Intelligent construction site dust environment monitoring method, system and storage medium

Abstract

The present invention discloses a smart construction site dust environment monitoring method, system and storage medium, which belong to the field of environmental monitoring technology. It solves the problem that the existing method is difficult to extract the significant features of monitoring index data based on the dangerous condition model trained by support vector machine or neural network machine learning. The method comprises: collecting time-series environmental monitoring information based on a multi-functional monitoring instrument to obtain a normalized evaluation feature vector; pre-constructing an environmental assessment and early warning model based on principal component analysis combined with random forest; the environmental assessment and early warning model identifies and analyzes the normalized evaluation feature vector and calculates the comprehensive pollution degree; the present invention extracts the significant features of the time-series environmental monitoring information by pre-processing the collected time-series environmental monitoring information, thereby ensuring that the real data distribution can be learned on the training data when the environmental assessment and early warning model based on principal component analysis combined with random forest is constructed and trained, and the risk of model overfitting is effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring, and specifically relates to a method, system and storage medium for monitoring dust environment at a smart construction site. Background Art

[0002] Construction site dust monitoring is the process of real-time monitoring and management of dust pollution at construction sites using modern sensor technology, the Internet of Things, and artificial intelligence technology. With the acceleration of urbanization, construction activities are becoming more frequent, and the resulting dust problem has become one of the important factors affecting urban air quality. Effective dust monitoring can not only help manage dust pollution, but also provide a healthier living environment for construction workers.

[0003] Chinese patent CN108267170B discloses an environmental monitoring method and device, including: obtaining and saving environmental monitoring index data obtained by monitoring the current environment by an environmental sensor on a wearable device; analyzing and predicting the environmental monitoring index data to obtain analysis and prediction results; and performing corresponding prompt or alarm operations on the wearable device according to the analysis and prediction results. The environmental monitoring device includes: a data acquisition unit, an analysis and prediction unit, and a prompt and alarm unit. However, the existing method is based on a dangerous condition model trained by support vector machine (SVM) or neural network machine learning, which is difficult to extract significant features of the monitoring index data, and the model has poor robustness when facing a multi-source heterogeneous detection index data training model. In response to the above problems, we propose a smart construction site dust environment monitoring method, system and storage medium. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a smart construction site dust environment monitoring method, system and storage medium, which solves the problem that the existing methods based on support vector machine (SVM) or neural network machine learning training of dangerous condition models are difficult to extract significant features of monitoring index data, and the model has poor robustness when facing multi-source heterogeneous detection index data training models.

[0005] The present invention is implemented in this way: a smart construction site dust environment monitoring method, the smart construction site dust environment monitoring method comprising:

[0006] Based on the multifunctional monitoring instrument, the time-series environmental monitoring information is collected, wherein the time-series environmental monitoring information is multi-source heterogeneous measurement data, and the time-series environmental monitoring information includes air quality data, dust content data, noise monitoring data, wind speed monitoring data, and dust particle shooting data. The collected time-series environmental monitoring information is pre-processed, and the significant features of the time-series environmental monitoring information are extracted to obtain a normalized evaluation feature vector;

[0007] Pre-build an environmental assessment and early warning model based on principal component analysis combined with random forest, iterate and train the improved environmental assessment and early warning model, and output the environmental assessment and early warning model;

[0008] The environmental assessment early warning model identifies and analyzes the normalized assessment feature vector, calculates the comprehensive pollution degree, and determines whether there is air pollution. If there is air pollution, it triggers the air pollution instruction;

[0009] The pollution calculation network in the environmental assessment and early warning model responds to air pollution instructions, loads normalized assessment feature vectors, calculates air pollution diffusion, and feeds back air pollution and air pollution diffusion.

[0010] The multifunctional monitor obtains the air pollution degree and air pollution diffusion degree, triggers the dust reduction instruction, and performs dust reduction treatment on the construction site based on the dust reduction instruction.

[0011] Preferably, the preprocessing of the collected time-series environmental monitoring information specifically includes:

[0012] Acquire time series environmental monitoring information, perform first preprocessing and second preprocessing on the time series environmental monitoring information, and obtain a first preprocessing set and a second preprocessing set, wherein the first preprocessing is a preprocessing of setting the mean of the monitoring information to 0, and the second preprocessing is a preprocessing of setting the root mean square error of the monitoring information to 1;

[0013] Among them, the collection of temporal environmental monitoring information is , the formula for setting the mean of monitoring information to 0 is:

[0014] (1)

[0015] Centralized time-series environmental monitoring information. is the mean value of monitoring information;

[0016] (2)

[0017] in, is the amount of data in the temporal environmental monitoring information set, It is the input time series environmental monitoring information;

[0018] (3)

[0019] in, is the root mean square error of the time series environmental monitoring information, is the mean value of the time series environmental monitoring information;

[0020] Obtain centralized time-series environmental monitoring information and root mean square error values, and construct a characteristic decomposition matrix based on the centralized time-series environmental monitoring information and root mean square error values;

[0021] Perform dimensionality reduction processing on the eigendecomposition matrix to obtain the eigendecomposition matrix after dimensionality reduction;

[0022] Based on the Bayesian algorithm, the significant features of the temporal environmental monitoring information are extracted and integrated to obtain the normalized evaluation feature vector.

[0023] Among them, the significant feature extraction function is:

[0024] (4)

[0025] To normalize the evaluation feature vector, is the significance transformation coefficient, is the magnitude of significant change;

[0026] (5)

[0027] in, is the significance transformation coefficient, is the magnitude of significant change.

[0028] Preferably, the method for pre-constructing an environmental assessment early warning model based on principal component analysis combined with random forest specifically includes:

[0029] Obtaining model training samples, wherein the model training samples are historical environmental monitoring information, and preprocessing the model training samples;

[0030] Initialize the random forest model, build a feature evaluator based on principal component analysis combined with the SimAM attention mechanism, and define the weighting function of the feature evaluator on sample features. The weighting function of the feature evaluator on sample features is expressed as:

[0031] (6)

[0032] in, is the weight value of the sample feature, is the number of neurons in the feature judge, The weight bias coefficient set for the feature evaluator, is the dimension of the feature vector, Normalized evaluation feature vector for model training samples;

[0033] The weighted model training samples are trained to initialize the random forest model, and a random forest decision tree layer that is good at air pollution detection is obtained;

[0034] The feature evaluator, random forest decision tree layer, and pollution calculation network are incorporated into the initial random forest model to obtain an environmental assessment and early warning model;

[0035] The environmental assessment and early warning model includes an input layer, a feature evaluator, a random forest decision tree layer, a pollution calculation network and an output layer.

