Granary design method, device and equipment based on three-dimensional model and storage medium

Abstract

The invention discloses a granary design method and device based on a three-dimensional model, equipment and a storage medium, and the design method comprises the steps: obtaining the original feature information of a target granary, carrying out the preprocessing of the original feature information, and obtaining the feature information after preprocessing; based on the preprocessed feature information, generating a three-dimensional model of the target granary by using a building information model technology; obtaining a target granary design model matched with the three-dimensional model from a pre-stored model database; performing a simulation test on the target granary design model to obtain a simulation test result at least including grain storage safety, full life cycle cost and extreme working condition adaptability; and judging the simulation test result according to a preset judgment standard. According to the method, multiple technologies are fused, granary design data are accurately collected, three-dimensional modeling, simulation evaluation and scheme optimization are realized through intelligent algorithm processing, the grain storage safety can be greatly improved, the cost is reduced, and the design efficiency and quality are improved.

Description

Technical Field

[0001] This application relates to the field of urban infrastructure construction, specifically to a three-dimensional model-based granary calculation and design method, device, equipment and storage medium. Background Art

[0002] In the food security system, granaries are key infrastructure, and the rationality and scientificity of their design are directly related to the storage safety, operational efficiency and stability of the entire food supply chain.

[0003] Traditional granary design relies primarily on 2D CAD drawings and empirical experience, but this approach suffers from significant deficiencies in visualization and communication efficiency. 2D drawings struggle to intuitively represent the silo's internal spatial layout, grain stack height, and the spatial relationships between its various components. This leads to misunderstandings between designers, builders, and operators, increasing the time and cost of adjusting plans. Furthermore, key aspects such as silo capacity calculations rely heavily on fixed parameters and the designer's experience, lacking a comprehensive quantitative analysis of complex factors such as climate characteristics, grain variety characteristics, and grain circulation efficiency. Regional differences in climate, the mass density and physical properties of different grain varieties, and the varying frequency of grain in and out of silos and mechanized operation requirements make it difficult to accurately assess these factors using empirical parameters alone. This can easily lead to problems such as insufficient silo capacity, excessive energy consumption, and low grain storage safety after construction.

[0004] Furthermore, in the traditional design process, warehouse capacity calculation, structural design, and cost estimation are independent processes, lacking data linkage and collaborative optimization mechanisms. For example, increasing warehouse capacity may lead to increased structural load and higher costs, but designers cannot understand the impact of different design parameters on cost and safety in real time. This requires repeated manual adjustments, which is inefficient and prone to overlooking key constraints.

[0005] With the development of digital technology, although some research has attempted to incorporate 3D modeling and simple simulation techniques, significant limitations remain. Existing simulations are often confined to a single physical field and fail to fully consider the interplay of multiple physical factors, such as grain physical properties, in-warehouse airflow, and temperature and humidity diffusion. This makes it impossible to accurately assess risks such as condensation and mold during grain storage. Furthermore, model databases are often static and pre-set, lacking the ability to learn from and iterate on historical project data, making it difficult to automatically adapt and optimize design solutions to the specific needs of different regions.

[0006] When it comes to multi-party collaborative design, design, construction, and operations currently rely primarily on offline document transfers, lacking tools and platforms for real-time collaboration. This results in untimely and inaccurate information transfer, the inability to synchronize design modifications in real time, and frequent design changes during the construction phase, seriously impacting project progress and quality.

[0007] The trend toward smart granary construction is driving higher demands on granary design technology. These requirements include achieving digital management throughout the entire granary lifecycle, achieving a balanced optimization among multiple objectives such as storage capacity, construction cost, energy consumption, and safety, and improving adaptability and response to extreme conditions such as natural disasters like earthquakes and rainstorms, as well as sudden changes in grain conditions. However, existing granary design technology has significant shortcomings in 3D visual communication, dynamic adaptation of multiple factors, full-process simulation optimization, and real-time collaboration among multiple parties, failing to meet the demands of modern smart granary construction. Therefore, a systematic solution is urgently needed that integrates advanced 3D modeling, machine learning, multi-physics simulation, and collaborative interaction technologies to enhance the accuracy, intelligence, and efficiency of granary design. Summary of the Invention

[0008] The main purpose of this application is to provide a granary design method, device, equipment and storage medium based on a three-dimensional model to solve the problem in the prior art that it takes a lot of time to transport workpieces back and forth across different workshops, resulting in excessively high time costs for producing chemical pumps, thereby further restricting the production efficiency of the pump body.

