A method for calculating electrical appliance energy consumption based on digital twin model

Abstract

The present invention relates to the technical field of electrical appliance energy consumption, and in particular to a method for calculating electrical appliance energy consumption based on a digital twin model. The method comprises the following steps: obtaining electrical data, thermodynamic data and mechanical data; performing data preprocessing on the electrical data, thermodynamic data and mechanical data to generate electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values; mapping the electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values ​​to three-dimensional space to generate three-dimensional point clouds, and generating electrical appliance characteristic point cloud data; performing morphological surface analysis on the electrical appliance characteristic point cloud data to generate electrical appliance surface analysis data; establishing a digital twin model based on the electrical appliance surface analysis data to generate an electrical appliance digital twin model; the present invention ensures the accuracy and efficiency of energy consumption optimization calculations through standardization of data, precise construction of models and comprehensive evaluation in multiple dimensions.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical appliance energy consumption, and in particular to a method for calculating electrical appliance energy consumption based on a digital twin model. Background Art

[0002] With the rapid development of smart grid, Internet of Things and intelligent manufacturing technology, energy consumption management and optimization of electrical equipment has become a key link to improve energy utilization efficiency, reduce energy consumption and achieve sustainable development. At present, the traditional energy consumption calculation method of electrical equipment usually relies on real-time data and preset static models in the operation of the equipment, and calculates energy consumption by measuring current, voltage and temperature parameters and combining the power characteristics of the equipment. However, the traditional energy consumption calculation method is usually based on a single static model, which is difficult to fully reflect the dynamic behavior of electrical appliances in a complex and changeable operating environment. With the increase of usage time, various performance indicators of electrical appliances such as efficiency and power factor will change, resulting in a gradual deviation between actual energy consumption and theoretical calculation. Electrical equipment accumulates a large amount of operating data during its life cycle, which contains the laws and trends of equipment performance changes. The limitations of traditional methods in data utilization have prevented these valuable historical data from being fully utilized, resulting in insufficient effectiveness of energy consumption prediction and optimization. Finally, the existing calculation methods are often complex and difficult to quickly calculate the energy consumption of electrical appliances. Summary of the invention

[0003] Based on this, it is necessary to provide an electrical appliance energy consumption calculation method based on a digital twin model to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for calculating electrical appliance energy consumption based on a digital twin model is provided, the method comprising the following steps:

[0005] Step S1: Acquire electrical data, thermodynamic data and mechanical data; perform data preprocessing on the electrical data, thermodynamic data and mechanical data to generate electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values;

[0006] Step S2: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to three-dimensional space to generate three-dimensional point cloud, thereby generating electrical appliance characteristic point cloud data; performing morphological surface analysis on the electrical appliance characteristic point cloud data to generate electrical appliance surface analysis data; establishing a digital twin model based on the electrical appliance surface analysis data to generate an electrical appliance digital twin model;

[0007] Step S3: Use the electrical appliance digital twin model to trace the power energy source of the real-time operation data to generate the power energy traceability result; perform electrical appliance energy consumption calculation on the power energy traceability result to generate an electrical appliance energy consumption data set; perform dual calculation of time component loss simulation on the electrical appliance energy consumption data set to generate the electrical appliance energy consumption calculation result;

[0008] Step S4: extract the energy consumption trajectory path of the electrical appliance energy consumption calculation result to generate the energy consumption trajectory path; extract the abnormal and smooth section data of the energy consumption trajectory path to generate the section with abnormal energy consumption fluctuation and the section with smooth energy consumption fluctuation; perform section energy consumption selection and integration processing on the section with abnormal energy consumption fluctuation to generate the energy consumption simulation data with abnormal fluctuation of electrical appliances; perform energy consumption smooth screening based on the section with smooth energy consumption fluctuation to generate the optimal energy consumption selection section data; perform smooth section energy consumption section simulation on the optimal energy consumption selection section data, and perform energy consumption aggregation with the energy consumption simulation data with abnormal fluctuation of electrical appliances to generate the energy consumption simulation data of electrical appliances, thereby completing the energy consumption optimization calculation of electrical appliances.

[0009] The beneficial effect of the present invention is that by acquiring and preprocessing electrical data, thermodynamic data and mechanical data, electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values ​​are generated. This process not only extracts the key characteristics of various types of data, but also lays a solid data foundation for subsequent steps. These characteristic engineering values ​​are mapped to three-dimensional space to generate three-dimensional point cloud data, and through morphological surface analysis, the complex relationship and change law of electrical characteristics in the spatial dimension are further extracted. This not only improves the expressiveness of the data, but also enables the digital twin model to more accurately reflect the operating status of the actual system. By using the generated digital twin model, the real-time operation data of the electrical appliance is traced to the source of electric energy, and the dual calculation of electrical appliance energy consumption calculation and time component loss simulation is completed accordingly. This process enables the energy consumption data set to be fully simulated and analyzed in the time dimension, providing a reliable basis for the long-term energy consumption trend prediction of electrical appliances. Subsequently, the accuracy and optimization of energy consumption calculation were further deepened. By extracting and analyzing the energy consumption trajectory path, the sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations were identified, and then the section energy consumption was selected and integrated and the smooth section energy consumption was simulated. The final electrical energy consumption simulation data was generated through the energy consumption set. This series of operations ensures the accuracy and efficiency of energy consumption optimization calculation by separating and processing abnormal and smooth sections.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: acquiring electrical data, thermodynamic data and mechanical data through sensors, wherein the electrical data includes power factor and electric energy, the thermodynamic data includes thermal expansion coefficient and cooling efficiency, and the mechanical data includes mechanical efficiency and electrical amplitude rate;

[0012] Step S12: performing random noise reduction processing on the power factor and electric energy, the thermal expansion coefficient and the cooling efficiency, the mechanical efficiency and the electrical amplitude rate to generate electric energy characteristic noise reduction data, thermal energy characteristic noise reduction data and thermal energy characteristic noise reduction data; performing data standardization processing on the electric energy characteristic noise reduction data, the thermal energy characteristic noise reduction data and the thermal energy characteristic noise reduction data to generate electric energy standardized data, thermal energy standardized data and mechanical standardized data;

[0013] Step S13: Perform abnormal value identification processing on the electric energy standardized data to generate electric energy characteristic engineering values; perform temperature medium change analysis on the thermal energy standardized data to generate thermal energy characteristic engineering values; perform mechanical structure stress analysis on the mechanical standardized data to generate mechanical characteristic engineering values.

[0014] The electrical data, thermodynamic data and mechanical data acquired by the present invention through sensors cover the key parameters of power factor, electric energy, thermal expansion coefficient, cooling efficiency, mechanical efficiency and electrical amplitude rate in multiple dimensions. The comprehensiveness of these data ensures that the state and behavior of the system in different physical fields can be fully characterized, and provides a wide range of data input sources. The introduction of random noise reduction processing effectively reduces the noise components in the data and generates more reliable electric energy feature noise reduction data, thermal energy feature noise reduction data and mechanical feature noise reduction data. Noise reduction processing not only improves the cleanliness of the data, but also enhances the availability of the data and reduces the model deviation caused by noise interference. Next, data standardization processing further eliminates the differences between different data dimensions, and generates standardized data of electric energy, thermal energy and machinery by scaling the data to the same scale. This operation not only simplifies the computational complexity in subsequent analysis, but also ensures the reasonable comparison and integration of different types of data within the same analysis framework. By detecting and processing outliers on the electric energy standardized data, representative electric energy feature engineering values ​​are generated. This process can effectively identify and eliminate extreme values ​​or abnormal situations in the data, ensuring the accuracy and stability of feature engineering results. The temperature medium change analysis of the thermal energy standardized data generates the thermal energy characteristic engineering value that reflects the thermal behavior of the system by deeply analyzing the dynamic changes of the thermal energy characteristics, laying the foundation for the subsequent thermodynamic modeling. Finally, by performing mechanical structure stress analysis on the mechanical standardized data, the characteristics of the mechanical system under different stress conditions are extracted to generate the mechanical characteristic engineering value. This characteristic value can reflect the health status and potential risks of the mechanical structure in operation, greatly improving the analysis depth and practical application value of the mechanical data.

[0015] Preferably, step S2 comprises the following steps:

[0016] Step S21: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to a three-dimensional space according to a preset mapping rule to generate three-dimensional space characteristic data; generating a three-dimensional point cloud according to the three-dimensional space characteristic data to generate electrical mechanical characteristic point cloud data and electrical power thermal energy characteristic point cloud data;

[0017] Step S22: performing surface fitting representative analysis on the electrical appliance power and thermal energy characteristic point cloud data to generate electrical appliance power and thermal energy surface analysis data;

[0018] Step S23: Establish a digital twin model of the electrical appliance mechanical characteristic point cloud data, and assign geometric attributes to the electrical appliance power and thermal energy surface analysis data to generate a digital twin model of the electrical appliance.

