Polluted site remediation system and method based on artificial intelligence

Abstract

The invention discloses a polluted site remediation system and method based on artificial intelligence. The monitoring module determines the category and quantity of environment monitoring data required to be acquired according to the monitoring scheme; acquiring corresponding environment monitoring data; analyzing the acquired environment monitoring data based on a preset prediction model, and identifying and predicting a pollution condition and a change trend; acquiring basic geographic information data; the three-dimensional module processes the collected geographic information data and constructs a three-dimensional model of the polluted site; marking environmental monitoring data, pollution conditions and change trends in the three-dimensional model; on the basis of the three-dimensional model, different remediation schemes are generated to conduct simulation remediation on the contaminated site, and remediation effects of the different remediation schemes are determined on the basis of a preset rehearsal model; and the repair module determines a repair scheme according to the repair effect of the simulated repair. According to the method, the repairing efficiency, the repairing accuracy and the repairing scientificity can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of environmental pollution monitoring and control, and specifically relates to a contaminated site remediation system and method based on artificial intelligence. Background Art

[0002] Traditional monitoring and control methods for environmental pollution have problems such as low efficiency and high cost. In recent years, the development of artificial intelligence technology has provided new solutions for environmental pollution control. Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods and application systems for simulating, extending and expanding human intelligence. As a cutting-edge technology with powerful data processing and autonomous learning capabilities, it has become the core driving force for a new round of scientific and technological revolution and industrial transformation. The widespread application of artificial intelligence provides strong support for the rational allocation of ecological resources and significantly improves the efficiency of ecological environmental governance. Summary of the invention

[0003] The purpose of the present invention is to provide a contaminated site remediation system and method based on artificial intelligence, which can improve the efficiency, accuracy and scientificity of remediation.

[0004] The technical solution provided by this application is:

[0005] The present application provides a contaminated site remediation system based on artificial intelligence, comprising: a monitoring module, a three-dimensional module and a remediation module;

[0006] The monitoring module determines the type and quantity of environmental monitoring data to be acquired according to the monitoring plan; acquires the corresponding environmental monitoring data; analyzes the acquired environmental monitoring data based on a preset prediction model to identify and predict pollution conditions and change trends; and acquires basic geographic information data;

[0007] The three-dimensional module is used to process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data and the pollution status and change trend in the three-dimensional model;

[0008] The three-dimensional module is also used to generate different restoration schemes based on the three-dimensional model to simulate the restoration of the contaminated site, and determine the restoration effects of different restoration schemes based on the preset preview model;

[0009] The repair module determines a repair plan according to the repair effect of the simulated repair.

[0010] The prediction model and preview model are constructed, trained and solved based on artificial intelligence algorithms (such as machine learning algorithms).

[0011] In a possible implementation, the system is built with a cloud server as the core;

[0012] The obtaining of corresponding environmental monitoring data includes:

[0013] Use sensors to collect corresponding environmental monitoring data;

[0014] The sensor transmits the collected environmental monitoring data to the LoRa gateway through LoRa wireless communication technology;

[0015] The LoRa gateway receives the environmental monitoring data sent by the sensor and uploads the environmental monitoring data to the IoT cloud platform;

[0016] The IoT cloud platform stores environmental monitoring data uploaded from the LoRa gateway and provides a data access interface for the cloud server to pull environmental monitoring data;

[0017] The cloud server pulls environmental monitoring data from the IoT cloud platform.

[0018] In one possible implementation, the environmental monitoring data includes historical and real-time data on pollutant locations, pollutant types, pollutant migration parameters, pollutant chemical parameters, and / or pollution levels;

[0019] The pollution status and changing trends include the location and type of pollution sources, possible pollution diffusion paths, changes in pollution scope, changes in pollutant chemical parameters and / or changes in pollution degree.

[0020] In a possible implementation, the remediation module is further used to adjust the monitoring plan according to the actual situation during the remediation process after the remediation plan is determined and implemented on the contaminated site, and feed back to the monitoring module.

