A construction site construction monitoring management method and system

Abstract

The application relates to the technical field of construction safety management, and discloses a construction monitoring and management method and system for a building engineering site, which comprises the following steps: acquiring an original data set, performing data preprocessing according to the original data set to obtain a preprocessed feature data set, performing sequential optimization on the preprocessed feature data set to obtain an optimized data uploading sequence, performing time synchronization on the optimized data uploading sequence to obtain a unified time reference data set, performing space calibration on the unified time reference data set to obtain a space-calibrated data set, performing data clustering analysis on the space-calibrated data set to obtain a regional-level data deviation analysis result, performing abnormal region identification according to the regional-level data deviation analysis result to obtain an abnormal region report. The method can realize dynamic identification of abnormal regions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of construction safety management, and particularly relates to a construction site construction monitoring management method and system. BACKGROUND

[0002] Construction monitoring is an important technical means to ensure construction safety and improve engineering quality. With the expansion of modern building scale and the improvement of construction complexity, traditional monitoring methods cannot meet the needs of real-time monitoring and intelligent management. In order to improve the monitoring accuracy and safety of the construction site, the industry gradually introduces advanced means such as Internet of Things, sensing technology, edge computing and intelligent analysis to improve the breadth and depth of data collection. Through multi-sensor fusion technology, core data such as support structure displacement, concrete strength and environmental factors can be monitored in real time, and combined with big data analysis technology, construction safety can be predicted and risk assessed. The development of these technologies greatly improves the intelligent level of construction monitoring, enabling construction management to more efficiently protect safety and warn of risks.

[0003] Current construction monitoring technology mainly relies on fixed sensor networks, which collect key parameters such as support structure displacement, concrete strength, environmental factors (such as temperature and humidity, wind speed) in real time through sensors installed on the construction site (such as displacement sensors, stress sensors, environmental monitoring equipment, etc.). These systems use wireless or wired data transmission to upload monitoring data to a central processing unit for storage and analysis, and determine the safety of the construction area based on a pre-set threshold model. Since these thresholds are based on experience, the system can only trigger an alarm when the collected data exceeds the pre-set range, and cannot adapt to the complex and changing environment of the construction site. For example, the displacement of support structures in some construction areas fluctuates dramatically in a short period of time, and the traditional system cannot respond in time before the threshold is exceeded, resulting in delayed risk identification. In addition, some advanced systems have introduced edge computing and data fusion technology to improve data processing efficiency and reduce data transmission delay, but these systems still rely mainly on static threshold analysis and cannot dynamically adjust to the evolving trends of abnormal areas. Therefore, the existing construction monitoring technology is still essentially a static analysis mode, lacking the ability to adapt to abnormal changes in complex construction environments.

[0004] The existing construction monitoring technology lacks spatio-temporal calibration and intelligent analysis, so it is difficult to accurately identify the dynamic evolution of abnormal areas, which can easily lead to false positives or false negatives, affecting the real-time and effectiveness of construction safety monitoring. SUMMARY

[0005] The present application provides a construction site construction monitoring management method and system to dynamically identify abnormal areas.

[0006] In a first aspect, to solve the above technical problems, the present application provides a construction site construction monitoring management method, comprising:

[0007] Obtaining an original data set;

[0008] According to the original data set, data preprocessing is performed to obtain a preprocessed feature data set;

[0009] The preprocessed feature data set is sequentially optimized to obtain an optimized data upload sequence;

[0010] The optimized data upload sequence is time-synchronized to obtain a unified time reference data set;

[0011] The unified time reference data set is spatially calibrated to obtain a spatially calibrated data set;

[0012] The spatially calibrated data set is subjected to data clustering analysis to obtain a regional level data deviation analysis result;

[0013] According to the regional level data deviation analysis result, an abnormal area is identified to obtain an abnormal area report.

[0014] Preferably, the original data set includes horizontal displacement, vertical settlement, inclination angle, compressive strength, splitting tensile strength, concrete density, temperature, humidity and wind speed.

[0015] Preferably, according to the original data set, data preprocessing is performed to obtain a preprocessed feature data set, comprising:

[0016] Based on the filtering algorithm, the original data set is subjected to data denoising to obtain a denoising data set;

[0017] According to the denoising data set, feature extraction is performed to obtain a feature data set;

[0018] Based on data difference coding, the feature data set is subjected to data compression to obtain a preprocessed feature data set.

[0019] Preferably, the preprocessed feature data set is sequentially optimized to obtain an optimized upload batch set, comprising:

[0020] The preprocessed feature data set is subjected to data priority sorting to obtain a priority sorting list;

[0021] The priority sorting list is subjected to dimension reduction to obtain a reduced feature data set;

[0022] Based on a dynamic scheduling strategy, the reduced feature data set is subjected to transmission sequence optimization to obtain an optimized upload batch set.

[0023] Preferably, the optimized data upload sequence is time-synchronized to obtain a unified time reference dataset, including:

[0024] The optimized data upload sequence is corrected for clock bias based on a distributed clock synchronization algorithm to obtain a clock-corrected dataset;

[0025] The clock-corrected dataset is time-stamped aligned based on a time sequence reconstruction algorithm to obtain a time-aligned dataset;

[0026] The time-aligned dataset is verified for time consistency to obtain a unified time reference dataset.

[0027] Preferably, the unified time reference dataset is spatially calibrated to obtain a spatially calibrated dataset, including:

[0028] The unified time reference dataset is compensated for device positioning errors to obtain a compensated positioning dataset;

[0029] The compensated positioning dataset is spatially coordinated to obtain an aligned dataset;

[0030] The aligned dataset is authenticated for data consistency to obtain a spatially calibrated dataset.

[0031] Preferably, the spatially calibrated dataset is analyzed and calculated to obtain regional-level data analysis results, including:

[0032] The regional support structure displacement value is calculated by the following formula:

[0033]

[0034] wherein, is the support structure displacement value of the i-th region, is the horizontal displacement of the i-th region, is the vertical settlement of the i-th region, is the inclination angle of the i-th region; The regional concrete strength value is calculated by the following formula:

[0035]

[0036]

[0037] wherein, is the concrete strength value of the i-th region, ​​​​​For the first The compressive strength of each region For the first Splitting tensile strength of each region For the first Concrete density in each area;

[0038] The regional environmental monitoring values ​​are calculated using the following formula:

[0039]

[0040] in, For the first Environmental monitoring values ​​for each area For the first The ambient temperature of each region No. Humidity of each area For the first Wind speed in each area;

[0041] The regional data deviation analysis results include: support structure displacement values, concrete strength values, and environmental monitoring values.

[0042] Preferably, based on the regional-level data deviation analysis results, anomaly region identification is performed to obtain an anomaly region report, including:

[0043] If the displacement value of the regional support structure is greater than the preset support structure displacement threshold, it is determined that the support structure displacement index is abnormal.

[0044] If the concrete strength value in a region is less than the preset concrete strength threshold, it is determined that the concrete strength index is abnormal.

[0045] If the regional environmental monitoring value is greater than the preset environmental impact threshold, it is determined that the environmental monitoring index is abnormal.

[0046] If a region has three abnormal indicators, it is identified as a high-risk region; if two indicators are abnormal, it is identified as a medium-risk region; if one indicator is abnormal, it is identified as a low-risk region; and if no indicators are abnormal, it is identified as a risk-free region.

