Method and system for predicting hardening deformation of concrete

Abstract

This invention provides a method and system for predicting concrete hardening deformation, relating to the fields of tunnels and underground engineering. The method includes: acquiring historical sensor datasets; performing data fusion analysis on the historical sensor datasets to obtain a fused state vector; establishing a nonlinear mapping relationship based on the fused state vector to obtain a shrinkage trend prediction model; acquiring real-time sensor datasets; obtaining prediction trends and risk assessment results through real-time prediction and adaptive updates; performing quantitative analysis based on the prediction trends and risk assessment results to obtain stress state criteria for columns and foundations; and assessing the fit between newly constructed concrete columns and existing foundations based on the stress state criteria to obtain concrete hardening deformation assessment results. This invention constructs an efficient intelligent measurement system that monitors the hardening deformation state of flowing concrete in real time based on measurement data, improving the accuracy and real-time performance of shrinkage deformation monitoring during the concrete hardening process.

Description

Technical Field

[0001] This invention relates to the field of tunnels and underground engineering, specifically to a method and system for predicting concrete hardening deformation. Background Technology

[0002] In building underpinning projects, column underpinning technology is a key technique for structural reinforcement and repair. To ensure the overall load-bearing capacity and stability of the new column and the existing foundation after underpinning, a tight fit between the connection areas must be ensured. However, concrete inevitably undergoes volume shrinkage during the hardening process, especially with the use of flowing concrete, which can easily lead to uneven contact or gaps between the new column and the foundation, thus affecting structural safety and load-bearing performance.

[0003] Against this backdrop, intelligent measurement technology has gradually become the core of solutions. Utilizing advanced sensor networks and data fusion methods, intelligent measurement technology provides accurate measurements of concrete hardening shrinkage deformation through real-time monitoring and automatic feedback. Based on this technology, this invention proposes a method and system for predicting concrete hardening deformation. Construction workers can more accurately predict the shrinkage trend of concrete and make appropriate construction adjustments based on actual humidity conditions to ensure that concrete hardens under optimal conditions and reduce quality problems caused by shrinkage deformation. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for predicting the settlement of diaphragm walls in foundation pits, thereby improving the aforementioned problems. To achieve this objective, the technical solution adopted by this invention is as follows:

[0005] Firstly, this application provides a method for predicting concrete hardening deformation, including:

[0006] Acquire historical sensor datasets, which include concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity.

[0007] Based on the historical sensor dataset, data fusion analysis is performed, and a unified state estimation framework is used to filter out noise and optimize estimation accuracy to obtain a fused state vector.

[0008] Based on the fused state vector, a nonlinear mapping relationship is established between the displacement, pressure, temperature, and humidity parameter sequences and the shrinkage deformation sequence to obtain a concrete shrinkage trend prediction model;

[0009] Acquire real-time sensor datasets and input them into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updating of the data, obtain the predicted trend and risk assessment results.

[0010] Based on the predicted trend and risk assessment results and the historical sensor dataset, a quantitative analysis is performed. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, the stress state criteria of the column and the foundation are obtained.

[0011] The bonding state between the newly constructed concrete column and the existing foundation is evaluated based on the stress state criterion, and the concrete hardening deformation evaluation result is obtained.

[0012] Secondly, this application also provides a concrete hardening deformation prediction system, including:

[0013] The acquisition module is used to acquire historical sensor datasets, which include concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity.

[0014] The processing module is used to perform data fusion analysis based on the historical sensor dataset, filter out noise and optimize estimation accuracy based on a unified state estimation framework, and obtain a fused state vector.

[0015] The mapping module establishes a nonlinear mapping relationship between the displacement, pressure, temperature, and humidity parameter sequences and the shrinkage deformation sequence based on the fused state vector, thereby obtaining a concrete shrinkage trend prediction model.

[0016] The prediction module acquires real-time sensor datasets and inputs them into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updates of the data, the predicted trend and risk assessment results are obtained.

[0017] The calculation module performs quantitative analysis based on the predicted trend and risk assessment results and the historical sensor dataset. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, it obtains the stress state criteria for the column and the foundation.

[0018] The output module is used to evaluate the fit between the newly built concrete column and the existing foundation according to the stress state criterion, and obtain the concrete hardening deformation evaluation result.

[0019] The beneficial effects of this invention are as follows:

[0020] The concrete hardening deformation prediction method and system described in this invention utilizes intelligent measurement technology, advanced sensor networks, and data fusion methods for real-time monitoring and automatic feedback of data. The system can monitor the hardening process of concrete in real time and continuously, providing accurate data for the connection between old and new structures during concrete column support, and accurately predicting the hardening shrinkage deformation state of concrete.

[0021] The concrete hardening deformation prediction method described in this invention integrates multiple sensors and intelligent algorithms to accurately monitor and predict the complex dynamic behavior of concrete hardening, ensuring a tight fit between the newly built column and the foundation, and achieving efficient and safe replacement of the engineering structure. It not only improves the quality of the project, but also provides a new application direction for intelligent monitoring technology in future construction projects. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the concrete hardening deformation prediction method described in the embodiments of the present invention;

[0024] Figure 2 This is a schematic diagram of the concrete hardening deformation prediction system described in an embodiment of the present invention;

[0025] Figure 3 This is a sensor layout diagram of the concrete hardening deformation prediction method and system described in this embodiment of the invention;

[0026] Figure 4 This is a schematic diagram of the data transmission between the central control system for predicting concrete hardening deformation and the sensor data in an embodiment of the present invention.

