Building Structure Analysis Method and Device

Abstract

This application relates to the field of data analysis technology, and particularly to a building structure analysis method and device. Obtain the building structure design data corresponding to multiple candidate designs of the target building; the building structure design data includes building structure type, structural material type, structural material size, structural material usage, and structural node data; for each candidate design, analyze the structural safety level and carbon emission compliance level of the target building according to the building structure design data; for each candidate design, based on the structural safety level and carbon emission compliance level, perform a design score on the candidate design; determine the candidate design with the highest design score as the final building structure design scheme of the target building. By obtaining and analyzing multi-dimensional data of the building structure design, a comprehensive assessment of the structural safety level and carbon emission compliance level of the target building is realized, and a design score is performed based on the assessment results to determine the optimal building structure scheme.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis, and particularly to a method and device for analyzing building structures. Background Art

[0002] With the acceleration of the urbanization process and the continuous improvement of people's requirements for building quality, building structure design has increasingly become the core link in the field of construction engineering. Building structure design not only concerns the safety, stability and durability of buildings, but also directly affects their economy, environmental protection and aesthetics. Traditional building structure design methods often focus on single-dimensional considerations, such as only paying attention to the safety or economy of the structure, while ignoring the comprehensive evaluation of other important factors. Once the building structure is selected and enters the construction preparation stage, any adjustment will greatly affect the construction progress.

[0003] Therefore, there is an urgent need for a technology that can conduct a comprehensive and reasonable analysis during building structure design to balance structural safety, economy and environmental protection. Summary of the Invention

[0004] To solve the problems in the background art, the present application provides a method and device for analyzing building structures. By comprehensively obtaining and analyzing multi-dimensional data of building structure design, a comprehensive evaluation of the safety level of the target building structure and the carbon emission compliance level is realized, and a design score is given based on the evaluation results, and finally the optimal building structure plan is determined.

[0005] In a first aspect, the present application provides a method for analyzing building structures, including:

[0006] Obtain building structure design data corresponding to multiple candidate designs of the target building; the building structure design data includes building structure type, structural material type, structural material size, structural material usage, and structural node data;

[0007] For each candidate design, analyze the structural safety level and the carbon emission compliance level of the target building according to the building structure design data;

[0008] For each candidate design, conduct a design score for the candidate design based on the structural safety level and the carbon emission compliance level;

[0009] Determine the candidate design with the highest design score as the final building structure design plan of the target building.

[0010] Optionally, the analyzing the structural safety level and the carbon emission compliance level of the target building according to the building structure design data includes:

[0011] Determine the load type and the corresponding load demand of the target building according to the building type and the building location;

[0012] Based on the building structure type, structural material type, structural material size, structural material usage, and structural joint data, perform structural strength analysis;

[0013] According to the structural strength and the load quantity requirements corresponding to different load types, analyze the structural strength grade of the target building;

[0014] Combined with the instability factors, perform second-order effect analysis, conduct stability analysis, and determine the critical load when the structure becomes unstable;

[0015] According to the critical load when the structure becomes unstable and the load quantity requirements corresponding to different load types, analyze the stability grade of the target building;

[0016] According to the building location, determine the seismic intensity and geological conditions at the location of the target building;

[0017] According to the seismic intensity and geological conditions, analyze the seismic grade of the target building;

[0018] According to the structural strength grade, stability grade, and seismic grade of the target building, determine the structural safety grade of the target building.

[0019] Optionally, for each design, according to the building structure design data, analyze the structural safety grade and carbon emission compliance grade of the target building, including:

[0020] Obtain the building data and relevant carbon emission requirement data of the target building; the building data includes building age data, building structure data, building scale data, building lifespan data, building location data, and building type data;

[0021] Input the building data and relevant carbon emission requirement data into the shared input layer of the trained carbon emission phased prediction model; the carbon emission phased prediction model is trained based on historical building data, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; the historical carbon emission data includes carbon emission data at different stages of the building's whole life cycle; the carbon emission phased prediction model includes a main network and multiple sub-networks, the main network includes a shared input layer, and each sub-network includes an independent hidden layer and an independent output layer, respectively corresponding to a stage in the whole life cycle;

[0022] At the multiple independent output layers of the carbon emission phased prediction model, respectively output the preliminary carbon emission prediction values corresponding to different stages of the target building;

[0023] Based on the preliminary carbon emission prediction values corresponding to different stages of the target building, calculate the prediction correlation degree between carbon emission data at each stage;

[0024] If the predicted correlation degree is not within the preset correlation degree range, adjust the preliminary predicted carbon emission values corresponding to different stages of the target building until the predicted correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, so as to obtain the predicted carbon emission values corresponding to different stages of the target building.

[0025] Optionally, the step of "If the predicted correlation degree is not within the preset correlation degree range, adjust the preliminary predicted carbon emission values corresponding to different stages of the target building until the predicted correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, so as to obtain the predicted carbon emission values corresponding to different stages of the target building" includes:

[0026] For the predicted correlation degree between the carbon emission data of any two stages, calculate the deviation direction and deviation value between the predicted correlation degree and the preset correlation degree between the carbon emission data of the two stages;

[0027] Determine the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of each two stages;

[0028] Adjust the preliminary predicted carbon emission value of the deviation stage until the predicted correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, so as to obtain the predicted carbon emission values corresponding to different stages of the target building.

[0029] Optionally, the training process of the carbon emission stage prediction model includes:

[0030] Obtain the building data of historical buildings, historical relevant carbon emission requirement data and corresponding historical carbon emission data;

[0031] Analyze the characteristics of the historical carbon emission data, determine the time step, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building;

[0032] Input the carbon emission time series sample data of different stages of the whole life cycle of the historical building into the constructed long short-term memory model for iterative training until the set stop condition is reached;

[0033] Input the historical building data and historical relevant carbon emission requirement data in the carbon emission time series test data into the iteratively trained long short-term memory model, and compare the output result with the historical carbon emission data in the carbon emission time series test data set to verify the training effect;

[0034] Repeat the steps of iterative training and verification until the expected training effect is achieved, and obtain the trained carbon emission prediction model.

[0035] Optionally, analyzing the characteristics of the historical carbon emission data to determine the time step, and constructing the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building, including:

[0036] For the carbon emission data of each stage corresponding to each historical building, set a time window, sample the carbon emission data of this stage, the initial size of the time window is the time span of this stage, and the step size of the time window is the size of the time window;

[0037] For the sampled data within the time window, calculate its range value and variance value. If the range value is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then retain all the data within the time window, reduce the size of the time window, and perform resampling. Repeat this step until the range values of all the data within the time windows are not greater than the first preset threshold, and the variance values are not greater than the second preset threshold;

[0038] Determine the time step according to the size of each time window at this time, determine the carbon emission data corresponding to each time step according to the mean value of the data within each time window, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building.

[0039] Optionally, reducing the size of the time window includes:

[0040] If the range value of the sampled data in any two adjacent time windows is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then calculate the distance between the two maximum values in the two adjacent time windows;

[0041] If the time distance between the two maximum values is less than or equal to the window size, then reduce the time window by 1 / 3.