[0019] The present invention generates three-dimensional spatial characteristic data by mapping the electrical energy characteristic engineering value, thermal energy characteristic engineering value and mechanical characteristic engineering value to three-dimensional space according to a preset mapping rule. This mapping process converts multidimensional characteristic data into spatial characteristics, so that data of different physical properties can be visualized and analyzed in a unified three-dimensional coordinate system, effectively improving the correlation and comparability between data. Through the three-dimensional point cloud generation step, not only the accurate expression of electrical mechanical characteristics and electrical electrical power and thermal energy characteristics in three-dimensional space is realized, but also the foundation for subsequent geometric analysis and model construction is laid. By performing surface fitting representative analysis on the electrical power and thermal energy characteristic point cloud data, electrical power and thermal energy surface analysis data is generated. The key to this step is to use point cloud data to perform surface fitting on power and thermal energy characteristics, and extract the main characteristic parameters of the system in terms of power and thermal energy by analyzing the geometric morphology and distribution characteristics of the surface. This analysis method based on surface fitting can not only capture the global trend of data, but also identify local subtle changes, and enhance the depth of understanding of the complex characteristics of the system. This surface analysis data provides an accurate parameter basis for the geometric attribute assignment in the subsequent digital twin model. Finally, the point cloud data of the mechanical characteristics of the electrical appliance is used to establish the digital twin model, and the geometric properties in the electrical power and thermal energy surface analysis data are assigned to the model to generate a complete electrical digital twin model. This model integrates power, thermal energy and mechanical characteristics, not only realizing multi-dimensional dynamic simulation of the electrical system, but also providing precise digital support for subsequent performance optimization, fault prediction and energy efficiency management. Through the spatial mapping, point cloud generation, surface fitting and construction of digital twin models of this multi-dimensional feature data, the process effectively improves the data integration and the accuracy of system modeling, and provides a data-driven scientific basis for the full life cycle management of complex electrical systems.

[0020] Preferably, step S22 includes the following steps:

[0021] Step S221: performing point cloud data segmentation on the electrical appliance power and thermal energy feature point cloud data to generate electrical appliance power and thermal energy point cloud segmentation data;

[0022] Step S222: performing spline interpolation surface fitting on the electrical appliance power and thermal energy point cloud segmentation data to generate electrical appliance power and thermal energy fitting data;

[0023] Step S223: Performing morphological characteristic surface analysis on the electrical power and thermal energy fitting data to generate electrical surface analysis data.

[0024] The present invention generates electrical power and thermal energy point cloud segmentation data by segmenting the electrical power and thermal energy feature point cloud data. The core of this segmentation operation is to identify and extract feature subsets of different regions through spatial division of point cloud data, so as to ensure that subsequent analysis can deal with each local characteristic change in a targeted manner. This segmentation-based processing method not only helps to improve the resolution of the data, but also effectively reduces the local details ignored in the overall analysis, thereby improving the overall expression ability of the data. The generated electrical power and thermal energy point cloud segmentation data is subjected to spline interpolation surface fitting to generate electrical power and thermal energy fitting data. Spline interpolation surface fitting is a smooth surface construction method with local adjustment capability. It generates a continuous and smooth surface by interpolating the segmented point cloud data, thereby more accurately capturing the spatial characteristics of the data. This fitting method can not only effectively smooth the influence of noise, but also ensure the local accuracy of the surface, so that the fitting result is closer to the actual physical characteristics, and is particularly suitable for the expression of complex morphological power and thermal energy feature data. The fitting data generated by this process provides a high-precision basic data set for subsequent morphological feature analysis. Based on the fitting data, morphological characteristic surface analysis is performed to generate electrical surface analysis data. Through morphological characteristic surface analysis, it is possible to deeply explore the local and overall characteristics of the surface geometry, such as curvature, inflection point, and slope, so as to extract key morphological characteristic parameters related to electrical performance. This analysis not only improves the depth of understanding of the thermodynamic and electrical characteristics of the system, but also provides high-precision data input for geometric modeling and performance prediction in the digital twin model. Overall, this process effectively improves the meticulousness of data processing and the accuracy of analysis results through point cloud segmentation, spline interpolation surface fitting, and morphological characteristic analysis, so that the digital twin model of the electrical system can more realistically reflect the actual operation.

[0025] Preferably, step S3 comprises the following steps:

[0026] Step S31: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to trace the appliance energy source of the real-time operation data to generate an appliance energy traceability result, wherein the appliance energy traceability result includes direct power energy and indirect power energy;

[0027] Step S32: Calculate the electrical appliance energy consumption based on the electrical appliance energy tracing result to generate an electrical appliance energy consumption data set, wherein the electrical appliance energy consumption data set includes direct electric drive energy and indirect electric drive energy;

[0028] Step S33: Set an initial loss rate based on historical appliance usage data; perform time step performance decay calculation on the appliance energy consumption data set based on the initial loss rate to generate a stage loss calculation result; perform time loss accumulation on the stage loss calculation result to generate an appliance energy consumption calculation result.

[0029] The present invention obtains historical electrical appliance usage data and electrical appliance real-time operation data, uses a digital twin model to perform electrical appliance energy source tracing analysis on real-time operation data, and generates electrical appliance energy source tracing results. This process simulates the operation characteristics and energy consumption of electrical appliances through a digital twin model, reproduces the energy types and sources used by electrical appliances during operation, and divides them into two categories: direct power energy and indirect power energy. This energy source tracing analysis not only helps to understand the energy consumption characteristics of electrical appliances under different operating environments, but also provides accurate energy classification data for subsequent energy consumption calculations. Electrical appliance energy consumption is calculated based on the electrical appliance energy source tracing results, and an electrical appliance energy consumption data set is generated, which includes direct power drive energy and indirect power drive energy. This energy consumption calculation process establishes an energy consumption model of electrical appliances driven by different energy sources through independent analysis and calculation of different types of energy. Through the subdivision and precise calculation of energy consumption data, not only the accuracy of energy consumption data is improved, but also the understanding of the comprehensive energy efficiency of electrical appliances under various energy supply conditions is enhanced. The establishment of an electrical appliance energy consumption data set provides detailed basic data support for subsequent loss analysis and energy consumption optimization. Finally, the initial loss rate is set by combining the historical appliance usage data, and the time step performance decay calculation is performed on the appliance energy consumption data set based on the loss rate to generate the stage loss calculation result. This step deeply explores the changing pattern of appliance energy consumption during long-term use by calculating and analyzing the decay trend of appliance performance in different time periods. Subsequently, the stage loss calculation results are accumulated over time to finally generate the appliance energy consumption calculation results. This cumulative analysis on the time series can effectively simulate the energy consumption accumulation of appliances after long-term operation, and provide accurate predictions of the overall service life and long-term energy efficiency of appliances.

[0030] Preferably, step S31 includes the following steps:

[0031] Step S311: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to identify the energy category of the appliance real-time operation data and generate an energy category identification result;

[0032] Step S312: Perform energy source traceability graph analysis on the energy category identification result to generate an electric energy source traceability graph;

[0033] Step S313: Perform energy consumption classification matching on the electric energy traceability map and the historical appliance usage data to generate an electric energy traceability result, wherein the electric energy traceability result includes direct electric energy and indirect electric energy.

[0034] The present invention obtains historical electrical appliance usage data and electrical appliance real-time operation data, and uses the electrical appliance digital twin model to identify the energy category of the electrical appliance real-time operation data to generate an energy category identification result. This process dynamically identifies and classifies the energy usage mode of the electrical appliance in actual operation through the refined simulation of the digital twin model, and the generated energy category identification result can accurately reflect the energy type and consumption mode of the electrical appliance under different operating conditions. This category identification not only improves the resolution of the data, but also provides basic data support for subsequent energy traceability analysis. The energy category identification result is analyzed by energy traceability graph to generate an electric energy traceability graph. This analysis process constructs a detailed energy usage path graph by deep mining the spatial and temporal dimensions of the identification results. The energy traceability graph not only shows the flow path and conversion relationship of energy, but also reveals the energy consumption change trend of electrical appliances driven by different energy sources. This graph analysis intuitively presents the complexity and diversity of energy use through visualization means, providing a comprehensive reference basis for subsequent energy consumption optimization. Finally, the electric energy traceability graph is matched with the historical electrical appliance usage data for energy consumption classification to generate an electric energy traceability result, including a detailed classification of direct electric energy and indirect electric energy. This step accurately locates the energy source and consumption mode of electrical appliances in actual operation by matching and analyzing historical data with the traceability map. The generated power energy traceability results provide a clear classification basis for energy management. Through this matching analysis, not only can the usage ratio of different types of energy be identified, but also potential energy efficiency improvement space and optimization path can be discovered.

[0035] Preferably, step S32 includes the following steps:

[0036] Step S321: Calculate the instantaneous energy consumption of voltage and current for direct electric energy to generate instantaneous power energy consumption data; perform time integration on the instantaneous power energy consumption data to generate electric drive energy consumption data;

[0037] Step S322: extracting solar energy and wind energy data from indirect electric drive energy to generate solar energy data and wind energy data; extracting light intensity characteristics from photovoltaic solar panels to generate light intensity curve data; performing Monte Carlo simulation on the light intensity curve data and solar energy data to generate solar drive energy consumption data;

[0038] Step S323: Obtain wind speed change data; perform hidden Markov calculation on the wind speed change data and wind energy data to calculate instantaneous output power and generate wind loss output power; perform state transfer matrix analysis on the wind loss output power and perform time integration to generate wind energy drive energy consumption data.

