An intelligent monitoring platform and method for construction dust

Abstract

The application discloses a kind of construction dust intelligent monitoring platform and method, related to dust monitoring data processing technical field, the platform includes: traversing building construction area layout multiple monitoring equipment carries out data acquisition, obtains multiple construction monitoring data;Determine dust data correlation network;Multiple construction monitoring data are dust forecasted, obtain dust prediction result;According to dust prediction result, trace to source is carried out in building construction area;Dust control scheme is optimized, and dust control optimization scheme is generated to the dust of building construction area is intelligently handled.Solve the existing building construction dust monitoring processing exists and is difficult to real-time, comprehensive monitoring building construction area, cannot accurately locate dust pollution source, and then lead to dust pollution monitoring efficiency is not high, and the technical problem that management scheme is insufficient in pertinence, realize the intelligent management of building construction dust control, reach the technical effect of improving building construction area dust pollution monitoring efficiency and management pertinence.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dust monitoring data processing, and particularly relates to an intelligent monitoring platform and method for construction dust. BACKGROUND

[0002] Under the background of accelerating urbanization process, building construction has become an important force to promote urban development. However, with large-scale construction activities, the problem of dust pollution in the process of building construction has become increasingly prominent, which has become a major challenge to urban air quality, residents' health and ecological environment. Dust not only reduces the visibility of the city and increases the incidence of respiratory diseases, but also causes irreversible damage to the surrounding vegetation, water and other natural ecology. Traditional dust control methods rely on simple experience and judgment, and have the disadvantages of limited monitoring range, untimely data collection, lagging treatment measures and the like. It is difficult to achieve comprehensive and real-time monitoring of dust pollution sources, and it is impossible to accurately locate the main source of dust pollution through traceability analysis, so as to meet the strict requirements of modern building construction on environmental protection, thereby affecting the environmental management level and green construction of building sites.

[0003] Therefore, in the present dust monitoring and processing related technology, it is difficult to monitor the building construction area in real time and comprehensively, and it is impossible to accurately locate the dust pollution source, which leads to the technical problems of low dust pollution monitoring efficiency and insufficient targetedness of treatment scheme. SUMMARY

[0004] The present application provides an intelligent monitoring platform and method for construction dust, which solves the technical problems of existing building construction dust monitoring and processing, such as difficulty in real-time and comprehensive monitoring of building construction area, inability to accurately locate dust pollution source, and low dust pollution monitoring efficiency and insufficient targetedness of treatment scheme, and realizes intelligent management of building construction dust treatment, thereby achieving the technical effects of improving dust pollution monitoring efficiency and treatment targeting of building construction area.

[0005] The application provides a construction dust intelligent monitoring platform, the platform comprises: a construction monitoring data obtaining module for traversing a building construction area to arrange a plurality of monitoring devices for data collection and obtaining a plurality of construction monitoring data; a dust data correlation network determining module for calling a plurality of monitoring site positions of the plurality of monitoring devices to perform dust correlation analysis on the plurality of construction monitoring data and determining a dust data correlation network; a dust prediction result obtaining module for performing dust prediction on the plurality of construction monitoring data according to the dust data correlation network and obtaining a dust prediction result; a dust control scheme making module for traversing the building construction area according to the dust prediction result to trace the source, making a dust control scheme according to the trace result; and a dust control optimization scheme generating module for executing the dust control scheme, utilizing the plurality of monitoring devices to perform governance synchronous feedback, optimizing the dust control scheme reversely according to the governance feedback information, and generating a dust control optimization scheme to intelligently process the dust of the building construction area.

[0006] In a possible implementation, the dust data correlation network determining module further performs the following processing: constructing a regional coordinate system based on the building construction area, identifying the coordinates of the plurality of monitoring devices according to the regional coordinate system, and determining a plurality of monitoring site positions; dividing the plurality of monitoring site positions according to monitoring throughput to determine a plurality of monitoring groups; arranging the plurality of construction monitoring data according to the collection time sequence to obtain construction monitoring time sequence data; performing regression analysis on the construction monitoring time sequence data according to the plurality of monitoring groups to generate a plurality of construction dust data features; performing dynamic response evaluation on the plurality of construction dust data features to generate a response evaluation result; and mapping the response evaluation result to the plurality of construction monitoring data to construct the dust data correlation network.

[0007] In a possible implementation, the dust data correlation network determining module further performs the following processing: randomly extracting a first division group based on a throughput optimization space, and calculating a first total throughput of the first division group; obtaining a first neighborhood of the first division group based on a preset neighborhood interval, wherein the first neighborhood comprises a plurality of neighborhood monitoring site positions; sequentially calculating a plurality of neighborhood monitoring throughputs of the plurality of neighborhood monitoring site positions; performing maximum value screening on the plurality of neighborhood monitoring throughputs to obtain a first neighborhood optimal monitoring throughput; when the first neighborhood optimal monitoring throughput is greater than the first total throughput, reversely matching a first neighborhood of the first neighborhood optimal monitoring throughput, and dividing by the first neighborhood, thereby iterating to a preset iteration threshold value, and outputting the plurality of monitoring groups.

[0008] In a possible implementation, the dust-raising data association network determination module further performs the following processing: performing time domain analysis on the construction monitoring time series data based on the plurality of monitoring groups to generate a time domain analysis result; identifying a dust-raising periodic variation trend of the construction site based on the time domain analysis result; performing frequency domain analysis on the construction monitoring time series data based on the plurality of monitoring groups to generate a frequency domain analysis result; identifying a dust-raising spatial distribution feature of the construction site based on the frequency domain analysis result; and adding the dust-raising periodic variation trend and the dust-raising spatial distribution feature to the plurality of construction dust data features.

