Park carbon monitoring and energy efficiency optimization method and system based on digital twinning

Abstract

The invention discloses a park carbon monitoring and energy efficiency optimization method and system based on digital twinning, and relates to the technical field of carbon emission intelligent monitoring, and the method comprises the steps: monitoring a target park based on different types of monitoring equipment, and obtaining different types of monitoring data; preprocessing different types of monitoring data to obtain different types of preprocessed monitoring data, and fusing the preprocessed monitoring data to obtain a dynamic heterogeneous data set; based on the park architectural drawing of the target park, constructing an initial park digital twinborn model; based on the initial park digital twinborn model and the dynamic heterogeneous data set, constructing a dynamic park digital twinborn model; and based on the dynamic park digital twinborn model, predicting the carbon emission trend of the target park to obtain carbon emission trend prediction information. According to the application, through multi-source data acquisition, real-time analysis and emission early warning, real-time monitoring of the carbon emission condition of the park is realized, and a theoretical basis is provided for later energy optimization.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent carbon emission monitoring, and specifically to a method and system for carbon monitoring and energy efficiency optimization of a park based on digital twins. Background Art

[0002] In recent years, with the rapid development of the Internet of Things, big data, and artificial intelligence (AI), digital twin technology has gradually become a core tool for industrial intelligence. By constructing high-fidelity virtual models of physical entities, it enables data-driven real-time simulation and decision-making optimization. In the field of carbon management, traditional approaches rely on static statistical models and isolated sensor networks, making them difficult to address the challenges of integrating multi-source heterogeneous data, accurately predicting carbon emissions in complex scenarios, and dynamically regulating them. While deep learning models (such as LSTM and Transformer) have shown potential in time series forecasting, they still face limitations in real-time performance, computational efficiency, and multi-objective collaborative optimization. Furthermore, existing systems generally suffer from low data quality (noise and missing values), weak cross-modal correlations, and poor interpretability of prediction results, hindering the intelligent upgrade of industrial park carbon management. Against this backdrop, digital twin systems, integrating edge computing, improved multi-task real-time prediction models, and adaptive optimization algorithms, have become a key path to overcoming technical bottlenecks and achieving closed-loop control of carbon emissions throughout the entire process.

[0003] In order to meet actual needs, a park carbon monitoring and energy efficiency optimization technology based on digital twins is proposed. Summary of the Invention

[0004] In response to the defects in the existing technology, the purpose of this application is to provide a park carbon monitoring and energy efficiency optimization method and system based on digital twins. Through multi-source data collection, real-time analysis and emission early warning, real-time monitoring of the park's carbon emissions can be achieved, providing a theoretical basis for subsequent energy optimization.

[0005] In order to achieve the above objectives, the technical solution adopted by this application is: In a first aspect, the present application provides a method for carbon monitoring and energy efficiency optimization of a park based on digital twins, the method comprising the following steps: Monitor the target park using different types of monitoring equipment to obtain different types of monitoring data; Preprocessing different types of monitoring data to obtain different types of preprocessed monitoring data, and fusing them to obtain a dynamic heterogeneous data group; Build an initial digital twin model of the target park based on the park building drawings; Constructing a dynamic park digital twin model based on the initial park digital twin model and the dynamic heterogeneous data group; Based on the dynamic park digital twin model, the carbon emission trend of the target park is predicted to obtain carbon emission trend prediction information.

[0006] On the basis of the above technical solution, the method further comprises the following steps: Based on the carbon emission trend forecast information and the set carbon emission threshold, a carbon emission warning is performed.

[0007] On the basis of the above technical solution, the method further comprises the following steps: Based on the dynamic park digital twin model, the corresponding carbon emission heat map and energy flow path are obtained, and energy efficiency optimization suggestions are issued.

[0008] Based on the above technical solution, the method of monitoring the target park based on different types of monitoring equipment and obtaining different types of monitoring data includes the following steps: Based on smart meters, the target park is monitored to obtain the corresponding energy consumption; Based on gas sensors, the target park is monitored to obtain the corresponding carbon emissions; Based on the environmental monitoring instrument, the target park is monitored, and the corresponding park humidity and park temperature are obtained.

