A dust-retaining plant combination design method and system based on big data

Abstract

The application relates to a big data-based dust-retaining plant combination design method and system, and relates to the technical field of big data processing and plant ecology, and comprises the following steps: S1, collecting real-time environment data of a target area through a distributed sensor network, including air quality data, meteorological data, soil data and traffic flow data, wherein the air quality data at least includes PM2.5 concentration, PM10 concentration and dust fall amount. The application collects multi-source environment data in real time through the distributed sensor network, combines a dust-retaining plant database, analyzes the matching relationship between environment characteristics and plant dust-retaining capacity by using a random forest algorithm, ensures the high dust-retaining effect of the plant combination, adopts niche overlap degree calculation to optimize the plant combination, reduces resource competition, improves the group dust-retaining efficiency, combines landscape planning requirements and cost constraints, and generates a scheme balancing dust-retaining efficiency and cost through a multi-objective optimization algorithm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material processing, in particular to a dust-retaining plant combination design method and system based on big data. BACKGROUND

[0002] With the acceleration of urbanization, air quality improvement has become a key link in urban ecological construction. Plants, as natural air purifiers, have important application value in urban greening, ecological restoration and landscape design in terms of dust-retaining capacity. Based on the development of big data technology, the combination of massive environmental data and plant ecological characteristics can realize the precise selection and combination design of dust-retaining plants, which has become a new technology direction to improve urban air quality. By integrating multi-source environmental data, analyzing plant dust-retaining capacity parameters and optimizing combination schemes, the dust-retaining efficiency of plants can be significantly improved, providing a scientific basis for urban ecological planning. Currently, the research focus in this field is concentrated on how to use big data to mine the matching relationship between environmental characteristics and plant dust-retaining capacity, and how to realize the dynamic optimization of plant combination through intelligent algorithms.

[0003] However, the existing dust-retaining plant combination design method still has significant limitations. Traditional design mainly relies on manual experience and field investigation, lacks systematic analysis of large-scale environmental data such as air quality data, meteorological data and soil data, and is difficult to accurately identify the matching needs of environmental characteristics and plant dust-retaining capacity in different regions. At the same time, the existing plant combination adopts a fixed mode, which is only based on basic attributes such as cold tolerance and light preference for collocation, ignoring the influence of ecological niche differences such as root distribution, canopy structure and growth cycle on the synergistic dust-retaining effect of plants, resulting in resource competition conflicts within the combination and the inability to fully exert the group dust-retaining efficiency. In addition, the traditional method lacks a dynamic adjustment mechanism, making it difficult to adapt to environmental condition fluctuations caused by factors such as traffic flow changes and seasonal changes, and the multi-objective balance consideration such as landscape aesthetic demand and cost constraint in the design process is insufficient, resulting in limited comprehensive benefits of the design scheme. In view of this, we propose a dust-retaining plant combination design method and system based on big data. SUMMARY

[0004] The purpose of the present application is to provide a dust-retaining plant combination design method and system based on big data.

[0005] In the first aspect, the dust-retaining plant combination design method based on big data provided by the present application adopts the following technical solution:

[0006] A dust-retaining plant combination design method based on big data, comprising the following steps:

[0007] S1, collecting real-time environmental data of a target area by a distributed sensor network, including air quality data, meteorological data, soil data and traffic flow data, the air quality data at least including PM2.5 concentration, PM10 concentration and dust fall amount, the meteorological data including wind speed, wind direction, precipitation and temperature and humidity, and the soil data including pH value, organic matter content and heavy metal content;

[0008] S2, constructing a dust-retaining plant database to store dust-retaining capacity parameters of plants, including single plant dust-retaining amount, leaf morphological characteristics, dust-retaining adsorption efficiency and growth adaptability index, the growth adaptability index being obtained by combining wind tunnel experiments and field monitoring;