[0009] In a possible implementation, the dust-raising management scheme formulation module further performs the following processing: performing dust source identification on the construction site in combination with the dust-raising prediction result to determine a plurality of dust source data; performing analysis on dust-raising space-time distribution based on the plurality of dust source data to generate a dust-raising space-time distribution result; calculating a plurality of dust-raising contribution rates based on the dust-raising space-time distribution result, the plurality of dust-raising contribution rates having a corresponding relationship with the plurality of dust source data; arranging the plurality of dust-raising contribution rates in descending order to generate a dust-raising contribution sequence; and performing traceability identification on the construction site according to the dust-raising contribution sequence to generate a traceability result.

[0010] In a possible implementation, the dust-raising management optimization scheme generation module further performs the following processing: performing management analysis on the construction site based on the dust-raising management scheme to generate a regional management result; continuously monitoring the construction site by using the plurality of monitoring devices to generate a regional monitoring result; integrating the regional management result and the regional monitoring result to generate regional dust pollution status information; determining whether the regional dust pollution status information reaches a dust-raising expectation threshold value, and if not, generating a feedback instruction, feeding back and optimizing the dust-raising management scheme according to the feedback instruction, and generating a dust-raising management optimization scheme.

[0011] In a possible implementation, the dust-raising management optimization scheme generation module further performs the following processing: if the regional dust pollution status information does not reach the dust-raising expectation threshold value, performing over-standard analysis on the construction site to generate a plurality of over-standard regions; performing dust pollution analysis based on the plurality of over-standard regions to determine a plurality of over-standard levels; merging the plurality of over-standard levels and the plurality of over-standard regions to generate an over-standard result, and when there is data greater than or equal to a preset critical value in the over-standard result, generating an alarm token and adding the alarm token to the feedback instruction.

[0012] The application also provides an intelligent monitoring method for construction dust, which comprises the following steps: traversing a building construction area to arrange a plurality of monitoring devices to collect data and obtain a plurality of construction monitoring data; calling a plurality of monitoring station positions of the plurality of monitoring devices to perform dust correlation analysis on the plurality of construction monitoring data, and determining a dust data correlation network; performing dust prediction on the plurality of construction monitoring data according to the dust data correlation network, and obtaining a dust prediction result; traversing the building construction area according to the dust prediction result to trace the source, formulating a dust control scheme according to the tracing result; executing the dust control scheme, performing governance feedback by using the plurality of monitoring devices, optimizing the dust control scheme reversely according to the governance feedback information, and generating a dust control optimization scheme to intelligently process the dust in the building construction area.

[0013] The application provides an intelligent monitoring platform and method for construction dust. First, a plurality of monitoring devices are arranged in a building construction area to collect data and obtain a plurality of construction monitoring data. Then, the plurality of construction monitoring data are analyzed based on a plurality of monitoring station positions of the plurality of monitoring devices to determine a dust data correlation network. The dust data correlation network is combined with the plurality of construction monitoring data to synchronize to a dust prediction model to obtain a dust prediction result. Then, the building construction area is traced according to the dust prediction result to formulate a dust control scheme. Finally, the dust control scheme is executed, governance feedback is performed by using the plurality of monitoring devices, the dust control scheme is optimized, a dust control optimization scheme is generated, and the dust in the building construction area is intelligently processed. The technical problems that the existing building construction dust monitoring and processing cannot realize real-time and comprehensive monitoring of the building construction area, cannot accurately locate the dust pollution source, and thus cannot achieve high dust pollution monitoring efficiency and insufficiently targeted control scheme are solved. The intelligent management of the building construction dust control is realized, and the technical effects of improving the dust pollution monitoring efficiency of the building construction area and the targeting of the control are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. In the present application, a flowchart is used to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously as needed. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0015] Figure 1 A structural schematic diagram of an intelligent monitoring platform for construction dust provided by the embodiments of the present application is shown in FIG. 1.

[0016] Figure 2A flowchart of an intelligent construction dust monitoring method provided by an embodiment of the present application is shown.

[0017] The reference signs are explained as follows: a construction monitoring data obtaining module 10, a dust data correlation network determining module 20, a dust prediction result obtaining module 30, a dust control scheme making module 40, and a dust control optimization scheme generating module 50. DETAILED DESCRIPTION

[0018] The above description is only a summary of the technical solutions of the present application. In order to make the technical solutions of the present application more clear, the embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0019] In order to make the purposes, technical solutions and advantages of the present application more clear, the following will further describe the present application with reference to the accompanying drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without making creative efforts fall within the scope of protection of the present application.

[0020] In the following description, "some embodiments" are described, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict, and the term "first\second" referred to only distinguishes similar objects, and does not represent a specific order of the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, platform, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] An embodiment of the present application provides an intelligent construction dust monitoring platform, as shown in Figure 1 The platform comprises:

[0022] The construction monitoring data obtaining module 10 is configured to traverse the construction area to arrange a plurality of monitoring devices to collect data and obtain a plurality of construction monitoring data. The plurality of monitoring devices are arranged in the construction area to collect data and obtain a plurality of construction monitoring data, which means that through the scientific arrangement of monitoring sites, the advanced monitoring technology and equipment are used to measure and record various environmental parameters generated in the construction process in real time and continuously, and a plurality of construction monitoring data are obtained. Specifically, when arranging the monitoring devices, a plurality of factors need to be considered, including the selection of the monitoring site, the type and accuracy of the monitoring device, the frequency and method of data collection, etc., so as to realize the comprehensive, real-time and accurate monitoring of the dust pollution in the construction area, which can include air quality monitoring, meteorological parameter monitoring, noise monitoring, video and image monitoring, etc. The air quality monitoring data include the concentration of particulate matter (such as the concentration of fine particulate matter and inhalable particulate matter such as PM2.5, PM10, etc.) and other pollutants (such as the concentration of harmful gases such as sulfur dioxide and nitrogen oxides); the meteorological parameter monitoring data include wind speed and direction, humidity and temperature, which affect the concentration and distribution of dust or particulate matter in the air; the noise data are not a direct parameter for measuring dust pollution, but the noise in the construction process is often closely related to the construction activities, and is also an important part of the construction monitoring; the camera and image recognition technology can be used to monitor the construction area in real time, capture the moment and process of dust generation, and provide direct evidence and basis for dust control.