[0009] On the basis of the above technical solution, the different types of monitoring data are preprocessed to obtain different types of preprocessed monitoring data, and then fused to obtain a dynamic heterogeneous data group, including the following steps: Performing noise filtering, outlier correction, and normalization processing on the energy consumption, the carbon emissions, the park humidity, and the park temperature to obtain corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity, and pre-processed park temperature; Based on the energy consumption after pre-processing, the carbon emission after pre-processing, the humidity of the park after pre-processing, and the temperature of the park after pre-processing, a dynamic heterogeneous data set of book search is obtained by fusion.

[0010] In a second aspect, the present application provides a digital twin-based park carbon monitoring and energy efficiency optimization system, the system comprising: A data acquisition module, which is used to control different types of monitoring equipment to monitor the target park and obtain different types of monitoring data; A data processing module, which is used to preprocess different types of monitoring data to obtain different types of preprocessed monitoring data, and fuse them to obtain a dynamic heterogeneous data group; A model building module, which is used to build an initial park digital twin model based on the park building drawings of the target park; The model construction module is further used to construct a dynamic park digital twin model based on the initial park digital twin model and the dynamic heterogeneous data group; A trend prediction module is used to predict the carbon emission trend of the target park based on the dynamic park digital twin model to obtain carbon emission trend prediction information.

[0011] On the basis of the above technical solution, the system further includes: The emission warning module is used to provide carbon emission warning based on the carbon emission trend prediction information and the set carbon emission threshold.

[0012] On the basis of the above technical solution, the system further includes: The emission analysis module is used to obtain the corresponding carbon emission heat map and energy flow path based on the dynamic park digital twin model, and to issue energy efficiency optimization suggestions.

[0013] On the basis of the above technical solution, the data acquisition module is also used to monitor the target park based on the smart meter to obtain the corresponding energy consumption; The data acquisition module is also used to monitor the target park based on the gas sensor to obtain the corresponding carbon emissions; The data acquisition module is also used to monitor the target park based on the environmental monitoring instrument, and then obtain the corresponding park humidity and park temperature.

[0014] On the basis of the above technical solution, the data processing module is further used to perform noise filtering, outlier correction and normalization processing on the energy consumption, carbon emissions, park humidity and park temperature to obtain the corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity and pre-processed park temperature; The data processing module is further configured to obtain a dynamic heterogeneous data set for book searching based on the energy consumption after preprocessing, the carbon emissions after preprocessing, the humidity of the park after preprocessing, and the temperature of the park after preprocessing.

[0015] Compared with the prior art, the advantages of this application are: This application realizes real-time monitoring of the park's carbon emissions through multi-source data collection, real-time analysis and emission early warning, providing a theoretical basis for subsequent energy optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a flowchart of the steps of the digital twin-based park carbon monitoring and energy efficiency optimization method according to an embodiment of the present application; Figure 2 This is a structural block diagram of the digital twin-based campus carbon monitoring and energy efficiency optimization system in an embodiment of the present application. DETAILED DESCRIPTION

[0018] Explanation of terms: LSTM: Long Short-Term Memory, long short-term memory network; IQR: Interquartile Range, interquartile range; BIM: Building Information Modeling; CIM: City Information Modeling; IoT: Internet of Things; GRU: Gated Recurrent Unit, recurrent neural network; ERP: Enterprise Resource Planning; MES: Manufacturing Execution System.

[0019] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] The embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0021] The embodiments of the present application provide a digital twin-based park carbon monitoring and energy efficiency optimization method and system, which realizes real-time monitoring of the park's carbon emissions through multi-source data collection, real-time analysis and emission warning, and provides a theoretical basis for subsequent energy optimization.

[0022] To achieve the above technical effects, the overall idea of ​​this application is as follows: A digital twin-based park carbon monitoring and energy efficiency optimization method includes the following steps: S1. Monitor the target park using different types of monitoring equipment to obtain different types of monitoring data; S2. Preprocess different types of monitoring data to obtain different types of preprocessed monitoring data, and fuse them to obtain a dynamic heterogeneous data group; S3. Build an initial digital twin model of the target park based on the park building drawings; S4. Based on the initial park digital twin model and the dynamic heterogeneous data set, a dynamic park digital twin model is constructed; S5. Based on the dynamic park digital twin model, predict the carbon emission trend of the target park and obtain carbon emission trend prediction information.

