Adjustable continuous beam cantilever construction monitoring system

Abstract

The invention discloses an adjustable continuous beam cantilever construction monitoring system. The system comprises the following steps: S1, collecting data in a construction process; s2, performing decoding, filtering and digital processing to generate an original monitoring data set; s3, performing error correction and optimization on the original monitoring data set based on a Kalman filtering algorithm to obtain an optimized monitoring data set; s4, analyzing and optimizing the monitoring data set by adopting a support vector machine algorithm, and generating a construction adjustment instruction; s5, performing time sequence analysis and pattern recognition on the optimized monitoring data set, and detecting potential construction risks; and S6, receiving a construction adjustment instruction and a construction early warning signal, and dynamically adjusting the working parameters of the construction equipment. The system has the advantages of being high in data processing precision, high in real-time performance and high in construction safety.

Description

Technical Field

[0001] The invention relates to the technical field of construction monitoring, and in particular to an adjustable continuous beam cantilever construction monitoring system. Background Art

[0002] With the continuous development of the construction engineering field, construction quality and safety management have become the focus of the industry. Especially in the cantilever construction of continuous beams, due to the complex construction environment and large load changes during the construction process, there are many potential construction risks, such as structural deformation and stress overrun, which may have a serious impact on the quality and safety of the project. Therefore, how to accurately and real-time monitor various parameters during the construction process and adjust the construction status in time has become the key to improving construction efficiency and ensuring project safety.

[0003] In the existing technology, traditional construction monitoring systems mostly rely on simple sensor data collection and a single early warning mechanism. Although these methods can provide certain monitoring functions, they have obvious shortcomings in the following aspects: 1. Insufficient monitoring data processing capabilities: Most existing construction monitoring systems rely only on traditional data analysis methods, such as simple mean calculations or rule judgments based on experience, and lack the ability to deeply analyze and process complex data. They are unable to effectively identify potential construction risks, resulting in low accuracy and timeliness of the early warning mechanism.

[0004] 2. Lack of intelligent data fusion and optimization: In traditional systems, data processing at each monitoring point is often independent, lacking intelligent data fusion methods. It is impossible to fully utilize the redundant information provided by multi-sensor data, and it is impossible to perform real-time state estimation and optimization, resulting in the monitoring data being difficult to reflect changes in the actual construction status, and it is impossible to dynamically adjust construction parameters to cope with changes on site.

[0005] 3. Delayed adjustment of construction parameters: Existing construction monitoring systems are mostly static early warning mechanisms. The adjustment of construction parameters usually relies on manual judgment, with a long adjustment cycle and slow response. This makes the adaptive adjustment capability of construction parameters insufficient in a dynamic construction environment and cannot meet the real-time control requirements under complex working conditions.

[0006] 4. Inaccurate construction risk warning: Most existing construction risk warning systems rely on simple threshold settings or empirical rules, which cannot accurately and comprehensively identify potential construction risks, and lack comprehensive monitoring and early warning of dynamic changes in the construction process. This results in the inability to detect and handle sudden risks that may occur during the construction process in a timely manner.

[0007] Therefore, how to provide an adjustable continuous beam cantilever construction monitoring system is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0008] One purpose of the present invention is to propose an adjustable continuous beam cantilever construction monitoring system, which combines big data analysis, sensor data fusion and support vector machine algorithm to intelligently monitor, predict and adjust parameters during the construction process. The system can dynamically adjust parameters, accurately identify potential risks and issue early warning signals during the construction process through the fusion and real-time optimization of multi-sensor data, combined with intelligent prediction and early warning of construction status, and has the advantages of high data processing accuracy, strong real-time performance and high construction safety.

[0009] An adjustable continuous beam cantilever construction monitoring system according to an embodiment of the present invention comprises: S1, fiber Bragg grating sensor array, is deployed at key positions of the continuous beam cantilever construction to collect displacement data, stress data and temperature data during the construction process; S2, a data preprocessing module, connected to the fiber grating sensor array, decodes, filters and digitizes the displacement data, stress data and temperature data to generate a set of original monitoring data; S3, data optimization module, performs error correction and optimization on the original monitoring data set based on the Kalman filter algorithm, removes redundant information, and obtains an optimized monitoring data set; S4, construction parameter adaptive adjustment module, uses support vector machine algorithm to analyze and optimize monitoring data set, predict changes in key parameters during construction, and generate construction adjustment instructions; S5, construction status warning module, combines big data analysis to perform time series analysis and pattern recognition on the optimized monitoring data set, detects potential construction risks, and triggers construction warning signals when construction risks exceed the limit; S6, intelligent control module, receives construction adjustment instructions and construction warning signals, and dynamically adjusts the working parameters of the construction equipment.

