Digital intelligence prediction system and method for zero-carbon transformation effectiveness of existing building

Abstract

The invention discloses an existing building zero-carbon transformation effectiveness digital intelligence prediction system and method, and relates to the technical field of existing building transformation optimization. The system comprises an information acquisition module which is used for acquiring and storing building model information and time sequence data associated with prediction of zero-carbon transformation effectiveness; the processing and analyzing module is used for processing, mining and fusing multi-source heterogeneous data and then accounting the full-aperture energy consumption active carbon emission; the scheme optimization module is used for formulating an existing building zero-carbon transformation strategy and iterating parameters and algorithms associated with effectiveness prediction; and the evaluation and prediction module is used for evaluating the carbon reduction efficiency of the transformation strategy and predicting the annual energy consumption activity total carbon emission after optimization. According to the method, the zero-carbon transformation effectiveness of the existing building is rapidly predicted by comprehensively applying multiple digital intelligence technologies, the rapid prediction model is established by coupling finite measured data through mathematical simulation, the livable operation carbon footprint distribution of the existing building is checked, and the prediction result is closer to the actual operation effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of existing building renovation optimization, in particular to an existing building zero-carbon renovation effectiveness digital prediction system and method. BACKGROUND

[0002] Unlike qualitative optimization oriented by low carbon and energy saving, building zero-carbon renovation is a quantitative research, which needs to reduce the carbon footprint data of each energy consumption activity in a targeted manner. However, current zero-carbon design schemes mostly rely on empirical description or focus on local optimization of a single indicator. For example, CN117688658B discloses evaluation indicators, criteria and carbon reduction suggestions for each stage of the building life cycle, and CN116663412B discloses an optimization method and system based on deep learning technology for building layout, but there is still a lack of objective and quantitative tools to verify whether a building can achieve zero-carbon operation. Therefore, the existing building zero-carbon renovation effectiveness prediction mainly faces the following challenges: intervention on the normal operation of the building should be reduced, and the principle of light intervention should be followed; a large number of existing buildings lack technical drawings and standard building management standards, and reverse digital modeling information acquisition is complex; the relevant parameters for predicting the carbon footprint of building operation are multi-source and heterogeneous, and depend on scattered tools, which are difficult to integrate; the real operation state of some buildings is dynamic and complex (such as the actual behavior of personnel), and the prediction results of existing prediction tools (such as EnergyPlus) deviate greatly from the actual situation. Therefore, the present application proposes an existing building zero-carbon renovation effectiveness digital prediction system and method. SUMMARY

[0003] The present application aims to provide an existing building zero-carbon renovation effectiveness digital prediction system and method to solve the problems raised in the background.

[0004] According to the first aspect of the present application, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme: an existing building zero-carbon renovation effectiveness digital prediction system, comprising the following steps: An information collection module is used to collect and store multi-source and heterogeneous data related to the prediction of zero-carbon renovation effectiveness, wherein the multi-source and heterogeneous data includes static building model information and dynamic time series data; A processing and analysis module is used to process, mine and fuse multi-source and heterogeneous data, and then calculate the carbon emissions of all energy consumption activities; A scheme optimization module is used to develop a zero-carbon renovation strategy for existing buildings, and iteratively predict the parameters and algorithms related to effectiveness; An evaluation and prediction module is used to evaluate the carbon reduction efficiency of the renovation strategy and predict the total carbon emissions of energy consumption activities in a year after optimization.

[0005] Further, the information collection module includes a model mapping layer and a parameter perception layer: The model mapping layer is used to collect building macro information and three-dimensional surface data through global positioning system, remote sensing, geographic information system, unmanned aerial oblique photography technology and three-dimensional laser scanning technology, and to perform three-dimensional reverse digital information modeling and storage based on BIM technology, and the output is static building model information; The parameter perception layer is used to collect time series data of building operation carbon footprint related parameters, including outdoor meteorological data, indoor physical environment data and user positioning data, through Internet of Things sensors and Bluetooth beacons, and to transmit and store the data to a non-relational time series database through a cloud computing platform, and the output is dynamic time series data. The outdoor meteorological data includes air temperature and humidity, illumination, wind speed and direction, and rainfall; the indoor physical environment data includes air temperature, radiant temperature, illumination, wind speed and direction, and air pollutants.

[0006] Further, the processing and analysis module includes a data mining layer and an accounting analysis layer: The data mining layer is used to receive the original time series data output by the information collection module, clean and denoise through programming language, and construct an indoor environment prediction model using computational fluid dynamics, Radiance numerical simulation software and RBF-ANN algorithm, and output processed multi-source heterogeneous data. The indoor environment prediction model includes an input layer, a hidden layer and an output layer, and the indoor environment prediction model is trained using the following loss function: Wherein yi is the true value, is the predicted value, and N is the number of samples. The accounting analysis layer is used to receive the multi-source heterogeneous data processed by the data mining layer and the static parameters in the BIM model, divide the data based on the temperature frequency method, and calculate the carbon emissions using the full-range energy consumption activity carbon emission accounting algorithm, and the output is the building operation stage carbon emissions C, which is as follows: The carbon emissions of existing buildings in the operation stage are set as C, and the process is as follows: In the formula, C C represents the carbon emissions of building refrigeration energy consumption, C W represents the carbon emissions of building heating energy consumption, C L represents the carbon emissions of building lighting energy consumption, C V represents the carbon emissions of building ventilation energy consumption, C E represents the carbon emissions of building elevator energy consumption, CH representative of the building's carbon emissions from hot water use, C K representative of the building's carbon emissions from cooking use, C S representative of the building's carbon emissions from plug loads, C R representative of the building's carbon emissions from all renewable energy reductions, C G representative of the building's carbon emissions from all green plant carbon sink systems; wherein the variables C R The remaining carbon emissions from multiple use activities are calculated by embedding the DesignBuilder building performance simulation software into the BIM model, combining measured meteorological data for estimation, and obtaining the formula as follows: wherein, C i representative of the building's carbon emissions from each type of use activity, T i,j is the carbon emissions from the first use activity in the building, j i is the duration of the W i,j is the energy consumption of the use equipment per unit time for this activity, EF i,j is the carbon emission factor of the energy consumed this time; Among them, the assignment of variables related to refrigeration, heating, lighting, and ventilation use activities T i,j refers to the user positioning data and physical environment data, that is, the length of time when a certain physical environment index in the room does not meet the livable standard and there is a user in the space; the assignment of variables related to elevator, hot water, cooking, and plug load use activities T i,j and the energy consumption of all use equipment per unit time for all activities are based on field research and estimation; W i,j C G The formula for obtaining wherein, m is the total number of plant species in the building, f l is the carbon reduction per unit time area of the l th plant, A l is the planting area of the l th plant, t is the accounting duration.​​

[0007] Further, the scheme optimization module comprises a retrofit design layer and an iterative updating layer: The retrofit design layer is configured to formulate a zero-carbon retrofit scheme by a computational design method based on the carbon emission accounting result of the processing and analysis module, specifically including passive form optimization, active energy system updating, and implantation of a smart operation and management control system, and the output is the optimized retrofit scheme. The iterative updating layer is configured to receive the scheme of the retrofit design layer, update the building information, energy-using equipment parameters, and green plant carbon sink data in the BIM model, and calibrate the indoor environment prediction model and the carbon emission accounting algorithm, and the output is the iteratively updated carbon emission accounting algorithm and parameters.