[0023] The embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0024] First, see Figure 1 As shown, the embodiment of the present application provides a method for carbon monitoring and energy efficiency optimization of a park based on digital twins, which includes the following steps: S1. Monitor the target park using different types of monitoring equipment to obtain different types of monitoring data; S2. Preprocess different types of monitoring data to obtain different types of preprocessed monitoring data, and fuse them to obtain a dynamic heterogeneous data group; S3. Build an initial digital twin model of the target park based on the park building drawings; S4. Based on the initial park digital twin model and the dynamic heterogeneous data set, a dynamic park digital twin model is constructed; S5. Based on the dynamic park digital twin model, predict the carbon emission trend of the target park and obtain carbon emission trend prediction information.

[0025] In the embodiment of the present application, through multi-source data collection, real-time analysis and emission warning, real-time monitoring of the park's carbon emissions is achieved, providing a theoretical basis for subsequent energy optimization.

[0026] Furthermore, the method further comprises the following steps: Based on the carbon emission trend forecast information and the set carbon emission threshold, a carbon emission warning is performed.

[0027] Furthermore, the method further comprises the following steps: Based on the dynamic park digital twin model, the corresponding carbon emission heat map and energy flow path are obtained, and energy efficiency optimization suggestions are issued.

[0028] Furthermore, the method of monitoring the target park based on different types of monitoring equipment and obtaining different types of monitoring data includes the following steps: Based on smart meters, the target park is monitored to obtain the corresponding energy consumption; Based on gas sensors, the target park is monitored to obtain the corresponding carbon emissions; Based on the environmental monitoring instrument, the target park is monitored, and the corresponding park humidity and park temperature are obtained.

[0029] Furthermore, the preprocessing of different types of monitoring data to obtain different types of preprocessed monitoring data and fusing them to obtain a dynamic heterogeneous data group includes the following steps: Performing noise filtering, outlier correction, and normalization processing on the energy consumption, the carbon emissions, the park humidity, and the park temperature to obtain corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity, and pre-processed park temperature; Based on the energy consumption after pre-processing, the carbon emission after pre-processing, the humidity of the park after pre-processing, and the temperature of the park after pre-processing, a dynamic heterogeneous data set of book search is obtained by fusion.

[0030] The technical solution of the embodiment of the present application, when implemented, mainly operates as follows: First, multi-source data collection and preprocessing: IoT devices (such as smart meters, gas sensors, and environmental monitors) are deployed at key nodes in the park to collect data such as energy consumption, carbon emissions, temperature and humidity in real time. The data is normalized, noise filtered, and outlier corrected to ensure data quality.

[0031] Dynamic heterogeneous data fusion: Cross-modal embedding coding maps data of different modalities (numerical, categorical, textual, etc.) into a unified vector space to facilitate model processing and fusion, and aligns data of different sampling frequencies through time alignment interpolation.

[0032] Real-time data cleaning at the edge: Anomaly detection is performed on edge devices to identify sensor failures or data anomalies in real time. Preliminary filtering with thresholds and IQR detection are then performed to remove noise. Quartiles (Q1 and Q3) and IQR are calculated: Q1 is the median of the first half of the data, and Q3 is the median of the second half. The lower bound is: Q1 - 1.5 × IQR, and the upper bound is: Q3 + 1.5 × IQR. Interpolation and repair are then performed: outliers are replaced with the median or window mean (such as the mean of the first three values).

[0033] Second, digital twin model construction: By using park architectural drawings and 3D modeling technology, a digital twin model of energy facilities, production equipment, green areas, and other elements is constructed. This integrates real-time and historical data to achieve dynamic mapping between physical space and virtual models. 3D modeling and data integration: Based on campus architectural drawings, BIM or CIM, and high-precision remote sensing data, a 3D model is constructed that includes buildings, roads, green spaces, and energy facilities (such as photovoltaic panels, energy storage stations, and charging stations). Real-time data from Internet of Things (IoT) devices (electricity meters, gas meters, temperature and humidity sensors) and production system data are integrated to achieve dynamic mapping between physical space and virtual models. A carbon flow tracking module is also introduced to correlate energy consumption with carbon emission factors.

[0034] Carbon emission heat map and energy efficiency analysis: Based on real-time collected energy consumption data (electricity, gas) and emission factor database, the cubic spline interpolation formula algorithm is used for interpolation, as follows: For the interval [t i , t i+1 The cubic polynomial expression of ] is: ; The coefficients are determined by the following formula: ; (interval length); is a node The second-order derivative at can be obtained by solving the three-moment equations.