[0010] Optionally, S3 specifically includes: S31, a data receiving unit connected to the data preprocessing module, receiving the displacement data collected by the fiber grating sensor array , stress data and temperature data The data preprocessing module decodes, filters and digitizes the data to generate the original monitoring data set. , and the original monitoring data set Perform time synchronization correction to keep the data timing of different monitoring points consistent and obtain a timing correction data set ; S32, a noise suppression unit, performs a timing correction on the data set De-noising is performed by using an adaptive signal filtering method combined with the Kalman filtering algorithm to remove environmental noise and random interference to obtain a de-noised data set. ; S33, state estimation unit, for the denoised data set Perform Kalman filter state estimation; S34, data fusion unit, calculates the optimal estimate based on the Kalman gain, fuses the data of multiple monitoring points, corrects the current measurement value based on the prior information, and calculates the optimal state estimate , and output the optimized monitoring data set ; S35, anomaly detection unit, optimizes the monitoring data set Perform outlier identification based on optimized monitoring data set Calculate data distribution characteristics and build dynamic thresholds : ; in, For the current moment The mean of the optimized monitoring data set, For the current moment The standard deviation of the optimized monitoring data set, is the threshold adjustment coefficient; Optimizing monitoring data collection Perform point-by-point detection to determine the measured values ​​in the optimized monitoring data set Is it satisfied? , if satisfied, then the measured value Record it as abnormal data and mark the corresponding monitoring point , and use historical monitoring data collection Interpolation correction of abnormal data: ; in, is the modified optimized monitoring data set, is the correction coefficient matrix, It is the data value corresponding to the historical monitoring data. At the same time, it records the temporal and spatial information of the abnormal data and generates an abnormal data log.

[0011] Optionally, S33 specifically includes: S331, state initialization unit, denoising data set Assign initial state and set initial state estimate and the initial error covariance matrix : ; in, is the initial error covariance matrix, is the mathematical expectation operator, It represents the estimated value of the initial state at the initial moment; S332, prediction update unit, predicting the current time based on the state transfer equation State estimation data, calculate the predicted state estimation value And the prediction error covariance matrix : ; ; in, is the forecast error covariance matrix, is the process noise covariance matrix, is the state transfer matrix, For The transposed matrix of is the control input matrix, Adjusting instructions for construction; S333, measurement update unit, based on the current observation value Calculate Kalman gain : ; in, is the measurement noise covariance matrix, is the measurement matrix, To measure the transpose of the matrix, use the Kalman gain Correct the predicted state estimate to obtain the optimal state estimate , and the current moment The optimal state estimate of Store to estimation data set : ; And update the error covariance: ; in, is the identity matrix, is the error covariance matrix.

[0012] Optionally, S34 specifically includes: S341, multi-sensor data synchronization unit, receiving estimated data sets from multiple monitoring points , synchronize the timestamps of different monitoring points and generate a time-synchronized data set ; S342, weighted data fusion unit, based on time synchronization data set , weighted fusion of the state estimation values ​​of each monitoring point is performed using the Kalman gain Compute the weighted best estimate: ; in, is the optimal state estimate after fusion, is the number of monitoring points, For the The estimated value of the state of each monitoring point, is the Kalman gain of the monitoring point; S343, a priori information correction unit, based on historical monitoring data set and statistical characteristics, weighted optimal estimate Perform deviation correction, calculate the corrected state estimate, and convert the corrected state estimate into Store to optimized monitoring data set : ; in, is the correction coefficient matrix, A collection of historical monitoring data.