[0008] Further, the evaluation and prediction module is configured to receive the iteratively updated parameters and algorithm of the scheme optimization module, step-by-step evaluate the carbon emission reduction amount of the passive optimization and active optimization strategies for energy-using activities, and predict the renewable energy production capacity and total annual carbon emission based on the full-year measured meteorological data by using a building performance simulation software, and output the zero-carbon retrofit effectiveness prediction result.

[0009] According to the second aspect of the present application, the present application provides a zero-carbon retrofit effectiveness digitalization prediction method for existing buildings, which adopts the zero-carbon retrofit effectiveness digitalization prediction system for existing buildings described in the first aspect, and comprises the following steps: S1: receiving and storing the building model information and building operation carbon footprint associated parameter time series data related to the prediction of zero-carbon retrofit effectiveness; S2: cleaning and denoising, mining analysis, and correlation fusion are performed on the building model information and time series data received in S1 to obtain multi-source heterogeneous data, and the full-range carbon emission of energy-using activities is calculated based on the multi-source heterogeneous data, and the carbon emission accounting result is outputted; S3: based on the carbon emission accounting result of S2, a zero-carbon retrofit strategy for existing buildings is formulated, and the indoor environment prediction model parameters and the carbon emission accounting algorithm are iteratively updated, and the optimized retrofit strategy and calibrated parameters are outputted; S4: receiving the updated parameters of S3, evaluating the carbon reduction efficiency of the retrofit strategy, predicting the total carbon emission of energy-using activities in a year after optimization, and outputting the effectiveness prediction result.

[0010] Further, the building model information and building operation carbon footprint associated parameter time series data related to the prediction of zero-carbon retrofit effectiveness received and stored in step S1 are as follows: S11. Based on the model mapping layer, the building macro information and three-dimensional surface data are collected by using global positioning system, remote sensing, geographic information system, unmanned aerial oblique photography technology, and three-dimensional laser scanning technology, and the three-dimensional reverse digital information model is modeled and stored based on BIM technology; S12. Based on the parameter perception layer, the time series data of building operation carbon footprint related parameters are collected through Internet of Things sensors and Bluetooth beacons, including outdoor meteorological data, indoor physical environment data and user positioning data, and are transmitted and stored to a non-relational time series database through a cloud computing platform; Among them, the outdoor meteorological data includes air temperature and humidity, illumination, wind speed and direction, and rainfall; the indoor physical environment data includes air temperature, radiant temperature, illumination, wind speed and direction, and air pollutants.

[0011] Further, in step S2, the building model information and time series data are cleaned, denoised, analyzed and fused to obtain multi-source heterogeneous data, and the carbon emissions of all-capacity energy activities are calculated according to the multi-source heterogeneous data, and the carbon emission calculation results are output, as follows: S21. Based on the data mining layer, the original time series data output by the information collection module are received, cleaned and denoised through programming language, and indoor environment prediction models are constructed by using computational fluid dynamics, Radiance numerical simulation software and RBF-ANN algorithm, and the processed multi-source heterogeneous data are output; Among them, the indoor environment prediction model includes an input layer, a hidden layer and an output layer, and the indoor environment prediction model is trained by using the following loss function: Among them yi is the true value, is the predicted value, and N is the sample number; S22. Based on the accounting analysis layer, the multi-source heterogeneous data processed by the data mining layer and the static parameters in the BIM model are received, the data is grouped based on the temperature frequency method, and the all-capacity energy activity carbon emission calculation algorithm is used to calculate the carbon emissions, as follows: The carbon emissions of existing building operation stage are set as C, and the process is as follows: In the formula, C C represents the carbon emissions of building refrigeration energy, C W represents the carbon emissions of building heating energy, C L represents the carbon emissions of building lighting energy, C V represents the carbon emissions of building ventilation energy, C E represents the carbon emissions of building elevator energy, C H represents the carbon emissions of building hot water energy, C K represents the carbon emissions of building cooking energy,C S Carbon emission of energy use of building, C R Carbon emission of renewable energy reduction of building, C G Carbon emission of green plant carbon sink system reduction of building; Wherein the variable C R Through BIM model implantation of DesignBuilder building performance simulation software, fusion of measured meteorological data for estimation, the remaining multi-class energy use activity carbon emission amount obtains formula: In the formula, C i Carbon emission of each type of energy use activity of building, T i,j For the first j Space of existing building i Class energy use activity duration, W i,j Energy consumption of energy use equipment per unit time for this activity, EF i,j Carbon emission factor of the energy consumed this time; Among them, the assignment of variables related to refrigeration, heating, lighting, ventilation energy use activities T i,j Reference to user positioning data and physical environment data, that is, when the indoor physical environment index does not meet the livable standard and the length of the time range when the space exists the user; The assignment of variables related to elevator, hot water, cooking, socket energy use activities T i,j And all activity-related energy use equipment unit time energy consumption W i,j Are based on field research to obtain and estimate; C G The formula for obtaining is: In the formula, m Total number of plant species in building, f l Carbon reduction per unit time area of the l Plant, A l Planting area of the l Plant, t Accounting duration.

[0012] Further, step S3 is based on the carbon emission accounting result, formulates the existing building zero carbon reconstruction strategy, and iteratively updates the indoor environment prediction model parameter and the carbon emission accounting algorithm, and outputs the optimized reconstruction strategy and the calibrated parameter, as follows: S31. Based on the reconstruction design layer, a zero-carbon reconstruction scheme is formulated by using a computational design method based on the carbon emission accounting result, specifically including passive form optimization, active energy system updating, and implantation of intelligent operation and management control system; S32. Based on the iterative update layer, the building information in the BIM model, the energy-using equipment parameters and the green plant carbon sink data are updated based on the scheme received from the reconstruction design layer, and the indoor environment prediction model and the carbon emission accounting algorithm are calibrated.

[0013] Further, in step S4, the updated parameters are received, the carbon reduction efficiency of the reconstruction strategy is evaluated, the total carbon emission of the optimized annual energy-using activity is predicted, and the effectiveness prediction result is output, as follows: The parameters and algorithms iterated by the scheme optimization module are received, the carbon emission reduction of the passive optimization and active optimization strategies on the energy-using activity is evaluated in steps, and based on the annual measured meteorological data, the renewable energy production capacity and the total annual carbon emission are predicted by using the building performance simulation software, and the zero-carbon reconstruction effectiveness prediction result is output.

[0014] The present application has at least the following advantages: 1. The present application can advance the verification of building zero-carbon operation from "after reconstruction" to "before reconstruction", through scientific prediction and evaluation, help decision-makers to clarify the effectiveness of the reconstruction scheme before implementation, thereby greatly reducing the investment risk caused by failed or ineffective reconstruction, optimizing resource allocation, and avoiding unnecessary waste of funds.

[0015] 2. The present application proposes a method for sensing and storing complex model information and multi-element time series data of existing buildings based on BIM, Internet of Things, big data and other digital technologies. The method has high collection efficiency, can quickly and accurately obtain building model information and operation carbon footprint correlation parameters without damaging the structure and function of the building body, minimizes the intervention to the existing building body, protects the original value of the building, and is especially suitable for existing buildings with historical value or special significance.