[0042] Optionally, determining the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of every two stages includes:

[0043] For each stage, if the deviation value of the predicted correlation degree between the carbon emission data of this stage and the carbon emission data of at least two other stages with respect to the preset correlation degree is greater than the preset value, and the deviation direction is consistent with the deviation direction between the preset correlation degrees corresponding to the carbon emission data of the at least two other stages, then determine this stage as the deviation stage.

[0044] Optionally, the method further includes:

[0045] After each stage of the target building is completed, obtain the energy consumption data of this stage, and determine the actual carbon emission data of this stage according to the energy consumption data of this stage;

[0046] Compare the actual carbon emission data of the stage with the predicted carbon emission value of the stage. If the data difference is greater than the third preset threshold, adjust the predicted carbon emission value of the next stage based on the data difference and the preset correlation degree to determine the corrected predicted carbon emission value.

[0047] Second, this application provides a building structure analysis device, including:

[0048] An acquisition module, configured to acquire building structure design data corresponding to multiple candidate designs of a target building; the building structure design data includes building structure type, structural material type, structural material size, structural material consumption, and structural node data;

[0049] An analysis module, configured to analyze the structural safety level and carbon emission compliance level of the target building according to the building structure design data for each candidate design;

[0050] A design scoring module, configured to perform a design score on each candidate design based on the structural safety level and carbon emission compliance level;

[0051] A design scheme determination module, configured to determine the candidate design with the highest design score as the final building structure design scheme of the target building.

[0052] Optionally, the analysis module is specifically configured to acquire building data and relevant carbon emission requirement data of the target building; the building data includes building age data, building structure data, building scale data, building lifespan data, building location data, and building type data; input the building data and relevant carbon emission requirement data into the shared input layer of the trained carbon emission phased prediction model; the carbon emission phased prediction model is trained based on historical building data, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; the historical carbon emission data includes carbon emission data at different stages of the building's entire life cycle; the carbon emission phased prediction model includes a main network and multiple sub-networks, the main network includes a shared input layer, and each sub-network includes an independent hidden layer and an independent output layer, respectively corresponding to one stage in the entire life cycle; output the preliminary predicted carbon emission values corresponding to different stages of the target building at the multiple independent output layers of the carbon emission phased prediction model; calculate the predicted correlation degree between the carbon emission data of each stage based on the preliminary predicted carbon emission values corresponding to different stages of the target building; if the predicted correlation degree is not within the preset correlation degree range, adjust the preliminary predicted carbon emission values corresponding to different stages of the target building until the predicted correlation degree between the carbon emission data of each stage reaches the preset correlation degree range to obtain the predicted carbon emission values corresponding to different stages of the target building.

[0053] Optionally, the preliminary prediction value adjustment module is specifically configured to:

[0054] Calculate the deviation direction and deviation value between the predicted correlation degree and the preset correlation degree between the carbon emission data of any two stages for the predicted correlation degree between the carbon emission data of any two stages;

[0055] Determine the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of each two stages;

[0056] Adjust the preliminary carbon emission prediction value of the deviation stage until the predicted correlation degree between the carbon emission data of each stage reaches the preset correlation degree range, and obtain the carbon emission prediction value corresponding to different stages of the target building.

[0057] Optionally, it further includes a training module for:

[0058] Obtain the building data of historical buildings, historical relevant carbon emission requirement data and corresponding historical carbon emission data;

[0059] Analyze the characteristics of the historical carbon emission data, determine the time step, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building;

[0060] Input the carbon emission time series sample data of different stages of the whole life cycle of the historical building into the constructed long short-term memory model for iterative training until the set stop condition is reached;

[0061] Input the historical building data and historical relevant carbon emission requirement data in the carbon emission time series test data into the long short-term memory model trained iteratively, and compare the output result with the historical carbon emission data in the carbon emission time series test dataset to verify the training effect;

[0062] Repeat the steps of iterative training and verification until the expected training effect is achieved, and obtain a trained carbon emission prediction model.

[0063] Optionally, when the training module analyzes the characteristics of the historical carbon emission data, determines the time step, and constructs the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building, it is specifically configured to:

[0064] For the carbon emission data of each stage corresponding to each historical building, set a time window, sample the carbon emission data of this stage, the initial size of the time window is the time span of this stage, and the step size of the time window is the size of the time window;

[0065] For the sampled data within the time window, calculate its range value and variance value. If the range value is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then retain all the data within the time window, reduce the size of the time window, perform resampling, and repeat this step until the range values of the data in all time windows are not greater than the first preset threshold and the variance values are not greater than the second preset threshold;

[0066] Determine the time step according to the size of each time window at this time, determine the carbon emission data corresponding to each time step according to the mean value of the data within each time window, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the entire life cycle of the historical building.

[0067] Optionally, when the training module reduces the size of the time window, it is specifically used for:

[0068] If the range value of the sampled data in any two adjacent time windows is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then calculate the distance between the two maximum values in the two adjacent time windows;

[0069] If the time distance between the two maximum values is less than or equal to the window size, then reduce the time window by 1 / 3.

[0070] Optionally, when the preliminary predicted value adjustment module determines the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of every two stages, it is specifically used for:

[0071] For each stage, if the deviation value of the prediction correlation degree corresponding to the carbon emission data of this stage and the carbon emission data of at least two other stages with respect to the preset correlation degree is greater than the preset value, and the deviation direction is consistent with the deviation direction between the preset correlation degrees corresponding to the carbon emission data of the at least two other stages, then determine this stage as the deviation stage.

[0072] Optionally, the device further includes a predicted value correction module, which is used for:

[0073] After each stage of the target building is completed, obtain the energy consumption data of this stage, and determine the actual carbon emission data of this stage according to the energy consumption data of this stage;

[0074] Compare the actual carbon emission data of this stage with the predicted carbon emission value of this stage. If the data difference is greater than the third preset threshold, then adjust the predicted carbon emission value of the next stage based on the data difference and the preset correlation degree to determine the corrected predicted carbon emission value.

[0075] In a third aspect, the present application provides an electronic device, including: a memory and a processor, where a computer program capable of being loaded and executed by the processor for the method of the first aspect is stored on the memory.

[0076] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program capable of being loaded and executed by the processor for the method of the first aspect.

[0077] In a fifth aspect, the present application provides a computer program product, including: a computer program; when the computer program is executed by a processor, the method described in any item of the first aspect is implemented.

[0078] The present application provides a building structure analysis method and device. By comprehensively acquiring and analyzing multi-dimensional data of building structure design, a comprehensive evaluation of the safety level and carbon emission compliance level of the target building structure is achieved, and a design score is carried out based on the evaluation results, and finally the optimal building structure scheme is determined. This method has the following remarkable technical effects:

[0079] 1. Comprehensiveness and accuracy: By acquiring multi-dimensional data of building structure design (including building structure type, structural material type, structural material size, structural material consumption, structural joint data, etc.), this method can comprehensively reflect various performance indicators of the building structure, improving the accuracy and reliability of the evaluation.

[0080] 2. Comprehensive evaluation ability: This method not only focuses on the safety of the structure, but also takes into account economy and environmental protection (such as carbon emission compliance level), achieving a comprehensive evaluation of the building structure design scheme. This comprehensive evaluation method helps designers find the best balance among multiple goals and design a building structure that is both safe and economical and environmentally friendly.

