Building construction cost monitoring method and system based on real-time evaluation

Abstract

The invention relates to the technical field of cost control in building engineering management, in particular to a building construction cost monitoring method and system based on real-time evaluation, and the method comprises the steps: 1, constructing a dynamic mapping model of physical parameters and cost projects; 2, generating an environment-adaptive dynamic cost reference, correcting a material loss coefficient according to real-time environment sensor data, and generating minute-level reference cost in combination with the BIM design quantity of the current construction area; 3, multi-modal root cause diagnosis and early warning are executed, and when the actual cost deviation rate continuously exceeds the limit, the physical parameter contradiction combination is subjected to cross validation. By dynamically adjusting the weight of the physical parameters and combining the self-adaptive correction of the environmental data, the construction cost can be predicted and controlled more accurately, and errors caused by environmental changes or data islands are reduced.

Description

Technical Field

[0001] This invention relates to the field of cost control technology in construction project management, and in particular to a construction cost monitoring method and system based on real-time assessment. Background Technology

[0002] In the field of construction project management, dynamic control of construction costs is a core element of project profitability. Traditional cost monitoring methods mainly rely on manually entered periodic (usually weekly or monthly) reports, achieving control by comparing budgeted values ​​with actual expenditures. However, as modern large-scale projects develop towards super high-rise buildings and irregular structures, this type of method exposes the following inherent flaws: Because events such as material waste (e.g., uncontrolled rebar cutting excess), unplanned machinery idleness (e.g., tower crane scheduling conflicts), and rework (e.g., substandard concrete pouring) during construction are sudden and instantaneous, traditional methods require manual compilation of documents before cost calculation. This results in an average time lag of several days between the occurrence and discovery of the problem, leading to losses of hundreds of thousands of yuan per deviation (for example, a super high-rise project experienced a daily machinery cost overrun of 120,000 yuan due to the pump truck being idle and not detected in time). Industry practice shows that the cost of correcting cost deviations is exponentially related to the time to discovery; a lag of more than 24 hours will reduce the effectiveness of corrective measures by more than 50%.

[0003] In addition, cost-related data at the construction site are scattered across independently operating subsystems, specifically reflected in: Material consumption is recorded in materials management software, machine operating status is displayed on the equipment monitoring platform, and labor hours are tallied in the attendance system. These systems lack a physical layer linkage mechanism. For example: The inability to directly convert mixer vibration sensor data into a shift cost metering unit, the inability to correct material costs in real time through steel bar scrap image recognition results, and the data silo phenomenon keep cost analysis at the post-event statistical level, making it impossible to establish a real-time conversion link between "physical behavior and cost items".

[0004] Therefore, there is an urgent need for a construction cost monitoring method and system based on real-time assessment to solve the above problems. Summary of the Invention

[0005] To achieve the above objectives, the present invention provides a method and system for monitoring construction costs based on real-time assessment, wherein the method for monitoring construction costs based on real-time assessment includes the following steps: Step 1: Construct a dynamic mapping model between physical parameters and cost items: Construction costs are broken down into three categories: material costs, machinery costs, and labor costs. Two types of physical verification parameters are dynamically linked to each cost category. Material costs are related to the spatial displacement trajectory of materials and the rate of change in the visual inventory of materials; Mechanical costs are related to the effective vibration duration of the equipment and the fluctuation value of the equipment energy consumption. Labor costs are related to the distribution of personnel location hot zones and the deviation of work time in each process. The weights of physical parameters are dynamically adjusted during the construction phase, and the weight values ​​are generated through training on historical engineering cost deviation events. Step 2: Generate an environment-adaptive dynamic cost baseline, adjust the material loss coefficient based on real-time environmental sensor data, and generate a minute-level baseline cost by combining the BIM design quantities of the current construction area. Step 3: Perform multimodal root cause diagnosis and early warning. When the actual cost deviation rate continuously exceeds the limit, cross-validate contradictory combinations of physical parameters: When the spatial displacement trajectory of a material is abnormal but the visual inventory remains unchanged, an abnormal transfer warning is triggered. When the effective vibration duration of the equipment reaches the standard but the energy consumption fluctuation value is zero, a metering fault warning is triggered. The corresponding graded early warning system for the construction area will be activated based on the diagnostic results.

[0006] Preferably, the dynamic binding of the two types of physical verification parameters in step 1 includes: The spatial displacement trajectory of the material is collected via RFID tags and UWB positioning base stations. The positioning data is mapped to three-dimensional grid coordinates according to the building information model partition coding. The rate of change in the visual inventory of materials was obtained through time-series image analysis using a fixed-view camera, specifically including: Perform material target segmentation on consecutive frame images and calculate the percentage reduction in pixel area per unit time. Infrared supplementary lighting is activated when the light intensity is below a threshold to ensure image recognition stability. The physical parameter weighting adjustment process is as follows: During the basic construction phase, the weight of the material spatial displacement trajectory is increased to the upper limit. During the decoration phase, the weight of personnel location hot zone distribution increases linearly with the progress completion rate; The weight training uses the correlation statistics between cost overrun events and physical parameters in historical projects.

[0007] Preferably, step 2, which involves correcting the material loss coefficient based on real-time environmental sensor data, includes: The correction method for the material loss coefficient is as follows: Acquire real-time rainfall and wind speed sensor data; When rainfall exceeds the local historical average for the same period, the loss coefficient of mortar materials is adjusted upward according to the meteorological bureau's rainfall level. When the wind speed continuously exceeds the safe construction threshold, the loss coefficient of lightweight building materials increases non-linearly based on the derivative relationship of the wind resistance formula. The process of generating minute-level benchmark costs is as follows: Extract the design material usage from the current construction grid from the building information model; Baseline material cost = Design usage × (1 + Environmentally corrected loss factor) × Material unit price; Baseline mechanical cost = Scheduled machine shifts × Vibration effective duration percentage × Machine shift rate.

[0008] Preferably, the contradictory combinations of physical parameters in step 3 include: Material-related contradiction verification: If the RFID display material is still in the original stacking area, but the rate of decrease in image recognition inventory exceeds twice the design value, it is judged as abnormal loss; If the material's spatial coordinates are moved to a non-work area and there is no construction instruction record, a theft warning will be triggered. Mechanical contradiction verification: The vibration sensor detected that the equipment amplitude continuously exceeded the operating threshold, but the data fluctuation value of the fuel flow meter was lower than the idle speed reference, which was determined to be a sensor failure; A sudden increase in equipment energy consumption, but the vibration intensity did not meet the standard, triggered a mechanical fault warning. The threshold for the number of consecutive exceedances is determined based on the standard deviation of the normal distribution of cost deviation rates for similar projects.

