitor and adjust via remote terminals, limiting the flexibility and responsiveness of construction management. Summary of the Invention

[0006] This application provides a concrete strength prediction method based on multi-source data fusion to solve one of the above technical problems.

[0007] The technical solutions adopted in this application are:

[0008] The present invention provides a method for predicting concrete strength based on multi-source data fusion, comprising:

[0009] Based on the real-time environmental parameters, a first concrete strength value is calculated using the empirical formula of the maturity method, and based on the historical environmental parameters, a second concrete strength value is calculated using the empirical formula of the maturity method;

[0010] calculating a difference between the first concrete strength value and the second concrete strength value to obtain a first concrete strength residual value, using the historical environmental parameter as an input feature and the first concrete strength residual value as a target variable to train a machine learning model to obtain a trained machine learning model;

[0011] The real-time environmental parameters are input into the trained machine learning model to obtain a second concrete strength residual value, and a concrete strength prediction value is obtained based on the second concrete strength residual value and the first concrete strength value.

[0012] According to one embodiment of the present application, based on real-time environmental parameters, the first concrete strength value is calculated using the empirical formula of the maturity method, and based on historical environmental parameters, the second concrete strength value is calculated using the empirical formula of the maturity method, specifically:

[0013] Acquire the real-time environmental parameters, including ambient temperature, humidity, and curing time parameters, in real time through sensors;

[0014] The first concrete strength value of the concrete under the real-time environmental parameters is calculated using the empirical formula of the maturity method. The specific formula is as follows:

[0015] S(t)=S ∞ ·exp(-k·t)

[0016] Among them, S(t) represents the concrete strength value; S ∞ represents the final strength; k is the empirical coefficient, and t is the curing time;

[0017] collecting a data set containing said historical environmental parameters under specific conditions;

[0018] The second concrete strength value of the concrete under the historical environmental parameters is calculated using the empirical formula of the maturity method.

[0019] According to one embodiment of the present application, it further includes:

[0020] Preset concrete strength growth target value, humidity and temperature range;

[0021] comparing the concrete strength prediction value with the concrete strength growth target value;

[0022] If the predicted concrete strength value is less than the target concrete strength growth value, it is considered that the concrete strength growth under the current curing conditions is not ideal and the curing strategy needs to be dynamically adjusted.

[0023] According to one embodiment of the present application, the dynamic adjustment of the maintenance strategy includes:

[0024] If the humidity is lower than the lower limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic water spraying mechanism is triggered;

[0025] If the temperature exceeds the upper limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic ventilation mechanism is triggered.

[0026] According to one embodiment of the present application, the automatic water spraying mechanism is specifically:

[0027] When the humidity detected by the humidity sensor is lower than the lower limit of the preset range, DO outputs a high level, the indicator light lights up and the water pump is started;

[0028] When the humidity rises back to above the upper limit of the preset range, DO outputs a low level and stops adding water.

[0029] According to one embodiment of the present application, the automatic ventilation mechanism is specifically:

[0030] When the temperature detected by the temperature sensor is higher than the upper limit of the preset range, the fan is started to cool down;

[0031] When the temperature drops to within a preset range, the fan stops working.

[0032] According to one embodiment of the present application, it further includes:

[0033] The predicted concrete strength value and the real-time environmental parameters are uploaded to a mobile phone APP via a WiFi module. The user can check the current status and remotely adjust the humidity and temperature thresholds according to the actual situation.

[0034] A computer-readable storage medium stores a program, which implements the steps in the method when executed by a processor.

[0035] An electronic device comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein the steps in the method are implemented when the processor executes the program.

[0036] Due to the adoption of the above technical solution, the beneficial effects achieved by this application are as follows:

[0037] This application provides a preliminary estimate of concrete strength under current curing conditions, achieving real-time and non-destructive strength prediction. Compared with the traditional test block method, it saves a lot of time and resources and is suitable for the online monitoring needs of large-scale construction sites.