[0027] Figure 5 This is a flowchart illustrating the real-time monitoring and adjustment process of the concrete hardening deformation prediction method and system described in this embodiment of the invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] Before disclosing the embodiments of the present invention, the technical problem solved by the present invention is described: Traditional methods for measuring shrinkage deformation rely on manual operation and simple mechanical equipment, such as displacement gauges and rulers. These methods are not only difficult to achieve real-time monitoring, but also have low measurement accuracy, failing to accurately capture the complex physical changes during the hardening process of concrete. Furthermore, the hardening of concrete is affected by various environmental factors, such as changes in temperature, heat of hydration, and ambient humidity, all of which significantly influence its shrinkage behavior. Therefore, there is a need to provide a method and system capable of accurately monitoring and predicting the complex dynamic behavior of concrete during hardening, such as… Figure 5 As shown in the figure, this diagram illustrates the concrete hardening deformation prediction method and the system's real-time monitoring and adjustment flowchart, recording the entire process of data acquisition, fusion processing, and system suggestion feedback from various sensors during the concrete hardening process.

[0031] Example 1:

[0032] This embodiment provides a method for predicting concrete hardening deformation.

[0033] The specific implementation process is as follows:

[0034] See Figure 1 The figure shows that the method includes steps S100 to S600.

[0035] Step S100: Obtain historical sensor dataset, which includes concrete deformation parameters, bonding pressure between concrete and foundation, concrete temperature, and ambient humidity.

[0036] Specifically, the historical sensor dataset is collected from concrete structure construction projects in the field of tunnels and underground engineering, focusing on monitoring data of the hardening process of flowing concrete in actual projects. The dataset covers four core dimensions: concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity. All data are collected by corresponding sensors throughout the construction cycle: displacement sensors fixed to the bottom of existing foundations monitor shrinkage deformation; pressure sensors installed at the bottom of the foundation record bonding pressure data; temperature changes due to concrete hydration heat are captured by temperature sensors embedded in the formwork; and ambient humidity fluctuations are obtained from humidity sensors on the side of the foundation. Simultaneously, the dataset must include monitoring data under different construction environments and concrete mix proportions. The raw data undergoes preliminary screening and calibration to remove obvious outliers, ensuring data integrity, continuity, and validity, providing comprehensive and reliable basic data support for subsequent analysis.

[0037] Step S200: Perform data fusion analysis processing based on the historical sensor dataset, filter out noise and optimize estimation accuracy based on a unified state estimation framework, and obtain a fused state vector.

[0038] Specifically, after all sensors are calibrated, they are connected to the central control system via a wireless network to ensure real-time data transmission. A unified state estimation framework is constructed based on the Kalman filter algorithm, and data fusion analysis is performed on the historical sensor dataset. First, the measured values ​​of four parameters—concrete deformation, bonding pressure, temperature, and humidity—are integrated into a unified state vector, serving as the basis for state estimation. State prediction is then performed based on the state vector from the previous moment, combined with the state transition matrix and the control input matrix related to construction adjustments, while considering the impact of process noise to complete covariance prediction. Next, the measured values ​​of various sensors are substituted into the framework for updating and correction. By calculating the Kalman gain, combined with the observation matrix and the measurement noise covariance matrix, the prediction results are optimized to obtain a fused state vector after noise removal. The entire process is continuously iterated during data processing; each new set of data inputs performs a prediction and update, effectively filtering out noise interference in sensor measurements and data transmission, optimizing parameter estimation accuracy, and ensuring that the fused state vector accurately reflects the true state of the concrete hardening process. This ensures that the system maintains high accuracy, real-time performance, and stability throughout the entire process.

[0039] Step S300: Based on the fused state vector, establish a nonlinear mapping relationship between the displacement, pressure, temperature and humidity parameter sequences and the shrinkage deformation sequence to obtain a concrete shrinkage trend prediction model.

[0040] Specifically, based on the fused state vector, the raw data stream is received in real time with a set sampling period (e.g., 1 second or 5 seconds). Displacement, pressure, temperature, and humidity parameters at different time points are extracted to construct corresponding parameter sequences. Simultaneously, the concrete shrinkage deformation at each time point is analyzed to form a shrinkage deformation sequence. Feature extraction is performed on both sequences. Through differencing and normalization, the parameter sequences are transformed into feature variables that reflect the rate of change between adjacent time points, focusing on feature indicators that significantly affect the concrete shrinkage trend. Based on the characteristics of time-series data, a nonlinear regression method is used to construct a mapping relationship model. Displacement, pressure, temperature, and humidity feature variables are used as inputs, and shrinkage deformation is used as the output. Through training and fitting with a large amount of historical data, the predicted shrinkage trend value is obtained. During the modeling process, the nonlinear mapping logic of the model is optimized by combining the physical laws of concrete hydration reaction, allowing the model to accurately reflect the inherent laws of concrete shrinkage deformation under the synergistic effect of multiple parameters. Finally, a robust and highly accurate concrete shrinkage trend prediction model is obtained.

[0041] Step S400: Obtain the real-time sensor dataset and input it into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updating of the data, obtain the prediction trend and risk assessment results.

[0042] Specifically, displacement, pressure, temperature, and humidity sensors deployed at the engineering site collect sensor data in real time according to a preset sampling period (1 second or 5 seconds), forming a real-time sensor dataset. The data acquisition process ensures continuity and real-time performance. The real-time sensor dataset is first preprocessed using a Kalman filter framework to filter out noise in the real-time measurements, resulting in a fused real-time state vector. This vector is then input into a pre-trained concrete shrinkage trend prediction model. The model calculates the estimated shrinkage displacement of concrete over a future period based on the real-time parameter data, compares it with the current displacement measurement value to obtain the predicted shrinkage trend, and immediately generates a risk warning if the trend value exceeds a preset safety threshold. Simultaneously, the system continuously collects new real-time monitoring data, calculates the residual between the predicted and actual measured values, and adaptively updates the parameters of the prediction model according to the minimum mean square error criterion. This allows the model to dynamically optimize as the concrete hardens, maintaining high prediction accuracy and promptly outputting accurate prediction trends and risk assessment results.

