A diffusion model framework construction method based on wind simulation and building performance evaluation

Abstract

The application is suitable for the technical field of wind dynamics simulation, and provides a diffusion model framework construction method based on wind simulation and building performance evaluation, which comprises the following steps: obtaining multiple multi-angle wind field data information, then generating wind simulation data set information according to the multiple multi-angle wind field data information, and finally training a preset multi-angle diffusion model based on the wind simulation data set information to effectively generate target wind simulation model information. The application can provide a simplified solution for rapid wind field simulation and building performance evaluation, realize the prediction of multi-angle wind dynamics in a high-density urban environment, enable designers and planners to seamlessly integrate wind field analysis into the early stage of design exploration, realize a more dynamic evaluation process, greatly reduce the time and computing workload required for performance-driven decision-making, and significantly improve reliability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind dynamics simulation, in particular to a diffusion model framework construction method based on wind simulation and building performance evaluation. BACKGROUND

[0002] With the advancement of global urbanization, more and more people choose to live in cities and their suburbs. High population density greatly increases urban space density, reduces ventilation, and exacerbates urban heat island effects. Rising temperatures and reduced ventilation directly affect human health, comfort, and overall quality of life. Therefore, understanding urban wind environment is crucial for urban and building research, which helps to improve microclimate and improve the adaptability and sustainability of urban and human settlements.

[0003] Currently, traditional wind simulation methods are usually limited to two-dimensional planes, lack the ability to model three-dimensional environments, and cannot simulate time changes, limiting their applicability in dynamic scenarios. There is a problem of low reliability, which needs to be further improved. SUMMARY

[0004] Therefore, based on this, the embodiments of the present application provide a diffusion model framework construction method based on wind simulation and building performance evaluation to solve the problem of low reliability in the prior art.

[0005] In a first aspect, the embodiments of the present application provide a diffusion model framework construction method based on wind simulation and building performance evaluation, which comprises:

[0006] Obtaining a plurality of multi-angle wind field data information;

[0007] Generating wind simulation dataset information according to a plurality of multi-angle wind field data information;

[0008] Training a preset multi-angle diffusion model based on the wind simulation dataset information to generate target wind simulation model information.

[0009] Compared with the prior art, the diffusion model framework construction method based on wind simulation and building performance evaluation provided by the embodiments of the present application has the beneficial effects that: the terminal device can first obtain a plurality of multi-angle wind field data information, then quickly generate wind simulation dataset information according to a plurality of multi-angle wind field data information, and finally effectively generate target wind simulation model information by training a preset multi-angle diffusion model based on the wind simulation dataset information, thereby providing a simplified solution for rapid wind field simulation and building performance evaluation, achieving prediction of multi-angle wind dynamics in high-density urban environments, greatly reducing the time and computational workload required for performance-driven decision-making, making wind simulation not only limited to two-dimensional planes, but also improving applicability in dynamic scenarios, and to some extent solving the problem of low reliability.

[0010] In a second aspect, the embodiments of the present application provide a diffusion model framework construction system based on wind simulation and building performance evaluation, the system comprising:

[0011] A multi-angle wind field data information acquisition module is configured to acquire a plurality of multi-angle wind field data information.

[0012] A wind simulation dataset information generation module is configured to generate wind simulation dataset information according to the plurality of multi-angle wind field data information.

[0013] A target wind simulation model information generation module is configured to train a preset multi-angle diffusion model based on the wind simulation dataset information, and generate target wind simulation model information.

[0014] In a third aspect, the embodiments of the present application provide a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the computer program.

[0015] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the steps of the method of the first aspect.

[0016] It can be understood that the beneficial effects of the second aspect to the fourth aspect can be referred to the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description.