[0038] By introducing historical data for comparative analysis, we can identify deviations between current forecasts and historical trends, providing a foundation for subsequent model training. This approach improves the robustness of the forecast system and avoids misjudgments caused by short-term environmental disturbances.

[0039] By building a residual learning model based on historical data, we can automatically identify systematic errors in empirical formula forecasts and dynamically compensate for them. This process greatly improves forecast accuracy and enables the model to self-learn and continuously optimize.

[0040] The final concrete strength prediction not only comprehensively considers the impact of current environmental conditions but also accurately corrects the initial prediction using a machine learning model, resulting in a more realistic strength assessment. This method overcomes the limitations of traditional empirical formulas, which suffer from low accuracy and poor adaptability, significantly enhancing the credibility and application value of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 A flowchart of a concrete strength prediction method based on multi-source data fusion provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to more clearly illustrate the overall concept of the present application, a detailed description is given below in an illustrative manner in conjunction with the accompanying drawings.

[0044] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application may also be implemented in other ways than those described herein, and therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below. It should be noted that the embodiments of the present application and the features of each embodiment may be combined with each other unless there is a conflict.

[0045] In this application, unless otherwise expressly specified and limited, a first feature "above" or "below" a second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0046] Example 1

[0047] like Figure 1 As shown, a concrete strength prediction method based on multi-source data fusion includes:

[0048] Based on the real-time environmental parameters, the first concrete strength value is calculated using the empirical formula of the maturity method. Based on the historical environmental parameters, the second concrete strength value is calculated using the empirical formula of the maturity method.

[0049] As mentioned above, real-time environmental parameters refer to the specific environmental condition data collected at the current moment, such as temperature, humidity, etc. These data are obtained in real time through various sensors deployed on site (such as DS18B20 temperature sensor, humidity sensor, etc.).

[0050] Maturity method empirical formula: A method used to estimate concrete strength, usually in the form S(t) = S ∞ ·e -k·t in

[0051] S(t) represents the intensity at a specific time point, S ∞ is the final strength, k is the empirical coefficient, and t is the time.

[0052] Use the real-time collected data (such as current temperature, humidity, etc.) and substitute it into the empirical formula of the maturity method for calculation.

[0053] The result of this step is a preliminary estimated concrete strength value based on the current environmental conditions, called the "first concrete strength value".

[0054] Historical environmental parameters: refers to environmental condition data recorded over a certain period of time in the past. These data can be collected from previous projects or from the earlier stages of the same project, and they reflect the actual environmental conditions at different points in time.

[0055] Empirical formula of maturity method: Similarly, the above mentioned maturity method formula is used here to estimate the concrete strength.

[0056] Use historical data (such as past temperature, humidity records, etc.) and substitute it into the same empirical formula for calculation.

[0057] The result of this step is the concrete strength value calculated based on historical environmental conditions, which is called the "second concrete strength value".

[0058] For example, let’s assume that a concrete structure is being constructed on a construction site, and we are using an intelligent concrete curing system to monitor and optimize the curing process. Here are the steps:

[0059] First concrete strength value (based on real-time environmental parameters)

[0060] Real-time monitoring: At the current time point, the sensor detects that the ambient temperature at the construction site is 20°C and the relative humidity is 60%.

[0061] Applying an empirical formula: We input this real-time data into the maturity method’s empirical formula to estimate the concrete’s strength development under current conditions. This formula aims to predict the concrete’s strength growth over a specific time period based on known conditions such as temperature and humidity.

[0062] The system calculates that, under the current conditions, after seven days of curing, the concrete will reach a strength of approximately 39.43 MPa. This is what we call the "first concrete strength value," which reflects the concrete's potential strength under the current actual environmental conditions.

[0063] Second concrete strength value (based on historical environmental parameters)

[0064] Reviewing historical data: Now let's look at the historical data for the same location over the past month. We find that the average temperature during this period was approximately 22°C and the average relative humidity was 58%.

[0065] Reapply the empirical formula: Using these historical data as input, the empirical formula of the maturity method is reapplied to calculate. This is done to understand what the strength growth trend of concrete is under similar but non-current specific conditions.

