Landfill vertical anti-seepage facility management method and system based on digital twinning

Abstract

The invention discloses a landfill vertical anti-seepage facility management method and system based on digital twinning, and relates to the technical field of environmental governance, and the method comprises the steps: building a landfill digital twinning model based on geological exploration data, and carrying out the parametric modeling of a vertical curtain anti-seepage layer; synchronizing real-time data and the digital twinborn model; processing the monitoring data in combination with a machine learning algorithm model; and remote monitoring and operation of the landfill are realized by combining a cloud platform and a remote sensor. According to the landfill vertical anti-seepage facility management method based on digital twinning, the digital twinning model of the landfill is constructed based on geological exploration data, the reliability and durability of the landfill anti-seepage facility are effectively improved, the remote supervision and risk assessment model is constructed on the cloud platform, the environmental risk is reduced to the maximum extent, and the safety of the landfill is improved. The method has better effects in the aspects of reliability, durability, long-term operation cost and safety of the landfill anti-seepage facility.

Description

Technical Field

[0001] The present invention relates to the field of environmental governance technology, and specifically to a landfill vertical anti-seepage facility management method and system based on digital twin. Background Art

[0002] In the continuous development of landfill management technology, traditional anti-seepage facility design and management methods mainly rely on static design and periodic manual inspection. These methods are usually based on experience or preliminary geological exploration reports to determine the design parameters of the anti-seepage layer, such as material selection, thickness, permeability, etc. However, with the expansion of landfill scale and the increase in the complexity of waste treatment, these traditional methods have gradually exposed their shortcomings. Specifically, the environmental conditions and diffusion behavior of pollutants in landfills are extremely complex, and it is difficult to cope with various variables in the long-term operation of landfills by simply relying on initial static design. In addition, conventional monitoring methods usually rely on manual regular data collection, which makes it difficult to achieve real-time and comprehensive monitoring of landfills, which may lead to delayed response to environmental risks.

[0003] In recent years, with the development of digital twin technology, especially in the field of engineering and infrastructure management, this technology has gradually been introduced into landfill management. Digital twin technology achieves accurate monitoring and optimized management of physical systems by building digital models of physical entities and combining real-time data with dynamic updates of simulation models. However, existing digital twin applications are usually concentrated in a single dimension or a single scenario, such as limited to structural health monitoring or energy consumption management, and lack the ability to comprehensively manage multiple dimensions and variables in the complex environment of landfills. In addition, most of the existing digital twin models are based on simple physical models or data-driven models, and fail to fully combine the complex geological, hydrological, chemical reactions and other factors in the landfill, resulting in certain limitations in the design of anti-seepage layers, prediction of pollutant diffusion, and environmental risk assessment. Especially in dealing with the nonlinear diffusion and complex reaction of pollutants in landfills, the limitations of traditional methods are more prominent, and it is difficult to meet the needs of long-term stable operation and environmental protection of landfills. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing design and management methods of anti-seepage facilities have the problems of poor reliability and durability of landfill anti-seepage facilities, low safety, and environmental protection efficiency.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a landfill vertical anti-seepage facility management method based on digital twins, comprising constructing a landfill digital twin model based on geological exploration data, and performing parametric modeling of the vertical curtain anti-seepage layer; synchronizing real-time data with the digital twin model; processing the monitoring data in combination with a machine learning algorithm model; and realizing remote supervision and operation of the landfill in combination with a cloud platform and remote sensors.

[0007] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twins described in the present invention, wherein: the construction of a landfill digital twin model based on geological exploration data includes first collecting design documents, monitoring plans, geological and hydrological conditions, and landfill record information of the landfill site;

[0008] Use Revit to model the project in 3D, build a geological and hydrological model based on the geological survey report, and add information on stratum type, groundwater level, and drainage system;

[0009] Establish a geometric model of the garbage pile, including the layout of the landfill, the type and composition of each part of the garbage, the depth and time of the landfill;

[0010] Add climate and environmental information of the landfill site, including temperature, humidity, wind speed, wind direction, and precipitation;

[0011] Combining the diffusion-convection equation and the reaction term, a pollutant diffusion model in the landfill is constructed, which is expressed as:

[0012]

[0013] Where C represents the pollutant concentration, represents the concentration gradient, D represents the diffusion coefficient, represents the divergence operator, v represents the groundwater velocity vector, k r is the reaction rate constant, C max Indicates the maximum concentration value of pollutants in the system;

[0014] The pollutant diffusion model is used to predict the concentration distribution of pollutants at future time points.

