BIM collaborative construction site dust spray device dynamic optimization and construction application system

Abstract

The application relates to the technical field of construction site dust reduction, in particular to a BIM collaborative construction site dust reduction spraying device dynamic optimization and construction application system, which comprises an environment sensing module, a spraying decision module, an execution control module and an abnormal response module. The system generates a dynamic environment image by collecting environment parameters through a sensor network, optimizes a spraying coverage scheme in combination with a BIM model, and simultaneously detects abnormal accumulation points to generate a reinforcement instruction, while monitoring and adjusting the spraying effect in real time through a closed-loop control mechanism. The application can realize the precision, dynamic and energy saving of the construction site dust reduction, improve the construction environment quality and reduce resource consumption.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of construction site dust reduction, and particularly relates to a BIM collaborative construction site dust reduction spraying device dynamic optimization and construction application system. BACKGROUND

[0002] The increasing demand for construction site dust reduction has driven the widespread application of spraying dust reduction devices in construction environments. However, existing spraying dust reduction devices have certain limitations in intelligent control, dynamic optimization, and collaboration with construction management systems, making it difficult to meet the needs of modern construction sites for efficient and precise dust reduction. Through retrieval, a patent with publication number CN107869128B discloses a spraying dust reduction vehicle. This technology solves the safety problems of traditional dust reduction vehicles by setting a water baffle and a hydraulic cylinder to adjust the spraying angle, and improves the road dust reduction effect. However, this scheme mainly relies on manual operation or simple mechanical control, and has deficiencies in intelligent dynamic adjustment, making it difficult to optimize spraying parameters in real time according to the specific environment of the construction site (such as dust concentration, wind speed, humidity, etc.). In addition, this device does not involve collaborative work with construction management systems (such as BIM systems), and has certain limitations in the unified planning and execution of overall dust reduction strategies on the construction site.

[0003] On the other hand, a patent with publication number CN111570125B discloses a dust reduction spraying machine. This technology improves the coverage range and working efficiency of spraying dust reduction by setting an atomizer, a blowing fan, and a rotating mechanism, and reduces dead angles. However, this scheme still relies on preset spraying angles and fixed working modes, making it difficult to respond to dynamic changes in the construction site. At the same time, its control system fails to combine modern information technology (such as BIM models or Internet of Things sensors), leaving room for improvement in data-driven precise dust reduction and resource optimization. In addition, the complexity of the structure of this device may have an impact on maintenance costs and the promotion and application of small and medium-sized construction sites.

[0004] The above problems show that there is still significant room for improvement in the intelligent control, dynamic optimization, and collaboration with construction management systems of existing spraying dust reduction devices. Therefore, the present application proposes a BIM collaborative construction site dust reduction spraying device dynamic optimization and construction application system, which aims to realize the dynamic adjustment and optimization of dust reduction spraying devices by introducing BIM technology and intelligent algorithms, improve the dust reduction efficiency in construction environments while reducing resource consumption, and better meet the needs of modern construction sites for efficient, precise, and intelligent dust reduction. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to propose a BIM collaborative construction site dust reduction spraying device dynamic optimization and construction application system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a BIM-collaborative construction site dust suppression spray device dynamic optimization and construction application system, the system comprising:

[0007] The environmental perception module collects data based on a sensor network deployed on the construction site, including dust concentration, wind speed, humidity and temperature parameters. It combines real-time meteorological information and spatial distribution characteristics of the construction area to generate a dynamic environmental profile of the construction site.

[0008] The spray decision module, based on the dynamic environmental profile of the construction site, calls the construction progress node data and spatial zoning information in the BIM model to identify the dust diffusion trend and potential accumulation area in the current construction area. By constructing a spray coverage optimization model, it outputs spray angle, spray intensity and operation sequence instructions.

[0009] The execution control module drives the mechanical adjustment mechanism of the spray device to adjust the nozzle position according to the spray angle, spray intensity and operation sequence instructions, and controls the flow and pressure output of the spray pump. Combined with the real-time feedback loop to monitor the spray effect, a closed-loop control mechanism is formed.

[0010] The abnormal response module calls the real-time feedback data in the closed-loop control mechanism, extracts the particulate matter concentration change curve within the spray coverage area, analyzes the concentration fluctuation amplitude and frequency, detects abnormal accumulation points, and generates local enhanced spray commands.

[0011] As a further aspect of the present invention, the dynamic environmental profile of the construction site includes a dust concentration distribution map, a wind speed vector field map, and a humidity heat map; the spray angle includes a horizontal deflection angle and a vertical pitch angle; the spray intensity includes the spray volume per unit time and the atomized particle size distribution; the runtime sequence instructions include the start time, duration, and interval; and the localized enhanced spray instruction includes the target area number, execution priority, and spray mode switching.

[0012] As a further aspect of the present invention, the environment perception module includes:

[0013] The parameter acquisition submodule extracts raw signal data from dust sensors, anemometers, and thermometers based on the sensor network deployed on the construction site, and combines the data with timestamps and spatial coordinates to generate a multi-dimensional environmental parameter sequence.

[0014] The meteorological fusion submodule, based on the multi-dimensional environmental parameter sequence, calls the external meteorological service interface to obtain real-time meteorological forecast data, combines the surrounding topographic information of the construction site, simulates the wind flow path and humidity diffusion trend, and generates a meteorological environment prediction map of the construction site.

