Industrial organic polluted soil remediation intelligent management platform based on digital twinning

Abstract

The invention relates to an intelligent management platform for industrial organic contaminated soil remediation based on digital twinning. The intelligent management platform comprises a construction data acquisition module, a data processing and analysis module, an intelligent construction supervision module, an intelligent thermal desorption equipment management and control module and an intelligent carbon emission analysis module. The comprehensive environment and construction data are collected, the digital twinning technology is combined to provide accurate construction state reflection, intelligent scheduling of resources is achieved through the construction intelligent supervision module, the resource use efficiency is improved to the maximum extent, and the overall construction efficiency is improved. Meanwhile, a carbon emission data acquisition and analysis model is adopted, energy consumption and carbon emission in the soil remediation process are monitored in real time, optimization suggestions are provided, project management personnel are helped to reduce unnecessary carbon emission, environmental protection compliance is ensured, and the economic benefit is improved. An intelligent management and control module of the thermal desorption equipment is adopted to monitor the equipment state and pollutant emission concentration in real time, fault diagnosis and early warning are carried out in combination with an artificial intelligence algorithm, and safe and efficient operation of the equipment is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection and pollution control, and particularly to an intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin. Background Art

[0002] Soil pollution, especially the remediation of industrial organic contaminated soil, is an important task in the current environmental governance field. With the acceleration of the industrialization process, the problem of soil pollution is becoming increasingly serious. In particular, organic pollutants in industries such as petrochemical, metallurgy, and agriculture have a huge impact on soil quality. Although traditional soil remediation methods can effectively remove some pollutants, they have problems such as low remediation efficiency, insufficient resource utilization, excessive pollutant emissions, and lack of real-time monitoring and management during the remediation process.

[0003] Currently, during the soil remediation process, although some enterprises have begun to use modern equipment for operation monitoring, there is a lack of an effective integrated management platform. The collection of construction site data mainly relies on manual operations and local sensors, lacking an intelligent and highly real-time scheduling and monitoring system, resulting in key factors such as construction progress, resource consumption, and environmental impact not being timely feedback and optimized. In addition, traditional methods for remediating contaminated soil mostly rely on manual judgment, lacking data-driven scientific decision-making, leading to low remediation effects and construction efficiency, and it is difficult to ensure safety and environmental protection.

[0004] Specifically, there are usually the following main defects in the current soil remediation construction monitoring:

[0005] (1) Incomplete and inaccurate real-time monitoring and data collection:

[0006] Current soil remediation projects mostly rely on traditional sensors and manual collection methods, with limited accuracy and coverage of data acquisition, unable to fully reflect the dynamic state of the construction site.

[0007] The complex geological environment and changing climate conditions at the construction site may cause sensor failures and even data anomalies, affecting the remediation effect and project progress.

[0008] (2) Inefficient construction resource scheduling and management:

[0009] Due to the lack of an intelligent resource scheduling system, the allocation of construction resources (such as personnel, machinery, earthwork, etc.) often relies on manual arrangements, resulting in problems of overuse or idle waste.

[0010] The monitoring of construction progress and equipment usage is lagging, and the construction plan cannot be adjusted in a timely manner, resulting in low efficiency.

[0011] (3) Lack of environmental protection monitoring and carbon emission optimization:

[0012] During the current repair process, the monitoring of environmental protection parameters such as pollutant emissions and energy consumption is insufficient, and the real-time monitoring and optimization of carbon emissions cannot be achieved, which easily leads to non-compliant emissions and resource waste.

[0013] During the repair process, the use of equipment and energy lacks precise optimization, resulting in unnecessary carbon emissions, affecting the environment and repair costs.

[0014] (4) Lack of equipment failure prediction and timely maintenance:

[0015] The operation status monitoring and maintenance management of key equipment such as thermal desorption equipment are insufficient, and there is a lack of intelligent failure prediction and early warning mechanisms, resulting in frequent equipment failures and affecting the repair progress and efficiency. Summary of the Invention

[0016] The technical problem to be solved by the present invention is to overcome the deficiencies in the prior art and provide an intelligent management platform for the repair of industrial organic contaminated soil based on digital twins, which is applied to the intelligent monitoring and resource scheduling in the soil repair process. By using digital twin technology and Internet of Things (IoT) devices, various data during the construction process are collected, analyzed, warned, and optimized in real time to improve the soil repair efficiency, reduce resource waste, and ensure environmental protection compliance.

[0017] The present invention is realized through the following technical solutions:

[0018] An intelligent management platform for the repair of industrial organic contaminated soil based on digital twins, comprising:

[0019] A construction data collection module, which is used to collect construction data and transmit the data to the cloud or local server through a wireless communication network. The construction data includes construction progress data, mechanical equipment operation status, environmental monitoring data, soil pollution data, and construction safety data;

[0020] A data processing and analysis module, including data cleaning, data modeling, real-time analysis, and data visualization, which is used to perform real-time analysis on the collected construction data, extract key information, and provide decision support;

[0021] A construction intelligent supervision module, including a personnel scheduling system, a mechanical scheduling system, an earthwork scheduling system, and a safety management system, which is used to perform intelligent scheduling and management of resources at the construction site based on the collection and analysis of construction data;

[0022] A thermal desorption equipment intelligent control module, including an equipment status monitoring system, a pollutant monitoring system, a remote control system, and a fault diagnosis and early warning system, which is used to perform intelligent monitoring, adjustment, and warning on the thermal desorption equipment used in the repair process;

[0023] The carbon emission intelligent analysis module includes a carbon emission data collection system, a carbon emission analysis model, an optimization suggestion system, and an environmental protection compliance monitoring system, which is used to monitor and calculate carbon emissions during the soil remediation process and optimize the carbon emission level.

[0024] According to the above technical solution, preferably, the construction data collection module includes a temperature and humidity sensor, an earthwork volume sensor, a mechanical operation status monitor, an air pollutant concentration sensor, and a data collection gateway. The temperature and humidity sensor, the earthwork volume sensor, and the mechanical operation status monitor are used to collect construction data, and the data collection gateway is used to receive the construction data and transmit the data to the cloud or a local server through one or more wireless communication technologies such as Wi-Fi, 4G / 5G, or LoRaWAN.

[0025] According to the above technical solution, preferably, in the data processing and analysis module, the data cleaning includes missing value filling, outlier detection and removal. Among them, the interpolation method is used to fill the missing values in the data, and the Z-score method is used to detect outliers.