[0066] Results: Calculations based on historical data indicate that, under similar conditions, the expected strength of the concrete after a seven-day curing period is approximately 38.5 MPa. This is our "second concrete strength value," which provides a reference for concrete strength development under similar but different environmental conditions.

[0067] It should be noted that in specific implementation scenarios, the above scheme can also be used to identify the limitations and sources of error in the empirical formula by comparing the difference between the first concrete strength value (real-time prediction value) and the actual measured value, as well as the difference between the second concrete strength value (historical prediction value) and the actual measured value. Based on the above analysis results, the parameters in the empirical formula can be regularly updated or corrected to make them more realistic. In addition, machine learning algorithms can be introduced to continuously optimize the hybrid model and improve prediction accuracy.

[0068] In specific implementation scenarios, building on the above solution, if the first concrete strength value falls significantly below the expected target (for example, due to extreme weather conditions), the system can automatically trigger an early warning mechanism, alerting management to take emergency measures (such as increasing water spraying or strengthening ventilation). Trend reports generated based on historical data can help predict potential future problems and prepare for them in advance. For example, identifying which seasons or conditions are more prone to slower concrete strength growth allows for the development of corresponding preventative strategies.

[0069] Calculate the difference between the first concrete strength value and the second concrete strength value to obtain a first concrete strength residual value, use the historical environmental parameter as an input feature, and use the first concrete strength residual value as a target variable to train a machine learning model to obtain a trained machine learning model.

[0070] As mentioned above, the first concrete strength value is the concrete strength prediction value calculated using the maturity method's empirical formula based on current real-time environmental conditions (such as temperature and humidity). The second concrete strength value is the concrete strength prediction value calculated using the same empirical formula based on past historical environmental conditions. By comparing these two values, the difference between them is calculated, which is the "first concrete strength residual value." This residual value reflects the error in the concrete strength prediction based on the empirical formula at different time points or conditions.

[0071] For example, assuming that the first concrete strength value calculated under the current environment is 39.43 MPa, and the second concrete strength value calculated based on historical data is 38.5 MPa, the residual value of the first concrete strength is 39.43-38.5=0.93 MPa.

[0072] Here, we use historical environmental parameters (such as past temperature and humidity records) as input features. This data represents the various changes in environmental conditions during the concrete curing period. The residual value of the first concrete strength calculated above is used as the target variable. This means that our goal is to train a machine learning model that can predict the difference between the actual concrete strength and the value predicted by the empirical formula based on the given historical environmental parameters.

[0073] A variety of machine learning algorithms can be selected for training, such as random forest regression, support vector machine, neural network, etc. In this example, a random forest regression model is used. The collected historical environmental parameters are used as input features, and the corresponding first concrete strength residual value is used as the target variable to train the machine learning model. The model learns how to extract patterns from the input features and predict the output target variable (i.e., residual value) based on this. The performance of the model is evaluated by methods such as cross-validation, and the model parameters are adjusted as needed to improve its accuracy. After sufficient training, a machine learning model that can accurately predict the residual value of concrete strength is obtained. This model can be used to correct the preliminary prediction results obtained by the empirical formula, thereby providing a more accurate concrete strength prediction value. In actual projects, the environmental parameters monitored in real time can be input into this trained model to obtain a concrete strength prediction that is closer to the actual situation, helping to formulate a more scientific and reasonable maintenance strategy.

[0074] For example, imagine you are working on concrete curing for a large bridge construction project and using an intelligent concrete curing system to optimize the curing process.

[0075] Real-time monitoring: At the current time point, the sensor detects that the ambient temperature at the construction site is 20°C and the relative humidity is 60%.

[0076] Applying the empirical formula: Based on this real-time data, the empirical formula of the maturity method was used to calculate the predicted strength of the concrete after 7 days of curing to be 39.43 MPa. This is our first concrete strength value.

[0077] Reviewing historical data: Looking at the historical records of the same location over the past month, we found that the average temperature during this period was about 22°C and the average relative humidity was 58%.