[0018] Figure 1 FIG. 1 is a flowchart of a diffusion model framework construction method provided by an embodiment of the present application;

[0019] Figure 2 FIG. 2 is a flowchart of step S210 in the diffusion model framework construction method provided by an embodiment of the present application;

[0020] Figure 3 FIG. 3 is a first schematic diagram of impermeable area information provided by an embodiment of the present application;

[0021] Figure 4 FIG. 4 is a second schematic diagram of impermeable area information provided by an embodiment of the present application;

[0022] Figure 5 FIG. 5 is a third schematic diagram of impermeable area information provided by an embodiment of the present application.

[0023] Figure 6 is a schematic diagram of wind field image information provided by an embodiment of the present application;

[0024] Figure 7 is a flowchart of step S300 in the diffusion model framework construction method provided by an embodiment of the present application;

[0025] Figure 8 is a schematic diagram of an adjustment process provided by an embodiment of the present application;

[0026] Figure 9 is a flowchart of a process after step S320 in the diffusion model framework construction method provided by an embodiment of the present application;

[0027] Figure 10 is a schematic diagram of a wind field reconstruction with wind strength information provided by an embodiment of the present application;

[0028] Figure 11 is a schematic diagram of a wind field reconstruction with wind direction information provided by an embodiment of the present application;

[0029] Figure 12 is a schematic diagram of training loss and learning rate of a training process provided by an embodiment of the present application;

[0030] Figure 13 is a schematic diagram of a prediction result provided by an embodiment of the present application;

[0031] Figure 14 is a module block diagram of a diffusion model framework construction system provided by an embodiment of the present application;

[0032] Figure 15 is a schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0033] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the application. However, persons of ordinary skill in the art will readily recognize that embodiments of the application can be practiced without

[0034] In the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0035] Reference within the specification of this application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specified

[0036] To illustrate the technical solutions described in the present application, the following will be described by specific embodiments.

[0037] Please refer to Figure 1 , Figure 1 is a flowchart of the diffusion model framework construction method provided by the embodiment of the present application based on wind simulation and building performance evaluation. In the embodiment, the execution subject of the diffusion model framework construction method is a terminal device. It can be understood that the types of the terminal device include but are not limited to mobile phones, tablet computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc., and the specific type of the terminal device is not limited by the embodiment of the present application.

[0038] Please refer to Figure 1 , the diffusion model framework construction method provided by the embodiment of the present application includes but is not limited to the following steps:

[0039] In S100, a plurality of multi-angle wind field data information is acquired.

[0040] Specifically, the terminal device can first acquire a plurality of multi-angle wind field data information, wherein the multi-angle wind field data information is used to describe the data of the multi-angle wind field.

[0041] In some possible implementation manners, in order to facilitate the subsequent data, before step S100, the method further includes but is not limited to the following steps:

[0042] In S101, a three-dimensional vector data grid is generated based on a preset visual programming language.

[0043] Specifically, the terminal device can first generate a three-dimensional vector data grid based on a preset visual programming language, each three-dimensional point in the three-dimensional vector data grid representing the behavior of local wind, thereby providing detailed information for the interaction between air flow and the building environment, wherein the visual programming language can be Grasshopper; the three-dimensional vector data grid is used to capture wind intensity information and wind direction information.

[0044] Correspondingly, the above step S100 includes but is not limited to the following steps:

[0045] In S110, a plurality of multi-angle wind field data information is generated based on a preset simulation tool.

[0046] Specifically, after the terminal device generates the three-dimensional vector data grid, the terminal device can generate a plurality of multi-angle wind field data information based on a preset simulation tool, thereby simulating a high-resolution wind field, generating an accurate air flow pattern around the city buildings under different wind conditions, and providing key inputs for subsequent processing. The simulation tool can be Eddy CFD.

[0047] Illustratively, high-fidelity simulation can be performed on a specified 1 kilometer by 1 kilometer city core zone slice, aiming to capture complex urban wind dynamics, ensuring that the results accurately reflect local changes in wind intensity and wind direction changes, while the output data can serve as a basic data set for encoding and further analysis, while effectively preserving the complex geometric and aerodynamic characteristics of these dense urban environments.