[0043] Step S500: Perform quantitative analysis based on the predicted trend and risk assessment results and the historical sensor dataset. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, obtain the stress state criteria for the column and the foundation.

[0044] Specifically, combining predicted trends and risk assessment results, historical sensor datasets and real-time monitoring data are integrated to conduct a multi-dimensional quantitative analysis of the stress state of columns and foundations. First, pressure distribution analysis is performed. Based on the spatial coordinates of the pressure sensors, a two-dimensional distribution model of the column-foundation interface is established. Discrete pressure monitoring data is transformed into a continuous pressure distribution on the interface using interpolation methods. The average pressure and standard deviation of the pressure are calculated to obtain a pressure distribution uniformity index, quantitatively assessing whether the pressure distribution on the interface is uniform. Next, shrinkage deformation analysis is performed. Based on displacement sensor data, the relative deformation and overall average shrinkage rate at different stages of concrete hardening are calculated and compared with the design reference shrinkage limit to locate deviation areas where shrinkage deformation exceeds the limit. Based on the results of these two types of analysis, a multi-dimensional comprehensive evaluation function including pressure uniformity and shrinkage stability is constructed. Weight coefficients for each index are set according to the actual engineering situation. The function calculation yields quantitative criteria for the stress state of columns and foundations. These criteria need to clearly define the quantitative thresholds for different states such as good fit, uneven fit, and excessive deformation, providing clear judgment standards for subsequent fit state assessment.

[0045] Step S600: Evaluate the fit between the newly constructed concrete column and the existing foundation according to the stress state criterion to obtain the concrete hardening deformation evaluation result.

[0046] Specifically, the stress state results calculated by the multidimensional comprehensive evaluation function are compared one by one with preset quantitative thresholds for good fit, uneven fit, and excessive deformation to evaluate the fit between the new concrete column and the existing foundation. Based on the actual values ​​of the pressure distribution uniformity index and shrinkage stability index, and combined with the standard requirements of the stress state judgment criteria, the fit state level is accurately determined. Simultaneously, real-time monitoring data and historical data of the concrete hardening process are used to analyze the causes and impact range of abnormal conditions. For problems such as uneven fit and excessive deformation discovered during the evaluation process, the specific location, degree of exceedance, and corresponding risk level of the abnormal areas are clearly marked, and targeted rectification reference directions are proposed based on the actual project situation. The system integrates all evaluation data, judgment results, and abnormal analysis content to generate a standardized concrete hardening deformation evaluation report. The report includes the fit state level, details of abnormal problems, risk assessment conclusions, and rectification suggestions, ultimately forming a complete and comprehensive concrete hardening deformation evaluation result, providing a scientific and reliable basis for project construction acceptance, subsequent maintenance, and structural safety assurance.

[0047] Further, step S200 includes steps S210 to S230.

[0048] Step S210: Define state variables based on the historical sensor dataset. By combining the measured displacement, pressure, temperature and humidity, obtain the state vector of the measurement dataset.

[0049] Step S220: Predict the hardening state of concrete based on the state vector of the measurement dataset, create a prediction model based on the state vector structure state parameters and map the system state to obtain the prediction state matrix.

[0050] Step S230: Update and correct the prediction results based on the predicted state matrix and historical sensor dataset, and obtain the fused state vector by filtering out noise and optimizing the estimation accuracy based on a unified state estimation framework.

[0051] Specifically, first, determine the placement location of the sensors and install them, such as... Figure 3 As shown in the diagram, displacement sensors are installed at the bottom of the existing foundation to monitor the fit between the concrete and the foundation, as well as shrinkage deformation. Humidity sensors are installed on the sides of the foundation to monitor humidity changes during the concrete hardening process. Pressure sensors are installed at the bottom of the foundation to monitor the pressure between the new column and the foundation in real time, ensuring a tight fit. Temperature sensors are placed inside the formwork before concrete pouring to record changes in the heat of hydration during concrete hardening. All sensors are connected to the central control system via wireless communication technology, enabling real-time data acquisition and transmission, thus supporting subsequent data analysis and monitoring.

[0052] After installation, the sensors are calibrated to ensure data accuracy. Displacement sensors require zero-point calibration to ensure accurate measurement of concrete shrinkage deformation. Pressure sensors are calibrated using standard loads to ensure real-time reflection of pressure changes between the foundation and concrete. Temperature sensors are calibrated according to standard temperatures to ensure accurate capture of hydration heat changes within the concrete. Humidity sensors are also calibrated according to standard humidity levels to accurately monitor humidity fluctuations.

[0053] After all sensors have been calibrated, the software platform of the central control system is activated to ensure it can receive data from the displacement, pressure, temperature, and humidity sensors. Figure 4 As shown in the attached diagram, this illustrates the connection and data processing flow between the sensors and the central control system. Various sensors (displacement, pressure, temperature, humidity) are connected to the central control system wirelessly to collect and transmit relevant data during the concrete hardening process in real time. The central control system is configured with different data acquisition modules according to the sensor type and displays real-time data through a monitoring interface. The data collected by the sensors is fused using a Kalman filter algorithm to remove noise and ensure the accuracy of the measurement data and the stability of the intelligent monitoring. The specific fusion steps are as follows:

[0054] Step S211, Definition of state variables:

[0055] The system integrates concrete deformation parameters (displacement), the bonding pressure between concrete and the foundation, concrete temperature, ambient humidity, and measurements from four types of sensors into a unified state vector.