[0039] The present invention calculates the instantaneous energy consumption of the voltage and current of the direct electric energy source, and integrates the instantaneous data in time, and the generated electric drive energy consumption data can provide real-time monitoring and historical analysis of the energy consumption of the power system. This analysis method combining real-time and historical data allows better identification of energy consumption peaks and anomalies, thereby achieving more accurate energy consumption management and energy-saving strategy formulation. By extracting solar energy and wind energy data, and combining light intensity characteristics and Monte Carlo simulation, the efficiency of indirect electric drive energy is deeply analyzed. In particular, the use of Monte Carlo simulation for uncertainty analysis can generate more reliable solar drive energy consumption data based on different lighting conditions. This method provides strong support for the optimal utilization of solar energy resources and ensures that the performance and benefits of solar panels can be effectively evaluated under different environmental conditions. The instantaneous output power of wind power is calculated by a hidden Markov model, and the wind energy drive energy consumption data generated by state transfer matrix analysis is combined to provide a method for dynamically analyzing the performance of a wind energy system. Through sensitivity analysis of wind speed changes and time integration of state transfer, the energy consumption and potential losses of a wind system can be more accurately predicted. This method not only helps to improve the efficiency of wind energy utilization, but also provides data support for the design and operation and maintenance of wind energy systems.

[0040] Preferably, step S33 includes the following steps:

[0041] Step S331: setting an initial loss rate based on historical appliance usage data; performing Weibull distribution attenuation calculation on the appliance energy consumption data set based on the initial loss rate to generate appliance energy consumption attenuation distribution data;

[0042] Step S332: Connect the distribution nodes of the electrical appliance energy consumption attenuation distribution data in series to generate electrical appliance energy consumption attenuation series data; perform time step performance attenuation calculation on the electrical appliance energy consumption attenuation series data to generate stage loss calculation results;

[0043] Step S333: Accumulate the time loss of the stage loss calculation results to generate the electrical energy consumption calculation results.

[0044] The present invention sets the initial loss rate through historical electrical appliance usage data, and uses Weibull distribution to calculate energy consumption decay, so that the prediction of energy consumption decay has statistical rigor and reliability. As a commonly used life distribution model, Weibull distribution can effectively capture the performance changes of electrical appliances at different use stages when dealing with the problem of electrical appliance energy consumption decay, thereby generating more accurate electrical appliance energy consumption decay distribution data. Electrical appliance energy consumption decay distribution data is connected in series through distribution nodes to form electrical appliance energy consumption decay series data. This process not only integrates the energy consumption decay information of different time nodes, but also provides a basis for subsequent time step performance decay calculation. The generation of this series data enables the performance decay of electrical appliance energy consumption in different time steps to be quantitatively analyzed, thereby generating stage loss calculation results. Through such analysis, the key time nodes that affect the energy efficiency of electrical appliances and their corresponding loss characteristics can be identified. Finally, the final calculation result of electrical appliance energy consumption is generated by accumulating the time loss of the stage loss calculation results. This process provides an energy consumption analysis from a time accumulation perspective, so that the energy consumption changes at different use stages can be comprehensively evaluated.

[0045] Preferably, step S4 comprises the following steps:

[0046] Step S41: Perform graph theory modeling on the electrical appliance energy consumption calculation results to generate electrical appliance energy consumption state nodes; perform TSP solution on the electrical appliance energy consumption state nodes to generate energy consumption trajectory paths;

[0047] Step S42: extracting abnormal fluctuation sections from the energy consumption trajectory path to generate abnormal energy consumption fluctuation sections; performing data set difference operation on the abnormal energy consumption fluctuation sections and the energy consumption trajectory path to generate smooth energy consumption fluctuation sections; performing smooth energy consumption fluctuation screening on the smooth energy consumption fluctuation sections to generate optimal energy consumption selected section data;

[0048] Step S43: Perform a smooth section energy consumption section simulation on the optimal energy consumption section data to generate electrical appliance smooth fluctuation energy consumption simulation data; perform section energy consumption selection integration processing on the section with abnormal energy consumption fluctuation to generate electrical appliance abnormal fluctuation energy consumption simulation data; perform energy consumption aggregation on the electrical appliance smooth fluctuation energy consumption simulation data and the electrical appliance abnormal fluctuation energy consumption simulation data to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0049] The present invention generates electrical appliance energy consumption state nodes by graph theory modeling of the electrical appliance energy consumption calculation results, and solves the traveling salesman problem (TSP) for these nodes, thereby generating an energy consumption trajectory path. This process utilizes the powerful modeling ability of graph theory and the path optimization characteristics of TSP, can effectively identify the energy consumption path of electrical appliances in different states, and provides a structured basis for subsequent energy consumption optimization. By extracting the abnormal fluctuation section of the energy consumption trajectory path, the abnormal energy consumption fluctuation section is generated, and the energy consumption fluctuation smooth section is distinguished by data set difference operation. Through this method, the abnormal fluctuation interval and the stable interval of electrical appliance energy consumption can be effectively identified, laying a data foundation for further optimization processing. Then, by screening the energy consumption fluctuation smooth section, the optimal energy consumption section data is generated. This process ensures that in the energy consumption path, only the most favorable stable section for the overall energy consumption is retained, thereby providing support for energy consumption optimization. The optimal energy consumption section data is simulated to generate electrical appliance fluctuation smooth energy consumption simulation data, and the section energy consumption selection integral processing is performed to generate electrical appliance fluctuation abnormal energy consumption simulation data. This simulation process combines the characteristics of normal and abnormal energy consumption, and generates the final appliance energy consumption simulation data by combining the energy consumption of the two. This process provides a comprehensive energy consumption evaluation perspective, allowing the performance of appliances under different energy consumption states to be fully understood.

[0050] Preferably, step S43 includes the following steps:

[0051] Step S431: Analyze the energy consumption characteristic curve of the optimal energy consumption selected section data to generate key state node data; estimate the state transition probability of the key state node data to generate electrical appliance energy consumption probability data; simulate the smooth section energy consumption section of the electrical appliance energy consumption probability data to generate electrical appliance fluctuation smooth energy consumption simulation data;

[0052] Step S432: Performing section energy consumption selection and integration processing on the energy consumption fluctuation abnormal data to generate electrical appliance fluctuation abnormal energy consumption simulation data;

[0053] Step S433: Energy consumption is aggregated for the electrical appliance energy consumption simulation data with smooth fluctuations and the electrical appliance energy consumption simulation data with abnormal fluctuations to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0054] The present invention identifies and generates key state node data by analyzing the energy consumption characteristic curve of the optimal energy consumption selected section data. This process utilizes the changing trend of energy consumption characteristics to effectively capture the energy consumption characteristics of electrical appliances under different operating states, and provides important data support for the subsequent state transition probability estimation. Through the estimation of the state transition probability, the system generates electrical appliance energy consumption probability data. This probability-based analysis method makes energy consumption prediction more flexible and accurate, and can reflect the energy consumption distribution and its changing trend of electrical appliances under different states. The electrical appliance energy consumption probability data is used to simulate the energy consumption section of the gentle section to generate electrical appliance fluctuation gentle energy consumption simulation data. This simulation process comprehensively considers the energy consumption characteristics of electrical appliances under stable operating conditions, so that the simulation results can more realistically reflect the actual energy consumption of electrical appliances, thereby providing a reliable basis for the implementation of the optimization strategy. Step S432 generates electrical appliance fluctuation abnormal energy consumption simulation data by performing section energy consumption selection integral processing on the energy consumption fluctuation abnormal data. This processing process deeply analyzes and integrates the abnormal energy consumption characteristics, and provides data support for identifying and evaluating the energy consumption performance of electrical appliances under non-stable conditions. Finally, the energy consumption simulation data of electrical appliances with smooth fluctuations and abnormal fluctuations are combined to generate the energy consumption simulation data of electrical appliances. This energy consumption aggregation method unifies the characteristics of smooth and abnormal energy consumption under a unified framework for analysis, so that the energy consumption simulation data generated can fully reflect the energy consumption performance of electrical appliances under different operating conditions.