[0078] Using this historical data as input, we again applied the maturity method's empirical formula. The results showed that under similar conditions, after a seven-day curing period, the expected concrete strength would be approximately 38.5 MPa. This is our second concrete strength value.

[0079] Difference calculation: Subtract the second concrete strength value (38.5 MPa) from the first concrete strength value (39.43 MPa) to obtain the residual value of the first concrete strength: 39.43 - 38.5 = 0.93 MPa. This residual value represents the difference between the concrete strength prediction under the current real-time environment and the historical conditions.

[0080] Collect data from multiple historical time periods, including environmental parameters such as temperature and humidity. For example, we have the following sets of historical data:

[0081] Group 1: temperature 22°C, humidity 58%, the corresponding residual value is 0.93 MPa.

[0082] Group 2: temperature 21°C, humidity 55%, the corresponding residual value is 0.85 MPa.

[0083] Group 3: temperature 23°C, humidity 62%, the corresponding residual value is 0.98 MPa.

[0084] (More historical data sets...)

[0085] For each set of historical data, the corresponding concrete strength residual value is known as the target variable.

[0086] Select a suitable machine learning algorithm (such as a random forest regression model) for training.

[0087] Using the prepared training dataset, historical environmental parameters (such as temperature and humidity) are used as input features, and the corresponding concrete strength residual values ​​are used as target variables. This data is then fed into a machine learning model for training. The model learns how to extract patterns from the input features and predict the target variable (i.e., the residual value) based on these patterns.

[0088] Evaluation and Tuning: Evaluate the performance of the model through methods such as cross-validation, and adjust model parameters as needed to improve accuracy.

[0089] In future maintenance processes, when new real-time environmental parameters are obtained (such as temperature 20°C and humidity 60%), they can be input into the trained machine learning model to predict the corresponding concrete strength residual value.

[0090] The first concrete strength value calculated initially is corrected based on the residual value predicted by the model. For example, if the residual value predicted by the model is 0.9 MPa, the corrected concrete strength prediction value is 39.43 + 0.9 = 40.33 MPa.

[0091] It's important to note that, in specific implementation scenarios, the above approach can also be used to leverage trained machine learning models to predict real-time environmental parameters and dynamically adjust curing strategies based on the predicted results. For example, if the prediction indicates unsatisfactory concrete strength growth under current conditions, the water injection rate can be increased or the curing time extended. The system can automatically adjust model parameters based on the latest measured data and predicted results, ensuring they remain optimal and improving prediction accuracy and reliability.

[0092] In specific implementation scenarios, in addition to temperature and humidity, other factors affecting concrete strength, such as wind speed, light intensity, and construction methods, can be incorporated into the above solution as input features for model training. This helps to more fully understand the impact of various factors on concrete strength. By combining multiple factors for comprehensive risk assessment, potential risk points (such as extreme weather conditions) can be identified in advance, and corresponding preventive measures can be formulated to reduce losses caused by improper maintenance.

[0093] The real-time environmental parameters are input into the trained machine learning model to obtain a second concrete strength residual value, and a concrete strength prediction value is obtained based on the second concrete strength residual value and the first concrete strength value.

[0094] As mentioned above, enter the real-time environment parameters

[0095] Real-time environmental parameters: These are the actual data obtained from sensors at the current moment, such as temperature, humidity, etc. Assume that the current ambient temperature is 20°C and the relative humidity is 60%.

[0096] Trained machine learning model: This is a model that has been trained using historical environmental parameters (such as past temperature and humidity records) as input features and the first concrete strength residual value (that is, the difference between the first concrete strength value calculated based on real-time environmental parameters and the second concrete strength value calculated based on historical environmental parameters) as the target variable.

[0097] Input real-time data: Input the current real-time environmental parameters (such as 20°C temperature and 60% humidity) into this trained machine learning model.

[0098] Second, the residual value of concrete strength: This is a correction value predicted by the model based on the input real-time environmental parameters. It represents the difference between the concrete strength predicted by the empirical formula and the actual strength that can be achieved under the current environment. For example, the model may predict a residual value of -0.9 MPa.