[0021] In one possible implementation, the system also includes an optimization module, which uses deep learning technology to continuously optimize the monitoring module, the three-dimensional module and the repair module, including the algorithms, structures and parameters of the prediction model, three-dimensional modeling and preview model therein.

[0022] In a second aspect, the present application provides a contaminated site remediation system and method based on artificial intelligence, including:

[0023] S1. According to the monitoring plan, determine the type and quantity of environmental monitoring data to be obtained; obtain the corresponding environmental monitoring data; analyze the obtained environmental monitoring data based on the preset prediction model, identify and predict the pollution status and change trend; obtain basic geographic information data;

[0024] S2. Process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data, pollution status and change trend in the three-dimensional model;

[0025] S3. Based on the three-dimensional model, generate different remediation schemes to simulate the remediation of the contaminated site, and determine the remediation effects of different remediation schemes based on the preset preview model;

[0026] S4. Determine the repair plan based on the repair effect of the simulated repair.

[0027] In a possible implementation, the system is built with a cloud server as the core;

[0028] The obtaining of corresponding environmental monitoring data includes:

[0029] Use sensors to collect corresponding environmental monitoring data;

[0030] The sensor transmits the collected environmental monitoring data to the LoRa gateway through LoRa wireless communication technology;

[0031] The LoRa gateway receives the environmental monitoring data sent by the sensor and uploads the environmental monitoring data to the IoT cloud platform;

[0032] The IoT cloud platform stores environmental monitoring data uploaded from the LoRa gateway and provides a data access interface for the cloud server to pull environmental monitoring data;

[0033] The cloud server pulls environmental monitoring data from the IoT cloud platform.

[0034] In one possible implementation, the environmental monitoring data includes historical and real-time data on pollutant locations, pollutant types, pollutant migration parameters, pollutant chemical parameters, and / or pollution levels;

[0035] The pollution status and changing trends include the location and type of pollution sources, possible pollution diffusion paths, changes in pollution scope, changes in pollutant chemical parameters and / or changes in pollution degree.

[0036] In a possible implementation, the remediation module is further used to adjust the monitoring plan according to the actual situation during the remediation process after the remediation plan is determined and implemented on the contaminated site, and feed back to the monitoring module.

[0037] In a possible implementation, the system further includes an optimization module, which utilizes deep learning technology to continuously optimize the monitoring module, the three-dimensional module, and the repair module.

[0038] Beneficial effects:

[0039] This application uses real-time environmental monitoring to accurately predict pollution trends, generate three-dimensional models of contaminated sites, and optimize remediation plans, while continuously optimizing the system through deep learning. This application can improve remediation efficiency, accuracy, and scientificity, while reducing costs and resource waste, which is of great significance to the environment and human health. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a system schematic diagram in one embodiment of the present application;

[0041] Figure 2 A flow chart for establishing a model of a three-dimensional module in one embodiment of the present application;

[0042] Figure 3 This is a flow chart of a communication solution based on a LoRa smart gateway in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0044] Specific embodiments according to the present application will be described below with reference to the accompanying drawings.

[0045] Embodiment 1:

[0046] This embodiment provides a contaminated site remediation system based on artificial intelligence, including: a monitoring module, a three-dimensional module and a remediation module;

[0047] The monitoring module determines the type and quantity of environmental monitoring data to be acquired according to the monitoring plan; acquires the corresponding environmental monitoring data; analyzes the acquired environmental monitoring data based on a preset prediction model to identify and predict pollution conditions and change trends; and acquires basic geographic information data;

[0048] The three-dimensional module is used to process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data and the pollution status and change trend in the three-dimensional model;

[0049] The three-dimensional module is also used to generate different restoration schemes based on the three-dimensional model to simulate the restoration of the contaminated site, and determine the restoration effects of different restoration schemes based on the preset preview model;

[0050] The repair module determines a repair plan according to the repair effect of the simulated repair.

[0051] In some embodiments, the remediation module is also used to adjust the monitoring plan according to the actual situation during the remediation process after determining the remediation plan and implementing the remediation plan on the contaminated site, and feed back to the monitoring module.