[0026] According to the above technical solution, preferably, in the data processing and analysis module, data modeling is performed on the construction data after data cleaning to construct a multi-dimensional analysis model during the construction process, including a construction efficiency prediction model, an equipment health prediction model, and a pollutant emission prediction model.

[0027] According to the above technical solution, preferably, in the data processing and analysis module, the real-time analysis corresponding to the construction efficiency prediction model, the equipment health prediction model, and the pollutant emission prediction model all adopts an adaptive sliding window mechanism, and the window time parameter is dynamically adjusted according to the physical characteristics of the variable to evaluate the performance of the construction process in real time.

[0028] According to the above technical solution, preferably, in the construction intelligent supervision module, the personnel scheduling system is based on RFID tag technology and can track the working status and location of each worker in real time and automatically optimize task allocation. The mechanical scheduling system is based on the predicted values output by the equipment health prediction model and the data collected by the mechanical operation status monitor to monitor and schedule the equipment at the construction site in real time. The earthwork scheduling system is based on the data collected by the earthwork volume sensor to track the construction progress in real time and dynamically adjust the earthwork transportation task. The safety management system is based on the data collected by the temperature and humidity sensor, the mechanical operation status monitor, and the air pollutant concentration sensor to monitor the safety parameters collected at the construction site in real time and identify potential safety hazards.

[0029] According to the above technical solution, preferably, in the intelligent control and management module of the thermal desorption equipment, the equipment status monitoring system collects the operating status of the thermal desorption equipment in real time through sensors, including one or more key parameters such as temperature, pressure, and flow rate, so that it is within a predetermined operating range. The pollutant monitoring system monitors the concentration of pollutants in the exhaust gas of the equipment in real time, so that the harmful gases meet the environmental protection discharge standards. The remote control system can adjust the operating parameters of the thermal desorption equipment according to the equipment status monitoring system and the pollutant monitoring system. The fault diagnosis and early warning system can analyze the operating status of the equipment in real time based on the equipment operating data and historical data collected by the equipment status monitoring system, predict potential faults that may occur in the equipment, and issue early warnings.

[0030] According to the above technical solution, preferably, in the intelligent carbon emission analysis module, the carbon emission data acquisition system obtains the energy consumption data of the soil excavation, transportation, repair, and external transportation links during the construction process in real time through sensors and IoT devices. The carbon emission analysis model analyzes the carbon emission situation of the construction process based on the energy consumption data, and compares it with the environmental protection standards to find the optimization space. The optimization suggestion system provides specific energy conservation and emission reduction solutions based on the carbon emission analysis model, including optimizing equipment scheduling and adjusting construction processes. The environmental protection compliance monitoring system can track in real time whether the carbon emissions during the repair process meet the environmental protection standards, and issue early warnings when problems are found.

[0031] The beneficial effects of the present invention are as follows:

[0032] The present invention provides an intelligent management platform for the remediation of industrial organic contaminated soil based on digital twins. By deploying a variety of sensors (temperature and humidity, pollutant concentration, mechanical operating status, etc.) at the construction site, comprehensive environmental and construction data are collected in real time, and accurate construction status reflection is provided in combination with digital twin technology. Through the construction intelligent supervision module, intelligent scheduling of resources such as personnel, machinery, and earthwork is realized, the resource utilization efficiency is maximized, overuse or inefficient use is avoided, and the overall construction efficiency is improved.

[0033] At the same time, the present invention adopts a carbon emission data acquisition and analysis model to monitor the energy consumption and carbon emissions during the soil remediation process in real time, and puts forward optimization suggestions to help project managers reduce unnecessary carbon emissions and ensure environmental protection compliance.

[0034] In addition, the intelligent control and management module of the thermal desorption equipment monitors the equipment status, pollutant emission concentration, etc. in real time, combines artificial intelligence algorithms for fault diagnosis and early warning, realizes the early prediction and timely maintenance of equipment failures, and ensures the efficient operation of the equipment. Description of the Drawings

[0035] Figure 1It is the system architecture diagram of the intelligent management platform for industrial organic contaminated soil remediation based on digital twin disclosed by the present invention.

[0036] Figure 2 It is the example data actually collected in the construction data acquisition module of the present invention. Detailed implementation manners

[0037] In order to enable those skilled in the art of the present technology to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and the best embodiments. Based on the embodiments of the invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the scope of protection of the invention.

[0038] As shown in the figure, the present invention includes:

[0039] (1) Construction data acquisition module:

[0040] The construction data acquisition module is the basic part of the digital twin platform and undertakes the task of real-time acquisition of various key data at the construction site. First, this module makes precise sensor arrangements at the construction site, and the sensors should be reasonably configured according to different construction links. The deployment work includes selecting appropriate sensor types and deployment positions according to the complexity of the project, soil characteristics, and requirements of the construction area. After the deployment is completed, the sensors start to collect data in real time and transmit it to the platform through the data acquisition gateway. In order to ensure the accuracy and reliability of the data, the platform also sets up a data quality monitoring mechanism. By monitoring the quality of data acquisition in real time, abnormal values can be detected in a timely manner, and necessary correction measures can be taken. The platform can also generate real-time construction status reports based on the collected data.

[0041] Construction data includes construction progress data, mechanical equipment operation status, environmental monitoring data, soil pollution data, and construction safety data. The construction data acquisition module includes a temperature and humidity sensor, an earthwork volume sensor, a mechanical operation status monitor, an air pollutant concentration sensor, and a data acquisition gateway. The temperature and humidity sensor, earthwork volume sensor, mechanical operation status monitor, and air pollutant concentration sensor are used to acquire construction data, and each device is responsible for collecting different types of data. The earthwork volume sensor can monitor the progress of soil excavation and transportation in real time, while the pollution gas sensor is responsible for monitoring the concentration of harmful gases at the construction site to ensure compliance with environmental protection standards. In addition, the mechanical operation status monitor can provide real-time feedback on the operation status of construction machinery, helping management personnel to detect equipment failures or inefficient operations in a timely manner. The data acquisition gateway is used to receive the construction data, which includes real-time temperature and humidity, gas concentration, mechanical operation status, construction progress, and other information, providing comprehensive and timely data support for the construction site. To ensure the stability and security of data transmission, the data is transmitted to the cloud or local server through one or more wireless communication technologies such as Wi-Fi, 4G / 5G, or LoRaWAN, ensuring long-distance and high-frequency data transmission. Through this real-time data acquisition, the platform can continuously monitor various dynamics during the construction process, providing basic data for subsequent data processing and analysis.