[0081] 3. High efficiency and intelligence: Through the automated data analysis and design scoring process, this method significantly improves the efficiency of building structure design. At the same time, the design selection process based on the evaluation results also reflects the characteristics of intelligent decision-making, helping to quickly determine the optimal building structure scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0083] Figure 1 It is a flowchart of a building structure analysis method provided by an embodiment of the present application;

[0084] Figure 2 A flowchart of a carbon emission prediction process during a building process provided by an embodiment of the present application;

[0085] Figure 3 A flowchart of a training process of a carbon emission stage prediction model provided by an embodiment of the present application;

[0086] Figure 4 A schematic structural diagram of a building structure analysis device provided by an embodiment of the present application;

[0087] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0088] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts shall fall within the scope of protection of the present application.

[0089] In addition, the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, both A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0090] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings of the specification.

[0091] Figure 1 A flowchart of a building structure analysis method provided by the present application, as Figure 1 shown, the method includes:

[0092] S101: Obtain building structure design data corresponding to multiple candidate designs of a target building; the building structure design data includes building structure types, structural material types, structural material dimensions, structural material usage amounts, and structural node data.

[0093] For each candidate design of the target building, detailed building structure design data is collected. This data includes the type of building structure (such as frame, shear wall, tube structure, etc.), the type of structural material (such as steel, concrete, wood, etc.), the dimensions of the structural material (such as the cross-sectional dimensions of beams, the thickness of slabs, etc.), the quantity of structural material used (total quantity or quantity per unit area of various materials), and structural joint data (such as the connection method of joints, material reinforcement at joints, etc.).

[0094] The dimensions included in the building structure design data are multi-faceted, and the above-listed are some of the main dimensions. Structural types include frame structures, truss structures, arch structures, cable structures, etc. Common structural materials include steel, concrete, wood, stone, glass, etc. Each material has its unique physical and chemical properties. Structural material dimensions include the span of roof beams, values of roof slabs and columns, etc. Structural joints include connection methods, components, dimensions, and materials, etc.

[0095] S102: For each candidate design, analyze the structural safety level and carbon emission compliance level of the target building based on the building structure design data.

[0096] For each candidate design, conduct a structural safety analysis based on its building structure design data. At the same time, it is also necessary to analyze the carbon emissions of each candidate design, including carbon emissions at each stage in the entire life cycle of the building such as building material production, transportation, building construction, and building operation, to determine its carbon emission compliance level.

[0097] S103: For each candidate design, based on the structural safety level and carbon emission compliance level, conduct a design score for the candidate design.

[0098] Based on the structural safety level and carbon emission compliance level, conduct a score for each candidate design. The score can be a comprehensive index considering both structural safety and environmental protection performance. For example, a weight can be set to combine the structural safety level and carbon emission compliance level in a certain proportion to obtain a comprehensive score.

[0099] S104: Determine the final building structure design plan for the target building as the candidate design with the highest design score.

[0100] Among all candidate designs, select the one with the highest design score as the final building structure design plan for the target building. This plan should achieve the best balance between structural safety and environmental protection performance.

[0101] By comprehensively obtaining and analyzing multi-dimensional data of building structure design, a comprehensive assessment of the safety level and carbon emission compliance level of the target building structure is achieved, and design scores are carried out based on the assessment results, and finally the optimal building structure scheme is determined. This method has the following remarkable technical effects:

[0102] 1. Comprehensiveness and accuracy: By obtaining multi-dimensional data of building structure design (including building structure type, structural material type, structural material size, structural material consumption, structural joint data, etc.), this method can comprehensively reflect various performance indicators of the building structure, improving the accuracy and reliability of the assessment.

[0103] 2. Comprehensive assessment ability: This method not only focuses on the safety of the structure, but also takes into account economy and environmental protection (such as carbon emission compliance level), achieving a comprehensive assessment of the building structure design scheme. This comprehensive assessment method helps designers find the best balance among multiple goals and design a building structure that is both safe, economical and environmentally friendly.

[0104] 3. Efficiency and intelligence: Through the automated data analysis and design scoring process, this method significantly improves the efficiency of building structure design. At the same time, the design selection process based on the assessment results also reflects the characteristics of intelligent decision-making, helping to quickly determine the optimal building structure scheme.

[0105] In some specific embodiments, according to the building structure design data, analyzing the structural safety level and carbon emission compliance level of the target building includes: determining the load type and corresponding load demand of the target building according to the building type and building location; performing structural strength analysis based on the building structure type, structural material type, structural material size, structural material consumption and structural joint data; analyzing the structural strength level of the target building according to the structural strength and the load demand corresponding to different load types; combining instability factors, performing second-order effect analysis, performing stability analysis, and determining the critical load when the structure is unstable; analyzing the stability level of the target building according to the critical load when the structure is unstable and the load demand corresponding to different load types; determining the seismic intensity and geological conditions of the location where the target building is located according to the building location; analyzing the seismic grade of the target building according to the seismic intensity and geological conditions; and determining the structural safety level of the target building according to the structural strength level, stability level and seismic grade of the target building.

[0106] Structural strength analysis aims to evaluate the load-bearing capacity of building structures under normal use and extreme conditions, ensuring that the structure does not fail under various loadings. According to the usage function and geographical location of the building, determine the types of loads that may act on the structure, including dead loads (such as the self-weight of the structure), live loads (such as the weight of people and furniture), wind loads, snow loads, seismic loads, etc. Corresponding calculation models can be established, for example, using professional structural analysis software (such as STAAD, ANSYS, etc.), to establish an accurate structural calculation model based on the building structure type, material type, material dimensions, and joint data. According to relevant codes, different types of loads are combined to simulate the most unfavorable working conditions that the structure may bear. Through software calculation, the stress, strain, and displacement distributions of the structure under various load combinations can be obtained to evaluate whether the strength of the structure meets the requirements.

[0107] Stability analysis focuses on the ability of the structure to maintain its original equilibrium state under specific loadings, preventing the structure from experiencing overall or local instability. According to the structure type and joint connection method, identify possible instability modes, such as overall overturning, local buckling, etc. Incorporate instability factors into the structural calculation model and conduct second-order effect analysis (such as P-Δ effect) to more accurately evaluate the stability of the structure. Through software calculation, obtain the critical load at which the structure becomes unstable and compare it with the design load to evaluate whether the stability of the structure meets the requirements.

[0108] Seismic performance analysis aims to evaluate the response of building structures under seismic actions and their ability to resist damage, ensuring that the structure can maintain overall stability during an earthquake and reducing casualties and property losses. According to the seismic intensity, site category, and geological conditions of the building location, select appropriate ground motion parameters (such as acceleration time history curves) as the input for seismic analysis. Calculate modal parameters such as the natural vibration period, vibration mode, and damping ratio of the structure through software to understand the dynamic characteristics of the structure. Apply the ground motion input to the structural calculation model and conduct time history analysis to obtain response parameters such as displacement, velocity, acceleration, and internal forces of the structure under seismic actions. According to the structural response parameters and failure criteria, evaluate whether the seismic performance of the structure meets the code requirements. Pay particular attention to the ductility, energy dissipation capacity, and reinforcement measures for weak links of the structure.

[0109] In some embodiments, the process of determining the carbon emission compliance level includes: first predicting the carbon emission prediction values corresponding to different stages of the target building, and then comparing the current relevant carbon emission requirements to determine the carbon emission compliance level.