[0036] Preferably, the method of identifying and analyzing the normalized assessment feature vector and calculating the comprehensive pollution degree by the environmental assessment early warning model specifically includes:

[0037] A normalized evaluation feature vector is obtained, and the feature evaluator in the environmental assessment early warning model identifies abnormal feature factors of the normalized evaluation feature vector based on the K-means algorithm;

[0038] Among them, the abnormal feature factor extraction function is:

[0039] (7);

[0040] Extract the value of the abnormal characteristic factor. When extracting, set the abnormal characteristic factor judgment value to , by comparing the abnormal feature factor extraction value with the abnormal feature factor judgment value, the feature factor in the normalized evaluation feature vector is determined to be an abnormal feature factor, where, To extract the base number;

[0041] The abnormal characteristic factor judgment value of the abnormal characteristic factor is input into the random forest decision tree layer to calculate the comprehensive pollution degree;

[0042] (8)

[0043] in, is the comprehensive pollution degree, is the bias coefficient.

[0044] The present invention also provides a smart construction site dust environment monitoring system, the smart construction site dust environment monitoring system comprising:

[0045] A multifunctional monitor, which is used to collect time-series environmental monitoring information;

[0046] A data processing module, which is used to pre-process the collected time-series environmental monitoring information, extract the significant features of the time-series environmental monitoring information, and obtain a normalized evaluation feature vector;

[0047] Model building module: The model building module pre-builds an environmental assessment and early warning model based on principal component analysis combined with random forest, iteratively trains the improved environmental assessment and early warning model, and outputs the environmental assessment and early warning model;

[0048] Pollution comprehensive judgment module: The pollution comprehensive judgment module identifies and analyzes the normalized evaluation feature vector based on the environmental assessment and early warning model, calculates the comprehensive pollution degree, and determines whether there is air pollution. If there is air pollution, it triggers the air pollution instruction, calculates the air pollution diffusion degree, and feeds back the air pollution degree and air pollution diffusion degree;

[0049] The dust reduction processing module performs dust reduction processing on the construction site based on the dust reduction instructions.

[0050] Preferably, the multifunctional monitor comprises:

[0051] The monitoring instrument body comprises a monitoring base, a support rod, an equipment support seat and an adjustment mounting seat, wherein the support rod is rotatably mounted on the monitoring base, the equipment support seat is detachably connected to the top of the support rod, and the adjustment mounting seat is fixedly connected to the equipment support seat;

[0052] A multi-source data acquisition unit installed on the equipment support, the multi-source data acquisition unit is used to collect time-series environmental monitoring information;

[0053] A position adjustment component, the position adjustment component includes a main body adjustment part and a device adjustment part, the main body adjustment part is installed on the monitoring base, the main body adjustment part is connected to the support rod, the main body adjustment part is used to adjust the rotation angle of the support rod, the device adjustment part is installed on the adjustment mounting seat, the device adjustment part is connected to the multi-source data acquisition part, and the device adjustment part is used to adjust the inclination angle of the multi-source data acquisition part.

[0054] Preferably, the main body adjustment portion comprises:

[0055] A first motor, wherein the first motor is fixedly mounted on a monitoring base;

[0056] A first gear fixedly connected to the output end of the first motor, wherein the first gear is rotatably connected to the upper surface of the monitoring base;

[0057] A second gear fixedly sleeved on the outside of the support rod, the second gear meshing with the first gear for transmission;

[0058] The equipment adjustment unit comprises:

[0059] A second motor, wherein the second motor is fixedly mounted on the adjustment mounting seat, an output end of the second motor is fixedly connected to a transmission gear plate, and the transmission gear plate is rotatably mounted on one side of the adjustment mounting seat;

[0060] At least one set of third gears, the third gears are arranged on one side of the transmission gear disc, and the third gears are meshed with the transmission gear disc for transmission, a transmission screw is fixedly connected to one side of the third gear, the transmission screw is rotatably connected to the side wall of the adjustment mounting seat, a threaded sleeve is provided with a movable gear seat at one end of the transmission screw away from the third gear, and the movable gear seat is slidably connected to the equipment support seat through a guide block;

[0061] A fourth gear, the fourth gear is rotatably mounted on the equipment support seat, the fourth gear is meshed with the mobile gear seat for transmission, and the fourth gear is also connected to the multi-source data acquisition unit;

[0062] A negative pressure transmission shaft is fixedly connected to the transmission gear disc, and at least one group of negative pressure dust extraction fans are detachably mounted on the end of the negative pressure transmission shaft, and the negative pressure dust extraction fans are used to assist in cleaning the multi-source data acquisition unit.

[0063] Preferably, the multi-source data acquisition unit includes:

[0064] A collector controller, wherein the collector controller is fixedly connected to the fourth gear;

[0065] A collection swing seat installed on the collector controller, wherein a plurality of atomizing spray ports are embedded in the collection swing seat, wherein the atomizing spray ports are connected to a water storage tank via a telescopic water pipe, and the atomizing spray ports perform dust reduction treatment on the construction site based on a dust reduction instruction;

[0066] A CCD camera installed on the collection swing seat, the CCD camera is used to collect dust particle shooting data;

[0067] A dust sensor, wherein the dust sensor is used to collect dust content data;

[0068] A noise collector, wherein the noise collector is used to collect noise monitoring data;

[0069] Air quality monitor, the air quality monitor is used to collect air quality data;

[0070] A wind speed collector, which is used to collect wind speed monitoring data;

[0071] The collector controller is electrically connected to the CCD camera, the dust sensor, the noise collector, the air quality monitor and the wind speed collector respectively.

[0072] On the other hand, the present invention also provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed, the smart construction site dust environment monitoring method is implemented.

[0073] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0074] In the embodiment of the present invention, by preprocessing the collected time-series environmental monitoring information, extracting the significant features of the time-series environmental monitoring information, and obtaining a normalized evaluation feature vector, the collected multi-source heterogeneous data can be normalized, thereby accurately extracting the significant features of the data, ensuring that the true data distribution can be learned on the training data when constructing and training the environmental assessment and early warning model based on principal component analysis combined with random forests, effectively reducing the risk of model overfitting, and ensuring the accuracy of the comprehensive pollution assessment.