[0015] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twin described in the present invention, wherein: the parametric modeling of the vertical curtain anti-seepage layer includes parametric modeling of the vertical curtain anti-seepage layer in the digital twin model, and incorporating key design parameters of the anti-seepage layer into the model, including thickness, material type, and permeability;

[0016] The vertical curtain model is combined with the geological and garbage dump models. Numerical simulation methods, including finite element analysis and numerical permeability simulation, are used to simulate the permeability of different anti-seepage layer design parameters. The performance of each combination of anti-seepage layer design parameters, including permeability, seepage fluid head, and leachate flow rate, is evaluated. Multi-objective optimization is performed using an optimization algorithm to determine the optimal anti-seepage layer design parameters, which are expressed as:

[0017]

[0018] Among them, K(x) represents the permeability coefficient, which varies with the design parameter x, C(x) represents the total cost, taking into account the material, construction and maintenance costs, and α represents the cost weight coefficient.

[0019] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twins described in the present invention, wherein: the synchronized real-time data and the digital twin model include determining parameters to be monitored, including groundwater level, soil moisture content, chemical composition of landfill materials, and gas emissions;

[0020] According to the nature of the monitoring parameters and the actual situation of the landfill, sensors and monitoring equipment are selected, including gas detectors, water quality sensors, and soil samplers. The sensor layout is optimized by using information entropy and cost optimization, and the sensor deployment and real-time monitoring model is constructed as follows:

[0021]

[0022] Where n represents the number of sensors, H(Z i ) represents information entropy, i represents sensor, Z i represents the observation data of sensor i, λ represents the weight coefficient, cost(X i ) represents the layout cost of sensor i, X i represents the layout position of sensor i;

[0023] Based on the sensor deployment and real-time monitoring model, the information gain and cost balance model under the optimal sensor layout scheme is constructed, which is expressed as:

[0024]

[0025] Among them, F max Under the optimal sensor layout scheme, it represents the maximum value of the total information gain brought by all sensor layouts minus the total cost. Indicates that sensor i is in the optimal position Observational data at

[0026] Based on the twin model, the sensor network is arranged to ensure the distribution of monitoring points, taking into account the environment, topography, geology, landfill material distribution, landfill size and layout factors;

[0027] Establish a real-time data synchronization system to ensure that the real-time data collected by sensors is synchronized to the digital twin model in a timely manner.

[0028] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twins described in the present invention, wherein: the processing of monitoring data in combination with a machine learning algorithm model includes processing the monitoring data in combination with a machine learning algorithm model, using a digital twin model to simulate the impact of different factors in the landfill on the performance of the anti-seepage layer, predicting performance changes, discovering potential problems in advance, developing a real-time decision support system, providing decision makers with real-time landfill operation status based on real-time data and simulation results, and supporting decision makers to formulate immediate management and maintenance plans;

[0029] Ensure the quality and integrity of monitoring data, perform pre-processing, remove outliers, and normalize;

[0030] Construct a long short-term memory network model to process time series data. Input the prepared time series data into the long short-term memory network model for training. Through learning from historical data, the long short-term memory network model collects the changing patterns of various monitoring parameters in the landfill and forms an understanding of the landfill behavior.

[0031] The long short-term memory network model predicts monitoring data in the future and performs anomaly detection;

[0032] Integrating the long short-term memory network model into the digital twin decision support system provides a comprehensive digital twin view and supports real-time decision making.

[0033] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twins described in the present invention, wherein: the remote supervision and operation of the landfill in combination with the cloud platform and the remote sensor includes remote supervision and operation of the landfill in combination with the cloud platform and the remote sensor;

[0034] Use digital twin technology to conduct long-term performance evaluation, analyze the changing trends of landfills, and build a cloud platform remote supervision and risk assessment model:

[0035]

[0036] Where R represents the overall risk, Θ represents the parameter space, L(θ) represents the loss function. The larger the value of the loss function, the higher the risk under the parameter. D represents the observed data, p(θ|D) represents the posterior probability density function, and θ represents the uncertain parameters in the system model, including the physical properties of the landfill, the concentration of pollutants, and the groundwater flow rate. represents the estimated value of the parameter, represents the Fisher information matrix;

[0037] Based on the assessment results, develop maintenance and upgrade strategies.