[0099] First concrete strength value: This is a preliminary concrete strength prediction value calculated based on the current real-time environmental conditions (such as temperature 20°C and humidity 60%) using the empirical formula of the maturity method. Assume that this value is 39.43 MPa.

[0100] Calculate the final predicted concrete strength: Combine the first concrete strength value obtained in the first step with the second concrete strength residual value obtained in the third step to calculate the final predicted concrete strength. Specifically, add the first concrete strength value to the second concrete strength residual value. For example, if the first concrete strength value is 39.43 MPa and the second concrete strength residual value is -0.9 MPa, the final predicted concrete strength value is 39.43 + (-0.9) = 38.53 MPa.

[0101] For example, suppose in a specific engineering project:

[0102] Real-time monitoring data: The current ambient temperature is 20°C and the relative humidity is 60%.

[0103] First concrete strength value: Calculated using the empirical formula of the maturity method, the predicted concrete strength after 7 days of curing under current conditions is 39.43 MPa.

[0104] Trained machine learning model: This model has been trained using a large amount of historical data and can predict the corrected value of concrete strength based on the input real-time environmental parameters.

[0105] Second, the residual value of concrete strength: the current real-time environmental parameters (20°C, 60% humidity) are input into the trained model, and a predicted residual value of -0.9 MPa is obtained.

[0106] Final concrete strength prediction value: Add the first concrete strength value of 39.43 MPa and the second concrete strength residual value of -0.9 MPa to obtain the final concrete strength prediction value of 38.53 MPa.

[0107] According to one embodiment of the present application, based on real-time environmental parameters, the first concrete strength value is calculated using the empirical formula of the maturity method, and based on historical environmental parameters, the second concrete strength value is calculated using the empirical formula of the maturity method, specifically:

[0108] Acquire the real-time environmental parameters, including ambient temperature, humidity, and curing time parameters, in real time through sensors;

[0109] The first concrete strength value of the concrete under the real-time environmental parameters is calculated using the empirical formula of the maturity method. The specific formula is as follows:

[0110] S(t)=S ∞ ·exp(-k·t)

[0111] Among them, S(t) represents the concrete strength value; S ∞ represents the final strength; k is the empirical coefficient, and t is the curing time;

[0112] collecting a data set containing said historical environmental parameters under specific conditions;

[0113] The second concrete strength value of the concrete under the historical environmental parameters is calculated using the empirical formula of the maturity method.

[0114] It's important to note that in specific implementation scenarios, building on the above solution, a trained machine learning model can be used to continuously monitor real-time environmental parameters and dynamically adjust maintenance strategies based on the predicted results. For example, if the prediction shows that concrete strength growth under current conditions is unsatisfactory, the water injection rate can be automatically increased or the curing time can be extended. The system can continuously update model parameters based on the latest measured data to ensure they are always in optimal condition. This adaptive learning algorithm can improve prediction accuracy and reliability, allowing for timely response to environmental changes.

[0115] In specific implementation scenarios, building on the above approach, other factors affecting concrete strength, such as wind speed, light intensity, and construction methods, can be considered as input features for model training, in addition to temperature and humidity. This helps to more fully understand the impact of various factors on concrete strength. By combining multiple factors for comprehensive risk assessment, potential risk points (such as extreme weather conditions) can be identified in advance, and corresponding preventive measures can be formulated to reduce losses caused by improper maintenance.

[0116] According to one embodiment of the present application, it further includes:

[0117] Preset concrete strength growth target value, humidity and temperature range;

[0118] comparing the concrete strength prediction value with the concrete strength growth target value;

[0119] If the predicted concrete strength value is less than the target concrete strength growth value, it is considered that the concrete strength growth under the current curing conditions is not ideal and the curing strategy needs to be dynamically adjusted.

[0120] As mentioned above, this is the minimum strength requirement that concrete should achieve after a specific curing time, as specified in the project design or specification. For example, a bridge project may require the concrete strength to be at least 35 MPa after 7 days.