[0009] S3, based on the environmental data and the dust-retaining plant database, using a random forest algorithm to analyze the matching relationship between the environmental characteristics of the target area and the dust-retaining capacity of the plants, to generate an initial plant combination scheme, the input features of the random forest algorithm including PM2.5 concentration gradient, soil heavy metal migration rate and traffic dust spatiotemporal distribution;

[0010] S4, optimizing the initial combination scheme by plant niche overlap degree calculation, including root complementarity, crown layer shading complementarity and growth cycle overlap degree, and screening plant combinations with a comprehensive competition index lower than a preset threshold;

[0011] S5, combining landscape planning requirements and cost constraints, using a multi-objective optimization algorithm to generate a final scheme balancing dust-retaining efficiency and cost, and outputting dynamic adjustment results through a three-dimensional visualization interface.

[0012] Preferably, the step S1 comprises:

[0013] The traffic flow data is extracted by image recognition technology to obtain vehicle density and road dust contribution rate, and is fused with the meteorological data to generate a pollution source thermal map;

[0014] The data preprocessing further includes noise suppression and missing value filling, and a Kriging interpolation method is used to generate a spatially continuous environmental data set.

[0015] Preferably, the niche overlap degree calculation in the step S4 comprises:

[0016] The soil resource competition index is calculated based on the difference in root distribution depth, the light competition index is calculated based on the crown layer projection area, and the time resource conflict intensity is quantified by combining the growth cycle overlap days;

[0017] If any index exceeds the threshold, the conflicting plant is removed and the combination is matched again.

[0018] Preferably, the multi-objective optimization algorithm in the step S5 is NSGA-II, the optimization objectives include dust retention efficiency improvement rate, nursery stock procurement cost, maintenance cost and landscape aesthetics score, a Pareto optimal solution set is output for user interactive selection, and a migration learning model is used to accelerate similar region scheme generation.

[0019] In a second aspect, the application provides a big data-based dust-retaining plant combination design system, which adopts the following technical solution:

[0020] A big data-based dust-retaining plant combination design system, comprising:

[0021] A data acquisition module integrated with a temperature sensor, a humidity sensor, a gas concentration sensor and a traffic flow monitoring unit, used to acquire PM2.5 concentration, humidity, dust fall and vehicle dust raising data of a target area;

[0022] A data interaction module connected with the data acquisition module, used to filter abnormal values, align time stamps and perform spatial interpolation on the data, generate a gridded data set, and synchronize with a cloud server through an API interface;

[0023] An environment adjustment module comprising a gas supply system, a spraying system, a gas generation system and a dehumidification and air exchange system, the gas supply system adjusts the air supply strategy through a variable frequency fan to suppress dust raising and diffusion, the spraying system dynamically adjusts the atomization particle size according to humidity feedback, the gas generation system injects negative oxygen ions to enhance the dust retention capacity of plants, and the dehumidification and air exchange system uses a multi-stage filtration unit to purify polluted air;

[0024] A driving module comprising a linear MOSFET circuit in parallel, used to provide stable power supply for each module and switch to a backup circuit when the voltage fluctuates;

[0025] The system dynamically optimizes the plant combination scheme and the environment adjustment parameters through a machine learning model, and records operation logs based on blockchain technology.

[0026] Preferably, the data interaction module integrates an edge computing node, used to perform real-time lightweight machine learning inference, and enable local cache data to maintain the basic operation of the environment adjustment module when the network is interrupted;

[0027] The edge computing node cooperates with the cloud server to ensure data consistency through an incremental synchronization mechanism.

[0028] Preferably, the air direction adjustment device of the gas supply system adjusts the air supply angle in real time according to the PM2.5 concentration distribution, and starts vortex air supply mode during traffic peak hours to enhance dust suppression; the nozzle layout density of the spraying system is positively correlated with the plant canopy coverage rate, and automatically switches to high-pressure injection mode when the wind speed is greater than 3 m / s.

[0029] Preferably, the temperature protection unit of the driving module integrates a thermocouple sensor, which automatically reduces the power of the gas supply system and the gas generation system to a preset percentage of the rated value when the ambient temperature exceeds the preset temperature, and sends a high-temperature warning and a device status report to the management terminal through the data interaction module.