[0075] In an embodiment of the present invention, an environmental assessment and early warning model based on principal component analysis combined with random forest is provided. The environmental assessment and early warning model is an improved random forest model, and the SimAM attention mechanism is introduced to construct a feature evaluator during model construction. At the same time, the combination of principal component analysis and random forest can integrate the advantages of principal component analysis in extracting significant features and the advantages of random forest in long-distance modeling, thereby better extracting features of multi-source heterogeneous data and improving the accuracy of random forest decision tree layers and feature evaluators.

[0076] In an embodiment of the present invention, a smart construction site dust environment monitoring system is provided. The smart construction site dust environment monitoring system consists of a multi-functional monitoring instrument, a data processing module, a model building module, a comprehensive pollution judgment module, and a dust reduction processing module. The multi-functional monitoring instrument can accurately realize the collection of time-series environmental monitoring information, and the collection coverage area is larger and the accuracy is higher. The multi-functional monitoring instrument and the dust reduction processing module can optimize the dust reduction spray path based on the air pollution diffusion degree, thereby reducing the energy consumption of dust reduction operations and realizing smart green and environmentally friendly construction.

[0077] In an embodiment of the present invention, a multifunctional monitoring instrument is provided. The multifunctional monitoring instrument realizes accurate collection of environmental monitoring data of different areas of the construction site through a multi-source data acquisition unit, thereby providing data support for the environmental assessment and early warning model to analyze and evaluate the construction environment. At the same time, the equipment adjustment unit can synchronously adjust the positions of multiple groups of multi-source data acquisition units, which not only facilitates data collection, but also facilitates spray dust removal operations on the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a schematic diagram of the implementation flow of the smart construction site dust environment monitoring method provided by the present invention.

[0079] Figure 2 It is a schematic diagram of the implementation flow of preprocessing the collected time-series environmental monitoring information provided by the present invention.

[0080] Figure 3It is a schematic diagram of the implementation process of the method for pre-constructing an environmental assessment and early warning model based on principal component analysis combined with random forests provided by the present invention.

[0081] Figure 4 The invention provides an environmental assessment early warning model for identifying and analyzing normalized assessment feature vectors and a schematic diagram of a method for calculating a comprehensive pollution degree.

[0082] Figure 5 It is a control framework diagram of the smart construction site dust environment monitoring system provided by the present invention.

[0083] Figure 6 It is a structural schematic diagram of the multifunctional monitoring instrument provided by the present invention.

[0084] Figure 7 It is a three-dimensional structural schematic diagram of the multifunctional monitoring instrument provided by the present invention.

[0085] Figure 8 It is a structural schematic diagram of the multi-source data acquisition unit provided by the present invention.

[0086] Fig. 9 It is an axonometric diagram of the multi-source data acquisition unit provided by the present invention.

[0087] Fig.10 It is a front view of the multi-source data acquisition unit provided by the present invention.

[0088] In the figure: 10-multi-function monitor, 11-monitoring base, 12-support rod, 13-equipment support seat, 14-adjustment mounting seat, 2-position adjustment component, 21-main body adjustment part, 211-first motor, 212-first gear, 213-second gear, 22-equipment adjustment part, 221-second motor, 222-transmission gear plate, 223-third gear, 224-transmission screw, 225-movable gear seat, 226-guide block, 227-fourth Gear, 228-negative pressure transmission shaft, 229-negative pressure dust extraction fan, 3-multi-source data acquisition unit, 31-collector controller, 32-collection swing seat, 33-atomizing spray nozzle, 34-telescopic water pipe, 35-CCD camera, 36-noise collector, 37-dust sensor, 38-air quality monitor, 39-wind speed collector, 20-data processing module, 30-model building module, 40-pollution comprehensive judgment module, 50-dust reduction treatment module. DETAILED DESCRIPTION

[0089] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0090] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0091] Existing methods based on support vector machine (SVM) or neural network machine learning training of dangerous condition models are difficult to extract significant features of monitoring indicator data, and the model has poor robustness when facing multi-source heterogeneous detection indicator data training models. To address the above problems, we propose a smart construction site dust environment monitoring method, system and storage medium. In short, the method includes collecting time-series environmental monitoring information based on a multi-function monitor 10, pre-building an environmental assessment and early warning model based on principal component analysis combined with random forests, the environmental assessment and early warning model identifies and analyzes normalized assessment feature vectors, calculates the comprehensive pollution degree, and determines whether there is air pollution. The pollution calculation network in the environmental assessment and early warning model responds to air pollution instructions, loads normalized assessment feature vectors, and calculates the air pollution diffusion degree. In the embodiment of the present invention, by preprocessing the collected time-series environmental monitoring information, extracting the significant features of the time-series environmental monitoring information, and obtaining a normalized evaluation feature vector, the collected multi-source heterogeneous data can be normalized, thereby accurately extracting the significant features of the data, ensuring that the true data distribution can be learned on the training data when constructing and training the environmental assessment and early warning model based on principal component analysis combined with random forests, effectively reducing the risk of model overfitting, and ensuring the accuracy of the comprehensive pollution assessment.

[0092] The embodiment of the present invention provides a method for monitoring dust environment in a smart construction site. Figure 1 The figure shows a schematic diagram of the implementation process of the smart construction site dust environment monitoring method, which specifically includes:

[0093] Step S10, collecting time-series environmental monitoring information based on the multifunctional monitor 10, wherein the time-series environmental monitoring information is multi-source heterogeneous measurement data, and the time-series environmental monitoring information includes air quality data, dust content data, noise monitoring data, wind speed monitoring data, and dust particle shooting data, pre-processing the collected time-series environmental monitoring information, extracting significant features of the time-series environmental monitoring information, and obtaining a normalized evaluation feature vector;

[0094] It should be noted that the time-series environmental monitoring information is multi-source heterogeneous measurement data, and the types of multi-source heterogeneous measurement data can be structured data, semi-structured data and unstructured data, among which unstructured data includes but is not limited to text, pictures, audio and video data. At the same time, the time-series environmental monitoring information collection period can be 30 minutes, 60 minutes, 2 hours, and 4 hours.

[0095] Step S20, pre-constructing an environmental assessment early warning model based on principal component analysis combined with random forest, iteratively training the improved environmental assessment early warning model, and outputting the environmental assessment early warning model;

[0096] In this embodiment, the environmental assessment early warning model may be iteratively trained 100-2000 times, and the hyperparameter optimization method of the environmental assessment early warning model may be grid search (GridSearchCV) and random search (RandomizedSearchCV).