[0023] The dust data correlation network determination module 20 is used for analyzing the plurality of construction monitoring data based on the plurality of monitoring site positions of the plurality of monitoring devices, and determining the dust data correlation network. In the construction area, according to the characteristics of the construction activities, the positions of the environmentally sensitive areas, and the monitoring requirements, a plurality of monitoring sites are scientifically and reasonably arranged, which are distributed at different positions so as to comprehensively cover the construction area and capture the dust pollution conditions of different areas. Each monitoring site is equipped with corresponding monitoring devices, which can collect various environmental parameter data in the construction process in real time and continuously. Then, the collected raw data is preprocessed, including data cleaning (removing abnormal values, missing values, etc.), data standardization (unifying dimensions and units), etc., so as to ensure the quality and consistency of the data. Then, the preprocessed monitoring data is analyzed based on statistical analysis, including analyzing the similarity and difference between the data of each monitoring site, exploring the correlation and mutual influence between different environmental parameters, etc. Finally, based on the results of the data analysis, the dust data correlation network is constructed, which takes the monitoring sites as nodes and the correlation between the data of the sites as edges, forming a complex network structure. Through this network, the mutual influence and transmission relationship between the data of different monitoring sites, and the spatial distribution and dynamic changes of the dust pollution in the entire construction area can be intuitively displayed, so as to evaluate the importance and influence of different monitoring sites, optimize the layout and quantity of the monitoring sites, and improve the monitoring efficiency and accuracy.

[0024] The dust prediction result obtaining module 30 is used for performing dust prediction on the plurality of construction monitoring data according to the dust data correlation network, and obtaining a dust prediction result. The target of the dust prediction model is determined, that is, to predict the dust concentration of a specific area in a future period of time (such as hours, days, weeks, etc.). The dust monitoring historical data of the plurality of monitoring sites are obtained, and the historical dust concentration, meteorological conditions, topography, human activity intensity, etc. are extracted from the original monitoring data through feature extraction technology (such as principal component analysis, feature dimension reduction, etc.) to construct a prediction model. Specifically, the prediction model is constructed based on an event sequence model, a neural network, etc. The prediction model is trained using historical data, the prediction performance of the model is optimized by continuously adjusting the model parameters and training strategies, the trained model is evaluated using an independent test data set, and finally the dust prediction model is obtained to predict the dust pollution of a specific area. Then, the dust data correlation network and the plurality of construction monitoring data are input into the constructed dust prediction model, the dust prediction model predicts the dust prediction result in a future period of time, mainly including the predicted value of the particulate matter concentration.

[0025] The dust control scheme formulation module 40 is used to trace the construction site according to the dust prediction results, and formulate a dust control scheme according to the tracing results. The results output by the dust prediction model are analyzed in detail, that is, the key parameters in the prediction results, such as PM10 and PM2.5 concentrations, and their relevance to meteorological conditions (such as wind speed, wind direction, humidity, etc.) are analyzed to determine the high-risk areas, time periods and possible sources of dust pollution. According to the prediction results, the construction site is comprehensively traversed, and the high-risk areas identified in the prediction are checked. During the traversal process, attention is paid to the actual situation of material storage and vehicle transportation in the construction site. Then, through on-site observation and data analysis, the main source of dust pollution is determined. Possible sources of pollution include earth excavation, material loading and unloading, vehicle transportation, construction machinery operation, etc. Each potential source of pollution is marked and recorded. According to the tracing results, the specific goals of dust control are determined, such as reducing the dust concentration in a specific area and improving the construction environment. A dust pollution control scheme is formulated, including source control to reduce dust generation from the source, for example, using wet operation to reduce dust during earth excavation, using enclosed transport vehicles to prevent material from spilling during transportation, and storing materials that are prone to dust generation in a covered or sealed manner. Process control is used to control dust dispersion during construction, for example, setting up fences and dust screens to block exposed ground and stored materials, regularly watering to reduce dust, reasonably arranging construction time and work area to reduce dust generation, and end-of-pipe treatment is used to control dust that has already been generated, for example, installing online dust monitoring equipment to monitor dust concentration in real time, configuring fog cannon vehicles and watering vehicles for dust reduction, and greening the construction area to reduce exposed ground.