[0056] ;

[0057] in, Sampling time; Sampling time The displacement; Sampling time The pressure; For temperature; Sampling time humidity; Sampling time Structural state parameters.

[0058] Step S221, Prediction Step:

[0059] First, make a prediction based on the state vector from the previous time step:

[0060] State prediction formula:

[0061] ;

[0062] in, Sampling time; Based on The sampling time of the previous unit of time; Based on All information at the sampling time, for Prior estimation of the state at the sampling time; This is the prior estimate of the state prediction vector; In order to be in State transition matrix at sampling time; In order to be in Control input matrix at sampling time; for The state prediction vector; In order to be in System control variables (construction adjustment information) at the sampling time.

[0063] Covariance prediction formula:

[0064] ;

[0065] in, Sampling time; Based on The sampling time of the previous unit of time; Based on All information at the sampling time, for Prior estimation of the state at the sampling time; This represents the prior estimate prediction error covariance matrix; In order to be in State transition matrix at sampling time; Indicates in The process noise covariance matrix at the sampling time; The prediction error covariance matrix; State transition matrix The transpose of .

[0066] Step S231, Update Step:

[0067] The new sensor measurements are used to correct the prediction results, and the Kalman gain calculation formula is applied.

[0068] ;

[0069] in, Sampling time; Based on The sampling time of the previous unit of time; Based on All information at the sampling time, for Prior estimation of the state at the sampling time; This represents the prior estimate prediction error covariance matrix; Sampling time The Kalman gain matrix is ​​used to characterize the weighting relationship between the predicted state and the measurement information in the state update. Sampling time Observation matrix; Observation matrix The transpose of the matrix; Sampling time Measure the noise covariance matrix.

[0070] State update formula:

[0071] ;

[0072] in, Sampling time; Based on All information at the sampling time, for Prior estimation of the state at the sampling time; Indicates the sampling time State update vector; This is the prior estimate of the state prediction vector; Sampling time The Kalman gain matrix; Sampling time The collected sensor measurement vectors; Sampling time Observation matrix.

[0073] Covariance update formula:

[0074] ;

[0075] in, Sampling time; Based on All information at the sampling time, for Prior estimation of the state at the sampling time; Sampling time Covariance update matrix; It is the identity matrix; Sampling time The Kalman gain matrix; Sampling time Observation matrix; This represents the covariance matrix of the prior estimate prediction error.

[0076] Step S232, Generation of fusion results:

[0077] After the above prediction and update steps, a fused state vector with noise removed is obtained. This vector represents the optimal estimate of displacement, pressure, temperature, and humidity at that moment and is displayed in real time on the central control system interface for trend prediction and alarm judgment. The above steps are continuously iterated throughout the entire concrete hardening process. A prediction and update are performed every time new sensor data is received, ensuring that the system maintains high accuracy, real-time performance, and stability throughout the entire process.

[0078] Further, step S300 includes steps S310 to S330.

[0079] Step S310: Receive the raw data stream according to the fused state vector at a preset sampling period, and convert the displacement, pressure, temperature, and humidity data to obtain a parameter sequence.

[0080] Step S320: Screen and analyze the parameters that affect the shrinkage trend of concrete according to the parameter sequence, and obtain the characteristic variables by differentiating and normalizing the parameters.

[0081] Step S330: Establish a prediction model based on the characteristic variables, predict the future shrinkage deformation trend based on the nonlinear mapping relationship between time series data and shrinkage deformation, and obtain the concrete shrinkage trend prediction model.

[0082] Specifically, the software platform of the central control system is activated to ensure it can receive and process data from various sensors. Data acquisition modules are configured according to sensor type (displacement, pressure, temperature, humidity), and a monitoring interface is set up for real-time data display, establishing historical records for subsequent analysis. System parameters are adjusted according to different data types to ensure the data processing flow adapts to monitoring requirements.

[0083] The system performs real-time analysis of the data collected by the sensors as follows:

[0084] Step S311, Real-time Data Acquisition and Preprocessing:

[0085] The system receives raw data streams in real time using displacement, pressure, temperature, and humidity sensors at a set sampling period (e.g., 1 second or 5 seconds). Kalman filtering is performed on the received data to remove transmission noise and sensor measurement errors, resulting in a fused state vector.

[0086] ;

[0087] in, Indicates in time; Indicates time Estimated displacement data collected; Indicates time Estimated pressure from data collection; Indicates time Estimated temperature readings; Indicates time Estimated humidity levels.

[0088] Step S321, Feature Extraction:

[0089] In the fused state vector, displacement, pressure, temperature, and humidity data are converted into feature variables required for analysis. For parameters that significantly influence concrete shrinkage trends, the system obtains the following characteristics through differencing and normalization:

[0090] ;

[0091] ;

[0092] ;

[0093] in, Indicates in time; Indicates time-based The previous unit of time; In time The rate of change of displacement estimate; Indicates time Displacement estimation; Indicates in Estimation of displacement over time; Indicates time The estimated rate of change in temperature; Indicates time Temperature estimation; Indicates in Temperature estimation over time; Indicates time The estimated rate of change in humidity; Indicates time Humidity estimation; Indicates in Humidity estimates over time. These features are used to represent the rate of change between adjacent sampling times in order to be incorporated into the prediction model.

[0094] Step S331: Establishing a nonlinear regression prediction model:

[0095] This system uses a nonlinear regression function based on time-series data to establish a concrete shrinkage trend prediction model:

[0096] ;

[0097] in, Indicates in time; Indicates time-based The Future time; To predict residuals; Indicates prediction in Displacement over time (contraction). Indicates time The pressure valuation; Indicates time Temperature estimation; Indicates time Humidity estimation; In time The nonlinear mapping function.