[0016] 3. The present application establishes a rapid prediction model by coupling mathematical simulation with limited measured data to account for the carbon footprint distribution of the livable operation of existing buildings. Compared with traditional simulation software, the prediction result of the present application is closer to the actual operation effect, with an error range of less than 10%. This high-precision prediction capability can provide more reliable basis for zero-carbon reconstruction, and ensure that the reconstructed building can truly achieve the zero-carbon operation target.

[0017] 4. The retrofitting scheme carbon reduction performance step-by-step evaluation method can quickly simulate and compare the emission reduction effects of different technical strategies, which changes the current situation of qualitative description of existing zero-carbon retrofit design, enables decision makers to flexibly select retrofit measures based on the effectiveness of zero-carbon retrofit, and formulates the optimal retrofit path to improve the feasibility and implementation effect of the retrofit scheme.

[0018] 5. The existing building zero-carbon retrofit effectiveness prediction system and method has low intervention degree to the building body, does not affect the normal use and structural safety of the building, has high evaluation efficiency, can complete the comprehensive evaluation of the retrofit scheme in a short time, has small prediction error, provides accurate data support for retrofit decision, has low operation cost, can be implemented without complex equipment and a large number of professional personnel, is applicable to various types of existing buildings, and has strong scientificity and practicality.

[0019] Of course, implementing any product of the present application does not necessarily require all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a system block diagram of the prediction system described in the present application; Figure 2 is a technical route schematic diagram of the prediction system described in the present application; Figure 3 is a zero-carbon retrofit effectiveness prediction result schematic diagram, wherein (a) is a passive retrofit measure effectiveness and annual carbon emission amount sub-item prediction, (b) is a DesignBuilder-based example photovoltaic tile annual power generation estimation, and (c) is a zero-carbon retrofit effectiveness prediction; Figure 4 is a flowchart of the prediction method described in the present application; Figure 5 is a schematic diagram of the indoor microclimate physical environment simulation data dimensionality reduction and discrete processing result in the present application; Figure 6 is a structure schematic diagram of the indoor environment prediction model in the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present disclosure.

[0022] Embodiment one: Related term explanation: Electric Load Satisfied: Electric load satisfaction forecast.

[0023] Fuel-fired Power Generation: Fuel power generation.

[0024] High Temperature Geothermal: High temperature geothermal power generation.

[0025] Photovoltaic Power: Photovoltaic power generation.

[0026] Wind Power: Wind power generation.

[0027] RBF-ANN algorithm: A hybrid model combining radial basis function (RBF) and artificial neural network (ANN).

[0028] Please refer to Figures 1-3 The present application provides a technical solution: a zero-carbon retrofit effectiveness digital prediction system for existing buildings, comprising: Information acquisition module: for acquiring and storing building model information and time series data related to zero-carbon retrofit effectiveness prediction; The information acquisition module includes a model mapping layer and a parameter perception layer, corresponding to the following steps: Step S1: Collect and store static model information related to zero-carbon retrofit of existing buildings; Step S2: Collect and store dynamic time series data related to building operation carbon footprint parameters; Step S1 specifically includes: First, the Global Positioning System (GPS), remote sensing (RS), geographic information system (GIS) (3S technology) and unmanned aerial oblique photography technology are used to collect macro information such as the geographic location and overall surrounding environment of existing buildings, and to position the volume relationship between water features, green spaces, buildings and infrastructure; Then use the point cloud technology-based three-dimensional laser scanning technology to efficiently obtain three-dimensional information of building surfaces through computer perspective logic and realize three-dimensional mapping; In view of the limitations of three-dimensional scanners in collecting external model data such as roof, aerial survey technology based on oblique photography is used to make up for it; Then, through field visits and field research, information such as building materials, operating characteristics, and energy-using equipment attributes is collected; Finally, based on BIM technology, combined with on-site investigation, a three-dimensional reverse digital information model is built to store all static model information related to zero-carbon retrofit of existing buildings; Step S2 specifically includes: Based on the Internet of Things technology, the integrated sensor, Bluetooth beacon and other intelligent instruments are used to automatically and real-time perceive the multi-element time series data in the whole period. Then, the cloud computing platform is used to transmit the multi-source heterogeneous data. Finally, based on the big data technology, the non-relational database targeting the object-oriented database is used to process and store the massive time series data in the distributed environment. The required building operation carbon footprint related parameters mainly include: outdoor meteorological data, including air temperature and humidity, illumination, wind speed and direction, rainfall, etc.; indoor physical environment data, including air temperature, radiation temperature, illumination, wind speed and direction, air pollutants, etc.; and user positioning data. The performance of the physical environment collection instrument should meet the accuracy, range and response time requirements specified in the international standard ISO 7726. In terms of sensing instrument layout, the physical environment collection device is preferably 2-3, and is integrated and boxed with waterproof and flame-retardant materials. The selected points should avoid as much as possible the interference of human behavior activities on the data. The user position information sensing should first use mathematical simulation algorithms such as clustering analysis, spatial interpolation and computational fluid dynamics (CFD) to divide the space, and then install the collection device one by one. Processing and analysis module: for processing, mining, and fusing multi-source heterogeneous data, and then calculating the carbon emissions of all-inclusive energy activities; The processing and analysis module includes a data mining layer and an accounting and analysis layer, corresponding to the following steps: Step S3: multi-source heterogeneous data cleaning, noise reduction, mining analysis, correlation fusion Step S4: accounting of carbon emissions of all-inclusive energy activities in the building operation stage Step S3 specifically includes: First, use PYTHON, MATLAB and other programming languages to clean and denoise the original time series data. Then, for dynamic and non-uniformly distributed microclimate physical environment indicators such as temperature and humidity, pollutants, etc., use CFD, Radiance and other numerical simulation software to repeatedly simulate with multiple sets of measured physical environment data as boundary conditions, and perform dimensionality reduction and dispersion on the environment values in each cluster space of the existing building. A multi-source heterogeneous database is constructed, machine learning methods are used to train the function relationship of the database, and then outdoor meteorological data is used as the input end of the prediction model. According to the model training results, the indoor space environment parameters are quickly predicted, so as to realize the implementation prediction of indoor multiple dynamic physical environments. Finally, use SPSS, EXCEL and other statistical software to fuse and correlate multi-source time series data according to time sequence, and use the Bin-method to group and divide the multi-source heterogeneous data, while integrating the static parameters and thresholds related to the operation carbon emission accounting in the BIM model, so as to improve the statistical efficiency. Specifically, the prediction process of the indoor environment prediction model is as follows: In order to solve the problem that the limited monitoring point data cannot represent the dynamic non-uniform distribution of microclimate physical environment states such as temperature and humidity, pollutants and the like in each space in the residential building, as shown in Figure 5 , first, based on the building model clustering division result, a plurality of indoor environment such as velocity field, temperature field and concentration field obtained by using computational simulation technology is discretely cut, the differential equation for controlling fluid flow is solved by using differential thought value, and the discrete distribution of the environmental flow field on the continuous region in space is mined. Further, the data group in the clustered space is processed by mean dimension reduction, and low-dimensional linear data is obtained in units of space. By repeatedly simulating a plurality of environment fields with different boundary conditions, an indoor space environment database is constructed, a suitable machine learning algorithm model is used to train the database, and then the measured data of the monitoring point space is used as the input parameter, and the corresponding environmental parameter value of each space is calculated through the trained function, so that the rapid prediction of the indoor multi-physical environment parameter is realized. , as shown in Figure 6 , the indoor environment prediction model is constructed by using RBF-ANN algorithm, including input layer, hidden layer and output layer, and the indoor environment prediction model is trained by using the following loss function: , wherein yi is the true value, is the predicted value, and N is the sample number; Step S4 is specifically: The carbon emission of the existing building in the operation stage is set as C, and the process is as follows: , wherein C C represents the carbon emission of building refrigeration energy consumption, C W represents the carbon emission of building heating energy consumption, C L represents the carbon emission of building lighting energy consumption, C V represents the carbon emission of building ventilation energy consumption, C E represents the carbon emission of building elevator energy consumption, C H represents the carbon emission of building hot water energy consumption, C K represents the carbon emission of building cooking energy consumption, C S represents the carbon emission of building socket energy consumption, C R represents the carbon emission of building renewable energy consumption, C GCarbon emissions reduced by all green plants carbon sink system of the building; wherein wherein C R Carbon emissions reduced by all renewable energy of the building, mainly rely on building performance simulation software for prediction, DesignBuilder as a professional and independent software, provides data interface (gbXML) for BIM model, can be directly linked with the BIM model established in this system, DesignBuilder has a user-friendly modeling interface, almost all the index parameters required for building performance optimization. The software has high integration, is the most ideal and mature prediction tool, for common renewable energy systems (photovoltaic, geothermal, wind energy, etc.), Designbuilder has reserved adjustable parameter interface, can predict the annual power generation by adjusting the key parameters Figure 3 (b); taking photovoltaic system as an example, DesignBuilder can implant actual project location, meteorological data, etc., combined with imported BIM model to complete scene setting, and then adjust the parameters of photovoltaic panel elements (such as manual input of photoelectric conversion rate based on actual photovoltaic panel performance), that is, the annual photovoltaic power generation can be predicted by simulation; The formula for obtaining the carbon emissions of various energy-using activities is: In the formula, C i The carbon emissions of various energy-using activities of the building are represented by T i,j The carbon emissions of the first j space of the existing building are represented by i the length of time of various energy-using activities, W i,j the energy consumption of the energy-using equipment per unit time, EF i,j and the carbon emission factor of the energy consumed; wherein, the assignment of variables related to refrigeration, heating, lighting, and ventilation energy-using activities T i,j needs to refer to the user positioning data and physical environment data, that is, when the indoor physical environment index does not meet the livable standard and the space exists for the length of time of the user; the assignment of variables related to elevator, hot water, cooking, and socket energy-using activities T i,j and the energy consumption of all activity-related energy-using equipment per unit time W i,j are based on field research and estimation; the energy carbon emission factor EF i,j value is obtained from the national standard "Building Carbon Emission Calculation Standard" (GB / T 51366-2019); C G The formula for obtaining it is: In the formula, m This represents the total number of vegetation species within the building. f l For the first l Carbon reduction per unit area of ​​plantations over time A l For the first l Planting area of ​​plants t For the calculation duration; among which, variables f l Obtained by consulting relevant materials. A l The numerical values ​​are acquired and stored in the BIM model during the model information acquisition phase.