[0121] Ideal humidity and temperature ranges are set based on optimal concrete curing conditions. For example, the humidity range can be set to 40%-60%, and the temperature range can be set to 15°C-25°C. These ranges ensure that the concrete can harden under optimal conditions and achieve the desired strength.

[0122] Using the aforementioned method (combining empirical formulas and machine learning models), we can calculate the predicted concrete strength under current conditions based on real-time environmental parameters. Assume the calculated predicted value is 38.53 MPa.

[0123] The predicted concrete strength value is compared with the preset concrete strength growth target value. For example, if the target value is 35MPa, it is necessary to check whether 38.53MPa meets or exceeds this target value.

[0124] If the predicted concrete strength value is greater than or equal to the preset target value (such as 38.53MPa>=35MPa in this example), it is considered that the concrete strength growth under the current curing conditions is in line with expectations.

[0125] If the predicted concrete strength value is less than the preset target value, it indicates that the concrete strength growth is not ideal under the current curing conditions.

[0126] When the predicted concrete strength value is lower than the preset target value, the system will automatically analyze the reason. This may be because the current environmental conditions (such as temperature and humidity) are not suitable for the optimal hardening process of concrete.

[0127] Increase water spraying: If the humidity is lower than the preset ideal range (such as below 40%), the automatic water spraying mechanism is activated to increase the humidity to ensure that the concrete surface maintains proper wetness.

[0128] Enhance ventilation and cooling: If the temperature exceeds the ideal range (such as above 25°C), start the fan to cool it down to avoid excessively high temperatures affecting the development of concrete strength.

[0129] Extended curing time: In some cases, even after adjusting humidity and temperature, additional time may be required to ensure that the concrete reaches the required strength. In these cases, the system may recommend extending the curing period.

[0130] According to one embodiment of the present application, the dynamic adjustment of the maintenance strategy includes:

[0131] If the humidity is lower than the lower limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic water spraying mechanism is triggered;

[0132] If the temperature exceeds the upper limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic ventilation mechanism is triggered.

[0133] As mentioned above, establish an ideal humidity range, such as 40%-60%. This range ensures the concrete surface remains appropriately moist, promoting optimal hardening. Establish an ideal temperature range, such as 15°C-25°C. This helps prevent excessively high or low temperatures from adversely affecting concrete strength development. This is the minimum strength requirement for concrete after a specific curing time, as specified in the project design or specification. For example, after seven days, the concrete strength should be at least 35 MPa.

[0134] If the humidity sensor detects that the current humidity is lower than the lower limit of the preset range (eg, lower than 40%), it is considered that the current environment is too dry and is not conducive to the optimal hardening process of concrete.

[0135] If the temperature sensor detects that the current temperature exceeds the upper limit of the preset range (such as above 25°C), it is considered that the current ambient temperature is too high and may affect the strength development of concrete.

[0136] Use empirical formulas and machine learning models to calculate the predicted strength value of concrete under current conditions.

[0137] The predicted value is compared with the preset concrete strength growth target value. If the predicted value is less than the target value, it indicates that the concrete strength growth under the current curing conditions is not ideal.

[0138] If the humidity falls below the lower limit of a preset range (e.g., below 40%) and the predicted concrete strength falls below the target, the automatic water spray mechanism is triggered. A water pump is activated to spray water onto the concrete surface, increasing the ambient humidity and ensuring the concrete surface maintains the proper level of moisture for optimal hardening. For example, if the current humidity is 35% and the predicted concrete strength is 34 MPa (lower than the target value of 35 MPa), the system will automatically activate the water pump and increase the water spray until the humidity returns to the preset range (e.g., 40%-60%).

[0139] If the temperature exceeds the upper limit of the preset range (e.g., above 25°C) and the predicted concrete strength is lower than the target value, the automatic ventilation mechanism is triggered. The fan is activated to cool the environment and reduce the ambient temperature to prevent the adverse effects of high temperature on the development of concrete strength. Assuming the current temperature is 28°C and the predicted concrete strength is 33MPa (lower than the target value of 35MPa), the system will automatically activate the fan to ventilate and cool the concrete until the temperature drops to within the preset range (e.g., 15°C-25°C).