[0015] The spatial mapping submodule, based on the construction site meteorological environment prediction map, calls the spatial partition information of the BIM model, matches the environmental parameter sequence with the three-dimensional spatial structure of the construction site, and generates a dynamic environmental profile of the construction site.

[0016] As a further aspect of the present invention, the spray decision module includes:

[0017] The dust diffusion modeling submodule, based on the dynamic environmental profile of the construction site, extracts the dust concentration distribution map and wind speed vector field map, combines the boundary conditions of the construction area and the type of construction activities, and uses the finite element method to simulate the dust diffusion path and generate a dust diffusion trend map.

[0018] The accumulation area identification submodule, based on the dust diffusion trend map, calls the data on the location of construction material stacking and the operation trajectory of mechanical equipment in the BIM model to analyze the residence time and concentration gradient changes of dust in local areas and generate a list of potential accumulation areas.

[0019] The spray optimization submodule, based on the list of potential accumulation areas, calls the technical parameter library of the spray device, combines the spray angle, spray intensity and runtime sequence constraints, and uses a genetic algorithm to solve the spray coverage optimization model, outputting the spray angle, spray intensity and runtime sequence instructions.

[0020] As a further aspect of the present invention, the execution control module includes:

[0021] The mechanical adjustment submodule, based on the spray angle command, drives the servo motor of the spray device to adjust the horizontal deflection angle and vertical pitch angle of the nozzle, and combines the angle sensor to monitor the nozzle position deviation in real time and generate an angle correction signal.

[0022] The flow control submodule, based on the injection intensity command, calls the frequency converter of the injection pump to adjust the pump body flow and pressure output, and generates a flow correction signal by combining the feedback signals from the flow meter and pressure sensor;

[0023] The effect monitoring submodule, based on the angle correction signal and flow correction signal, calls the particulate matter concentration sensor to collect the particulate matter concentration change curve in real time within the spray coverage area, and generates a spray effect evaluation report by combining the concentration gradient distribution map and the spray coverage area.

[0024] As a further aspect of the present invention, the anomaly response module includes:

[0025] The concentration fluctuation analysis submodule extracts the particulate matter concentration change curve based on the spray effect evaluation report, calculates the concentration fluctuation amplitude and frequency, and generates a concentration anomaly markers by combining the preset fluctuation threshold range.

[0026] The accumulation point detection submodule, based on the concentration anomaly markers, calls the dust concentration distribution map and wind speed vector field map in the dynamic environmental profile of the construction site, analyzes the spatial distribution characteristics and temporal evolution of the concentration anomaly area, and generates a list of abnormal accumulation points.

[0027] The enhanced instruction generation submodule, based on the list of abnormal accumulation points, calls the spray coverage optimization model of the spray optimization submodule, and generates local enhanced spray instructions by combining the target area number and execution priority constraints.

[0028] As a further aspect of the present invention, the system further includes:

[0029] The resource optimization module, based on the local enhanced spray command, calls the historical operation records and energy consumption data of the spray device, extracts the relationship curve between spray intensity and energy consumption, and generates an energy-saving operation strategy for the spray device in combination with the site's power supply constraints.

[0030] The energy-saving operation strategy includes energy consumption optimization curves, operation mode switching rules, and equipment maintenance cycles.

[0031] As a further aspect of the present invention, the resource optimization module includes:

[0032] The energy consumption analysis submodule extracts the product of spray intensity and spray time based on the local enhanced spray command, and generates a real-time energy consumption estimate of the spray device by combining the rated power and efficiency curve of the spray pump.

[0033] The mode optimization submodule, based on the real-time energy consumption estimate, calls the load distribution map of the construction site power supply system, and combines the operation priority of the spraying device with the construction progress node data to generate operation mode switching rules;

[0034] The maintenance planning submodule, based on the aforementioned operating mode switching rules, calls the component life database of the spraying device and combines it with the failure rate statistics in historical operating records to generate an equipment maintenance cycle table.

[0035] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0036] In this invention, by combining environmental sensing technology with real-time meteorological data, the system can intelligently adjust the operating status of the spraying device according to environmental changes. It dynamically optimizes the spraying effect based on environmental parameters, ensuring precise and efficient dust suppression and reducing unnecessary resource waste. The system can adjust the spray angle and intensity according to construction progress and spatial zoning information to maximize the dust suppression effect in each area. A closed-loop feedback mechanism ensures real-time monitoring and optimization of the spraying effect, rapid response to abnormal situations, and the implementation of enhanced measures to ensure that the air quality at the construction site meets standards. Intelligent energy management further improves the system's energy efficiency, meets the needs of efficient and precise dust suppression, and promotes the sustainable development of the construction environment. Attached Figure Description

[0037] Figure 1 This is a system flowchart of the present invention;

[0038] Figure 2 This is a flowchart illustrating the acquisition process of the environmental perception module of the present invention.

[0039] Figure 3 This is a flowchart illustrating the acquisition process of the spray decision module of the present invention;

[0040] Figure 4 This is a flowchart illustrating the acquisition process of the control module in this invention.

[0041] Figure 5 This is a flowchart illustrating the acquisition process of the anomaly response module of the present invention.

[0042] Figure 6 This is a flowchart illustrating the acquisition process of the resource optimization module of this invention. Detailed Implementation

[0043] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0044] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0045] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0046] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0047] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0048] Please see Figure 1 This invention provides a technical solution: a BIM-based collaborative construction site dust suppression spray device dynamic optimization and construction application system, the system comprising:

[0049] The environmental perception module collects data based on a sensor network deployed on the construction site, including dust concentration, wind speed, humidity and temperature parameters. It combines real-time meteorological information and spatial distribution characteristics of the construction area to generate a dynamic environmental profile of the construction site.