[0047] The indicators include: support structure displacement indicators, concrete strength indicators, and environmental monitoring indicators;

[0048] The abnormal area report includes: risk-free areas, low-risk areas, medium-risk areas, and high-risk areas.

[0049] Secondly, the present invention provides a construction site monitoring and management system for building projects, comprising:

[0050] The data acquisition module is used to acquire the raw dataset;

[0051] a preprocessing module, configured to perform data preprocessing according to the original data set to obtain a preprocessed feature data set;

[0052] a sequential optimization module, configured to perform sequential optimization on the preprocessed feature data set to obtain an optimized data uploading sequence;

[0053] a time synchronization module, configured to perform time synchronization on the optimized data uploading sequence to obtain a unified time reference data set;

[0054] a spatial calibration module, configured to perform spatial calibration on the unified time reference data set to obtain a spatially calibrated data set;

[0055] a cluster analysis module, configured to perform data cluster analysis on the spatially calibrated data set to obtain a regional level data deviation analysis result;

[0056] an abnormal region identification module, configured to perform abnormal region identification according to the regional level data deviation analysis result to obtain an abnormal region report.

[0057] In a third aspect, the present application also provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the construction site construction monitoring management method according to any one of the above.

[0058] In a fourth aspect, the present application also provides a computer readable storage medium, comprising a stored computer program, wherein the computer program controls a device where the computer readable storage medium is located to execute the construction site construction monitoring management method according to any one of the above when the computer program runs.

[0059] Compared with the prior art, the present application has the following beneficial effects:

[0060] (1) The present application improves the data transmission efficiency and real-time performance through data preprocessing and optimized uploading strategy.

[0061] The existing construction monitoring system has problems of high transmission redundancy, large bandwidth occupation and long uploading delay due to a large amount of data, which affects the real-time performance and analysis efficiency of the monitoring data. The present application adopts filtering denoising, feature extraction and data compression technology to preprocess the original monitoring data, reduce redundant data and improve data quality. At the same time, based on data priority sorting, dimensionality reduction optimization and dynamic scheduling strategy, the data uploading sequence is optimized, so that high-priority data can be transmitted in time, and low-value data can be avoided to occupy transmission bandwidth, thereby improving the efficiency of data uploading, ensuring the low delay and high response of the construction monitoring system, and meeting the real-time monitoring needs of the construction site.

[0062] (2) The present application improves data consistency and reliability based on time synchronization and space calibration.

[0063] Due to the wide distribution of construction site monitoring equipment, there are time deviations and spatial errors in the data of different equipment, which leads to inaccurate data analysis. The present application adopts a distributed clock synchronization algorithm to synchronize the data of each monitoring node in time, corrects the system clock deviation, and aligns the data timestamp based on a time sequence reconstruction algorithm, thereby obtaining a unified time reference data set, ensuring that all monitoring data is analyzed under the same time reference. In addition, the present application compensates for the positioning error of the equipment, aligns the spatial coordinates and authenticates the data consistency, so that the data can be processed under a unified coordinate reference, improving the spatial accuracy of the monitoring data and enhancing the reliability of the data analysis.

[0064] (3) The present application adopts intelligent data clustering analysis to improve the recognition ability of abnormal areas.

[0065] The present application proposes a data clustering analysis method to analyze multi-dimensional data such as support structure displacement, concrete strength and environmental factors, calculate the data deviation degree of each area, and based on dynamically adjusted abnormal judgment standards, accurately identify the abnormal conditions of the construction area. At the same time, the present application adopts a four-level risk grading mechanism of no risk, low risk, medium risk and high risk, so that the abnormal area identification is more refined and accurate, improves the intelligent level of construction monitoring, and enhances the construction safety warning ability.

[0066] In summary, the present application improves the data accuracy, spatio-temporal consistency and risk recognition ability of construction monitoring through data preprocessing, time synchronization, space calibration, intelligent clustering analysis and dynamic abnormality identification, solves the problems of low data transmission efficiency, large time and space errors and insufficient abnormality recognition ability in the prior art, and makes the construction safety management more intelligent, real-time and efficient. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 is a schematic diagram of the building engineering site construction monitoring management method provided by the first embodiment of the present application;

[0068] Figure 2 FIG. 1 is a schematic diagram of a construction site construction monitoring management system according to a second embodiment of the present application. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0070] With reference to Figure 1 The first embodiment of the present application provides a construction site construction monitoring management method, comprising the following steps:

[0071] S11, obtaining an original data set;

[0072] S12, performing data preprocessing according to the original data set to obtain a preprocessed feature data set;

[0073] S13, performing sequential optimization on the preprocessed feature data set to obtain an optimized data uploading sequence;

[0074] S14, performing time synchronization on the optimized data uploading sequence to obtain a unified time reference data set;

[0075] S15, performing spatial calibration on the unified time reference data set to obtain a spatially calibrated data set;

[0076] S16, performing data clustering analysis on the spatially calibrated data set to obtain a regional level data deviation analysis result;

[0077] S17, performing abnormal region identification according to the regional level data deviation analysis result to obtain an abnormal region report.

[0078] In step S11, an original data set is obtained.

[0079] It should be noted that the original data set includes horizontal displacement, vertical settlement, inclination angle, compressive strength, splitting tensile strength, concrete density, temperature, humidity, and wind speed.

[0080] It is worth mentioning that in the construction site construction monitoring management method of the present application, the acquisition of the original data set is the basis of the entire monitoring system, ensuring the accuracy of subsequent data analysis, anomaly identification and construction safety warning. The present application adopts a dynamic real-time data acquisition strategy, combining fixed monitoring equipment and mobile monitoring nodes to achieve high-precision, multi-dimensional acquisition of key parameters in the construction site. The key parameters of data acquisition include horizontal displacement, vertical settlement, inclination angle, compressive strength, splitting tensile strength, concrete density, temperature, humidity and wind speed, each of which is measured based on a sensor and combined with a mechanism for dynamically adjusting the acquisition frequency to adapt to real-time changes in the construction environment, improving the accuracy and reliability of data acquisition.

[0081] The acquisition of horizontal displacement uses high-precision displacement sensors installed at key support structures, reinforced concrete frames, formwork systems and infrastructure in the construction site. The system measures the horizontal displacement of the support structure based on photoelectric encoding, laser ranging and GPS technology. When material deformation, uneven settlement of the foundation or changes in structural stress occur during construction, the sensor will record the data in real time and upload it to the monitoring system. In addition, to improve data accuracy, the system dynamically adjusts the acquisition frequency, and when the support structure is in a high-risk area or experiences significant displacement changes, the data acquisition frequency is automatically increased to more closely monitor the displacement trend.

[0082] The measurement of vertical settlement relies on settlement monitors and high-precision electronic levels, which are deployed at the foundation of the building, load-bearing walls and key structural locations. Electronic level measurement technology and millimeter-level laser range finders are used to ensure high accuracy of the data. During construction, compression of the foundation soil layer, settlement of backfill soil and long-term load action can cause vertical settlement. The system of the present application fuses data from multiple measurement points through intelligent acquisition nodes and analyzes the settlement rate and abnormal conditions through time series analysis. In the early stages of construction, the vertical settlement changes rapidly, so the system sets a higher acquisition frequency, and when the settlement stabilizes, the acquisition frequency is reduced, thereby improving the resource utilization of the system.