[0038] As a preferred solution of the landfill vertical anti-seepage facility management method based on digital twins described in the present invention, wherein: the remote supervision and operation of the landfill achieved by combining the cloud platform and remote sensors includes the output of the evaluation results in the cloud platform including a real-time monitoring dashboard, an alarm and notification system, report generation, and forecast and trend analysis;

[0039] The assessment results are categorized into:

[0040] Normal operating status, performance degradation, anomaly detection, risk warning, and optimization suggestions;

[0041] Normal operation status means that the evaluation results show that the system is operating within the expected range and no immediate action is required;

[0042] Performance degradation indicates that a performance indicator has been identified to have degraded, requiring maintenance or adjustment of operating parameters;

[0043] Anomaly detection means finding abnormal points in the data, indicating equipment failure or operational errors;

[0044] Risk warning means that potential risks are predicted and measures need to be taken in advance to avoid problems;

[0045] Optimization suggestions indicate that the analysis results indicate there is room for improvement and provide recommendations for optimizing operations or processes.

[0046] Another object of the present invention is to provide a landfill vertical anti-seepage facility management system based on digital twin, which can solve the problems of poor reliability and durability of landfill anti-seepage facilities in current anti-seepage facility design and management methods by constructing a landfill digital twin model and performing parametric modeling.

[0047] As a preferred solution of the landfill vertical anti-seepage facility management system based on digital twin described in the present invention, it includes: a landfill digital twin model construction module, an optimization design module for a vertical curtain anti-seepage layer, a sensor and monitoring equipment deployment module, a monitoring data processing module, and a remote supervision and operation module; the landfill digital twin model construction module is used to create a BIM model of the landfill site; the vertical curtain anti-seepage layer optimization design module is used to simulate and analyze to determine the optimal anti-seepage layer thickness and material type design parameters; the sensor and monitoring equipment deployment module is used to synchronize real-time data with the digital twin model; the monitoring data processing module is used to process the monitoring data in combination with a machine learning algorithm model; the remote supervision and operation module is used to combine a cloud platform and remote sensors to achieve remote supervision and operation of the landfill.

[0048] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for managing vertical anti-seepage facilities of a landfill based on digital twins.

[0049] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a landfill vertical anti-seepage facility management method based on digital twins.

[0050] Beneficial effects of the present invention: The landfill vertical anti-seepage facility management method based on digital twin provided by the present invention constructs a digital twin model of the landfill based on geological exploration data to achieve accurate simulation of the internal structure and pollutant distribution of the landfill. The ability to predict and design in advance can greatly reduce potential design changes and environmental problems in actual construction, and effectively improve the reliability and durability of the landfill anti-seepage facilities. By synchronizing real-time data with the digital twin model, it is ensured that the model can be updated in real time as the operation of the landfill changes. Real-time synchronization can capture dynamic changes in the environment within the landfill, such as fluctuations in groundwater levels, changes in soil moisture content, etc., to avoid potential environmental hazards and ensure the safe operation of the landfill. The monitoring data is processed in combination with the machine learning algorithm model. By learning from historical data, the machine learning model can predict abnormal situations that may occur in the operation of the landfill. The system can automatically identify potential environmental risks in the landfill and provide instant Decision support can be provided to effectively reduce the need for human intervention, improve the automation and intelligence level of the system, and further ensure environmental safety. Combined with the cloud platform and remote sensors, remote supervision and operation of the landfill can be realized, the situation on the site can be grasped in real time, and immediate action can be taken when an abnormality occurs, effectively reducing risks. By using digital twin technology for long-term performance evaluation, potential weaknesses and signs of aging of landfill anti-seepage facilities can be identified in advance, so that preventive maintenance measures can be taken before the problem worsens, the service life of the facilities can be extended, and long-term operating costs can be reduced. A remote supervision and risk assessment model can be built on the cloud platform, and statistical methods such as Bayesian inference can be used in combination with real-time data to dynamically evaluate the operating risks of the landfill, formulate more accurate management and maintenance strategies, minimize environmental risks, and ensure the safe and compliant operation of the landfill. The present invention has achieved better results in terms of the reliability and durability of landfill anti-seepage facilities, long-term operating costs, and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0052] Figure 1 An overall flow chart of a landfill vertical anti-seepage facility management method based on digital twins is provided for the first embodiment of the present invention.