[0048] In S200, wind simulation dataset information is generated according to the plurality of multi-angle wind field data information.

[0049] In some possible implementations, in order to realize the creation of a comprehensive dataset for training, step S200 includes but is not limited to the following steps:

[0050] In S210, for each multi-angle wind field data information: the multi-angle wind field data information is encoded to generate wind simulation dataset information.

[0051] Specifically, after the terminal device generates a plurality of multi-angle wind field data information, the terminal device can perform processing for each multi-angle wind field data information: the multi-angle wind field data information is encoded, and the generated wind field is encoded into an RGB image to generate wind simulation dataset information, wherein the wind simulation dataset information includes a plurality of wind field image information, and the wind field image information is an RGB image.

[0052] In some possible implementations, in order to realize the generation of wind simulation dataset information, please refer to Figure 2 , step S210 includes but is not limited to the following steps:

[0053] In S211, for each multi-angle wind field data information: based on a logarithmic transformation algorithm, wind intensity information of the multi-angle wind field data information is mapped to a green channel to generate green channel information.

[0054] Specifically, the terminal device can perform the following processing for each multi-angle wind field data information: based on a logarithmic transformation algorithm, wind intensity information of the multi-angle wind field data information is mapped to a green channel to generate green channel information, wherein the green channel information can be expressed as:

[0055] G=round[255×log(w i +1)÷log(W mmm +1)],

[0056] In the formula, G represents the green channel information, round[] represents a mathematical function of rounding parameters, w i represents the wind intensity information, and W mmm represents preset maximum wind intensity information; it should be noted that the base in the green channel information can be any positive number, such as e, 2, or 10.

[0057] In S212, relative angle information is obtained.

[0058] Specifically, after the terminal device generates the green channel information, the terminal device can obtain the relative angle information, wherein the relative angle information is used to describe the relative angle between the wind direction vector and the prevailing wind direction.

[0059] In S213, based on the relative angle information, wind direction information of the multi-angle wind field data information is mapped to a blue channel to generate blue channel information.

[0060] Specifically, after the terminal device obtains the relative angle information, the terminal device can map the wind direction information of the multi-angle wind field data information to a blue channel based on the relative angle information to generate blue channel information, wherein the blue channel information can be expressed as:

[0061] B=round[255×w d ·θ÷360],

[0062] In the formula, B represents the blue channel information, w d represents the wind direction information, and θ represents the relative angle information.

[0063] In S214, impermeable terrain area information and building area information are obtained.

[0064] For example, please refer to Figure 3 , Figure 4 and Figure 5After the terminal device generates the blue channel information, the terminal device can obtain impermeable terrain area information and building area information, where the impermeable terrain area information is used to describe an area corresponding to an impermeable terrain, and the building area information is used to describe an area corresponding to an impermeable building.

[0065] In S215, impermeable area information is generated according to the impermeable terrain area information and the building area information.

[0066] For example, please refer to Figure 4 and Figure 5 After the terminal device obtains the impermeable terrain area information and the building area information, the terminal device can generate impermeable area information according to the impermeable terrain area information and the building area information, so as to determine the impermeable areas such as buildings and terrains.

[0067] In S216, the impermeable area information is mapped to a red channel to generate red channel information.

[0068] Specifically, after the terminal device generates the impermeable area information, the terminal device can map the impermeable area information to a red channel to generate red channel information, where the red channel information can be represented as R, and the specific value of the red channel information can be 255.

[0069] In S217, wind field image information is generated according to the green channel information, the blue channel information, and the red channel information.

[0070] For example, please refer to Figure 6 After the terminal device generates the impermeable area information, the terminal device can generate wind field image information according to the green channel information, the blue channel information, and the red channel information, so as to complete the encoding processing of the multi-angle wind field data information.