[0097] Step S30, the environmental assessment early warning model identifies and analyzes the normalized assessment feature vector and calculates the comprehensive pollution degree;

[0098] Step S40, determining whether there is air pollution;

[0099] It should be noted that, unlike the current use of a single evaluation index to judge the degree of air pollution, in this embodiment, the current construction environment air environment is comprehensively evaluated through the comprehensive pollution degree, and the basis for judging whether there is air pollution is whether the calculated comprehensive pollution degree exceeds the preset pollution threshold, and the preset pollution threshold can be set to 0.5-0.8.

[0100] Step S50, if there is air pollution, triggering an air pollution instruction;

[0101] If there is no air pollution, the current comprehensive pollution level is output, and the multifunctional monitor 10 continues to periodically collect time-series environmental monitoring information.

[0102] Step S60, the pollution calculation network in the environmental assessment and early warning model responds to the air pollution instruction, loads the normalized assessment feature vector, calculates the air pollution diffusion, and feeds back the air pollution degree and the air pollution diffusion.

[0103] In step S70, the multifunctional monitor 10 obtains the air pollution degree and the air pollution diffusion degree, triggers the dust reduction instruction, and performs dust reduction treatment on the construction site based on the dust reduction instruction.

[0104] In the embodiment of the present invention, by preprocessing the collected time-series environmental monitoring information, extracting the significant features of the time-series environmental monitoring information, and obtaining a normalized evaluation feature vector, the collected multi-source heterogeneous data can be normalized, thereby accurately extracting the significant features of the data, ensuring that the true data distribution can be learned on the training data when constructing and training the environmental assessment and early warning model based on principal component analysis combined with random forests, effectively reducing the risk of model overfitting, and ensuring the accuracy of the comprehensive pollution assessment.

[0105] The embodiment of the present invention provides a method for preprocessing collected time-series environmental monitoring information. Figure 2 The figure shows a schematic diagram of the implementation process of preprocessing the collected time-series environmental monitoring information. The preprocessing of the collected time-series environmental monitoring information specifically includes:

[0106] Step S101, acquiring time-series environmental monitoring information, performing a first preprocessing and a second preprocessing on the time-series environmental monitoring information, to obtain a first preprocessing set and a second preprocessing set, wherein the first preprocessing is a preprocessing of setting the mean of the monitoring information to 0, and the second preprocessing is a preprocessing of setting the root mean square error of the monitoring information to 1;

[0107] In the embodiment of the present invention, data centralization can be achieved by performing the first preprocessing and the second preprocessing on the time series environmental monitoring information, thereby eliminating the influence of different feature dimensions on the data analysis results, making the data more suitable for comprehensive comparative evaluation.

[0108] Among them, the collection of temporal environmental monitoring information is , the formula for setting the mean of monitoring information to 0 is:

[0109] (1)

[0110] Centralized time-series environmental monitoring information. is the mean value of monitoring information;

[0111] (2)

[0112] in, is the amount of data in the temporal environmental monitoring information set, It is the input time series environmental monitoring information;

[0113] (3)

[0114] in, is the root mean square error of the time series environmental monitoring information, is the mean of the temporal environmental monitoring information.

[0115] Step S102, obtaining centralized time-series environmental monitoring information and root mean square error values, and constructing a characteristic decomposition matrix based on the centralized time-series environmental monitoring information and root mean square error values;

[0116] In this embodiment, constructing a eigendecomposition matrix based on centralized time-series environmental monitoring information and root mean square error values ​​can, on the one hand, simplify the model calculation process and improve algorithm efficiency; on the other hand, by constructing a eigendecomposition matrix, a balance can be found between the centralization of the model and the root mean square error value, thereby reducing the risk of overfitting and improving the model's prediction performance on new data.

[0117] It should be noted that the method for constructing the eigendecomposition matrix based on the centralized time-series environmental monitoring information and the root mean square error value can be: find the eigenvalues ​​and eigenvectors of those centralized time-series environmental monitoring information and the root mean square error value. Then, find the eigenvector corresponding to the eigenvalue by solving the linear equation system, and standardize it into a unit vector, and then construct the eigendecomposition matrix.

[0118] Step S103, performing dimensionality reduction processing on the eigendecomposition matrix to obtain a dimensionality-reduced eigendecomposition matrix;

[0119] Step S104, extracting significant features of the time-series environmental monitoring information based on the Bayesian algorithm, and integrating to obtain a normalized evaluation feature vector;

[0120] Among them, the significant feature extraction function is:

[0121] (4)

[0122] To normalize the evaluation feature vector, is the significance conversion coefficient. In this embodiment, the significance conversion coefficient can be set to 0.01-0.02. is the magnitude of significant change;

[0123] (5)

[0124] in, is the significance transformation coefficient, is the magnitude of significant change.

[0125] The embodiment of the present invention provides a method for pre-constructing an environmental assessment early warning model based on principal component analysis combined with random forests. Figure 3The schematic diagram of the implementation process of the method for pre-constructing an environmental assessment and early warning model based on principal component analysis combined with random forest is shown. The method for pre-constructing an environmental assessment and early warning model based on principal component analysis combined with random forest specifically includes:

[0126] Step S201, obtaining a model training sample, wherein the model training sample is historical environmental monitoring information, and preprocessing the model training sample;

[0127] It should be noted that the model training samples are also multi-source heterogeneous environmental monitoring information. The model training samples can be indexed from the multi-function monitoring instrument 10 or obtained from a shared platform, and the method of preprocessing the model training samples is the same as the preprocessing of the collected time-series environmental monitoring information.

[0128] Step S202, initialize the random forest model, build a feature evaluator based on principal component analysis combined with the SimAM attention mechanism, and define the weighting function of the feature evaluator on the sample features, where the weighting function of the feature evaluator on the sample features is expressed as:

[0129] (6)

[0130] in, is the weight value of the sample feature, The number of neurons in the feature judger can be 10-100. is the weight deviation coefficient set for the feature evaluator. In this embodiment, the weight deviation coefficient can be set to 0.1 or 0.2. is the dimension of the feature vector. In this embodiment, the feature vector is a normalized evaluation feature vector, and the feature dimension of the normalized evaluation feature vector may be 2 or 3. Normalized evaluation feature vector for model training samples;

[0131] Step S203, training the weighted model training samples to initialize the random forest model, and obtaining a random forest decision tree layer that is good at air pollution detection;

[0132] Step S204, incorporating the feature evaluator, the random forest decision tree layer, and the pollution calculation network into the initialized random forest model to obtain an environmental assessment early warning model.