[0013] Optionally, S4 specifically includes: S41, data preprocessing unit, receiving optimized monitoring data set and historical monitoring data collection , to optimize the monitoring data set and historical monitoring data collection Perform standardization, normalize the numerical range of each parameter, and construct a training data set and real-time input data collection ,in, is the corresponding set of known construction parameters and monitoring data, To indicate the The construction parameters of training samples, To indicate the The monitoring data of training samples, represents the number of samples in the training data set; S42, support vector machine training unit, based on the training data set Train the support vector machine model, establish the construction parameter prediction model, and solve the optimal classification hyperplane: ; in, is the Lagrange multiplier, is the actual observed value of the construction parameter, is the Gaussian radial basis kernel function, is the kernel parameter, is the number of training samples; S43, real-time prediction unit, based on the trained support vector machine model, Make predictions and calculate construction parameter prediction values : ; in, is the model bias term, For the current moment Predicted values ​​of construction parameters; S44, adjustment instruction generation unit, based on construction parameter prediction value and optimize monitoring data collection Calculate parameter adjustment , and generate construction adjustment instructions based on the adjustment amount .

[0014] Optionally, S44 specifically includes: S441, adjustment amount calculation unit, based on the construction parameter prediction value and optimize monitoring data collection , calculate the construction parameter adjustment : ; in, is the target reference value of the construction parameter, Adjust the weight matrix for the construction parameters, Adjust the weight matrix for monitoring data, It is a collection of historical monitoring data; S442, adjustment strategy optimization unit, calculates the optimal adjustment strategy through multi-objective optimization method , and select the adjustment mode according to the current working conditions, including incremental adjustment mode and global optimization mode; S443, the adjustment instruction generation unit, according to the optimal adjustment strategy And the calculated construction parameter adjustment , generate construction adjustment instructions , the instruction format is as follows: ; in, To adjust the execution time parameters of the instruction.

[0015] Optionally, S5 specifically includes: S51, time series analysis unit, receiving optimized monitoring data set , based on historical monitoring data and optimized monitoring data collection To carry out time series modeling, the autoregressive integrated moving average model is used to calculate the current moment The monitoring data is used to predict and generate time series forecast values , and output the current time Trend forecast of monitoring data; S52, pattern recognition unit, based on time series prediction value and optimize monitoring data collection , using big data analysis methods to perform pattern recognition on monitoring data, combined with known construction risk pattern libraries, and using decision tree algorithms to classify and pattern match monitoring data, and output construction risk indications : ; in, is the pattern recognition function, For the current moment The construction risk indicator indicates whether there are potential construction risks in the current construction environment; S53, risk threshold judgment unit, setting risk threshold , the construction risk indication output by the pattern recognition unit Make a judgment, if the construction risk indication exceeds the set risk threshold , then the construction warning signal is triggered : ; in, It is a construction warning signal. When it is on, it means that there is a potential risk in the current construction status, and an early warning needs to be triggered and corresponding adjustments need to be made; S54, warning signal output unit, according to the judgment result, sends the construction warning signal The data is output to the intelligent control module to generate early warning notifications and provide real-time feedback to construction personnel.

[0016] (1) The present invention realizes accurate monitoring and intelligent adjustment of the continuous beam cantilever construction process by combining multi-sensor data fusion, Kalman filter algorithm, support vector machine algorithm and big data analysis. The system can collect data from multiple monitoring points in real time, accurately predict construction parameters and make adaptive adjustments through data fusion and state estimation, thereby significantly improving the accuracy and safety of the construction process.

[0017] (2) The present invention adopts intelligent anomaly detection and construction status warning modules, combined with time series analysis and pattern recognition technology, to effectively identify potential construction risks and trigger warnings in a timely manner when the risk threshold is exceeded. This mechanism greatly enhances the real-time monitoring capability of the construction process, improves the risk prevention and control level during the construction process, and ensures construction safety.

[0018] (3) The present invention can optimize the construction plan in real time for different construction environments and conditions by dynamically adjusting the construction parameters, combining construction status prediction and historical data correction, thus reducing the need for manual intervention. The system can continuously learn and adapt to changes in the construction process, improve the intelligence and automation level of the construction process, reduce human errors and construction delays, and further improve construction efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a general framework diagram of an adjustable continuous beam cantilever construction monitoring system proposed by the present invention. DETAILED DESCRIPTION

[0020] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0021] refer to Figure 1 , an adjustable continuous beam cantilever construction monitoring system, the system comprising: S1, fiber Bragg grating sensor array, is deployed at key positions of the continuous beam cantilever construction to collect displacement data, stress data and temperature data during the construction process; This embodiment receives sensor data sets from multiple monitoring points, performs denoising processing on them, and uses the Kalman filter algorithm to achieve accurate data estimation and fusion, thereby effectively improving the quality and reliability of monitoring data.