[0035] Three bending moment equations: 。

[0036] Generate a heat map that supports playback by time dimension to trace carbon emissions; set graded warning thresholds to automatically trigger alarms in areas where the threshold is exceeded; identify inefficient equipment by comparing historical data with industry benchmarks and mark them as optimization priorities; combined with a digital twin model, the impact of different energy-saving strategies on the heat map can be simulated to more accurately predict the trends of different energy-saving strategies.

[0037] Third, carbon emission analysis and forecast: An improved LSTM-Transformer hybrid model is used to combine time series data with external environmental parameters (such as weather and production plans) to predict carbon emission trends over the next 24 hours. At the same time, an attention mechanism is introduced to enhance the model's ability to capture key features and improve prediction accuracy: Improved LSTM-Transformer hybrid model: The traditional LSTM-Transformer hybrid model integrates information inefficiently, considers all relevant time periods during calculation, and lacks a robust forgetting mechanism that dynamically adjusts to external parameters. The main improvements are as follows: (1) Bidirectional GRU is used to replace the traditional LSTM, considering both forward and reverse time series, enhancing the capture of previous and next information. GRU is simpler in structure than LSTM, with only two gates: reset gate and update gate, making calculation faster and simpler. Bidirectional means considering both forward and reverse sequences at the same time. Normal prediction is made through the forward sequence. If carbon emissions suddenly surge on a certain day, but there is no obvious precursor in historical data, the possible cause is found through the reverse sequence, and potential risks similar to external parameters are identified in advance, so that the model can predict the risk of carbon emissions surge through the cause during forward processing.

[0038] (2) Introducing an adaptive forget gate to dynamically integrate external environmental parameters (such as temperature and production plans), optimizing the sparse self-attention mechanism of the Transformer, and only calculating the key-value pairs with high Top-K similarity to reduce computational complexity. LSTM extrapolates trends through recent data, but cannot predict some situations where real-time regulation or sudden changes in external parameters occur; Transformer analyzes historical data from the same period to correct regular predictions. Specifically, when external conditions are stable, more emphasis is placed on predicting carbon emissions based on basic parameters such as temperature and humidity (i.e., LSTM); when an external parameter suddenly changes significantly, the Transformer's reliance is increased. For example, when the temperature suddenly surges, the carbon emissions of the historical high-temperature period are considered, and the reference carbon emission values ​​of the period with low correlation and parameters such as temperature are forgotten (i.e., adaptive forgetting and only considering the key-value pairs with high Top-K similarity). The reliance of the two is dynamically integrated to calculate the final predicted carbon emissions.

[0039] y ^ t = αt •LSTM( Xt )+(1- αt )•Transformer( X history).

[0040] Fourth, dynamic optimization and early warning: Set a carbon emission threshold. When the predicted value approaches the threshold, the system automatically triggers an early warning and generates an emission reduction plan through multi-objective optimization algorithms such as NSGA-II. Combined with the simulation function of the digital twin model, the feasibility of the optimization plan is verified: (1) Multi-objective optimization engine: Based on the improved NSGA-II algorithm, the Pareto optimal solution for carbon emissions, energy costs, and production efficiency is sought while also imposing constraints such as the amount of production tasks completed and the maximum equipment load. ① The traditional NSGA-II algorithm has a fixed reference point. When the optimization objective is complex or the constraints are variable, the algorithm may become trapped in a local optimum or converge slowly. For example, if the goal is to minimize carbon emissions and energy costs, and the current solution is generally too costly, the reference point will shift to a "low-emissions, low-cost" region to guide subsequent searches. ② Adaptive constraint handling: Traditional methods simply discard infeasible solutions, potentially missing high-quality solutions. The degree to which each solution violates a constraint (such as the amount of uncompleted production tasks or equipment overload) is calculated. Solutions with minor constraint violations are retained and gradually corrected, while solutions with severe violations are eliminated. ③ Traditional NSGA-II lacks the ability to refine local searches, potentially missing even more optimal solutions nearby. NSGA-II uses non-dominated sorting and genetic operations (crossover and mutation) to quickly identify dominant regions (e.g., solutions with 12% carbon emissions and 8% cost). It then applies small perturbations to the elite solutions in the decision variable space (e.g., ±0.5% parameter adjustments) and calculates the number of neighbors around each solution. More neighbors indicates higher density (dense regions); fewer neighbors indicates lower density (sparse regions). Small perturbations are applied in dense regions and smaller perturbations in sparse regions.

