Intelligent monitoring and decision-making system and method for soil pollution remediation process

Abstract

The invention relates to an intelligent monitoring and decision-making system for a soil pollution remediation process, and the system comprises a data collection layer which is used for collecting and uploading the data of a pollution remediation site; the data processing layer is used for receiving, cleaning, storing and managing data of a pollution remediation site; the analysis and decision-making layer is used for carrying out intelligent analysis such as pollution diffusion prediction, equipment state monitoring and restoration progress optimization on the data; and the user interface layer is used for remote monitoring, dynamic operation and information feedback of pollution remediation data and equipment states. According to the system, through cooperative work of the data acquisition layer, the data processing layer, the analysis and decision-making layer and the user interface layer, intelligent management and scientific decision-making of the soil pollution remediation process are achieved. The system collects on-site key data in real time through the Internet of Things, provides real-time monitoring, automatic control and decision support for pollution remediation projects by combining big data analysis and machine learning technologies, and ensures that the remediation process is efficient, low-carbon and safe.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection and soil remediation, and in particular to an intelligent monitoring and decision-making system and method for a soil pollution remediation process. Background Art

[0002] At present, soil pollution remediation projects often involve complex harmful substances, multiple pollution sources, and various treatment methods, which requires efficient monitoring and decision-making mechanisms. However, traditional soil remediation technology has obvious deficiencies in real-time data collection, analysis, and control, including:

[0003] (1) Data collection is delayed and lacks real-time performance: During the repair process, data such as pollutant concentration and equipment status mostly rely on manual measurement, which results in delayed response and makes it difficult to provide real-time feedback on on-site conditions.

[0004] (2) Insufficient data integration: Remediation project data covers multiple dimensions such as pollutant monitoring, soil characteristics, and equipment operation. Traditional methods are unable to integrate multi-source data, resulting in data isolation and incomplete decision-making.

[0005] (3) Lack of automated control: The remediation equipment requires manual control and cannot dynamically respond to pollution changes, resulting in high energy consumption and low efficiency.

[0006] (4) Imperfect early warning and decision support: Traditional systems are unable to provide pollution diffusion trend predictions and equipment early warnings, which affects the efficiency and safety of the construction process.

[0007] The shortcomings of existing soil pollution remediation technologies are mainly concentrated in the aspects of non-real-time data collection, insufficient data integration, lack of intelligent control and decision support, which limit the efficiency and safety of soil remediation projects. In view of these technical bottlenecks, the present invention proposes an intelligent monitoring and decision-making system based on the Internet of Things and big data, which realizes the dynamic management of the whole life cycle of pollution remediation by constructing a digital twin model of the soil pollution remediation process. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the deficiencies in the prior art and provide an intelligent monitoring and decision-making system and method for soil pollution remediation process based on the Internet of Things and big data.

[0009] The present invention is achieved through the following technical solutions:

[0010] An intelligent monitoring and decision-making system for soil pollution remediation process, comprising:

[0011] The data collection layer includes a variety of sensors deployed at the pollution remediation site to collect and upload data from the pollution remediation site;

[0012] A data processing layer, used for receiving, cleaning, storing and managing the data of the pollution remediation site transmitted from the data acquisition layer;

[0013] The analysis and decision-making layer is used to conduct intelligent analysis of data, including pollution spread prediction, equipment status monitoring, and repair progress optimization;

[0014] The user interface layer is used for remote monitoring, dynamic operation and information feedback of pollution remediation data and equipment status.

[0015] According to the above technical solution, preferably, in the data acquisition layer, the sensor includes one or more of a pollutant sensor, a temperature and humidity sensor, a soil pH sensor, and an equipment status sensor.

[0016] According to the above technical solution, preferably, the pollutant sensor is used to collect VOC concentration and benzopyrene concentration, the temperature and humidity sensor is used to collect temperature and humidity, the soil pH sensor is used to collect soil pH, and the equipment status sensor is used to collect equipment operating time, equipment temperature, and energy consumption.

[0017] According to the above technical solution, preferably, the data processing layer includes: data cleaning, eliminating outliers and filling missing values ​​in the collected data; data formatting, standardizing the data collected by different sensors; data storage and management, storing the cleaned data in a relational database, and indexing the data by timestamp and sensor type. The data processing layer establishes a standard API interface to quickly call data.

[0018] According to the above technical solution, preferably, in the pollution diffusion prediction, based on VOC concentration, benzopyrene concentration, temperature, humidity, soil pH, the pollutant diffusion trend is predicted by a pollution diffusion prediction model.

[0019] According to the above technical solution, preferably, the overall architecture of the pollution diffusion prediction model includes: a CNN layer for extracting the spatial characteristics of pollutant concentration distribution; an LSTM layer for capturing the changing trend in the time dimension, especially the long-term dependency of multi-time series data; and a fully connected layer for outputting the concentration distribution results of pollutant diffusion prediction.