[0110] Among them, the method for predicting carbon emissions during the building process is as Figure 2 shown, including:

[0111] S201: Obtain the building data and relevant carbon emission requirement data of the target building.

[0112] In this application, "building data" refers to data related to buildings, including but not limited to detailed data such as the building age, building structure, building scale, building lifespan, building location, building type, and building style. The building age may include the time of building design, the time of starting construction, etc.; different eras have different design and construction methods, which also have different impacts on carbon emissions. The building scale may include the sizes of various different building spaces. The building type may include various building uses such as commercial, residential, and industrial. The building style may include various styles such as Neo-Chinese, European, and Italian.

[0113] The relevant carbon emission requirement data refers to the relevant data of the normative requirements related to carbon emissions corresponding to the entire life cycle of the building. The promulgation and implementation of relevant regulations will also have different degrees of impact on carbon emissions.

[0114] The target building may be a building in various stages such as planning, design, construction, use, maintenance, and demolition. Therefore, its building data and relevant carbon emission requirement data may be complete or incomplete. For incomplete data, reasonable supplementation can be carried out.

[0115] These data can provide a data basis for subsequent carbon emission prediction.

[0116] S202: Input the building data and the relevant carbon emission requirement data into the shared input layer of the trained carbon emission stage prediction model.

[0117] S203: Output the preliminary carbon emission prediction values corresponding to different stages of the target building respectively in multiple independent output layers of the carbon emission stage prediction model.

[0118] In this application, the model basis of the carbon emission stage prediction model is the Long Short-Term Memory (LSTM) model. A main LSTM network is constructed. The input layer of this network receives common features, namely the building data and the relevant carbon emission requirement data, which are related to each stage of the building life cycle. From this shared input layer, multiple independent LSTM sub-networks can be branched out. Each sub-network corresponds to a specific carbon emission prediction stage, such as design, construction, use, maintenance, demolition, etc. The independent LSTM sub-networks contain independent hidden layers and independent output layers, allowing the sub-networks corresponding to each stage to independently learn their unique time-dependent patterns and output the carbon emission prediction values for the corresponding stages. According to the prediction target, a corresponding activation function is set for each output layer. During training, the loss functions of all sub-networks can be combined into a total loss, and then the entire model is optimized through backpropagation. This architecture helps the model learn general features across stages and make predictions in the specific context of each stage, ensuring the independence and accuracy of the predictions.

[0119] Among them, the historical carbon emission data includes the carbon emission data of different stages of the building's whole life cycle.

[0120] The characteristics of this model are that it includes a main network and multiple sub-networks. The main network is responsible for receiving input data, and each sub-network corresponds to a stage in the building's whole life cycle and independently outputs the preliminary predicted value of carbon emissions at that stage. This structure enables the model to more precisely consider the carbon emission characteristics of each stage of the building.

[0121] S204: Calculate the predicted correlation degree between the carbon emission data of each stage based on the preliminary predicted values of carbon emissions corresponding to different stages of the target building.

[0122] After obtaining the preliminary predicted values of carbon emissions for each stage of the target building at the multiple independent output layers of the model, further calculate the predicted correlation degree between these preliminary predicted values. This correlation degree reflects the degree of mutual influence between the carbon emissions of each stage reflected in the carbon emission prediction data and is an important indicator for evaluating the rationality of the prediction results.

[0123] To calculate the correlation degree, it can be measured by a correlation coefficient (such as the Pearson correlation coefficient).

[0124] S205: If the predicted correlation degree is not within the preset correlation degree range, adjust the preliminary predicted values of carbon emissions corresponding to different stages of the target building until the predicted correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtain the predicted values of carbon emissions corresponding to different stages of the target building.

[0125] The preset correlation degree range is the degree of association between different stages of the building determined based on the analysis of historical carbon emission data. Even for the same two stages, different types of buildings may correspond to different correlation degrees. Therefore, the predicted correlation degree is more likely to be a range. When judging the predicted correlation degree, it can be judged whether it falls into the corresponding range, or the preset correlation degree range can be further subdivided according to the type of the building to judge whether it falls into the range corresponding to the type of the building.

[0126] If the calculated predicted correlation degree is not within the preset correlation degree range, it indicates that there may be logical inconsistencies or practical infeasibilities between the preliminary predicted values. At this time, the preliminary predicted values need to be adjusted until the predicted correlation degree between each stage reaches the preset range. This step ensures the accuracy and reliability of the prediction results.

[0127] After the above adjustment, the predicted values of carbon emissions for each stage of the target building are finally obtained. These predicted values not only consider the characteristics of the building itself but also fully reflect the association relationship between each stage, so they have higher practical value.

[0128] Through the method of this embodiment, a phased carbon emission prediction model is constructed. The main LSTM is used to input building data and relevant carbon emission requirement data, and independent LSTM subnets are used to output the carbon emission prediction values corresponding to each phase respectively, allowing the subnets corresponding to each phase to independently learn their unique time-dependent patterns for more accurate prediction of each phase. At the same time, based on the correlation degree (preset correlation degree) between different phases, the data of each phase is adjusted so that the carbon emission prediction data conforms to the time-dependent characteristics of a single phase and satisfies the special correlation degree between phases, improving the prediction accuracy of carbon emission data. This can provide strong support for carbon emission management and the formulation of emission reduction strategies.

[0129] For each candidate design, the process of design scoring based on the structural safety level and carbon emission compliance level can follow the following steps. For the structural safety level, it can be divided into different levels according to relevant building codes and standards, and corresponding scores are assigned to each level. For the carbon emission compliance level, different compliance levels can also be set according to environmental protection requirements and standards, and corresponding scores are assigned. In design scoring, the importance of the structural safety level and the carbon emission compliance level may be different. Therefore, different weights can be assigned to these two aspects to reflect their relative importance in the overall scoring. The assignment of weights can be adjusted according to the specific requirements and goals of the project. For example, if the project particularly emphasizes environmental performance, a higher weight can be given to the carbon emission compliance level. For each candidate design, the corresponding scores are found in the scoring criteria according to its structural safety level and carbon emission compliance level. Then, these two scores are multiplied by their respective weights to obtain weighted scores. Finally, the weighted scores are added together to obtain the total score of the candidate design. After calculating the total scores of all candidate designs, they can be compared. The candidate design with the highest total score will be regarded as the solution that achieves the best balance between structural safety and environmental performance.

[0130] In some implementation manners, if the predicted correlation degree is not within the preset correlation degree range as described above, the preliminary carbon emission prediction values corresponding to different phases of the target building are adjusted until the predicted correlation degree between the carbon emission data of each phase reaches within the preset correlation degree range to obtain the carbon emission prediction values corresponding to different phases of the target building, including: calculating the deviation direction and deviation value of the predicted correlation degree from the preset correlation degree between the carbon emission data of any two phases; determining the deviation phases according to the deviation direction and deviation value corresponding to the carbon emission data of each two phases; and adjusting the preliminary carbon emission prediction values of the deviation phases until the predicted correlation degree between the carbon emission data of each phase reaches within the preset correlation degree range to obtain the carbon emission prediction values corresponding to different phases of the target building.

[0131] The deviation direction refers to whether the predicted correlation is higher or lower than the preset value, and the deviation value is the specific gap between them.