[0009] Preferably, the triggering method for the tiered early warning includes: Level 1 warning, audible and visual alarm: Triggering condition: The cost deviation rate of a single construction grid is greater than the dynamic threshold and continues for 3 detection cycles; Dynamic threshold = average deviation rate of similar projects + real-time environmental risk coefficient × standard deviation; Level 2 alert, mobile push notification: Triggering conditions: The contradictory combination of associated physical parameters is verified and the schedule delay rate is greater than the tolerance value; The push notification includes abnormal coordinates, physical parameter comparison charts, and a database of handling suggestions; The environmental risk coefficient is dynamically adjusted based on meteorological warning levels and geological monitoring data.

[0010] Preferably, the illumination compensation mechanism in the time-series image analysis includes: Real-time monitoring of illuminance values ​​using an ambient light sensor; When the illuminance is lower than the preset threshold, the infrared supplementary lighting device is controlled to enhance the illumination of a specific wavelength. Adaptive histogram equalization is performed on the compensated image to eliminate shadow interference.

[0011] Preferably, the process for determining the safe construction threshold is as follows: Obtain the maximum wind speed records for the construction site within the past ten years from the meteorological bureau's database; The critical value for equipment operation safety is derived by inversely calculating the wind load calculation formula in the building safety code. Increase the safety margin factor confirmed by the structural engineer.

[0012] Preferably, it further includes: Model self-optimization steps: After each construction phase is completed, the accuracy rate of physical parameters in cost deviation events is statistically analyzed. When the diagnostic accuracy of a certain parameter exceeds the confidence threshold for N consecutive diagnostic tests, its priority in the weighted model is increased. Update the environmental loss coefficient library: Write the ratio of actual loss value to predicted value into the new coefficient matrix.

[0013] Accordingly, embodiments of the present invention also provide a construction cost monitoring system based on real-time assessment, used to run the construction cost monitoring method based on real-time assessment described in the embodiments of the present invention, comprising the following interconnected modules: The dynamic mapping configuration module is used to establish the binding relationship between physical parameters and cost items, including: The cost item decomposition unit breaks down construction costs into three categories: material costs, machinery costs, and labor costs. The physical parameter binding unit configures two types of verification parameters for each type of cost item: Material costs are related to the spatial displacement trajectory of materials and the rate of change in the visual inventory of materials; Mechanical costs are related to the effective vibration duration of the equipment and the fluctuation value of the equipment energy consumption. Labor costs are related to the distribution of personnel location hot zones and the deviation of work time in each process. The weighted dynamic adjustment unit modifies the weights of physical parameters based on the construction phase, and the weight values ​​are generated through training on a historical database. The environment adaptive baseline generation module, which is data-connected to the dynamic mapping configuration module, includes: An environmental sensor interface is provided to receive real-time rainfall and wind speed data. The loss coefficient correction subunit adjusts the material loss coefficient in segments based on environmental data. The baseline calculation sub-unit calls the design quantities from the building information model to generate minute-level baseline costs. The multimodal diagnostic early warning module interacts with the environmental adaptive benchmark signal generation signal, including: The physical parameter discrepancy analysis unit executes when the cost deviation rate continuously exceeds the limit: Material trajectory-inventory contradiction detector, comparing displacement trajectory with visual inventory changes; Equipment vibration-energy consumption contradiction detector to verify the relationship between vibration duration and energy consumption fluctuation; The tiered early warning execution unit activates the alarm devices in the corresponding construction area based on the conflict detection results. Data bus architecture, the physical interface connecting each module: The positioning base station interface is connected to the UWB positioning base station via an RS485 bus; The image acquisition interface connects to a fixed-view camera via Ethernet; The warning output interface controls the audible and visual alarm via GPIO.

[0014] Preferably, the physical parameter binding unit includes the following sub-units: The material spatial displacement trajectory acquisition subunit consists of radio frequency tags deployed on building materials and UWB positioning base stations installed at the vertices of the construction grid. The base station coordinates are bound to the building information model partition coding. The material visual inventory change rate acquisition subunit consists of a dustproof infrared camera and a supplementary light controller. The supplementary light controller activates a specific band infrared light source based on the ambient light sensor data. The effective vibration duration acquisition subunit includes a triaxial vibration sensor mounted on the mechanical housing, whose signal conditioning circuit filters out non-operating frequency noise. The data bus architecture adds the following dedicated channels: Spatiotemporal alignment channel: An FPGA processor that converts positioning base station coordinates into BIM grid coordinates; Contradiction Analysis Acceleration Channel: A DSP chip used for image time series analysis and vibration energy consumption ratio calculation; Early warning feedback loop: The alarm device trigger signal is transmitted back to the CAN bus of the dynamic mapping configuration module.

[0015] The beneficial effects of this invention are: 1. This invention monitors physical behaviors during construction in real time, such as material spatial displacement trajectories, vibration duration and energy consumption fluctuations of mechanical equipment, and thermal distribution of personnel positions. Combined with BIM design models and environmental sensor data, it generates dynamic cost benchmarks in real time, enabling timely detection of cost deviations during construction and prompt activation of early warnings based on diagnostic results. This method, through multimodal root cause diagnosis and early warning, can quickly identify and correct deviations when problems occur, avoiding losses caused by delayed detection.

[0016] 2. This invention constructs a dynamic mapping model between physical parameters and cost items, and acquires and binds key data such as material consumption, machinery usage, and labor hours in real time through radio frequency identification, UWB positioning base stations, and visual image recognition. This breaks down the isolation barriers between subsystems, ensures the correlation and synchronous update of data at the physical layer, and enables every physical behavior in the construction process to affect and adjust related cost items in real time, thereby achieving dynamic and accurate cost monitoring and management.

[0017] 3. This invention generates accurate minute-level benchmark costs by acquiring environmental data in real time and adjusting the material loss coefficient based on this data. Through this adaptive correction mechanism, material loss at the construction site can be dynamically adjusted, ensuring the accuracy of material costs and reducing cost errors caused by changes in environmental factors.