[0052] In some embodiments, the system further includes an optimization module, which utilizes deep learning technology to continuously optimize the monitoring module, the three-dimensional module, and the repair module to improve the accuracy and efficiency of the system.

[0053] The system schematic diagram of the embodiment of this application is as follows Figure 1 shown.

[0054] The model establishment flow chart of the three-dimensional module in the embodiment of the present application is as follows Figure 2 The specific process is as follows:

[0055] Determine the goal: clarify the goal that the model needs to achieve, that is, the site remediation goal.

[0056] Review and edit relevant information: Collect and organize information related to the model.

[0057] Establish or improve conceptual model: Build or optimize conceptual model based on objectives and data.

[0058] Whether additional information is needed: Check whether the existing information is sufficient. If not, more information needs to be collected.

[0059] If yes, return to the "Gather required information" step.

[0060] If no, proceed to the next step.

[0061] Choose the right program: Depending on the needs of your model, choose the appropriate program or tool.

[0062] Build or Improve Numerical Models: Using a selected program, build or optimize numerical models.

[0063] Debug the model and perform sensitivity analysis: Debug the model to ensure its correctness and analyze the sensitivity of the model.

[0064] Whether the model results are consistent with the field observations: Compare the model's predictions with the actual observations.

[0065] If not, return to the "Review and edit related information" step.

[0066] If they match, proceed to the next step.

[0067] Model prediction: Use the model to make predictions.

[0068] Evaluate the uncertainty of prediction results: Evaluate the uncertainty of the model's prediction results.

[0069] Whether the conclusion contains uncertainty: Check whether the conclusion has included an assessment of uncertainty.

[0070] If no, the process ends.

[0071] If yes, return to the "Gather required information" step.

[0072] Through the above iterative process, the accuracy and reliability of the model are ensured.

[0073] The communication scheme schematic diagram of the embodiment of the present application based on the LoRa smart gateway is as follows Figure 3 shown.

[0074] The functions and synergistic relationships of each part are described in detail below.

[0075] Sensors:

[0076] Function: Responsible for collecting various environmental monitoring data during the site remediation process, such as soil moisture, temperature, pollutant concentration, etc.

[0077] Collaborative relationship: The sensor transmits data to the LoRa gateway through LoRa wireless communication technology.

[0078] LoRa Gateway:

[0079] Function: Serves as a bridge between sensors and the IoT cloud platform, receiving data sent by sensors and uploading it to the IoT cloud platform.

[0080] Collaborative relationship: The LoRa gateway communicates with the sensor through the LoRa protocol and uploads the collected data to the IoT cloud platform.

[0081] IoT Cloud Platform:

[0082] Function: Stores data uploaded from the LoRa gateway and provides a data access interface for the cloud server to pull data.

[0083] Collaborative relationship: The cloud server pulls data from the IoT cloud platform for further processing and analysis.

[0084] Cloud Server:

[0085] Function: As the core of data processing and intelligent algorithm operation, it pulls data from the IoT cloud platform and performs preliminary data processing and analysis.

[0086] Collaborative relationship: The cloud server sends the processed data to the intelligent algorithm center for in-depth analysis, and feeds back the analysis results to the contaminated site remediation system based on artificial intelligence.

[0087] Intelligent Algorithm Center:

[0088] Function: Use artificial intelligence algorithms to conduct in-depth analysis of data sent by cloud servers, identify environmental change trends, predict potential problems, and provide decision support for site remediation.

[0089] Collaborative relationship: The intelligent algorithm center will feed back the analysis results to the cloud server, which will then integrate this information into the contaminated site remediation system based on artificial intelligence.

[0090] Router and Camera:

[0091] Function: The router provides network connection, and the camera is used to monitor the real-time situation of the venue.

[0092] Collaborative relationship: The router ensures that the cloud server and the intelligent algorithm center can access the network stably. The camera data can also be uploaded to the cloud server through the network for analysis by the intelligent algorithm center.