[0132] If the deviation direction and / or deviation value of the predicted correlation of a certain stage from the preset value is inconsistent, then this stage is marked as a "deviation stage". For the deviation stage, adjust the parameters of the model or use other methods to correct the carbon emission prediction value. This process may need to be iterated until the predicted correlations of all stages are within the preset acceptable range.

[0133] When determining the deviation stage, specifically, each stage can be analyzed. If the deviation values of the predicted correlations corresponding to the carbon emission data of this stage and at least two other stages of carbon emission data from the preset correlation are both greater than the preset value and the deviation directions are the same, then this stage is determined as the deviation stage.

[0134] For example, if the deviation value between the predicted correlation 1 between stage 1 and stage 2 and the preset correlation 1 is greater than the preset value, and the deviation direction is positive; the deviation value between the predicted correlation 2 between stage 1 and stage 3 and the preset correlation 2 is greater than the preset value, and the deviation direction is positive; then stage 1 can be determined as the deviation stage. After adjusting stage 1, the predicted correlation 1 and the predicted correlation 2 can basically be corrected to the acceptable range.

[0135] As Figure 3 shown, the training process of the carbon emission phased prediction model includes:

[0136] S301: Obtain the building data of historical buildings, historical relevant carbon emission requirement data, and corresponding historical carbon emission data.

[0137] Collect the building data of historical buildings, relevant carbon emission requirement data, and corresponding historical carbon emission data. These data constitute the basic data set for model training.

[0138] Sort out the corresponding historical carbon emission data to ensure the accuracy and integrity of the data. For example, preprocess the collected data, including data cleaning, missing value filling, outlier processing, etc.

[0139] S302: Analyze the characteristics of the historical carbon emission data, determine the time step, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building.

[0140] Analyze the characteristics of the historical carbon emission data, determine the appropriate time step, and construct the carbon emission time series sample data and test data based on this. The key to this step is to extract the time series characteristics that can reflect the carbon emission change law through reasonable data processing.

[0141] The characteristics of historical carbon emission data, such as seasonality, periodicity, trend, etc., can be deeply analyzed. According to the characteristics of the data, an appropriate time step is determined for constructing time series samples. Construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of historical buildings. Ensure that the sample data can comprehensively reflect the carbon emissions of buildings at different stages.

[0142] S303: Input the carbon emission time series sample data for different stages of the whole life cycle of the historical building into the constructed long short-term memory model for iterative training until the set stopping condition is reached.

[0143] Input the constructed time series sample data into the long short-term memory model for iterative training. Through continuous iterative optimization, the model can learn the implicit laws in the historical data.

[0144] The LSTM model has good performance in processing time series data.

[0145] First, initialize the parameters of the model, including weights, bias terms, etc. During the training process, use an appropriate loss function (such as mean squared error MSE) and optimization algorithm (such as Adam, RMSprop, etc.) to optimize the parameters of the model. Set appropriate stopping conditions, such as the number of training epochs, the rate of loss value decrease, etc. When the stopping condition is reached, stop the training.

[0146] S304: Input the historical building data and historical related carbon emission requirement data in the carbon emission time series test data into the iteratively trained long short-term memory model, and compare the output result with the historical carbon emission data in the carbon emission time series test dataset to verify the training effect.

[0147] Use the test data to verify the trained model and evaluate its prediction performance. If the prediction effect does not meet the expectation, repeat the iterative training and verification until the model performance reaches a satisfactory level.

[0148] Input the historical building data and historical related carbon emission requirement data in the carbon emission time series test data into the iteratively trained LSTM model to obtain the prediction result. Compare the prediction result with the historical carbon emission data in the carbon emission time series test dataset, calculate evaluation metrics (such as accuracy, recall rate, F1 value, etc.) to verify the training effect of the model. According to the verification result, optimize the model, including adjusting the model structure, parameters, optimization algorithm, etc.

[0149] S305: Repeat the steps of iterative training and verification until the expected training effect is achieved to obtain the trained carbon emission prediction model.

[0150] Repeat the steps of model training and validation until the expected training effect is achieved. When the performance of the model meets the preset requirements, determine the model as the final phased carbon emission prediction model. Deploy the trained model to the actual application scenario to predict the carbon emissions of the building at different stages of its whole life cycle. Provide scientific basis and suggestions for the energy conservation and emission reduction of the building according to the prediction results.

[0151] Based on the characteristics of the historical carbon emission data analyzed above, determine the time step, and construct the time series sample data and time series test data of the carbon emissions at different stages of the historical building's whole life cycle, including: for the carbon emission data of each stage corresponding to each historical building, set a time window, sample the carbon emission data of this stage, the initial size of the time window is the time span of this stage, and the step size of the time window is the size of the time window; for the sampled data within the time window, calculate its range value and variance value. If the range value is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then retain all the data within the time window, reduce the size of the time window, and perform sampling again. Repeat this step until the range values of all the data within all the time windows are not greater than the first preset threshold, and the variance value is not greater than the second preset threshold; determine the time step according to the size of each time window at this time, and determine the carbon emission data corresponding to each time step according to the mean value of the data within each time window, and construct the time series sample data and time series test data of the carbon emissions at different stages of the historical building's whole life cycle.

[0152] For each stage of each historical building in its whole life cycle, set an initial time window. The initial size of this time window can be set as the time span of this stage. Set the step size of the time window, and this step size can be set as a proportion of the initial size of the time window, such as 100%, 50% or 25%, etc.

[0153] Sample the carbon emission data within each time window. This can be achieved by selecting all the data points within the time window or selecting representative data points. Calculate the range value (the difference between the maximum value and the minimum value) and the variance value of the sampled data within each time window. These two indicators can reflect the volatility and dispersion degree of the data.

[0154] If the extreme difference of the data within the time window is greater than the first preset threshold, or the variance value is greater than the second preset threshold, it is considered that the data within this time window has excessive fluctuations or a too high degree of dispersion, containing many time series data features and needs to be retained as much as possible. At this time, it is necessary to reduce the size of the time window and re-sample and analyze the characteristics. Repeat this step until the data within all time windows meet the preset threshold conditions. At this time, the data within each window tends to be stable and homogeneous, with fewer features, and the data volume can be compressed by selecting specific values for representation.

[0155] According to the finally determined size of each time window, the time step can be calculated. The time step is the time interval considered each time the model processes time series data. The choice of the time step should be based on the characteristics of the data and the requirements of the model. A shorter time step can capture more details, but may lead to an overly complex model; while a longer time step may ignore some important details.

[0156] Based on the mean value or other statistics (such as median, mode, etc.) of the data within each time window, determine the carbon emission data corresponding to each time step. Arrange these data in chronological order to construct the carbon emission time series sample data at different stages of the whole life cycle of the historical building. At the same time, divide a part of the original data as the carbon emission time series test data to verify the generalization ability and prediction accuracy of the model. That is, compress the data within a window into one data, greatly reducing the sample data volume, making the training efficiency of the model higher, and at the same time, the sample features are not lost, which does not affect the training effect of the model.

[0157] If the carbon emission data in some stages is too scarce or unbalanced, data augmentation techniques can be considered to generate more training samples to improve the stability and robustness of the model. For example, methods such as interpolation, resampling, and noise addition can be used to augment the training data.

[0158] To improve the training efficiency and prediction accuracy of the model, the time series data can be normalized or standardized. This can eliminate the dimensional difference and order of magnitude difference between different data, making it easier for the model to learn and predict.