[0018] 4. This invention makes the cost monitoring model more consistent with the actual construction process by dynamically adjusting the weights of physical parameters based on the construction stage. It can give appropriate attention to key parameters at different construction stages, thereby improving the monitoring accuracy and the adaptability of the model. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of the steps of the method of the present invention; Figure 2 This is a flowchart illustrating the steps of the illumination compensation mechanism in the temporal image analysis method of the present invention. Figure 3 This is a structural block diagram of the system of the present invention. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0022] Please see Figures 1-3 This invention provides a method for monitoring construction costs based on real-time assessment. In step 1, construction costs are divided into three categories: material costs, machinery costs, and labor costs. Each cost item is linked to physical verification parameters to track various behaviors during construction in real time.

[0023] Understandably, material costs are addressed by tracking the spatial displacement of materials using sensors or image recognition technology. For example, during the use of rebar, sensors record the material's movement trajectory and combine this with visual inventory change rates (such as the amount of rebar remaining in the warehouse) to determine if material consumption exceeds expectations. If the spatial displacement change does not match the visual inventory change, the system will trigger an alert. This allows for timely responses to rebar waste or loss, preventing cost overruns.

[0024] Machinery costs: The operation of machinery and equipment is monitored by vibration sensors to determine its effective working time, while energy consumption fluctuations are used to assess the equipment's efficiency. If the vibration duration of the equipment meets the standard, but the energy consumption fluctuation value is zero, it indicates that the equipment may have a metering fault or be malfunctioning. The system will then issue a metering fault warning to prevent uncontrolled costs due to undetected equipment malfunctions.

[0025] Labor costs: By analyzing worker work areas through positioning systems and heat zone distribution, combined with attendance and process time data, labor costs are assessed. If there is a significant deviation in the time of a certain process (such as delays or repetitive work), the system will generate an alarm based on the process time deviation value, thereby reducing waste of labor costs.

[0026] The impact of physical parameters varies at different construction stages. For example, material waste is more severe during the foundation construction stage, thus requiring a higher weighting of material-related physical parameters. In the later finishing stages, labor costs and machinery costs become more important. Therefore, based on historical project data, the system dynamically adjusts the weights of these parameters to reflect the changing trends of various costs during actual construction.

[0027] In step 2, the system automatically adjusts the material loss coefficient based on real-time environmental sensor data (such as temperature, humidity, and precipitation). For example, in hot weather, cement dries faster, potentially increasing cement loss. The system automatically adjusts the material loss coefficient based on these environmental factors and, combined with the BIM design data for the current construction area, generates an accurate minute-level cost baseline. This baseline cost reflects the dynamic changes in materials, machinery, and labor during construction, ensuring real-time monitoring of any budget overruns.

[0028] In step 3, when the actual cost deviation rate continuously exceeds a set threshold, the system triggers a root cause diagnosis process. The system helps identify potential causes of cost deviations by cross-validating contradictory combinations of various physical parameters. For example, if the material's spatial displacement trajectory is abnormal but the visual inventory remains unchanged, it may indicate an anomaly in the material's transportation or consumption process, triggering a transfer anomaly warning. Conversely, if the equipment's effective vibration duration meets the standard, but the energy consumption fluctuation value is zero, it may indicate a metering system malfunction, prompting the system to activate a metering fault warning.

[0029] Based on the root cause diagnosis results, the system will activate tiered early warnings for the corresponding construction areas to ensure that deviations of different degrees can be addressed in a timely manner. For example, the system will issue a reminder for minor deviations; for serious deviations, the system will immediately initiate corrective measures, such as adjusting resource scheduling and reassessing the budget.

[0030] In one possible implementation, to accurately monitor material usage and flow during construction, this method combines Radio Frequency Identification (RFID) tags with UWB (Ultra-Wideband) positioning base stations to track material locations in real time. RFID tags are attached to the materials, while the UWB positioning base stations collect spatial displacement data of the materials in real time. By processing the UWB positioning data and using the zoning coding of the Building Information Modeling (BIM), each material location is mapped to a three-dimensional grid coordinate system, thereby obtaining the material's real-time spatial location information. The zoning coding of the BIM ensures accurate tracking of materials in different areas of the building, effectively controlling the risk of material waste and theft.

[0031] The visual inventory change rate of materials is obtained through time-series image analysis using a fixed-view camera. At each moment, the camera captures images of the scene. After target segmentation of consecutive frames, the system calculates the percentage reduction in pixel area per unit time. In this way, the system can accurately estimate the amount of material consumed. If the pixel area in the image decreases, it indicates that the material consumption is increasing, and the system will adjust the cost budget accordingly. In addition, the camera dynamically adjusts its shooting mode based on the lighting conditions. When the light intensity is below a preset threshold, the system activates infrared supplementary lighting to ensure the stability and accuracy of image recognition, maintaining efficient material consumption monitoring even in complex environments.

[0032] Depending on the construction phase, the weights of various cost items, such as materials, labor, and machinery, are dynamically adjusted. During the foundation construction phase, because material transportation and storage are critical, the system increases the weight of material spatial displacement trajectories to the maximum value to ensure strict control of material costs. During the decoration phase, the work progress and work sequence arrangement have a significant impact on costs; therefore, the system linearly increases the weight of personnel location hotspot distribution according to the progress completion rate. In this way, the system can flexibly allocate the monitoring focus of various costs at each stage, thereby achieving refined management.

[0033] The system uses historical project data for weight training. By analyzing cost overruns in historical projects, the correlation between various physical parameters and cost deviations is statistically analyzed to establish a weight adjustment model. This model can dynamically adjust the weight values ​​of each physical parameter according to the actual situation at different stages, thereby making cost monitoring more accurate and personalized. The training results of historical data can effectively improve the predictive ability of the real-time monitoring system and reduce cost runaway caused by changes in project stages.

[0034] In one possible implementation, real-time environmental sensors are first deployed to acquire rainfall and wind speed data. Rainfall sensors monitor precipitation, and wind speed sensors monitor wind speed at the construction site. Real-time acquisition of environmental data provides immediate meteorological information, serving as an important basis for adjusting material loss coefficients. In practice, the sensors continuously collect rainfall and wind speed data and transmit it to the construction cost monitoring system.

[0035] When rainfall exceeds the local historical average for the same period, the loss coefficient for mortar materials will be adjusted upwards in stages according to the rainfall level provided by the meteorological bureau. Specifically, the higher the rainfall level, the greater the increase in the mortar loss coefficient. This adjustment is to reflect the potential increase in loss of mortar and other materials due to increased humidity and slower concrete curing during heavy rain. The system automatically identifies rainfall data and corrects it according to preset rules to ensure accurate reflection of construction costs.