[0098] Specifically, the Kalman filter algorithm is used to filter out noise in sensor data, optimizing data accuracy and real-time performance, and ensuring accurate monitoring of the concrete hardening process. Simultaneously, the system's predictive function is configured to track potential deformation trends during concrete hardening. Alarm thresholds and control logic are set for the system. Corresponding alarm values ​​are set based on the safe ranges for displacement, pressure, temperature, and humidity. Once the monitored data exceeds the preset range, the system automatically issues an alarm to alert operators for timely intervention. A comprehensive system test is conducted, simulating different sensor data inputs to check the system's response time, data processing accuracy, and alarm functions. Based on the test results, the data processing speed and system stability are adjusted to optimize overall performance and ensure continuous and stable operation of the system during the concrete hardening process.

[0099] Further, step S400 includes steps S410 to S430.

[0100] Step S410: Based on the real-time sensing data collected by the sensor, substitute the data into the concrete shrinkage trend prediction model to obtain the expected shrinkage trend value.

[0101] Step S420: Calculate the residuals based on the real-time sensing data and the expected shrinkage trend value, and adaptively update the parameters of the concrete shrinkage trend prediction model using data optimization criteria to obtain an optimized prediction model;

[0102] Step S430: Simulate the optimized prediction model based on the displacement measurement value of the real-time sensing data to obtain the prediction trend and risk assessment results.

[0103] Specifically, during the concrete hardening process, the central control system collects data from displacement, pressure, temperature, and humidity sensors in real time. Through the monitoring interface, operators can view the current status of each sensor at any time, including concrete shrinkage deformation, bonding pressure, temperature changes in hydration heat release, and ambient humidity. The system continuously records data at preset time intervals to ensure real-time and continuous monitoring.

[0104] Step S411: The system performs real-time analysis on the data collected by the sensors. Using the Kalman filter algorithm and nonlinear regression model, the system can remove noise and predict the shrinkage trend of concrete. Based on data such as temperature, humidity, and pressure, the system analyzes the hardening state of the concrete, predicts potential deformation risks in advance, and facilitates decision-making by operators.

[0105] Real-time forecasts and updates:

[0106] Using the fused sensor data at the current moment, and substituting it into the established prediction model, the estimated value of the future contraction displacement is calculated:

[0107] ;

[0108] in, Indicates in time; Indicates time-based The Future time; In order to be in Estimated value of the contraction displacement over time; Indicates time The pressure valuation; Indicates time Temperature estimation; Indicates time Humidity estimation; In time The nonlinear mapping function.

[0109] The estimated future contraction displacement is compared with the current displacement measurement to obtain the predicted contraction trend value:

[0110] ;

[0111] in, Indicates in time; Indicates in time; Indicates time-based The Future time; In order to be in The projected contraction trend value over time; In order to be in Estimates of the time-contraction displacement; Indicates in The system estimates the displacement over time; if the expected contraction trend exceeds the preset safety threshold, the system will issue an early warning on the central control platform, prompting construction personnel to make adjustments.

[0112] Step S421, Adaptive update of model parameters:

[0113] The system continuously collects new real-time data during the concrete hardening process and performs residual calculations with the predicted values:

[0114] ;

[0115] in, Indicates in time; In order to be in Time residuals; Indicates in Estimation of displacement over time; This is real-time displacement data.

[0116] The model parameters are adaptively updated using the minimum mean square error (MSE) criterion.

[0117] ;

[0118] in, These are the parameters to be optimized. This represents the total number of monitoring points. The number of samples; For the first The square of the sample error is used to update the model, achieving dynamic optimization as the model hardens, thus improving prediction accuracy and robustness.

[0119] Step S431: Mark the predicted shrinkage trend curve, risk assessment results, and possible abnormal periods on the monitoring interface. The system generates adjustment suggestions, such as adjusting ambient humidity, changing curing methods, or increasing local support pressure, to assist operators in decision-making. When the system detects abnormalities during the concrete hardening process, such as excessive displacement or insufficient pressure, it will generate corresponding adjustment suggestions. Operators can manually adjust according to these suggestions to ensure that the concrete hardening process is within a safe range. The suggestions are based on the analysis of current data and trend predictions to help operators make correct operational judgments. All monitoring data throughout the concrete hardening process is stored in the system database, forming a detailed historical record. Through data storage, the hardening process can be retrospectively analyzed later to verify the accuracy of the monitoring process and provide a reference for subsequent similar projects.

[0120] Further, step 500 includes steps S510 to S530.

[0121] Step S510: Analyze the pressure distribution at the interface between the concrete column and the foundation based on the pressure monitoring data of the real-time sensing data. Establish a two-dimensional distribution model of the interface between the column and the foundation based on the spatial arrangement coordinates of the pressure sensors to obtain the uniformity index of the pressure distribution.

[0122] Step S520: Calculate the relative deformation of the concrete based on the displacement measurement data of the real-time sensing data to obtain the overall average shrinkage rate of the concrete.

[0123] Step S530: Analyze the stress condition of the column and the foundation based on the uniformity index of the pressure distribution and the overall average shrinkage rate of the concrete. Combine the predicted trend and risk assessment results to make a multivariate judgment and obtain the stress state criteria of the column and the foundation.

[0124] Specifically, by collecting all monitoring data from displacement, pressure, temperature, and humidity sensors, the system conducts a detailed analysis of the fit between the new column and the existing foundation. The system focuses on assessing the pressure distribution between the column and the foundation during the concrete hardening process and whether shrinkage deformation is within acceptable limits to ensure a good fit.