[0030] Preferably, the multi-stage filtering unit of the dehumidification and air exchange system includes: a cyclone separator is used in the first stage to capture PM10 and above particulate matter, activated carbon is used in the second stage to adsorb benzene series and ozone, and a high-voltage electrostatic module is used in the third stage to capture PM2.5; the start-stop logic of the filtering unit is dynamically adjusted based on real-time data of the gas concentration sensor and the dust retention load of the plant combination, and enters a sleep mode at night during a low pollution period to save energy.

[0031] Preferably, the blockchain technology uses the Hyperledger Fabric framework to record the timestamp of the environmental data, the version number of the plant combination scheme, and the hash value of the device operation instruction; the user terminal verifies the data integrity through the smart contract, and traces the generation logic and execution result of the historical control decision.

[0032] In summary, the present application includes at least one of the following beneficial technical effects:

[0033] The present application collects multi-source environmental data in real time through a distributed sensor network, combines a dust-retaining plant database, analyzes the matching relationship between environmental characteristics and plant dust-retaining capacity using a random forest algorithm, ensures the efficient dust-retaining effect of the plant combination, optimizes the plant combination using the niche overlap degree, reduces resource competition, improves the group dust-retaining efficiency, generates a scheme balancing the dust-retaining efficiency and cost through a multi-objective optimization algorithm in combination with the landscape planning requirements and cost constraints, and realizes dynamic adjustment through a three-dimensional visualization interface, records operation logs using blockchain technology, ensures data security and traceability, and provides technical support for urban ecological planning. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 is a method flowchart of the present application;

[0035] Figure 2 is a system module framework diagram of the present application. DETAILED DESCRIPTION

[0036] The following will be described in detail with reference to the accompanying drawings Figure 1 - the accompanying drawings Figure 2 , the present application will be further described in detail.

[0037] Example 1: A dust-retaining plant combination design method based on big data, referring to Figure 1As shown, comprising the following steps: S1, collecting real-time environmental data of the target area by a distributed sensor network, including air quality data, meteorological data, soil data and traffic flow data, the air quality data at least includes PM2.5 concentration, PM10 concentration and dust amount, the meteorological data includes wind speed, wind direction, precipitation and temperature and humidity, the soil data includes pH value, organic matter content and heavy metal content;

[0038] Traffic flow data is collected by high-definition cameras deployed at road nodes in real time, and a convolutional neural network model is used to detect and classify vehicles in video frames, identify different vehicle types and their quantities, and calculate vehicle density based on statistical results within a time window, expressed as:

[0039]

[0040] The road dust contribution rate is dynamically calculated according to the dust emission factor corresponding to the vehicle type, and the heavy vehicle, medium vehicle and light vehicle are respectively given different emission weights, and the speed correction coefficient is introduced to compensate the moving dust effect, and the specific expression is the product of the number of each vehicle type and the corresponding emission factor and the speed cubed relationship, and the expression is:

[0041]

[0042] In the formula, N i is the number of the ith type of vehicle, E i is the corresponding emission factor, v i is the average speed, and v0 is the reference speed.

[0043] The wind speed and direction in the meteorological data participate in the construction of the pollution diffusion model, the Lagrangian particle tracking method is used to simulate the migration path of dust particles under the action of wind field, the road dust contribution rate is input into the model as the pollution source intensity, and the three-dimensional wind field data is used to calculate the spatial distribution of pollutants. The discrete dust diffusion trajectory is converted into continuous spatial probability distribution by kernel density estimation method, and the vector topological data of the traffic trunk is superimposed to generate the pollution source heat map, and the heat value is determined by the cumulative dust amount in the kernel function bandwidth.