[0050] The spraying decision module, based on the dynamic environmental profile of the construction site, calls the construction progress node data and spatial zoning information in the BIM model to identify the dust diffusion trend and potential accumulation areas in the current construction area. By constructing a spraying coverage optimization model, it outputs the spraying angle, spraying intensity and operation sequence instructions.

[0051] The execution control module drives the mechanical adjustment mechanism of the spray device to adjust the nozzle position according to the spray angle, spray intensity and operation sequence commands, and controls the flow and pressure output of the spray pump. Combined with the real-time feedback loop to monitor the spray effect, a closed-loop control mechanism is formed.

[0052] The abnormal response module calls the real-time feedback data in the closed-loop control mechanism, extracts the particulate matter concentration change curve within the spray coverage area, analyzes the concentration fluctuation amplitude and frequency, detects abnormal accumulation points, and generates local enhanced spray instructions.

[0053] The resource optimization module, based on the local enhanced spray command, calls the historical operation records and energy consumption data of the spray device, extracts the relationship curve between spray intensity and energy consumption, and generates an energy-saving operation strategy for the spray device by combining the site's power supply constraints.

[0054] The dynamic environmental profile of the construction site includes a dust concentration distribution map, a wind speed vector field map, and a humidity heat map. The spray angle includes horizontal deflection angle and vertical pitch angle. The spray intensity includes the spray volume per unit time and the atomized particle size distribution. The operation sequence instructions include the start time, duration, and interval. The local enhanced spray instructions include the target area number, execution priority, and spray mode switching. The energy-saving operation strategy includes energy consumption optimization curves, operation mode switching rules, and equipment maintenance cycles.

[0055] Please see Figure 2 The environmental perception module includes:

[0056] The parameter acquisition submodule extracts raw signal data from dust sensors, anemometers, and thermometers based on the sensor network deployed on the construction site, and combines the data with timestamps and spatial coordinates to generate a multi-dimensional environmental parameter sequence.

[0057] Based on a sensor network deployed at the construction site, raw signal data from dust sensors, anemometers, and thermometers / hygrometers were extracted. Data was then labeled using timestamps and spatial coordinates. First, for the PM2.5 dust sensor PS001, located at coordinates (15.5, 30.2, 5.0) in the BIM model, the raw signal collected at a starting timestamp T0 was a voltage signal of 2.85V. The voltage-concentration conversion formula C = k × V + b, pre-defined for this type of sensor, was used for conversion. The values ​​of the conversion coefficient k and the offset b were determined based on calibration experiments conducted on this sensor. These experiments involved placing the sensor in a standard experimental chamber at 50 μg / m³ concentrations. 3 150μg / m 3 300μg / m 3 500μg / m 3 Under standard particulate matter concentration conditions, the output voltage was recorded. Specific data are shown in Table 1. Linear regression analysis of the data in Table 1 determined the conversion coefficient k to be 195.3 and the offset b to be -56.8. Therefore, the current dust concentration is 195.3 × 2.85V - 56.8 = 499.7 μg / m³. 3 Subsequently, an anemometer at the same location, numbered WS001, was used. Its pulse frequency signal, collected at the same timestamp, was 32Hz. The pulse-wind speed conversion relationship v = 0.1 × f (where the coefficient 0.1 was calibrated by the wind tunnel experiment) was applied, calculating the wind speed to be 3.2 m / s. The wind direction was calibrated to 225°. Finally, a hygrometer at the same location, numbered THS001, was used. Its temperature was 28.5℃ and relative humidity was 75%. The calculated and collected data were then bound to the timestamp and spatial coordinates (15.5, 30.2, 5.0) to form the data node [T0, (15.5, 30.2, 5.0), 499.7 μg / m 3 [3.2m / s, 225°, 28.5°C, 75%], the above data extraction, transformation and labeling process is repeated for all 15 sensor nodes in the network in 12 consecutive sampling cycles (one cycle every 5 seconds) to generate a multidimensional environmental parameter sequence.

[0058] Table 1: Sensor Calibration Experiment Data Table

[0059] Standard concentration (pg / m 3 )]]> Output voltage (V) 50 0.55 150 1.06 300 1.83 500 2.85

[0060] As shown in Table 1, this table lists the calibration experimental data used to determine the voltage-concentration conversion relationship of the sensor.

[0061] The meteorological fusion submodule, based on a multi-dimensional environmental parameter sequence, calls an external meteorological service interface to obtain real-time meteorological forecast data, combines the surrounding topographic information of the construction site, simulates the wind flow path and humidity diffusion trend, and generates a meteorological environment prediction map of the construction site.