[0125] By collecting monitoring data from all sensors, the system conducts a detailed analysis of the fit between the newly constructed column and the existing foundation. The specific analysis process is as follows:

[0126] Step S511, Data Summary and Organization:

[0127] The system inputs displacement, pressure, temperature, and humidity data collected throughout the concrete hardening process into the database of the central control system. Let the measuring points in the sensor array be: The raw data measured by the sensor is: .

[0128] After all data are fused using Kalman filtering, the effective noise reduction measurements are obtained:

[0129] ;

[0130] in, The sensor's measurement point number; Indicates in time; In order to be in time Effective measurement value of noise reduction at the detection point; In order to be in time Displacement of detection points after fusion processing; exist time Pressure after detection point fusion processing; In order to be in time Temperature after detection point fusion processing; In order to be in time Humidity after detection point fusion processing.

[0131] Step S512, Pressure Distribution Analysis:

[0132] The system establishes a two-dimensional distribution model of the column-foundation interface based on the spatial coordinates of the pressure sensors. The pressure at any point on the interface is defined as... Data from discrete measurement points can be transformed into a continuous distribution using interpolation methods (such as bilinear interpolation or radial basis functions).

[0133] ;

[0134] in, The sensor's measurement point number; The x-coordinate of the junction surface; The vertical coordinate of the junction surface; To combine the pressure at any point on the surface; This represents the total number of monitoring points. In order to be in Pressure after detection point fusion processing; In order to be in Weighting function for detection points; For coordinate points The corresponding weighting function.

[0135] Step S513: Calculate the uniformity index of pressure distribution in the system:

[0136] ;

[0137] in, This refers to the pressure value. It serves as an index for the uniformity of pressure distribution; The average pressure across the entire field; For pressure standard deviation. When (Setting a threshold) indicates that the pressure distribution between the column and the foundation is uniform and the fit is good; otherwise, the system will indicate that there is uneven fit.

[0138] Step S521, Shrinkage Deformation Analysis:

[0139] Based on the measurement data from the displacement sensor, the system calculates the relative deformation of the concrete at different stages of hardening:

[0140] ;

[0141] in, The sensor's measurement point number; In order to be in The relative deformation at different stages of the detection point; and Indicates time status; In order to be in testing point The relative deformation under the condition; In order to be in testing point The relative deformation under the given conditions.

[0142] And calculate the overall average shrinkage rate:

[0143] ;

[0144] in, This represents the average shrinkage rate. Number of monitoring points; The number of samples; This represents the initial distance or structural reference length for each measuring point.

[0145] Step S531: The system compares the above calculation results with the design reference shrinkage limit. In comparison, when This indicates that the concrete shrinkage is within an acceptable range; when some measuring points show... The system automatically locates deviation areas and marks them as risk zones. By collecting all monitoring data from displacement, pressure, temperature, and humidity sensors, the system performs a detailed analysis of the fit between the new column and the existing foundation. The system focuses on evaluating the pressure distribution between the column and the foundation during concrete hardening and whether shrinkage deformation is within acceptable limits to ensure a good fit.

[0146] Further, step 600 includes steps S610 to S630.

[0147] Step S610: Establish a state assessment model based on the stress state criterion, and obtain the assessment state model by introducing weight coefficients to represent the relative stress state of the joint surface between the column and the foundation.

[0148] Step S620: Determine the fit between the column and the foundation according to the evaluation state model. By analyzing the pressure distribution and contraction state of the joint surface between the column and the foundation, obtain the fit condition criteria.

[0149] Step S630: Based on the fitting state criterion and the evaluation model, evaluate the load capacity of the newly constructed concrete column, integrate the data from the evaluation process, and obtain the concrete hardening deformation evaluation result.

[0150] Step S611: Specifically, a comprehensive quantitative judgment is performed. The system evaluates the bonding state through a multi-dimensional comprehensive function.

[0151] ;

[0152] in, This refers to the pressure value. For a suitable fit value; It serves as an index for the uniformity of pressure distribution; This represents the average shrinkage rate. Shrinkage limit; and , where is the weighting coefficient, representing the relative influence of pressure uniformity on contraction stability.

[0153] Step S621, when ( If the connection threshold is reached (i.e., the column and foundation are properly bonded), the system determines that the bond is good; otherwise, the system automatically issues an alarm and prompts construction personnel to reinforce or adjust the connection. During the stage where the concrete hardens to the design strength, a pressure sensor measures the load pressure borne by the newly constructed column to verify its ability to bear the design load. If the pressure value meets expectations, the connection strength between the column and foundation is sufficient; if not, further inspection of the concrete strength or the bond condition is required.

[0154] Step S631, Result Output and Reporting:

[0155] After the concrete has hardened, the system verifies the fit between the new column and the existing foundation, confirming a tight bond. Pressure sensors assess the bonding pressure between the column and the foundation to ensure there are no gaps or uneven bonding. Subsequently, the system conducts load tests to ensure the new column meets the design load-bearing capacity. The analysis results are displayed graphically: the system generates a pressure distribution map and a shrinkage deformation trend map, marking uneven areas, and automatically outputs an evaluation report. This report records all monitoring data and verification results throughout the construction process, serving as a scientific basis for construction acceptance and quality assessment, and providing data support for subsequent maintenance.

[0156] Example 2:

[0157] like Figure 2 As shown, this embodiment provides a concrete hardening deformation prediction system, which includes:

[0158] The acquisition module 101 is used to acquire historical sensor datasets, which include concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity.

[0159] Processing module 102 is used to perform data fusion analysis processing based on the historical sensing dataset, filter out noise and optimize estimation accuracy based on a unified state estimation framework, and obtain a fused state vector.