[0022] S2, a data preprocessing module, connected to the fiber grating sensor array, decodes, filters and digitizes the displacement data, stress data and temperature data to generate a set of original monitoring data; This implementation provides accurate monitoring and prediction capabilities for the construction process by combining the Kalman filter algorithm and multi-sensor data fusion technology. By denoising, predicting and weighted fusion of real-time data from different monitoring points, the present invention can effectively eliminate noise interference in the data and improve the accuracy of state estimation. At the same time, by combining historical monitoring data for deviation correction, the prediction accuracy of construction parameters is further optimized, so that changes in key parameters during the construction process can be tracked and adjusted in real time.

[0023] S3, data optimization module, performs error correction and optimization on the original monitoring data set based on the Kalman filter algorithm, removes redundant information, and obtains an optimized monitoring data set; In this implementation, S3 specifically includes: S31, a data receiving unit connected to the data preprocessing module, receiving the displacement data collected by the fiber grating sensor array , stress data and temperature data The data preprocessing module decodes, filters and digitizes the data to generate the original monitoring data set. , and the original monitoring data set Perform time synchronization correction to keep the data timing of different monitoring points consistent and obtain a timing correction data set ; S32, a noise suppression unit, performs a timing correction on the data set De-noising is performed by using an adaptive signal filtering method combined with the Kalman filtering algorithm to remove environmental noise and random interference to obtain a de-noised data set. ; S33, state estimation unit, for the denoised data set Perform Kalman filter state estimation; S34, data fusion unit, calculates the optimal estimate based on the Kalman gain, fuses the data of multiple monitoring points, corrects the current measurement value based on the prior information, and calculates the optimal state estimate , and output the optimized monitoring data set ; S35, anomaly detection unit, optimizes the monitoring data set Perform outlier identification based on optimized monitoring data set Calculate data distribution characteristics and build dynamic thresholds : ; in, For the current moment The mean of the optimized monitoring data set, For the current moment The standard deviation of the optimized monitoring data set, is the threshold adjustment coefficient; Optimizing monitoring data collection Perform point-by-point detection to determine the measured values ​​in the optimized monitoring data set Is it satisfied? , if satisfied, then the measured value Record it as abnormal data and mark the corresponding monitoring point , and use historical monitoring data collection Interpolation correction of abnormal data: ; in, is the modified optimized monitoring data set, is the correction coefficient matrix, It is the data value corresponding to the historical monitoring data. At the same time, it records the temporal and spatial information of the abnormal data and generates an abnormal data log.

[0024] The S33 specifically includes: S331, state initialization unit, denoising data set Assign initial state and set initial state estimate and the initial error covariance matrix : ; in, is the initial error covariance matrix, is the mathematical expectation operator, It represents the estimated value of the initial state at the initial moment; S332, prediction update unit, predicting the current time based on the state transfer equation State estimation data, calculate the predicted state estimation value And the prediction error covariance matrix : ; ; in, is the forecast error covariance matrix, is the process noise covariance matrix, is the state transfer matrix, for The transposed matrix of is the control input matrix, Adjusting instructions for construction; S333, measurement update unit, based on the current observation value Calculate Kalman gain : ; in, is the measurement noise covariance matrix, is the measurement matrix, To measure the transpose of the matrix, use the Kalman gain Correct the predicted state estimate to obtain the optimal state estimate , and the current moment The optimal state estimate of Store to estimation data set : ; And update the error covariance: ; in, is the identity matrix, is the error covariance matrix.

[0025] The S34 specifically includes: S341, multi-sensor data synchronization unit, receiving estimated data sets from multiple monitoring points , synchronize the timestamps of different monitoring points and generate a time-synchronized data set ; S342, weighted data fusion unit, based on time synchronization data set , weighted fusion of the state estimation values ​​of each monitoring point is performed using the Kalman gain Compute the weighted best estimate: ; in, is the optimal state estimate after fusion, is the number of monitoring points, For the The estimated value of the state of each monitoring point, is the Kalman gain of the monitoring point; S343, a priori information correction unit, based on historical monitoring data set and statistical characteristics, weighted optimal estimate Perform deviation correction, calculate the corrected state estimate, and convert the corrected state estimate into Store to optimized monitoring data set : ; in, is the correction coefficient matrix, A collection of historical monitoring data.