[0083] The acquisition of the inclination angle relies on inclination sensors installed at high-rise buildings, support structures and scaffolding to monitor the inclination of the structure. Inclination sensors based on MEMS accelerometers and gyroscopes can detect subtle changes in angle to ensure safety during construction. When the inclination angle changes exceed the warning threshold, the system triggers a high-frequency acquisition mode to improve the time resolution of data acquisition to analyze the inclination trend.

[0084] The compressive strength is an important indicator of the safety of concrete structures, measured by embedded stress sensors and non-destructive testing techniques. During the construction process, stress sensors are placed at different locations to monitor the internal pressure of the concrete in real time. In addition, the system also supports ultrasonic rebound testing, which measures the surface hardness and internal density of the concrete through ultrasonic probes to estimate the compressive strength. Since the strength of the concrete gradually increases over time, the system dynamically adjusts the sampling frequency based on the age curve, increasing the sampling rate during the initial setting stage and reducing it when the strength tends to be stable, to improve data collection efficiency.

[0085] The measurement of splitting tensile strength uses wireless strain sensors and acoustic emission monitoring technology, which are installed on concrete test blocks or bearing structures to monitor the internal tensile stress distribution of the concrete. Due to the influence of vibration, load changes and environmental temperature and humidity during construction, the splitting tensile strength will fluctuate, so the system will adaptively adjust the data collection frequency based on load changes to ensure high-frequency sampling during key stages such as concrete stress testing or critical construction stages, to accurately judge the mechanical properties of the material.

[0086] The density of concrete directly affects the durability and impermeability of the structure, and is detected by X-ray scanning, ultrasonic transmission and resistivity testing. The system uses embedded detection probes to measure the internal density of the concrete during construction, while combining ultrasonic technology to analyze internal defects. Since the change of concrete density is closely related to the pouring process and environmental conditions, the system will perform high-frequency measurements during the initial construction and curing period, and reduce the data collection frequency after stabilization to ensure the continuity and scientific nature of the monitoring.

[0087] Temperature and humidity measurements rely on digital temperature and humidity sensors installed at different locations on the construction site, including concrete pouring points, internal reinforcement, support structures, and environmental control areas. Changes in temperature and humidity have a significant impact on the development of concrete strength, material expansion and contraction, and construction progress. The system will combine weather data to dynamically adjust the sampling interval of the monitoring points, increasing the sampling frequency during weather conditions with large temperature and humidity fluctuations to obtain more accurate environmental data.

[0088] Wind speed measurement relies on ultrasonic wind speed sensors and mechanical anemometers installed in high-altitude work areas, tower cranes, scaffolding and other locations on the construction site to monitor wind speed changes in real time. Changes in wind speed on the construction site directly affect the safety of high-altitude work, so the system will increase the data collection frequency when the wind speed is high based on the wind speed trend, to provide timely warnings to construction management personnel and reduce safety hazards.

[0089] During the entire data acquisition process, the system of the application adopts an intelligent node dynamic adjustment of acquisition frequency strategy, automatically adjusts the acquisition frequency of different sensors according to the construction progress, environmental changes and risk levels. When the system detects that an abnormal trend occurs in a certain area (such as sudden increase of displacement, sudden change of temperature and humidity, and sudden increase of wind speed), a high-frequency sampling mode is triggered to improve the temporal and spatial resolution of data acquisition, so as to ensure the accuracy of construction monitoring. At the same time, in the case of stable environment and slow structural change, the system will reduce the sampling frequency to reduce data redundancy, improve transmission efficiency and ensure the efficient operation of the data acquisition system.

[0090] In summary, the original data set acquisition method of the application is based on multi-sensor fusion technology, combined with a dynamic adjustment of sampling frequency strategy, to ensure that the core monitoring data of the construction site can be accurately obtained in different construction stages and different risk areas, and to provide solid data support for subsequent data analysis, abnormal area identification and construction safety warning.

[0091] In step S12, according to the original data set, data preprocessing is performed to obtain a preprocessed feature data set, including:

[0092] Based on the filtering algorithm, the original data set is subjected to data denoising to obtain a denoised data set;

[0093] According to the denoised data set, feature extraction is performed to obtain a feature data set;

[0094] Based on data difference encoding, the feature data set is subjected to data compression to obtain a preprocessed feature data set.

[0095] It is worth noting that in the data denoising link, first, the original data collected by various sensors on the construction site is obtained, including support structure displacement, concrete strength, environmental temperature and humidity, etc. Due to the existence of a large amount of environmental noise in the construction site, such as equipment vibration, wind interference, temperature fluctuation, etc., the data collected by the sensor often has random error or systematic error. In order to improve the accuracy of the data, this step uses filtering algorithm to denoise the original data. Specifically, for displacement data, since its trend is relatively flat, sliding average filtering method can be used to smooth the data and reduce the influence of short-term fluctuations. For example, if a displacement sensor of a support structure collects data every minute, an individual data point is abnormal due to equipment jitter, and the average value of the data in the last 5 minutes is calculated through sliding window, which can effectively reduce the influence of sudden noise. For environmental temperature and humidity data, due to the influence of instantaneous airflow or local temperature change, this step uses Kalman filtering method to predict the current value according to the historical data and dynamically adjusts the filtering weight to improve the data stability. In addition, for high-frequency vibration signals (such as wind speed data), this step uses wavelet transform denoising method to decompose the signal into multiple frequency components and remove high-frequency noise to ensure the authenticity and usability of the data. After denoising, the system obtains the denoised data set, which provides more stable data input for subsequent analysis.

[0096] In the feature extraction link, based on the denoised data set, the feature parameters which have key influence on construction safety are extracted. The types of monitoring data on the construction site are various, and directly using the original data for analysis leads to data redundancy and increased computational complexity, so it is necessary to extract key features to improve the representativeness and computational efficiency of the data. For example, in support structure monitoring, in addition to directly recording the horizontal displacement and vertical settlement values, this step further calculates the displacement rate to identify whether there is an abnormal growth trend of displacement. Specifically, if the displacement of a certain area increases from 2 millimeters to 6 millimeters in 10 minutes, while the growth amplitude in the past 1 hour is only 1 millimeter, the system can identify that there is a structural instability risk in that area. In concrete strength monitoring, this step not only extracts the compressive strength value, but also calculates the comprehensive strength feature by combining the splitting tensile strength and density data to judge whether the overall performance of the concrete meets the design requirements. In addition, in environmental monitoring, temperature and humidity data cannot directly reflect the influence on construction quality, so the system calculates the temperature and humidity change gradient to identify the mutation that affects concrete curing. For example, if the temperature drops from 25 degrees Celsius to 10 degrees Celsius in 30 minutes, it will affect the concrete curing process. Through feature extraction, the system can remove redundant information and only retain the key feature data set which is most representative for construction safety analysis.

[0097] In the data compression link, in order to reduce the overhead of data storage and transmission, this step performs data compression on the feature data set based on data differential encoding. The monitoring data of the construction site has strong time continuity, and the data changes between adjacent time points are small, so the differential encoding technology can be used to record only the data change amount, rather than store the complete numerical value. For example, in the displacement monitoring of the supporting structure, if the displacement data of a support point is 2.1 mm, 2.2 mm, 2.3 mm in turn, the system can only store the increment (+0.1 mm), thereby reducing the data storage space. In addition, for environmental data such as temperature and humidity, since the change is relatively smooth, a time window sliding storage strategy can be adopted to replace the average value within a certain time range with a single data point, further compressing the data amount. For example, if the temperature of a certain area changes by no more than 1 degree Celsius within 1 hour, only the average temperature of this time period can be stored, and all data points do not need to be stored one by one. After data compression processing, the system obtains the preprocessed feature data set, which reduces the redundancy of data storage and transmission under the premise of ensuring the integrity of key information, and improves the efficiency and response speed of subsequent data analysis.