[0062] Based on a multidimensional environmental parameter sequence, 60 seconds after the start timestamp T0, an external meteorological service interface is invoked to obtain macro-meteorological forecast data for the area where the construction site is located (longitude 116.3, latitude 39.9). This data shows that the prevailing wind direction for the next hour is southwest at 220°, with a wind speed of 2.5 m / s and a relative humidity of 80%. The sensor node data closest to the current timestamp is extracted from the multidimensional environmental parameter sequence, for example, the data at sensor PS001 [3.2 m / s, 225°]. The weight W of the on-site sensor data is set. local Weighted by external meteorological data W ext The reference standard for setting the weights is the distance d between the prediction point and the sensor, and the weight W is... local =1-(d / D) max ) 0.5 D max Given the maximum diagonal length of the construction site, set to 200m, for a prediction point P1 located 10m away from the PS001 sensor, its W... local =1-(10 / 200) 0.5 ≈0.776, then W ext =1-0.776=0.224. The combined wind speed at prediction point P1 is calculated as 3.2m / s×0.776+2.5m / s×0.224=3.04m / s, and the combined wind direction is 225°×0.776+220°×0.224=223.88°. Next, information about the surrounding terrain from the BIM model is retrieved, identifying a 30m high building under construction along the predicted wind flow path. For a building (coordinate range X:[50,70], Y:[20,30]), when the simulated wind field streamline travels within 5m of the windward side of the building, the wind speed vector in this area is multiplied by a damping coefficient of 0.4, and the wind direction vector is deflected by 15° in the direction perpendicular to the building surface. By repeatedly performing the above weight fusion and terrain correction calculation on all points in the entire construction site grid (grid resolution 2mx2m), a construction site meteorological environment prediction map is generated.

[0063] The spatial mapping submodule, based on the construction site meteorological environment prediction map, calls the spatial partition information of the BIM model, matches the environmental parameter sequence with the three-dimensional spatial structure of the construction site, and generates a dynamic environmental profile of the construction site.

[0064] Based on the site's meteorological environment forecast map, the spatial zoning information of the BIM model was used. This information divided the site into Zone A (earthwork excavation zone), Zone B (rebar processing zone), and Zone C (material storage zone). 65 seconds after the start timestamp T0, dust concentration data from three sensors (PS002, PS003, and PS004) in Zone A were extracted from the multidimensional environmental parameter sequence, showing a concentration of 510.2 μg / m³. 3 580.5 μg / m 3 555.8 μg / m 3 The average dust concentration in this area is calculated to be (510.2 + 580.5 + 555.8) / 3 = 548.8 μg / m³. 3 This average concentration value is assigned to the corresponding three-dimensional spatial volume in area A. Simultaneously, wind speed vector field data for area A is extracted from the site's meteorological environment prediction map, revealing an average wind speed of 2.8 m / s and a wind direction of 230°. This wind speed and direction information is also assigned to the three-dimensional spatial volume in area A. The same environmental parameter matching process is repeated for areas B and C. For example, the average concentration matched for area B is 120.3 μg / m³. 3 The average wind speed was 1.5 m / s, the wind direction was 215°, and the average concentration matched in area C was 250.6 μg / m³. 3 With an average wind speed of 1.8 m / s and a wind direction of 220°, a dynamic environmental profile of the construction site is generated by matching and assigning values ​​to the real-time environmental parameters of all zones with the three-dimensional spatial structure in the BIM model one by one.

[0065] Please see Figure 3 The spray decision module includes:

[0066] The dust diffusion modeling submodule extracts dust concentration distribution maps and wind speed vector field maps based on the dynamic environmental profile of the construction site. Combining the boundary conditions of the construction area and the type of construction activities, it uses the finite element method to simulate the dust diffusion path and generate a dust diffusion trend map.

[0067] Based on the dynamic environmental profile of the construction site generated by the aforementioned steps, the dust concentration distribution map of Area A (earthwork excavation area) was extracted, with an average concentration of 548.8 μg / m³. 3The BIM model was used to obtain the geometric boundary conditions of area A, which was set as an open space with dimensions of 50m x 30m x 10m. The current construction activity type was determined to be "excavator loading operation," which is associated with a dust source strength parameter set to 1.5g / s. Area A was divided into 2m x 2m x 2m grid cells. For each grid cell, fluid dynamics calculations were performed based on the Navier-Stokes equations, coupled with particle transport equations. The wind speed vector field was used as input to calculate the dust flux between cells. Specifically, for two adjacent cells i and j, the dust flux F between them was calculated. ij Through the concentration difference at the unit center (C) i -C j ), interface area A ij And the diffusion coefficient D (determined from a table based on temperature and particle size, taken as 0.02m here). 2 The calculation is performed by multiplying the advection term caused by the wind speed vector field by 0.1s. After 300 iterations with a time step of 0.1s, the spatial distribution of dust concentration in the entire area A within the next 30s is obtained, and a dust diffusion trend map is generated.

[0068] The accumulation area identification submodule, based on the dust diffusion trend map, calls the data on the location of construction materials and the operation trajectory of mechanical equipment in the BIM model to analyze the residence time and concentration gradient changes of dust in local areas and generate a list of potential accumulation areas.

[0069] The dust diffusion trend map shows a high concentration area at the downwind location of area A (coordinates X:[40,50], Y:[0,10]), with a concentration value of 600 μg / m³. 3 Up to 750 μg / m 3 During this process, data on the location of construction material stockpiles from the BIM model was retrieved, identifying a bare soil stockpile point with coordinates (45, 5, 0) within the area. Furthermore, data on the movement of machinery was collected, revealing that an excavator (equipment number EX01) traversed this high-concentration area from t-10s to time t. The concentration gradient change within this area was analyzed, and the concentration values ​​at the center point (45, 5, 2) and eight surrounding points were extracted. The modulus of the concentration gradient was calculated, with the gradient at the center point being 5 μg / m². 4 The gradient at points outside the region is 50 μg / m². 4 When the concentration gradient modulus is less than the threshold of 10 μg / m 4 And the concentration value is higher than the threshold of 500 μg / m 3 When this time, mark the area as a retention zone and calculate the retention time T. retentionT is obtained by dividing the characteristic length of the area (10m) by the local average wind speed (1.2m / s, obtained from the dust diffusion trend map). retention =10m / 1.2m / s=8.33s. This value is greater than the residence time threshold of 5s. Therefore, this area is identified as a potential accumulation area and added to the list. This analysis process is repeated for the entire diffusion trend map to generate a list of potential accumulation areas.