[0093] The artificial intelligence-based contaminated site remediation system integrates the functions of all modules to achieve real-time monitoring and intelligent management of the site remediation process. It receives the analysis results of the intelligent algorithm center to guide the site remediation work, and exchanges data with the Internet of Things cloud platform through the cloud server. The entire system realizes comprehensive monitoring and management of the site remediation environment through wireless communication, cloud storage, data processing and artificial intelligence analysis. The modules cooperate with each other through data flow and control flow to ensure the effective operation of the system.

[0094] Embodiment 2:

[0095] This embodiment provides a contaminated site remediation system and method based on artificial intelligence, including:

[0096] S1. According to the monitoring plan, determine the type and quantity of environmental monitoring data to be obtained; obtain the corresponding environmental monitoring data; analyze the obtained environmental monitoring data based on the preset prediction model, identify and predict the pollution status and change trend; obtain basic geographic information data;

[0097] In some embodiments, the environmental monitoring data may be historical and real-time data of pollutant location, pollutant type, pollutant migration parameters, pollutant chemical parameters (such as pollutant concentration, effective attenuation coefficient) and / or pollution degree (pollution level). Environmental monitoring data may also include soil (temperature, humidity, dispersion coefficient), groundwater (pH, water temperature, conductivity, redox potential, dissolved oxygen, angular velocity), permeability coefficient, etc.

[0098] In some embodiments, the pollution status and change trend may be the location of the pollution source, possible pollution diffusion path, change in pollution range, change in pollutant chemical parameters and / or change in pollution degree;

[0099] In some embodiments, the basic geographic information data includes topography, landforms, water systems, etc.

[0100] In some embodiments, the prediction model for predicting pollutant concentration is:

[0101]

[0102] Where C is the pollutant concentration at time point (X, Y); X is the dimensionless x-coordinate; Y is the dimensionless y-coordinate; T is the dimensionless time; B is the boundary concentration function of the pollutant concentration changing with time; D is the dimensionless soil dispersion coefficient; Λ is the dimensionless effective attenuation coefficient of the pollutant, and ω is the groundwater angular velocity, in rad / s;

[0103] In some embodiments, the accuracy of the prediction is evaluated by a loss function, which is:

[0104]

[0105] Where N is the number of monitoring samples; y i is the true value of the pollution status and change trend of the i-th sample; is the pollution status and change trend prediction value of the i-th sample.

[0106] S2. Process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data, pollution status and change trend in the three-dimensional model;

[0107] This step ensures that users / decision makers can intuitively and in real time understand the current status and forecast of the contaminated site.

[0108] In some embodiments, marking the environmental monitoring data, pollution status and change trend in the three-dimensional model includes marking the location and type of the pollution source and the possible pollution diffusion path in the three-dimensional model.

[0109] S3. Based on the three-dimensional model, generate different remediation schemes to simulate the remediation of the contaminated site, and determine the remediation effects of different remediation schemes based on the preset preview model;

[0110] In some embodiments, this step includes, for each restoration plan, predicting the restoration effect of the restoration plan based on preset model parameters and algorithms; the restoration effect includes changes in the degree of pollution, such as reduction in pollutant concentration, ecological recovery of the restoration area, etc.

[0111] Through this step, the user simulates the repair in the three-dimensional model, and the repair effect of the simulated repair can be fed back to the monitoring module and the repair module, providing a basis for adjusting the actual monitoring plan and the repair plan.

[0112] In some embodiments, the parameters of the repair scheme, such as the type, amount, and repair time of the repair material, can be adjusted to obtain different repair schemes.

[0113] S4. Determine the repair plan based on the repair effect of the simulated repair.

[0114] In some embodiments, after the remediation plan is determined, the remediation plan is implemented on the contaminated site, and the monitoring plan is adjusted according to the actual situation during the remediation process and fed back to the monitoring module.