[0041] (2) Graded early warning mechanism: The warning threshold is updated in real time based on various factors such as weather and production plans, and the threshold is dynamically adjusted. Optimization suggestions, restrictions on high-energy-consuming equipment, and activation of emergency plans are promptly pushed according to different warning levels.

[0042] Fifth, visualization and decision support platform: Build a unified management platform to display carbon emission heat maps, energy flow paths, optimization suggestions, etc. in real time, provide a "carbon footprint traceability" function, support historical data query by time, region, and device dimensions, integrate report generation and multi-scenario simulation functions, and assist managers in formulating long-term carbon reduction strategies: (1) 3D visual cockpit: Dynamically display the carbon emission heat map and energy flow path in the digital twin model to optimize low-carbon management decisions; support clicking on the equipment model to view the carbon footprint of the entire life cycle (production, transportation, operation, and scrapping).

[0043] (2) System integration and low-carbon decision-making platform: Integrate modules such as carbon emission monitoring, energy scheduling optimization, equipment management, and environmental perception to build a unified management platform. It can adopt a microservice architecture, support seamless connection with the park's existing systems (such as ERP, MES), and obtain production plans and equipment status in real time; generate daily / monthly carbon emission reports, and support historical data queries by region, equipment, and time dimensions.

[0044] Second, see Figure 2 As shown, the embodiment of the present application provides a campus carbon monitoring and energy efficiency optimization system based on digital twins, which includes: A data acquisition module, which is used to control different types of monitoring equipment to monitor the target park and obtain different types of monitoring data; A data processing module, which is used to preprocess different types of monitoring data to obtain different types of preprocessed monitoring data, and fuse them to obtain a dynamic heterogeneous data group; A model building module, which is used to build an initial park digital twin model based on the park building drawings of the target park; The model construction module is further used to construct a dynamic park digital twin model based on the initial park digital twin model and the dynamic heterogeneous data group; A trend prediction module is used to predict the carbon emission trend of the target park based on the dynamic park digital twin model to obtain carbon emission trend prediction information.

[0045] In the embodiment of the present application, through multi-source data collection, real-time analysis and emission warning, real-time monitoring of the park's carbon emissions is achieved, providing a theoretical basis for subsequent energy optimization.

[0046] Furthermore, the system further comprises: The emission warning module is used to provide carbon emission warning based on the carbon emission trend prediction information and the set carbon emission threshold.

[0047] Furthermore, the system further comprises: The emission analysis module is used to obtain the corresponding carbon emission heat map and energy flow path based on the dynamic park digital twin model, and to issue energy efficiency optimization suggestions.

[0048] Furthermore, the data acquisition module is also used to monitor the target park based on the smart meter to obtain the corresponding energy consumption; The data acquisition module is also used to monitor the target park based on the gas sensor to obtain the corresponding carbon emissions; The data acquisition module is also used to monitor the target park based on the environmental monitoring instrument, and then obtain the corresponding park humidity and park temperature.

[0049] Furthermore, the data processing module is further used to perform noise filtering, outlier correction, and normalization on the energy consumption, carbon emissions, park humidity, and park temperature to obtain corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity, and pre-processed park temperature; The data processing module is further configured to obtain a dynamic heterogeneous data set for book searching based on the energy consumption after preprocessing, the carbon emissions after preprocessing, the humidity of the park after preprocessing, and the temperature of the park after preprocessing.

[0050] To sum up, the digital twin-based campus carbon monitoring and energy efficiency optimization system provided in the embodiment of the present application has the same technical principles as the digital twin-based campus carbon monitoring and energy efficiency optimization method provided in the first aspect in terms of technical issues, technical solutions and technical effects, so they will not be elaborated here.