[0029] In summary, based on the coupling of field surveys, measured data and mathematical simulations in steps S1-S3, it is possible to assign values ​​to all necessary variables for carbon footprint accounting. Then, statistical software can be used to assess and analyze the carbon footprint distribution of energy-consuming activities in different time periods and spaces, thereby clarifying the focus and objectives of zero-carbon retrofitting of existing buildings and promoting the formulation of retrofitting strategies. Solution optimization module: used to formulate zero-carbon retrofit strategies for existing buildings and iteratively predict the parameters and algorithms associated with effectiveness; The solution optimization module is characterized by comprising a modification design layer and an iterative update layer, each corresponding to the following steps: Step S5: Zero-carbon oriented multi-dimensional computational retrofit design of existing buildings Step S6: Update and calibrate building operation carbon footprint correlation parameters and algorithms Step S5 is as follows: Based on the existing building energy saving reconstruction design process of "passive priority, active optimization, intelligent control", passive design is preferred, according to the climate characteristics and site conditions of the existing building, the thermal elements such as form, space and interface in different dimensions are adjusted to realize climate adaptability regulation and improve the building operation performance, then the active technology is used to optimize the energy system structure, including renewable energy system replacing primary energy, high energy efficiency intelligent terminal equipment and carbon balance and regulation technology, finally the intelligent operation and control system is implanted, the advanced monitoring and control devices are applied to realize the digital control of various energy using systems of the building operation, and the actual application condition of the building is ensured to operate according to the designed scheme; The overall zero-carbon reconstruction design of the existing building should refer to the performance-based design method given in the national standard "Technical standard for near zero energy consumption building" GB / T51350-2019, based on the computational design principle, the sensitivity of the index parameters is analyzed based on quantitative analysis, the design strategy and design parameters are optimized and iterated through repeated calculation, so as to find the design scheme meeting the performance target; Step S6 is specifically: Based on the reconstruction design method given in step S5, the building information, energy using system, equipment performance and green plant carbon sink and other building operation carbon footprint related parameters in the BIM model are updated, at the same time, the indoor physical environment prediction model in step S3 is calibrated based on the topological relationship of the reconstructed building space, and finally the all-inclusive energy using activity carbon emission accounting algorithm in step S4 is iterated; The evaluation and prediction module is used to evaluate the carbon reduction efficiency of the reconstruction strategy, and predict the total carbon emission of the optimized annual energy using activity: The evaluation and prediction module includes the efficiency evaluation layer, which corresponds to the following steps: Step S7: Step-by-step evaluation of zero-carbon reconstruction strategy efficiency and effectiveness prediction Step S7 is specifically: Based on the all-inclusive energy using activity carbon emission accounting algorithm updated in S6, the carbon emission reduction amount of different reconstruction strategies of passive optimization design and active energy optimization for different energy using activities is estimated step by step. Based on the measured meteorological data throughout the year, the building performance simulation software such as DesignBuilder is used to estimate the energy production capacity of various renewable energy sources, so as to predict the annual building operation carbon emission and the effectiveness of zero-carbon reconstruction. If the reduction amount is greater than the carbon emission of the building operation before reconstruction, the decision maker can select the reconstruction strategy according to the demand, or introduce energy storage or surplus electricity feeding back to the grid technology, so that the existing building becomes a power generation building.

[0030] Next, the technical solutions of the present application will be further described in combination with specific embodiments: The present application intends to take a certain well type traditional residence in a province as an embodiment to predict the effectiveness of zero-carbon reconstruction, and the implementation technical route is as shown in Figure 2 The following steps are included: The information collection module comprises a data mining layer and an accounting analysis layer, and comprises the following steps: Step S1: collecting and storing model information related to zero-carbon reconstruction of existing buildings.