[0098] In summary, through the three key links of data denoising, feature extraction and data compression, this step ensures the accuracy, representativeness and efficiency of the monitoring data of the construction site. Denoising reduces the influence of environmental interference on the data and improves the data quality; feature extraction selects the information most valuable to construction safety analysis, reducing the computational complexity; data compression reduces the storage and transmission burden, improving the real-time performance of data processing. This data preprocessing process lays a solid data foundation for subsequent dynamic abnormal area identification.

[0099] In step S13, the preprocessed feature data set is sequentially optimized to obtain an optimized upload batch set, including:

[0100] The preprocessed feature data set is prioritized to obtain a priority sorting list;

[0101] The priority sorting list is dimensionally reduced to obtain a dimensionally reduced feature data set;

[0102] The dimensionally reduced feature data set is optimized in transmission sequence based on a dynamic scheduling strategy to obtain an optimized upload batch set.

[0103] It is worth mentioning that in the data priority ranking link, the pre-processed feature data set is first classified, and the priority is ranked according to the importance, real-time and construction risk level of the data. The data types on the construction site are various, including support structure displacement, concrete strength, environmental temperature and humidity, etc. Among them, different data have different influences on construction safety, and the priority of data also has significant differences. Therefore, before uploading the data, it is necessary to determine which data should be transmitted first to ensure the real-time and accuracy of the monitoring system. For example, the horizontal displacement and vertical settlement of the support structure are key monitoring indicators. If the data is abnormal, it will cause structural instability and affect construction safety, so the priority is the highest and should be uploaded first. Concrete compressive strength and splitting tensile strength are also core parameters for structural safety, and the second priority is transmitted. Compared with the environmental parameters such as temperature, humidity and wind speed, the changes of which have a relatively slow influence on construction quality, the priority is relatively low and can be uploaded later. In addition, the system also considers the data change rate to adjust the priority ranking. For example, if the displacement of the support structure in a certain construction area changes dramatically in a short time, the system will automatically increase the priority of the monitoring data in this area to ensure that the relevant data can be uploaded in time. After priority ranking, the system generates a priority ranking list to ensure that key data can enter the upload queue first so that construction management personnel can grasp important safety information in the first time.

[0104] In the data dimension reduction link, in order to improve the data processing efficiency and reduce the storage and transmission resources occupied by invalid data, the system performs dimension reduction processing on the priority ranking list. Construction monitoring data often contains a large amount of redundant information, such as some environmental parameters (such as temperature and humidity) that change little in a long time. Directly uploading all data will cause waste of storage and transmission resources. In order to solve this problem, the system uses principal component analysis method to select the most representative data features and remove data with high correlation or redundant information. For example, in concrete strength monitoring, there is a strong correlation among compressive strength, splitting tensile strength and concrete density, so feature extraction can be used to upload only the parameter that best represents the overall quality of the concrete, while reducing the transmission of other data. In addition, for monitoring data with time sequence characteristics, the system uses time window moving average method to calculate the mean value of key data in a period of time, thereby reducing the data redundancy caused by short-term fluctuations. For example, in a certain construction area, if the environmental temperature fluctuates within 0.5 degrees Celsius in the past hour, the system can only upload the average temperature of this period, without uploading the data every minute, thereby greatly reducing the data storage amount. After dimension reduction processing, the system obtains the dimension-reduced feature data set, which not only retains the key information but also reduces the occupation of invalid data, improving the data transmission efficiency.

[0105] In the data transmission sequence optimization link, the system optimizes the transmission sequence of the reduced feature data set based on a dynamic scheduling strategy, ensuring that high-priority data can be quickly uploaded and low-priority data can be delayed for uploading when network conditions permit. The network environment of the construction monitoring system is complex, and network bandwidth is limited or data transmission is delayed in some construction areas, so it is necessary to reasonably arrange the data transmission sequence to ensure the real-time performance of important data. For example, during peak construction periods, the system will prioritize uploading key safety data such as support structure displacement and concrete strength, while delaying the transmission of environmental data such as temperature and humidity to ensure the rational allocation of bandwidth resources. In addition, the system will dynamically adjust according to the risk level of the monitoring area. If an anomaly occurs in a certain area, the system will immediately increase the data transmission priority of that area to ensure that the monitoring data of that area is uploaded to the central server first. For example, in a deep foundation pit construction site, the system detected that the horizontal displacement of the support structure at a certain monitoring point increased by 3 mm within 10 minutes, exceeding the safety threshold. The system immediately adjusts the transmission sequence to prioritize the data from this monitoring point while delaying the data from other low-risk areas. After dynamic scheduling, the system obtains an optimized upload batch set that ensures the real-time transmission of critical data while optimizing the use of bandwidth resources and improving the overall efficiency of the construction monitoring system.

[0106] In summary, this step achieves efficient management of monitoring data through three key links: data priority sorting, data dimensionality reduction, and transmission sequence optimization. Data priority sorting ensures that the most critical construction safety data is uploaded first, improving system response speed; data dimensionality reduction reduces data redundancy and reduces storage and transmission resource consumption; transmission sequence optimization combines construction risk levels and network bandwidth conditions to achieve dynamic adjustment of data upload, improving data transmission stability and reliability. This optimization process ensures that the construction monitoring system can achieve precise monitoring of the construction site under limited network and computing resources, providing reliable data support for construction safety management.

[0107] In step S14, the optimized data upload sequence is time-synchronized to obtain a unified time reference data set, including:

[0108] Based on the distributed clock synchronization algorithm, the optimized data upload sequence is corrected for clock bias to obtain a clock-corrected data set.

[0109] Based on the time series reconstruction algorithm, the clock-corrected data set is time-stamped to obtain a time-aligned data set.

[0110] The time-aligned data set is verified for time consistency to obtain a unified time reference data set.

[0111] It is worth mentioning that in the clock bias correction link, in order to ensure that the data of multiple sensors on the construction site can be analyzed under the same time reference, the system uses a distributed clock synchronization algorithm to correct the clock bias of the optimized data upload sequence. The monitoring system on the construction site is composed of multiple distributed sensor nodes, and there is a slight deviation in the internal clock of each node, which leads to inconsistent data timestamps, affecting data comparison and anomaly analysis. Therefore, the system first obtains the standard time from the central server and broadcasts the standard time signal to each monitoring node using a time synchronization protocol (such as the Network Time Protocol or the Distributed Clock Synchronization Algorithm). After receiving the time signal, each sensor node compares it with its local clock, calculates the clock drift, and automatically corrects it. For example, in the monitoring of foundation pit support structures, the clock of a displacement sensor is 1.2 seconds faster than the central server, and the clock of another temperature and humidity sensor is 0.8 seconds slower than the central server. In order to ensure data consistency, the system will automatically adjust the time of each sensor to align with the standard time of the central server. After clock bias correction, the system obtains the clock-corrected data set, which ensures that data from different monitoring devices can be analyzed within the same time reference framework.