[0036] When wind speed consistently exceeds the safe construction threshold, the loss coefficient of lightweight building materials will increase non-linearly based on the derivative relationship of the wind resistance formula. In practice, increased wind speed not only damages the surface of building materials such as lightweight panels but also affects the efficiency of construction operations. Therefore, it is necessary to quantify the relationship between wind speed and building material loss, and adjust the loss coefficient according to changes in wind speed. As wind speed continues to increase, the loss coefficient of lightweight building materials increases non-linearly according to the wind resistance formula, thus accurately reflecting the actual impact of wind speed on building material loss.

[0037] Extract the design material usage from the building information model (BIM) for the current construction grid, and calculate the actual material loss based on the corrected material loss coefficient. The baseline material cost formula is: Baseline material cost = Design usage × (1 + Environmentally corrected loss factor) × Material unit price; This calculation method allows the system to dynamically correct material loss based on real-time environmental data, accurately reflecting material consumption during actual construction.

[0038] The baseline machinery cost consists of the scheduled number of shifts, the percentage of effective vibration time, and the shift rate. This process takes into account the operating efficiency of equipment on the construction site, calculating the machinery cost for each stage by analyzing data such as equipment operating time, vibration duration, and rates. The formula is: Baseline machine cost = Scheduled machine shifts × Vibration effective duration percentage × Machine shift rate; This calculation method helps to accurately estimate the cost of machinery and equipment, avoiding cost deviations caused by equipment downtime or inefficient operation.

[0039] By real-time correction of material loss coefficients and minute-level cost generation, the accuracy and real-time nature of construction cost monitoring are enhanced, thus providing strong support for project cost control and risk management.

[0040] In one possible implementation, the system tracks materials in real time using radio frequency identification (RFID) technology. When the RFID system shows that the material is still in its original storage area, but the rate of inventory reduction detected by the image recognition system exceeds twice the design value, the system determines it as abnormal loss. This verification method can automatically detect whether material consumption exceeds expectations, thereby identifying potential waste or mismanagement problems early and taking timely measures to reduce unnecessary losses. The dual verification of image recognition and RFID provides a high-precision means of loss monitoring.

[0041] When the spatial coordinates of materials are moved to a non-operational area and there is no record of construction instructions, the system will trigger a theft warning. This verification method, by tracking the real-time location of materials and operation instruction records, can accurately identify material movements that do not conform to the predetermined process. If materials are found to have been moved to a non-operational area without any operation instructions, it indicates a possible theft, thus issuing an alarm in a timely manner to ensure the safety of engineering materials.

[0042] During equipment operation, vibration sensors continuously monitor the vibration intensity. When the vibration amplitude consistently exceeds the set operating threshold, but the fuel flow meter's data fluctuation value is below the idle speed reference, the system determines that the sensor has failed. This verification method avoids false alarms or the inability to detect equipment faults in a timely manner due to sensor malfunctions. Cross-validation of key equipment parameters ensures the reliability and accuracy of the monitoring system.

[0043] When equipment experiences a sudden increase in energy consumption, but the vibration intensity does not meet the standard, the system will trigger a mechanical fault warning. This verification mechanism accurately identifies potential equipment failure risks by comparing and analyzing energy consumption and vibration data in real time. For example, a sudden increase in energy consumption may signal wear or malfunction of internal components, while a failure to meet the standard vibration intensity may indicate that the equipment is not operating as expected. Timely warnings can prevent downtime and higher maintenance costs caused by equipment failure.

[0044] The system determines the threshold for consecutive exceedances based on the standard deviation of the normal distribution of cost deviation rates for similar projects. Through big data analysis, the system can automatically calculate the normal deviation range, identify abnormal fluctuations, and trigger warnings when the set standard deviation value is exceeded. This method uses statistical models to quantitatively analyze construction cost fluctuations, providing project managers with more accurate cost control data and avoiding overreactions or overlooking potential risks due to human error.

[0045] By cross-validating physical parameters across multiple dimensions, a more intelligent, accurate, and reliable means of monitoring construction costs is provided. Through these real-time monitoring and verification mechanisms, the management efficiency, cost control, and safety assurance at construction sites have all been significantly improved, thereby promoting the modernization and intelligentization of construction project management.

[0046] In one possible implementation, the trigger condition for the Level 1 early warning system is that the cost deviation rate of a single construction grid exceeds a dynamic threshold, and this deviation persists for more than three detection cycles. The dynamic threshold is calculated as follows: Dynamic threshold = Average deviation rate of similar projects + (Real-time environmental risk coefficient × standard deviation); The average deviation rate for similar projects is obtained through statistical analysis of historical similar projects, reflecting the normal range of cost deviations in projects of the same type. By analyzing a large amount of project data, a benchmark value can be obtained, which is used to determine whether the cost deviation of the current project exceeds the normal fluctuation range.

[0047] The real-time environmental risk coefficient is dynamically adjusted based on real-time meteorological warning levels and geological monitoring data. For example, the environmental risk coefficient increases in the event of extreme weather (such as heavy rain, strong winds, etc.) or geological anomalies (such as earthquakes, changes in soil moisture, etc.). The result of multiplying this coefficient by the standard deviation increases the sensitivity of the dynamic threshold, enabling the system to detect potential risks in a timely manner.

[0048] Standard deviation is a measure of historical cost data fluctuations, representing the range of cost fluctuations during normal construction. Combined with real-time environmental risk coefficients, it allows for more accurate prediction of potential cost anomalies during construction.

[0049] When the cost deviation rate of the construction grid exceeds the dynamic threshold and persists for three consecutive detection cycles, the system will trigger an audible and visual alarm. At this time, managers will be immediately alerted and can quickly take corrective measures to prevent excessive deviation in construction costs and further economic losses.

[0050] A Level 2 warning will be triggered when, during construction, a contradictory combination of related physical parameters is verified and the schedule delay rate exceeds the tolerance limit. The specific triggering conditions are as follows: By analyzing data from multiple sensors (such as vibration, temperature, humidity, and displacement), an early warning is triggered if inconsistencies are found in the combination of certain physical parameters (e.g., changes in certain materials do not match the expected construction conditions). This type of verification helps identify potential problems in equipment or during the construction process.