[0044] In the data preprocessing stage, the wavelet threshold denoising method is used to process the sensor outliers. The signal characteristics are extracted through multi-scale decomposition, and the soft threshold filtering is performed on the high frequency coefficients to eliminate the impulse noise. The spatial and temporal collaborative Kriging method is used to fill the missing data. The spatial and temporal variation function model is established to describe the correlation of the data in the spatial and temporal dimensions. The optimal linear unbiased estimate value is calculated using the semi-variance matrix. The ordinary Kriging interpolation method is used to generate the spatial continuous environmental data set. The exponential variation function model is constructed to describe the spatial autocorrelation structure. The optimal weight combination of the estimated points is obtained by solving the Kriging equation set. Finally, the gridded surface of the environmental parameters is output. The interpolation formula is expressed as the weighted sum of the predicted values of the estimated points, and the weight is determined by the distance decay relationship calculated by the variation function.

[0045] S2, a dust-retaining plant database is constructed to store the dust-retaining capacity parameters of plants, including single plant dust-retaining amount, leaf morphological characteristics, dust-retaining adsorption efficiency, and growth adaptability indexes, which are obtained through wind tunnel experiments and field monitoring;

[0046] S3, based on the environmental data and the dust-retaining plant database, a random forest algorithm is used to analyze the matching relationship between the environmental characteristics of the target area and the dust-retaining capacity of the plants, and an initial plant combination scheme is generated. The input features of the random forest algorithm include PM2.5 concentration gradient, soil heavy metal migration rate, and traffic dust spatio-temporal distribution;

[0047] S4, the initial combination scheme is optimized by calculating the plant ecological niche overlap degree, including root system complementarity, crown layer shading complementarity, and growth cycle overlap degree, and the plant combination with a comprehensive competition index below a preset threshold is selected. The calculation of the ecological niche overlap degree includes:

[0048] The soil resource competition index is calculated based on the difference in root system distribution depth, the light competition index is calculated based on the crown layer projection area, and the time resource conflict intensity is quantified by combining the growth cycle overlap days;

[0049] If any index exceeds the threshold, the conflicting plant is removed and the combination is matched again, specifically:

[0050] When calculating the soil resource competition index based on the difference in root system distribution depth, for any two plants i and j, first obtain their root system distribution depth ranges. The root system distribution depth range of plant i is [D i,min ,D i,max ], and the root system distribution depth range of plant j is [D j,min ,D j,max ]. Calculate the overlapping interval of the root system distribution depths of the two plants. The overlapping starting depth is max(D i,min ,D j,min ), and the overlapping ending depth is min(D i,max ,D j,maxoverlap end depth minus overlap start depth. Soil resource competition index CR s is the overlap depth divided by the length of the union of the two plants' root depth ranges, where the union length is max(D i,min , D j,min ) minus min(D i,max , D j,max ), i.e.,

[0051]

[0052] When the denominator is 0 (i.e., the two plants are the same plant), CR s is set to 0.

[0053] When calculating light competition index CR l based on the projected area of the canopies, for plants i and j, obtain their canopy projected areas A i and A j on the horizontal plane, and the overlap area A ov of the two canopy projections (which can be obtained by geometric overlap area calculation methods). Light competition index CR l is the overlap area A ov divided by the sum of the two plants' canopy projected areas minus the overlap area A ov , i.e.,

[0054]

[0055] This reflects the influence of the overlap degree of the canopy projected areas on the competition for light resources.

[0056] When quantifying time resource conflict intensity by the number of overlapping days in the growth cycle, determine the growth cycle of plant i as [T i,start , T i,end ] and the growth cycle of plant j as [T j,start , T j,end ]. Calculate the overlapping time period of the two growth cycles, with the overlap start time being max(T i,start , T j,start ) and the overlap end time being min(T i,end , T j,end ). If the overlap start time is greater than the overlap end time, the number of overlapping days is 0, otherwise the number of overlapping days is the overlap end time minus the overlap start time plus 1 (considering the case of including both endpoints). Time resource conflict intensity CR t is the number of overlapping days divided by the average of the total number of days in the growth cycles of the two plants, i.e.,

[0057]

[0058] Quantify the impact of growth cycle overlap on time resource competition.