[0055] The beneficial effect of the present invention is that by acquiring and preprocessing electrical data, thermodynamic data and mechanical data, electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values ​​are generated. This process not only extracts the key characteristics of various types of data, but also lays a solid data foundation for subsequent steps. These characteristic engineering values ​​are mapped to three-dimensional space to generate three-dimensional point cloud data, and through morphological surface analysis, the complex relationship and change law of electrical characteristics in the spatial dimension are further extracted. This not only improves the expressiveness of the data, but also enables the digital twin model to more accurately reflect the operating status of the actual system. By using the generated digital twin model, the real-time operation data of the electrical appliance is traced to the source of electric energy, and the dual calculation of electrical appliance energy consumption calculation and time component loss simulation is completed accordingly. This process enables the energy consumption data set to be fully simulated and analyzed in the time dimension, providing a reliable basis for the long-term energy consumption trend prediction of electrical appliances. Subsequently, step S4 further deepens the accuracy and optimization of energy consumption calculation. By extracting and analyzing the energy consumption trajectory path, the sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations were identified, and then the section energy consumption was selected and integrated and the smooth section energy consumption was simulated. The final electrical energy consumption simulation data was generated through the energy consumption set. This series of operations ensures the accuracy and efficiency of energy consumption optimization calculation by separating and processing abnormal and smooth sections. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of the steps of a method for calculating electrical appliance energy consumption based on a digital twin model;

[0057] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0058] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0059] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0060] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0062] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0063] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0064] To achieve this, please refer to Figures 1 to 4 , a method for calculating electrical appliance energy consumption based on a digital twin model, the method comprising the following steps:

[0065] Step S1: Acquire electrical data, thermodynamic data and mechanical data; perform data preprocessing on the electrical data, thermodynamic data and mechanical data to generate electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values;

[0066] Step S2: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to three-dimensional space to generate three-dimensional point cloud, thereby generating electrical appliance characteristic point cloud data; performing morphological surface analysis on the electrical appliance characteristic point cloud data to generate electrical appliance surface analysis data; establishing a digital twin model based on the electrical appliance surface analysis data to generate an electrical appliance digital twin model;

[0067] Step S3: Use the electrical appliance digital twin model to trace the power energy source of the real-time operation data to generate the power energy traceability result; perform electrical appliance energy consumption calculation on the power energy traceability result to generate an electrical appliance energy consumption data set; perform dual calculation of time component loss simulation on the electrical appliance energy consumption data set to generate the electrical appliance energy consumption calculation result;

[0068] Step S4: extracting energy consumption trajectory paths from the electrical appliance energy consumption calculation results to generate energy consumption trajectory paths;

[0069] The data of abnormal and smooth sections of the energy consumption trajectory path are extracted to generate sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations; the sections with abnormal energy consumption fluctuations are processed with section energy consumption selection points to generate electrical appliance abnormal energy consumption simulation data; based on the sections with smooth energy consumption fluctuations, the energy consumption fluctuations are screened to generate the optimal energy consumption selection section data; the optimal energy consumption selection section data is simulated for the smooth section energy consumption, and the energy consumption is aggregated with the electrical appliance abnormal energy consumption simulation data to generate the electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0070] The beneficial effect of the present invention is that by acquiring and preprocessing electrical data, thermodynamic data and mechanical data, electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values ​​are generated. This process not only extracts the key characteristics of various types of data, but also lays a solid data foundation for subsequent steps. These characteristic engineering values ​​are mapped to three-dimensional space to generate three-dimensional point cloud data, and through morphological surface analysis, the complex relationship and change law of electrical characteristics in the spatial dimension are further extracted. This not only improves the expressiveness of the data, but also enables the digital twin model to more accurately reflect the operating status of the actual system. By using the generated digital twin model, the real-time operation data of the electrical appliance is traced to the source of electric energy, and the dual calculation of electrical appliance energy consumption calculation and time component loss simulation is completed accordingly. This process enables the energy consumption data set to be fully simulated and analyzed in the time dimension, providing a reliable basis for the long-term energy consumption trend prediction of electrical appliances. Subsequently, step S4 further deepens the accuracy and optimization of energy consumption calculation. By extracting and analyzing the energy consumption trajectory path, the sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations were identified, and then the section energy consumption was selected and integrated and the smooth section energy consumption was simulated. The final electrical energy consumption simulation data was generated through the energy consumption set. This series of operations ensures the accuracy and efficiency of energy consumption optimization calculation by separating and processing abnormal and smooth sections.

[0071] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for calculating the energy consumption of an electrical appliance based on a digital twin model of the present invention. In this example, the method for calculating the energy consumption of an electrical appliance based on a digital twin model includes the following steps:

[0072] Step S1: Acquire electrical data, thermodynamic data and mechanical data; perform data preprocessing on the electrical data, thermodynamic data and mechanical data to generate electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values;

[0073] In the embodiment of the present invention, data acquisition is performed through a variety of sensors and data acquisition systems, which can collect relevant data from power equipment, thermal systems and mechanical devices in real time. Electrical data comes from current and voltage sensors and smart meters, while thermodynamic data is obtained through temperature sensors, thermocouples and infrared thermal imagers. Mechanical data is usually collected by accelerometers, vibration sensors and displacement sensors. The accuracy and timeliness of data are the key to ensuring the quality of subsequent analysis, so the data acquisition system needs to have high-precision and high-frequency sampling capabilities. Data preprocessing is the process of cleaning, converting and feature extraction of raw data to generate electrical energy feature engineering values, thermal energy feature engineering values ​​and mechanical feature engineering values. Data cleaning is a necessary step to remove noise, outliers and missing data. Common cleaning techniques include mean filling, interpolation and data smoothing. Afterwards, data standardization and normalization are common preprocessing operations that can eliminate dimensional effects and make data comparable on the same scale. In addition, data dimensionality reduction techniques such as principal component analysis (PCA) are also applied to reduce data dimensions, highlight the main features, and help improve computational efficiency and model performance. Feature extraction is a key step in preprocessing, which involves converting processed data into characteristic values ​​that can represent the system status and performance. In power feature engineering, the extracted features include power quality indicators such as harmonic content, power factor, and current and voltage fluctuation characteristics; for thermal energy feature engineering, the focus is on temperature gradient, heat flux, and system thermal efficiency indicators; mechanical feature engineering focuses on vibration spectrum characteristics, stress-strain state, and the dynamic characteristics of machine operation. The selection and extraction of these features often rely on the combination of domain knowledge and machine learning algorithms to ensure that the extracted features can effectively reflect the complex dynamic behavior of the system.

[0074] Step S2: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to three-dimensional space to generate three-dimensional point cloud, thereby generating electrical appliance characteristic point cloud data; performing morphological surface analysis on the electrical appliance characteristic point cloud data to generate electrical appliance surface analysis data; establishing a digital twin model based on the electrical appliance surface analysis data to generate an electrical appliance digital twin model;

[0075] In an embodiment of the present invention, the electrical energy feature engineering value, the thermal energy feature engineering value, and the mechanical feature engineering value are mapped to a three-dimensional space to generate a three-dimensional point cloud, and this process involves a variety of data processing and computing technologies. Specifically, the mapping process usually requires selecting a suitable feature combination as a representative of the three-dimensional coordinate axis, and mapping the high-dimensional feature space to the three-dimensional space through mathematical transformation or dimensionality reduction algorithms (such as t-SNE or UMAP). These point cloud data can not only reflect the overall characteristics and state distribution of the device, but also provide an intuitive observation perspective through visualization technology. The generated electrical characteristic point cloud data is then subjected to morphological surface analysis, which is usually performed with the help of algorithms in computational geometry and computer vision, using Delaunay triangulation or Poisson surface reconstruction technology to fit discrete point cloud data into a continuous surface. This process involves topological structure analysis of point cloud data and surface smoothness adjustment to generate a more accurate and usable surface model. A digital twin model is established based on the generated electrical surface analysis data. The construction of a digital twin model is a multi-level, multi-step process, which usually combines physical modeling, data assimilation, and machine learning techniques to achieve a realistic digital reproduction of physical objects. Surface analysis data provides detailed information about the morphological structure of physical equipment, which can serve as the geometric basis of the digital twin model. On this basis, dynamic characteristic information (such as electrical performance, thermodynamic behavior, and mechanical properties) must be integrated to simulate the response behavior of the equipment under different working conditions by establishing a multi-physics field coupling model. Data-driven machine learning models (such as neural networks and random forests) can be used to capture complex nonlinear relationships and supplement the deficiencies of traditional physical models. Such a multi-level model can not only reflect the operating status of the equipment in real time, but also be used to predict and optimize equipment performance.

[0076] Step S3: Use the electrical appliance digital twin model to trace the power energy source of the real-time operation data to generate the power energy traceability result; perform electrical appliance energy consumption calculation on the power energy traceability result to generate an electrical appliance energy consumption data set; perform dual calculation of time component loss simulation on the electrical appliance energy consumption data set to generate the electrical appliance energy consumption calculation result;

[0077] In the embodiment of the present invention, the real-time collected electrical data is correlated and analyzed with its corresponding physical state and operating conditions through the precise dynamic simulation capability of the digital twin model to track and identify the transmission path and usage of electric energy in the system. The digital twin model can analyze complex energy flow processes and identify energy losses and efficiency bottlenecks through the combination of high-fidelity physical simulation and data-driven models. This process is usually applied to state estimation algorithms and energy balance equations to ensure the accuracy and reliability of traceability results. The generated electric energy traceability results provide a basis for the calculation of electrical energy consumption. When calculating the energy consumption of electrical appliances, it is necessary to conduct a refined quantitative analysis of energy usage. This process usually combines data from energy management systems (EMS) and advanced metering infrastructure (AMI) to refine the energy consumption patterns of electrical appliances under different working conditions. Through real-time data analysis and historical data comparison, using model predictive control (MPC) and machine learning algorithms, the energy consumption data set of electrical appliances can be accurately calculated. This data set not only contains instantaneous energy consumption information, but also involves the energy efficiency performance of the equipment under different operating conditions. The purpose of dual calculation of time component loss simulation on electrical energy consumption data sets is to gain a deeper understanding of the energy consumption characteristics and component wear of the equipment in long-term operation. Time component loss simulation is usually performed through life prediction models and fatigue analysis techniques, which can predict the wear rate and remaining life of key components based on the equipment's operating history and current status. Through dual calculation of energy consumption data, optimization recommendations for the overall energy efficiency of the equipment and the formulation of maintenance strategies can be achieved. These calculations are usually combined with finite element analysis (FEA) and data-driven predictive models to provide a comprehensive assessment of equipment performance.