[0070] Table 2: List of Potential Accumulation Areas

[0071] Region number Center coordinates Average concentration (pg / m 3 )]]> Priority PA-01 (45,5,2) 680 1 PA-02 (12,45,3) 515 2 PA-03 (25,18,1) 490 3

[0072] As shown in Table 2, this table lists the potential dust accumulation areas and their key attributes generated after analysis.

[0073] The spray optimization submodule, based on the list of potential accumulation areas, calls the technical parameter library of the spray device, combines the spray angle, spray intensity and runtime sequence constraints, and uses a genetic algorithm to solve the spray coverage optimization model, outputting the spray angle, spray intensity and runtime sequence instructions;

[0074] Based on the list of potential accumulation areas, the highest priority area PA-01 was selected as the target, with its center coordinates at (45, 5, 2). The technical parameter library of the spray device (number SP01, located at coordinates (35, 5, 8)) was accessed. This library contains data such as the relationship between spray distance and pressure, spray cone angle, and rated power. The constraints for the spray angle were set as follows: horizontal deflection angle θ within [0°, 90°], vertical pitch angle φ within [-45°, 0°], and spray intensity (characterized by pressure P). At a pressure of [1.0 MPa, 3.0 MPa], with a runtime sequence (characterized by duration t) of [5 s, 30 s], an initial population containing 50 parameter combinations is generated. For example, individual 1 has parameters [θ = 30°, φ = -20°, P = 2.2 MPa, t = 15 s], and individual 2 has parameters [θ = 45°, φ = -15°, P = 1.8 MPa, t = 20 s]. For each individual, its fitness score F is calculated as F = w1 × R. cov -w2×E cost The coverage rate R cov The energy consumption E is obtained by simulating the percentage of the geometric intersection area between the spray jet trajectory and the PA-01 region under these parameters relative to the total area of ​​PA-01. cost The power value is obtained by finding the corresponding power value from the pressure-power curve in the technical parameter database based on pressure P and multiplying it by time t. Weights w1 and w2 are set according to the importance of dust reduction efficiency and energy saving; here, based on historical data analysis, w1 = 0.7 and w2 = 0.3 are set. After calculation, the R of individual 1... cov1 =85%, E cost1=1.2kWh, then F1 = 0.7 × 0.85 - 0.3 × 1.2 = 0.235, R for individual 2 cov2 =95%, E cost2 =1.5kWh, then F2 = 0.7 × 0.95 - 0.3 × 1.5 = 0.215. Select the top 20% (i.e., 10) of individuals with the highest fitness scores to enter the next generation. Through crossover (e.g., new θ = parent 1θ × 0.6 + parent 2θ × 0.4) and mutation (e.g., new P = old P + random value [-0.1, 0.1]) operations on the parameters of these 10 individuals, generate 40 new individuals. Together with the 10 superior individuals retained, they form a new population of 50. Repeat this selection, crossover, and mutation process for 100 generations, or stop iterating when the optimal fitness score changes by less than 1% for 10 consecutive generations. Select the parameter combination corresponding to the individual with the highest final fitness as the output spray angle [θ = 35°, φ = -18°], spray intensity 2.0MPa, and runtime sequence 18s command.

[0075] Please see Figure 4 The control module includes:

[0076] The mechanical adjustment submodule, based on the spray angle command, drives the servo motor of the spray device to adjust the horizontal deflection angle and vertical pitch angle of the nozzle, and combines the angle sensor to monitor the nozzle position deviation in real time and generate an angle correction signal.

[0077] Based on the spray angle command [θ = 35°, φ = -18°], the horizontal servo motor (number HM01) and vertical servo motor (number VM01) of the spray device SP01 are driven. The servo motor controller converts the target angles of 35° and -18° into the required number of pulses and sends them to the two motor drivers respectively. The motors start to rotate. At the same time, the angle encoder (resolution 0.01°) mounted coaxially with the motors begins to report the current angle value in real time. For example, at t = 0.5s, the horizontal angle encoder reading is 25.5° and the vertical angle encoder reading is -12°. The controller calculates the deviation between the current angle and the target angle. The horizontal deviation is 35° - 25.5° = 9.5°, and the vertical deviation is -18° - (-12.1°) = -5.9°. Based on this deviation value, the PID controller algorithm calculates the adjusted pulse frequency and sends it to the motor driver. When the real-time position deviation detected by the angle sensor is less than the preset threshold of 0.1°, the controller stops sending pulses and generates an angle correction signal, which is marked as [Angle_Lock_H:OK,Angle_Lock_V:OK].