[0031] Firstly, based on geographic information system and unmanned aerial oblique photography technology, the geographic coordinates and overall surrounding environment data of the embodiment are collected, and a site model is preliminarily established based on Trimble Sketchup software. Then, Trimble X7 three-dimensional laser scanner is used to obtain three-dimensional coordinate point cloud data of the residence, and the point cloud data is integrated with the unmanned aerial vehicle collection point cloud data. Trimble Realworks is used to extract the point cloud model and link it with Trimble Sketchup, and three-dimensional reverse modeling of the embodiment is completed. The Sketchup model is imported into Revit based on IFC format, and the information such as building materials, resident information, and energy-using equipment attributes obtained through field visits and field research is stored in the BIM model. The static model information related to zero-carbon reconstruction of all embodiments is shown in Table 1: Table 1: Information collection content of zero-carbon reconstruction related model of the embodiment Step S2: sensing and storing time sequence data related to building operation carbon footprint parameters.

[0032] In the embodiment, the outdoor weather station, integrated physical environment sensor, Bluetooth beacon and other Internet of Things are used to collect carbon footprint related time sequence parameters (Table 2), and Aliyun is used for transmission. It needs to be further explained that in the specific implementation process, the integrated physical environment sensor in the embodiment is processed by iron box sealing, and is fixed on the porch wooden column by using a hoop, so as to reduce the interference of human behavior activities on data collection and avoid damage to cultural heritage components. Considering the use function and clustering analysis result, the space of the embodiment is divided, the Bluetooth beacon device is arranged in each space, the Bluetooth information is collected based on the smart phone used by the resident, and the PDR algorithm is used to confirm the position of the user in combination with the space constraint information and signal strength of the embodiment; the frequency of all mass data collection is 0.5h / time, and InfluxDB time sequence database is used for storage; Table 2: Information collection content of carbon footprint related time sequence parameters in the embodiment The processing and analysis module comprises a data mining layer and an accounting analysis layer, and comprises the following steps: Step S3: multi-source heterogeneous data cleaning, noise reduction, mining analysis, correlation fusion; The embodiment first uses MATLAB R2021a to clean and denoise the original time series data. Then, for dynamic non-uniformly distributed microclimate physical environment indicators such as temperature, humidity, and pollutants, the embodiment uses the famous CFD simulation software ANSYS Fluent and the light environment simulation software Radiance to perform physical environment numerical simulation. The data is processed by dimensionality reduction and discretization method and a multi-source heterogeneous database is constructed. Further, the RBF artificial neural network algorithm in the embodiment completes data mining and function relationship training. The outdoor meteorological data is used as the input end of the prediction model, and the indoor environmental parameters are quickly predicted according to the model training results, so as to realize the implementation prediction of various dynamic physical environments in the room. Finally, the IBM SPSS V26.0 statistical software is used to arrange and fuse the correlation multi-source time series data in time sequence, and the Bin-method is used to group and divide the multi-source heterogeneous data. The data is grouped from the minimum value to the maximum value according to the step distance of 0.5. At the same time, the static parameter values related to the operation carbon emission accounting such as energy-using equipment power, green land carbon sink, clean energy and the like are also stored into the statistical software.

[0033] Step S4: Carbon emission accounting of all energy-using activities in the building operation phase.

[0034] The carbon emission of the existing building in the operation phase is set as C, and the process is as follows: In the formula, C C represents the carbon emission of building refrigeration energy consumption, C W represents the carbon emission of building heating energy consumption, C L represents the carbon emission of building lighting energy consumption, C V represents the carbon emission of building ventilation energy consumption, C E represents the carbon emission of building elevator energy consumption, C H represents the carbon emission of building hot water energy consumption, C K represents the carbon emission of building cooking energy consumption, C S represents the carbon emission of building socket energy consumption, C R represents the carbon emission reduced by all renewable energy of the building, C G represents the carbon emission reduced by all green plant carbon sink systems of the building; In the embodiment, there is no elevator and clean energy, C E 、 CR The variable value is 0. The formulas for obtaining carbon emissions from various energy-consuming activities are: In the formula, C i Represents the carbon emissions from various energy-consuming activities in buildings. T i,j For existing buildings j Each space i Energy usage activity duration, W i,j This refers to the energy consumption per unit time of the energy-consuming equipment during this event. EF i,j This refers to the carbon emission factor of the energy consumed in this activity; among which, variables related to energy consumption activities for cooling, heating, lighting, and ventilation are included. T i,j The values ​​assigned need to refer to user location data and physical environment data, that is, the length of time during which a certain physical environment indicator in the room does not meet the livability standard and users are present in the space. In this embodiment, the livability standard is obtained with reference to the national standard "Technical Standard for Near-Zero Energy Buildings" (GB / T 51350-2019); variables related to hot water, cooking, and socket energy consumption activities. T i,j The assigned values ​​and the energy consumption per unit time of all energy-consuming equipment related to the activities. W i,j All data were obtained and estimated based on field research; energy carbon emission factors EF i,j The numerical values ​​were obtained with reference to the national standard "Standard for Calculation of Carbon Emissions from Buildings" (GB / T 51366-2019). C G The formula for obtaining it is: In the formula, m This represents the total number of vegetation species within the building. f l For the first l Carbon reduction per unit area of ​​plantations over time A l For the first l Planting area of ​​plants t For calculation duration. In this embodiment, the variable is... f l This information was obtained by consulting data from the Shanghai Botanical Garden and Chenshan Botanical Garden, which constructed a carbon sequestration database of 215 common garden plants. A l The numerical values ​​have been acquired and stored in the BIM model during the model information acquisition phase.

[0035] In summary, based on the field surveys, measured data, and mathematical simulations in steps S1-S3, this embodiment assesses and analyzes the carbon footprint distribution of energy-consuming activities in different time periods and spaces. This clarifies that this embodiment should emphasize passive design and renovation of indoor spaces, the integration of modern energy systems and the acceleration of equipment electrification, and the introduction of renewable energy as key elements of zero-carbon transformation, thereby promoting the formulation of transformation strategies.

[0036] The solution optimization module includes a redesign layer and an iterative update layer, and includes the following steps: Step S5: Zero-carbon oriented multi-dimensional computational retrofit design of existing buildings This design process for energy-saving retrofitting of existing buildings is based on the principles of "passive priority, active optimization, and intelligent management." The passive design in this embodiment includes double-layer lightweight wood wall cladding, raised wooden flooring, and form optimization design that couples ventilation and lighting. DesignBuilder is used to refine multi-objective coupled optimization schemes for this embodiment, iterating and optimizing form parameters through repeated calculations to quantitatively identify the optimal performance design strategy. Next, active technologies are used to optimize the energy system structure, including the introduction of rooftop photovoltaic tiles, intelligent ventilation fans, variable frequency intelligent fans, variable-dimmable LED energy-saving artificial lighting, solar thermal systems, and biomass pellet stoves. Finally, a digital twin intelligent operation and maintenance management platform is developed for this embodiment, enabling intelligent management of the energy system through various intelligent remote control devices.

[0037] Step S6: Update and calibrate building operation carbon footprint correlation parameters and algorithms Based on the renovation design method given in step S5, the building interface attributes, photovoltaic power generation system, high-tech energy-consuming equipment and green plant carbon sink area of ​​the zero-carbon renovation in this embodiment are updated in the BIM model. At the same time, the indoor physical environment prediction model in step S3 is calibrated based on the renovated building space form. Finally, the updated parameter values ​​and algorithms are iterated into the full-caliber energy activity carbon emission accounting algorithm in step S4.