[0133] In this embodiment, the pollution calculation network can be a yolov8 model backbone network that introduces the K-means algorithm, the input layer is connected to the feature evaluator, the feature evaluator is connected to the random forest decision tree layer, and the pollution calculation network is connected to the output layer

[0134] The environmental assessment and early warning model includes an input layer, a feature evaluator, a random forest decision tree layer, a pollution calculation network and an output layer.

[0135] In an embodiment of the present invention, an environmental assessment and early warning model based on principal component analysis combined with random forest is provided. The environmental assessment and early warning model is an improved random forest model, and the SimAM attention mechanism is introduced to construct a feature evaluator during model construction. At the same time, the combination of principal component analysis and random forest can integrate the advantages of principal component analysis in extracting significant features and the advantages of random forest in long-distance modeling, thereby better extracting features of multi-source heterogeneous data and improving the accuracy of random forest decision tree layers and feature evaluators.

[0136] The embodiment of the present invention provides a method for identifying and analyzing normalized evaluation feature vectors of an environmental assessment early warning model and calculating a comprehensive pollution degree. Figure 4 The figure shows a schematic diagram of the implementation process of the environmental assessment early warning model identifying and analyzing the normalized assessment feature vector and calculating the comprehensive pollution degree method. The environmental assessment early warning model identifying and analyzing the normalized assessment feature vector and calculating the comprehensive pollution degree method specifically includes:

[0137] Step S301, obtaining a normalized evaluation feature vector, and the feature evaluator in the environmental assessment early warning model identifies abnormal feature factors of the normalized evaluation feature vector based on the K-means algorithm;

[0138] Among them, the abnormal feature factor extraction function is:

[0139] (7);

[0140] Extract the value of the abnormal characteristic factor. When extracting, set the abnormal characteristic factor judgment value to , by comparing the abnormal feature factor extraction value with the abnormal feature factor judgment value, the feature factor in the normalized evaluation feature vector is determined to be an abnormal feature factor, where, is the extraction base, in this embodiment, the extraction base may be 0.3-0.8;

[0141] Step S302, inputting the abnormal characteristic factor judgment value of the abnormal characteristic factor into the random forest decision tree layer to calculate the comprehensive pollution degree;

[0142] (8)

[0143] in, is the comprehensive pollution degree, is the bias coefficient. In this embodiment, the bias coefficient can be updated by an optimization algorithm such as gradient descent to minimize the loss function. The bias coefficient can be set to 1-5.

[0144] In this embodiment, the comprehensive pollution degree is used to characterize the degree of environmental pollution. When calculating the comprehensive pollution degree, the environmental assessment and early warning model combines multiple pollution factors such as dust pollution, noise pollution, and air quality pollution, thereby achieving a comprehensive assessment of environmental pollution.

[0145] Step S303, calculating the air pollution diffusion degree based on the comprehensive pollution degree;

[0146] The air pollution diffusion is calculated by formula (9):

[0147] (9)

[0148] in, is the air pollution diffusion, is the comprehensive pollution degree, and is the amount of data in the temporal environmental monitoring information set, is the wind speed feature vector in the time series environmental monitoring information set, It is the wind direction feature vector in the time series environmental monitoring information set.

[0149] On the other hand, the embodiment of the present invention also provides a smart construction site dust environment monitoring system. Figure 5 The control framework diagram of the smart construction site dust environment monitoring system is shown. The smart construction site dust environment monitoring system specifically includes:

[0150] A multifunctional monitoring instrument 10, wherein the multifunctional monitoring instrument 10 is used to collect time-series environmental monitoring information;

[0151] The data processing module 20 is used to pre-process the collected time-series environmental monitoring information, extract the significant features of the time-series environmental monitoring information, and obtain a normalized evaluation feature vector;

[0152] Model building module 30, the model building module 30 pre-builds an environmental assessment and early warning model based on principal component analysis combined with random forest, iteratively trains the improved environmental assessment and early warning model, and outputs the environmental assessment and early warning model;

[0153] The pollution comprehensive judgment module 40, based on the environmental assessment early warning model, identifies and analyzes the normalized assessment feature vector, calculates the comprehensive pollution degree, determines whether there is air pollution, and if there is air pollution, triggers the air pollution instruction, calculates the air pollution diffusion degree, and feeds back the air pollution degree and air pollution diffusion degree;

[0154] The dust reduction processing module 50 performs dust reduction processing on the construction site based on the dust reduction instruction.

[0155] It should be noted that the multifunctional monitor 10, the data processing module 20, the model building module 30, the pollution comprehensive judgment module 40, and the dust reduction processing module 50 use Bluetooth or a local area network to achieve data interaction. In an embodiment of the present invention, a smart construction site dust environment monitoring system is provided. The smart construction site dust environment monitoring system is composed of a multifunctional monitor 10, a data processing module 20, a model building module 30, a pollution comprehensive judgment module 40, and a dust reduction processing module 50. The multifunctional monitor 10 can accurately realize the collection of time-series environmental monitoring information, and the collection coverage area is larger and the accuracy is higher. The multifunctional monitor 10 and the dust reduction processing module 50 can optimize the dust reduction spray path based on the air pollution diffusion, thereby reducing the energy consumption of dust reduction operations and realizing smart green environmental protection construction.

[0156] The embodiment of the present invention provides a multifunctional monitoring instrument 10, Figure 6-Figure 7 The structure diagram of the multifunctional monitor 10 is shown. The multifunctional monitor 10 specifically comprises:

[0157] The monitoring instrument body includes a monitoring base 11, a support rod 12, an equipment support seat 13 and an adjustment mounting seat 14. The support rod 12 is rotatably mounted on the monitoring base 11, the equipment support seat 13 is detachably connected to the top of the support rod 12, and the adjustment mounting seat 14 is fixedly connected to the equipment support seat 13;

[0158] It should be noted that the monitoring base 11 can be a rectangular base or a round base. In order to facilitate the movement of the multifunctional monitor 10, multiple sets of movable rollers can be installed at the bottom of the monitoring base 11, and the equipment support seat 13 and the top of the support rod 12 can be connected by threading or plugging. The equipment support seat 13 and the adjustment mounting seat 14 can both be round seats or rings with hollow interiors, and the equipment support seat 13 and the adjustment mounting seat 14 are fixedly connected by snaps or bolts.