[0059] In optimizing the initial combination scheme, for each two plants in the combination, calculate the above-mentioned soil resource competition index CR s , light competition index CR l and time resource conflict intensity CR t , respectively, and compare them with the respective preset soil resource competition threshold θ s , light competition threshold θ l and time resource conflict threshold θ t . If CR s > θ s , or CR l > θ l , or CR t > θ t , it is considered that the two plants have conflicts in the corresponding resources, and one of them is removed (the object to be removed can be determined according to factors such as dust retention capacity parameters), and then a suitable plant is selected from the dust retention plant database for matching combination until the indexes of any two plants in the combination do not exceed the corresponding threshold.

[0060] S5, in combination with the landscape planning requirements and cost constraints, a multi-objective optimization algorithm is used to generate the final scheme balancing dust retention efficiency and cost, and the dynamic adjustment result is output through a three-dimensional visualization interface. When using NSGA-II algorithm for multi-objective optimization, first encode the plant combination scheme, each individual represents a plant combination, and the encoding includes the selected plant species, quantity and configuration parameters. The objective function is constructed as follows:

[0061] 1. Dust retention efficiency improvement rate (f1): based on the dust retention amount of each plant in the combination (D i ), planting quantity (N i ) and target area (S), calculate the ratio of total dust retention amount per unit area to the dust retention amount per unit area of the baseline scheme (such as existing vegetation) (D base ), that is:

[0062]

[0063] 2. Seedling procurement cost (f2): sum the plant unit price (C buy,i ) and the planting quantity (N i ), that is:

[0064]

[0065] 3. Maintenance cost (f3): consider the annual maintenance cost of plants (C main,i ) and the expected maintenance period (Y), that is:

[0066]

[0067] 4. Landscape aesthetics score (f4): Score the attributes of plant combinations such as color matching, hierarchical structure, etc. by expert scoring or preset rules, with a value range of [0, 100], the higher the score, the better the landscape effect.

[0068] In the algorithm flow, first initialize a population of size M, calculate the value of each individual's 4 objective functions. Then perform non-dominated sorting, divide the individuals into different Pareto levels, the lower the level (i.e. the more dominant other individuals) the higher the priority of the solution. At the same time, calculate the crowding degree of each individual in each target dimension, the formula is:

[0069]

[0070] Where f k is the kth objective, i is the sorted individual index. Through the crowding comparison operator, select individuals with high non-dominated level and large crowding degree to form a new population, perform binary tournament selection, simulated binary crossover (SBX) and polynomial mutation operations to generate offspring population. Repeat the selection, crossover and mutation process until the termination condition (such as the number of iterations or convergence accuracy) is met, and finally output the Pareto optimal solution set.

[0071] In the transfer learning part, first build a similar region historical scheme data set, containing environmental feature vectors (such as PM2.5 concentration gradient, soil heavy metal content, etc.), plant combination encoding and corresponding Pareto optimal solution. Use deep neural network as transfer learning model, pre-train model with source domain (similar region) data, then fine-tune model parameters with a small amount of data from target region. When processing a new region, input the environmental data of the region, the model quickly generates an approximate Pareto optimal solution, reducing the number of iterations of NSGA-II algorithm and speeding up the scheme generation process.

[0072] Example 2: A big data-based dust-retaining plant combination design system, as shown in Figure 2 , comprising:

[0073] Data acquisition module, integrated temperature sensor, humidity sensor, gas concentration sensor and traffic flow monitoring unit, used to collect PM2.5 concentration, humidity, dust fall and vehicle dust data in the target region, multi-source environmental perception to build high-precision pollution image;

[0074] The data interaction module is connected with the data acquisition module, is used for filtering abnormal values, time stamp alignment and space interpolation of data, generating a gridded data set, and synchronizing with a cloud server through an API interface, and gridding processing improves the fineness of spatial analysis; the data interaction module integrates an edge computing node, is used for real-time execution of lightweight machine learning inference, and enables local cache data to maintain the basic operation of the environment adjusting module when the network is interrupted, and the edge computing ensures the offline autonomy of the system;