[0071] Without loss of generality, the terminal device can form a data set containing 200 samples, and each image is accompanied by a text prompt to describe the angle of view and the wind condition.

[0072] In S300, a preset multi-angle diffusion model is trained based on the wind simulation data set information to generate target wind simulation model information.

[0073] Specifically, after the terminal device generates the wind simulation data set information, the terminal device can train a preset multi-angle diffusion model based on the wind simulation data set information to generate target wind simulation model information, so as to not only be limited to two-dimensional planes, but also fully consider time changes, improve applicability in dynamic scenarios, provide an extensible and accurate solution for urban wind field analysis, and improve reliability.

[0074] In some possible implementations, in order to implement the generation of effective target wind simulation model information, please refer to Figure 7 Step S300 includes but is not limited to the following steps:

[0075] In S310, the preset LoRA fine-tuning mechanism is integrated into the preset multi-angle diffusion model to generate a to-be-trained diffusion model.

[0076] Specifically, after the terminal device generates the wind simulation dataset information, the terminal device can integrate the preset LoRA fine-tuning mechanism into the preset multi-angle diffusion model to generate a to-be-trained diffusion model, wherein the LoRA fine-tuning mechanism includes a text embedding prompt adjustment mechanism and a control network adjustment mechanism.

[0077] In S320, based on the wind simulation dataset information, the to-be-trained diffusion model is trained to generate target wind simulation model information.

[0078] Specifically, after the terminal device generates the to-be-trained diffusion model, the terminal device can train the to-be-trained diffusion model based on the wind simulation dataset information, complete the LoRA training of the diffusion model, and generate target wind simulation model information.

[0079] Exemplarily, please refer to Figure 8 The terminal device can efficiently and accurately simulate the wind field by using the two core adjustment mechanisms of the text embedding prompt adjustment mechanism and the control network adjustment mechanism; wherein the adjustment process can start from the encoder, the encoder extracts latent representations (Z t ) from the input wind field data (W), which are encoded in RGB, to capture wind strength, wind direction, and impervious areas, and these latent representations are continuously improved through the diffusion process to gradually learn the multi-dimensional complexity of wind dynamics.

[0080] Without loss of generality, the generated text embedding can encode two key aspects: wind direction and cross-section angle of the simulated wind field, and these embedding information can be used as a specific angle prompt to guide the model to generate output consistent with the specific direction and cross-section input. At the same time, the control network (ControlNet) adjustment mechanism can also be applied to the geometric and structural information of the building environment; through this double adjustment mechanism, the model can adapt to high-level contextual features and local structural changes in the dataset.

[0081] Specifically, LoRA fine-tuning can introduce an efficient parameter adjustment layer within this framework, which integrates a low-order adaptive layer to optimize the computational resources while maintaining high accuracy. Exemplarily, the key training parameters can include 50 learning steps, 20 time horizons, and 1x10 - -learning rate and 1x10-- Learning rate. These parameters can be adjusted using a cosine annealing strategy to avoid over-pursuing optimal values ​​or getting trapped in local minima, thus ensuring robust convergence.

[0082] Specifically, the denoising UNet plays a crucial role in the decoding stage, as it can denoise the latent representation (Z). t Convert back to spatial resolution wind field prediction These predictions are conditioned on the fused output of text embeddings and structural features processed by a conditional projector, which integrates information from both sources. This allows UNet to accurately reconstruct wind dynamics in multi-angle and diverse urban scenes, ultimately outputting a dynamic 3D wind field simulation. Reconstructed from multi-angle inputs, it can represent the complexity of the interaction between wind flow and urban geometry. By combining the advantages of LoRA fine-tuning, text embedding cues, and structural adjustment via a control network, the proposed framework overcomes the limitations of traditional simulation methods, providing a scalable and accurate solution for urban wind field analysis.