[0053] Figure 2 A schematic diagram of a landfill vertical anti-seepage facility management method based on digital twins provided in the first embodiment of the present invention.

[0054] Figure 3 An overall flow chart of a landfill vertical anti-seepage facility management system based on digital twin is provided for the third embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0056] Example 1, reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides a landfill vertical anti-seepage facility management method based on digital twins, comprising:

[0057] S1: Construct a digital twin model of the landfill based on geological exploration data and perform parametric modeling of the vertical curtain anti-seepage layer.

[0058] Furthermore, first collect information related to the landfill site, such as design documents, monitoring plans, geological and hydrological conditions, and landfill records; use Revit to model the project in three dimensions, establish a geological and hydrological model based on the geological survey report, and add necessary attributes and parameters, such as stratum type, groundwater level, and drainage system; establish a geometric model of the garbage pile, including information such as the layout of the landfill, the type and composition of each part of the garbage, and the depth and time of the landfill; add climate and environmental information of the landfill site, such as temperature, humidity, wind speed, wind direction, and precipitation.

[0059] It should be noted that the pollutant diffusion model in the landfill is constructed by combining the diffusion-convection equation and the reaction term, which is expressed as:

[0060]

[0061] Where C represents the pollutant concentration, represents the concentration gradient, D represents the diffusion coefficient, represents the divergence operator, v represents the groundwater velocity vector, k ris the reaction rate constant, C max Indicates the maximum concentration of pollutants in the system.

[0062] It should also be noted that due to the large area of ​​the landfill site, the large amount of garbage pile, and the huge number of data and information files involved, the quality and accuracy of various information must be guaranteed; in the Revit modeling process, the properties and parameters of various models must be clarified to ensure the orderliness of the information; and an information update mechanism must be established to ensure that the model is synchronized with changes in the actual landfill.

[0063] S2: Synchronize real-time data with digital twin models.

[0064] Furthermore, the vertical curtain anti-seepage layer is parametrically modeled in the digital twin model, and the key design parameters of the anti-seepage layer are incorporated into the model, such as thickness, material type, permeability, etc.; the vertical curtain model is combined with the geological and garbage dump models, and numerical simulation methods such as finite element analysis and numerical permeability simulation are used to simulate the permeability under different anti-seepage layer design parameters, and the performance of each combination of anti-seepage layer design parameters is evaluated, including permeability, infiltration hydraulic head, etc. Multi-objective optimization is performed using optimization algorithms to determine the optimal anti-seepage layer design parameters.

[0065] It should be noted that the optimization algorithm is used for multi-objective optimization to determine the optimal design parameters of the anti-seepage layer, which is expressed as:

[0066]

[0067] Among them, K(x) represents the permeability coefficient, which varies with the design parameter x, C(x) represents the total cost, taking into account the material, construction and maintenance costs, and α represents the cost weight coefficient.

[0068] It should also be noted that the modeling of the vertical curtain anti-seepage layer should consider multi-scale issues, including local details and overall structure, involving multi-level and multi-resolution modeling methods to ensure that the model has sufficient details and can be simulated efficiently. When establishing the material of the anti-seepage layer, in addition to basic parameters such as thickness and density, the characteristics of the material, such as impermeability and chemical corrosion resistance, should also be considered.

[0069] Furthermore, when evaluating the performance of the design parameters of the anti-seepage layer, it is necessary to select appropriate evaluation indicators, such as permeability, infiltration hydraulic head, leachate flow rate, etc. These indicators should be able to fully reflect the anti-seepage performance of the anti-seepage layer. The objectives of multi-objective optimization include minimizing permeability, minimizing infiltration hydraulic head, minimizing leachate flow rate, etc. Select appropriate multi-objective optimization algorithms, such as genetic algorithms, particle swarm optimization, etc., to find the optimal combination of anti-seepage layer design parameters.