[0160] The mapping module 103 establishes a nonlinear mapping relationship between the displacement, pressure, temperature and humidity parameter sequences and the shrinkage deformation sequence based on the fused state vector, thereby obtaining a concrete shrinkage trend prediction model.

[0161] The prediction module 104 acquires the real-time sensor dataset and inputs it into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updating of the data, the prediction trend and risk assessment results are obtained.

[0162] The calculation module 105 performs quantitative analysis based on the predicted trend and risk assessment results and the historical sensor dataset. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, it obtains the stress state criteria of the column and the foundation.

[0163] The output module 106 is used to evaluate the fit between the newly built concrete column and the existing foundation according to the stress state criterion, and obtain the concrete hardening deformation evaluation result.

[0164] In one specific embodiment of the present invention, the processing module 102 includes:

[0165] The first processing unit is used to define state variables based on the historical sensor dataset, and obtain the state vector of the measurement dataset by combining the measured displacement, pressure, temperature and humidity.

[0166] The second processing unit is used to predict the hardening state of concrete based on the state vector of the measurement dataset, create a prediction model based on the state vector structure state parameters, and perform mapping processing on the system state to obtain the prediction state matrix.

[0167] The third processing unit is used to update and correct the prediction results based on the predicted state matrix and the historical sensor dataset, and to filter out noise and optimize the estimation accuracy based on a unified state estimation framework to obtain a fused state vector.

[0168] In one specific embodiment of the present invention, the mapping module 103 includes:

[0169] The first mapping unit is used to receive the raw data stream according to the fused state vector at a preset sampling period, and to convert the displacement, pressure, temperature and humidity data to obtain a parameter sequence.

[0170] The second mapping unit is used to screen and analyze the parameters affecting the shrinkage trend of concrete based on the parameter sequence, and obtain the characteristic variables by performing difference and normalization processing on the parameters.

[0171] The third mapping unit is used to establish a prediction model based on the feature variables, predict the future shrinkage deformation trend based on the nonlinear mapping relationship between time series data and shrinkage deformation, and obtain a concrete shrinkage trend prediction model.

[0172] In one specific embodiment of the present invention, the prediction module 104 includes:

[0173] The first prediction unit is used to input the real-time sensing data collected by the sensor into the concrete shrinkage trend prediction model to obtain the expected shrinkage trend value.

[0174] The second prediction unit is used to compare and analyze the resistance of soil particles to groundwater forces based on the micromechanical equilibrium criterion. By comparing the magnitude of the resistance of soil particles to dynamic forces and the driving force of groundwater seepage, the stability conditions of soil particles are obtained.

[0175] The third prediction unit is used to simulate the optimized prediction model based on the displacement measurement value of the real-time sensing data to obtain the prediction trend and risk assessment results.

[0176] In one specific embodiment of the present invention, the calculation module 105 includes:

[0177] The first calculation unit is used to analyze the pressure distribution of the concrete column and the foundation joint surface based on the pressure monitoring data of the real-time sensing data, establish a two-dimensional distribution model of the column and foundation joint surface based on the spatial arrangement coordinates of the pressure sensors, and obtain the uniformity index of the pressure distribution.

[0178] The second calculation unit is used to calculate the relative deformation of the concrete based on the displacement measurement data of the real-time sensing data, and to obtain the overall average shrinkage rate of the concrete.

[0179] The third calculation unit is used to analyze the stress condition of the column and the foundation based on the uniformity index of the pressure distribution and the overall average shrinkage rate of the concrete, and to make a multivariate judgment based on the predicted trend and risk assessment results to obtain the stress state criteria of the column and the foundation.

[0180] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of predicting a hardening deformation of concrete, characterized by, include: Acquire historical sensor datasets, which include concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity. Based on the historical sensor dataset, data fusion analysis is performed, and a unified state estimation framework is used to filter out noise and optimize estimation accuracy to obtain a fused state vector. Based on the fused state vector, a nonlinear mapping relationship is established between the displacement, pressure, temperature, and humidity parameter sequences and the shrinkage deformation sequence to obtain a concrete shrinkage trend prediction model; Acquire real-time sensor datasets and input them into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updating of the data, obtain the predicted trend and risk assessment results. Based on the predicted trend and risk assessment results and the historical sensor dataset, a quantitative analysis is performed. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, the stress state criteria of the column and the foundation are obtained. The bonding state between the newly constructed concrete column and the existing foundation is evaluated based on the stress state criterion, and the concrete hardening deformation evaluation result is obtained.

2. The method according to claim 1, wherein Based on the historical sensor dataset, data fusion analysis is performed. A unified state estimation framework is used to filter out noise and optimize estimation accuracy, resulting in a fused state vector, including: State variables are defined based on the historical sensor dataset. By combining the measured displacement, pressure, temperature and humidity, a state vector of the measurement dataset is obtained. The hardening state of concrete is predicted based on the state vector of the measurement dataset. A prediction model is created based on the state vector structure state parameters and the system state is mapped to obtain the prediction state matrix. The prediction results are updated and corrected based on the predicted state matrix and historical sensor dataset. A unified state estimation framework is used to filter out noise and optimize estimation accuracy to obtain a fused state vector.

3. The method for predicting concrete hardening deformation according to claim 1, characterized in that, Based on the fused state vector, a nonlinear mapping relationship is established between the displacement, pressure, temperature, and humidity parameter sequences and the shrinkage deformation sequence to obtain a concrete shrinkage trend prediction model, including: Based on the fused state vector, the raw data stream is received at a preset sampling period, and the displacement, pressure, temperature, and humidity are converted to obtain a parameter sequence. The parameters affecting the shrinkage trend of concrete are screened and analyzed based on the parameter sequence. Characteristic variables are obtained by differentiating and normalizing the parameters. A prediction model is established based on the aforementioned characteristic variables, and the future shrinkage deformation trend is predicted based on the nonlinear mapping relationship between time series data and shrinkage deformation, thus obtaining a concrete shrinkage trend prediction model.