[0159] Through the above steps, high-quality and representative carbon emission time series sample data and test data can be constructed, providing strong support for subsequent model training and verification.

[0160] Specifically, reducing the size of the time window includes: if the extreme difference between the sampled data in any two adjacent time windows is greater than a first preset threshold, and / or the variance value is greater than a second preset threshold, then calculate the distance between the two maximum values in the two adjacent time windows; if the time distance between the two maximum values is less than or equal to the window size, then reduce the time window by 1 / 3.

[0161] For each historical building at each stage of its full life cycle, set an initial time window. The initial size of this time window is usually set to the time span of this stage.

[0162] Calculate the extreme difference (the difference between the maximum value and the minimum value) and the variance value of the data within each time window.

[0163] Check the data characteristics of adjacent time windows. If there are any two adjacent time windows where the extreme difference of the sampled data within them is greater than a first preset threshold, or the variance value is greater than a second preset threshold, then perform the following steps.

[0164] Calculate the time distance between the respective maximum values (extreme values) within these two adjacent time windows. If the time distance between the two maximum values is less than or equal to the size of the current time window, then reduce the size of the time window by 1 / 3. This means that the new size of the time window will be 2 / 3 of the original size.

[0165] Repeat the above steps and continue to check the data characteristics within the new time window until all preset conditions are met.

[0166] This process can ensure the stability of time series data and can adaptively adjust the size of the time window when the data fluctuates greatly, so as to more accurately capture the changing trend of carbon emissions. At the same time, this adaptive method can also reduce the impact of outliers on model training to a certain extent.

[0167] Optionally, the method further includes: after each stage of the target building is completed, obtain the energy consumption data of this stage, and determine the actual carbon emission data of this stage according to the energy consumption data of this stage; compare the actual carbon emission data of this stage with the predicted carbon emission value of this stage. If the data difference is greater than a third preset threshold, then adjust the predicted carbon emission value of the next stage based on the data difference and a preset correlation degree to determine a corrected predicted carbon emission value.

[0168] After a certain stage of the target building is completed, comparing the actual carbon emission data with the predicted value and adjusting the predicted value for the subsequent stage according to the difference can improve the accuracy and practicality of the model. Specifically, first collect the actual carbon emission data. After each stage of the target building is completed, collect the actual carbon emission data for that stage. During the process, the actual energy consumption data for that stage can be recorded and statistically analyzed. For example, record the electricity consumption data through an electricity meter; record the gas usage data through a gas meter, etc. Then, based on certain statistical methods, calculate the corresponding actual carbon emission data from the energy consumption data. In some specific implementation methods, existing statistical algorithms can be used for calculation, and the calculation results of multiple algorithms can be averaged or the median or extreme values can be taken to calculate the actual carbon emission data. The existing statistical algorithms can also be improved to calculate the actual carbon emission data with a new algorithm. It should be noted that no matter which algorithm is adopted, in order to ensure the consistency between the prediction result and the true calculation data, try to ensure the algorithm related to the phased carbon emission prediction model.

[0169] In addition, the data type of these data should be the same as the data type relied on during model prediction to ensure the accuracy of comparison. Then compare the predicted value with the actual value. Compare the collected actual carbon emission data with the carbon emission predicted value for the corresponding stage. The difference or percentage difference between the two can be calculated. Further, determine whether the data difference is significant. A third preset threshold can be set to determine whether the difference between the actual data and the predicted value is significant. This threshold can be set according to the actual situation and model performance, usually a percentage or an absolute value. If the data difference is greater than the third preset threshold, it is considered that there is a significant difference between the predicted value and the actual value, and adjustment is required. The reason for the difference can also be analyzed. After determining that the predicted value needs to be adjusted, analyze the reasons for the difference. This may include errors in the model itself, inaccurate input data, changes in certain factors during the actual building stage, etc. Considering these reasons for the error, the predicted value can be further adjusted based on the data difference and correlation. Adjust the carbon emission predicted value for the next stage according to the difference between the actual data and the predicted value and the preset correlation. The specific adjustment method can be to directly add a correction factor or indirectly affect the predicted value by adjusting the parameters of the model. The predicted value after adjustment is the corrected carbon emission predicted value. This value will be used as the basis for carbon emission prediction in subsequent stages and is used to guide building operation and management. Throughout the entire life cycle of the building, continuously collect the actual carbon emission data and compare it with the corrected predicted value. Continuously iterate and adjust the prediction model according to the comparison results to improve the accuracy and adaptability of the model.

[0170] Through this process, the effectiveness and reliability of the carbon emission prediction model in practical applications can be ensured, providing strong support for building energy conservation and emission reduction.

[0171] In some embodiments, the prediction results also need to be compared with certain specific emission standards. In case of possible exceedance of the emission standards, it may also be necessary to adjust the building data at specific stages and re - perform the prediction.

[0172] As Figure 4 shown, the present application also provides a building structure analysis device 400, including:

[0173] An acquisition module 401, configured to acquire building structure design data corresponding to multiple candidate designs of a target building; the building structure design data includes building structure type, structural material type, structural material size, structural material consumption, and structural joint data;

[0174] An analysis module 402, configured to analyze the structural safety level and carbon emission compliance level of the target building according to the building structure design data for each candidate design;

[0175] A design scoring module 403, configured to perform a design score on each candidate design based on the structural safety level and carbon emission compliance level;

[0176] A design scheme determination module 404, configured to determine the final building structure design scheme of the target building as the candidate design with the highest design score.

[0177] The analysis module 402 is specifically configured to:

[0178] Determine the load type and the corresponding load quantity requirement of the target building according to the building type and building location;

[0179] Perform a structural strength analysis based on the building structure type, structural material type, structural material size, structural material consumption, and structural joint data;

[0180] Analyze the structural strength level of the target building according to the structural strength and the load quantity requirements corresponding to different load types;

[0181] Combined with the instability factors, perform a second - order effect analysis, perform a stability analysis, and determine the critical load at which the structure loses stability;

[0182] Analyze the stability level of the target building according to the critical load at which the structure loses stability and the load quantity requirements corresponding to different load types;

[0183] Determine the seismic intensity and geological conditions of the location where the target building is located according to the building location;

[0184] Analyze the seismic resistance level of the target building according to the seismic intensity and geological conditions;

[0185] Determine the structural safety level of the target building according to the structural strength level, stability level, and seismic resistance level of the target building.

[0186] The analysis module 402 is specifically configured to:

[0187] Obtain the building data and relevant carbon emission requirement data of the target building; the building data includes building age data, building structure data, building scale data, building life data, building location data, and building type data;

[0188] Input the building data and relevant carbon emission requirement data into the shared input layer of the trained carbon emission phased prediction model; the carbon emission phased prediction model is trained based on historical building data, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; the historical carbon emission data includes carbon emission data at different stages of the building's entire life cycle; the carbon emission phased prediction model includes a main network and multiple sub-networks, the main network includes a shared input layer, and each sub-network includes an independent hidden layer and an independent output layer, respectively corresponding to one stage in the entire life cycle;

[0189] Output the preliminary carbon emission prediction values corresponding to different stages of the target building respectively at the multiple independent output layers of the carbon emission phased prediction model;

[0190] Based on the preliminary carbon emission prediction values corresponding to different stages of the target building, calculate the prediction correlation degree between the carbon emission data of each stage;

[0191] If the prediction correlation degree is not within the preset correlation degree range, adjust the preliminary carbon emission prediction values corresponding to different stages of the target building until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtain the carbon emission prediction values corresponding to different stages of the target building.