[0051] Schedule delay rate refers to the difference between the actual construction progress and the planned progress. When the schedule delay rate exceeds a predetermined tolerance threshold, it means that there has been a significant deviation in the construction progress, and further investigation is required.

[0052] After a Level 2 alert is triggered, the system sends an alarm to relevant personnel via mobile push notifications. The notification content includes: Abnormal coordinates: Displays the specific location of the abnormality, facilitating timely location and action by on-site management personnel.

[0053] Physical parameter comparison chart: Provides a comparison chart of abnormal physical parameters with normal values ​​to help managers quickly understand the root cause of the problem.

[0054] Handling suggestion library: Provides a series of handling suggestions based on historical data and expert experience, including possible causes of failure, adjustment measures and repair methods.

[0055] The environmental risk coefficient is a crucial component of this system, dynamically adjusted based on meteorological warning levels and geological monitoring data. For instance, extreme weather conditions such as storms and lightning can impact construction safety and costs; therefore, the risk coefficient needs to be adjusted in real-time according to changes in these external conditions to enhance the sensitivity of the early warning system. Geological monitoring data, such as soil moisture and landslide warnings, also influence the environmental risk coefficient, ensuring that construction management can adapt to constantly changing external conditions.

[0056] Through real-time data dynamic analysis and intelligent early warning mechanisms, the cost control, schedule management and risk response capabilities of construction projects have been effectively improved, and the overall management level of the projects has been optimized.

[0057] In one possible implementation, the first step of the illumination compensation mechanism is to monitor illuminance values ​​in real time using ambient light sensors installed at the construction site. These sensors continuously track the light intensity at the construction site, capturing data on light changes over different time periods. This data not only provides a basis for subsequent image processing but also triggers the compensation mechanism promptly when lighting conditions change significantly. For example, when the construction site becomes cloudy or nighttime, the illuminance value may drop sharply, leading to a loss of image clarity and detail, affecting subsequent analysis. Real-time monitoring of illuminance values ​​allows the system to react promptly and activate the infrared supplementary lighting device.

[0058] When the ambient light sensor detects that the illuminance is below a preset threshold, the system automatically activates the infrared supplementary lighting device. This device typically uses infrared LEDs or other infrared light sources to enhance the illumination of the image acquisition area without interfering with normal operations at the construction site. The supplementary lighting wavelength is usually selected within the infrared spectrum to avoid interference or excessively bright light sources within the visual range. By providing specific wavelengths of illumination through supplementary lighting equipment, cameras or image acquisition devices can capture more detail in low-light environments, improving image contrast and clarity.

[0059] Even after supplemental lighting, areas of the image may still be too dark or too bright, especially under uneven lighting conditions. To further optimize image quality, the system performs adaptive histogram equalization on the compensated image. Histogram equalization is a commonly used image processing technique that adjusts the brightness distribution of an image to make the brightness range more uniform, thereby improving the visual effect of the image. Adaptive histogram equalization, on the other hand, performs equalization processing on local areas of the image, which can effectively eliminate shadow interference caused by uneven local lighting. Especially in construction sites, shadows or highlights may appear due to object obstruction or uneven lighting. Adaptive histogram equalization can effectively eliminate these adverse effects, ensuring the clarity and contrast of image details.

[0060] The illumination compensation mechanism can significantly improve image quality under low light conditions, provide reliable data support for construction cost monitoring, and ensure the effectiveness of the monitoring method in complex construction environments.

[0061] In one possible implementation, to accurately assess the potential wind risks at the construction site, it is first necessary to obtain the maximum wind speed records for the past ten years from the meteorological bureau's database. This data provides long-term wind speed trends and historical data for determining wind speed thresholds that may affect construction safety. The meteorological bureau's database typically contains wind speed data for each season of the year, especially records of wind speeds during extreme weather conditions such as strong winds and typhoons. By analyzing this data, the range of local wind speed fluctuations can be understood, thus providing a basis for subsequent wind load calculations.

[0062] Wind load is a crucial factor affecting the safety of buildings and equipment. Based on wind load calculation formulas in building safety codes and combined with specific environmental data from the construction site (such as wind speed, terrain, building height, and shape), the critical safety values ​​for equipment operation can be derived. Wind load calculation formulas are typically based on meteorological data and building structural characteristics to assess the actual impact of wind speed on the building. For example, when wind speed exceeds a certain critical value, the stability of building equipment or structures may be affected, leading to construction risks. Therefore, wind load calculations can accurately assess the potential risks of wind speed to equipment operation and determine the maximum critical wind speed to be avoided during construction.

[0063] To ensure safe construction, a safety margin factor is typically added to the wind load calculations. This factor is determined by experienced structural engineers based on the specific site conditions. The structural engineer considers various uncertainties that may arise during construction, such as equipment load, unforeseen circumstances, and the operating procedures of on-site personnel, to determine an appropriate safety margin factor. This factor provides additional safety assurance beyond the calculated critical safety value, allowing construction workers to stop work promptly when wind speeds approach the critical value, avoiding construction under dangerous wind speed conditions.

[0064] The process of determining this safe construction threshold not only helps to improve construction safety, but also enhances the risk control capabilities during the construction process, ensuring that construction projects can be completed smoothly while ensuring the safety of personnel and equipment, and effectively controlling construction costs.

[0065] In one possible implementation, during construction, after each construction phase is completed, the system verifies the physical parameters and calculates their accuracy in cost deviation events. These physical parameters include, but are not limited to, cost-related indicators such as building material consumption, construction progress, and personnel efficiency. Accuracy is assessed by comparing the deviation between predicted and actual values. If a physical parameter consistently provides accurate diagnostic results in cost deviation events, that parameter is considered to have high predictive ability. Collecting and recording this accuracy data provides a basis for subsequent model optimization and enables scientific decisions regarding model weight adjustments.

[0066] When the diagnostic accuracy of a certain physical parameter exceeds a set confidence threshold N times consecutively, the priority of that parameter will be increased in the weighted model. This means that the parameter will be given a higher weight in subsequent cost prediction and analysis, and the system will rely more heavily on the data of this parameter for prediction. For example, if a parameter (such as material consumption) accurately reflects cost changes during construction multiple times consecutively, this parameter will be considered a key indicator, and the system will increase its weight in subsequent predictions. This allows the model to pay more attention to parameters closely related to actual cost changes, improving the accuracy of predictions.