[0112] In the data timestamp alignment link, due to network delays, signal transmission speeds, and other reasons, the timestamps of sensor data on the construction site do not match. The system uses a time series reconstruction algorithm to align the timestamps of the clock-corrected data set. Data from different sensors is uploaded at different time points, such as every 5 seconds for one sensor and every 10 seconds for another sensor, making it impossible to directly compare the data in the time dimension. To address this issue, the system uses interpolation calculation methods to remap data with different timestamps to a standard time axis. For example, in the monitoring of deep foundation pit support structures, the data obtained from different sensors includes displacement data of the support structure at 12:00:05, temperature data at 12:00:07, and humidity data at 12:00:10. Direct analysis would result in time misalignment. The system will complete the time axis and interpolate the data at 12:00:07 and 12:00:10 according to adjacent time points, so that all data can be calculated under the same time reference framework, ultimately obtaining a time-aligned data set.

[0113] In the time consistency verification link, in order to ensure that all aligned data can maintain time consistency, the system will detect the time consistency of the time-aligned data set to find time anomalies. For example, due to signal interference or data loss, some sensors have abnormal time stamps, and the time stamps of other sensors have large deviations. The system will detect these abnormal points and determine whether they need to be resynchronized. For example, in high-rise building construction monitoring, the upload data timestamp of the wind speed sensor suddenly changes at a certain time, with a deviation of 2 seconds, while the time error of other sensors is less than 0.1 second. This is caused by sensor failure or data transmission delay. The system will compare these data and use a time backtracking mechanism to reacquire the data at that time point or use historical data to correct the data at that time point. Finally, the time stamps of all data are consistent, and a unified time reference data set is obtained.

[0114] In summary, this step ensures the time synchronization of construction monitoring data through three key links: clock deviation correction, data timestamp alignment, and time consistency verification. Clock deviation correction eliminates the influence of different sensor clock drift on data timestamps, improving data consistency. Data timestamp alignment uses interpolation calculation and time axis mapping to enable data with different sampling frequencies to be analyzed at the same time point, avoiding time misalignment. Time consistency verification detects timestamp anomalies to ensure that all data maintain high consistency in the time dimension, improving the reliability of the monitoring system. The final unified time reference data set enables monitoring data on the construction site to be compared and calculated under the same time framework, providing a solid time basis for subsequent data analysis and anomaly identification.

[0115] In step S15, the unified time reference data set is subjected to spatial calibration to obtain a spatially calibrated data set, including:

[0116] The unified time reference data set is subjected to device positioning error compensation to obtain a compensated positioning data set.

[0117] The compensated positioning data set is subjected to data space coordinate alignment to obtain an aligned data set.

[0118] The aligned data set is subjected to data consistency authentication to obtain a spatially calibrated data set.

[0119] It is worth mentioning that in the device positioning error compensation link, due to the wide distribution of monitoring devices on the construction site, there is a deviation between the actual installation position of each sensor and the system preset coordinates. These deviations are caused by device installation errors, environmental interference or satellite signal errors. In order to ensure the spatial accuracy of the monitoring data, the system first compensates for the positioning errors of all sensors. The compensation method includes static calibration and dynamic adjustment. In the static calibration stage, the system uses high-precision total station, laser range finder or high-precision GPS equipment to obtain the actual installation position of each sensor when the device is installed, and compares it with the preset coordinates. For example, in tunnel construction monitoring, the preset coordinates of a support structure displacement sensor are X=100.5m, Y=200.8m, and the actual installation position measured by the total station is X=100.2m, Y=200.6m. The system will automatically calculate the deviation and compensate it. In the dynamic adjustment stage, the system combines historical data to analyze the stability of the sensor data. If the coordinate data of a sensor abnormally drifts over time, for example, the position of a GPS device suddenly changes by 2 meters on a certain day, and there is no large-scale displacement in the construction site, the system will identify the abnormal data and automatically correct it through data filtering algorithm, and finally obtain the compensated positioning data set.

[0120] In the data space coordinate alignment link, in order to ensure that all monitoring data can be analyzed in the same spatial reference system, the system aligns the coordinates of the compensated positioning data set. The construction monitoring system has diverse data sources, and different devices use different coordinate systems, such as some sensors use geographic coordinates (latitude and longitude), while other devices use relative coordinates (local coordinates of the construction site). If the coordinates are not aligned, the data of different devices cannot be directly calculated in space. For example, in deep foundation pit construction monitoring, the ground settlement monitor uses UTM coordinates, while the stress sensor inside the foundation pit uses a local construction coordinate system. If the data is directly fused, it will cause calculation errors. Therefore, the system converts all data to the same coordinate system through coordinate conversion algorithm. For example, for the data of GPS devices, the system uses the ellipsoid model to convert it to the relative coordinates of the construction site, and for the construction surveying data, the system maps it to the geographic coordinate system through the control points measured on site, ensuring that the spatial coordinates of all monitoring data can be matched, and finally obtaining the aligned data set.

[0121] In the data consistency verification stage, the system performs a consistency check on the aligned dataset to ensure spatial consistency of data from all sensors. Due to the complex construction environment, some sensors are subject to external interference, leading to data anomalies. For example, some displacement sensors installed on tunnel support structures may experience slight deformation of their supports due to temperature changes, affecting the spatial accuracy of the data. To address this issue, the system employs a spatial consistency verification algorithm to analyze whether the data from adjacent sensors have a reasonable spatial relationship. For instance, in subway construction monitoring, assuming the settlement values ​​of three adjacent settlement monitoring points in a certain area are 2.1mm, 2.3mm, and 10mm, the system will identify the data anomaly at the third monitoring point and further analyze the source of error, including equipment failure, data acquisition errors, or construction disturbances. If the data is confirmed as an error point, the system will automatically remove it or correct it using an interpolation algorithm, ultimately ensuring spatial consistency and obtaining a spatially calibrated dataset.

[0122] In summary, this step ensures the spatial accuracy of construction monitoring data through three stages: equipment positioning error compensation, data spatial coordinate alignment, and data consistency verification. Equipment positioning error compensation eliminates the impact of sensor installation errors on data location, improving positioning accuracy. Data spatial coordinate alignment transforms data from different devices to a unified coordinate system, ensuring data comparability. Data consistency verification detects and corrects outliers in the spatial data, improving data reliability. The final spatially calibrated dataset ensures precise spatial matching of construction site monitoring data, providing an accurate spatial basis for subsequent anomaly area identification and risk assessment.

[0123] In step S16, data analysis and calculation are performed on the spatially calibrated dataset to obtain regional-level data analysis results, including:

[0124] The displacement value of the regional support structure is calculated using the following formula:

[0125]

[0126] in, For the first Displacement values ​​of the support structure in each region For the first Horizontal displacement of each region For the first Vertical settlement in each area For the first The tilt angle of each region;

[0127] The regional concrete strength value is calculated using the following formula:

[0128]

[0129] in, For the first Concrete strength values ​​for each region For the first The compressive strength of each region For the first Splitting tensile strength of each region For the first Concrete density in each area;

[0130] The regional environmental monitoring values ​​are calculated using the following formula:

[0131]

[0132] in, For the first Environmental monitoring values ​​for each area For the first The ambient temperature of each region No. Humidity of each area For the first Wind speed in each area;

[0133] The regional data deviation analysis results include: support structure displacement values, concrete strength values, and environmental monitoring values.