[0026] This implementation method uses the Kalman filter algorithm to perform state estimation and optimization on the denoised data set, and combines the steps of prediction update, measurement update and data fusion to effectively reduce the noise interference in the construction monitoring process and improve the accuracy of the monitoring data. By continuously correcting and optimizing the state estimation value, the system can reflect the state changes in the construction process in real time and accurately, ensuring the high quality and high accuracy of the construction monitoring data.

[0027] S4, construction parameter adaptive adjustment module, uses support vector machine algorithm to analyze and optimize monitoring data set, predict changes in key parameters during construction, and generate construction adjustment instructions; In this implementation, S4 specifically includes: S41, data preprocessing unit, receiving optimized monitoring data set and historical monitoring data collection , to optimize the monitoring data set and historical monitoring data collection Perform standardization, normalize the numerical range of each parameter, and construct a training data set and real-time input data collection ,in, is the corresponding set of known construction parameters and monitoring data, To indicate the The construction parameters of training samples, To indicate the The monitoring data of training samples, represents the number of samples in the training data set; S42, support vector machine training unit, based on the training data set Train the support vector machine model, establish the construction parameter prediction model, and solve the optimal classification hyperplane: ; in, is the Lagrange multiplier, is the actual observed value of the construction parameter, is the Gaussian radial basis kernel function, is the kernel parameter, is the number of training samples; S43, real-time prediction unit, based on the trained support vector machine model, Make predictions and calculate construction parameter prediction values : ; in, is the model bias term, For the current moment Predicted values ​​of construction parameters; S44, adjustment instruction generation unit, based on construction parameter prediction value and optimize monitoring data collection Calculate parameter adjustment , and generate construction adjustment instructions based on the adjustment amount .

[0028] The S44 specifically includes: S441, adjustment amount calculation unit, based on the construction parameter prediction value and optimize monitoring data collection , calculate the construction parameter adjustment : ; in, is the target reference value of the construction parameter, Adjust the weight matrix for the construction parameters, Adjust the weight matrix for monitoring data, It is a collection of historical monitoring data; S442, adjustment strategy optimization unit, calculates the optimal adjustment strategy through multi-objective optimization method , and select the adjustment mode according to the current working conditions, including incremental adjustment mode and global optimization mode; S443, the adjustment instruction generation unit, according to the optimal adjustment strategy And the calculated construction parameter adjustment , generate construction adjustment instructions , the instruction format is as follows: ; in, To adjust the execution time parameters of the instruction.

[0029] This implementation provides an in-depth analysis of construction parameter prediction by combining support vector machine algorithms and optimizing monitoring data sets. This method can not only predict construction parameters based on real-time data, but also make corrections based on historical data to generate accurate construction adjustment instructions. Through real-time monitoring and adaptive adjustment, the system can dynamically optimize construction parameters during the construction process, improve the accuracy and safety of construction, and reduce the risks caused by construction parameter errors.

[0030] S5, construction status warning module, combines big data analysis to perform time series analysis and pattern recognition on the optimized monitoring data set, detects potential construction risks, and triggers construction warning signals when construction risks exceed the limit; In this implementation, S5 specifically includes: S51, time series analysis unit, receiving optimized monitoring data set , based on historical monitoring data and optimized monitoring data collection To carry out time series modeling, the autoregressive integrated moving average model is used to calculate the current moment The monitoring data is used to predict and generate time series forecast values , and output the current time Trend forecast of monitoring data; S52, pattern recognition unit, based on time series prediction value and optimize monitoring data collection , using big data analysis methods to perform pattern recognition on monitoring data, combined with known construction risk pattern libraries, and using decision tree algorithms to classify and pattern match monitoring data, and output construction risk indications : ; in, is the pattern recognition function, For the current moment The construction risk indicator indicates whether there are potential construction risks in the current construction environment; S53, risk threshold judgment unit, setting risk threshold , the construction risk indication output by the pattern recognition unit Make a judgment, if the construction risk indication exceeds the set risk threshold , then the construction warning signal is triggered : ; in, It is a construction warning signal. When it is on, it means that there is a potential risk in the current construction status, and an early warning needs to be triggered and corresponding adjustments need to be made; S54, warning signal output unit, according to the judgment result, sends the construction warning signal The data is output to the intelligent control module to generate early warning notifications and provide real-time feedback to construction personnel.