[0042] To better illustrate the working principle of the construction data acquisition module, as Figure 2 shown, several example data actually collected are listed. These data cover key aspects of the soil remediation project, such as construction progress, mechanical equipment operation status, environmental monitoring, and soil pollution status.

[0043] (2) Data Processing and Analysis Module:

[0044] The main function of the data processing and analysis module in the digital twin platform is to perform real-time analysis on a large amount of raw data obtained from the construction data acquisition module, extract key information, and provide decision support. It includes data cleaning, data modeling, real-time analysis, and data visualization.

[0045] (1) Data Cleaning: It is the preprocessing of data collected from the site to remove incomplete, inaccurate, or redundant data, thereby ensuring the accuracy of subsequent analysis results. Since the data acquisition process at the construction site may be affected by factors such as environmental interference and equipment failures, the raw data may contain noise, missing values, or outliers, which may all affect the analysis results.

[0046] Specific implementation methods:

[0047] Missing value filling: Interpolation methods (such as linear interpolation) are used to fill in the missing values in the data. In time series data, if the temperature data at a certain moment is missing, it can be estimated by linear interpolation of the data before and after.

[0048] Outlier detection and removal: The Z-score method is used to detect outliers. Z-score is a standardized statistical method, and the formula is:

[0049]

[0050] where X is a certain data point, μ is the mean of the data set, and σ is the standard deviation. When Z > 3, it means that the data point is an outlier and can be removed.

[0051] (2) Data modeling: A data modeling system based on multivariate regression analysis includes three core prediction models: construction efficiency prediction model (SE-Model), equipment health prediction model (EH-Model), and pollutant emission prediction model (PE-Model). Each model collects construction machinery operation parameters, environmental monitoring data, and material consumption data in real time through the industrial Internet of Things, and establishes a dynamic regression equation for predictive analysis.

[0052] (2-1) Construction efficiency prediction model (SE-Model):

[0053] Input variable group:

[0054] X1: Equipment load rate (kW, collected by the power metering module)

[0055] X2: Environmental temperature and humidity index (THI = (T × 0.8) + (H × 0.2), T is in degrees Celsius, H is the relative humidity percentage)

[0056] X3: Operator proficiency (grading coefficient 1-5, calculated by associating the face recognition attendance system with historical working hour data)

[0057] Output variable:

[0058] Y: Polluted soil treatment volume per unit working hour (m 3 / h, calculated by comparing GNSS positioning with the BIM model)

[0059] Modeling steps:

[0060] 1) Data standardization: Perform Z-score normalization on {X1, X2, X3} to eliminate the dimension difference

[0061] 2) Multicollinearity test: Calculate the variance inflation factor VIF, and start the principal component analysis when VIF > 5

[0062] 3) Regression equation construction: Y = β0 + β1X1 + β2X2^2 + β3log(X3) + ε

[0063] 4) Parameter estimation: Solve the β coefficient matrix using the least squares method, where:

[0064] β1 represents the marginal contribution of the equipment load rate to efficiency (m 3 / (h·kW))

[0065] β2 reveals the non - linear effect of the quadratic humidity - temperature effect on efficiency (m 3 / (h·THI 2 ))

[0066] (2 - 2) Equipment health prediction model (EH - Model):

[0067] Input variable group:

[0068] X4: Vibration intensity of the hydraulic system (mm / s, collected by a three - axis accelerometer)

[0069] X5: Engine oil temperature change rate (℃ / min, dynamically sampled by a temperature sensor)

[0070] X6: Hydraulic oil particle concentration (ppm, detected by an on - line oil monitor)

[0071] Output variable:

[0072] Y: Remaining useful life of the equipment (RUL, hours, fitted based on the Weibull distribution)

[0073] Modeling steps:

[0074] 1) Feature engineering: Construct time - domain features (mean, variance) and frequency - domain features (wavelet packet energy entropy)

[0075] 2) Step - wise regression: Use the AIC criterion to screen significant variables and establish Y = β0 + β1X4^(1 / 3)+β2exp(X5)+ε

[0076] 3) Survival analysis: Combine the Cox proportional hazards model for failure probability prediction) Residual diagnosis: Verify the independence of the error term ε through the Durbin - Watson test.

[0077] (2 - 3) Pollutant emission prediction model (PE - Model):

[0078] Input variable group:

[0079] X7: Instantaneous diesel fuel consumption (L / h, measured by a fuel flow meter)

[0080] X8: Working voltage of the exhaust after - treatment system (V, collected by the CAN bus)

[0081] X9: Mud content of aggregate (%, online near-infrared spectrum detection)

[0082] Output variables:

[0083] Y: PM2.5 emission concentration (μg / m 3 , real-time monitoring by laser scattering method)

[0084] Modeling steps:

[0085] 1) Variable transformation: Perform Box-Cox transformation on X7 to eliminate heteroscedasticity

[0086] 2) Ridge regression modeling: Y = β0 + β1X7 + β2X8 -1 + β3X9 2 + ε, regularization parameter λ = 0.1

[0087] 3) Cross-validation: Use k-fold method to verify the generalization ability of the model.

[0088] (3) Real-time analysis: The three core prediction models (SE-Model, EH-Model, PE-Model) generated through data modeling form a closed-loop control with the real-time analysis engine. The real-time analysis module corresponding to each model adopts an adaptive sliding window mechanism, and the window time parameter is dynamically adjusted according to the physical characteristics of the variables.

[0089] (3-1) Real-time analysis of construction efficiency (associated with SE-Model):

[0090] Data flow characteristics:

[0091] Data sources: GNSS positioning system (1Hz), power metering module (10Hz), temperature and humidity sensor (0.2Hz)

[0092] Window parameter: T = 5 minutes (set based on the initial setting time of concrete)

[0093] Real-time analysis steps:

[0094] 1) Window data normalization: Perform online Z-score standardization on {X1, X2, X3} within the window

[0095] Streaming standardization incremental calculation: mean = previous_mean + (x_new - previous_mean) / nstd = sqrt(((n - 1)*previous_std 2 + (x_new - mean) 2 ) / n)

[0096] 2) Efficiency dynamic prediction: Update the regression equation every 30 seconds: β0 + β1X1 + β2X2 2 + β3log(X3)

[0097] 3) Progress deviation warning: When the predicted value Y of 3 consecutive windows < 85% of the BIM planned value, trigger the following operations: Adjustment suggestions, automatically generate the equipment load optimization plan X1' = X1 × (Y_target / Y_current)^(1 / β1)