[0009] To achieve the above objectives, this application provides the following technical solutions:

[0010] A granary design method based on a three-dimensional model, characterized in that the design method includes:

[0011] Acquiring original feature information of the target granary, and preprocessing the original feature information to obtain preprocessed feature information;

[0012] Based on the pre-processed feature information, a three-dimensional model of the target granary is generated using building information modeling technology;

[0013] Acquire a target granary design model that matches the three-dimensional model from a pre-stored model database;

[0014] Conducting simulation tests on the target granary design model to obtain simulation test results that include at least grain storage safety, full life cycle cost, and adaptability to extreme working conditions;

[0015] The simulation test results are judged according to preset judging criteria. When the judging results meet the preset qualification conditions, the design scheme of the target granary is output; if not, the process returns to the step of re-obtaining the matching design model from the pre-stored model database until the judging results are qualified.

[0016] As a further improvement of the present application, the original feature information includes at least building height, building depth, building width, grain pile height, grain mass density, climate characteristics and grain circulation efficiency, wherein the building height, building depth and building width data are collected by sensors, grain mass density, average annual humidity and other data are obtained from historical data records, and grain circulation efficiency-related data are obtained through user input; preprocessing the original feature information includes using a sliding window filtering algorithm to filter outliers in the spatial dimension data, the sliding window size is dynamically adjusted according to historical project data, and the original feature information is filtered outliers to obtain the preprocessed feature information.

[0017] As a further improvement of the present application, the step of obtaining the target granary design model from the model database includes:

[0018] Obtain historical granary project data and use machine learning algorithms to train the pre-processed historical granary project data, including storage capacity, grain variety, construction cost, operating results, climate characteristics, and grain circulation efficiency;

[0019] Constructing a neural network model comprising an input layer, a hidden layer, and an output layer, inputting the preprocessed target granary feature information into the neural network model, and calculating a comprehensive design score;

[0020] Based on the comprehensive design score, the target granary design model is matched from the model database using a cosine similarity algorithm, and the model database is self-iteratively optimized using an incremental learning algorithm.

[0021] As a further improvement of the present application, the step of performing simulation testing on the target granary design model includes:

[0022] Constructing a multi-physics field coupling simulation model, the model including physical property parameters of pre-processed grain, an airflow field model in the warehouse, a temperature and humidity diffusion model, and a structural mechanics model;

[0023] Based on the multi-physics field coupling simulation model, the load-bearing capacity of the walls and roof is evaluated through finite element analysis. The heat diffusion process of grain respiration is simulated through the heat conduction equation. The temperature and humidity distribution cloud map and structural stress-strain curve are output. The risk of grain condensation at different grain stacking heights is simulated, and the critical stacking height safety threshold is calculated.

[0024] A full life cycle cost model is introduced, which includes a pre-processed construction investment function, an operating energy consumption function, and a maintenance cost function, and a multi-objective optimization solution set of "warehouse capacity-cost-energy consumption" is generated through a Pareto optimal algorithm.

[0025] As a further improvement of the present application, the method further includes constructing a digital twin model of the target granary based on the preprocessed BIM modeling parameters, wherein the digital twin model includes a full-factor mapping of geometric information, material properties, and equipment layout;

[0026] Use augmented reality technology to achieve superimposed display of 3D models and real scenes, and use virtual reality technology to achieve immersive roaming interaction;

[0027] A parameter linkage module is set in the three-dimensional model interface to adjust the pre-processed building size parameters, and to synchronously update the calculation results of the warehouse capacity calculation formula, cost estimation and simulation test data in real time.

[0028] As a further improvement of the present application, in the simulation test execution step, natural disaster conditions and sudden changes in grain conditions are preset, and the structural mechanical properties of the target granary design model under natural disaster conditions are evaluated through finite element analysis. The risk factors of the target granary design model under sudden changes in grain conditions are analyzed through a fault tree model, and reinforcement suggestions for weak links in the structure are output based on the finite element analysis and fault tree model.

[0029] As a further improvement of the present application, in the test result evaluation step, the preset evaluation criteria include a grain storage safety index, a full life cycle cost index, and an extreme working condition adaptability index.

[0030] To achieve the above objectives, this application also provides the following technical solutions:

[0031] A granary design device based on a three-dimensional model, comprising:

[0032] A preprocessing module is used to obtain original feature information of the target granary, preprocess the original feature information, and obtain preprocessed feature information;

[0033] A construction module, wherein the construction module is used to generate a three-dimensional model of the target granary based on the pre-processed feature information using building information modeling technology;

[0034] A matching module, the matching module is used to obtain a target granary design model that matches the three-dimensional model from a pre-stored model database;

[0035] A testing module, wherein the testing module is used to perform simulation testing on the target granary design model to obtain simulation test results including at least grain storage safety, full life cycle cost, and adaptability to extreme working conditions;

[0036] The evaluation module is used to evaluate the simulation test results according to preset evaluation criteria. When the evaluation results meet the preset qualification conditions, the design scheme of the target granary is output; if not, the design scheme of the target granary is returned to the step of re-obtaining the matching design model from the pre-stored model database until the evaluation results are qualified.