[0159] A multi-source data acquisition unit 3 installed on the equipment support 13, the multi-source data acquisition unit 3 is used to collect time-series environmental monitoring information;

[0160] The position adjustment component 2 includes a main body adjustment part 21 and a device adjustment part 22. The main body adjustment part 21 is installed on the monitoring base 11, and the main body adjustment part 21 is connected to the support rod 12. The main body adjustment part 21 is used to adjust the rotation angle of the support rod 12. The device adjustment part 22 is installed on the adjustment mounting seat 14, and the device adjustment part 22 is connected to the multi-source data acquisition part 3. The device adjustment part 22 is used to adjust the inclination angle of the multi-source data acquisition part 3.

[0161] In an embodiment of the present invention, a multifunctional monitoring instrument 10 is provided. The multifunctional monitoring instrument 10 realizes accurate collection of environmental monitoring data of different areas of the construction site through a multi-source data acquisition unit 3, thereby providing data support for the environmental assessment and early warning model to analyze and evaluate the construction environment. At the same time, the equipment adjustment unit 22 can synchronously adjust the positions of multiple groups of multi-source data acquisition units 3, which not only facilitates data collection, but also facilitates spray dust removal operations on the construction site.

[0162] In a further preferred embodiment of the present invention, Figure 6 As shown, the main body adjustment part 21 includes:

[0163] A first motor 211, wherein the first motor 211 is fixedly mounted on the monitoring base 11;

[0164] A first gear 212 fixedly connected to an output end of the first motor 211, wherein the first gear 212 is rotatably connected to an upper surface of the monitoring base 11;

[0165] A second gear 213 is fixedly sleeved on the outside of the support rod 12 , and the second gear 213 is meshed with the first gear 212 for transmission.

[0166] It should be noted that the first motor 211 can be a servo motor, and the first motor 211 is fixedly mounted on the monitoring base 11 by fastening bolts, the output end of the first motor 211 is fixedly connected to the first gear 212 by interference fit, and the second gear 213 is fixedly mounted on the outer wall of the support rod 12 by mortise and tenon or plug-in.

[0167] During operation, when the position and angle of the multi-source data acquisition unit 3 need to be adjusted, the first motor 211 is turned on. The start of the first motor 211 can drive the first gear 212 to rotate, so that the first gear 212 drives the second gear 213 and the support rod 12 to rotate, thereby realizing the adjustment of the position and angle of the multi-source data acquisition unit 3.

[0168] In this embodiment, the device adjustment unit 22 includes:

[0169] A second motor 221, the second motor 221 is fixedly mounted on the adjustment mounting seat 14, the output end of the second motor 221 is fixedly connected to a transmission gear plate 222, and the transmission gear plate 222 is rotatably mounted on one side of the adjustment mounting seat 14;

[0170] It should be noted that the second motor 221 can be a single-phase asynchronous motor, and the output end of the second motor 221 is fixedly connected to the transmission gear disc 222 by interference fit, and the transmission gear disc 222 is rotatably connected to the side wall of the adjustment mounting seat 14 through rollers or bearings.

[0171] At least one set of third gears 223, the third gears 223 are arranged on one side of the transmission gear plate 222, and the third gears 223 and the transmission gear plate 222 are meshed and transmitted, a transmission screw 224 is fixedly connected to one side of the third gear 223, the transmission screw 224 is rotatably connected to the side wall of the adjustment mounting seat 14, and a movable gear seat 225 is threadedly sleeved on one end of the transmission screw 224 away from the third gear 223, and the movable gear seat 225 is slidably connected to the equipment support seat 13 through a guide block 226;

[0172] A fourth gear 227, the fourth gear 227 is rotatably mounted on the equipment support seat 13, the fourth gear 227 is meshed with the mobile gear seat 225 for transmission, and the fourth gear 227 is also connected to the multi-source data acquisition unit 3;

[0173] In this embodiment, the number of the third gears 223 can be three groups or four groups, and the third gears 223 are riveted or welded to the end of the transmission screw 224, and the transmission screw 224 is rotatably connected to the side wall of the adjustment mounting seat 14 through a bearing, and the movable gear seat 225 is a threaded seat with a hollow interior, and the side wall of the movable gear seat 225 is provided with a guide groove, and the guide groove is slidably connected to the guide block 226, and the guide block 226 is fixedly connected to the equipment support seat 13 through a support rod or a fastening bolt, and the fourth gear 227 is rotatably connected to the equipment support seat 13 through a bearing or a rotating shaft.

[0174] A negative pressure transmission shaft 228 is fixedly connected to the transmission gear plate 222 , and at least one set of negative pressure dust extraction fans 229 are detachably mounted on the end of the negative pressure transmission shaft 228 , and the negative pressure dust extraction fans 229 are used to assist in cleaning the multi-source data acquisition unit 3 .

[0175] In this embodiment, when the spray angle or the data collection angle needs to be adjusted, the second motor 221 is turned on. The start of the second motor 221 can drive the transmission gear plate 222 to rotate, so that the transmission gear plate 222 synchronously drives the multiple groups of third gears 223 to rotate, and the third gear 223 drives the transmission screw 224 to rotate. When the transmission screw 224 rotates, it can drive the mobile gear seat 225 to move, so that the mobile gear seat 225 drives the fourth gear 227 to rotate, and the rotation of the fourth gear 227 drives the multi-source data acquisition unit 3 to swing, which facilitates the adjustment of the spray angle and the data collection angle.

[0176] In a further preferred embodiment of the present invention, Figure 8-Figure 10 As shown, the multi-source data acquisition unit 3 includes:

[0177] A collector controller 31, wherein the collector controller 31 is fixedly connected to the fourth gear 227;

[0178] A collection swing seat 32 is installed on the collection instrument controller 31, and multiple groups of atomizing spray ports 33 are embedded in the collection swing seat 32. The atomizing spray ports 33 are connected to a water storage tank through a telescopic water pipe 34. The atomizing spray ports 33 perform dust reduction treatment on the construction site based on the dust reduction instruction.

[0179] It should be noted that the collector controller 31 can be a PLC controller, and the collector controller 31 is also electrically connected to the first motor 211 and the second motor 221. The collector controller 31 is used to control the opening and closing of the first motor 211 and the second motor 221. The collector controller 31 is also communicatively connected to the data processing module 20, the model building module 30, the comprehensive pollution judgment module 40, and the dust reduction processing module 50.