[0038] The evaluation and prediction module includes a performance evaluation layer, comprising the following steps: Step S7: Step-by-step evaluation and effectiveness prediction of zero-carbon retrofit strategy Based on the S6-updated algorithm for carbon emissions from all energy-consuming building activities, the zero-carbon retrofit efficiency of this embodiment can be quickly predicted and evaluated. For example... Figure 3 As shown in (a), the reduction in carbon emissions and its proportion due to passive design and active energy consumption equipment optimization for different energy-consuming activities throughout the year in this embodiment can be quickly calculated using statistical software. Then, by embedding the annual measured meteorological data into DesignBuilder, the annual power generation of the rooftop photovoltaic tile system can be estimated.Figure 3 (b) ). Finally, if the building is optimized according to the zero-carbon retrofit strategy, the predicted annual building operation carbon emissions are-1373.918 kg, that is, the zero-carbon retrofit scheme is effective ( Figure 3 (c) ). Since the predicted annual operation carbon emissions are negative, this embodiment has the possibility of becoming a productive building, or the decision maker can select and discard the retrofit strategy according to the actual demand to ensure the implementability of the zero-carbon retrofit scheme.

[0039] Example Two: As shown in the Figure 4 , the present application provides a kind of zero-carbon retrofit effectiveness intelligent prediction method for existing building, using the zero-carbon retrofit effectiveness intelligent prediction system for existing building described in example one, specifically comprising: S1: receive and store the building model information associated with the prediction of zero-carbon retrofit effectiveness and the time series data of building operation carbon footprint associated parameters; S2: clean up, denoise, mine analysis and correlation fusion to the building model information and time series data received by S1, obtain multi-source heterogeneous data, and calculate the carbon emissions of all energy activities according to multi-source heterogeneous data, output carbon emissions accounting result; S3: based on the carbon emissions accounting result of S2, formulate zero-carbon retrofit strategy for existing building, and iteratively update indoor environment prediction model parameters and carbon emissions accounting algorithm, output optimized retrofit strategy and calibration parameters; S4: receive the updated parameters of S3, evaluate the carbon reduction efficiency of the retrofit strategy, predict the total carbon emissions of energy activities after optimization, and output effectiveness prediction result.

[0040] Specifically, in step S1, the building model information associated with the prediction of zero-carbon retrofit effectiveness and the time series data of building operation carbon footprint associated parameters are received and stored, as follows: S11. Based on model mapping layer, collect building macro information and three-dimensional surface data through global positioning system, remote sensing, geographic information system, unmanned aerial oblique photography technology and three-dimensional laser scanning technology, and build and store three-dimensional reverse digital information model based on BIM technology; S12. Based on parameter perception layer, collect time series data of building operation carbon footprint associated parameters through Internet of Things sensors and Bluetooth beacons, including outdoor meteorological data, indoor physical environment data and user positioning data, and transmit and store to non-relational time series database through cloud computing platform; Wherein the outdoor meteorological data includes air temperature and humidity, illumination, wind speed and direction and rainfall; Indoor physical environment data includes air temperature, radiation temperature, illumination, wind speed and direction and air pollutants.

[0041] The building model information and time series data in step S2 are cleaned, denoised, analyzed, and associated and fused to obtain multi-source heterogeneous data, and the carbon emissions of all-energy activities are calculated according to the multi-source heterogeneous data, and the carbon emission calculation results are output, as follows: S21. Based on the data mining layer, the original time series data output by the information collection module is received, cleaned and denoised through a programming language, and an indoor environment prediction model is constructed by using computational fluid dynamics, Radiance numerical simulation software and machine learning methods, and the processed multi-source heterogeneous data is output; S22. Based on the accounting analysis layer, the multi-source heterogeneous data processed by the data mining layer and the static parameters in the BIM model are received, the data is divided based on the temperature frequency method, and the carbon emissions are calculated by using the all-energy activity carbon emission calculation algorithm, as follows: The carbon emissions of the existing building in the operation stage are set as C, and the process is as follows: In the formula, C C represents the carbon emissions of building refrigeration energy, C W represents the carbon emissions of building heating energy, C L represents the carbon emissions of building lighting energy, C V represents the carbon emissions of building ventilation energy, C E represents the carbon emissions of building elevator energy, C H represents the carbon emissions of building hot water energy, C K represents the carbon emissions of building cooking energy, C S represents the carbon emissions of building socket energy, C R represents the carbon emissions reduced by all renewable energy of the building, C G represents the carbon emissions reduced by all green plant carbon sink systems of the building; wherein the variable C R The BIM model is implanted into the DesignBuilder building performance simulation software, and the measured meteorological data are fused for estimation, and the carbon emissions of all other energy activities are obtained by the following formula: In the formula, C i represents the carbon emissions of all energy activities of the building, T i,j is the carbon emissions of the existing building in the operation stage.j Each space i Energy usage activity duration, W i,j This refers to the energy consumption per unit time of the energy-consuming equipment during this event. EF i,j The carbon emission factor of the energy consumed in this event; Among them, variables related to energy consumption activities in cooling, heating, lighting, and ventilation. T i,j The values ​​are assigned based on user location data and physical environment data, specifically the duration of time a user is present in the space when a certain indoor physical environment indicator does not meet the livability standard; variables related to energy consumption activities such as elevators, hot water, cooking, and electrical outlets. T i,j The assigned values ​​and the energy consumption per unit time of all energy-consuming equipment related to the activities. W i,j All data and estimates were obtained and estimated during field research. C G The formula for obtaining it is: In the formula, m This represents the total number of vegetation species within the building. f l For the first l Carbon reduction per unit area of ​​plantations over time A l For the first l Planting area of ​​plants t For the calculation of time.

[0042] Step S3, based on the carbon emission accounting results, formulates a zero-carbon retrofit strategy for existing buildings, iteratively updates the parameters of the indoor environment prediction model and the carbon emission accounting algorithm, and outputs the optimized retrofit strategy and calibration parameters, as follows: S31. Based on the transformation design layer, a zero-carbon transformation plan is formulated using computational design methods based on the carbon emission accounting results. This plan includes passive form optimization, active energy system upgrades, and the integration of a smart operation and maintenance management system. S32. Based on the iterative update layer, by receiving the scheme from the renovation design layer, the building information, energy-consuming equipment parameters and green plant carbon sink data in the BIM model are updated, and the indoor environment prediction model and carbon emission accounting algorithm are calibrated.

[0043] Step S4 receives updated parameters, evaluates the carbon reduction efficiency of the retrofit strategy, predicts the total carbon emissions from energy-consuming activities throughout the year after optimization, and outputs the effectiveness prediction results, as follows: The system receives parameters and algorithms from the optimization module after iteration, evaluates the reduction of carbon emissions from energy activities by passive and active optimization strategies step by step, and predicts renewable energy production and total annual carbon emissions using building performance simulation software based on annual measured meteorological data, outputting the prediction results of the effectiveness of zero-carbon retrofit.