[0078] Step S4: extract the energy consumption trajectory path of the electrical appliance energy consumption calculation result to generate the energy consumption trajectory path; extract the abnormal and smooth section data of the energy consumption trajectory path to generate the section with abnormal energy consumption fluctuation and the section with smooth energy consumption fluctuation; perform section energy consumption selection and integration processing on the section with abnormal energy consumption fluctuation to generate the energy consumption simulation data with abnormal fluctuation of electrical appliances; perform energy consumption smooth screening based on the section with smooth energy consumption fluctuation to generate the optimal energy consumption selection section data; perform smooth section energy consumption section simulation on the optimal energy consumption selection section data, and perform energy consumption aggregation with the energy consumption simulation data with abnormal fluctuation of electrical appliances to generate the energy consumption simulation data of electrical appliances, thereby completing the energy consumption optimization calculation of electrical appliances.

[0079] In the embodiment of the present invention, the energy consumption of the equipment is analyzed during operation. The trajectory of the change of the energy consumption of the equipment over time and operating conditions is realized. Specifically, it is necessary to use time series analysis technology to analyze the dynamic changes of energy consumption data and identify the characteristic patterns of energy consumption paths. This usually involves segmentation of energy consumption data to extract energy consumption paths in different operation stages, and classify similar energy consumption patterns through clustering algorithms (K-means) to generate energy consumption trajectory paths. After obtaining the energy consumption trajectory path, the abnormal and gentle section data are extracted. This step requires the combination of statistical analysis and anomaly detection algorithms (Z-score) to identify abnormal fluctuations and stable stages in energy consumption data. Abnormal sections usually represent unstable or inefficient stages in equipment operation, while gentle sections represent the energy consumption performance of equipment in a stable and efficient state. The extracted energy consumption fluctuation abnormal sections and energy consumption fluctuation gentle sections provide basic data for subsequent energy consumption optimization. The section energy consumption selection and integration processing of energy consumption fluctuation abnormal sections is to perform a refined analysis of abnormal energy consumption sections through mathematical integration methods to quantify the impact of abnormal fluctuations on overall energy consumption. This usually requires building an abnormal energy consumption model, using integral tools to calculate the energy consumption contribution of the abnormal fluctuation interval, and generating electrical appliance fluctuation abnormal energy consumption simulation data. At the same time, based on the smooth energy consumption fluctuation section, the energy consumption fluctuation is screened to identify the optimal energy consumption path. This step is usually combined with a multi-objective optimization algorithm. By comparing the energy consumption efficiency of different smooth sections, the section with the best energy consumption performance is screened out to generate the optimal energy consumption selected section data. Finally, the optimal energy consumption selected section data is simulated for the smooth section energy consumption section, and the energy consumption is aggregated with the electrical appliance fluctuation abnormal energy consumption simulation data. This process requires the integration of simulation and optimization technologies. By building a comprehensive energy consumption model, the efficient energy consumption mode of the smooth section is combined with the improvement suggestions for the abnormal fluctuation section to generate electrical appliance energy consumption simulation data. This comprehensive simulation not only provides data support for the optimization of the energy consumption path, but also provides specific improvement strategies for improving the energy efficiency of equipment, thereby effectively completing the electrical appliance energy consumption optimization calculation.

[0080] Preferably, step S1 comprises the following steps:

[0081] Step S11: acquiring electrical data, thermodynamic data and mechanical data through sensors, wherein the electrical data includes power factor and electric energy, the thermodynamic data includes thermal expansion coefficient and cooling efficiency, and the mechanical data includes mechanical efficiency and electrical amplitude rate;

[0082] Step S12: performing random noise reduction processing on the power factor and electric energy, the thermal expansion coefficient and the cooling efficiency, the mechanical efficiency and the electrical amplitude rate to generate electric energy characteristic noise reduction data, thermal energy characteristic noise reduction data and thermal energy characteristic noise reduction data; performing data standardization processing on the electric energy characteristic noise reduction data, the thermal energy characteristic noise reduction data and the thermal energy characteristic noise reduction data to generate electric energy standardized data, thermal energy standardized data and mechanical standardized data;

[0083] Step S13: Perform abnormal value identification processing on the electric energy standardized data to generate electric energy characteristic engineering values; perform temperature medium change analysis on the thermal energy standardized data to generate thermal energy characteristic engineering values; perform mechanical structure stress analysis on the mechanical standardized data to generate mechanical characteristic engineering values.

[0084] In the embodiment of the present invention, obtaining electrical data, thermodynamic data and mechanical data through sensors is the basis for realizing comprehensive monitoring and analysis of equipment status. The acquisition of electrical data usually involves the use of smart meters and current sensors, which can measure power factor and electric energy to evaluate the efficiency and load condition of the electrical system. The collection of thermodynamic data relies on temperature sensors and thermocouples, which can provide information on thermal expansion coefficient and cooling efficiency for evaluating the performance of thermal management systems. Mechanical data is obtained through accelerometers and vibration sensors to measure mechanical efficiency and electrical amplitude rate, thereby evaluating the dynamic performance and stability of mechanical systems. Random noise reduction processing is a key step in data preprocessing, which is used to remove data inaccuracy caused by sensor noise or environmental interference. Commonly used random noise reduction techniques include wavelet transform, Kalman filtering and adaptive filtering, which can effectively remove noise while retaining the true characteristics of the signal. The denoised data needs to be standardized to eliminate the dimensional differences between different features so that they can be compared on a unified scale. Standardization processing usually uses Z-score standardization or minimum-maximum standardization to convert the data into a specific distribution range, thereby generating standardized data for electrical energy, thermal energy and machinery. Outlier identification is performed on the electrical energy standardized data, which usually uses statistical methods such as box plot analysis or machine learning algorithms such as isolation forests and support vector machines (SVM) to detect and process outliers. These technologies can identify potential abnormal patterns, ensure the integrity and reliability of the data, and generate electrical energy feature engineering values. For thermal energy standardized data, temperature medium change analysis involves thermodynamic modeling and heat transfer analysis. By analyzing the impact of temperature changes on system performance, thermal energy feature engineering values ​​are extracted. This process uses finite element analysis (FEA) to simulate the temperature field distribution and help identify key thermal characteristics. Mechanical structural stress analysis of mechanical standardized data uses mechanical analysis and structural simulation technology to evaluate the stress conditions of mechanical components to generate mechanical feature engineering values. This analysis is usually combined with stress-strain curves and material properties, and is performed through computer-aided engineering (CAE) tools to ensure accurate modeling and fatigue prediction of mechanical systems.

[0085] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0086] Step S21: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to a three-dimensional space according to a preset mapping rule to generate three-dimensional space characteristic data; generating a three-dimensional point cloud according to the three-dimensional space characteristic data to generate electrical mechanical characteristic point cloud data and electrical power thermal energy characteristic point cloud data;

[0087] Step S22: performing surface fitting representative analysis on the electrical appliance power and thermal energy characteristic point cloud data to generate electrical appliance power and thermal energy surface analysis data;

[0088] Step S23: Establish a digital twin model of the electrical appliance mechanical characteristic point cloud data, and assign geometric attributes to the electrical appliance power and thermal energy surface analysis data to generate a digital twin model of the electrical appliance.

[0089] In an embodiment of the present invention, the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value are mapped to a three-dimensional space by a preset mapping rule to generate corresponding three-dimensional space characteristic data. This process involves the feature extraction of multidimensional data and the application of mapping rules to ensure that different types of characteristic data can be represented in a unified three-dimensional space. Subsequently, by processing these three-dimensional space characteristic data, three-dimensional point cloud data are generated, including electrical mechanical characteristic point cloud data and electrical electrical power and thermal energy characteristic point cloud data. Point cloud generation technology is used in this step, which can effectively convert characteristic data into spatial point distribution, which is convenient for subsequent analysis and processing. Surface fitting analysis is performed on the generated electrical power and thermal energy characteristic point cloud data to generate electrical power and thermal energy surface analysis data. Surface fitting technology plays a key role in this process. By fitting the point cloud data, a smoother and continuous surface representation can be obtained to reflect the characteristics of electrical equipment in terms of power and thermal energy. This process not only helps to extract useful information, but also reduces data noise by fitting the surface, and improves the accuracy and reliability of data analysis. Finally, the electrical mechanical characteristic point cloud data is used to establish a digital twin model. At the same time, the geometric properties of the previously generated electrical power and thermal energy surface analysis data are assigned to the digital twin model to generate a complete electrical digital twin model. The digital twin model is a virtual representation of the physical device. By combining the geometric properties of mechanical properties and power and thermal energy properties, a comprehensive simulation and analysis of electrical equipment can be achieved. This step involves the application of digital twin technology to ensure high-precision mapping between physical equipment and virtual models, thereby achieving accurate prediction and management of equipment status and behavior.