[0051] In the description of this application, it should be noted that the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be internal communication between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0052] It should be noted that, in this application, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0053] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A digital twin-based park carbon monitoring and energy efficiency optimization method, characterized by: The method comprises the following steps: Monitor the target park using different types of monitoring equipment to obtain different types of monitoring data; Preprocessing different types of monitoring data to obtain different types of preprocessed monitoring data, and fusing them to obtain a dynamic heterogeneous data group; Build an initial digital twin model of the target park based on the park building drawings; Constructing a dynamic park digital twin model based on the initial park digital twin model and the dynamic heterogeneous data group; Based on the dynamic park digital twin model, the carbon emission trend of the target park is predicted to obtain carbon emission trend prediction information.

2. The digital twin-based park carbon monitoring and energy efficiency optimization method according to claim 1 is characterized in that: The method further comprises the following steps: Based on the carbon emission trend forecast information and the set carbon emission threshold, a carbon emission warning is performed.

3. The digital twin-based park carbon monitoring and energy efficiency optimization method according to claim 1 is characterized in that: The method further comprises the following steps: Based on the dynamic park digital twin model, the corresponding carbon emission heat map and energy flow path are obtained, and energy efficiency optimization suggestions are issued.

4. The digital twin-based park carbon monitoring and energy efficiency optimization method according to claim 1 is characterized in that: The method of monitoring the target park based on different types of monitoring equipment and obtaining different types of monitoring data includes the following steps: Based on smart meters, the target park is monitored to obtain the corresponding energy consumption; Based on gas sensors, the target park is monitored to obtain the corresponding carbon emissions; Based on the environmental monitoring instrument, the target park is monitored, and the corresponding park humidity and park temperature are obtained.

5. The digital twin-based park carbon monitoring and energy efficiency optimization method according to claim 4 is characterized in that: The preprocessing of different types of monitoring data to obtain different types of preprocessed monitoring data and fusing them to obtain a dynamic heterogeneous data group includes the following steps: Performing noise filtering, outlier correction, and normalization processing on the energy consumption, the carbon emissions, the park humidity, and the park temperature to obtain corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity, and pre-processed park temperature; Based on the energy consumption after pre-processing, the carbon emission after pre-processing, the humidity of the park after pre-processing, and the temperature of the park after pre-processing, a dynamic heterogeneous data set of book search is obtained by fusion.

6. A digital twin-based park carbon monitoring and energy efficiency optimization system, characterized by: The system comprises: A data acquisition module, which is used to control different types of monitoring equipment to monitor the target park and obtain different types of monitoring data; A data processing module, which is used to preprocess different types of monitoring data to obtain different types of preprocessed monitoring data, and fuse them to obtain a dynamic heterogeneous data group; A model building module, which is used to build an initial park digital twin model based on the park building drawings of the target park; The model construction module is further used to construct a dynamic park digital twin model based on the initial park digital twin model and the dynamic heterogeneous data group; A trend prediction module is used to predict the carbon emission trend of the target park based on the dynamic park digital twin model to obtain carbon emission trend prediction information.

7. The digital twin-based park carbon monitoring and energy efficiency optimization system according to claim 6 is characterized in that: The system further comprises: The emission warning module is used to provide carbon emission warning based on the carbon emission trend prediction information and the set carbon emission threshold.

8. The digital twin-based park carbon monitoring and energy efficiency optimization system according to claim 6 is characterized in that: The system further comprises: The emission analysis module is used to obtain the corresponding carbon emission heat map and energy flow path based on the dynamic park digital twin model, and to issue energy efficiency optimization suggestions.

9. The digital twin-based park carbon monitoring and energy efficiency optimization system according to claim 6, characterized in that: The data acquisition module is also used to monitor the target park based on the smart meter to obtain the corresponding energy consumption; The data acquisition module is also used to monitor the target park based on the gas sensor to obtain the corresponding carbon emissions; The data acquisition module is also used to monitor the target park based on the environmental monitoring instrument, and then obtain the corresponding park humidity and park temperature.

10. The digital twin-based park carbon monitoring and energy efficiency optimization system according to claim 9, characterized in that: The data processing module is further configured to perform noise filtering, outlier correction, and normalization on the energy consumption, carbon emissions, park humidity, and park temperature to obtain corresponding pre-processed energy consumption, pre-processed carbon emissions, pre-processed park humidity, and pre-processed park temperature; The data processing module is further configured to obtain a dynamic heterogeneous data set for book searching based on the energy consumption after preprocessing, the carbon emissions after preprocessing, the humidity of the park after preprocessing, and the temperature of the park after preprocessing.

Images