[0180] In this embodiment, the atomizing spray port 33 is arranged in a matrix or linear manner on the side wall of the collection swing seat 32, and a high-pressure atomizing nozzle is arranged in the atomizing spray port 33. The arrangement of the atomizing spray port 33 and the high-pressure atomizing nozzle facilitates the dust reduction treatment of the construction environment. The collection swing seat 32 can be a rectangular seat or a "T"-shaped seat structure with a hollow interior. One end of the collection swing seat 32 is clamped or fixedly connected to the side wall of the collection instrument controller 31 by a fastening bolt.

[0181] The CCD camera 35 installed on the collection swing seat 32 is used to collect dust particle shooting data, wherein the CCD camera 35 directly captures the light changes in the image through the photoelectric elements on its sensor, converts the light signal into an electrical signal, and finally forms a digital image. When shooting dust and dust, the light reflected or scattered by these particles is captured and recorded by the CCD sensor, thereby showing the existence of dust and dust in the image.

[0182] A dust sensor 37, wherein the dust sensor 37 is used to collect dust content data;

[0183] The noise collector 36 is used to collect noise monitoring data. In this embodiment, the noise collector 36 can be a rectangular plate or a fan-shaped plate structure. The noise collector 36 has a built-in microphone, which can convert the received sound waves into electrical signals. This conversion is based on the vibration of the film inside the microphone caused by the sound waves, which in turn generates a voltage change to achieve the conversion from the sound signal to the electrical signal. In the embodiment of the present invention, the noise sensor can be a CRY2110 sensor with a measurement range of 25-130dBA and a sampling rate of 48kHz.

[0184] An air quality monitor 38, which is used to collect air quality data. In this embodiment, the air quality monitor 38 can measure the concentration of pollutants such as sulfur dioxide, nitrogen dioxide, PM10, and PM2.5;

[0185] Wind speed collector 39, the wind speed collector 39 is used to collect wind speed monitoring data, the wind speed collector 39 output mode selects RS485, the wind speed collector 39 can be mechanical or ultrasonic;

[0186] The collector controller 31 is electrically connected to the CCD camera 35 , the dust sensor 37 , the noise collector 36 , the air quality monitor 38 and the wind speed collector 39 .

[0187] In this embodiment, the CCD camera 35, the dust sensor 37, the noise collector 36, the air quality monitor 38 and the wind speed collector 39 are installed on the end of the collection swing seat 32 by means of snaps or fastening bolts.

[0188] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program instructions, and the computer program instructions can be executed by a processor. When the computer program instructions are executed, the method of any of the above embodiments is implemented.

[0189] The computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. Volatile memory may include a random access memory (RAM), which may serve as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0190] In summary, the present invention provides a smart construction site dust environment monitoring method, system and storage medium. In the embodiments of the present invention, by preprocessing the collected time-series environmental monitoring information, extracting the significant features of the time-series environmental monitoring information, and obtaining a normalized evaluation feature vector, the collected multi-source heterogeneous data can be normalized, thereby accurately extracting the significant features of the data, ensuring that the true data distribution can be learned on the training data when constructing and training an environmental assessment and early warning model based on principal component analysis combined with random forests, effectively reducing the risk of model overfitting, and ensuring the accuracy of the comprehensive pollution assessment.

[0191] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A smart construction site dust environment monitoring method, characterized in that: The smart construction site dust environment monitoring method comprises: Based on the multifunctional monitoring instrument, the time-series environmental monitoring information is collected, wherein the time-series environmental monitoring information is multi-source heterogeneous measurement data, and the time-series environmental monitoring information includes air quality data, dust content data, noise monitoring data, wind speed monitoring data, and dust particle shooting data. The collected time-series environmental monitoring information is pre-processed, and the significant features of the time-series environmental monitoring information are extracted to obtain a normalized evaluation feature vector; Pre-build an environmental assessment and early warning model based on principal component analysis combined with random forest, iterate and train the improved environmental assessment and early warning model, and output the environmental assessment and early warning model; The environmental assessment early warning model identifies and analyzes the normalized assessment feature vector, calculates the comprehensive pollution degree, and determines whether there is air pollution. If there is air pollution, it triggers the air pollution instruction; The pollution calculation network in the environmental assessment and early warning model responds to the air pollution instruction, loads the normalized assessment feature vector, calculates the air pollution diffusion, and feeds back the air pollution degree and air pollution diffusion; The method for pre-constructing an environmental assessment and early warning model based on principal component analysis combined with random forest specifically includes: Obtaining model training samples, wherein the model training samples are historical environmental monitoring information, and preprocessing the model training samples; Initialize the random forest model, build a feature evaluator based on principal component analysis combined with the SimAM attention mechanism, and define the weighting function of the feature evaluator on sample features. The weighting function of the feature evaluator on sample features is expressed as: （6） in, is the weight value of the sample feature, is the number of neurons in the feature judge, The weight bias coefficient set for the feature evaluator, is the dimension of the feature vector, Normalized evaluation feature vector for model training samples; The weighted model training samples are trained to initialize the random forest model, and a random forest decision tree layer that is good at air pollution detection is obtained; The feature evaluator, random forest decision tree layer, and pollution calculation network are incorporated into the initial random forest model to obtain an environmental assessment and early warning model; The environmental assessment and early warning model includes an input layer, a feature evaluator, a random forest decision tree layer, a pollution calculation network and an output layer; The method of identifying and analyzing the normalized evaluation feature vector and calculating the comprehensive pollution degree by the environmental assessment early warning model specifically includes: A normalized evaluation feature vector is obtained, and the feature evaluator in the environmental assessment early warning model identifies abnormal feature factors of the normalized evaluation feature vector based on the K-means algorithm; Among them, the abnormal feature factor extraction function is: （7）； Extract the value of the abnormal characteristic factor. When extracting, set the abnormal characteristic factor judgment value to , by comparing the abnormal feature factor extraction value with the abnormal feature factor judgment value, the feature factor in the normalized evaluation feature vector is determined to be an abnormal feature factor, where, To extract the base number; The abnormal characteristic factor judgment value of the abnormal characteristic factor is input into the random forest decision tree layer to calculate the comprehensive pollution degree; （8） in, is the comprehensive pollution degree, is the bias coefficient.