[0026] The dust control optimization scheme generation module 50 is used for executing the dust control scheme, performing control feedback by using the plurality of monitoring devices, optimizing the dust control scheme in reverse according to the control feedback information, and generating a dust control optimization scheme to intelligently process the dust in the building construction area. According to the dust control scheme, dust pollution control is performed, and control feedback is performed by using a plurality of monitoring devices such as PM2.5 / PM10 sensors, weather stations, video monitoring, and the like, that is, dust data in the building construction area is monitored in real time and accurately, including real-time collection of dust concentration, diffusion direction, work surface dynamics, and the like. The environmental data after control is continuously collected by the monitoring device, the particle concentration change, pollution duration, and the like before and after control are compared, the actual effect of each control measure is quantitatively evaluated, the control feedback information is obtained, the control effect of the dust control scheme is reversely evaluated according to the control feedback information, the dust control scheme is optimized according to the evaluation result, the dust control optimization scheme is generated, and then the dust in the building construction area is intelligently processed by using the Internet of Things, artificial intelligence, and the like based on the dust control optimization scheme, for example, dust data is monitored in real time by using an intelligent monitoring platform, and control measures are automatically adjusted; the dust pollution trend is predicted by using a data analysis algorithm, and preventive measures are taken in advance, and the like, thereby improving the dust control effect and environmental quality in the building construction area.

[0027] The intelligent monitoring platform for construction dust according to the embodiment of the application is used to solve the technical problems that the existing building construction dust monitoring and processing cannot be monitored in real time and comprehensively, the dust pollution source cannot be accurately positioned, and the dust pollution monitoring efficiency is not high and the control scheme is not targeted, realizes intelligent management of building construction dust control, and achieves the technical effects of improving the dust pollution monitoring efficiency and the control targeting in the building construction area. The intelligent monitoring platform for construction dust includes a construction monitoring data obtaining module 10, a dust data correlation network determining module 20, a dust prediction result obtaining module 30, a dust control scheme formulating module 40, and a dust control optimization scheme generation module 50.

[0028] The specific configuration of the dust data correlation network determination module 20 will be described in detail below. The dust data correlation network determination module 20 can further include: constructing a regional coordinate system based on the construction area, coordinate identifying the plurality of monitoring devices according to the regional coordinate system, and determining the plurality of monitoring site positions. Based on geographic coordinates (such as latitude and longitude), a regional coordinate system is constructed in the construction area, and each position in the region is accurately positioned. The origin, direction and unit of the coordinate system are set according to the actual situation to ensure that it can accurately reflect the layout and characteristics of the construction area. In the constructed regional coordinate system, each monitoring device is coordinate identified to determine the plurality of monitoring site positions, including determining the specific position (such as latitude and longitude or relative coordinates), installation height and angle of the monitoring device and other parameters. It also includes dividing the plurality of monitoring site positions into a plurality of monitoring groups according to the monitoring throughput. According to the coordinate identification of the monitoring devices, the distribution of the monitoring devices in the construction area is analyzed, including considering the coverage range of the monitoring devices, the monitoring throughput and the characteristics of the construction area, determining the reasonable position of the monitoring site, and dividing the plurality of monitoring sites into different monitoring groups according to the position of the monitoring site, the monitoring throughput and the demand of the monitoring task. The monitoring sites in each monitoring group should have similar monitoring tasks and data processing requirements.

[0029] It also includes arranging the plurality of construction monitoring data according to the collection time sequence to obtain construction monitoring time sequence data. According to the set collection frequency and time sequence, construction monitoring data is collected from each monitoring site, and the collected construction monitoring data is arranged according to the collection time sequence to form construction monitoring time sequence data. The time sequence data should include time stamp, monitoring site identification, monitoring index (such as PM10, PM2.5 concentration, etc.) and monitoring value and other information. It also includes performing regression analysis on the construction monitoring time sequence data according to the plurality of monitoring groups to generate a plurality of construction dust data features. According to the regression analysis of the plurality of monitoring groups on the construction monitoring time sequence data, the relationship between the monitoring data and time, space and other influencing factors is revealed, so as to extract the key features of the construction dust data, and then generate a plurality of construction dust data features, which can include the change trend of dust concentration, the time period of peak value occurrence, and the correlation with meteorological conditions (such as wind speed and direction).

[0030] Further comprising, performing dynamic response evaluation on the plurality of construction dust data features to generate a response evaluation result; mapping the response evaluation result to the plurality of construction monitoring data to construct the dust data association network. The dynamic response evaluation on the generated plurality of construction dust data features obtains a response evaluation result, including understanding the response law of construction dust pollution under different time and space conditions, and the feedback effect of monitoring data on the treatment measures. The response evaluation result is mapped to the plurality of construction monitoring data to form the association relationship between the data. Finally, based on the mapped construction monitoring data and response evaluation result, the dust data association network is constructed to directly show the interaction relationship between the construction dust pollution and the monitoring data and the treatment measures, thereby improving the efficiency and accuracy of dust treatment.

[0031] Next, the specific configuration of the dust data association network determination module 20 will be described in detail. The dust data association network determination module 20 can further include: based on the throughput optimization space, randomly extracting a first division group, and calculating a first total throughput of the first division group. The throughput optimization space refers to the total amount of data processing constituted by the monitoring data of the plurality of monitoring sites. In this space, different configurations or combinations may result in different throughput performances. Randomly selecting a part of the monitoring sites from the throughput optimization space as the initial division group means that it does not guarantee to select the optimal group configuration at the beginning, but only provides a starting point. For the first division group randomly extracted, the total throughput of the division group is calculated according to the performance parameters (such as data transmission rate, processing capacity, etc.) of the internal elements and the interaction mode (such as data transmission protocol, load balancing strategy, etc.) between them, which is used to measure the data processing performance of the group under the current configuration. Further comprising, obtaining a first neighborhood of the first division group based on a preset neighborhood interval, wherein the first neighborhood includes a plurality of neighborhood monitoring site positions. According to the preset neighborhood interval (which can be a geographically adjacent area, a data transmission delay threshold, etc.), a plurality of monitoring site positions adjacent to the first division group are determined to determine the potential sites adjacent to the current group to form the first neighborhood. Further comprising, sequentially calculating a plurality of neighborhood monitoring throughputs of the plurality of neighborhood monitoring site positions. The plurality of neighborhood monitoring throughputs of the plurality of neighborhood monitoring site positions are calculated.