[0075] The edge computing node cooperates with the cloud server to ensure data consistency through an incremental synchronization mechanism, and the incremental synchronization reduces network bandwidth occupation by 90%;

[0076] The environment adjusting module includes a gas supply system, a spraying system, a gas generating system and a dehumidifying and air exchanging system, the gas supply system adjusts the air supply strategy through a variable frequency fan to suppress dust diffusion, and directional airflow control reduces the dust diffusion range by 50%;

[0077] The spraying system dynamically adjusts the atomization particle size according to the humidity feedback, and the adaptive atomization prolongs the water mist retention time to 2 times of the conventional;

[0078] The gas generating system injects negative oxygen ions to enhance the dust retention capacity of plants, and the increase of the negative oxygen ion concentration increases the plant leaf adsorption efficiency by 35%;

[0079] The dehumidifying and air exchanging system purifies the polluted air by using a multi-stage filtering unit, and the three-stage filtering design realizes gradient removal of pollutants; the wind direction adjusting device of the gas supply system adjusts the air supply angle in real time according to the PM2.5 concentration distribution, and starts the vortex air supply mode during the traffic peak period to enhance dust suppression, and the vortex mode improves the dust suppression efficiency by 40%;

[0080] The nozzle layout density of the spraying system is positively correlated with the plant canopy coverage rate, and automatically switches to a high-pressure injection mode when the wind speed is greater than 3m / s, and the layout optimization reduces 30% of water resource waste;

[0081] The multi-stage filtering unit of the dehumidifying and air exchanging system includes: the first stage uses a cyclone separator to capture PM10 and above particulate matter, and mechanical separation avoids filter screen blockage;

[0082] The second stage uses activated carbon to adsorb benzene series and ozone, and chemical adsorption removes gaseous pollutants;

[0083] The third stage uses a high-voltage electrostatic module to capture PM2.5, and the electrostatic dust collection efficiency reaches 99%;

[0084] The start-stop logic of the filtering unit is dynamically adjusted based on the real-time data of the gas concentration sensor and the dust retention load of the plant combination, and enters a sleep mode at night during the low pollution period to save energy, and the intelligent start-stop strategy reduces energy consumption by 45%;

[0085] The driving module comprises a linear MOSFET circuit in parallel, which is used for providing stable power supply for each module and switching standby circuit when voltage fluctuates, and the dual-circuit redundancy design ensures continuous operation of the equipment;

[0086] The temperature protection unit of the driving module is integrated with a thermocouple sensor, when the ambient temperature exceeds the preset temperature, the power of the gas supply system and the gas generation system is automatically reduced to a preset percentage of the rated value, and a high-temperature early warning and equipment state report is sent to the management terminal through the data interaction module, and the overheating protection mechanism prolongs the service life of the equipment by 30%;

[0087] The system dynamically optimizes the plant combination scheme and the environmental regulation parameter through a machine learning model, and records operation logs based on a blockchain technology, the blockchain technology adopts a Hyperledger Fabric framework, records a timestamp of environmental data, a version number of a plant combination scheme and a hash value of a device operation instruction, and the tamper-proof log meets environmental audit requirements;

[0088] The user terminal verifies data integrity through a smart contract, and traces generation logic and execution results of historical regulation and control decisions, and the smart contract automatically verifies to reduce manual auditing cost.

[0089] In summary, the advantages of the present application are:

[0090] The present application realizes scientific design and intelligent regulation and control of dust-retaining plant combination based on big data technology, and has many significant advantages. In the data acquisition and processing link, multi-dimensional data such as air quality, weather, soil and traffic flow are integrated through a distributed sensor network, precise traffic flow analysis is combined with a convolutional neural network, dust contribution rates of different vehicle types are dynamically calculated, wavelet threshold denoising and spatio-temporal collaborative kriging method are used to process abnormal values and missing data, a gridded environmental parameter surface is generated, and the data comprehensiveness, accuracy and spatial continuity are ensured, providing solid data support for subsequent design.