[0134] It is worth noting that in the construction site monitoring and management method of this invention, the purpose of regional data analysis is to quantify the safety status of the construction area. Through mathematical calculations, the displacement values ​​of the support structure, concrete strength values, and environmental monitoring values ​​are obtained, providing a reliable analytical basis for subsequent identification of abnormal areas. The physical environment of the construction site is complex, and various monitoring indicators influence each other. Therefore, it is necessary to integrate and calculate data from different dimensions using mathematical models to extract representative key indicators. This invention employs multi-parameter fusion calculation, combining core monitoring data from each area to form accurate regional data deviation analysis results, ensuring the monitoring system's accurate assessment of construction risks.

[0135] The purpose of calculating the displacement value of the supporting structure is to evaluate the stability of the structure, and by integrating the displacement information in different directions, the overall deformation trend of the supporting structure is judged. The present application adopts three parameters of horizontal displacement, vertical settlement and inclination angle for calculation, wherein the horizontal displacement reflects the displacement amplitude of the structure in the horizontal direction, the vertical settlement indicates the subsidence degree of the foundation, and the inclination angle is used to measure the inclination degree of the structure. In the formula, the horizontal displacement and vertical settlement data are calculated by using the mean square average to ensure the representativeness of the overall displacement, and the influence of the inclination angle is calculated by using the exponential promotion, so that when the structure inclination exceeds a certain range, its influence presents nonlinear growth in the calculation. This calculation method can more accurately reflect the stability of the supporting structure, avoid the error caused by single parameter judgment, and thus improve the reliability of construction monitoring.

[0136] The calculation of concrete strength value aims to comprehensively evaluate the bearing capacity of concrete and ensure that the quality of construction materials meets the safety standards. The present application is based on three core indicators of compressive strength, splitting tensile strength and concrete density for calculation, wherein the compressive strength reflects the bearing capacity of concrete under stress state, the splitting tensile strength is used to measure the failure trend of concrete under tensile stress, and the concrete density is an important factor affecting the overall performance of concrete. In the calculation formula, the ratio of compressive strength to splitting tensile strength is used to measure the structural integrity of concrete, and the density is used as an exponential term to participate in the calculation to adjust the calculation result of concrete strength, so that it can better adapt to different construction conditions. Through this calculation method, the system can more accurately evaluate the durability and bearing capacity of concrete, and improve the accuracy of construction quality monitoring.

[0137] The calculation of environmental detection value is used to evaluate the environmental influence factors of construction area, to ensure that the external conditions in the construction process will not adversely affect the safety of the structure. The present application comprehensively considers three key parameters of environmental temperature, humidity and wind speed, wherein the temperature has important influence on the expansion and contraction characteristics of materials, the humidity affects the curing quality and structural durability of concrete, and the wind speed affects the construction stability of high-rise buildings. The product relationship of temperature and humidity is used in the calculation formula to measure the comprehensive influence of hot and humid environment on the construction area, and the square term of wind speed is combined to emphasize the nonlinear influence of strong wind on construction safety. In addition, the exponential decay term is used to describe the dynamic change of humidity on environmental influence, so that the contribution of humidity to environmental detection value gradually decreases in high humidity environment, thereby improving the rationality of environmental influence evaluation. This calculation method ensures that the construction monitoring system can dynamically adapt to different climate conditions, and improves the scientificity and applicability of environmental monitoring.

[0138] To sum up, the application accurately evaluates the structural stability, material performance and environmental impact of the construction area through three calculation models of support structure displacement value, concrete strength value and environmental detection value. The calculation method of support structure displacement value comprehensively considers displacement information in different directions, making the structural stability analysis more comprehensive. The calculation method of concrete strength value integrates multiple strength indicators to ensure the accuracy of construction quality evaluation. The calculation method of environmental detection value uses dynamic weight adjustment to adapt to changes in different climate environments. This analysis method can provide quantitative basis for safety management of construction site and lay a solid data foundation for subsequent abnormal area identification and construction optimization strategy formulation.

[0139] In step S17, according to the regional level data deviation analysis result, abnormal area identification is carried out to obtain an abnormal area report, including:

[0140] If the regional support structure displacement value is greater than the preset support structure displacement threshold value, it is determined that the support structure displacement index is abnormal;

[0141] If the regional concrete strength value is less than the preset concrete strength threshold value, it is determined that the concrete strength index is abnormal;

[0142] If the regional environmental detection value is greater than the preset environmental impact threshold value, it is determined that the environmental detection index is abnormal;

[0143] If a region has three abnormal indexes, it is identified as a high-risk region, if it has two abnormal indexes, it is identified as a medium-risk region, if it has one abnormal index, it is identified as a low-risk region, and if it has no abnormal index, it is identified as a no-risk region;

[0144] The indexes include support structure displacement index, concrete strength index and environmental detection index;

[0145] The abnormal area report includes no-risk area, low-risk area, medium-risk area and high-risk area.

[0146] It is worth noting that in the construction site construction monitoring and management method of the application, the core of abnormal area identification is the calculated support structure displacement value, concrete strength value and environmental detection value, which are compared with the unique preset support structure displacement threshold value, concrete strength threshold value and environmental impact threshold value to determine whether there is an abnormal situation in the construction area. Each threshold value is a separate numerical value for comprehensive measurement of the safety state of the construction area, rather than setting a range for a specific measurement unit or a single parameter. This ensures that abnormal areas can be effectively identified under different working conditions.

[0147] The setting of the support structure displacement threshold aims to evaluate the stability of the support structure during construction, preventing excessive deformation from affecting structural safety. Through analysis of multiple engineering cases and monitoring data, combined with the standards of the "Technical Code for Building Foundation Pit Support", the support structure displacement threshold is set to 0.6. This value represents the allowable range of the support structure under normal stress conditions during construction. When the calculated support structure displacement value exceeds this threshold, it means that the support system in that area is under excessive load, and there is a risk of structural instability. For example, in soft soil foundation construction, the deformation of the support structure is large, but if the deformation exceeds 0.6, it means that the soil pressure is too large, the support stiffness is insufficient, or the foundation has excessive settlement, and reinforcement measures or adjustment of construction technology need to be taken.

[0148] The setting of the concrete strength threshold is used to determine whether the concrete quality in the construction area meets the design requirements, ensuring that the structure has sufficient bearing capacity and durability. Combined with the "Code for Design of Concrete Structures", the concrete strength threshold set by the invention is 0.4. When the calculated concrete strength value is less than this threshold, it indicates that the concrete has insufficient strength, which is caused by unreasonable mix design, improper curing conditions, or material quality problems. For example, in the core tube area of a high-rise building, the bearing requirement of concrete is higher. If the concrete strength value in this area is lower than 0.4, it will result in insufficient structural bearing capacity, cracks, or reduced durability. Therefore, in areas with abnormal strength, strength review measures should be taken, such as detecting concrete strength through rebound method or core drilling, and if necessary, increasing post-curing or performing surface repair to improve the final performance of concrete.