[0032] Further comprising maximum filtering the multiple neighborhood monitoring throughputs to obtain a first neighborhood optimal monitoring throughput. The maximum value is filtered from all neighborhood monitoring throughputs, that is, the first neighborhood optimal monitoring throughput, that is, the station with the best performance of the neighborhood throughput. Further comprising, when the first neighborhood optimal monitoring throughput is greater than the first total throughput, then the first neighborhood of the first neighborhood optimal monitoring throughput is reversely matched, and the first neighborhood is divided, thereby iterating to a preset iteration threshold, and outputting the multiple monitoring groups. If the first neighborhood optimal monitoring throughput is greater than the first total throughput, it means that the total throughput of the group can be improved by replacing or adding the station to the current group, in which case the station of the first neighborhood optimal monitoring throughput is reversely matched to its original group (if it does not originally belong to the first divided group), and then a new group is reconstructed around the station (possibly including some stations of the original group and some stations of the new neighborhood), and the above process is repeated until a preset iteration threshold (such as an upper limit of the number of iterations, a throughput improvement amplitude below a certain threshold, etc.) is reached, at which time the final multiple monitoring groups are output.

[0033] Next, the specific configuration of the dust data correlation network determination module 20 will be described in detail. The dust data correlation network determination module 20 can further comprise: performing time domain analysis on the construction monitoring time series data based on the multiple monitoring groups to generate a time domain analysis result; and identifying the periodic variation trend of dust in the construction area according to the time domain analysis result. In construction monitoring, time domain analysis is used to analyze the variation law of time series data over time to reveal the periodic variation trend of dust in the construction area. Specifically, time series analysis methods such as regression analysis, trend analysis, and seasonal decomposition are used to analyze the construction monitoring time series data in the time domain to identify the periodic variation, trend variation, and other characteristics of dust concentration, generate time domain analysis results including periodic variation trend graphs, trend prediction models, etc., and finally identify the periodic variation trend of dust in the construction area according to the time domain analysis result.

[0034] Further comprising performing frequency domain analysis on the construction monitoring time series data based on the multiple monitoring groups to generate a frequency domain analysis result; and identifying the spatial distribution characteristics of dust in the construction area according to the frequency domain analysis result. In construction monitoring, frequency domain analysis is used to analyze the performance of time series data in the frequency domain to reveal the spatial distribution characteristics of dust in the construction area. Specifically, time domain data is converted to the frequency domain through Fourier transform and other techniques to obtain a frequency spectrum graph, the main frequency, secondary frequency, and other characteristics in the frequency spectrum graph are analyzed, the spatial distribution characteristics of dust corresponding to different frequency components are identified, and the spatial distribution law of dust concentration in different frequency bands is analyzed in combination with the spatial position information of the monitoring groups to generate frequency domain analysis results including frequency spectrum graphs, dust spatial distribution characteristic maps, etc.

[0035] Further, the periodic variation trend of the dust and the spatial distribution characteristics of the dust are added to the plurality of construction dust data characteristics. The periodic variation trend and the spatial distribution characteristics obtained by the time domain analysis and the frequency domain analysis are added to the construction dust data characteristics, so as to more comprehensively describe and understand the dust condition of the construction area. Specifically, the time domain analysis result (such as the periodic variation trend and the trend prediction model) and the frequency domain analysis result (such as the frequency spectrum diagram and the spatial distribution characteristic diagram) are integrated with the original construction dust data characteristics, key characteristic parameters (such as the periodic length, the trend slope, and the main frequency component) are extracted from the analysis result, and the key characteristic parameters are added to the construction dust data characteristics.

[0036] Next, the specific configuration of the dust control scheme formulation module 40 will be described in detail. The dust control scheme formulation module 40 can further include: traversing the construction area to identify dust sources based on the dust prediction result, and determining a plurality of dust source data. The entire construction area is carefully investigated, which can include different work areas (such as excavation areas, stacking areas, transportation routes, etc.) and different construction stages, and the dust prediction result is combined to identify the main sources of dust, such as excavation work, construction sites, road transportation, stockpiles, bare ground, vehicle driving, etc., to form dust source data. Further, based on the plurality of dust source data, the dust spatio-temporal distribution is analyzed to generate a dust spatio-temporal distribution result. The dust spatio-temporal distribution is analyzed in depth by using the dust source data in combination with the time (such as different time periods) and space (such as different positions) dimensions, which can include evaluating the dust intensity and diffusion range of different dust sources at different times and positions, and through analysis, a detailed dust spatio-temporal distribution is generated to intuitively show the distribution of the dust in the construction area.

[0037] Further, according to the dust spatio-temporal distribution result, a plurality of dust contribution rates are obtained, and the plurality of dust contribution rates have a corresponding relationship with the plurality of dust source data. Based on the dust spatio-temporal distribution result, each dust source is quantitatively evaluated by considering the intensity, duration, position, etc. of different dust sources, and the contribution rate of each dust source to the overall dust level is calculated. For each identified dust source, a corresponding contribution rate is obtained, and these contribution rates have a one-to-one correspondence with the dust source data. Specifically, at each time point and spatial position, the total dust concentration of all dust sources is calculated, assuming that there are n dust sources, the total dust concentration at time t and position (x, y) is wherein, Ci(t, x, y) represents the dust concentration of the i th dust source at time t and position (x, y), the contribution rate of each dust source to the total dust concentration is calculated, and the contribution rate of the i th dust source at time t and position (x, y) is The calculation formula is: .