[0031] This implementation combines big data analysis, time series analysis and pattern recognition technology to conduct in-depth mining of optimized monitoring data sets and effectively detect potential construction risks. By building a time series model of the construction status and identifying abnormal patterns that may occur during the construction process, the system can identify risk points in the construction in real time and issue early warnings, thereby providing timely protection for construction safety.

[0032] S6, intelligent control module, receives construction adjustment instructions and construction warning signals, and dynamically adjusts the working parameters of the construction equipment.

[0033] This embodiment predicts and adjusts construction parameters based on historical monitoring data and real-time optimization monitoring data, and can accurately predict changes in key parameters during the construction process. By calculating the adjustment amount and generating construction adjustment instructions, the present invention can adjust the construction status in real time and improve construction accuracy and efficiency. Example

[0034] In order to verify the feasibility of the present invention, the present invention is applied to a project of a medium-sized construction company B. Company B is carrying out a large-scale bridge construction project, which requires precise construction and monitoring of the continuous beam of the bridge to ensure the safety and efficiency of the construction process. During the implementation of the project, due to the complex construction environment and the involvement of multiple links, the changes in construction data and parameters are difficult to predict, which makes construction adjustment and monitoring more difficult, and even causes construction progress delays and safety risks due to parameter fluctuations.

[0035] In order to improve the accuracy and efficiency of construction, Company B decided to deploy the intelligent construction management system based on adaptive adjustment and construction monitoring of the present invention. The system combines the support vector machine algorithm, the construction parameter prediction model and the dynamic adjustment mechanism, and automatically adjusts the construction strategy and parameters by real-time monitoring of construction parameters and monitoring data to ensure the smooth progress of the construction process.

[0036] The system first monitors the key parameters of the construction process in real time by optimizing the monitoring data set, and uses the SVM algorithm to train the historical construction data to establish a construction parameter prediction model. On this basis, the system predicts the possible change trend of the construction parameters in the future, and automatically generates construction adjustment instructions based on the predicted values. During the implementation process, the system transmits various data of the construction site to the data preprocessing unit through real-time data acquisition equipment, and performs standardization and normalization. Subsequently, the system uses the trained SVM model to predict the real-time data, obtain the predicted values ​​of the construction parameters, and calculate the adjustment amount to generate the construction adjustment instructions.

[0037] During the specific implementation process, the system monitored the changes in construction parameters in real time during the construction process, and obtained the predicted values ​​of some key parameters through the prediction model. During a certain construction process, the system predicted the upcoming instability of the supporting force, and promptly adjusted the operation of the construction equipment through adjustment instructions, thus avoiding construction safety problems caused by changes in supporting force. In addition, during this construction stage, due to the low ambient temperature, the hardening speed of the concrete required during the construction process was slow. By analyzing the construction parameters, the system discovered the impact of temperature on the construction progress during the concrete hardening process, and generated adjustment instructions to accelerate the construction progress.

[0038] With the help of the system, Company B successfully achieved real-time prediction and automatic adjustment of key parameters during the construction process. The system can provide scientific adjustment decisions for the construction process based on the combination of historical data and real-time data, and issue construction adjustment instructions in real time, making the operation on the construction site more accurate, efficient and safe.

[0039] In order to further verify the effectiveness of the system, we collected relevant data before and after the implementation of Company B's construction project. The data is shown in the following table: Table 1 Comparison of construction management data of B company's construction projects ; As can be seen from the table above, before the implementation of the system, the monthly construction progress delay days of Company B was 7 days, and after the system was deployed, the number was significantly reduced to 2 days. In terms of construction safety hazards, the implementation of the system has reduced the safety hazards caused by parameter fluctuations during the construction process by 80%, from 5 times per month to 1 time per month. In addition, the accuracy of construction parameter prediction has increased from 85.2% to 95.7%, indicating that the system is more accurate and reliable in predicting changes in key parameters during the construction process. Through automated construction adjustment command generation and rapid response, the efficiency of the construction site has been greatly improved, and the construction volume completed per unit time has increased from 10 square meters / day to 15 square meters / day.

[0040] In a specific case, during one construction process, the system predicted that the prestress value of the supporting structure was about to exceed the safety threshold, and generated adjustment instructions in time to instruct the equipment to reduce the applied pressure, thus avoiding potential safety accidents. In another construction process, due to climate reasons, the hardening speed of concrete was slow. The system predicted construction delays by analyzing historical data and real-time climate data, adjusted the construction progress in advance, and ensured that the project was completed on time.