[0098] (3-2) Real-time analysis of equipment health (associated with EH-Model):

[0099] Data stream characteristics:

[0100] Data sources: Triaxial vibration sensor (2kHz), oil temperature sensor (1Hz), oil fluid monitor (0.1Hz)

[0101] Window parameters: T = 20 minutes (covering the typical working cycle of the equipment)

[0102] Steps for real-time analysis:

[0103] 1) Vibration feature extraction: Calculate the frequency domain indicators within the window:

[0104] Wavelet packet energy entropy WPE = -Σ(p_i·log p_i), where p_i is the proportion of band energy

[0105] RMS value of the resonance band (800 - 1200Hz)

[0106] 2) Degradation trend prediction: Update Y = β0 + β1X4^(1 / 3) + β2exp(X5) on a minute-by-minute basis

[0107] 3) Fault pre-diagnosis: Start a three-level alarm when the following situations occur:

[0108] Yellow warning: X4 > 2.5mm / s and WPE mutation > 15%

[0109] Red warning: Automatically push the spare part replacement work order when the predicted RUL < 8h

[0110] (3-3) Real-time analysis of pollutant emissions (associated with PE-Model):

[0111] Data stream characteristics:

[0112] Data sources: Laser scattering PM2.5 detector (1Hz), fuel flow meter (4Hz)

[0113] Window parameters: T = 10 minutes (matching the monitoring specifications of the environmental protection department)

[0114] Real-time analysis steps:

[0115] 1) Dynamic ridge regression calculation: Update Y = β0 + β1X7 + β2X8 every 1 minute -1 + β3X9 2

[0116] The regularization parameter λ is automatically adjusted according to the signal-to-noise ratio of the data: λ = 0.1×log(‖X‖2)

[0117] 2) Exceedance response: Trigger when Y > 75 μg / m for 5 consecutive minutes 3 Trigger:

[0118] Control instruction: Increase the post-treatment voltage to X8' = X8×(Y_limit / Y_current)^(|β2|)

[0119] Material adjustment: Automatically reduce the proportion of muddy aggregate X9' = X9×(0.95)^k (k is the number of exceedance times)

[0120] (4) Data visualization: It is to display the results of data analysis in the form of graphs, charts or dashboards, so that construction managers can intuitively understand the data and make quick decisions based on it. Visualization can not only show the real-time progress of construction, but also help to discover potential bottlenecks and risks, and support intelligent decision-making.

[0121] Specific implementation methods:

[0122] (4-1) Dashboards and real-time charts: By constructing real-time dashboards, display key indicators during the construction process (such as construction progress, mechanical status, concentration of polluting gases, etc.). KPI (Key Performance Indicator) dashboards can be used to display this data. For example, a dashboard showing the progress of earth excavation can use a chart with a percentage progress bar, and indicate the current status through color changes (such as green for normal progress and red for lag).

[0123] (4-2) Scatter plots and line charts: Use scatter plots to show the relationship between equipment load and construction efficiency, or use line charts to show the changing trend of daily soil pollution concentration, to help project managers intuitively understand the key changes during construction.

[0124] (III) Construction intelligent supervision module:

[0125] The construction intelligent supervision module is one of the core modules of the digital twin platform, responsible for the intelligent scheduling and management of all resources at the construction site. It includes a personnel scheduling system, a machinery scheduling system, an earthwork scheduling system, and a safety management system, which are used to monitor the construction progress, personnel arrangements, the use of construction machinery and equipment, and earthwork transportation in real time based on the collection and analysis of construction data, to conduct intelligent scheduling and management of the resources at the construction site, optimize the allocation of various resources during the construction process, improve construction efficiency, reduce resource waste, and ensure construction quality and safety.

[0126] (1) Personnel scheduling system: It can reasonably allocate work tasks according to the actual situation of the construction site, ensure the efficient cooperation of personnel, and avoid resource idleness or duplicate work. Through RFID tag technology, the platform can track the working status and location of each worker in real time, automatically optimize task allocation, and ensure construction efficiency.

[0127] Obtaining key parameters:

[0128] 1) Real-time location data: UWB positioning system (accuracy ±15 cm, update frequency 1 Hz)

[0129] 2) Work type skill matrix: Industrial worker level (L1 - L5), high-altitude operation qualification, etc. (from the BIM database)

[0130] 3) Physiological state indicators: Smart safety helmets collect heart rate (bpm) and body temperature (°C) data

[0131] 4) Task topological relationship: Node weight w_i ∈ [1, 5] in the task dependency graph (G = (V, E))

[0132] Steps of the resource scheduling algorithm:

[0133] 1) Chromosome encoding: Adopt a three-dimensional gene structure:

[0134] · The first dimension: Personnel ID (RFID number)

[0135] · The second dimension: Task sequence (WBS number decomposed based on the BIM model)

[0136] · The third dimension: Time window constraint ([start time, end time])

[0137] 2) Calculation of the fitness function:

[0138] Multi-objective weighted evaluation

[0139] def fitness(chromosome):

[0140] efficiency = Σ(task standard working hours / actual allocated working hours) # Based on the historical working hours database

[0141] safety = 1 - Σ(overtime working hours) / total working hours # When the daily working hours > 10h, it is counted as overtime. skill_match = Σ(task required skill level - actual personnel level) 2 # Penalty for the deviation of industrial worker levels

[0142] return 0.6 * efficiency + 0.3 * safety + 0.1 * (1 / skill_match)

[0143] 3) Dynamic constraint handling:

[0144] Hard constraint: Gene repair is triggered when the detected heart rate of personnel > 120bpm

[0145] UPDATE chromosome SET task_assign = NULL

[0146] WHERE worker_id IN (SELECT id FROM workers WHERE heart_rate > 120)

[0147] Soft constraint: Skill mismatch is handled through a penalty function (weight coefficient λ = 0.05)

[0148] (2) Mechanical scheduling system: Real-time monitoring of all equipment at the construction site to ensure the reasonable scheduling of mechanical equipment and avoid equipment idleness or overuse. When a piece of machinery fails, the system can intelligently schedule backup equipment to ensure that the construction is not affected.