[0070] It should be noted that the characteristics and environmental impact of the landfill are studied to determine the key parameters that need to be monitored, such as groundwater level, soil moisture content, chemical composition of landfill materials, gas emissions, etc.; according to the nature of the monitoring parameters and the actual situation of the landfill, suitable sensors and monitoring equipment are selected, for example, gas detectors, water quality sensors, soil samplers, etc.; based on the twin model, considering factors such as the environment, topography, geology, distribution of landfill materials, size and layout of the landfill, the sensor network is arranged to ensure the reasonable distribution of monitoring points; a real-time data synchronization system is established to ensure that the real-time data collected by the sensor can be synchronized to the digital twin model in a timely manner, and the Internet of Things technology, cloud computing and other technical means are used to ensure the real-time and reliability of the data.

[0071] It should also be noted that according to the nature of the monitoring parameters and the actual situation of the landfill, sensors and monitoring equipment are selected, gas detectors, water quality sensors, and soil samplers are selected, and the sensor layout scheme is optimized by using information entropy and cost optimization. The sensor deployment and real-time monitoring model is constructed as follows:

[0072]

[0073] Where n represents the number of sensors, H(Z i ) represents information entropy, i represents sensor, Z i represents the observation data of sensor i, λ represents the weight coefficient, cost(X i ) represents the layout cost of sensor i, X i represents the layout position of sensor i;

[0074] Based on the sensor deployment and real-time monitoring model, the information gain and cost balance model under the optimal sensor layout scheme is constructed, which is expressed as:

[0075]

[0076] Among them, F max Under the optimal sensor layout scheme, it represents the maximum value of the total information gain brought by all sensor layouts minus the total cost. Indicates that sensor i is in the optimal position Observation data at .

[0077] Furthermore, in order to ensure the accuracy and reliability of the monitoring parameters during the monitoring process, it is necessary to develop a maintenance and calibration plan for the sensors and perform quality control on the sensors; determine the monitoring frequency and spatiotemporal resolution to adapt to changes in the landfill environment; consider the actual situation of the landfill, ensure the reasonable distribution of the sensor network, adopt an intelligent deployment strategy, and integrate the sensor network to ensure that the monitoring points cover the key areas of the landfill and ensure the comprehensiveness and representativeness of the data; select appropriate Internet of Things technologies and cloud computing platforms to ensure that the real-time data collected by the sensors can be quickly and reliably synchronized to the digital twin model.

[0078] S3: Process the monitoring data in combination with the machine learning algorithm model.

[0079] Furthermore, to ensure the quality and integrity of monitoring data, pre-processing is performed, such as removing outliers and normalizing. A long short-term memory network (LSTM) model is constructed to process time series data. The prepared time series data is input into the LSTM model for training. By learning from historical data, the LSTM model can learn the changing patterns of various monitoring parameters in the landfill and form an understanding of the behavior of the landfill. LSTM can predict monitoring data for a period of time in the future, help to warn potential problems in advance, and thus perform anomaly detection.

[0080] It should be noted that the LSTM model is constructed using a deep learning framework, such as TensorFlow or PyTorch. The trained LSTM model is used for anomaly detection, and the model can identify real-time monitoring results that are inconsistent with historical data, thereby discovering possible abnormal situations; the LSTM model is integrated into the digital twin decision support system, which provides a comprehensive digital twin view for landfill decision makers through real-time data, anomaly detection, performance simulation and other information to support real-time decision-making.

[0081] S4: Combine cloud platforms and remote sensors to achieve remote monitoring and operation of landfills.

[0082] Going further, we can select a suitable cloud platform and deploy it, integrate the real-time data of sensors into the cloud platform, combine it with machine learning for real-time simulation and analysis, identify possible problems and development trends based on the evaluation results, discover potential risks in advance, and provide more accurate and intelligent support for on-site management.

[0083] It should be noted that the digital twin technology is used to conduct long-term performance evaluation, analyze the changing trend of the landfill, and build a cloud platform remote supervision and risk assessment model:

[0084]

[0085] Where R represents the overall risk, Θ represents the parameter space, L(θ) represents the loss function. The larger the value of the loss function, the higher the risk under the parameter. D represents the observed data, p(θ|D) represents the posterior probability density function, and θ represents the uncertain parameters in the system model, including the physical properties of the landfill, the concentration of pollutants, and the groundwater flow rate. represents the estimated value of the parameter, represents the Fisher information matrix.