[0149] The setting of the environmental impact threshold is mainly used to evaluate the impact of external environmental conditions on construction safety, ensuring that the construction process can adapt to meteorological conditions and reduce construction quality problems or safety hazards caused by adverse environmental factors. Based on the "Technical Code for Construction Safety" and statistical analysis of construction environments in multiple locations, the environmental impact threshold is set to 0.75. This value is a comprehensive index calculated from parameters such as temperature, humidity, and wind speed. When the calculated environmental detection value exceeds 0.75, it indicates that the environmental conditions in that area have a negative impact on the construction process. For example, during concrete pouring, if the temperature is too high or the humidity is too low, it will accelerate the hydration reaction of concrete, affecting the final strength, and if the wind speed is too large, it will affect the safety of high-altitude work. Therefore, in the case of abnormal environment, the system will suggest construction management personnel to adjust the construction time or take appropriate protective measures, such as increasing water spraying maintenance in high-temperature weather or suspending high-altitude work in strong wind environment, to ensure construction safety.

[0150] By setting the support structure displacement threshold value 0.6, the concrete strength threshold value 0.4 and the environmental impact threshold value 0.75, the system can accurately evaluate the safety of the construction site. When the calculated value of a certain area exceeds the corresponding threshold value, the system will automatically mark the area as abnormal and further classify the risk level to guide the construction management personnel to take corresponding measures. The setting of the threshold value is not only based on engineering standards, but also combined with a large number of construction cases and data analysis, ensuring its applicability to different construction environments and effectively improving the construction quality and safety.

[0151] In the process of high-rise building construction, due to the high building structure, affected by wind load, support structure deformation, concrete strength change and other factors, structural stability problems are prone to occur. Therefore, real-time monitoring of the support structure displacement, concrete strength and environmental parameters of the construction site is needed to ensure construction safety. The method of the present application combines the method flow shown in Figure 1 and the system module shown in Figure 2 to realize data acquisition, processing, optimization, calibration and abnormality recognition in the process of building construction, ensuring the efficiency and intelligence of construction safety management.

[0152] In step S11, the system first deploys multiple intelligent monitoring nodes, including structure health monitoring sensors (SHM), concrete strength detection equipment, environmental monitoring equipment (wind speed sensor, temperature and humidity sensor), etc., for real-time collection of key data of building structure. These data include horizontal displacement, vertical settlement, inclination angle, compressive strength, splitting tensile strength, concrete density, temperature, humidity and wind speed. In the process of high-rise building construction, these data are crucial for evaluating structural stability, construction quality and environmental impact. For example, in a certain construction site, the system collects the horizontal displacement of the core tube of a certain floor as 8mm, the vertical settlement as 2.5mm, the inclination angle as 0.3°, the concrete compressive strength as 32MPa, the splitting tensile strength as 3.8MPa, the concrete density as 95%, the environmental temperature as 28℃, the humidity as 60%, and the wind speed as 15m / s, and transmits these data to the data acquisition module for storage and analysis.

[0153] In step S12, the original data of the construction site is affected by environmental noise, measurement error and equipment jitter, so the system pre-processes the data to ensure data quality. The support structure displacement data adopts sliding mean filtering algorithm to remove high-frequency noise and improve data stability. For example, the initial measurement value of a certain support node fluctuates between 7.8mm and 8.2mm, and the system calculates the smoothed displacement value as 8mm, eliminating short-term errors. The concrete strength data adopts time series analysis to eliminate abnormal measurement values and make strength growth prediction. For example, the 28-day strength of a certain area is measured as 30MPa, and the system combines historical measurement data to predict its final strength as 32MPa and adjust the data accuracy. Environmental data adopts Kalman filter for data smoothing to reduce sensor measurement error. For example, wind speed measurement data fluctuates between 14.5m / s and 15.5m / s, and after filtering, the system determines the stable wind speed as 15m / s. After preprocessing, the system obtains a stable feature data set to provide reliable input for subsequent calculation.

[0154] In step S13, in order to improve data upload efficiency, the system optimizes the data according to the data priority to ensure that key data can be processed and analyzed first. High-priority data includes support structure displacement data (affecting building stability), medium-priority data includes concrete strength data (affecting construction quality, but changing relatively slowly), and low-priority data includes environmental data (used for risk assessment, but changing little in a short period of time). For example, when the system detects that the lateral displacement of the core tube of a certain floor approaches the warning value (10mm), the system will prioritize uploading this data and delay the uploading of wind speed and temperature and humidity data to ensure the real-time nature of key data.

[0155] In step S14, due to the different time references of each monitoring device, the system needs to perform time synchronization to ensure that all data is analyzed under the same time reference framework. Distributed clock synchronization algorithm is adopted to obtain the clock deviation of each device. For example, the local time of a certain core tube displacement sensor is 1.2 seconds faster than the central server, while the wind speed sensor is 0.8 seconds slower, and the system automatically corrects the time of all devices to align to the standard time. Interpolation calculation is used to align the monitoring data at different times, for example, if the support displacement data is recorded at 12:00:05, but the environmental data is recorded at 12:00:07, the system will perform time compensation to synchronize the data to 12:00:06 for analysis. After time synchronization processing, all data can be calculated according to a unified time sequence, improving the accuracy of analysis.

[0156] In step S15, the construction monitoring device has spatial coordinate errors due to installation errors, geographical environment influences, and therefore the system performs spatial calibration to ensure the geographical position consistency of the data. The installation error of the support structure displacement monitoring point is 10 cm, and the system uses the total station and GPS positioning to compensate for the position and adjust it to the correct coordinates. The installation point of the wind speed sensor is offset by 5 cm relative to the design position, and the system corrects the position according to the construction plan to ensure the accuracy of the monitoring data. After spatial calibration, all data can be compared in the same coordinate system to improve the spatial consistency of the analysis.

[0157] In step S16, the system analyzes the data of different regions based on the clustering algorithm to identify the risk trends existing in the construction process. The density clustering method is used to analyze the support structure displacement data to identify abnormal regions. For example, if the lateral displacement of the core tube of a certain floor continues to increase, while the displacement of the adjacent floor is stable, there is a problem of structural stability in this region. The time series clustering is performed on the concrete strength data to determine the strength growth law of different pouring regions and identify the regions with insufficient strength. Finally, the system generates regional data analysis results to provide data support for subsequent anomaly detection.

[0158] In step S17, the system performs anomaly detection and risk level division according to the deviation of the regional data. High-risk region: if there are both support structure displacement anomalies (10 mm) and wind speed exceeding the standard (18 m / s) in a certain region, the system determines that the region is a high-risk region and recommends immediate reinforcement measures. Medium-risk region: if the support structure displacement of a certain region is normal, but the concrete strength is insufficient (30 MPa, lower than the standard 35 MPa), it is determined as a medium-risk region and it is recommended to strengthen monitoring. Low-risk region: if there is only environmental anomaly, such as wind speed slightly exceeding the standard range (16 m / s), but the structure data is normal, it is determined as a low-risk region and only needs to be continuously monitored. No-risk region: all monitoring data is normal and no additional adjustment is needed. Finally, the system generates an abnormal region report and provides risk warning and adjustment suggestions to the construction management personnel to ensure construction safety.

[0159] The method realizes intelligent monitoring of the high-rise building construction process through data acquisition, preprocessing, optimization, synchronization, calibration, analysis, and anomaly identification. Compared with traditional construction monitoring methods, the present application can dynamically adjust the monitoring strategy, improve the accuracy and real-time performance of data analysis, and provide stronger protection for construction safety.