[0078] The flow control submodule, based on the injection intensity command, calls the frequency converter of the injection pump to adjust the pump body flow and pressure output, and generates a flow correction signal by combining the feedback signals from the flow meter and pressure sensor;

[0079] Based on the injection intensity command of 2.0 MPa, the variable frequency controller (VFD01) of the injection pump (PMP01) is activated. This controller has a pre-stored table showing the correspondence between output pressure and inverter output frequency. Referring to the table, it is found that to achieve an outlet pressure of 2.0 MPa, the inverter needs to output a frequency of 45.0 Hz. The controller then sends a 45.0 Hz frequency command to the inverter, and the injection pump begins to accelerate. Simultaneously, the pressure sensor (PRS01) and flow meter (FLM01) installed on the injection pump outlet pipe begin to provide real-time feedback signals. At t = 1.0 s, the pressure sensor reading is 1.8 MPa, and the flow meter reading is 5.5 m³ / s. 3 The controller calculates a pressure deviation of 2.0 - 1.8 = 0.2 MPa per hour. Based on this deviation, the PID controller calculates a frequency increment of +1.5 Hz and sends the new target frequency of 46.5 Hz to the inverter. When the feedback signal value from the pressure sensor stabilizes within the range of 2.0 ± 0.05 MPa for more than 1 second, the controller locks the current frequency and generates a flow correction signal, labeled [Pressure_Lock:OK,Flow_Rate:6.0m]. 3 / h).

[0080] The effect monitoring submodule, based on the angle correction signal and the flow correction signal, calls the particulate matter concentration sensor to collect the particulate matter concentration change curve in real time within the spray coverage area, and combines the concentration gradient distribution map and the spray coverage area to generate a spray effect evaluation report;

[0081] Based on the angle correction signal [Angle_Lock_H:OK,Angle_Lock_V:OK] and the flow correction signal [Pressure_Lock:OK,Flow_Rate:6.0m] 3 After confirmation of all parameters, the spraying device began spraying according to an 18-second operating sequence. Simultaneously, the particulate matter concentration sensor PS008, located at the center point (45,5,2) of the target area PA-01, was activated to collect the particulate matter concentration change curve within the spray coverage area in real time at a frequency of 1Hz. The collected data sequence is [t=0s, 680.1; t=1s, 110.8; t=2s, 590.2; ...; t=18s, 110.8; t=19s, 112.3; ...]. The average dust reduction rate during the entire 18-second spraying process was calculated as (680.1-110.8) / 680.1×100%=83.7%. A gradient distribution diagram of concentration change over time was plotted. It was assumed that the fastest rate of concentration decrease was observed between t=10s and t=15s, with a slope of -45.0μg / (m³). 3Based on the BIM model and the technical parameters of the spraying device, the theoretical spray coverage area was calculated to be 85m². 2 By analyzing data from two additional auxiliary sensors, PS009 and PS010, the actual effective coverage area was assessed to be 78m. 2 The actual coverage rate reached 91.8% of the theoretical value. Based on the above data such as dust reduction rate, concentration gradient, and coverage area, a spray effect evaluation report was generated.

[0082] Please see Figure 5 The exception response module includes:

[0083] The concentration fluctuation analysis submodule extracts the particulate matter concentration change curve based on the spray effect evaluation report, calculates the concentration fluctuation amplitude and frequency, and generates concentration anomaly markers by combining the preset fluctuation threshold range.

[0084] Extract the particulate matter concentration change curve data within 30 seconds from the spray effect evaluation report, and calculate the first-order difference sequence of the curve to obtain the concentration fluctuation value. For example, the concentration is 112.3 μg / m³ at t = 19 seconds. 3 The concentration at t = 20 s was 125.6 μg / m³. 3 The fluctuation value was +13.3 μg / m 3 The standard deviation of the fluctuation value over the entire 30s period was calculated, and the fluctuation amplitude was found to be 15.8 μg / m. 3 The normal threshold range for concentration fluctuation is set as [0, 10 μg / m³]. 3 The threshold is set based on the following: after a stable dust suppression spraying process without significant external disturbances (such as sudden gusts of wind or new dust sources), the concentration reading should tend to stabilize. Historical data shows that the standard deviation of fluctuations under this stable state usually does not exceed 10 μg / m³. 3 The calculated fluctuation range is 15.8 μg / m 3 Since the concentration exceeded the threshold range, the data for this time period was marked as an anomaly. At the same time, a Fast Fourier Transform (FFT) analysis was performed on the concentration curve to calculate its spectrum. A significant frequency component of 0.2 Hz was found, while the normal fluctuation frequency should be below 0.05 Hz. This high-frequency component was also regarded as an anomaly, and a concentration anomaly label [Timestamp:T0+115s,Type:Amplitude_Exceeded,Value:15.8] was generated.

[0085] The accumulation point detection submodule, based on concentration anomaly markers, calls the dust concentration distribution map and wind speed vector field map in the dynamic environmental profile of the construction site to analyze the spatial distribution characteristics and temporal evolution of concentration anomaly areas and generate a list of abnormal accumulation points.

[0086] Based on the generated concentration anomaly markers, the time period of the anomaly was identified as 115 to 130 seconds after the start timestamp T0. The corresponding dynamic environmental profile of the construction site was retrieved, and the dust concentration distribution map and wind speed vector field map near the PA-01 area were extracted. It was found that the concentration value in the northeast corner of this area (coordinates X:[48,50], Y:[8,10]) increased from 120 μg / m³. 3 Rebound to 250 μg / m 3 It forms a concentration of 130 μg / m² with the surrounding area. 3 The concentration difference, along with the wind speed vector field map, showed that a gust of 3.5 m / s blew in from an unclosed construction passage (coordinates X:55, Y:9), causing a local vortex to form in that corner. This prevented the dust from effectively settling or dispersing, instead confining it to a small area where it circulated and accumulated. By comparing the concentration distribution map evolution over 15 consecutive seconds, it was confirmed that the high concentration point (center (49,9,2)) was spatially persistent and showed an oscillating upward trend in concentration. Therefore, it was identified as an abnormal accumulation point, and its information was added to the list. The list item is [ID:AP-001,Center_Coord:(49,9,2),Cause:Wind_Gust_Vortex,Peak_Concentration:255μg / m 3 Generate a list of abnormal accumulation points.