2. The method for monitoring dust environment at a smart construction site according to claim 1, characterized in that: The smart construction site dust environment monitoring method further includes: The multifunctional monitor obtains the air pollution degree and air pollution diffusion degree, triggers the dust reduction instruction, and performs dust reduction treatment on the construction site based on the dust reduction instruction.

3. The method for monitoring dust environment at a smart construction site according to claim 1, characterized in that: The preprocessing of the collected time-series environmental monitoring information specifically includes: Acquire time series environmental monitoring information, perform first preprocessing and second preprocessing on the time series environmental monitoring information, and obtain a first preprocessing set and a second preprocessing set, wherein the first preprocessing is a preprocessing of setting the mean of the monitoring information to 0, and the second preprocessing is a preprocessing of setting the root mean square error of the monitoring information to 1; Among them, the collection of temporal environmental monitoring information is , the formula for setting the mean of monitoring information to 0 is: （1） Centralized time-series environmental monitoring information. is the mean value of monitoring information; （2） in, is the amount of data in the temporal environmental monitoring information set, It is the input time series environmental monitoring information; （3） in, is the root mean square error of the time series environmental monitoring information, is the mean value of the time series environmental monitoring information; Obtain centralized time-series environmental monitoring information and root mean square error values, and construct a characteristic decomposition matrix based on the centralized time-series environmental monitoring information and root mean square error values; Perform dimensionality reduction processing on the eigendecomposition matrix to obtain the eigendecomposition matrix after dimensionality reduction; Based on the Bayesian algorithm, the significant features of the temporal environmental monitoring information are extracted and integrated to obtain the normalized evaluation feature vector. Among them, the significant feature extraction function is: （4） To normalize the evaluation feature vector, is the significance transformation coefficient, is the magnitude of significant change; （5） in, is the significance transformation coefficient, is the magnitude of significant change.

4. A smart construction site dust environment monitoring system, implemented by the smart construction site dust environment monitoring method as described in any one of claims 1 to 3, characterized in that: The smart construction site dust environment monitoring system includes: A multifunctional monitor, which is used to collect time-series environmental monitoring information; A data processing module, which is used to pre-process the collected time-series environmental monitoring information, extract the significant features of the time-series environmental monitoring information, and obtain a normalized evaluation feature vector; Model building module: The model building module pre-builds an environmental assessment and early warning model based on principal component analysis combined with random forest, iteratively trains the improved environmental assessment and early warning model, and outputs the environmental assessment and early warning model; Pollution comprehensive judgment module: The pollution comprehensive judgment module identifies and analyzes the normalized evaluation feature vector based on the environmental assessment and early warning model, calculates the comprehensive pollution degree, and determines whether there is air pollution. If there is air pollution, it triggers the air pollution instruction, calculates the air pollution diffusion degree, and feeds back the air pollution degree and air pollution diffusion degree; A dust reduction processing module performs dust reduction processing on the construction site based on dust reduction instructions; The multifunctional monitor comprises: The monitoring instrument body comprises a monitoring base, a support rod, an equipment support seat and an adjustment mounting seat, wherein the support rod is rotatably mounted on the monitoring base, the equipment support seat is detachably connected to the top of the support rod, and the adjustment mounting seat is fixedly connected to the equipment support seat; A multi-source data acquisition unit installed on the equipment support, the multi-source data acquisition unit is used to collect time-series environmental monitoring information; A position adjustment component, the position adjustment component includes a main body adjustment part and a device adjustment part, the main body adjustment part is installed on the monitoring base, the main body adjustment part is connected to the support rod, the main body adjustment part is used to adjust the rotation angle of the support rod, the device adjustment part is installed on the adjustment mounting seat, the device adjustment part is connected to the multi-source data acquisition part, and the device adjustment part is used to adjust the tilt angle of the multi-source data acquisition part; The main body adjustment part comprises: A first motor, wherein the first motor is fixedly mounted on a monitoring base; A first gear fixedly connected to the output end of the first motor, wherein the first gear is rotatably connected to the upper surface of the monitoring base; A second gear fixedly sleeved on the outside of the support rod, the second gear meshing with the first gear for transmission; The equipment adjustment unit comprises: A second motor, wherein the second motor is fixedly mounted on the adjustment mounting seat, an output end of the second motor is fixedly connected to a transmission gear plate, and the transmission gear plate is rotatably mounted on one side of the adjustment mounting seat; At least one set of third gears, the third gears are arranged on one side of the transmission gear disc, and the third gears are meshed with the transmission gear disc for transmission, a transmission screw is fixedly connected to one side of the third gear, the transmission screw is rotatably connected to the side wall of the adjustment mounting seat, a threaded sleeve is provided with a movable gear seat at one end of the transmission screw away from the third gear, and the movable gear seat is slidably connected to the equipment support seat through a guide block; A fourth gear, the fourth gear is rotatably mounted on the equipment support seat, the fourth gear is meshed with the mobile gear seat for transmission, and the fourth gear is also connected to the multi-source data acquisition unit; A negative pressure transmission shaft is fixedly connected to the transmission gear disc, and at least one group of negative pressure dust extraction fans are detachably mounted on the end of the negative pressure transmission shaft, and the negative pressure dust extraction fans are used to assist in cleaning the multi-source data acquisition unit.

5. The intelligent construction site dust environment monitoring system according to claim 4, characterized in that: The multi-source data acquisition unit comprises: A collector controller, wherein the collector controller is fixedly connected to the fourth gear; A collection swing seat installed on the collector controller, wherein a plurality of atomizing spray ports are embedded in the collection swing seat, wherein the atomizing spray ports are connected to a water storage tank via a telescopic water pipe, and the atomizing spray ports perform dust reduction treatment on the construction site based on a dust reduction instruction; A CCD camera installed on the collection swing seat, the CCD camera is used to collect dust particle shooting data; A dust sensor, wherein the dust sensor is used to collect dust content data; A noise collector, wherein the noise collector is used to collect noise monitoring data; Air quality monitor, the air quality monitor is used to collect air quality data; A wind speed collector, which is used to collect wind speed monitoring data; The collector controller is electrically connected to the CCD camera, the dust sensor, the noise collector, the air quality monitor and the wind speed collector respectively.

6. A computer-readable storage medium, characterized in that: Computer program instructions are stored, and when the computer program instructions are executed, the smart construction site dust environment monitoring method as described in any one of claims 1-3 is implemented.

Images