[0067] The environmental loss coefficient database is a record comparing actual losses with predicted losses during construction. During construction, losses can occur due to various factors (such as material waste, transportation losses, and construction errors). Whenever the actual loss value deviates from the predicted loss value, the system writes their ratio (i.e., the ratio of actual loss to predicted loss) into a new coefficient matrix, updating the environmental loss coefficient database. This process ensures that the loss coefficients are continuously optimized based on data from the actual construction process. When a new construction phase is completed, the system can adjust the loss predictions for future phases based on the updated loss coefficients, thereby improving the accuracy of cost monitoring.

[0068] The model's self-optimization process can continuously learn and adjust, improving the accuracy of construction cost monitoring, enhancing the system's adaptability and intelligence, and effectively helping managers reduce unnecessary costs and resource waste during construction.

[0069] Accordingly, embodiments of the present invention also provide a construction cost monitoring system based on real-time assessment, used to run the construction cost monitoring method based on real-time assessment described in the embodiments of the present invention, comprising the following interconnected modules: The dynamic mapping configuration module is used to establish the binding relationship between physical parameters and cost items, including: The cost item decomposition unit breaks down construction costs into three categories: material costs, machinery costs, and labor costs. The physical parameter binding unit configures two types of verification parameters for each type of cost item: Material costs are related to the spatial displacement trajectory of materials and the rate of change in the visual inventory of materials; Mechanical costs are related to the effective vibration duration of the equipment and the fluctuation value of the equipment energy consumption. Labor costs are related to the distribution of personnel location hot zones and the deviation of work time in each process. The weighted dynamic adjustment unit modifies the weights of physical parameters based on the construction phase, and the weight values ​​are generated through training on a historical database. The environment adaptive baseline generation module, which is data-connected to the dynamic mapping configuration module, includes: An environmental sensor interface is provided to receive real-time rainfall and wind speed data. The loss coefficient correction subunit adjusts the material loss coefficient in segments based on environmental data. The baseline calculation sub-unit calls the design quantities from the building information model to generate minute-level baseline costs. The multimodal diagnostic early warning module interacts with the environmental adaptive benchmark signal generation signal, including: The physical parameter discrepancy analysis unit executes when the cost deviation rate continuously exceeds the limit: Material trajectory-inventory contradiction detector, comparing displacement trajectory with visual inventory changes; Equipment vibration-energy consumption contradiction detector to verify the relationship between vibration duration and energy consumption fluctuation; The tiered early warning execution unit activates the alarm devices in the corresponding construction area based on the conflict detection results. Data bus architecture, the physical interface connecting each module: The positioning base station interface is connected to the UWB positioning base station via an RS485 bus; The image acquisition interface connects to a fixed-view camera via Ethernet; The warning output interface controls the audible and visual alarm via GPIO.

[0070] Preferably, the physical parameter binding unit includes the following sub-units: The material spatial displacement trajectory acquisition subunit consists of radio frequency tags deployed on building materials and UWB positioning base stations installed at the vertices of the construction grid. The base station coordinates are bound to the building information model partition coding. The material visual inventory change rate acquisition subunit consists of a dustproof infrared camera and a supplementary light controller. The supplementary light controller activates a specific band infrared light source based on the ambient light sensor data. The effective vibration duration acquisition subunit includes a triaxial vibration sensor mounted on the mechanical housing, whose signal conditioning circuit filters out non-operating frequency noise. The data bus architecture adds the following dedicated channels: Spatiotemporal alignment channel: An FPGA processor that converts positioning base station coordinates into BIM grid coordinates; Contradiction Analysis Acceleration Channel: A DSP chip used for image time series analysis and vibration energy consumption ratio calculation; Early warning feedback loop: The alarm device trigger signal is transmitted back to the CAN bus of the dynamic mapping configuration module.

[0071] The following examples will illustrate this in detail: This invention relates to technologies for wind load calculation and construction cost optimization, and in particular to technical solutions for cost monitoring and risk assessment during the construction phase using meteorological data, building parameters, and model optimization algorithms.

[0072] Traditional construction cost monitoring and safety assessment methods rely too heavily on static estimates, failing to adequately consider dynamic environmental factors (such as wind speed and weather conditions) and real-time data changes, resulting in significant cost deviations. Existing methods are not flexible enough to adapt to changes in different construction project environments and lack a precise dynamic optimization system.

[0073] The purpose of this invention is to provide a dynamic construction cost optimization method based on wind load and environmental parameters. This method can adjust the construction cost prediction in real time according to meteorological data and other environmental parameters at the construction site, optimize risk assessment, and optimize cost deviations based on historical data, so as to improve construction efficiency and reduce resource waste.

[0074] This example uses a large-scale construction project (Project A) in a city as an example. The project is currently constructing a steel structure building. Located in a coastal area, the project will be affected by seasonal storms during construction, therefore the impact of wind load on construction costs and safety needs to be considered.

[0075] Parameter settings: Wind speed: The maximum wind speed at the construction site is 20 meters per second, and the average wind speed during seasonal storms is 15 meters per second.

[0076] Building parameters: The building is 100 meters high, the structural type is reinforced concrete frame, and the building area is 10,000 square meters.

[0077] Initial value of environmental loss coefficient: set to 0.05, representing the proportion of material loss during construction.

[0078] Construction material consumption parameters: The estimated amount of concrete used per square meter is 2.5 tons, and the amount of steel used is 1.5 tons.

[0079] Project duration: The estimated construction period is 12 months.

[0080] Wind load is a significant factor affecting construction costs and safety. According to the wind load calculation formula in the "Code for Design of Building Structures" (GB50009-2012): ; in: Wind load (unit: Newtons); Wind speed (unit: meters per second) is set to a maximum wind speed of 20 meters per second; The windward area of ​​the building (unit: square meters) is calculated as the frontal area of ​​the building: 100 meters × 50 meters = 5000 square meters. This is the wind load factor, with a value of 0.8 (depending on the building type and wind direction angle).

[0081] Substituting these values ​​into the formula, we get: ; The building can withstand a wind load of 1,957,600 Newtons at maximum wind speed.

[0082] In actual construction, the loss coefficient and the consumption of construction materials will change due to variations in environmental factors such as wind speed, temperature, and humidity. Therefore, this invention employs a dynamic optimization algorithm based on historical data and real-time environmental monitoring to adjust the loss coefficient and cost prediction.