[0091] In the scheme design process, a plant database containing detailed dust-retaining capacity parameters and growth adaptability indexes is constructed, the matching relationship between environmental characteristics and plant dust-retaining capacity is analyzed by means of a random forest algorithm, an initial scheme is generated, and the combination is optimized through niche overlap calculation, resource competition is reduced from the dimensions of root system, canopy and growth cycle, and the synergy and stability of the plant combination are improved. NSGA-II multi-objective optimization algorithm is introduced to balance dust-retaining efficiency, cost, landscape aesthetics and other multiple objectives, and migration learning is used to accelerate new regional scheme generation, which ensures the scientificity of the design and improves the efficiency and reduces the consumption of computing resources.

[0092] The matched dust-retaining plant combination design system integrates multi-source environmental perception modules and edge computing nodes, realizes real-time data processing and offline autonomy, and improves spatial analysis accuracy through grid data. The environmental regulation module adjusts the dynamic strategy of the air supply, spraying, gas production, dehumidification and air exchange subsystems, such as variable frequency fan directional flow control, self-adaptive atomization to prolong water mist retention time, negative oxygen ion to enhance adsorption efficiency, multi-stage filtration to purify air, etc., which significantly improves the dust suppression effect and reduces resource consumption. The dual-circuit redundancy and temperature protection mechanism of the driving module ensure stable operation of the system, the blockchain technology ensures the operation log is tamper-proof, the smart contract simplifies the data verification process, and the overall system has high efficiency, energy saving, safety and traceability.

[0093] Through the deep integration of big data, machine learning and Internet of Things technology, the dust-retaining plant combination design realizes intelligentization and precision from data collection, scheme optimization to system regulation, which has significant advantages in improving dust control efficiency, reducing cost and ensuring stable operation of the system, and provides a scientific, efficient and sustainable solution for urban ecological environment governance.

[0094] The embodiments of the specific implementation are the preferred embodiments of the present application, not limited to the protection scope of the present application, wherein the same parts are indicated by the same reference numerals. Therefore: any equivalent changes made according to the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for designing combinations of dust-trapping plants based on big data, characterized in that, Includes the following steps: S1. Collect real-time environmental data of the target area through a distributed sensor network, including air quality data, meteorological data, soil data and traffic flow data. The air quality data includes at least PM2.5 concentration, PM10 concentration and dustfall. The meteorological data includes wind speed, wind direction, precipitation and temperature and humidity. The soil data includes pH value, organic matter content and heavy metal content. S2. Construct a dust-trapping plant database to store parameters of the dust-trapping capacity of plants, including the dust-trapping capacity of a single plant, leaf morphological characteristics, dust adsorption efficiency, and growth adaptability indicators. The growth adaptability indicators are obtained through a combination of wind tunnel experiments and field monitoring. S3. Based on environmental data and a dust-trapping plant database, the random forest algorithm is used to analyze the matching relationship between the environmental characteristics of the target area and the dust-trapping capacity of the plants, and to generate an initial plant combination scheme. The input features of the random forest algorithm include PM2.5 concentration gradient, soil heavy metal migration rate and spatiotemporal distribution of traffic dust. S4. Optimize the initial combination scheme by calculating the overlap of plant ecological niches, including root complementarity, canopy shading complementarity and growth cycle overlap, and screen plant combinations with a comprehensive competition index lower than the preset threshold. Niche overlap calculation includes: Soil resource competition index is calculated based on differences in root distribution depth, light competition index is calculated based on canopy projection area, and the intensity of time-related resource conflict is quantified by combining overlapping days of growth cycle. If any index exceeds the threshold, the conflicting plants are removed and a new combination is made. S5. Combining landscape planning requirements and cost constraints, a multi-objective optimization algorithm is used to generate a final solution that balances dust retention efficiency and cost, and the dynamic adjustment results are output through a three-dimensional visualization interface.