[0140] According to one embodiment of the present application, the automatic water spraying mechanism is specifically:

[0141] When the humidity detected by the humidity sensor is lower than the lower limit of the preset range, DO outputs a high level, the indicator light lights up and the water pump is started;

[0142] When the humidity rises back to above the upper limit of the preset range, DO outputs a low level and stops adding water.

[0143] According to one embodiment of the present application, the automatic ventilation mechanism is specifically:

[0144] When the temperature detected by the temperature sensor is higher than the upper limit of the preset range, the fan is started to cool down;

[0145] When the temperature drops to within a preset range, the fan stops working.

[0146] As mentioned above, a humidity sensor is installed in the system to monitor the humidity level in the environment in real time.

[0147] An ideal humidity range is preset, such as 40%-60%. When the humidity sensor detects that the current humidity is lower than the lower limit of the preset range (such as lower than 40%), the system will recognize that the current environment is too dry and is not conducive to the optimal hardening of concrete.

[0148] When the humidity is lower than the lower limit of the preset range, the digital output (DO) port outputs a high level signal. This signal triggers two actions:

[0149] First, the indicator light lights up, reminding the operator that the system is humidifying; second, the water pump is started to spray water on the concrete surface.

[0150] Increase ambient humidity.

[0151] As the water pump works, the ambient humidity gradually rises. When the humidity sensor detects that the humidity has risen above the upper limit of the preset range (such as over 60%), the DO port outputs a low-level signal, stops the water pump, and stops adding water.

[0152] Assume that in a specific project, the preset humidity range is 40%-60%:

[0153] If the humidity sensor detects that the current humidity is 35%, which is lower than the lower limit of the preset range of 40%, the system will trigger the automatic water spray mechanism. The DO port outputs a high level, the indicator light turns on, and the water pump is started for humidification.

[0154] As the water pump continues to work, the humidity gradually rises. When the humidity reaches above 60%, the DO port outputs a low level and the water pump stops working.

[0155] Do not continue to add water.

[0156] A temperature sensor is installed in the system to monitor the temperature changes in the environment in real time.

[0157] An ideal temperature range is preset, for example, 15°C-25°C. When the temperature sensor detects that the current temperature is higher than the upper limit of the preset range (such as higher than 25°C), the system will recognize that the current ambient temperature is too high and may affect the strength development of concrete.

[0158] When the temperature is higher than the upper limit of the preset range, the system will automatically start the fan for cooling, helping to lower the ambient temperature and prevent excessively high temperatures from having adverse effects on the concrete.

[0159] As the fan runs, the ambient temperature gradually drops. When the temperature sensor detects that the temperature drops to within the preset range (such as below 25°C),

[0160] The fan will stop working and will no longer provide cooling.

[0161] According to one embodiment of the present application, it further includes:

[0162] The predicted concrete strength value and the real-time environmental parameters are uploaded to a mobile phone APP via a WiFi module. The user can check the current status and remotely adjust the humidity and temperature thresholds according to the actual situation.

[0163] As mentioned above, the sensors in the system (such as humidity sensors and temperature sensors) continuously monitor environmental parameters, and the empirical formula of the maturity method combined with the machine learning model is used to calculate the predicted value of concrete strength.

[0164] This data (including real-time humidity, temperature, and calculated concrete strength predictions) is uploaded to a cloud server via the WiFi module, which acts as a data transmission bridge, ensuring that on-site data is sent promptly and accurately.

[0165] The uploaded data will be synchronized to the mobile phone APP, and users can view this information through a dedicated application installed on their smartphones. This allows users to grasp the key data of the concrete curing process at any time no matter where they are.

[0166] In the mobile app, users can intuitively see the current humidity and temperature values, as well as the latest concrete strength forecast. In addition, the app can also provide trend analysis charts of historical data to help users better understand data trends.