[0086] It should also be noted that the configuration of the cloud platform must meet the requirements of real-time data processing and storage to ensure the high availability and stability of the platform. The landfill model and predictive simulation algorithm prepared in advance are integrated into the platform, and appropriate communication protocols and data transmission methods are configured to ensure that the real-time data of the sensor can be efficiently and stably transmitted to the cloud platform; the results of simulation and analysis are presented in a visual way so that managers can intuitively understand the status of the landfill, which can include real-time dashboards, reports, charts and other visualization tools; a real-time alarm service is established, and when the algorithm model detects abnormal conditions or potential problems, it can promptly issue an alarm and notify relevant personnel so that timely action can be taken.

[0087] Example 2, an embodiment of the present invention, provides a landfill vertical anti-seepage facility management method based on digital twin. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0088] First, the experiment was conducted in a simulated environment of an actual landfill, divided into an experimental group and a control group. The experimental group applied the management method based on digital twins of the present invention, while the control group adopted the existing traditional anti-seepage facility management method.

[0089] The test team first built a digital twin model of the landfill based on geological exploration data and historical data of the landfill. The model contains multi-dimensional information such as geological conditions, groundwater flow rate, garbage accumulation depth and type. Based on this model, three-dimensional modeling was carried out using Revit software, and the vertical curtain anti-seepage layer was parametrically designed. The model includes key parameters such as material type, thickness, and permeability. In order to better simulate the actual performance of the anti-seepage layer, the model also integrates the diffusion-convection equation and reaction terms to predict the diffusion of pollutants in the future period.

[0090] The experimental group collected real-time environmental data such as groundwater level, soil moisture content, and gas emissions through a sensor network deployed at the landfill, and synchronized these data with the digital twin model in real time. The long short-term memory network (LSTM) algorithm was used to process the time series data, normalize the data, and remove outliers. Finally, a real-time landfill operation status report was generated, and an early warning of possible degradation of the impermeable layer performance was issued.

[0091] At the same time, the cloud platform integrates all sensor data and realizes remote monitoring and operation. Managers can remotely access the platform to monitor the landfill's anti-seepage facilities in real time and formulate corresponding maintenance plans based on system prompts.

[0092] The control group adopted the existing traditional management method. This method relies on the initial geological exploration and design to design and construct the landfill impermeable layer. In the control group, the design parameters of the impermeable layer, such as material type and thickness, were mainly based on experience and static calculations, and no parametric modeling and optimization were performed. Daily monitoring was only carried out through regular manual on-site inspections and sampling analysis. The monitoring data was updated less frequently, and there was no real-time synchronization and big data analysis function. The remote monitoring function of the cloud platform was not used in the control group, and all management and maintenance operations were performed manually.

[0093] The experiment lasted for 12 months, covering all seasons and different climatic conditions in landfill operations. During this period, all sensors continued to work, and data was collected and analyzed in real time through the cloud platform. During the experiment, key parameters such as the performance of the anti-seepage layer, the diffusion of pollutants, and the monitoring results of groundwater pollution in the experimental and control groups were recorded regularly. After the experiment, all data were sorted and summarized to analyze the performance differences of the two methods in the management of landfill anti-seepage facilities.

[0094] Table 1 Experimental data table

[0095] Test parameters Experimental group (digital twin) Control group (existing technology) Permeability coefficient (m / s) 1.5×10-10 3.2×10-10 Pollutant concentration (end of year) (mg / L) 0.05 0.12 Frequency of groundwater pollution detection (times / year) 365 12 Maintenance cost (10,000 yuan / year) 8 12 Number of failures of anti-seepage layer (times / year) 0 2

[0096] The permeability coefficient of the experimental group was significantly lower than that of the control group. Secondly, the pollutant concentration of the experimental group was only 0.05 mg / L at the end of the year, which was much lower than 0.12 mg / L of the control group. In terms of the frequency of groundwater pollution detection, the sensor network of the experimental group supports 365-day all-weather monitoring, while the control group only detects once a month manually. This high-frequency monitoring of the experimental group greatly improves the response speed to the spread of pollutants and ensures the real-time safety of the landfill environment. From the cost point of view, the maintenance cost of the experimental group is significantly lower than that of the control group. Although the experimental group has a large initial investment, the remote monitoring and predictive maintenance measures of the cloud platform have reduced unnecessary on-site inspections and emergency maintenance, reducing the overall operating costs. In addition, the control group experienced two anti-seepage layer failure events within a year, which not only increased maintenance costs, but also led to potential environmental risks. The experimental group achieved the goal of no failure throughout the year through early warning and real-time monitoring.