4. The method for predicting concrete hardening deformation according to claim 1, characterized in that, Real-time sensor data is acquired and input into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updating of the data, the predicted trend and risk assessment results are obtained, including: Based on the real-time sensing data collected by the sensors, the data is substituted into the concrete shrinkage trend prediction model to obtain the expected shrinkage trend value. Based on the real-time sensing data and the expected shrinkage trend value, the residual is calculated, and the parameters of the concrete shrinkage trend prediction model are adaptively updated using data optimization criteria to obtain an optimized prediction model. The optimized prediction model is simulated based on the displacement measurement values ​​of the real-time sensing data to obtain the prediction trend and risk assessment results.

5. The method for predicting concrete hardening deformation according to claim 1, characterized in that, Based on the predicted trends, risk assessment results, and historical sensor datasets, quantitative analysis is performed. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, the stress state criteria for the column and foundation are obtained, including: Based on the pressure monitoring data of the real-time sensing data, the pressure distribution at the interface between the concrete column and the foundation is analyzed. A two-dimensional distribution model of the interface between the column and the foundation is established based on the spatial arrangement coordinates of the pressure sensors to obtain the uniformity index of the pressure distribution. The relative deformation of the concrete is calculated based on the displacement measurement data of the real-time sensing data to obtain the overall average shrinkage rate of the concrete. The stress conditions of the column and the foundation are analyzed based on the uniformity index of the pressure distribution and the overall average shrinkage rate of the concrete. Combined with the predicted trend and risk assessment results, a multivariate judgment is made to obtain the stress state criteria of the column and the foundation.

6. A concrete hardening deformation prediction system, characterized in that, include: The acquisition module is used to acquire historical sensor datasets, which include concrete deformation parameters, bonding pressure between concrete and the foundation, concrete temperature, and ambient humidity. The processing module is used to perform data fusion analysis based on the historical sensor dataset, filter out noise and optimize estimation accuracy based on a unified state estimation framework, and obtain a fused state vector. The mapping module establishes a nonlinear mapping relationship between the displacement, pressure, temperature, and humidity parameter sequences and the shrinkage deformation sequence based on the fused state vector, thereby obtaining a concrete shrinkage trend prediction model. The prediction module acquires real-time sensor datasets and inputs them into the concrete shrinkage trend prediction model. Through real-time prediction and adaptive updates of the data, the predicted trend and risk assessment results are obtained. The calculation module performs quantitative analysis based on the predicted trend and risk assessment results and the historical sensor dataset. By analyzing the pressure distribution and shrinkage deformation state between the column and the foundation, it obtains the stress state criteria for the column and the foundation. The output module is used to evaluate the fit between the newly built concrete column and the existing foundation according to the stress state criterion, and obtain the concrete hardening deformation evaluation result.

7. The concrete hardening deformation prediction system according to claim 6, characterized in that, The processing module includes: The first processing unit defines state variables based on the historical sensor dataset and obtains the state vector of the measurement dataset by combining the measured displacement, pressure, temperature and humidity. The second processing unit predicts the hardening state of concrete based on the state vector of the measurement dataset, creates a prediction model based on the state vector structure state parameters, and maps the system state to obtain the prediction state matrix. The third processing unit updates and corrects the prediction results based on the predicted state matrix and the historical sensor dataset, and obtains the fused state vector by filtering out noise and optimizing the estimation accuracy based on a unified state estimation framework.

8. The concrete hardening deformation prediction system according to claim 6, characterized in that, The mapping module includes: The first mapping unit receives the raw data stream according to the fused state vector at a preset sampling period, and converts the displacement, pressure, temperature and humidity data to obtain a parameter sequence. The second mapping unit screens and analyzes the parameters that affect the shrinkage trend of concrete based on the parameter sequence, and obtains the characteristic variables by performing difference and normalization on the parameters. The third mapping unit establishes a prediction model based on the characteristic variables, and predicts the future shrinkage deformation trend based on the nonlinear mapping relationship between time series data and shrinkage deformation, thus obtaining a concrete shrinkage trend prediction model.

9. The concrete hardening deformation prediction system according to claim 6, characterized in that, The prediction module includes: The first prediction unit inputs the real-time sensing data collected by the sensor into the concrete shrinkage trend prediction model to obtain the expected shrinkage trend value. The second prediction unit performs residual calculations based on the real-time sensing data and the expected shrinkage trend value, and uses data optimization criteria to adaptively update the parameters of the concrete shrinkage trend prediction model to obtain an optimized prediction model. The third prediction unit simulates the optimized prediction model based on the displacement measurement value of the real-time sensing data to obtain the prediction trend and risk assessment results.

10. The concrete hardening deformation prediction system according to claim 6, characterized in that, The computing module includes: The first calculation unit is used to analyze the pressure distribution of the concrete column and the foundation joint surface based on the pressure monitoring data of the real-time sensing data, establish a two-dimensional distribution model of the column and foundation joint surface based on the spatial arrangement coordinates of the pressure sensors, and obtain the uniformity index of the pressure distribution. The second calculation unit is used to calculate the relative deformation of the concrete based on the displacement measurement data of the real-time sensing data, and to obtain the overall average shrinkage rate of the concrete. The third calculation unit is used to analyze the stress condition of the column and the foundation based on the uniformity index of the pressure distribution and the overall average shrinkage rate of the concrete, and to make a multivariate judgment based on the predicted trend and risk assessment results to obtain the stress state criteria of the column and the foundation.

Images