[0090] Preferably, step S22 includes the following steps:

[0091] Step S221: performing point cloud data segmentation on the electrical appliance power and thermal energy feature point cloud data to generate electrical appliance power and thermal energy point cloud segmentation data;

[0092] Step S222: performing spline interpolation surface fitting on the electrical appliance power and thermal energy point cloud segmentation data to generate electrical appliance power and thermal energy fitting data;

[0093] Step S223: Performing morphological characteristic surface analysis on the electrical power and thermal energy fitting data to generate electrical surface analysis data.

[0094] In an embodiment of the present invention, the electrical power and thermal energy characteristic point cloud data is segmented to generate electrical power and thermal energy point cloud segmentation data. Point cloud data segmentation technology plays an important role in this link. The point cloud data is segmented into different parts according to predefined criteria through an algorithm, so that subsequent processing is more efficient and targeted. This process usually involves cluster analysis, region growth algorithm or graph-based segmentation method to ensure that the segmentation result can accurately reflect the internal structure and characteristics of the point cloud data. Spline interpolation surface fitting is performed on the electrical power and thermal energy point cloud segmentation data to generate electrical power and thermal energy fitting data. Spline interpolation technology plays a key role in this step. By applying the spline interpolation algorithm to the segmented point cloud data, a continuous and smooth surface can be generated. This not only enhances the accuracy of data representation, but also effectively captures the detailed features of the surface morphology. Spline interpolation surface fitting can provide higher fitting accuracy and better smoothing effect when processing complex data structures, and is suitable for reflecting the electrical power and thermal energy characteristics of electrical equipment. Morphological characteristic surface analysis is performed on the electrical power and thermal energy fitting data to generate electrical surface analysis data. The morphological feature analysis technology is applied at this stage. By deeply analyzing the geometric morphological features of the fitting surface, key morphological feature information is extracted. These features include the curvature, convexity, and local extreme points of the surface. Through the analysis of these features, the behavior patterns and characteristics of electrical equipment in terms of power and thermal energy can be better understood.

[0095] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0096] Step S31: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to trace the appliance energy source of the real-time operation data to generate an appliance energy traceability result, wherein the appliance energy traceability result includes direct power energy and indirect power energy;

[0097] Step S32: Calculate the electrical appliance energy consumption based on the electrical appliance energy tracing result to generate an electrical appliance energy consumption data set, wherein the electrical appliance energy consumption data set includes direct electric drive energy and indirect electric drive energy;

[0098] Step S33: Set an initial loss rate based on historical appliance usage data; perform time step performance decay calculation on the appliance energy consumption data set based on the initial loss rate to generate a stage loss calculation result; perform time loss accumulation on the stage loss calculation result to generate an appliance energy consumption calculation result.

[0099] In the embodiment of the present invention, by obtaining historical appliance usage data and appliance real-time operation data, the appliance digital twin model is used to trace the energy source of the appliance to the real-time operation data, and the appliance energy traceability result is generated. The key technical means in this step is the application of the digital twin model. By mapping the real-time data to the virtual model, the energy usage of the appliance can be accurately tracked, and direct power energy and indirect power energy can be distinguished. This process involves data acquisition, data synchronization and model mapping technology to ensure that the real-time data can accurately reflect the actual operation status and energy consumption of the appliance. The appliance energy consumption is calculated for the appliance energy traceability result to generate an appliance energy consumption data set. The appliance energy consumption data set includes direct power drive energy and indirect power drive energy. This step mainly involves energy consumption calculation and data set construction technology. By analyzing and calculating the traceability results, the consumption of different types of energy is quantified. Energy consumption calculation is usually based on energy balance equations or statistical models, combined with historical data and actual operation data to ensure the accuracy and reliability of the calculation results. Finally, the initial loss rate is set according to the historical appliance usage data, and the time step performance decay calculation is performed on the appliance energy consumption data set based on the initial loss rate to generate the stage loss calculation result. Then, the time loss is accumulated for the stage loss calculation results to generate the electrical energy consumption calculation results. This step involves performance decay calculation and time series analysis technology. The setting of the initial loss rate is usually based on statistical analysis and empirical data. By performing a time step performance decay calculation on the energy consumption data set, the energy consumption changes of electrical appliances in different time periods can be simulated. The time step performance decay calculation usually uses a recursive algorithm or a differential equation, combined with a time series analysis model to ensure the accuracy of the stage loss calculation results. Finally, by accumulating the time of the stage loss results, the overall electrical energy consumption calculation results can be obtained, providing comprehensive energy consumption evaluation information.

[0100] Preferably, step S31 includes the following steps:

[0101] Step S311: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to identify the energy category of the appliance real-time operation data and generate an energy category identification result;

[0102] Step S312: Perform energy source traceability graph analysis on the energy category identification result to generate an electric energy source traceability graph;

[0103] Step S313: Perform energy consumption classification matching on the electric energy traceability map and the historical appliance usage data to generate an electric energy traceability result, wherein the electric energy traceability result includes direct electric energy and indirect electric energy.

[0104] In the embodiment of the present invention, by obtaining historical appliance usage data and appliance real-time operation data, the appliance digital twin model is used to identify the energy category of the appliance real-time operation data, and generate an energy category identification result. The key technical means of this step are the application of the digital twin model and the energy category identification algorithm. The digital twin model can reflect the working status of the appliance in real time by virtualizing the operating status of the physical appliance. The energy category identification algorithm is based on real-time data, combined with historical usage data, and identifies the energy category consumed by the appliance through pattern recognition and classification algorithms, such as support vector machine (SVM), decision tree or neural network, to generate an energy category identification result. The energy category identification result is analyzed by energy traceability graph to generate an electric energy traceability graph. The energy traceability graph analysis technology plays a key role in this step. By further analyzing the energy category identification results, a graph of energy flow and conversion is constructed. The graph intuitively displays the transmission and conversion process of different energy categories in the operation of the appliance through visualization tools and graph theory algorithms. This process involves complex network analysis, path tracing and energy flow modeling technology to ensure that the generated energy traceability graph can accurately reflect the energy flow inside the appliance. The power energy traceability map and historical appliance usage data are matched by energy consumption classification to generate power energy traceability results, which include direct power energy and indirect power energy. Energy consumption classification matching technology plays a key role in this step. By comparing and matching historical usage data and energy traceability maps, it can accurately distinguish and quantify the direct and indirect power energy consumption of appliances under different operating conditions.

[0105] Preferably, step S32 includes the following steps:

[0106] Step S321: Calculate the instantaneous energy consumption of voltage and current for direct electric energy to generate instantaneous power energy consumption data; perform time integration on the instantaneous power energy consumption data to generate electric drive energy consumption data;

[0107] Step S322: extracting solar energy and wind energy data from indirect electric drive energy to generate solar energy data and wind energy data; extracting light intensity characteristics from photovoltaic solar panels to generate light intensity curve data; performing Monte Carlo simulation on the light intensity curve data and solar energy data to generate solar drive energy consumption data;

[0108] Step S323: Obtain wind speed change data; perform hidden Markov calculation on the wind speed change data and wind energy data to calculate instantaneous output power and generate wind loss output power; perform state transfer matrix analysis on the wind loss output power and perform time integration to generate wind energy drive energy consumption data.

[0109] In the embodiment of the present invention, the voltage and current instantaneous energy consumption of direct electric energy is calculated to generate instantaneous power energy consumption data. This process involves real-time measurement of voltage and current, and calculation of instantaneous power by power formula. Then, the instantaneous power energy consumption data is time-integrated to generate electric drive energy consumption data. This step converts the instantaneous energy consumption data into cumulative energy consumption data by numerical integration method, such as Simpson method, to accurately reflect the power consumption of electrical appliances over a period of time. Solar energy and wind energy data are extracted for indirect electric drive energy to generate solar energy data and wind energy data. This process involves real-time data collection of solar panels and wind power generation equipment. For the solar energy part, the light intensity characteristics of photovoltaic solar panels are extracted to generate light intensity curve data. The light intensity curve data reflects the light conditions of solar panels in different time periods, and is obtained through sensors and data recording devices. Then, the light intensity curve data and solar energy data are Monte Carlo simulated to generate solar drive energy consumption data. Monte Carlo simulation is a statistical analysis method that estimates the performance and behavior of the system through multiple random sampling and simulation to ensure the accuracy and reliability of solar drive energy consumption data. The wind speed change data is obtained, and the instantaneous output power is calculated by the Hidden Markov Model (HMM) on the wind speed change data and wind energy data to generate the wind loss output power. The Hidden Markov Model is a statistical model used to describe a random process with hidden states. The instantaneous impact of wind speed changes on wind output is calculated through maximum likelihood estimation or Bayesian inference methods. Then, the state transfer matrix analysis of the wind loss output power is performed, and time integration is performed to generate wind energy drive energy consumption data. The state transfer matrix analysis is used to describe the transition probability of the system state. Through matrix operations and time integration methods, the cumulative energy consumption data of wind energy drive is calculated.