[0044] In summary, this invention achieves rapid prediction of the effectiveness of zero-carbon retrofitting of existing buildings by comprehensively utilizing various digital technologies. It transforms the "post-retrofit verification" of zero-carbon building operation into "pre-retrofit prediction," significantly reducing investment risk and optimizing resource allocation. The proposed method for sensing and storing complex model information and multi-dimensional time-series data of existing buildings based on digital technologies such as BIM, IoT, and big data has high acquisition efficiency and can minimize intervention in the building itself. The proposed method for establishing a rapid prediction model by coupling limited measured data through mathematical simulation and calculating the carbon footprint distribution of existing buildings for livable operation is also highly efficient. The prediction results are closer to actual operating effects than traditional simulation software, with an error range of less than 10%. The proposed step-by-step evaluation method for the carbon reduction efficiency of the retrofit scheme can quickly simulate and compare the emission reduction effects of different technical strategies, changing the current situation where most zero-carbon retrofit designs are qualitative descriptions. While ensuring the effectiveness of zero-carbon retrofits, it supports decision-makers in making trade-offs between retrofit measures based on actual project conditions and formulating the optimal retrofit path. In summary, this prediction system and method for the effectiveness of zero-carbon retrofits of existing buildings has low intervention in the building itself, high evaluation efficiency, small prediction error, low operating cost, wide applicability, and strong scientific validity.

[0045] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0046] For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on," "mounted on," "fixed to," or "set on" another element, it may be directly on the other element or there may be an intermediate element present. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible embodiments.

[0047] While embodiments of the present application have been shown and described, it is to be understood that the embodiments described are merely exemplary and that changes in form and detail can be made without departing from the principles and spirit of the application, the scope of which is defined by the appended claims as interpreted in their full breadth and spirit.

[0048] In the description of the specification, reference has been made to the terms "one embodiment", "an example", "a specific example" and the like. This is merely intended to mean that a particular feature, structure, material or characteristic described in connection with this embodiment or example is included in at least one embodiment or example of the disclosure. The appearances of the phrases "in one embodiment", "in an example", "in a specific example" or the like in various places in the specification are not necessarily referring to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

Claims

1. A digital prediction system for the effectiveness of zero-carbon retrofitting of existing buildings, characterized in that, include: Information acquisition module: used to collect and store multi-source heterogeneous data related to predicting the effectiveness of zero-carbon retrofitting, including static building model information and dynamic time series data; Processing and Analysis Module: Used to process, mine, and fuse multi-source heterogeneous data, and then calculate the carbon emissions of all energy-consuming activities; Solution optimization module: used to formulate zero-carbon retrofit strategies for existing buildings and iteratively predict the parameters and algorithms associated with effectiveness; Assessment and prediction module: Used to assess the carbon reduction efficiency of the transformation strategy and predict the total carbon emissions of energy use activities throughout the year after optimization.

2. The intelligent prediction system for the effectiveness of zero-carbon retrofitting of existing buildings according to claim 1, characterized in that: The information acquisition module includes a model mapping layer and a parameter perception layer: The model mapping layer is used to collect macroscopic information and three-dimensional surface data of buildings through GPS, remote sensing, geographic information system, UAV-borne oblique photogrammetry and 3D laser scanning technology, and to perform three-dimensional reverse digital information modeling and storage based on BIM technology. Its output is static building model information. The parameter perception layer is used to collect time-series data of building operation carbon footprint related parameters through IoT sensors and Bluetooth beacons. Specifically, it includes outdoor meteorological data, indoor physical environment data and user location data, and transmits and stores them to a non-relational time-series database through a cloud computing platform. Its output is dynamic time-series data. Outdoor meteorological data includes air temperature and humidity, illuminance, wind speed and direction, and rainfall; indoor physical environment data includes air temperature, radiation temperature, illuminance, wind speed and direction, and air pollutants.

3. The intelligent prediction system for the effectiveness of zero-carbon retrofitting of existing buildings according to claim 2, characterized in that: The processing and analysis module includes a data mining layer and an accounting analysis layer: The data mining layer receives the raw time-series data output by the information acquisition module, cleans and reduces noise using a programming language, and uses computational fluid dynamics, Radiance numerical simulation software, and RBF-ANN algorithm to build an indoor environment prediction model, outputting processed multi-source heterogeneous data. The indoor environment prediction model consists of an input layer, a hidden layer, and an output layer. The indoor environment prediction model is trained using the following loss function: in yi For the true value, The predicted value is N, where N is the number of samples. The accounting and analysis layer receives multi-source heterogeneous data processed by the data mining layer and static parameters from the BIM model. It groups and partitions the data based on the temperature-frequency method and calculates carbon emissions using a comprehensive energy-use activity carbon emission accounting algorithm. Its output is the carbon emissions C during the building operation phase, as detailed below: The carbon emissions during the operation phase of existing buildings are set as C, and the process of obtaining them is as follows; In the formula, C C Represents the carbon emissions from building cooling energy consumption. C W This represents the carbon emissions from building heating energy consumption. C L Represents the carbon emissions from building lighting energy consumption. C V This represents the carbon emissions from building ventilation energy consumption. C E This represents the carbon emissions from the energy consumption of building elevators. C H Represents the carbon emissions from building hot water energy consumption. C K Represents the carbon emissions from building cooking energy consumption. C S Represents the carbon emissions from energy consumption of building sockets. C R This represents the amount of carbon emissions reduced by all renewable energy sources used in the building. C G This represents the amount of carbon emissions reduced by all the green plant carbon sink systems in the building; Among the variables C R By integrating the BIM model with DesignBuilder building performance simulation software and combining measured meteorological data for estimation, the formula for obtaining carbon emissions from the remaining energy-consuming activities is as follows: In the formula, C i Represents the carbon emissions from various energy-consuming activities in buildings. T i,j For existing buildings j Each space i Energy usage activity duration, W i,j This refers to the energy consumption per unit time of the energy-consuming equipment during this event. EF i,j The carbon emission factor of the energy consumed in this event; Among them, variables related to energy consumption activities in cooling, heating, lighting, and ventilation. T i,j The values ​​are assigned based on user location data and physical environment data, specifically the duration of time a user is present in the space when a certain indoor physical environment indicator does not meet the livability standard; variables related to energy consumption activities such as elevators, hot water, cooking, and electrical outlets. T i,j The assigned values ​​and the energy consumption per unit time of all energy-consuming equipment related to the activities. W i,j All data and estimates were obtained and estimated during field research. C G The formula for obtaining it is: In the formula, m This represents the total number of vegetation species within the building. f l For the first l Carbon reduction per unit area of ​​plantations over time A l For the first l Planting area of ​​plants t For the calculation of time.

4. The intelligent prediction system for the effectiveness of zero-carbon retrofitting of existing buildings according to claim 3, characterized in that: The solution optimization module includes a modification design layer and an iterative update layer: The transformation design layer is used to formulate zero-carbon transformation plans based on the carbon emission accounting results of the processing and analysis module through computational design methods. Specifically, it includes passive form optimization, active energy system upgrading and intelligent operation and maintenance management system implantation. Its output is the optimized transformation plan. The iterative update layer receives the design scheme from the renovation layer, updates the building information, energy-consuming equipment parameters, and green plant carbon sink data in the BIM model, and calibrates the indoor environment prediction model and carbon emission accounting algorithm. Its output is the iterative carbon emission accounting algorithm and parameters.