[0087] The enhanced instruction generation submodule, based on the list of abnormal accumulation points, calls the spray coverage optimization model of the spray optimization submodule, and generates local enhanced spray instructions by combining the target area number and execution priority constraints.

[0088] Information about accumulation point AP-001 in the list of abnormal accumulation points is extracted. Its target area number is AP-001, and its center coordinates are (49,9,2). Its execution priority is set to the highest (Priority=1) because it is a sudden high concentration point and must be dealt with immediately. The spray coverage optimization model in the spray optimization submodule is called again, but the constraints of the calculation have changed this time. The target area is reduced to a 5m x 5m area centered at (49,9,2), and the coverage weight w1 is set to 0.9 and the energy consumption weight w2 is set to 0.1. The iterative optimization process is re-executed. Under the new weights and target area constraints, a new set of spray parameters is obtained. The parameters are spray angle [θ=48°, φ=-15°], spray intensity 2.5MPa, and runtime sequence 10s. This is the local enhanced spray command for this abnormal accumulation point.

[0089] Please see Figure 6 The resource optimization module includes:

[0090] The energy consumption analysis submodule extracts the product of spray intensity and spray time based on the local enhanced spray command, and generates a real-time energy consumption estimate of the spray device by combining the rated power and efficiency curve of the spray pump.

[0091] Extract the spray intensity of 2.5 MPa and the spray time of 10 s from the local enhanced spray command. Call the technical parameter library of the spray pump PMP01 to find its rated power and efficiency curve. When the outlet pressure is 2.5 MPa, the input power of the spray pump is found to be 15 kW and its operating efficiency is 85%. Therefore, its actual power consumption is 15 kW / 0.85 = 17.65 kW. Multiply this power value by the spray time of 10 s (i.e., 10 / 3600 hours) to calculate the estimated real-time energy consumption of this enhanced spray: 17.65 kW × (10 / 3600) h ≈ 0.049 kWh. Record this energy consumption value together with the command timestamp and equipment number SP01 to generate the estimated real-time energy consumption of the spray device.

[0092] The mode optimization submodule, based on real-time energy consumption estimates, calls the load distribution map of the construction site's power supply system, and combines the operating priority of the spraying device with construction progress node data to generate operating mode switching rules;

[0093] Based on the real-time energy consumption estimate of 0.049 kWh, the load distribution map of the construction site's power supply system is retrieved. The map shows that the current total power load of the construction site is 350 kW, which has reached 87.5% of the total transformer capacity of 400 kW, belonging to a high load period. The criterion for judging a high load period is that the total load exceeds 80% of the rated capacity. The operation priority and construction progress node data of the spraying device are retrieved. The current construction progress is "main structure construction". The priority of dust control is set to "high". Therefore, even during the high power load period, the dust suppression system still needs to operate, but the system switches to "energy saving mode". In this mode, all non-urgent spraying requests (such as routine wet curing) will be suspended or postponed. For "high" priority instructions, such as the local enhanced spraying in this case, the system will automatically increase the energy consumption weight w2 by 20% (i.e., from 0.1 to 0.12) and re-perform a quick optimization calculation to find a slightly lower energy consumption execution plan within an acceptable range. This is the operation mode switching rule.

[0094] The maintenance plan submodule, based on the operation mode switching rules, calls the component life database of the spraying device and combines it with the failure rate statistics in the historical operation records to generate the equipment maintenance cycle table;

[0095] Based on the operating mode switching rules, the system records the event of switching from "normal mode" to "energy-saving mode" and accumulates the total operating time under "energy-saving mode". It calls the component life database of the spray device SP01, which records the theoretical life of the seals of the jet pump PMP01 under different outlet pressures. The relevant data can be found in Table 3.

[0096] Table 3: Reference Table for the Service Life of Jet Pump Seals

[0097]

[0098]

[0099] As shown in Table 3, this table provides component life data as a reference for the maintenance plan. By calling historical operation records, the cumulative operating time of PMP01 in each pressure range is calculated, and combined with failure rate statistics, for example, the data shows that when the cumulative wear of the seals (calculated by weighting the operating time under different pressures) reaches 80% of the theoretical life, the failure rate will rise from 1% to 5%. The maintenance threshold is set to 80% of the theoretical life. Based on the current cumulative operating time and the operating time in each pressure range, the system predicts the time point when the maintenance threshold will be reached. For example, it predicts that 80% of the wear life will be reached in 25 days. Therefore, the system automatically generates a maintenance instruction: "Please replace the seals of the jet pump PMP01 of equipment SP01 within the next 25 days" and adds this instruction to the equipment maintenance cycle table.