[0097] In summary, the present invention achieves better results in terms of reliability and durability, long-term operating costs and safety of landfill anti-seepage facilities.

[0098] Example 3, reference Figure 3 , which is an embodiment of the present invention, provides a landfill vertical anti-seepage facility management system based on digital twin, including a landfill digital twin model construction module, an optimization design module for the vertical curtain anti-seepage layer, a sensor and monitoring equipment deployment module, a monitoring data processing module, and a remote supervision and operation module.

[0099] The landfill digital twin model construction module is used to create a BIM model of the landfill site. The vertical curtain anti-seepage layer optimization design module is used to simulate and analyze the optimal anti-seepage layer thickness and material type design parameters. The sensor and monitoring equipment deployment module is used to synchronize real-time data with the digital twin model. The monitoring data processing module is used to process the monitoring data in combination with the machine learning algorithm model. The remote supervision and operation module is used to combine the cloud platform and remote sensors to achieve remote supervision and operation of the landfill.

[0100] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0102] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0103] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A landfill vertical anti-seepage facility management method based on digital twin, characterized in that: include: A digital twin model of the landfill was constructed based on geological exploration data, and parametric modeling of the vertical curtain anti-seepage layer was performed; Synchronize real-time data with digital twin models; Combine machine learning algorithm models to process monitoring data; Combining cloud platforms and remote sensors to achieve remote monitoring and operation of landfills.

2. The landfill vertical anti-seepage facility management method based on digital twin according to claim 1, characterized in that: The construction of the landfill digital twin model based on geological exploration data includes first collecting design documents, monitoring plans, geological and hydrological conditions, and landfill record information of the landfill site; Use Revit to model the project in 3D, build a geological and hydrological model based on the geological survey report, and add information on stratum type, groundwater level, and drainage system; Establish a geometric model of the garbage pile, including the layout of the landfill, the type and composition of each part of the garbage, the depth and time of the landfill; Add climate and environmental information of the landfill site, including temperature, humidity, wind speed, wind direction, and precipitation; Combining the diffusion-convection equation and the reaction term, a pollutant diffusion model in the landfill is constructed, which is expressed as: Where C represents the pollutant concentration, represents the concentration gradient, D represents the diffusion coefficient, represents the divergence operator, v represents the groundwater velocity vector, k r is the reaction rate constant, C max Indicates the maximum concentration value of pollutants in the system; The pollutant diffusion model is used to predict the concentration distribution of pollutants at future time points.

3. The landfill vertical anti-seepage facility management method based on digital twin according to claim 2, characterized in that: The parametric modeling of the vertical curtain anti-seepage layer includes parametric modeling of the vertical curtain anti-seepage layer in the digital twin model, and incorporating key design parameters of the anti-seepage layer into the model, including thickness, material type, and permeability; The vertical curtain model is combined with the geological and garbage dump models. Numerical simulation methods, including finite element analysis and numerical permeability simulation, are used to simulate the permeability of different anti-seepage layer design parameters. The performance of each combination of anti-seepage layer design parameters, including permeability, seepage fluid head, and leachate flow rate, is evaluated. Multi-objective optimization is performed using an optimization algorithm to determine the optimal anti-seepage layer design parameters, which are expressed as: Among them, K(x) represents the permeability coefficient, which varies with the design parameter x, C(x) represents the total cost, taking into account the material, construction and maintenance costs, and α represents the cost weight coefficient.

4. The landfill vertical anti-seepage facility management method based on digital twin according to claim 3, characterized in that: The synchronization of real-time data and digital twin models includes determining parameters that need to be monitored, including groundwater level, soil moisture content, chemical composition of landfill materials, and gas emissions; According to the nature of the monitoring parameters and the actual situation of the landfill, sensors and monitoring equipment are selected, including gas detectors, water quality sensors, and soil samplers. The sensor layout is optimized by using information entropy and cost optimization, and the sensor deployment and real-time monitoring model is constructed as follows: Where n represents the number of sensors, H(Z i ) represents information entropy, i represents sensor, Z i represents the observation data of sensor i, λ represents the weight coefficient, cost(X i ) represents the layout cost of sensor i, X i represents the layout position of sensor i; Based on the sensor deployment and real-time monitoring model, the information gain and cost balance model under the optimal sensor layout scheme is constructed, which is expressed as: Among them, F max Under the optimal sensor layout scheme, it represents the maximum value of the total information gain brought by all sensor layouts minus the total cost. Indicates that sensor i is in the optimal position Observational data at Based on the twin model, the sensor network is arranged to ensure the distribution of monitoring points, taking into account the environment, topography, geology, landfill material distribution, landfill size and layout factors; Establish a real-time data synchronization system to ensure that the real-time data collected by sensors is synchronized to the digital twin model in a timely manner.