[0083] In some possible implementations, to achieve comprehensive multi-angle predictions and reconstruct a coherent wind field from new field data, please refer to [link to relevant documentation]. Figure 9 After step S320, the method further includes, but is not limited to, the following steps:

[0084] In S321, acquire on-site wind field data.

[0085] Specifically, the terminal device can acquire on-site wind field data, which is used to describe the on-site wind field data.

[0086] In S322, the on-site wind field data is input into the target wind simulation model to generate output results.

[0087] Specifically, after the terminal device acquires the on-site wind field data, it can input the on-site wind field data into the target wind simulation model information to generate output result information, which describes the output result of the target wind simulation model information.

[0088] In S323, based on the reverse conversion process, wind strength and wind direction information are generated according to the output information.

[0089] Specifically, after the terminal device generates the output result information, the terminal device can generate wind strength information and wind direction information based on the output result information through reverse conversion processing, thereby decoding the RGB encoded output generated by the model. The reverse conversion processing can be referred to the relevant descriptions in steps S211 to S216 above.

[0090] Exemplarily, please refer to Figure 10 and Figure 11 , the terminal device maps the green channel back to the wind intensity information through reverse conversion, while reconstructing the angle relationship of the wind direction vector relative to the prevailing wind direction and mapping the blue channel back to the wind direction information, ensuring accurate acquisition of wind intensity and wind direction from the model output through a double decoding process.

[0091] Exemplarily, please refer to Figure 10 and Figure 11 , multi-angle prediction fusion can produce a comprehensive three-dimensional representation of wind dynamics, combining individual two-dimensional cross-section outputs into a single spatially consistent field; this synthesis takes into account the overlapping and interdependent wind behavior between adjacent cross-sections, ensuring that local changes and interactions are preserved. In one possible implementation, the fusion process can employ an interpolation technique to integrate outputs from all angles under the guidance of geometric and structural constraints in urban environments, effectively reconstructing complex airflow patterns and capturing the intricate interactions between wind, buildings, and impervious surfaces.

[0092] Without loss of generality, by combining data from different angles, this method improves the accuracy and robustness of wind field simulation, especially in high-density urban environments, resulting in a three-dimensional wind field that provides actionable insights into wind intensity gradients, flow directions, and local turbulence, enabling practitioners to more confidently assess the impact of wind on urban planning and building performance. In addition, this method is flexible and can dynamically adapt to different spatial layouts and boundary conditions, making it applicable to previously unseen urban configurations.

[0093] Specifically, this multi-angle fusion and reconstruction process addresses the limitations of traditional two-dimensional simulation techniques by providing a dynamic three-dimensional representation of wind interactions. The reverse conversion from RGB encoding to physical parameters ensures the interpretability of the prediction results and aligns with real-world wind dynamics, providing an extensible and accurate tool for urban wind analysis and significant application potential for complex building and urban planning scenarios.

[0094] Exemplarily, please refer to Figure 12 , to facilitate subsequent more sensitive and detailed analysis, overcome the limitations of previous two-dimensional methods, and more realistically reproduce the wind dynamics in high-density urban areas, the terminal device can evaluate the performance of the target wind simulation model information, and Figure 12 , it can be seen that the target wind simulation model information shows stable convergence after a total of 40,000 training steps, indicating that it can accurately simulate multi-angle wind dynamics while maintaining computational efficiency.

[0095] Exemplarily, please refer to Figure 13, the terminal device can also generate a prediction result for the test site, and then perform multi-view cross-section wind field reconstruction. For example, refer to Table 1 below. As shown in Table 1, the prediction result is in good agreement with the expected wind dynamics, verifying the generalization capability of the target wind simulation model information to unknown environments. In terms of quantity, the structural similarity index (SSIM) of the image-level evaluation is 0.78, indicating that there is a high degree of similarity between the predicted wind field output and the reference wind field output, and the overall deviation of the wind intensity parameter matching in the entire range is less than 24.7%, which also confirms the accuracy of the target wind simulation model information in capturing wind intensity changes. At the same time, in terms of computational efficiency, compared with traditional CFD simulation, the diffusion model framework significantly shortens the processing time. On an NVIDIA RTX 4090 GPU, the process of generating multi-angle cross-section output and reconstructing the wind field only takes 15 minutes, which is 57% less than the time required for directly setting up and running a complex CFD simulation on site, which usually takes more than 35 minutes. These results highlight the potential of the diffusion model framework in simplifying the wind field analysis workflow without significantly reducing accuracy.