[0041] Through the above data and actual case verification, the intelligent construction management system of the present invention not only improves the management efficiency of the construction site, but also significantly improves the safety and quality of construction. The system can accurately predict problems in the construction process by real-time monitoring of changes in construction parameters and combining adaptive adjustment mechanisms, and automatically generate adjustment instructions for correction, which greatly reduces the safety hazards caused by parameter fluctuations during the construction process, optimizes the construction progress, and improves the quality and efficiency of construction.

[0042] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An adjustable continuous beam cantilever construction monitoring system, characterized in that: The system comprises: S1, fiber Bragg grating sensor array, is deployed at key positions of the continuous beam cantilever construction to collect displacement data, stress data and temperature data during the construction process; S2, a data preprocessing module, connected to the fiber grating sensor array, decodes, filters and digitizes the displacement data, stress data and temperature data to generate a set of original monitoring data; S3, data optimization module, performs error correction and optimization on the original monitoring data set based on the Kalman filter algorithm, removes redundant information, and obtains an optimized monitoring data set; S4, construction parameter adaptive adjustment module, uses support vector machine algorithm to analyze and optimize monitoring data set, predict changes in key parameters during construction, and generate construction adjustment instructions; S5, construction status warning module, combines big data analysis to perform time series analysis and pattern recognition on the optimized monitoring data set, detects potential construction risks, and triggers construction warning signals when construction risks exceed the limit; S6, intelligent control module, receives construction adjustment instructions and construction warning signals, and dynamically adjusts the working parameters of the construction equipment.

2. An adjustable continuous beam cantilever construction monitoring system according to claim 1, characterized in that: S3 specifically includes: S31, a data receiving unit connected to the data preprocessing module, receiving the displacement data collected by the fiber grating sensor array , stress data and temperature data The data preprocessing module decodes, filters and digitizes the data to generate the original monitoring data set. , and the original monitoring data set Perform time synchronization correction to keep the data timing of different monitoring points consistent and obtain a timing correction data set ; S32, a noise suppression unit, performs a timing correction on the data set De-noising is performed by using an adaptive signal filtering method combined with the Kalman filtering algorithm to remove environmental noise and random interference to obtain a de-noised data set. ; S33, state estimation unit, for the denoised data set Perform Kalman filter state estimation; S34, data fusion unit, calculates the optimal estimate based on the Kalman gain, fuses the data of multiple monitoring points, corrects the current measurement value based on the prior information, and calculates the optimal state estimate , and output optimized monitoring data set ; S35, anomaly detection unit, optimizes the monitoring data set Perform outlier identification based on optimized monitoring data set Calculate data distribution characteristics and build dynamic thresholds : ； in, For the current moment The mean of the optimized monitoring data set, For the current moment The standard deviation of the optimized monitoring data set, is the threshold adjustment coefficient; Optimizing monitoring data collection Perform point-by-point detection to determine the measured values ​​in the optimized monitoring data set Is it satisfied? , if satisfied, then the measured value Record it as abnormal data and mark the corresponding monitoring point , and use historical monitoring data collection Interpolation correction of abnormal data: ； in, is the modified optimized monitoring data set, is the correction coefficient matrix, It is the data value corresponding to the historical monitoring data. At the same time, it records the temporal and spatial information of the abnormal data and generates an abnormal data log.

3. An adjustable continuous beam cantilever construction monitoring system according to claim 2, characterized in that: S33 specifically includes: S331, state initialization unit, denoising data set Assign initial state and set initial state estimate and the initial error covariance matrix : ； in, is the initial error covariance matrix, is the mathematical expectation operator, It represents the estimated value of the initial state at the initial moment; S332, prediction update unit, predicting the current time based on the state transfer equation State estimation data, calculate the predicted state estimation value And the prediction error covariance matrix : ； ； in, is the forecast error covariance matrix, is the process noise covariance matrix, is the state transfer matrix, for The transposed matrix of is the control input matrix, Adjusting instructions for construction; S333, measurement update unit, based on the current observation value Calculate Kalman gain : ； in, is the measurement noise covariance matrix, is the measurement matrix, To measure the transpose of the matrix, use the Kalman gain Correct the predicted state estimate to obtain the optimal state estimate , and the current moment The optimal state estimate of Store to estimation data set : ； And update the error covariance: ； in, is the identity matrix, is the error covariance matrix.