[0083] A loss factor of 0.05 was set, and preliminary calculations were performed based on data such as construction progress and material consumption. In this embodiment of the invention, the total construction cost in the first month was 2 million yuan.

[0084] Based on real-time meteorological monitoring data, parameters such as wind speed and humidity are updated monthly, and new wind loads are calculated. For example, in the third month, a seasonal storm with wind speeds reaching 15 m / s occurred during construction. The wind load was recalculated based on this wind speed, resulting in: ; The wind load value has decreased compared to the initial forecast.

[0085] The loss coefficient of raw materials during construction will vary depending on changes in wind speed and other environmental conditions. For example, in the third month, due to the impact of storms, the loss of construction materials increases, so the loss coefficient is adjusted to 0.08. This will affect the calculation of material consumption; for example, the consumption of concrete will be adjusted from 2,500 tons to 2,700 tons, and the consumption of steel will be adjusted from 1,500 tons to 1,600 tons.

[0086] Based on the adjusted loss coefficient and wind load calculations, the increased consumption of construction materials led to a rise in overall construction costs. Therefore, the construction management system automatically generated a new cost forecast, with the updated construction cost at 2.05 million yuan.

[0087] To verify the effectiveness of this invention, it was compared with traditional cost monitoring methods. Traditional methods use fixed loss coefficients and wind load predictions that do not consider environmental factors, ignoring dynamic changes during construction.

[0088] In this embodiment of the invention, the loss factor is fixed at 0.05 throughout the construction period, and wind load calculations are only performed at the initial stage of the project. The total project cost calculated using traditional methods is 2.1 million yuan.

[0089] By using the dynamic optimization algorithm of this invention, combined with feedback from real-time environmental data and historical data, the construction cost is adjusted in real time in different months, with the final cost being 2.05 million yuan, which is about 2.4% lower than the traditional method.

[0090] To further verify the performance of this invention, model validation was performed using data from multiple construction projects. The calculated error rate was below 5%, significantly higher than the 15% accuracy of traditional methods. Especially in areas with highly variable weather conditions, this invention can adjust construction strategies and cost predictions in real time, reducing construction risks and effectively controlling budget overruns.

[0091] Compared to traditional methods, this invention not only improves the accuracy of construction cost prediction but also reduces budget overruns and resource waste caused by environmental changes. Therefore, the application of this invention in construction management has significant advantages, improving construction efficiency and reducing construction risks.

[0092] Examples of threshold settings in this embodiment include: The illuminance threshold is set to 200 lux. According to the industry standard "Code for Lighting Design of Construction Sites" (GB 50688-2011), when the ambient illuminance is below 200 lux, the image recognition accuracy drops below 80%. Real-time monitoring is conducted using an ambient light sensor. If the illuminance value is ≤200 lux, the supplementary lighting controller activates an 850nm infrared light source.

[0093] The safe construction threshold is set at 10 m / s. Based on the wind load formula in the *Code for Design of Building Structures* (GB 50009-2012), the wind load is calculated as follows: In the example calculation, with a building height of 100m, a windward area of ​​5000㎡, a wind load factor of 0.8, and a wind speed V = 10 m / s, the wind load F = 0.613 × 10² × 5000 × 0.8 = 245200 N. The safety margin factor is taken as 1.2 (to be confirmed by the structural engineer), therefore the actual threshold = 10 × 1.2 = 12 m / s.

[0094] In one embodiment, the threshold number of consecutive exceedances is set to 3 consecutive exceedances; The environmental risk coefficient is dynamically adjusted according to the meteorological warning level: 0.5 for yellow warning, 1.0 for orange warning, and 1.5 for red warning. The confidence threshold is set to 90%, and N=5 times; The tolerance threshold is set at 10%, based on the project schedule tolerance standard.

[0095] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0096] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring construction costs based on real-time assessment, characterized in that, Includes the following steps: Step 1: Construct a dynamic mapping model between physical parameters and cost items: Construction costs are broken down into three categories: material costs, machinery costs, and labor costs. Two types of physical verification parameters are dynamically linked to each cost category. Material costs are related to the spatial displacement trajectory of materials and the rate of change in the visual inventory of materials; Mechanical costs are related to the effective vibration duration of the equipment and the fluctuation value of the equipment energy consumption. Labor costs are related to the distribution of personnel location hot zones and the deviation of work time in each process. The weights of physical parameters are dynamically adjusted during the construction phase, and the weight values ​​are generated through training on historical engineering cost deviation events. Step 2: Generate an environment-adaptive dynamic cost baseline, adjust the material loss coefficient based on real-time environmental sensor data, and generate a minute-level baseline cost by combining the BIM design quantities of the current construction area. Step 3: Perform multimodal root cause diagnosis and early warning. When the actual cost deviation rate continuously exceeds the limit, cross-validate contradictory combinations of physical parameters: When the spatial displacement trajectory of a material is abnormal but the visual inventory remains unchanged, an abnormal transfer warning is triggered. When the effective vibration duration of the equipment reaches the standard but the energy consumption fluctuation value is zero, a metering fault warning is triggered. The corresponding graded early warning system for the construction area will be activated based on the diagnostic results.

2. The construction cost monitoring method based on real-time assessment according to claim 1, characterized in that, The two types of physical verification parameters dynamically bound in step 1 include: The spatial displacement trajectory of the material is collected via RFID tags and UWB positioning base stations. The positioning data is mapped to three-dimensional grid coordinates according to the building information model partition coding. The rate of change in the visual inventory of materials was obtained through time-series image analysis using a fixed-view camera, specifically including: Perform material target segmentation on consecutive frame images and calculate the percentage reduction in pixel area per unit time. Infrared supplementary lighting is activated when the light intensity is below a threshold to ensure image recognition stability. The physical parameter weighting adjustment process is as follows: During the basic construction phase, the weight of the material spatial displacement trajectory is increased to the upper limit. During the decoration phase, the weight of personnel location hot zone distribution increases linearly with the progress completion rate; The weight training uses the correlation statistics between cost overrun events and physical parameters in historical projects.