[0038] ​Further comprising, arranging the plurality of dust contribution rates in descending order to generate a dust contribution sequence. The plurality of dust contribution rates calculated are arranged in descending order, and the sequence of contribution rates after arrangement is the dust contribution sequence, which reflects the importance or influence of different dust sources on the overall dust level. Further comprising, tracing the source of the construction area according to the dust contribution sequence to generate a trace source result. According to the dust contribution sequence, the construction area is traced and marked, which means that the dust sources with high contribution rates are specially marked or labeled for subsequent key management and control. After the trace source marking is completed, the trace source result is generated, which clearly indicates the main dust source in the construction area, its position, contribution rate and other information.

[0039] In the following, the specific configuration of the dust control optimization scheme generation module 50 will be described in detail. The dust control optimization scheme generation module 50 can further comprise: performing the dust control scheme to analyze the construction area, and generating a regional control result. According to the predetermined dust control scheme (which may include measures such as watering dust reduction, enclosure, using low-dust building materials, and reasonable arrangement of construction time), the construction area is controlled, and the control effect is recorded and analyzed during the implementation process, such as by measuring the concentration of particulate matter in the air, observing the dust situation of the construction area, etc., to generate a regional control result. Further comprising, using the plurality of monitoring devices to continuously monitor the construction area, and generating a regional monitoring result. When implementing the control scheme, a plurality of monitoring devices (such as particulate matter concentration monitors, wind speed and direction instruments, cameras, etc.) are used to continuously and comprehensively monitor the construction area, real-time monitoring and collecting dust-related data of the construction area, and through data processing and analysis, generating a regional monitoring result. These results reflect the current dust pollution situation of the construction area, including the pollution degree, distribution range, change trend, etc.

[0040] Further, the regional dust pollution status information is generated by integrating the regional management result and the regional monitoring result. By comparative analysis, the actual effect of the management scheme and the current dust pollution status of the construction area can be comprehensively understood, and the regional dust pollution status information is generated. The regional dust pollution status information not only contains comparative data before and after management, but also can include information such as temporal and spatial distribution characteristics of dust pollution and main pollution sources, thereby providing a basis for subsequent decision-making. Further, it is determined whether the regional dust pollution status information reaches a dust expectation threshold. If not, a feedback instruction is generated, the dust management scheme is optimized according to the feedback instruction, and a dust management optimization scheme is generated. According to the integrated regional dust pollution status information, the dust expectation threshold (i.e., the expected dust pollution control standard) is compared. If the current pollution status does not reach the dust expectation threshold, it indicates that the management effect is not ideal or needs to be further strengthened. The dust expectation threshold refers to the expected dust management effect. At this time, a feedback instruction is generated to point out the existing problems and the direction for improvement. After receiving the feedback instruction, the original dust management scheme is reexamined and adjusted. According to the actual situation and professional knowledge, the management scheme is optimized. The optimized scheme can include adding new management measures, adjusting the implementation intensity or method of existing measures, increasing supervision, etc. Finally, the dust management optimization scheme is generated.

[0041] Next, the specific configuration of the dust management optimization scheme generation module 50 will be described in detail. The dust management optimization scheme generation module 50 can further include: if the regional dust pollution status information does not reach the dust expectation threshold, performing over-standard analysis on the construction area to generate a plurality of over-standard regions. If the regional dust pollution status information does not reach the dust expectation threshold, the entire construction area is carefully checked and evaluated without missing any region that can cause dust pollution. Based on the regional monitoring result, the dust pollution status of each region is analyzed one by one to determine whether it exceeds the preset dust pollution standard. The regions whose dust pollution exceeds the standard are marked as over-standard regions.

[0042] Further, dust pollution analysis is performed based on the plurality of over-standard regions to determine a plurality of over-standard levels. In-depth dust pollution analysis is performed on each over-standard region, considering factors such as the intensity, duration, and diffusion range of the pollution source. According to the analysis result, an over-standard level is determined for each over-standard region, which generally reflects the severity of pollution and the urgency of management. Different over-standard regions can have different over-standard levels, and finally a plurality of over-standard levels are determined.

[0043] Further, the multiple over-standard levels are combined with the multiple over-standard areas to generate an over-standard result, and when data greater than or equal to a preset threshold value exists in the over-standard result, an alarm token is generated and added to the feedback instruction. The over-standard level of each over-standard area is combined with information such as the geographical position and pollution characteristics of the over-standard area to form a complete over-standard result, which not only contains the position and over-standard level of the over-standard area, but also possibly includes detailed information such as the specific source of pollution and diffusion trend. When data greater than or equal to a preset threshold value exists in the over-standard result, an alarm token is generated and added to the feedback instruction. Specifically, the preset threshold value is a threshold value set according to actual conditions and management goals, and is used to determine whether the over-standard result has reached a degree requiring immediate action. The generated over-standard result is checked to find whether there is data greater than or equal to the preset threshold value. If data satisfying the condition is found, an alarm token is generated and added to the previous feedback instruction to form a complete feedback report containing detailed over-standard information and urgent alarm.

[0044] In the foregoing, with reference to Figure 1 A construction dust intelligent monitoring platform according to an embodiment of the present application is described in detail. Next, with reference to Figure 2 A construction dust intelligent monitoring method according to an embodiment of the present application is described.