[0100] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A BIM-based collaborative system for dynamic optimization and construction application of dust suppression spray devices at construction sites, characterized in that... The system includes: The environmental perception module collects data based on a sensor network deployed on the construction site, including dust concentration, wind speed, humidity and temperature parameters. It combines real-time meteorological information and spatial distribution characteristics of the construction area to generate a dynamic environmental profile of the construction site. The spraying decision module, based on the dynamic environmental profile of the construction site, calls the construction progress node data and spatial zoning information in the BIM model to identify the dust diffusion trend and potential accumulation area in the current construction area. By constructing a spraying coverage optimization model, it outputs spraying angle instructions, spraying intensity instructions and runtime sequence instructions. The spray decision module includes: The dust diffusion modeling submodule, based on the dynamic environmental profile of the construction site, extracts the dust concentration distribution map and wind speed vector field map, combines the boundary conditions of the construction area and the type of construction activities, and uses the finite element method to simulate the dust diffusion path and generate a dust diffusion trend map. The accumulation area identification submodule, based on the dust diffusion trend map, calls the data on the location of construction material stacking and the operation trajectory of mechanical equipment in the BIM model to analyze the residence time and concentration gradient changes of dust in local areas and generate a list of potential accumulation areas. The spray optimization submodule, based on the list of potential accumulation areas, calls the technical parameter library of the spray device, combines the spray angle, spray intensity and runtime sequence constraints, and uses a genetic algorithm to solve the spray coverage optimization model, outputting the spray angle, spray intensity and runtime sequence instructions; The execution control module drives the mechanical adjustment mechanism of the spray device to adjust the nozzle position according to the spray angle, spray intensity and operation sequence instructions, and controls the flow and pressure output of the spray pump. Combined with the real-time feedback loop to monitor the spray effect, a closed-loop control mechanism is formed. The execution control module includes: The mechanical adjustment submodule, based on the spray angle command, drives the servo motor of the spray device to adjust the horizontal deflection angle and vertical pitch angle of the nozzle, and combines the angle sensor to monitor the nozzle position deviation in real time and generate an angle correction signal. The flow control submodule, based on the injection intensity command, calls the frequency converter of the injection pump to adjust the pump body flow and pressure output, and generates a flow correction signal by combining the feedback signals from the flow meter and pressure sensor; The effect monitoring submodule, based on the angle correction signal and flow correction signal, calls the particulate matter concentration sensor to collect the particulate matter concentration change curve in real time within the spray coverage area, and generates a spray effect evaluation report by combining the concentration gradient distribution map and the spray coverage area. The abnormal response module calls the real-time feedback data in the closed-loop control mechanism, extracts the particulate matter concentration change curve within the spray coverage area, analyzes the concentration fluctuation amplitude and frequency, detects abnormal accumulation points, and generates local enhanced spray instructions. The localized enhanced spray command includes the target area number, execution priority, and spray mode switching; The anomaly response module includes: The concentration fluctuation analysis submodule extracts the particulate matter concentration change curve based on the spray effect evaluation report, calculates the concentration fluctuation amplitude and frequency, and generates a concentration anomaly markers by combining the preset fluctuation threshold range. The accumulation point detection submodule, based on the concentration anomaly markers, calls the dust concentration distribution map and wind speed vector field map in the dynamic environmental profile of the construction site, analyzes the spatial distribution characteristics and temporal evolution of the concentration anomaly area, and generates a list of abnormal accumulation points. The enhanced instruction generation submodule, based on the list of abnormal accumulation points, calls the spray coverage optimization model of the spray optimization submodule, and generates local enhanced spray instructions by combining the target area number and execution priority constraints.

2. The BIM collaborative construction site dust suppression spray device dynamic optimization and construction application system according to claim 1, characterized in that: The dynamic environmental profile of the construction site includes a dust concentration distribution map, a wind speed vector field map, and a humidity thermal map. The spray angle includes a horizontal deflection angle and a vertical pitch angle. The spray intensity includes the spray volume per unit time and the atomized particle size distribution. The operation sequence instructions include the start time, duration, and interval.

3. The BIM collaborative construction site dust suppression spray device dynamic optimization and construction application system according to claim 1, characterized in that, The environment sensing module includes: The parameter acquisition submodule extracts raw signal data from dust sensors, anemometers, and thermometers based on the sensor network deployed on the construction site, and combines the data with timestamps and spatial coordinates to generate a multi-dimensional environmental parameter sequence. The meteorological fusion submodule, based on the multi-dimensional environmental parameter sequence, calls the external meteorological service interface to obtain real-time meteorological forecast data, combines the surrounding topographic information of the construction site, simulates the wind flow path and humidity diffusion trend, and generates a meteorological environment prediction map of the construction site. The spatial mapping submodule, based on the construction site meteorological environment prediction map, calls the spatial partition information of the BIM model, matches the environmental parameter sequence with the three-dimensional spatial structure of the construction site, and generates a dynamic environmental profile of the construction site.

4. The BIM collaborative construction site dust suppression spray device dynamic optimization and construction application system according to claim 1, characterized in that, The system also includes: The resource optimization module, based on the local enhanced spray command, calls the historical operation records and energy consumption data of the spray device, extracts the relationship curve between spray intensity and energy consumption, and generates an energy-saving operation strategy for the spray device in combination with the site's power supply constraints. The energy-saving operation strategy includes energy consumption optimization curves, operation mode switching rules, and equipment maintenance cycles.

5. The BIM collaborative construction site dust suppression spray device dynamic optimization and construction application system according to claim 4, characterized in that, The resource optimization module includes: The energy consumption analysis submodule extracts the product of spray intensity and spray time based on the local enhanced spray command, and generates a real-time energy consumption estimate of the spray device by combining the rated power and efficiency curve of the spray pump. The mode optimization submodule, based on the real-time energy consumption estimate, calls the load distribution map of the construction site power supply system, and combines the operation priority of the spraying device with the construction progress node data to generate operation mode switching rules; The maintenance planning submodule, based on the aforementioned operating mode switching rules, calls the component life database of the spraying device and combines it with the failure rate statistics in historical operating records to generate an equipment maintenance cycle table.

Images