[0192] Optionally, when the prediction correlation degree is not within the preset correlation degree range, the analysis module 402 adjusts the preliminary carbon emission prediction values corresponding to different stages of the target building until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtains the carbon emission prediction values corresponding to different stages of the target building. Specifically, it is configured to:

[0193] For the prediction correlation degree between the carbon emission data of any two stages, calculate the deviation direction and deviation value of the prediction correlation degree from the preset correlation degree between the carbon emission data of the two stages;

[0194] Determine the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of each two stages;

[0195] Adjust the preliminary predicted value of carbon emissions in the deviation stage until the predicted correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, so as to obtain the predicted value of carbon emissions corresponding to different stages of the target building.

[0196] Optionally, it further includes a training module 405, which is used for:

[0197] Obtain the building data of historical buildings, historical relevant carbon emission requirement data and corresponding historical carbon emission data;

[0198] Analyze the characteristics of the historical carbon emission data, determine the time step, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building;

[0199] Input the carbon emission time series sample data of different stages of the whole life cycle of the historical building into the constructed long short-term memory model for iterative training until the set stop condition is reached;

[0200] Input the historical building data and historical relevant carbon emission requirement data in the carbon emission time series test data into the iteratively trained long short-term memory model, and compare the output result with the historical carbon emission data in the carbon emission time series test data set to verify the training effect;

[0201] Repeat the steps of iterative training and verification until the expected training effect is achieved, and obtain a trained carbon emission prediction model.

[0202] Optionally, when analyzing the characteristics of the historical carbon emission data, determining the time step, and constructing the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building, the training module 405 is specifically used for:

[0203] For the carbon emission data of each stage corresponding to each historical building, set a time window, sample the carbon emission data of this stage, the initial size of the time window is the time span of this stage, and the step size of the time window is the size of the time window;

[0204] For the sampled data within the time window, calculate its range value and variance value. If the range value is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then retain all the data within the time window, reduce the size of the time window, and perform resampling. Repeat this step until the range values of all the data within the time window are not greater than the first preset threshold, and the variance value is not greater than the second preset threshold;

[0205] Determine the time step according to the size of each time window at this time, determine the carbon emission data corresponding to each time step according to the mean value of the data within each time window, and construct the time series sample data and time series test data of carbon emissions in different stages of the full life cycle of the historical building.

[0206] Optionally, when the training module 405 reduces the size of the time window, it is specifically configured to:

[0207] If the extreme difference value of the sampling data within any two adjacent time windows is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then calculate the distance between the two maximum values within the two adjacent time windows;

[0208] If the time distance between the two maximum values is less than or equal to the window size, then reduce the time window by 1 / 3.

[0209] Optionally, when the analysis module 402 determines the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of every two stages, it is specifically configured to:

[0210] For each stage, if the deviation value of the prediction correlation degree between the carbon emission data of this stage and the carbon emission data of at least two other stages with respect to the preset correlation degree is greater than the preset value, and the deviation direction is consistent with the deviation direction between the preset correlation degrees corresponding to the carbon emission data of the at least two other stages, then determine this stage as the deviation stage.

[0211] Optionally, the device further includes a predicted value correction module 406, which is used for:

[0212] After each stage of the target building is completed, obtain the energy consumption data of this stage, and determine the actual carbon emission data of this stage according to the energy consumption data of this stage; compare the actual carbon emission data of this stage with the predicted carbon emission value of this stage, if the data difference is greater than the third preset threshold, then adjust the predicted carbon emission value of the next stage based on the data difference and the preset correlation degree, and determine the corrected predicted carbon emission value.

[0213] The device in this embodiment can be used to execute the method in any of the above embodiments, and its implementation principle and technical effects are similar, and will not be elaborated here.

[0214] Figure 5 The structural schematic diagram of an electronic device provided by an embodiment of the present application is shown as Figure 5 As shown, the electronic device 500 in this embodiment may include: a memory 501 and a processor 502.

[0215] The memory 501 stores a computer program that can be loaded and executed by the processor 502 to execute the method in the above embodiments.

[0216] Among them, the processor 502 is connected to the memory 501, such as through a bus.

[0217] Optionally, the electronic device 500 may further include a transceiver. It should be noted that in practical applications, there is no limit to the number of transceivers, and the structure of the electronic device 500 does not constitute a limitation on the embodiments of the present application.

[0218] The processor 502 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 502 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0219] The bus may include a path for transmitting information between the above components. The bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0220] The memory 501 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0221] The memory 501 is used to store the application program code for executing the solution of this application, and is controlled and executed by the processor 502. The processor 502 is used to execute the application program code stored in the memory 501 to implement the content shown in the foregoing method embodiments.

[0222] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 5 The illustrated electronic device is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0223] The electronic device of this embodiment can be used to execute the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar, and will not be elaborated here.

[0224] This application also provides a computer-readable storage medium storing a computer program that can be loaded and executed by a processor to execute the method in the foregoing embodiments.

[0225] Those of ordinary skill in the art can understand that all or part of the steps for implementing the foregoing method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the foregoing method embodiments; and the foregoing storage medium includes: ROM, RAM, magnetic disks, or optical discs and other various media that can store program code.

Claims

1. A building structure analysis method, characterized in that, Including: Obtaining building structure design data corresponding to multiple candidate designs of a target building; The building structure design data includes building structure type, structural material type, structural material size, structural material quantity, and structural joint data; For each candidate design, based on the building structure design data, analyzing the structural safety level and carbon emission compliance level of the target building; For each candidate design, based on the structural safety level and carbon emission compliance level, performing a design score on the candidate design; Determining the final building structure design plan of the target building as the candidate design with the highest design score; The analyzing the structural safety level and carbon emission compliance level of the target building based on the building structure design data includes: Determining the load type and corresponding load quantity requirements of the target building according to the building type and building location; Performing a structural strength analysis based on the building structure type, structural material type, structural material size, structural material quantity, and structural joint data; Analyzing the structural strength level of the target building according to the structural strength and the load quantity requirements corresponding to different load types; Combining instability factors, performing a second-order effect analysis, performing a stability analysis, and determining the critical load at which the structure becomes unstable; Analyzing the stability level of the target building according to the critical load at which the structure becomes unstable and the load quantity requirements corresponding to different load types; Determining the seismic intensity and geological conditions of the location where the target building is located according to the building location; Analyzing the seismic resistance level of the target building according to the seismic intensity and geological conditions; Determining the structural safety level of the target building according to the structural strength level, stability level, and seismic resistance level of the target building; The analyzing the structural safety level and carbon emission compliance level of the target building based on the building structure design data for each design includes: Obtaining the building data and relevant carbon emission requirement data of the target building; the building data includes building age data, building structure data, building scale data, building lifespan data, building location data, and building type data; Inputting the building data and relevant carbon emission requirement data into the shared input layer of a trained carbon emission phased prediction model; the carbon emission phased prediction model is trained based on historical building data, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; the historical carbon emission data includes carbon emission data at different stages of the building's entire life cycle; the carbon emission phased prediction model includes a main network and multiple sub-networks, the main network includes a shared input layer, each sub-network includes an independent hidden layer and an independent output layer, and each sub-network corresponds to a stage in the entire life cycle; Outputting the preliminary carbon emission prediction values corresponding to different stages of the target building respectively at the multiple independent output layers of the carbon emission phased prediction model; Based on the preliminary carbon emission prediction values corresponding to different stages of the target building, calculate the correlation coefficient between the preliminary carbon emission prediction values of each stage as the prediction correlation degree; the prediction correlation degree is used to reflect the degree of mutual influence between the carbon emissions of each stage reflected in the carbon emission prediction data; If the prediction correlation degree is not within the preset correlation degree range, adjust the preliminary carbon emission prediction values corresponding to different stages of the target building until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtain the carbon emission prediction values corresponding to different stages of the target building.