[0096] Table 1 verification result

[0097] Evaluation matrix Accuracy ratio Computing time savings SSIM(average) 0.78 20min(57%time saving) Wind intensity error 24.7％ Wind direction error 43.1％

[0098] The implementation principle of the diffusion model framework construction method for wind simulation and building performance evaluation based on the embodiments of the present application is as follows: the terminal device can first obtain a plurality of multi-angle wind field data information, then quickly generate a wind simulation data set information according to the plurality of multi-angle wind field data information, and finally train a preset multi-angle diffusion model based on the wind simulation data set information to effectively generate target wind simulation model information, thereby providing a simplified solution for rapid wind field simulation and building performance evaluation, predicting multi-angle wind dynamics in high-density urban environments, enabling designers and planners to seamlessly integrate wind field analysis into the early stages of design exploration, and enabling urban planners and architects to implement a more dynamic evaluation process, i.e., iteratively adjusting the design according to real-time wind performance feedback, such as establishing a dynamic optimization path, continuously updating wind field prediction and related performance indicators (such as energy load and ventilation efficiency) according to design changes, thereby significantly reducing the time and computational workload required for performance-driven decision-making, enabling wind simulation to be not limited to two-dimensional planes, and improving applicability and reliability in dynamic scenarios.

[0099] It should be noted that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0100] Embodiments of the present application also provide a diffusion model framework construction system based on wind simulation and building performance evaluation. For ease of illustration, only parts related to the present application are shown, such as Figure 14 As shown in FIG. 13, the system 140 includes:

[0101] A multi-angle wind field data information acquisition module 141 is configured to acquire a plurality of multi-angle wind field data information.

[0102] A wind simulation dataset information generation module 145 is configured to generate wind simulation dataset information according to the plurality of multi-angle wind field data information.

[0103] A target wind simulation model information generation module 143 is configured to train a preset multi-angle diffusion model based on the wind simulation dataset information, and generate target wind simulation model information.

[0104] Optionally, the system 140 further includes:

[0105] A three-dimensional vector data grid generation module is configured to generate a three-dimensional vector data grid based on a preset visual programming language, where the visual programming language is Grasshopper, and the three-dimensional vector data grid is used to capture wind intensity information and wind direction information.

[0106] Correspondingly, the multi-angle wind field data information acquisition module 141 includes:

[0107] A multi-angle wind field data information generation sub-module is configured to generate a plurality of multi-angle wind field data information based on a preset simulation and simulation tool, where the simulation and simulation tool is Eddy CFD.

[0108] Optionally, the wind simulation dataset information generation module 145 includes:

[0109] A wind simulation dataset information generation sub-module is configured to, for each multi-angle wind field data information: encode the multi-angle wind field data information to generate wind simulation dataset information, where the wind simulation dataset information includes a plurality of wind field image information, and the wind field image information is an RGB image.

[0110] The wind simulation dataset information generation sub-module includes:

[0111] A green channel information generation unit is configured to, for each multi-angle wind field data information: map wind intensity information of the multi-angle wind field data information to a green channel based on a logarithmic transformation algorithm to generate green channel information.

[0112] A relative angle information acquisition unit is configured to acquire relative angle information, where the relative angle information is used to describe a relative angle between a wind direction vector and a prevailing wind direction.

[0113] The blue channel information generation unit is configured to map wind direction information of the multi-angle wind field data information to a blue channel based on the relative angle information to generate blue channel information.