2. The method for designing dust-trapping plant combinations based on big data according to claim 1, characterized in that, Step S1 includes: Traffic flow data is used to extract vehicle density and road dust contribution rate through image recognition technology, and then fused with meteorological data to generate a pollution source heat map. Data preprocessing also includes noise suppression and missing value imputation, and Kriging interpolation is used to generate spatially continuous environmental datasets.

3. The method for designing dust-trapping plant combinations based on big data according to claim 1, characterized in that, The multi-objective optimization algorithm in step S5 is NSGA-II. The optimization objectives include the dust retention efficiency improvement rate, seedling procurement cost, maintenance cost, and landscape aesthetic score. It outputs a Pareto optimal solution set for user interaction and selection, and accelerates the generation of similar area schemes through a transfer learning model.

4. A dust-trapping plant combination design system based on big data, based on the dust-trapping plant combination design method based on big data as described in any one of claims 1-3, characterized in that, include: The data acquisition module integrates a temperature sensor, a humidity sensor, a gas concentration sensor, and a traffic flow monitoring unit to collect data on PM2.5 concentration, humidity, dustfall, and vehicle dust in the target area. The data interaction module, connected to the data acquisition module, is used to filter outliers, align timestamps, and perform spatial interpolation on the data to generate a gridded dataset, and synchronize it with the cloud server through an API interface. The environmental control module includes an air supply system, a spray system, an air generation system, and a dehumidification and ventilation system. The air supply system uses a variable frequency fan to adjust the air supply strategy to suppress dust diffusion. The spray system dynamically adjusts the atomization particle size based on humidity feedback. The air generation system injects negative oxygen ions to enhance the dust retention capacity of plants. The dehumidification and ventilation system uses a multi-stage filtration unit to purify polluted air. The drive module, including parallel linear MOSFET circuits, is used to provide stable power to each module and switch to backup circuits when voltage fluctuates. The system dynamically optimizes plant combination schemes and environmental regulation parameters through machine learning models, and records operation logs based on blockchain technology.

5. The dust-trapping plant combination design system based on big data according to claim 4, characterized in that, The data interaction module integrates edge computing nodes for real-time execution of lightweight machine learning inference and enables local cached data to maintain the basic operation of the environment adjustment module when the network is interrupted. The edge computing nodes work in conjunction with the cloud server to ensure data consistency through an incremental synchronization mechanism.

6. The dust-trapping plant combination design system based on big data according to claim 4, characterized in that, The air delivery system's air direction adjustment device adjusts the air delivery angle in real time according to the PM2.5 concentration distribution, and activates the vortex air delivery mode during peak traffic hours to enhance dust suppression; the nozzle layout density of the spray system is positively correlated with the plant canopy coverage, and automatically switches to high-pressure spray mode when the wind speed is greater than 3m / s.

7. The dust-trapping plant combination design system based on big data according to claim 4, characterized in that, The temperature protection unit of the drive module integrates a thermocouple sensor. When the ambient temperature exceeds the preset temperature, it automatically reduces the power of the gas supply system and the gas generation system to a preset percentage of the rated value, and sends a high temperature warning and equipment status report to the management terminal through the data interaction module.

8. The dust-trapping plant combination design system based on big data according to claim 4, characterized in that, The dehumidification and ventilation system includes a multi-stage filtration unit: the first stage uses a cyclone separator to capture particulate matter larger than PM10; the second stage uses activated carbon to adsorb benzene compounds and ozone; and the third stage uses a high-voltage electrostatic module to capture PM2.

5. The start-stop logic of the filtration unit is dynamically adjusted based on real-time data from the gas concentration sensor and the dust retention load of the plant combination, and it enters a sleep mode during low-pollution periods at night to save energy.

9. The dust-trapping plant combination design system based on big data according to claim 4, characterized in that, The blockchain technology uses the Hyperledger Fabric framework to record timestamps of environmental data, plant combination scheme version numbers, and hash values ​​of equipment operation instructions; the user terminal verifies data integrity through smart contracts and traces the generation logic and execution results of historical control decisions.

Images