[0020] The present application also discloses a soil pollution remediation process intelligent monitoring and decision-making method, based on the above-mentioned soil pollution remediation process intelligent monitoring and decision-making system, comprising the following steps:

[0021] S1. Collecting data from the pollution remediation site through the sensors in the data acquisition layer and transmitting it to the data processing layer;

[0022] S2. The data processing layer receives, cleans, stores and manages the data transmitted from the data acquisition layer for the analysis and decision-making layer and the user interface layer to call;

[0023] S3. The analysis and decision-making layer calls the data of the pollution remediation site of the data processing layer, performs pollution spread prediction, equipment status monitoring and remediation progress optimization on the data, and transmits it to the user interface layer in the form of structured data;

[0024] S4. The user interface layer performs remote monitoring, dynamic operation and information feedback on pollution remediation data and equipment status.

[0025] The beneficial effects of the present invention are:

[0026] Compared with the prior art, the system of the present invention has achieved significant improvements in the intelligence, automation and resource optimization of soil pollution remediation. The specific effects include:

[0027] (1) Enhance the real-time performance and accuracy of the system:

[0028] Through the Internet of Things technology, the system realizes automatic data collection and real-time update, which effectively makes up for the problem of delayed manual collection in traditional methods. The data processing layer integrates multi-source data, eliminates the problem of data islands, makes the information more comprehensive and accurate, and ensures accurate management of the repair process.

[0029] (2) Efficient intelligent equipment control:

[0030] Through the automated control module, the system dynamically adjusts the operating status of the equipment according to pollutant concentration, repair progress, etc., thereby improving the working efficiency of the repair equipment and reducing unnecessary energy consumption and human intervention.

[0031] (3) Intelligent analysis and prediction functions:

[0032] Based on machine learning and big data analysis, this system can predict pollutant diffusion trends and the status of repair equipment, and provide scientific construction strategies and equipment maintenance recommendations to improve the accuracy and timeliness of decision-making.

[0033] (4) Real-time warning and decision support:

[0034] The system has a sensitive early warning mechanism, which automatically alarms by setting thresholds for pollutant concentrations and equipment parameters to ensure the safety of the repair process. Managers can obtain the repair plans and risk warnings generated by the system through the interface to improve the reliability and safety of the repair project. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is the architecture diagram of the intelligent monitoring and decision-making system for the soil pollution remediation process in the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and the best embodiment. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the invention.

[0037] As shown in the figure, the present invention includes the following four functional modules: data acquisition layer, data processing layer, analysis and decision-making layer and user interface layer, which realize intelligent monitoring and decision-making support of soil pollution remediation process through multi-layer collaboration.

[0038] (i) Data collection layer, including a variety of sensors deployed at the pollution remediation site, used to collect and upload data at the pollution remediation site, including pollutant concentration, environmental parameters, equipment status, etc. Among them, in the data collection layer, the sensors include one or more of pollutant sensors, temperature and humidity sensors, soil pH sensors, and equipment status sensors.

[0039] Specifically, pollutant sensors are installed in polluted soil or air to detect specific pollutants such as volatile organic compounds (VOC), benzopyrene, and benzanthracene. Sensor types include gas concentration sensors and chemical sensors. Collection parameters: VOC concentration (ppm), benzopyrene concentration (mg / m 3 )wait.

[0040] Temperature and humidity sensors are placed in the soil remediation construction area to monitor the ambient temperature and humidity in order to analyze the volatilization characteristics of pollutants and remediation conditions. Collection parameters: temperature (℃), humidity (%).

[0041] The soil pH sensor is installed in the soil to monitor the soil pH value, which is convenient for adjusting the dosage of the chemical remediation. Collection parameters: soil pH.

[0042] The equipment status sensor is integrated into the repair equipment (such as thermal desorption equipment, chemical oxidation equipment) to monitor the equipment's operating status and energy consumption in real time. Collection parameters: equipment operating time (hours), equipment temperature (℃), energy consumption (kW·h).

[0043] The preferred implementation process in the data collection layer:

[0044] (1) Each sensor collects field data in real time and sends it to the IoT gateway regularly;

[0045] (2) Transmitting data to the data processing layer via a wireless network or a wired network;

[0046] (3) Data is stored in a standardized format to ensure consistency in subsequent data processing.

[0047] (ii) Data processing layer, which is used to receive, clean, store and manage the data of the pollution remediation site transmitted from the data collection layer, ensure the accuracy and consistency of the data, and provide support for the analysis layer. Specifically including:

[0048] Data cleaning: remove outliers (such as extreme temperatures and extremely high concentrations) and fill in missing values ​​in the collected data;

[0049] Data formatting: standardize the data collected by different sensors (such as the temperature unit is unified as Celsius) to ensure seamless integration of data within the system;

[0050] Data storage and management: The cleaned data is stored in a relational database for efficient query and retrieval; the data is indexed by timestamp and sensor type to facilitate subsequent analysis and display; the data processing layer establishes a standard API interface to support other modules of the system to quickly call data.