[0114] The building area information acquisition unit is configured to acquire impermeable terrain area information and building area information.

[0115] The impervious area information generation unit is configured to generate impervious area information according to the impermeable terrain area information and the building area information.

[0116] The red channel information generation unit is configured to map the impervious area information to a red channel to generate red channel information.

[0117] The wind field image information generation unit is configured to generate wind field image information according to the green channel information, the blue channel information and the red channel information.

[0118] Optionally, the target wind simulation model information generation module 143 includes:

[0119] The to-be-trained diffusion model generation sub-module is configured to integrate a preset LoRA fine-tuning mechanism into a preset multi-angle diffusion model to generate a to-be-trained diffusion model, wherein the LoRA fine-tuning mechanism includes a text embedding prompt adjustment mechanism and a control network adjustment mechanism.

[0120] The target wind simulation model information generation sub-module is configured to train the to-be-trained diffusion model based on wind simulation dataset information to generate target wind simulation model information.

[0121] Optionally, the system 140 further includes:

[0122] The field wind field data information acquisition module is configured to acquire field wind field data information.

[0123] The output result information generation module is configured to input the field wind field data information into the target wind simulation model information to generate output result information.

[0124] The wind intensity information generation module is configured to generate wind intensity information and wind direction information based on the output result information according to reverse conversion processing.

[0125] It should be noted that the information interaction, execution process and the like between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, which will not be described here.

[0126] The present application also provides a terminal device, such as Figure 15As shown, the terminal device 150 of this embodiment includes a processor 151, a memory 152, and a computer program 153 stored in the memory 152 and executable on the processor 151. The processor 151 implements the steps in the above-described diffusion model framework construction method embodiment when executing the computer program 153, for example Figure 1 the steps S100 to S300 shown; or the processor 151 implements the functions of the modules in the above-described apparatus when executing the computer program 153, for example Figure 14 the functions of the modules 141 to 143 shown.

[0127] The terminal device 150 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The terminal device 150 includes but is not limited to the processor 151 and the memory 152. Those skilled in the art can understand that Figure 15 The terminal device 150 is merely an example and does not constitute a limitation on the terminal device 150, which can include more or fewer components than shown, or combine some components, or include different components, for example, the terminal device 150 can also include an input / output device, a network access device, a bus, and the like.

[0128] The processor 151 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0129] The memory 152 can be an internal storage unit of the terminal device 150, for example, a hard disk or a memory of the terminal device 150. The memory 152 can also be an external storage device of the terminal device 150, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 150. Further, the memory 152 can include both the internal storage unit and the external storage device of the terminal device 150. The memory 152 can also store the computer program 153 and other programs and data required by the terminal device 150. The memory 152 can also be used to temporarily store data that has been output or will be output.

[0130] An embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program, when executed by a processor, can implement the steps of each method embodiment described above. The computer program includes computer program code, which can be in a form of source code, object code, executable file, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, software distribution medium, and the like.

[0131] The above are preferred embodiments of the present application, which do not limit the protection scope of the present application. Any equivalent changes made according to the methods, principles and structures of the present application should be covered within the protection scope of the present application.

Claims

1. A diffusion model framework construction method based on wind simulation and building performance evaluation, characterized by, The method comprises: obtaining a plurality of multi-angle wind field data information; generating wind simulation dataset information according to a plurality of the multi-angle wind field data information; training a preset multi-angle diffusion model based on the wind simulation dataset information to generate target wind simulation model information; wherein, generating wind simulation dataset information according to a plurality of the multi-angle wind field data information comprises: for each of the multi-angle wind field data information: encoding the multi-angle wind field data information to generate wind simulation dataset information, wherein the wind simulation dataset information comprises a plurality of wind field image information, and the wind field image information is an RGB image; wherein, for each of the multi-angle wind field data information: encoding the multi-angle wind field data information to generate wind simulation dataset information comprises: for each of the multi-angle wind field data information: mapping the wind strength information of the multi-angle wind field data information to the green channel based on a logarithmic transformation algorithm to generate green channel information; obtaining relative angle information, wherein the relative angle information is used to describe the relative angle between the wind direction vector and the prevailing wind direction; mapping the wind direction information of the multi-angle wind field data information to the blue channel based on the relative angle information to generate blue channel information; obtaining impermeable terrain area information and building area information; generating impermeable area information according to the impermeable terrain area information and the building area information; mapping the impermeable area information to the red channel to generate red channel information; generating the wind field image information according to the green channel information, the blue channel information and the red channel information.