5. The intelligent prediction system for the effectiveness of zero-carbon retrofitting of existing buildings according to claim 4, characterized in that: The assessment and prediction module is used to receive the parameters and algorithms after the iteration of the scheme optimization module, evaluate the carbon emission reduction of energy use activities step by step by passive optimization and active optimization strategies, and predict the renewable energy production and total annual carbon emissions based on the annual measured meteorological data through building performance simulation software, and output the prediction results of the effectiveness of zero-carbon transformation.

6. A method for predicting the effectiveness of zero-carbon retrofitting of existing buildings using digital intelligence, employing the digital intelligence prediction system for the effectiveness of zero-carbon retrofitting of existing buildings as described in any one of claims 1 to 5, characterized in that, Includes the following steps: S1: Receive and store building model information and time-series data of building operation carbon footprint correlation parameters that predict the effectiveness of zero-carbon retrofitting; S2: Clean, denoise, mine, analyze, and fused the building model information and time series data received from S1 to obtain multi-source heterogeneous data, and calculate the carbon emissions of all energy-consuming activities based on the multi-source heterogeneous data, and output the carbon emission calculation results. S3: Based on the carbon emission accounting results of S2, formulate a zero-carbon retrofit strategy for existing buildings, iteratively update the parameters of the indoor environment prediction model and the carbon emission accounting algorithm, and output the optimized retrofit strategy and calibration parameters. S4: Receives updated parameters from S3, evaluates the carbon reduction efficiency of the transformation strategy, predicts the total carbon emissions of energy use activities throughout the year after optimization, and outputs the effectiveness prediction results.

7. The method for predicting the effectiveness of zero-carbon retrofitting of existing buildings according to claim 6, characterized in that: Step S1 involves receiving and storing building model information and time-series data of building operation carbon footprint correlation parameters that predict the effectiveness of zero-carbon retrofitting, as detailed below: S11. Based on the model mapping layer, macroscopic information of buildings and three-dimensional surface data are collected through global positioning system, remote sensing, geographic information system, UAV-borne oblique photogrammetry and three-dimensional laser scanning technology, and three-dimensional reverse digital information model is modeled and stored based on BIM technology; S12. Based on the parameter perception layer, time-series data of building operation carbon footprint related parameters are collected through IoT sensors and Bluetooth beacons, specifically including outdoor meteorological data, indoor physical environment data and user location data, and transmitted and stored to a non-relational time-series database through a cloud computing platform; Outdoor meteorological data includes air temperature and humidity, illuminance, wind speed and direction, and rainfall; indoor physical environment data includes air temperature, radiation temperature, illuminance, wind speed and direction, and air pollutants.

8. The method for predicting the effectiveness of zero-carbon retrofitting of existing buildings according to claim 7, characterized in that: In step S2, the building model information and time series data are cleaned, denoised, mined, analyzed, and correlated to obtain multi-source heterogeneous data. Based on the multi-source heterogeneous data, the carbon emissions of all energy-consuming activities are calculated, and the carbon emission calculation results are output as follows: S21. Based on the data mining layer, the raw time-series data output by the information acquisition module is received, cleaned and denoised using a programming language, and an indoor environment prediction model is constructed using computational fluid dynamics, Radiance numerical simulation software and RBF-ANN algorithm, and the processed multi-source heterogeneous data is output. The indoor environment prediction model consists of an input layer, a hidden layer, and an output layer. The indoor environment prediction model is trained using the following loss function: in yi For the true value, The predicted value is N, where N is the number of samples. S22. Based on the accounting and analysis layer, by receiving multi-source heterogeneous data processed by the data mining layer and static parameters from the BIM model, the data is grouped and divided based on the temperature and frequency method, and the carbon emissions are calculated using a full-caliber energy activity carbon emission accounting algorithm, as detailed below: The carbon emissions during the operation phase of existing buildings are set as C, and the process of obtaining them is as follows; In the formula, C C Represents the carbon emissions from building cooling energy consumption. C W This represents the carbon emissions from building heating energy consumption. C L Represents the carbon emissions from building lighting energy consumption. C V This represents the carbon emissions from building ventilation energy consumption. C E This represents the carbon emissions from the energy consumption of building elevators. C H Represents the carbon emissions from building hot water energy consumption. C K Represents the carbon emissions from building cooking energy consumption. C S Represents the carbon emissions from energy consumption of building sockets. C R This represents the amount of carbon emissions reduced by all renewable energy sources used in the building. C G This represents the amount of carbon emissions reduced by all the green plant carbon sink systems in the building; Among the variables C R By integrating the BIM model with DesignBuilder building performance simulation software and combining measured meteorological data for estimation, the formula for obtaining carbon emissions from the remaining energy-consuming activities is as follows: In the formula, C i Represents the carbon emissions from various energy-consuming activities in buildings. T i,j For existing buildings j Each space i Energy usage activity duration, W i,j This refers to the energy consumption per unit time of the energy-consuming equipment during this event. EF i,j The carbon emission factor of the energy consumed in this event; Among them, variables related to energy consumption activities in cooling, heating, lighting, and ventilation. T i,j The values ​​are assigned based on user location data and physical environment data, specifically the duration of time a user is present in the space when a certain indoor physical environment indicator does not meet the livability standard; variables related to energy consumption activities such as elevators, hot water, cooking, and electrical outlets. T i,j The assigned values ​​and the energy consumption per unit time of all energy-consuming equipment related to the activities. W i,j All data and estimates were obtained and estimated during field research. C G The formula for obtaining it is: In the formula, m This represents the total number of vegetation species within the building. f l For the first l Carbon reduction per unit area of ​​plantations over time A l For the first l Planting area of ​​plants t For the calculation of time.

9. The method for predicting the effectiveness of zero-carbon retrofitting of existing buildings according to claim 8, characterized in that: Step S3, based on the carbon emission accounting results, formulates a zero-carbon retrofit strategy for existing buildings, iteratively updates the parameters of the indoor environment prediction model and the carbon emission accounting algorithm, and outputs the optimized retrofit strategy and calibration parameters, as follows: S31. Based on the transformation design layer, a zero-carbon transformation plan is formulated using computational design methods based on the carbon emission accounting results. This plan includes passive form optimization, active energy system upgrades, and the integration of a smart operation and maintenance management system. S32. Based on the iterative update layer, by receiving the scheme from the renovation design layer, the building information, energy-consuming equipment parameters and green plant carbon sink data in the BIM model are updated, and the indoor environment prediction model and carbon emission accounting algorithm are calibrated.

10. The method for predicting the effectiveness of zero-carbon retrofitting of existing buildings according to claim 9, characterized in that: Step S4 receives updated parameters, evaluates the carbon reduction efficiency of the retrofit strategy, predicts the total carbon emissions from energy-consuming activities throughout the year after optimization, and outputs the effectiveness prediction results, as follows: The system receives parameters and algorithms from the optimization module after iteration, evaluates the reduction of carbon emissions from energy activities by passive and active optimization strategies step by step, and predicts renewable energy production and total annual carbon emissions using building performance simulation software based on annual measured meteorological data, outputting the prediction results of the effectiveness of zero-carbon retrofit.

Images