2. The method according to claim 1, wherein The step of, if the prediction correlation degree is not within the preset correlation degree range, adjusting the preliminary carbon emission prediction values corresponding to different stages of the target building until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtaining the carbon emission prediction values corresponding to different stages of the target building, includes: For the prediction correlation degree between the carbon emission data of any two stages, calculate the deviation direction and deviation value between the prediction correlation degree and the preset correlation degree between the carbon emission data of the two stages; Determine the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of every two stages; Adjust the preliminary carbon emission prediction value of the deviation stage until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtain the carbon emission prediction values corresponding to different stages of the target building.

3. The method according to claim 1 or 2, characterized in that, The training process of the carbon emission prediction model by stages includes: Obtain the building data of historical buildings, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; Analyze the characteristics of the historical carbon emission data, determine the time step, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the full life cycle of the historical building; Input the carbon emission time series sample data of different stages of the full life cycle of the historical building into the constructed long short-term memory model for iterative training until the set stop condition is reached; Input the historical building data and historical relevant carbon emission requirement data in the carbon emission time series test data into the long short-term memory model after iterative training, and compare the output result with the historical carbon emission data in the carbon emission time series test dataset to verify the training effect; Repeat the steps of iterative training and verification until the expected training effect is achieved, and obtain the trained carbon emission prediction model.

4. The method according to claim 3, characterized in that, The step of analyzing the characteristics of the historical carbon emission data, determining the time step, and constructing the carbon emission time series sample data and carbon emission time series test data for different stages of the full life cycle of the historical building includes: For the carbon emission data of each stage corresponding to each historical building, set a time window, sample the carbon emission data of the stage, the initial size of the time window is the time span of the stage, and the step size of the time window is the size of the time window; For the sampled data within the time window, calculate its range value and variance value. If the range value is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then retain all the data within the time window, reduce the size of the time window, perform resampling, and repeat this step until the range values of the data in all time windows are not greater than the first preset threshold, and the variance values are not greater than the second preset threshold; Determine the time step according to the size of each time window at this time, determine the carbon emission data corresponding to each time step according to the mean value of the data within each time window, and construct the carbon emission time series sample data and carbon emission time series test data for different stages of the whole life cycle of the historical building.

5. The method according to claim 4, characterized in that, The reducing the size of the time window includes: If the range value of the sampled data in any two adjacent time windows is greater than the first preset threshold, and / or the variance value is greater than the second preset threshold, then calculate the distance between the two maximum values in the two adjacent time windows; If the time distance between the two maximum values is less than or equal to the window size, then reduce the time window by 1 / 3.

6. The method according to claim 2, wherein The determining the deviation stage according to the deviation direction and deviation value corresponding to the carbon emission data of each two stages includes: For each stage, if the deviation value of the predicted correlation degree between the carbon emission data of this stage and the carbon emission data of at least two other stages with respect to the preset correlation degree is greater than the preset value, and the deviation direction is consistent with the deviation direction between the preset correlation degrees corresponding to the carbon emission data of the at least two other stages, then determine this stage as the deviation stage.

7. The method according to claim 5 or 6, characterized in that, The method further includes: After each stage of the target building is completed, obtain the energy consumption data of this stage, and determine the actual carbon emission data of this stage according to the energy consumption data of this stage; Compare the actual carbon emission data of this stage with the predicted carbon emission value of this stage. If the data difference is greater than the third preset threshold, then adjust the predicted carbon emission value of the next stage based on the data difference and the preset correlation degree to determine the corrected predicted carbon emission value.

8. An architectural structure analysis device, characterized in that, It includes: An acquisition module, configured to acquire the building structure design data corresponding to multiple candidate designs of the target building; The building structure design data includes building structure type, structural material type, structural material size, structural material consumption, and structural joint data; An analysis module, configured to analyze the structural safety level and carbon emission compliance level of the target building according to the building structure design data for each candidate design; A design scoring module, configured to perform a design score on each candidate design based on the structural safety level and carbon emission compliance level; A design scheme determination module, configured to determine the candidate design with the highest design score as the final building structure design scheme of the target building; The analysis module is specifically configured to: determine the load type and the corresponding load demand of the target building according to the building type and building location; Based on the building structure type, structural material type, structural material size, structural material usage, and structural joint data, conduct structural strength analysis; according to the structural strength and the load quantity requirements corresponding to different load types, analyze the structural strength grade of the target building. Combined with instability factors, conduct second-order effect analysis, conduct stability analysis, and determine the critical load when the structure becomes unstable; according to the critical load when the structure becomes unstable and the load quantity requirements corresponding to different load types, analyze the stability grade of the target building. Based on the building location, determine the seismic intensity and geological conditions at the location of the target building. According to the seismic intensity and geological conditions, analyze the seismic grade of the target building; according to the structural strength grade, stability grade, and seismic grade of the target building, determine the structural safety grade of the target building. The analysis module is specifically configured to obtain the building data of the target building and the relevant carbon emission requirement data; the building data includes building age data, building structure data, building scale data, building life data, building location data, and building type data; input the building data and the relevant carbon emission requirement data into the shared input layer of the trained carbon emission phased prediction model; the carbon emission phased prediction model is trained based on historical building data, historical relevant carbon emission requirement data, and corresponding historical carbon emission data; the historical carbon emission data includes carbon emission data at different stages of the building's whole life cycle; the carbon emission phased prediction model includes a main network and multiple sub-networks, the main network includes a shared input layer, each sub-network includes an independent hidden layer and an independent output layer, and each sub-network corresponds to a stage in the whole life cycle respectively; at the multiple independent output layers of the carbon emission phased prediction model, respectively output the preliminary carbon emission prediction values corresponding to different stages of the target building; based on the preliminary carbon emission prediction values corresponding to different stages of the target building, calculate the correlation coefficient between the preliminary carbon emission prediction values of each stage as the prediction correlation degree; the prediction correlation degree is used to reflect the degree of mutual influence between the carbon emissions of each stage reflected in the carbon emission prediction data; if the prediction correlation degree is not within the preset correlation degree range, adjust the preliminary carbon emission prediction values corresponding to different stages of the target building until the prediction correlation degree between the carbon emission data of each stage reaches within the preset correlation degree range, and obtain the carbon emission prediction values corresponding to different stages of the target building.

9. An electronic device, comprising: A memory and a processor, and a computer program capable of being loaded and executed by the processor as claimed in any one of claims 1-7 is stored on the memory.

Images