2. The method of claim 1, wherein, Before the obtaining a plurality of multi-angle wind field data information, the method further comprises: generating a three-dimensional vector data grid based on a preset visual programming language, wherein the visual programming language is Grasshopper, and the three-dimensional vector data grid is used to capture wind strength information and wind direction information; correspondingly, the obtaining a plurality of multi-angle wind field data information comprises: generating a plurality of multi-angle wind field data information based on a preset simulation simulation tool, wherein the simulation simulation tool is Eddy CFD.

3. The method of claim 1, wherein, The training a preset multi-angle diffusion model based on the wind simulation dataset information to generate target wind simulation model information comprises: integrating a preset LoRA fine-tuning mechanism into a preset multi-angle diffusion model to generate a to-be-trained diffusion model, wherein the LoRA fine-tuning mechanism comprises a text embedding prompt adjustment mechanism and a control network adjustment mechanism; training the to-be-trained diffusion model based on the wind simulation dataset information to generate target wind simulation model information.

4. The method of claim 1, wherein, After the training a preset multi-angle diffusion model based on the wind simulation dataset information to generate target wind simulation model information, the method further comprises: obtaining field wind field data information; inputting the field wind field data information into the target wind simulation model information to generate output result information; generating the wind strength information and the wind direction information according to the output result information based on reverse conversion processing.

5. A diffusion model framework building system based on wind simulation and building performance assessment, characterized by, The system comprises: The multi-angle wind field data information acquisition module is configured to acquire a plurality of multi-angle wind field data information. The wind simulation dataset information generation module is configured to generate wind simulation dataset information according to the plurality of multi-angle wind field data information. The target wind simulation model information generation module is configured to train a preset multi-angle diffusion model based on the wind simulation dataset information to generate target wind simulation model information. The wind simulation dataset information generation module includes: The wind simulation dataset information generation submodule is configured to, for each of the multi-angle wind field data information: encode the multi-angle wind field data information to generate wind simulation dataset information, wherein the wind simulation dataset information includes a plurality of wind field image information, and the wind field image information is an RGB image. The green channel information generation unit is configured to, for each of the multi-angle wind field data information: map wind strength information of the multi-angle wind field data information to a green channel based on a logarithmic transformation algorithm to generate green channel information. The relative angle information acquisition unit is configured to acquire relative angle information, wherein the relative angle information is used to describe a relative angle between a wind direction vector and a prevailing wind direction. The blue channel information generation unit is configured to map wind direction information of the multi-angle wind field data information to a blue channel based on the relative angle information to generate blue channel information. The building region information acquisition unit is configured to acquire impermeable terrain region information and building region information. The impermeable region information generation unit is configured to generate impermeable region information according to the impermeable terrain region information and the building region information. The red channel information generation unit is configured to map the impermeable region information to a red channel to generate red channel information. The wind field image information generation unit is configured to generate the wind field image information according to the green channel information, the blue channel information, and the red channel information. The system further includes:

6. The system of claim 5, wherein, The three-dimensional vector data grid generation module is configured to generate a three-dimensional vector data grid based on a preset visual programming language, wherein the visual programming language is Grasshopper, and the three-dimensional vector data grid is used to capture wind strength information and wind direction information. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 4.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: ​

Images