[0045] A construction dust intelligent monitoring method, as shown in Figure 2 The method comprises: traversing a building construction area to deploy multiple monitoring devices to collect data and obtain multiple construction monitoring data; calling multiple monitoring site positions of the multiple monitoring devices to perform dust correlation analysis on the multiple construction monitoring data, and determining a dust data correlation network; performing dust prediction on the multiple construction monitoring data according to the dust data correlation network, and obtaining a dust prediction result; traversing the building construction area according to the dust prediction result to perform tracing, formulating a dust control scheme according to a tracing result; executing the dust control scheme, performing synchronous feedback using the multiple monitoring devices, optimizing the dust control scheme in reverse according to feedback information, and generating a dust control optimization scheme to intelligently process dust in the building construction area.

[0046] In a possible implementation, the analysis of the plurality of construction monitoring data based on the plurality of monitoring site positions of the plurality of monitoring devices determines a dust data correlation network, including: constructing a regional coordinate system based on a construction site area, identifying coordinates of the plurality of monitoring devices according to the regional coordinate system, and determining a plurality of monitoring site positions; dividing the plurality of monitoring site positions according to monitoring throughput to determine a plurality of monitoring groups; arranging the plurality of construction monitoring data according to collection time sequence to obtain construction monitoring time sequence data; performing regression analysis on the construction monitoring time sequence data according to the plurality of monitoring groups to generate a plurality of construction dust data features; performing dynamic response evaluation on the plurality of construction dust data features to generate a response evaluation result; and mapping the response evaluation result to the plurality of construction monitoring data to construct the dust data correlation network.

[0047] In a possible implementation, the plurality of monitoring groups are determined according to the plurality of monitoring site positions according to monitoring throughput, including: randomly extracting a first division group based on a throughput optimization space, and calculating a first total throughput of the first division group; obtaining a first neighborhood of the first division group based on a preset neighborhood interval, wherein the first neighborhood includes a plurality of neighborhood monitoring site positions; sequentially calculating a plurality of neighborhood monitoring throughputs of the plurality of neighborhood monitoring site positions; performing maximum value screening on the plurality of neighborhood monitoring throughputs to obtain a first neighborhood optimal monitoring throughput; when the first neighborhood optimal monitoring throughput is greater than the first total throughput, then reversely matching a first neighborhood of the first neighborhood optimal monitoring throughput, and dividing by the first neighborhood, thereby iterating to a preset iteration threshold, and outputting the plurality of monitoring groups.

[0048] In a possible implementation, the regression analysis of the construction monitoring time sequence data according to the plurality of monitoring groups generates a plurality of construction dust data features, including: performing time domain analysis on the construction monitoring time sequence data based on the plurality of monitoring groups to generate a time domain analysis result; identifying a dust cycle change trend of the construction site area according to the time domain analysis result; performing frequency domain analysis on the construction monitoring time sequence data based on the plurality of monitoring groups to generate a frequency domain analysis result; identifying a dust spatial distribution feature of the construction site area according to the frequency domain analysis result; and adding the dust cycle change trend and the dust spatial distribution feature to the plurality of construction dust data features.

[0049] In a possible implementation, the dust source is traced according to the dust prediction result, including: dust source identification is performed in combination with the dust prediction result in the construction area to determine a plurality of dust source data; the dust space-time distribution is analyzed based on the plurality of dust source data to generate a dust space-time distribution result; the plurality of dust contribution rates are obtained by calculation according to the dust space-time distribution result, the plurality of dust contribution rates have a corresponding relationship with the plurality of dust source data; the plurality of dust contribution rates are arranged in descending order to generate a dust contribution sequence; and the construction area is traced according to the dust contribution sequence to generate a trace result.

[0050] In a possible implementation, the dust control scheme is executed, the feedback is performed by using the plurality of monitoring devices, and the dust control scheme is optimized, including: the dust control scheme is executed to perform governance analysis on the construction area to generate a regional governance result; the plurality of monitoring devices are used to continuously monitor the construction area to generate a regional monitoring result; the regional governance result and the regional monitoring result are integrated to generate regional dust pollution status information; and it is judged whether the regional dust pollution status information reaches a dust expected threshold, if not, a feedback instruction is generated, the dust control scheme is fed back and optimized according to the feedback instruction, and a dust control optimization scheme is generated.

[0051] In a possible implementation, if the regional dust pollution status information does not reach the dust expected threshold, a feedback instruction is generated, and the implementation further includes: if the regional dust pollution status information does not reach the dust expected threshold, the construction area is traversed to perform an over-standard analysis to generate a plurality of over-standard areas; dust pollution analysis is performed based on the plurality of over-standard areas to determine a plurality of over-standard levels; the plurality of over-standard levels and the plurality of over-standard areas are merged to generate an over-standard result, and when there is data greater than or equal to a preset threshold in the over-standard result, an alarm token is generated and added to the feedback instruction.

[0052] The construction dust intelligent monitoring platform provided by the embodiment can execute the construction dust intelligent monitoring method provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0053] Although various references are made in this application to certain modules in the platform according to the embodiments of the application, however, any number of different modules can be used and run on the user terminal and / or server, and each unit and module included is only divided according to the function logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for convenient mutual distinction, and do not limit the protection scope of the application.

[0054] The above detailed description does not limit the scope of the application. Various modifications, combinations and equivalents thereof can be made in light of the above detailed description. Any modification, equivalent replacement and improvement made within the spirit and principle of the application shall fall within the scope of the application.