[0110] Preferably, step S33 includes the following steps:

[0111] Step S331: setting an initial loss rate based on historical appliance usage data; performing Weibull distribution attenuation calculation on the appliance energy consumption data set based on the initial loss rate to generate appliance energy consumption attenuation distribution data;

[0112] Step S332: Connect the distribution nodes of the electrical appliance energy consumption attenuation distribution data in series to generate electrical appliance energy consumption attenuation series data; perform time step performance attenuation calculation on the electrical appliance energy consumption attenuation series data to generate stage loss calculation results;

[0113] Step S333: Accumulate the time loss of the stage loss calculation results to generate the electrical energy consumption calculation results.

[0114] In an embodiment of the present invention, an initial loss rate is set based on historical appliance usage data. This step involves analysis and statistics of historical data. By studying the energy consumption changes of appliances under different usage conditions, an initial loss rate is set. Based on the initial loss rate, a Weibull distribution attenuation calculation is performed on the appliance energy consumption data set to generate appliance energy consumption attenuation distribution data. Weibull distribution is a statistical distribution commonly used in reliability analysis and life data analysis. Through parameter estimation (such as maximum likelihood estimation), the probability distribution of appliance energy consumption attenuation can be described, reflecting the energy consumption attenuation characteristics of appliances in different time periods. The appliance energy consumption attenuation distribution data is connected in series with distributed nodes to generate appliance energy consumption attenuation series data. The distributed node series technology connects the energy consumption attenuation distribution data of different time periods to form a continuous energy consumption attenuation sequence. This step usually involves time series analysis and data series connection algorithms to ensure that the energy consumption attenuation data can accurately reflect the energy consumption changes of the appliance throughout the entire usage cycle. The time step performance attenuation calculation is performed on the appliance energy consumption attenuation series data to generate a stage loss calculation result. The time-step performance decay calculation recursively calculates the series data at a fixed time step, simulates the energy consumption decay of the appliance in each time step, and generates a staged loss result. Finally, the stage loss calculation results are accumulated over time to generate the appliance energy consumption calculation results. The time loss accumulation technology accumulates the loss results of each stage to obtain the total energy consumption of the appliance during the entire use cycle. This step usually involves the accumulation and statistical analysis of time series data. By accumulating the staged loss data, the overall trend and total amount of appliance energy consumption can be obtained.

[0115] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0116] Step S41: Perform graph theory modeling on the electrical appliance energy consumption calculation results to generate electrical appliance energy consumption state nodes; perform TSP solution on the electrical appliance energy consumption state nodes to generate energy consumption trajectory paths;

[0117] Step S42: extracting abnormal fluctuation sections from the energy consumption trajectory path to generate abnormal energy consumption fluctuation sections; performing data set difference operation on the abnormal energy consumption fluctuation sections and the energy consumption trajectory path to generate smooth energy consumption fluctuation sections; performing smooth energy consumption fluctuation screening on the smooth energy consumption fluctuation sections to generate optimal energy consumption selected section data;

[0118] Step S43: Perform a smooth section energy consumption section simulation on the optimal energy consumption section data to generate electrical appliance smooth fluctuation energy consumption simulation data; perform section energy consumption selection integration processing on the section with abnormal energy consumption fluctuation to generate electrical appliance abnormal fluctuation energy consumption simulation data; perform energy consumption aggregation on the electrical appliance smooth fluctuation energy consumption simulation data and the electrical appliance abnormal fluctuation energy consumption simulation data to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0119] In the embodiment of the present invention, graph theory modeling is performed on the calculation results of the energy consumption of the electrical appliances to generate the energy consumption state nodes of the electrical appliances. The graph theory modeling technology represents the energy consumption data of the electrical appliances as a graph structure, in which the nodes represent different energy consumption states and the edges represent the conversion relationship between the states. The traveling salesman problem (TSP) is solved for the energy consumption state nodes of the electrical appliances to generate the energy consumption trajectory path. TSP solution is a classic combinatorial optimization problem. By determining the shortest path to visit all nodes, the energy consumption trajectory is optimized to ensure the shortest energy consumption path, thereby reducing the overall energy consumption. The energy consumption trajectory path is subjected to abnormal fluctuation section extraction to generate the energy consumption fluctuation abnormal section. The abnormal fluctuation section extraction technology identifies the section with abnormal energy consumption fluctuation by analyzing the energy consumption changes in the energy consumption trajectory path. The data set difference operation is performed on the abnormal energy consumption fluctuation section and the energy consumption trajectory path to generate the energy consumption fluctuation smooth section. The data set difference operation identifies the relatively stable energy consumption section by calculating the difference between the energy consumption trajectory path and the abnormal section. The energy consumption fluctuation smooth section is screened to generate the optimal energy consumption section data. This step further screens the flat sections and selects the path sections with the best energy consumption to ensure that energy consumption is minimized. The optimal energy consumption selected section data is simulated for the flat section energy consumption section to generate the electrical appliance fluctuation flat energy consumption simulation data. The simulation technology generates detailed energy consumption data by simulating the energy consumption of the flat sections. Then, the section energy consumption selection integral processing is performed on the sections with abnormal energy consumption fluctuations to generate the electrical appliance fluctuation abnormal energy consumption simulation data. The integral processing technology calculates the overall energy consumption by cumulatively analyzing the abnormal energy consumption sections. Finally, the electrical appliance fluctuation flat energy consumption simulation data and the electrical appliance fluctuation abnormal energy consumption simulation data are energy-collected to generate the electrical appliance energy consumption simulation data. The energy consumption collection technology generates the overall electrical appliance energy consumption simulation results by integrating the flat and abnormal energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0120] Preferably, step S43 includes the following steps:

[0121] Step S431: Analyze the energy consumption characteristic curve of the optimal energy consumption selected section data to generate key state node data; estimate the state transition probability of the key state node data to generate electrical appliance energy consumption probability data; simulate the smooth section energy consumption section of the electrical appliance energy consumption probability data to generate electrical appliance fluctuation smooth energy consumption simulation data;

[0122] Step S432: Performing section energy consumption selection and integration processing on the energy consumption fluctuation abnormal data to generate electrical appliance fluctuation abnormal energy consumption simulation data;

[0123] Step S433: Energy consumption is aggregated for the electrical appliance energy consumption simulation data with smooth fluctuations and the electrical appliance energy consumption simulation data with abnormal fluctuations to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

[0124] In an embodiment of the present invention, the energy consumption characteristic curve analysis is performed on the optimal energy consumption selected section data to generate key state node data. In this step, the key state nodes of energy consumption change are identified by analyzing the energy consumption characteristic curve. The energy consumption characteristic curve analysis technology usually involves time series analysis and signal processing methods, and extracts key state node data by detecting change trends and feature points. Next, the state transition probability of the key state node data is estimated to generate electrical appliance energy consumption probability data. The state transition probability estimation calculates the transition probability of the electrical appliance between different states through statistical analysis and probability models (such as Markov chain models) to generate energy consumption probability data. This process involves probability statistics and model fitting technology to ensure the accuracy of the transition probability. The electrical appliance energy consumption probability data is simulated for a flat section energy consumption section to generate electrical appliance fluctuation flat energy consumption simulation data. The flat section energy consumption section simulation technology simulates the operation of the electrical appliance in a flat energy consumption state by simulating the energy consumption probability data, and generates detailed energy consumption simulation data. This process usually involves Monte Carlo simulation or other random simulation methods, and estimates the energy consumption distribution of the electrical appliance in a flat state through multiple random experiments. The abnormal energy consumption fluctuation data is processed by section energy consumption extraction and integration to generate electrical appliance abnormal energy consumption simulation data. The section energy consumption extraction and integration processing technology calculates the energy consumption of electrical appliances under abnormal fluctuation conditions by accumulating and integrating the abnormal energy consumption data. Integration processing usually involves numerical integration methods, such as the trapezoidal method or the Simpson method, which generates electrical appliance abnormal energy consumption simulation data by integrating time series data. The electrical appliance smooth fluctuation energy consumption simulation data and the electrical appliance abnormal fluctuation energy consumption simulation data are energy-collected to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation. The energy consumption collection technology generates a complete electrical appliance energy consumption simulation result by integrating the smooth and abnormal energy consumption simulation data.

[0125] The beneficial effect of the present invention is that by acquiring and preprocessing electrical data, thermodynamic data and mechanical data, electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values ​​are generated. This process not only extracts the key characteristics of various types of data, but also lays a solid data foundation for subsequent steps. These characteristic engineering values ​​are mapped to three-dimensional space to generate three-dimensional point cloud data, and through morphological surface analysis, the complex relationship and change law of electrical characteristics in the spatial dimension are further extracted. This not only improves the expressiveness of the data, but also enables the digital twin model to more accurately reflect the operating status of the actual system. By using the generated digital twin model, the real-time operation data of the electrical appliance is traced to the source of electric energy, and the dual calculation of electrical appliance energy consumption calculation and time component loss simulation is completed accordingly. This process enables the energy consumption data set to be fully simulated and analyzed in the time dimension, providing a reliable basis for the long-term energy consumption trend prediction of electrical appliances. Subsequently, step S4 further deepens the accuracy and optimization of energy consumption calculation. By extracting and analyzing the energy consumption trajectory path, the sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations were identified, and then the section energy consumption was selected and integrated and the smooth section energy consumption was simulated. The final electrical energy consumption simulation data was generated through the energy consumption set. This series of operations ensures the accuracy and efficiency of energy consumption optimization calculation by separating and processing abnormal and smooth sections.