5. The landfill vertical anti-seepage facility management method based on digital twin according to claim 4, characterized in that: The processing of the monitoring data in combination with the machine learning algorithm model includes processing the monitoring data in combination with the machine learning algorithm model, using the digital twin model to simulate the influence of different factors in the landfill on the performance of the anti-seepage layer, predicting performance changes, discovering potential problems in advance, and developing a real-time decision support system. Based on real-time data and simulation results, the system provides decision makers with real-time landfill operation status and supports decision makers in formulating immediate management and maintenance plans; Ensure the quality and integrity of monitoring data, perform pre-processing, remove outliers, and normalize; Construct a long short-term memory network model to process time series data. Input the prepared time series data into the long short-term memory network model for training. Through learning from historical data, the long short-term memory network model collects the changing patterns of various monitoring parameters in the landfill and forms an understanding of the landfill behavior. The long short-term memory network model predicts monitoring data in the future and performs anomaly detection; Integrating the long short-term memory network model into the digital twin decision support system provides a comprehensive digital twin view and supports real-time decision making.

6. The landfill vertical anti-seepage facility management method based on digital twin according to claim 5, characterized in that: The combining of a cloud platform and a remote sensor to realize remote supervision and operation of a landfill includes combining a cloud platform and a remote sensor to realize remote supervision and operation of a landfill; Use digital twin technology to conduct long-term performance evaluation, analyze the changing trends of landfills, and build a cloud platform remote supervision and risk assessment model: Where R represents the overall risk, Θ represents the parameter space, L(θ) represents the loss function. The larger the value of the loss function, the higher the risk under the parameter. D represents the observed data, p(θ|D) represents the posterior probability density function, and θ represents the uncertain parameters in the system model, including the physical properties of the landfill, the concentration of pollutants, and the groundwater flow rate. represents the estimated value of the parameter, represents the Fisher information matrix; Based on the assessment results, develop maintenance and upgrade strategies.

7. The landfill vertical anti-seepage facility management method based on digital twin according to claim 6, characterized in that: The combination of the cloud platform and remote sensors to achieve remote monitoring and operation of the landfill includes output of evaluation results in the cloud platform including real-time monitoring dashboards, alarm and notification systems, report generation, and forecast and trend analysis; The assessment results are categorized into: Normal operating status, performance degradation, anomaly detection, risk warning, and optimization suggestions; Normal operation status means that the evaluation results show that the system is operating within the expected range and no immediate action is required; Performance degradation indicates that a performance indicator has been identified to have degraded, requiring maintenance or adjustment of operating parameters; Anomaly detection means finding abnormal points in the data, indicating equipment failure or operational errors; Risk warning means that potential risks are predicted and measures need to be taken in advance to avoid problems; Optimization suggestions indicate that the analysis results indicate there is room for improvement and provide recommendations for optimizing operations or processes.

8. A system using the landfill vertical anti-seepage facility management method based on digital twins as claimed in any one of claims 1 to 7, characterized in that: It includes landfill digital twin model construction module, vertical curtain anti-seepage layer optimization design module, sensor and monitoring equipment deployment module, monitoring data processing module, and remote supervision and operation module; The landfill digital twin model building module is used to create a BIM model of the landfill site; The optimization design module of the vertical curtain anti-seepage layer is used to simulate and analyze to determine the optimal anti-seepage layer thickness and material type design parameters; The sensor and monitoring equipment deployment module is used to synchronize real-time data with the digital twin model; The monitoring data processing module is used to process the monitoring data in combination with a machine learning algorithm model; The remote monitoring and operation module is used to combine the cloud platform and the remote sensor to realize the remote monitoring and operation of the landfill.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it implements the steps of the landfill vertical anti-seepage facility management method based on digital twin as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the landfill vertical anti-seepage facility management method based on digital twins described in any one of claims 1 to 7 are implemented.

Images