[0167] If the user finds that the current humidity or temperature deviates from the ideal range, or needs to fine-tune the maintenance conditions based on other practical considerations, the humidity and temperature thresholds can be remotely adjusted through the mobile phone APP.

[0168] For example, if the humidity is found to be consistently low, users can manually increase the lower humidity threshold in the app, prompting the system to activate the water spraying mechanism more frequently.

[0169] Similarly, if the temperature is often close to the upper limit, the user can appropriately lower the upper temperature threshold to increase the frequency of fan startup to maintain a suitable temperature.

[0170] A computer-readable storage medium stores a program, which implements the steps in the method when executed by a processor.

[0171] An electronic device comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein the steps in the method are implemented when the processor executes the program.

[0172] Anything not described in this application can be achieved by adopting or drawing on existing technologies.

[0173] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0174] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A concrete strength prediction method based on multi-source data fusion, characterized in that: include: Based on the real-time environmental parameters, a first concrete strength value is calculated using the empirical formula of the maturity method, and based on the historical environmental parameters, a second concrete strength value is calculated using the empirical formula of the maturity method; calculating a difference between the first concrete strength value and the second concrete strength value to obtain a first concrete strength residual value, using the historical environmental parameter as an input feature and the first concrete strength residual value as a target variable to train a machine learning model to obtain a trained machine learning model; The real-time environmental parameters are input into the trained machine learning model to obtain a second concrete strength residual value, and a concrete strength prediction value is obtained based on the second concrete strength residual value and the first concrete strength value.

2. The method according to claim 1, characterized in that Based on the real-time environmental parameters, the first concrete strength value is calculated using the empirical formula of the maturity method. Based on the historical environmental parameters, the second concrete strength value is calculated using the empirical formula of the maturity method. Specifically: Acquire the real-time environmental parameters, including ambient temperature, humidity, and curing time parameters, in real time through sensors; The first concrete strength value of the concrete under the real-time environmental parameters is calculated using the empirical formula of the maturity method. The specific formula is as follows: S(t)=S ∞ ·exp(-k·t) Among them, S(t) represents the concrete strength value; S ∞ Indicates the final strength; k is the empirical coefficient, and t is the curing time; collecting a data set containing said historical environmental parameters under specific conditions; The second concrete strength value of the concrete under the historical environmental parameters is calculated using the empirical formula of the maturity method.

3. The method according to claim 1, characterized in that Also includes: Preset concrete strength growth target value, humidity and temperature range; comparing the concrete strength prediction value with the concrete strength growth target value; If the predicted concrete strength value is less than the target concrete strength growth value, it is considered that the concrete strength growth under the current curing conditions is not ideal and the curing strategy needs to be dynamically adjusted.

4. The method according to claim 3, characterized in that The dynamic adjustment of the maintenance strategy includes: If the humidity is lower than the lower limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic water spraying mechanism is triggered; If the temperature exceeds the upper limit of the preset range and the predicted concrete strength value is less than the concrete strength growth target value, the automatic ventilation mechanism is triggered.

5. The method according to claim 4, characterized in that The automatic water spraying mechanism is specifically: When the humidity detected by the humidity sensor is lower than the lower limit of the preset range, DO outputs a high level, the indicator light lights up and the water pump is started; When the humidity rises back to above the upper limit of the preset range, DO outputs a low level and stops adding water.

6. The method according to claim 4, characterized in that The automatic ventilation mechanism is specifically: When the temperature detected by the temperature sensor is higher than the upper limit of the preset range, the fan is started to cool down; When the temperature drops to within a preset range, the fan stops working.

7. The method according to claim 1, characterized in that Also includes: The predicted concrete strength value and the real-time environmental parameters are uploaded to a mobile phone APP via a WiFi module. The user can check the current status and remotely adjust the humidity and temperature thresholds according to the actual situation.

8. A computer program product comprising instructions, which, when executed on a device, is characterized in that: The device is enabled to execute the steps in the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps in the method according to any one of claims 1 to 7 are implemented.

Images