[0051] Among them, the preferred implementation process of the data processing layer is:

[0052] (1) Receive the original data transmitted by the data acquisition layer;

[0053] (2) Remove outliers through data cleaning algorithms and fill in missing values;

[0054] (3) Data is stored in the database according to timestamp and parameter type to ensure that it is available for query and analysis at any time.

[0055] (iii) The analysis and decision-making layer conducts intelligent analysis of data based on big data and machine learning algorithms, including pollution spread prediction, equipment status monitoring, and repair progress optimization, thereby providing scientific decision-making support for managers.

[0056] In the pollution diffusion prediction, based on VOC concentration, benzopyrene concentration, temperature, humidity, and soil pH, the pollution diffusion prediction model is used to predict the pollutant diffusion trend. The overall architecture of the pollution diffusion prediction model includes: CNN layer, which is used to extract the spatial characteristics of pollutant concentration distribution; LSTM layer, which is used to capture the change trend in the time dimension, especially the long-term dependence of multi-time series data; fully connected layer, which is used to output the concentration distribution results of pollutant diffusion prediction.

[0057] Model input:

[0058] The pollutant concentration matrix C at the current moment t , indicating the pollutant concentration at different locations (unit: mg / m 3 );

[0059] Environmental parameter matrix E t : Including real-time data such as wind speed (m / s), humidity (%), temperature (℃);

[0060] Soil characteristic parameters S: including soil porosity, permeability, water content, etc.

[0061] Model output:

[0062] Predicted pollutant concentration matrix at time t+n in the future That is, the predicted value of pollutant concentration at each location at a future time point.

[0063] Algorithm flow:

[0064] 1. Data preprocessing: Historical pollutant concentration data C t―1 ,C t―2 ,…,C t―m and environmental parameter data E t―1 ,E t―2 ,…,E t―m Normalization and standardization are performed to form a training data set.

[0065] 2. Spatial feature extraction (CNN layer):

[0066] The spatial features of pollutant concentration distribution are extracted through convolution operation, and multiple convolution kernels are set to extract the relationship between pollution concentrations at different locations. The formula of convolution operation is as follows:

[0067]

[0068] in, represents the output after the lth layer of convolution, W (l) and b (l) are the weight and bias of the convolution kernel, and f is the activation function.

[0069] 3. Temporal feature capture (LSTM layer):

[0070] The spatial features extracted by CNN are used as input and sent to the LSTM layer for time series learning. LSTM uses a gating mechanism to control which information needs to be passed, forgotten, or updated.

[0071] The state update formula of LSTM is:

[0072] i t =σ(W i ·[h t―1 ,C t ]+b i )

[0073] f t =σ(W f ·[ht―1 ,C t ]+b f )

[0074] o t =σ(W o ·[h t―1 ,C t ]+b o )

[0075]

[0076] h t =o t *tanh(C t )

[0077] Among them, i t 、f t , o t They are input gate, forget gate and output gate respectively, σ represents Sigmoid activation function, C t and h t are the unit state and output state respectively.

[0078] 4. Fully connected layer outputs prediction results: The features output by the LSTM layer are passed to the fully connected layer to output the pollution concentration distribution prediction at the future time t+n

[0079] 5. Model training: Use historical pollutant concentration and environmental parameter data to train the model, and use mean square error (MSE) as the loss function:

[0080]

[0081] Where N is the number of prediction points, is the actual pollution concentration, is the predicted value. The optimizer selects the Adam optimization algorithm for back propagation and iteratively updates the model parameters.

[0082] In addition, in "Equipment Status Monitoring and Intelligent Control", combined with data such as equipment operating time and temperature, the algorithm detects equipment abnormalities (such as excessive temperature, excessive operating time), and automatically generates maintenance suggestions. In "Carbon Emission Calculation and Optimization", based on equipment energy consumption and repair methods, the carbon emissions of the repair process are calculated through big data models to provide low-carbon optimization solutions.

[0083] Optimal implementation process in the analysis and decision-making layer:

[0084] (1) Data is extracted from the data processing layer and enters the analysis module;

[0085] (2) Analyze data based on models, including pollution spread prediction, equipment monitoring, carbon emission calculation, etc.;

[0086] (3) The analysis results are delivered to the user interface layer in the form of structured data, and corresponding operation suggestions are provided.

[0087] (iv) User interface layer: provides an intuitive operating interface for management personnel and construction personnel, displays pollution remediation data and equipment status in real time, and supports remote monitoring, dynamic operation and information feedback of remediation projects through multiple platforms (PC, mobile, etc.).