4. An adjustable continuous beam cantilever construction monitoring system according to claim 3, characterized in that: S34 specifically includes: S341, multi-sensor data synchronization unit, receiving estimated data sets from multiple monitoring points , synchronize the timestamps of different monitoring points and generate a time-synchronized data set ; S342, weighted data fusion unit, based on time synchronization data set , weighted fusion of the state estimation values ​​of each monitoring point is performed using the Kalman gain Compute the weighted best estimate: ； in, is the optimal state estimate after fusion, is the number of monitoring points, For the The estimated value of the state of each monitoring point, is the Kalman gain of the monitoring point; S343, a priori information correction unit, based on historical monitoring data set and statistical characteristics, weighted optimal estimate Perform deviation correction, calculate the corrected state estimate, and convert the corrected state estimate into Store to optimized monitoring data set : ; in, is the correction coefficient matrix, A collection of historical monitoring data.

5. An adjustable continuous beam cantilever construction monitoring system according to claim 2, characterized in that: S4 specifically includes: S41, data preprocessing unit, receiving optimized monitoring data set and historical monitoring data collection , to optimize the monitoring data set and historical monitoring data collection Perform standardization, normalize the numerical range of each parameter, and construct a training data set and real-time input data collection ,in, is the corresponding set of known construction parameters and monitoring data, To indicate the The construction parameters of training samples, To indicate the The monitoring data of training samples, represents the number of samples in the training data set; S42, support vector machine training unit, based on the training data set Train the support vector machine model, establish the construction parameter prediction model, and solve the optimal classification hyperplane: ； in, is the Lagrange multiplier, is the actual observed value of the construction parameter, is the Gaussian radial basis kernel function, is the kernel parameter, is the number of training samples; S43, real-time prediction unit, based on the trained support vector machine model, Make predictions and calculate construction parameter prediction values : ； in, is the model bias term, For the current moment Predicted values ​​of construction parameters; S44, adjustment instruction generation unit, based on construction parameter prediction value and optimize monitoring data collection Calculate parameter adjustment , and generate construction adjustment instructions based on the adjustment amount .

6. An adjustable continuous beam cantilever construction monitoring system according to claim 5, characterized in that: S44 specifically includes: S441, adjustment amount calculation unit, based on the construction parameter prediction value and optimize monitoring data collection , calculate the construction parameter adjustment : ； in, is the target reference value of the construction parameter, Adjust the weight matrix for the construction parameters, Adjust the weight matrix for monitoring data, It is a collection of historical monitoring data; S442, adjustment strategy optimization unit, calculates the optimal adjustment strategy through multi-objective optimization method , and select the adjustment mode according to the current working conditions, including incremental adjustment mode and global optimization mode; S443, the adjustment instruction generation unit, according to the optimal adjustment strategy and the calculated construction parameter adjustment , generate construction adjustment instructions , the instruction format is as follows: ； in, To adjust the execution time parameters of the instruction.

7. An adjustable continuous beam cantilever construction monitoring system according to claim 2, characterized in that: S5 specifically includes: S51, time series analysis unit, receiving optimized monitoring data set , based on historical monitoring data and optimized monitoring data collection To carry out time series modeling, the autoregressive integrated moving average model is used to calculate the current moment The monitoring data is used to predict and generate time series forecast values , and output the current time Trend forecast of monitoring data; S52, pattern recognition unit, based on time series prediction value and optimize monitoring data collection , using big data analysis methods to perform pattern recognition on monitoring data, combined with known construction risk pattern libraries, and using decision tree algorithms to classify and pattern match monitoring data, and output construction risk indications : ; in, is the pattern recognition function, For the current moment The construction risk indicator indicates whether there are potential construction risks in the current construction environment; S53, risk threshold judgment unit, setting risk threshold , the construction risk indication output by the pattern recognition unit Make a judgment, if the construction risk indication exceeds the set risk threshold , then the construction warning signal is triggered : ; in, It is a construction warning signal. When it is on, it means that there is a potential risk in the current construction status, and an early warning needs to be triggered and corresponding adjustments need to be made; S54, warning signal output unit, according to the judgment result, sends the construction warning signal The data is output to the intelligent control module to generate early warning notifications and provide real-time feedback to construction personnel.

Images