Claims

1. An intelligent monitoring platform for construction dust, characterized in that, The platform includes: The construction monitoring data acquisition module is used to traverse the construction area, deploy multiple monitoring devices to collect data, and obtain multiple construction monitoring data. The dust data association network determination module is used to retrieve the locations of multiple monitoring stations of the multiple monitoring devices to perform dust association analysis on the multiple construction monitoring data and determine the dust data association network; The dust prediction result acquisition module is used to perform dust prediction on the multiple construction monitoring data according to the dust data association network, and obtain dust prediction results; The dust control plan formulation module is used to trace the source of dust throughout the construction area based on the dust prediction results, and formulate a dust control plan based on the source tracing results. The dust control optimization scheme generation module is used to execute the dust control scheme, use the multiple monitoring devices to provide synchronous feedback on the control, optimize the dust control scheme in reverse based on the control feedback information, and generate a dust control optimization scheme to intelligently handle dust in the construction area. The dust data association network determination module includes: A regional coordinate system is constructed based on the construction area, and the coordinates of the multiple monitoring devices are marked according to the regional coordinate system to determine the location of multiple monitoring stations; Based on the locations of the multiple monitoring stations and their monitoring throughput, multiple monitoring groups are determined; The multiple construction monitoring data are arranged according to the collection time sequence to obtain construction monitoring time series data; Regression analysis was performed on the construction monitoring time series data based on the multiple monitoring groups to generate multiple construction dust data features; Dynamic response evaluation is performed on the multiple construction dust data characteristics to generate response evaluation results; The response evaluation results are mapped to the multiple construction monitoring data to construct the dust data association network; The dust data association network determination module further includes: Based on the multiple monitoring groups, time-domain analysis is performed on the construction monitoring time series data to generate time-domain analysis results; Based on the time-domain analysis results, the periodic variation trend of dust in the construction area was identified; Frequency domain analysis is performed on the construction monitoring time series data based on the multiple monitoring groups to generate frequency domain analysis results; The spatial distribution characteristics of dust in the construction area are identified based on the frequency domain analysis results. The dust cycle variation trend and the dust spatial distribution characteristics are added to the multiple construction dust data features.

2. The intelligent monitoring platform for construction dust as described in claim 1, characterized in that, Based on the locations of the multiple monitoring stations and their monitoring throughput, multiple monitoring groups are determined, and the platform includes: The first partition group is randomly extracted based on the throughput optimization space, and the first total throughput of the first partition group is calculated. The first neighborhood of the first group is obtained based on a preset neighborhood interval, wherein the first neighborhood includes the locations of multiple neighborhood monitoring stations; The throughput of multiple neighborhood monitoring stations at each location is calculated sequentially. The maximum value of the monitoring throughput of the multiple neighborhoods is filtered to obtain the optimal monitoring throughput of the first neighborhood. When the optimal monitoring throughput of the first neighborhood is greater than the first total throughput, the first neighborhood of the optimal monitoring throughput of the first neighborhood is matched in reverse, and the first neighborhood is used for division. This process is iterated until a preset iteration threshold is reached, and the multiple monitoring groups are output.

3. The intelligent monitoring platform for construction dust as described in claim 1, characterized in that, Based on the dust prediction results, the platform traces the dust source across the construction area. The platform includes: By traversing the construction area and combining the dust prediction results, dust sources are identified, and multiple dust source data are determined. Based on the data from the multiple dust sources, the spatiotemporal distribution of dust is analyzed, and the spatiotemporal distribution results of dust are generated. Based on the spatiotemporal distribution results of dust, multiple dust contribution rates are calculated, and these multiple dust contribution rates correspond to the multiple dust source data. The multiple dust contribution rates are sorted in descending order to generate a dust contribution sequence. The construction area is identified and traced according to the dust contribution sequence, and the traceability results are generated.

4. The intelligent monitoring platform for construction dust as described in claim 1, characterized in that, The dust control plan is implemented, and the multiple monitoring devices are used for synchronous feedback. Based on the feedback information, the dust control plan is optimized. The platform includes: The dust control plan is implemented to analyze the dust control in the construction area and generate regional control results. The construction area is continuously monitored using the aforementioned multiple monitoring devices, and regional monitoring results are generated. The regional governance results are integrated with the regional monitoring results to generate regional dust pollution status information; Determine whether the dust pollution status information of the area has reached the expected dust threshold. If not, generate a feedback instruction and optimize the dust control plan according to the feedback instruction to generate an optimized dust control plan.

5. The intelligent monitoring platform for construction dust as described in claim 4, characterized in that, The system determines whether the dust pollution status information of the area has reached the expected dust threshold. If not, it generates a feedback instruction. The platform includes: If the dust pollution status information of the area does not reach the expected dust threshold, then the construction area is traversed to perform an analysis of exceeding the standard, generating multiple areas exceeding the standard. Dust pollution analysis was conducted based on the multiple areas exceeding the standards to determine multiple levels of exceedance. The multiple exceedance levels and multiple exceedance regions are merged to generate exceedance results. When there is data in the exceedance results that is greater than or equal to a preset threshold, an alarm token is generated and added to the feedback instruction.

6. A method for intelligent monitoring of construction dust, characterized in that, The method is applied to an intelligent monitoring platform for construction dust as described in any one of claims 1-5, and the method includes: Multiple monitoring devices were deployed throughout the construction area to collect data, resulting in a variety of construction monitoring data. By retrieving the locations of multiple monitoring stations from the multiple monitoring devices, dust correlation analysis is performed on the multiple construction monitoring data to determine the dust data correlation network. Dust prediction is performed on the multiple construction monitoring data according to the dust data association network to obtain dust prediction results; Based on the dust prediction results, the dust source is traced throughout the construction area, and a dust control plan is formulated based on the source tracing results. The dust control plan is implemented, and the multiple monitoring devices are used for synchronous feedback. Based on the feedback information, the dust control plan is optimized to generate an optimized dust control plan for intelligent treatment of dust in the construction area.

Images