[0088] The main functions of the user interface layer are:

[0089] Real-time data display: The user interface layer displays real-time data such as temperature, humidity, VOC concentration, equipment status, etc., and displays pollution remediation status through visual charts and 3D models;

[0090] Early warning and suggestion prompts: When the data is abnormal or exceeds the set threshold, the system displays an alarm message on the interface and generates operational suggestions (such as lowering the equipment temperature, increasing the amount of repair agent);

[0091] Visualization of repair progress: The digital twin model built based on BIM and GIS shows the diffusion of pollutants and the distribution of equipment during the repair process, which helps managers to intuitively understand the on-site conditions;

[0092] Decision support and operational suggestions: Decision support information generated through big data analysis is intuitively displayed on the interface, and managers can adopt the repair plan recommended by the system with one click.

[0093] At the same time, the user interface operation process in the user interface layer is preferably:

[0094] (1) The user logs in to the system, enters the monitoring page, and views real-time data and repair progress;

[0095] (2) Receive warning notifications and repair suggestions generated by the system, and make equipment adjustments or optimize repair strategies based on the suggestions displayed on the interface;

[0096] (3) You can choose to export or send the system analysis report to management as a basis for project decision-making.

[0097] The system of the present invention realizes intelligent management and scientific decision-making of the soil pollution remediation process through the coordinated work of the data acquisition layer, data processing layer, analysis and decision-making layer and user interface layer. The system collects key data on site in real time through the Internet of Things, combines big data analysis and machine learning technology, and provides real-time monitoring, automatic control and decision support for pollution remediation projects, ensuring that the remediation process is efficient, low-carbon and safe.

[0098] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent monitoring and decision-making system for soil pollution remediation process, characterized in that: include: The data collection layer includes a variety of sensors deployed at the pollution remediation site to collect and upload data from the pollution remediation site; A data processing layer, used for receiving, cleaning, storing and managing the data of the pollution remediation site transmitted from the data acquisition layer; The analysis and decision-making layer is used to perform intelligent analysis of data, including pollution spread prediction, equipment status monitoring, and repair progress optimization.

2. According to claim 1, a soil pollution remediation process intelligent monitoring and decision-making system is characterized in that: In the data acquisition layer, the sensors include one or more of pollutant sensors, temperature and humidity sensors, soil pH sensors, and equipment status sensors.

3. According to claim 2, a soil pollution remediation process intelligent monitoring and decision-making system is characterized in that: The pollutant sensor is used to collect VOC concentration and benzopyrene concentration, the temperature and humidity sensor is used to collect temperature and humidity, the soil pH sensor is used to collect soil pH, and the equipment status sensor is used to collect equipment operating time, equipment temperature, and energy consumption.

4. According to claim 1, the intelligent monitoring and decision-making system for soil pollution remediation process is characterized in that: The data processing layer includes: Data cleaning, removing outliers and filling missing values ​​in collected data; Data formatting, standardizing the data collected by different sensors; Data storage and management: The cleaned data is stored in a relational database. The data is indexed by timestamp and sensor type. The data processing layer establishes a standard API interface to quickly call data.

5. According to claim 3, the intelligent monitoring and decision-making system for soil pollution remediation process is characterized in that: In the pollution diffusion prediction, based on VOC concentration, benzopyrene concentration, temperature, humidity, and soil pH, the pollutant diffusion trend is predicted by a pollution diffusion prediction model.

6. According to claim 5, a soil pollution remediation process intelligent monitoring and decision-making system is characterized in that: The overall architecture of the pollution diffusion prediction model includes: CNN layer, used to extract the spatial characteristics of pollutant concentration distribution; LSTM layer, used to capture the changing trend in the time dimension, especially the long-term dependency of multiple time series data; The fully connected layer is used to output the concentration distribution results of pollutant diffusion prediction.

7. According to claim 1, the intelligent monitoring and decision-making system for soil pollution remediation process is characterized in that: Also includes: The user interface layer is used for remote monitoring, dynamic operation and information feedback of pollution remediation data and equipment status.

8. A soil pollution remediation process intelligent monitoring and decision-making method, based on the soil pollution remediation process intelligent monitoring and decision-making system of claim 7, characterized in that: The steps include: S1. Collecting data from the pollution remediation site through the sensors in the data acquisition layer and transmitting it to the data processing layer; S2. The data processing layer receives, cleans, stores and manages the data transmitted from the data acquisition layer for the analysis and decision-making layer and the user interface layer to call; S3. The analysis and decision-making layer calls the data of the pollution remediation site of the data processing layer, performs pollution spread prediction, equipment status monitoring and remediation progress optimization on the data, and transmits it to the user interface layer in the form of structured data; S4. The user interface layer performs remote monitoring, dynamic operation and information feedback on pollution remediation data and equipment status.

Images