[0149] Obtaining key parameters:

[0150] 1) Equipment health index: Predicted value of RUL (Remaining Useful Life) output by the EH - Model

[0151] 2) Task queue pressure: Quantity of transportation to be processed / rated transportation capacity of equipment (unit: trips / h)

[0152] 3) Energy consumption cost coefficient: Instantaneous fuel consumption of diesel engine (L / h) × real - time fuel price data

[0153] Steps of the resource scheduling algorithm:

[0154] 1) Gene coding optimization:

[0155] Adopt a double - layer coding structure:

[0156] Upper layer: Equipment - task assignment matrix (0 - 1 coding)

[0157] Lower layer: Task execution order (permutation coding)

[0158] 2) Multi-objective fitness function:

[0159] F = α * (1 / total fuel consumption) + β * equipment utilization rate + γ * Σ(RUL_i / RUL_initial)

[0160] where α = 0.5, β = 0.3, γ = 0.2

[0161] 3) Fault response mechanism:

[0162] When the EH-Model warns that RUL < 4h:

[0163] Dynamically adjust the equipment transport capacity coefficient: transport capacity' = transport capacity × (RUL / 8h)^2

[0164] Trigger the equipment replacement gene recombination operation

[0165] 4) Energy consumption-aware crossover operator:

[0166] When selecting the crossover point, preferentially retain the low fuel consumption task sequence segment

[0167] Introduce the fuel consumption gradient: Δc = |c_parent1 - c_parent2|

[0168] Technical features:

[0169] Transport capacity dynamic attenuation model: Q(t) = Q0 × e^(-kt), k = 0.05 / h (based on equipment wear data)

[0170] Oil circuit pressure compensation algorithm: Automatically correct the calculated transport capacity value when the oil pressure < 2.5MPa

[0171] (3) Earthwork scheduling system: Focus on the monitoring and scheduling of earthwork transportation. By real-time tracking of the construction progress, the system can dynamically adjust the earthwork transportation tasks to ensure that the excavation, transportation, and stacking of earthwork reach the best ratio, thereby avoiding excessive or insufficient earthwork transportation and reducing the risk of project delay or resource waste.

[0172] Obtaining key parameters:

[0173] 1) Real-time earthwork volume: The measurement accuracy of the 3D laser scanner is ±0.5m 3 , and the update period is 5min

[0174] 2) Transportation path topology: GIS-based slope-distance weight map (weight = fuel consumption × time)

[0175] 3) Stockpile capacity: The remaining capacity is monitored by an array of pressure sensors (unit: m 3 )

[0176] Steps of resource scheduling algorithm:

[0177] 1) Gene expression design:

[0178] Transport path gene: Use variable-length gene encoding for different combinations of transport routes

[0179] Loading capacity gene: Real number encoding (range: 3 - 15m 3 , step size 0.5m 3 )

[0180] 2) Dynamic fitness calculation:

[0181] def earth_fitness(individual):

[0182] transport_cost = Σ(path fuel consumption × real-time oil price)

[0183] time_penalty = max(0, actual progress - planned progress)^2

[0184] balance_score = 1 - |excavation volume - transportation volume| / total earthwork volume

[0185] return 0.7*(1 / transport_cost) + 0.2*balance_score + 0.1*(1 / time_penalty)

[0186] 3) Real-time correction mechanism:

[0187] When the excavation deviation detected by laser scanning > 10%:

[0188] Trigger gene mutation: Adjust the loading capacity gene with probability p = 0.3

[0189] Update the transport path weight graph

[0190] 4) Hybrid mutation strategy:

[0191] Gaussian mutation: Apply N(0, 0.5) perturbation to the loading capacity gene

[0192] Inversion mutation: Perform random inversion on the transport path gene segment

[0193] Technical features:

[0194] Earthwork balance prediction model: Dynamic prediction of transportation volume - stacking volume based on Kalman filter

[0195] Path energy consumption optimization algorithm: Hybrid solution of Dijkstra algorithm and genetic algorithm

[0196] (4) Safety Management System: By continuously monitoring various safety parameters at the construction site, such as gas concentration, temperature and humidity, equipment status, etc., it can automatically identify potential safety hazards. For example, when dangerous gas leakage or fire hazards occur at the construction site, the system will immediately issue an alarm and automatically adjust relevant equipment to ensure site safety.

[0197] Key Parameter Acquisition:

[0198] 1) Dangerous Gas Concentration: Electrochemical sensor (accuracy ±1ppm, response time < 30s)

[0199] 2) Structural Stress Data: Fiber Bragg Grating sensor (sampling rate 100Hz)

[0200] 3) Personnel Evacuation Route: Real-time personnel distribution identified by thermal imaging cameras

[0201] Resource Scheduling Algorithm Steps:

[0202] 1) Emergency Response Encoding:

[0203] Adopt event-driven gene encoding:

[0204] Gene bits 1 - 3: Hazard type encoding (fire, gas leakage, structural instability)

[0205] Gene bits 4 - 6: Emergency equipment startup priority

[0206] Gene bits 7 - 9: Personnel evacuation route weight

[0207] 2) Real-time Fitness Evaluation:

[0208]

[0209] 3) Mutation Acceleration Mechanism:

[0210] When the detected CO concentration > 50ppm:

[0211] The mutation probability is increased from 0.05 to 0.2

[0212] The population size is dynamically expanded to 200 individuals

[0213] 4) Multi-agent Collaboration:

[0214] Path planning of escape guidance robots and co-evolution of personnel scheduling genes

[0215] Encoding of ventilation equipment start / stop strategy and cross-validation of evacuation route genes

[0216] Technical Features:

[0217] Hazard Diffusion Prediction Model: Real-time smoke diffusion simulation based on Computational Fluid Dynamics (CFD)

[0218] Structural stress mutation detection algorithm: Wavelet transform to identify abnormal vibrations with a frequency > 20 Hz

[0219] During implementation, the construction intelligent supervision module collects real-time on-site data by integrating various hardware devices such as IoT devices, sensors, and video surveillance systems, and analyzes these data through algorithms to assist the platform in resource scheduling and optimization. Relying on the powerful computing power of the cloud computing platform, the module can process data from multiple sensors in real time and dynamically adjust the construction site according to the analysis results. Through this intelligent management, the platform can maximize construction efficiency, reduce resource waste, and ensure the smooth progress of the project.

[0220] (4) Intelligent control and management module for thermal desorption equipment:

[0221] The intelligent control and management module for thermal desorption equipment is a crucial part of the soil remediation process. Especially when using thermal desorption technology for treating contaminated soil, the efficient operation of the equipment is the key to ensuring the remediation effect. This module includes an equipment status monitoring system, a pollutant monitoring system, a remote control system, and a fault diagnosis and early warning system. Its main function is to intelligently monitor, adjust, and give early warnings to the thermal desorption equipment used in the remediation process through digital means, ensure that the equipment operates in the best state, promptly discover and solve potential faults, and optimize the remediation efficiency.