[0160] Reference Figure 2 The second embodiment of the present application provides a building engineering site construction monitoring and management system, which comprises:

[0161] A data acquisition module is used to acquire an original data set.

[0162] a preprocessing module, configured to perform data preprocessing according to the original data set to obtain a preprocessed feature data set;

[0163] a sequential optimization module, configured to perform sequential optimization on the preprocessed feature data set to obtain an optimized data uploading sequence;

[0164] a time synchronization module, configured to perform time synchronization on the optimized data uploading sequence to obtain a unified time reference data set;

[0165] a spatial calibration module, configured to perform spatial calibration on the unified time reference data set to obtain a spatially calibrated data set;

[0166] a cluster analysis module, configured to perform data cluster analysis on the spatially calibrated data set to obtain a regional-level data deviation analysis result;

[0167] an abnormal region identification module, configured to perform abnormal region identification according to the regional-level data deviation analysis result to obtain an abnormal region report.

[0168] It should be noted that the building site construction monitoring and management system provided by the embodiments of the present application is used to execute all process steps of the building site construction monitoring and management method provided by the above embodiments, and the working principles and beneficial effects of the two are one-to-one correspondence, thus not being repeated.

[0169] The embodiments of the present application further provide an electronic device. The electronic device comprises a processor, a memory, and a computer program, such as a building site construction monitoring and management program, stored in the memory and executable on the processor. The processor executes the computer program to implement the steps in the above various building site construction monitoring and management method embodiments, such as the step S11 shown in the figure. Alternatively, the processor executes the computer program to implement the functions of the modules / units in the above various device embodiments, such as the abnormal region identification module. Figure 1

[0170] Illustratively, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device.

[0171] ​The electronic device can be a computing device such as a desktop computer, a notebook computer, a palm computer, a smart tablet, etc. The electronic device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than the above, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, etc.

[0172] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the electronic device, and connects various parts of the electronic device through various interfaces and lines.

[0173] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer program and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function (such as a sound playing function, an image playing function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0174] The modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0175] It should be noted that the above-described device embodiments are only schematic, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. In addition, the connection relationship between the modules in the device embodiment provided by the present application indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0176] The above-described specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above-described specific embodiments are only for the specific embodiments of the present application and are not used to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A construction site construction monitoring management method characterized by, The method comprises the following steps: obtaining an original data set; performing data preprocessing on the original data set to obtain a preprocessed feature data set; performing sequential optimization on the preprocessed feature data set to obtain an optimized data upload sequence; performing time synchronization on the optimized data upload sequence to obtain a unified time reference data set; performing spatial calibration on the unified time reference data set to obtain a spatially calibrated data set; performing data clustering analysis on the spatially calibrated data set to obtain a regional level data deviation analysis result; performing abnormal region identification according to the regional level data deviation analysis result to obtain an abnormal region report; wherein the data clustering analysis on the spatially calibrated data set to obtain a regional level data deviation analysis result comprises: calculating the regional support structure displacement value by the following formula: wherein, is the support structure displacement value for the th region, is the horizontal displacement for the th region, is the vertical settlement for the th region, is the inclination angle for the th region; calculating the regional concrete strength value by the following formula: wherein, the concrete strength value for the nth region, the compressive strength for the nth region, the tensile splitting strength for the nth region, the compressive strength for the nth region, the tensile splitting strength for the nth region, the compressive strength for the nth region, the tensile splitting strength for the nth region, the concrete density for the nth region; calculating the regional environmental detection value by the following formula: in, For the first Environmental monitoring values ​​for each area For the first The ambient temperature of each region No. Humidity of each area For the first Wind speed in each area; The regional level data deviation analysis result includes support structure displacement value, concrete strength value and environmental detection value.

2. The construction site construction monitoring management method according to claim 1, characterized by, The original data set includes horizontal displacement, vertical settlement, inclination angle, compressive strength, splitting tensile strength, concrete density, temperature, humidity and wind speed.

3. The construction site construction monitoring management method according to claim 1, characterized by, The data preprocessing on the original data set to obtain a preprocessed feature data set comprises: performing data denoising on the original data set based on a filtering algorithm to obtain a denoised data set; performing feature extraction on the denoised data set to obtain a feature data set; performing data compression on the feature data set based on data difference coding to obtain a preprocessed feature data set.

4. The construction site construction monitoring management method according to claim 1, characterized by, The sequential optimization on the preprocessed feature data set to obtain an optimized data upload sequence comprises: performing data priority sorting on the preprocessed feature data set to obtain a priority sorting list; performing dimension reduction on the priority sorting list to obtain a reduced feature data set; performing transmission sequence optimization on the reduced feature data set based on a dynamic scheduling strategy to obtain an optimized upload batch set.

5. The construction site construction monitoring management method according to claim 1, characterized by, The time synchronization on the optimized data upload sequence to obtain a unified time reference data set comprises: performing clock bias correction on the optimized data upload sequence based on a distributed clock synchronization algorithm to obtain a clock corrected data set; performing data timestamp alignment on the clock corrected data set based on a time series reconstruction algorithm to obtain a time aligned data set; performing time consistency verification on the time aligned data set to obtain a unified time reference data set.

6. The construction site construction monitoring management method according to claim 1, characterized by, The spatial calibration on the unified time reference data set to obtain a spatially calibrated data set comprises: performing device positioning error compensation on the unified time reference data set to obtain a compensated positioning data set; performing data spatial coordinate alignment on the compensated positioning data set to obtain an aligned data set; performing data consistency authentication on the aligned data set to obtain a spatially calibrated data set.

7. The construction site construction monitoring management method according to claim 1, characterized by, The abnormal area recognition is performed according to the area-level data deviation analysis result, and an abnormal area report is obtained. If the displacement value of the regional support structure is greater than the preset support structure displacement threshold value, it is determined that the support structure displacement index is abnormal. If the regional concrete strength value is less than the preset concrete strength threshold value, it is determined that the concrete strength index is abnormal. If the regional environmental detection value is greater than the preset environmental influence threshold value, it is determined that the environmental detection index is abnormal. If three indexes of a region are abnormal, the region is determined as a high-risk region; if two indexes of a region are abnormal, the region is determined as a medium-risk region; if one index of a region is abnormal, the region is determined as a low-risk region; and if no index of a region is abnormal, the region is determined as a no-risk region. The indexes include a support structure displacement index, a concrete strength index, and an environmental detection index. The abnormal area report includes a no-risk region, a low-risk region, a medium-risk region, and a high-risk region.

8. A construction site construction monitoring management system characterized by, A construction site construction monitoring management method for implementing any one of claims 1 to 7 comprises: a data acquisition module for acquiring an original data set; a preprocessing module for performing data preprocessing according to the original data set to obtain a preprocessed feature data set; a sequential optimization module for performing sequential optimization on the preprocessed feature data set to obtain an optimized data upload sequence; a time synchronization module for performing time synchronization on the optimized data upload sequence to obtain a unified time reference data set; a spatial calibration module for performing spatial calibration on the unified time reference data set to obtain a spatially calibrated data set; a clustering analysis module for performing data clustering analysis on the spatially calibrated data set to obtain an area-level data deviation analysis result; an abnormal area recognition module for performing abnormal area recognition according to the area-level data deviation analysis result to obtain an abnormal area report.

9. An electronic device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor are included, and the processor implements the construction site construction monitoring management method according to any one of claims 1 to 7 when executing the computer program.

Images