[0115] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0116] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A contaminated site remediation system based on artificial intelligence, characterized in that: include: Monitoring module, 3D module and repair module; The monitoring module determines the type and quantity of environmental monitoring data to be acquired according to the monitoring plan; Obtain corresponding environmental monitoring data; analyze the acquired environmental monitoring data based on the preset prediction model, identify and predict pollution conditions and change trends; obtain basic geographic information data; The three-dimensional module is used to process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data and the pollution status and change trend in the three-dimensional model; The three-dimensional module is also used to generate different restoration schemes based on the three-dimensional model to simulate the restoration of the contaminated site, and determine the restoration effects of different restoration schemes based on the preset preview model; The repair module determines a repair plan according to the repair effect of the simulated repair.

2. The system according to claim 1, characterized in that The system is built with cloud servers as the core; The obtaining of corresponding environmental monitoring data includes: Use sensors to collect corresponding environmental monitoring data; The sensor transmits the collected environmental monitoring data to the LoRa gateway through LoRa wireless communication technology; The LoRa gateway receives the environmental monitoring data sent by the sensor and uploads the environmental monitoring data to the IoT cloud platform; The IoT cloud platform stores environmental monitoring data uploaded from the LoRa gateway and provides a data access interface for the cloud server to pull environmental monitoring data; The cloud server pulls environmental monitoring data from the IoT cloud platform.

3. The system according to claim 1, characterized in that The environmental monitoring data include historical and real-time data on pollutant locations, pollutant types, pollutant migration parameters, pollutant chemical parameters and / or pollution levels; The pollution status and changing trends include the location and type of pollution sources, possible pollution diffusion paths, changes in pollution scope, changes in pollutant chemical parameters and / or changes in pollution degree.

4. The system according to claim 1, characterized in that The remediation module is also used to adjust the monitoring plan according to the actual situation during the remediation process after the remediation plan is determined and implemented on the contaminated site, and feed back to the monitoring module.

5. The system according to claim 1, characterized in that The system also includes an optimization module, which uses deep learning technology to continuously optimize the monitoring module, the three-dimensional module and the repair module.

6. A contaminated site remediation method based on artificial intelligence, characterized in that: include: S1. Determine the type and quantity of environmental monitoring data to be obtained according to the monitoring plan; Obtain corresponding environmental monitoring data; Analyze the acquired environmental monitoring data based on the preset prediction model, identify and predict the pollution status and change trend; obtain basic geographic information data; S2. Process the collected geographic information data to construct a three-dimensional model of the contaminated site; mark the environmental monitoring data, pollution status and change trend in the three-dimensional model; S3. Based on the three-dimensional model, generate different remediation schemes to simulate the remediation of the contaminated site, and determine the remediation effects of different remediation schemes based on the preset preview model; S4. Determine the repair plan based on the repair effect of the simulated repair.

7. The method according to claim 1, characterized in that The system is built with cloud servers as the core; The obtaining of corresponding environmental monitoring data includes: Use sensors to collect corresponding environmental monitoring data; The sensor transmits the collected environmental monitoring data to the LoRa gateway through LoRa wireless communication technology; The LoRa gateway receives the environmental monitoring data sent by the sensor and uploads the environmental monitoring data to the IoT cloud platform; The IoT cloud platform stores environmental monitoring data uploaded from the LoRa gateway and provides a data access interface for the cloud server to pull environmental monitoring data; The cloud server pulls environmental monitoring data from the IoT cloud platform.

8. The method according to claim 1, characterized in that The environmental monitoring data include historical and real-time data on pollutant locations, pollutant types, pollutant migration parameters, pollutant chemical parameters and / or pollution levels; The pollution status and changing trends include the location and type of pollution sources, possible pollution diffusion paths, changes in pollution scope, changes in pollutant chemical parameters and / or changes in pollution degree.

9. The method according to claim 1, characterized in that: The remediation module is also used to adjust the monitoring plan according to the actual situation during the remediation process after the remediation plan is determined and implemented on the contaminated site, and feed back to the monitoring module.

10. The method according to claim 1, characterized in that The system also includes an optimization module, which uses deep learning technology to continuously optimize the monitoring module, the three-dimensional module and the repair module.

Images