[0126] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0127] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for calculating electrical appliance energy consumption based on a digital twin model, characterized in that: The following steps are involved: Step S1: Acquire electrical data, thermodynamic data and mechanical data; perform data preprocessing on the electrical data, thermodynamic data and mechanical data to generate electrical energy characteristic engineering values, thermal energy characteristic engineering values ​​and mechanical characteristic engineering values; Step S2: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to three-dimensional space to generate three-dimensional point cloud, thereby generating electrical appliance characteristic point cloud data; performing morphological surface analysis on the electrical appliance characteristic point cloud data to generate electrical appliance surface analysis data; establishing a digital twin model based on the electrical appliance surface analysis data to generate an electrical appliance digital twin model; Step S3: Use the electrical appliance digital twin model to trace the power energy source of the real-time operation data to generate a power energy traceability result; calculate the electrical appliance energy consumption based on the power energy traceability result to generate an electrical appliance energy consumption data set; Perform dual calculation of time component loss simulation on the electrical appliance energy consumption data set to generate the electrical appliance energy consumption calculation results; Step S4: extracting energy consumption trajectory paths from the electrical appliance energy consumption calculation results to generate energy consumption trajectory paths; Extract data of abnormal and smooth sections of energy consumption trajectory paths to generate sections with abnormal energy consumption fluctuations and sections with smooth energy consumption fluctuations; For sections with abnormal energy consumption fluctuations, energy consumption is selected and integrated to generate electrical appliance energy consumption simulation data with abnormal fluctuations. For sections with smooth energy consumption fluctuations, smooth energy consumption fluctuations are screened to generate optimal energy consumption selection section data. For the optimal energy consumption selection section data, smooth section energy consumption section simulation is performed, and energy consumption is aggregated with the electrical appliance energy consumption simulation data with abnormal fluctuations to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

2. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: acquiring electrical data, thermodynamic data and mechanical data through sensors, wherein the electrical data includes power factor and electric energy, the thermodynamic data includes thermal expansion coefficient and cooling efficiency, and the mechanical data includes mechanical efficiency and electrical amplitude rate; Step S12: performing random noise reduction processing on the power factor and electric energy, the thermal expansion coefficient and the cooling efficiency, the mechanical efficiency and the electrical amplitude rate to generate electric energy characteristic noise reduction data, thermal energy characteristic noise reduction data and thermal energy characteristic noise reduction data; performing data standardization processing on the electric energy characteristic noise reduction data, the thermal energy characteristic noise reduction data and the thermal energy characteristic noise reduction data to generate electric energy standardized data, thermal energy standardized data and mechanical standardized data; Step S13: Perform abnormal value identification processing on the electric energy standardized data to generate electric energy characteristic engineering values; perform temperature medium change analysis on the thermal energy standardized data to generate thermal energy characteristic engineering values; perform mechanical structure stress analysis on the mechanical standardized data to generate mechanical characteristic engineering values.

3. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: mapping the electrical energy characteristic engineering value, the thermal energy characteristic engineering value and the mechanical characteristic engineering value to a three-dimensional space according to a preset mapping rule to generate three-dimensional space characteristic data; generating a three-dimensional point cloud according to the three-dimensional space characteristic data to generate electrical mechanical characteristic point cloud data and electrical power thermal energy characteristic point cloud data; Step S22: performing surface fitting representative analysis on the electrical appliance power and thermal energy characteristic point cloud data to generate electrical appliance power and thermal energy surface analysis data; Step S23: Establish a digital twin model of the electrical appliance mechanical characteristic point cloud data, and assign geometric attributes to the electrical appliance power and thermal energy surface analysis data to generate a digital twin model of the electrical appliance.

4. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 3 is characterized in that: Step S22 includes the following steps: Step S221: performing point cloud data segmentation on the electrical appliance power and thermal energy feature point cloud data to generate electrical appliance power and thermal energy point cloud segmentation data; Step S222: performing spline interpolation surface fitting on the electrical appliance power and thermal energy point cloud segmentation data to generate electrical appliance power and thermal energy fitting data; Step S223: Performing morphological characteristic surface analysis on the electrical power and thermal energy fitting data to generate electrical surface analysis data.

5. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to trace the appliance energy source of the real-time operation data to generate an appliance energy traceability result, wherein the appliance energy traceability result includes direct power energy and indirect power energy; Step S32: Calculate the electrical appliance energy consumption based on the electrical appliance energy tracing result to generate an electrical appliance energy consumption data set, wherein the electrical appliance energy consumption data set includes direct electric drive energy and indirect electric drive energy; Step S33: Set an initial loss rate based on historical appliance usage data; perform time step performance decay calculation on the appliance energy consumption data set based on the initial loss rate to generate a stage loss calculation result; perform time loss accumulation on the stage loss calculation result to generate an appliance energy consumption calculation result.

6. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 5, characterized in that: Step S31 includes the following steps: Step S311: Acquire historical appliance usage data and appliance real-time operation data; use the appliance digital twin model to identify the energy category of the appliance real-time operation data and generate an energy category identification result; Step S312: Perform energy source traceability graph analysis on the energy category identification result to generate an electric energy source traceability graph; Step S313: Perform energy consumption classification matching on the electric energy traceability map and the historical appliance usage data to generate an electric energy traceability result, wherein the electric energy traceability result includes direct electric energy and indirect electric energy.

7. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 5, characterized in that: Step S32 includes the following steps: Step S321: Calculate the instantaneous energy consumption of voltage and current for direct electric energy to generate instantaneous power energy consumption data; perform time integration on the instantaneous power energy consumption data to generate electric drive energy consumption data; Step S322: extracting solar energy and wind energy data from indirect electric drive energy to generate solar energy data and wind energy data; extracting light intensity characteristics from photovoltaic solar panels to generate light intensity curve data; performing Monte Carlo simulation on the light intensity curve data and solar energy data to generate solar drive energy consumption data; Step S323: Obtain wind speed change data; perform hidden Markov calculation on the wind speed change data and wind energy data to calculate instantaneous output power and generate wind loss output power; perform state transfer matrix analysis on the wind loss output power and perform time integration to generate wind energy drive energy consumption data.

8. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 5, characterized in that: Step S33 includes the following steps: Step S331: setting an initial loss rate based on historical appliance usage data; performing Weibull distribution attenuation calculation on the appliance energy consumption data set based on the initial loss rate to generate appliance energy consumption attenuation distribution data; Step S332: Connect the distribution nodes of the electrical appliance energy consumption attenuation distribution data in series to generate electrical appliance energy consumption attenuation series data; perform time step performance attenuation calculation on the electrical appliance energy consumption attenuation series data to generate stage loss calculation results; Step S333: Accumulate the time loss of the stage loss calculation results to generate the electrical energy consumption calculation results.

9. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Perform graph theory modeling on the electrical appliance energy consumption calculation results to generate electrical appliance energy consumption state nodes; perform TSP solution on the electrical appliance energy consumption state nodes to generate energy consumption trajectory paths; Step S42: extracting abnormal fluctuation sections from the energy consumption trajectory path to generate abnormal energy consumption fluctuation sections; performing data set difference operation on the abnormal energy consumption fluctuation sections and the energy consumption trajectory path to generate smooth energy consumption fluctuation sections; performing smooth energy consumption fluctuation screening on the smooth energy consumption fluctuation sections to generate optimal energy consumption selected section data; Step S43: Perform a smooth section energy consumption section simulation on the optimal energy consumption section data to generate electrical appliance smooth fluctuation energy consumption simulation data; perform section energy consumption selection integration processing on the section with abnormal energy consumption fluctuation to generate electrical appliance abnormal fluctuation energy consumption simulation data; perform energy consumption aggregation on the electrical appliance smooth fluctuation energy consumption simulation data and the electrical appliance abnormal fluctuation energy consumption simulation data to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

10. The method for calculating electrical appliance energy consumption based on a digital twin model according to claim 9, characterized in that: Step S43 includes the following steps: Step S431: Analyze the energy consumption characteristic curve of the optimal energy consumption selected section data to generate key state node data; estimate the state transition probability of the key state node data to generate electrical appliance energy consumption probability data; simulate the smooth section energy consumption section of the electrical appliance energy consumption probability data to generate electrical appliance fluctuation smooth energy consumption simulation data; Step S432: Performing section energy consumption selection and integration processing on the energy consumption fluctuation abnormal data to generate electrical appliance fluctuation abnormal energy consumption simulation data; Step S433: Energy consumption is aggregated for the electrical appliance energy consumption simulation data with smooth fluctuations and the electrical appliance energy consumption simulation data with abnormal fluctuations to generate electrical appliance energy consumption simulation data, thereby completing the electrical appliance energy consumption optimization calculation.

Images