[0222] The equipment status monitoring system collects the operating status of the thermal desorption equipment in real time through sensors, such as key parameters like temperature, pressure, and flow rate, to ensure that the equipment operates within the predetermined working range. The pollutant monitoring system monitors the concentration of pollutants in the exhaust gas of the equipment in real time to ensure that the harmful gases during the remediation process meet the environmental protection emission standards. Through real-time data feedback, the remote control system can adjust the operating parameters of the equipment according to environmental changes and equipment status to optimize the remediation process. The fault diagnosis and early warning system relies on equipment operation data and historical data to analyze the operating status of the equipment in real time, predict possible faults of the equipment, and issue early warnings before the faults occur to notify maintenance personnel for repair. This module can effectively avoid problems such as production stagnation or poor remediation effect caused by equipment failures, and improve the working efficiency and remediation quality of thermal desorption equipment.

[0223] (1) Key points of innovative technology:

[0224] 1) Multi-parameter coupling control: Establish a dynamic coupling equation for temperature - pressure - flow rate, breaking through the limitations of traditional single-variable PID

[0225] dT / dt = k_1Q_gas - k_2(P_chamber - P_ambient) - k_3F_carrier

[0226] (k_1 = 0.15 °C / (kW·s), k_2 = 0.02 °C / (kPa·s), k_3 = 0.005 °C·h / m 3 )

[0227] 2) Nonlinear compensation technology: Superimpose a feedforward compensation amount at the PID output end:

[0228] u_total = u_PID + 0.3 * tanh(5 * (T_actual - 350))

[0229] 3) To compensate for the non - linear attenuation of the heat transfer efficiency in the high - temperature zone

[0230] Fault prediction - control coordination: When the SVM - predicted fault probability > 60%, automatically switch to the conservative control mode:

[0231] Kp is reduced by 40%

[0232] The integral term is frozen

[0233] The maximum gas flow rate is limited to 80% of the rated value

[0234] (2) Key operating parameter acquisition system:

[0235] 1) Temperature parameter group:

[0236] Heating section temperature: Measured by an 8 - point distributed thermocouple (range 0 - 600 °C, accuracy ±1.5 °C)

[0237] Tail gas outlet temperature: Infrared thermometer (range - 20 - 300 °C, resolution 0.1 °C)

[0238] Soil bed temperature: Fiber Bragg grating sensor array (spatial resolution 10 cm, accuracy ±0.5 °C)

[0239] 2) Pressure parameter group:

[0240] Combustion chamber pressure: Piezoresistive sensor (range 0 - 1 MPa, accuracy 0.5% FS)

[0241] Vacuum system pressure: Capacitance manometer (range 1 - 100 kPa, accuracy ±0.1 kPa)

[0242] Pipeline pressure difference: Differential pressure transmitter (range 0 - 10 kPa, response time ≤50 ms)

[0243] 3) Flow parameter group:

[0244] Gas flow rate: Thermal mass flowmeter (range 0 - 100 Nm 3 / h, repeatability ±0.2%)

[0245] Carrier gas flow rate: Vortex flowmeter (range 0 - 500 m 3 / h, temperature resistance 300 °C)

[0246] Tail gas emission: Ultrasonic flowmeter (two-way measurement, accuracy ±0.5%)

[0247] 4) Pollutant parameter group:

[0248] VOCs concentration: PID detector (range 0 - 5000 ppm, response time ≤ 2 s)

[0249] Dioxin equivalent: Online mass spectrometer (detection limit 0.1 ng-TEQ / m 3 )

[0250] Particulate matter concentration: β-ray method detector (range 0 - 50 mg / m 3 , resolution 1 μg / m 3 )

[0251] 5) Mechanical state parameter group:

[0252] Rotary kiln speed: Magnetoelectric encoder (resolution 0.1 rpm, range 0 - 10 rpm)

[0253] Vibration intensity: Triaxial accelerometer (frequency response range 5 - 5000 Hz, range ±50 g)

[0254] Seal leakage rate: Helium mass spectrometer leak detector (sensitivity 1×10 -6 Pa·m 3 / s)

[0255] (3) Implementation steps of PID control algorithm:

[0256] 1) Parameter normalization processing:

[0257] # Taking the temperature parameter as an example for normalization

[0258] T_norm = (T_actual - T_min) / (T_max - T_min)

[0259] # T_actual is the real-time measured value (°C), T_min / T_max is the process allowable range (such as 200 - 450 °C)

[0260] 2) Multivariable coupling error calculation:

[0261] % Temperature-pressure combined error function

[0262] e(t) = α*(T_set - T_actual)+β*(P_set - P_actual)

[0263] %α = 0.7 (℃ -1 ), β = 0.3 (kPa -1 ), Dimensionless unity coefficient

[0264] 3) Incremental PID control quantity calculation:

[0265] u(k) = Kp * [e(k) - e(k - 1)] + Ki * Ts * e(k) + Kd * [e(k) - 2e(k - 1) + e(k - 2)] / Ts

[0266] / / Where:

[0267] / / u(k) - Control quantity output (%)

[0268] / / Kp = 2.5 (Proportional coefficient, unit % / ℃)

[0269] / / Ki = 0.1 (Integral coefficient, % / (℃·s))

[0270] / / Kd = 0.05 (Derivative coefficient, %·s / ℃)

[0271] / / Ts = 0.5s (Sampling period)

[0272] 4) Actuator coordinated regulation:

[0273] Gas valve opening: ΔV = u(k) * V_max / 100 (V_max = 100%)

[0274] Induced draft fan frequency: f_new = f_old + 0.02 * u(k) (Hz / %)

[0275] Rotary kiln speed: n = n0 + ∫(0.015 * du / dt)dt (rpm / % / s)

[0276] 5) Parameter self - tuning algorithm:

[0277] # Online tuning based on the Ziegler - Nichols method

[0278] if abs(e(t)) > 5℃:

[0279] Kp_new = 0.6 * Ku

[0280] Ti_new = 0.5 * Tu

[0281] Td_new = 0.12 * Tu

[0282] # Ku is the critical gain, Tu is the critical period (automatically identified through step response)

[0283]

[0284]

[0285] Table 1 Physical Meaning and Unit of Control Parameters (4) Implementation of Fault Prediction Algorithm:

[0286] 1) Definition of Support Vector Machine (SVM) Parameters:

[0287] % Input feature vector X = [ΔT / Δt, P_avg, F_variance, Vibration_RMS]

[0288] % ΔT / Δt: Temperature rise rate (℃ / min)

[0289] % P_avg: Average pressure (kPa)

[0290] % F_variance: Flow rate fluctuation variance (m 3 / h) 2

[0291] % Vibration_RMS: Root mean square value of vibration (mm / s 2 )

[0292] % Gaussian kernel function parameter

[0293] K(x_i,x_j) = exp(-γ||x_i - x_j|| 2 )

[0294] % γ = 0.5 (kernel width coefficient, unit m -2 )

[0295] 2) Online learning mechanism:

[0296] Weighted processing of newly added data: w = 1 / (1 + 0.1*t) (t is data timeliness, unit hour)

[0297] Dynamic update of support vectors: Historical key samples with a retention rate ≥ 85%

[0298] 3) Setting of warning threshold:

[0299] Yellow warning: Decision function value f(x) ∈ [0.5, 0.8]

[0300] Red warning: Emergency shutdown is triggered when f(x) ≥ 0.8

[0301] (V) Intelligent Carbon Emission Analysis Module:

[0302] The main function of the intelligent carbon emission analysis module is to monitor and calculate the carbon emissions of various activities during the soil remediation process, ensuring that the entire remediation process meets environmental protection requirements and optimizes the carbon emission level. It includes a carbon emission data collection system, a carbon emission analysis model, an optimization suggestion system, and an environmental protection compliance monitoring system. Through data collection, carbon emission calculation, optimization analysis, and compliance inspection, it helps project managers to grasp the carbon emission situation during the construction process in real time and ensure the green and sustainable development of the project.

[0303] The data collection system obtains the energy consumption data of various activities during the construction process in real time through sensors and IoT devices, including the energy consumption data of soil excavation, transportation, remediation, and off-site transportation. Based on these data, the platform uses carbon emission factors to perform real-time carbon emission calculations and evaluate the carbon footprint during the construction process. Through the carbon emission analysis model, the system can comprehensively analyze the carbon emission situation of the construction process and compare it with environmental protection standards to find room for optimization. On this basis, the optimization suggestion system provides specific energy conservation and emission reduction solutions for the construction team, such as optimizing equipment scheduling and adjusting construction processes, to reduce unnecessary carbon emissions. Finally, the environmental protection compliance monitoring system will track in real time whether the carbon emissions during the remediation process comply with environmental protection regulations and give early warnings when problems are found to ensure the environmental protection compliance of the project.

[0304] (1) Method for obtaining energy consumption data by link

[0305] 1) Soil excavation link:

[0306] Energy consumption data source:

[0307] Excavator power: Current sensor (range 0 - 500A, accuracy ±1%) × Voltage (690V) → kW

[0308] Operation duration: Work status recognition triggered by GNSS positioning system (accuracy ±0.5s)

[0309] Calculation formula:

[0310]

[0311] (Unit: kWh, is the power factor, t j is the number of seconds of the jth operation)

[0312] 2) Earthwork transportation link:

[0313] Data collection:

[0314] Fuel consumption: Obtain instantaneous fuel consumption (ml / s) through in-vehicle CAN bus

[0315] Transportation distance: Calculate the actual path length through GNSS trajectory (accuracy ±3m)

[0316] Dynamic correction:

[0317] # Fuel consumption based on slope compensation

[0318] adjusted_fuel=fuel×(1+0.05×|slope|)# Fuel consumption increases by 5% for every 1% increase in slope 3) Thermal desorption repair process:

[0319] Energy consumption composition:

[0320] Gas consumption: Thermal mass flow meter (0-100Nm 3 / h)

[0321] Electricity consumption: Smart meter (0.5S level accuracy) sub-item measurement

[0322] Special treatment:

[0323] / / Waste heat recovery correction

[0324] E_net=E_gross-0.3*E_exhaust_heat / / 30%waste heat utilization

[0325]

[0326] Table 2 Model parameter definition system

[0327] (2) Carbon emission factor determination technology

[0328] 1) Standard database reference:

[0329] Fossil fuels: Use the default values in the Provincial Greenhouse Gas Inventory Guidelines

[0330] Electricity: Real-time access to the National Grid emission factor API (updated every hour)

[0331] 2) On-site measurement and calibration:

[0332]

[0333] 3) Device-level dynamic correction:

[0334] Calculate the actual combustion efficiency of the engine based on OBD data:

[0335]

[0336] (η is thermal efficiency, calculated by exhaust temperature-air-fuel ratio model)

[0337] (3) Multi-objective optimization implementation steps

[0338] 1) Constraint construction:

[0339] Schedule constraint:

[0340]

[0341] (v i is the efficiency of process i, and T max is the contract duration)

[0342] Resource constraint:

[0343]

[0344] (y k is the usage duration of equipment k, and R is the total amount of resources)

[0345] 2) Solving the optimization model:

[0346] # Use the PuLP library to solve the linear programming

[0347] prob = LpProblem("Carbon Optimization", LpMinimize)

[0348] prob += lpSum([beta[i] * x[i] for i in activities]), "Total Carbon" prob += lpSum([a_time[i] * x[i] for i in activities]) <= T_max, "Schedule" prob.solve(GUROBI_CMD(options=[("TimeLimit", "600")]))

[0349] 3) Sensitivity analysis:

[0350] Calculate the shadow price to analyze the constraint bottleneck:

[0351]

[0352] / / Reflect the carbon emission reduction amount brought by relaxing each unit of the j-th constraint

[0353] 4) Dynamic re-optimization trigger mechanism:

[0354] When the real-time monitored carbon emission intensity exceeds the benchmark value by 15%:

[0355] Start the equipment scheduling optimization: preferentially use low-emission equipment (such as electric excavators)

[0356] Adjust the process parameters: reduce the set value of the thermal desorption temperature (ΔT = 5 - 10 °C)

[0357] (4) Optimization effect verification method

[0358] 1) Carbon flow tracking technology:

[0359] · Blockchain-based carbon footprint record:

[0360]

[0361] 2) Digital twin verification:

[0362] Establish a virtual calibration scenario:

[0363] Benchmark scenario: Traditional scheduling mode

[0364] Optimized scenario: Intelligent scheduling mode

[0365] Comparison metrics:

[0366]

[0367] It is required that ΔC ≥ 12%

[0368] (5) Key points of intelligent carbon emission analysis

[0369] 1) Multi-source data fusion technology:

[0370] Fuse data from multiple systems such as OBD, SCADA, and BIM (data synchronization error < 50ms)

[0371] Energy consumption data compensation algorithm based on Kalman filter:

[0372] ^E k = E k + K(E IMYU ― HE k )

[0373] (K is the Kalman gain matrix)

[0374] 2) Dynamic carbon fingerprint model:

[0375]

[0376] Table 3 Equipment-level emission factor matrix updated hourly

[0377] 3) Dual optimization mechanism:

[0378] Feedforward optimization: Pre-scheduling plan based on BIM model

[0379] Feedback optimization: Real-time data-driven dynamic adjustment (adjustment period ≤ 15min)

[0380] The present invention provides an intelligent management platform for the remediation of industrial organic contaminated soil based on digital twins. By deploying a variety of sensors (temperature and humidity, pollutant concentration, mechanical operation status, etc.) at the construction site, comprehensive environmental and construction data are collected in real time, and accurate reflection of the construction status is provided in combination with digital twin technology. Through the intelligent construction supervision module, intelligent scheduling of resources such as personnel, machinery, and earthwork is realized, the resource utilization efficiency is maximized, overuse or inefficient use is avoided, and the overall construction efficiency is improved.

[0381] Meanwhile, the present invention adopts a carbon emission data collection and analysis model to monitor the energy consumption and carbon emissions during the soil remediation process in real time, and puts forward optimization suggestions to help project managers reduce unnecessary carbon emissions and ensure environmental protection compliance. In addition, the intelligent control module of the thermal desorption equipment realizes the early prediction and timely maintenance of equipment failures by monitoring the equipment status, pollutant emission concentration, etc. in real time and combining artificial intelligence algorithms, ensuring the efficient operation of the equipment.

[0382] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin, characterized in that, Including: A construction data collection module, which is used to collect construction data and transmit the data to the cloud or local server through a wireless communication network. The construction data includes construction progress data, mechanical equipment operation status, environmental monitoring data, soil pollution data, and construction safety data; A data processing and analysis module, including data cleaning, data modeling, real-time analysis, and data visualization, which is used to perform real-time analysis on the collected construction data, extract key information, and provide decision support; A construction intelligent supervision module, including a personnel scheduling system, a machinery scheduling system, an earthwork scheduling system, and a safety management system, which is used to intelligently schedule and manage the resources at the construction site based on the collection and analysis of construction data; A thermal desorption equipment intelligent control module, including an equipment status monitoring system, a pollutant monitoring system, a remote control system, and a fault diagnosis and early warning system, which is used to intelligently monitor, adjust, and give early warnings to the thermal desorption equipment used in the repair process; A carbon emission intelligent analysis module, including a carbon emission data collection system, a carbon emission analysis model, an optimization suggestion system, and an environmental protection compliance monitoring system, which is used to monitor and calculate carbon emissions during soil remediation and optimize the carbon emission level.

2. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 1, characterized in that, The construction data collection module includes a temperature and humidity sensor, an earthwork volume sensor, a mechanical operation status monitor, an air pollutant concentration sensor, and a data collection gateway. The temperature and humidity sensor, the earthwork volume sensor, the mechanical operation status monitor, and the air pollutant concentration sensor are used to collect construction data. The data collection gateway is used to receive the construction data and transmit the data to the cloud or local server through one or more wireless communication technologies such as Wi-Fi, 4G / 5G, or LoRaWAN.

3. The intelligent management platform for industrial organic contaminated soil remediation based on digital twin according to claim 1, wherein, In the data processing and analysis module, The data cleaning includes missing value filling, outlier detection and elimination. Among them, the interpolation method is used to fill the missing values in the data, and the Z-score method is used to detect outliers.

4. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 3, characterized in that, In the data processing and analysis module, Data modeling is performed on the construction data after data cleaning to construct a multi-dimensional analysis model during the construction process, including a construction efficiency prediction model, an equipment health prediction model, and a pollutant emission prediction model.

5. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 4, wherein In the data processing and analysis module, the real-time analysis corresponding to the construction efficiency prediction model, the equipment health prediction model, and the pollutant emission prediction model all adopts an adaptive sliding window mechanism, and the window time parameter is dynamically adjusted according to the physical characteristics of the variable to evaluate the performance of the construction process in real time.

6. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 4 or 5, characterized in that, In the construction intelligent supervision module, The personnel scheduling system is based on RFID tag technology, which can real-time track the working status and location of each worker and automatically optimize task allocation. The machinery scheduling system is based on the predicted values output by the equipment health prediction model and the data collected by the mechanical operation status monitor to perform real-time monitoring and scheduling of the equipment at the construction site. The earthwork scheduling system is based on the data collected by the earthwork volume sensor to perform real-time tracking of the construction progress and dynamically adjust the earthwork transportation tasks. The safety management system monitors the safety parameters collected at the construction site in real time based on the data collected by temperature and humidity sensors, mechanical operation status monitors, and air pollutant concentration sensors, and identifies potential safety hazards.

7. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 1, characterized in that, In the intelligent control and management module of the thermal desorption equipment, The equipment status monitoring system collects the operation status of the thermal desorption equipment in real time through sensors, including one or more key parameters such as temperature, pressure, and flow rate, to keep it within a predetermined working range. The pollutant monitoring system makes the harmful gases meet the environmental protection discharge standards by monitoring the pollutant concentration in the gas discharged by the equipment in real time. The remote control system can adjust the operation parameters of the thermal desorption equipment according to the equipment status monitoring system and the pollutant monitoring system. The fault diagnosis and early warning system can analyze the operation status of the equipment in real time based on the equipment operation data and historical data collected by the equipment status monitoring system, predict potential faults that may occur in the equipment, and issue early warnings.

8. The intelligent management platform for the remediation of industrial organic contaminated soil based on digital twin according to claim 1, wherein, In the intelligent carbon emission analysis module, The carbon emission data collection system obtains the energy consumption data of the soil excavation, transportation, repair, and external transportation links during the construction process in real time through sensors and IoT devices. The carbon emission analysis model analyzes the carbon emission situation of the construction process based on the energy consumption data and compares it with the environmental protection standards to find the optimization space. The optimization suggestion system provides specific energy conservation and emission reduction solutions based on the carbon emission analysis model, including optimizing equipment scheduling and adjusting construction processes. The environmental protection compliance monitoring system can track in real time whether the carbon emissions during the repair process meet the environmental protection standards and issue early warnings when problems are found.

Images