3. The construction cost monitoring method based on real-time assessment according to claim 1, characterized in that, Step 2, which involves correcting the material loss coefficient based on real-time environmental sensor data, includes: The correction method for the material loss coefficient is as follows: Acquire real-time rainfall and wind speed sensor data; When rainfall exceeds the local historical average for the same period, the loss coefficient of mortar materials is adjusted upward according to the meteorological bureau's rainfall level. When the wind speed continuously exceeds the safe construction threshold, the loss coefficient of lightweight building materials increases non-linearly based on the derivative relationship of the wind resistance formula. The process of generating minute-level benchmark costs is as follows: Extract the design material usage from the current construction grid from the building information model; Baseline material cost = Design usage × (1 + Environmentally corrected loss factor) × Material unit price; Baseline mechanical cost = Scheduled machine shifts × Vibration effective duration percentage × Machine shift rate.

4. The construction cost monitoring method based on real-time assessment according to claim 1, characterized in that, The contradictory combinations of cross-validation physical parameters in step 3 include: Material-related contradiction verification: If the RFID display material is still in the original stacking area, but the rate of decrease in image recognition inventory exceeds twice the design value, it is judged as abnormal loss; If the material's spatial coordinates are moved to a non-work area and there is no construction instruction record, a theft warning will be triggered. Mechanical contradiction verification: The vibration sensor detected that the equipment amplitude continuously exceeded the operating threshold, but the data fluctuation value of the fuel flow meter was lower than the idle speed reference, which was determined to be a sensor failure; A sudden increase in equipment energy consumption, but the vibration intensity did not meet the standard, triggered a mechanical fault warning. The threshold for the number of consecutive exceedances is determined based on the standard deviation of the normal distribution of cost deviation rates for similar projects.

5. The construction cost monitoring method based on real-time assessment according to claim 1, characterized in that, The triggering methods for the tiered early warning include: Level 1 warning, audible and visual alarm: Triggering condition: The cost deviation rate of a single construction grid is greater than the dynamic threshold and continues for 3 detection cycles; Dynamic threshold = average deviation rate of similar projects + real-time environmental risk coefficient × standard deviation; Level 2 alert, mobile push notification: Triggering conditions: The contradictory combination of associated physical parameters is verified and the schedule delay rate is greater than the tolerance value; The push notification includes abnormal coordinates, physical parameter comparison charts, and a database of handling suggestions; The environmental risk coefficient is dynamically adjusted based on meteorological warning levels and geological monitoring data.

6. The construction cost monitoring method based on real-time assessment according to claim 2, characterized in that, The illumination compensation mechanism in the time-series image analysis includes: Real-time monitoring of illuminance values ​​using an ambient light sensor; When the illuminance is lower than the preset threshold, the infrared supplementary lighting device is controlled to enhance the illumination of a specific wavelength. Adaptive histogram equalization is performed on the compensated image to eliminate shadow interference.

7. The construction cost monitoring method based on real-time assessment according to claim 3, characterized in that, The process for determining the safe construction threshold is as follows: Obtain the maximum wind speed records for the construction site within the past ten years from the meteorological bureau's database; The critical value for equipment operation safety is derived by inversely calculating the wind load calculation formula in the building safety code. Increase the safety margin factor confirmed by the structural engineer.

8. The construction cost monitoring method based on real-time assessment according to claim 1, characterized in that, Also includes: Model self-optimization steps: After each construction phase is completed, the accuracy rate of physical parameters in cost deviation events is statistically analyzed. When the diagnostic accuracy of a certain parameter exceeds the confidence threshold for N consecutive diagnostic tests, its priority in the weighted model is increased. Update the environmental loss coefficient library: Write the ratio of actual loss value to predicted value into the new coefficient matrix.

9. A construction cost monitoring system based on real-time assessment, used to run the construction cost monitoring method based on real-time assessment as described in any one of claims 1-8, characterized in that, Includes the following interconnected modules: The dynamic mapping configuration module is used to establish the binding relationship between physical parameters and cost items, including: The cost item decomposition unit breaks down construction costs into three categories: material costs, machinery costs, and labor costs. The physical parameter binding unit configures two types of verification parameters for each type of cost item: Material costs are related to the spatial displacement trajectory of materials and the rate of change in the visual inventory of materials; Mechanical costs are related to the effective vibration duration of the equipment and the fluctuation value of the equipment energy consumption. Labor costs are related to the distribution of personnel location hot zones and the deviation of work time in each process. The weighted dynamic adjustment unit modifies the weights of physical parameters based on the construction phase, and the weight values ​​are generated through training on a historical database. The environment adaptive baseline generation module, which is data-connected to the dynamic mapping configuration module, includes: An environmental sensor interface is provided to receive real-time rainfall and wind speed data. The loss coefficient correction subunit adjusts the material loss coefficient in segments based on environmental data. The baseline calculation sub-unit calls the design quantities from the building information model to generate minute-level baseline costs. The multimodal diagnostic early warning module interacts with the environmental adaptive benchmark signal generation signal, including: The physical parameter discrepancy analysis unit executes when the cost deviation rate continuously exceeds the limit: Material trajectory-inventory contradiction detector, comparing displacement trajectory with visual inventory changes; Equipment vibration-energy consumption contradiction detector to verify the relationship between vibration duration and energy consumption fluctuation; The tiered early warning execution unit activates the alarm devices in the corresponding construction area based on the conflict detection results. Data bus architecture, the physical interface connecting each module: The positioning base station interface is connected to the UWB positioning base station via an RS485 bus; The image acquisition interface connects to a fixed-view camera via Ethernet; The warning output interface controls the audible and visual alarm via GPIO.

10. A construction cost monitoring system based on real-time assessment according to claim 9, characterized in that, The physical parameter binding unit includes the following sub-units: The material spatial displacement trajectory acquisition subunit consists of radio frequency tags deployed on building materials and UWB positioning base stations installed at the vertices of the construction grid. The base station coordinates are bound to the building information model partition coding. The material visual inventory change rate acquisition subunit consists of a dustproof infrared camera and a supplementary light controller. The supplementary light controller activates a specific band infrared light source based on the ambient light sensor data. The effective vibration duration acquisition subunit includes a triaxial vibration sensor mounted on the mechanical housing, whose signal conditioning circuit filters out non-operating frequency noise. The data bus architecture adds the following dedicated channels: Spatiotemporal alignment channel: An FPGA processor that converts positioning base station coordinates into BIM grid coordinates; Contradiction Analysis Acceleration Channel: A DSP chip used for image time series analysis and vibration energy consumption ratio calculation; Early warning feedback loop: The alarm device trigger signal is transmitted back to the CAN bus of the dynamic mapping configuration module.

Images