[0037] To achieve the above objectives, this application also provides the following technical solutions:

[0038] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned granary design method based on the three-dimensional model is implemented.

[0039] To achieve the above objectives, this application also provides the following technical solutions:

[0040] A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned granary design method based on a three-dimensional model.

[0041] To achieve the above objectives, this application also provides the following technical solutions:

[0042] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the granary design method based on the three-dimensional model as described above is implemented.

[0043] To achieve the above objectives, this application also provides the following technical solutions:

[0044] A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned granary design method based on a three-dimensional model.

[0045] Beneficial effects: The present invention preprocesses multi-dimensional characteristic information such as building size, grain variety characteristics, and climatic conditions, effectively filters out abnormal data and standardizes processing, providing a reliable data basis for subsequent modeling and simulation, reducing grain storage safety hazards and resource waste caused by data deviations in traditional designs, and ensuring that core parameters such as warehouse capacity calculation and structural design are more in line with actual needs.

[0046] This invention uses building information modeling (BIM) to construct a three-dimensional visualization model, and combines augmented reality (AR) and virtual reality (VR) technologies to achieve immersive interaction, allowing designers, builders, and operators to intuitively view the spatial layout and parameter impact of the granary. It supports real-time adjustment of building dimensions and synchronous updates of warehouse capacity, construction costs, and simulation results, significantly improving communication efficiency among multiple parties, shortening the plan adjustment cycle, and reducing design changes caused by misunderstandings.

[0047] The present invention also comprehensively evaluates the safety and reliability of granaries under different storage conditions and extreme working conditions by integrating multi-physics field simulation models such as grain physical properties, airflow field in the silo, and structural mechanics. At the same time, it introduces full life cycle cost analysis to balance multiple objective requirements such as storage capacity, construction cost, and energy consumption, avoiding the limitations of single indicator optimization in traditional design and improving the economy and practicality of the granary throughout its entire cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a schematic diagram of the steps of an embodiment of a granary design method based on a three-dimensional model of the present application;

[0049] Figure 2 Schematic diagram of the steps for matching the 3D model of this application with the target granary design model;

[0050] Figure 3 Schematic diagram of the simulation test process for the target granary design model for this application;

[0051] Figure 4 This is a schematic diagram of the functional modules of an embodiment of a granary design device based on a three-dimensional model of the present application;

[0052] Figure 5 This is a structural diagram of an embodiment of the electronic device of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] like Figure 1 As shown, in order to solve the problems in the background technology, the present invention provides a granary calculation and design method based on a three-dimensional model, comprising the following steps:

[0055] S1. Obtain the original characteristic information of the target granary through multiple sources. The characteristic information includes spatial parameters such as building height H, depth l0, width b0, grain pile height h, grain mass density ρ, as well as climate characteristics such as annual average humidity w, extreme weather frequency r, and in-and-out frequency f. t , mechanized operation requirements, and other operational parameters to ensure that the data covers all dimensional factors affecting granary design. Systematic preprocessing is performed on the raw data. Sliding window filtering and the interquartile range method are combined to detect building dimension anomalies. Local median interpolation is used to repair abnormal data points. Grain physical parameters and climate data are normalized to eliminate dimensional differences. Operational parameters are uniformly converted into a standard unit system to form high-quality input data.

[0056] S2. Based on the preprocessed feature information, a three-dimensional model of the target granary is constructed using Building Information Modeling (BIM) technology. This model integrates all elements, including geometric structure, material properties, and equipment layout, and is mapped to the physical entity through digital twin technology. Augmented reality (AR) or virtual reality (VR) technology is used to achieve an immersive interactive display of the model, allowing users to adjust the building size by dragging and dropping. The system also synchronizes and updates the calculation results of the warehouse capacity calculation formula, cost estimates, and multi-physics field simulation data in real time, forming an intuitive parameter linkage feedback mechanism.

[0057] S3. When obtaining a matching design model from a pre-stored self-iterative model database, a machine learning algorithm, which in this case may be a gradient boosting decision tree or a multi-layer perceptron, is used to train historical granary project data, construct a neural network model including an attention mechanism to dynamically adjust the weights of climate and operational parameters, calculate a comprehensive design score, and match the optimal model using a cosine similarity algorithm;

[0058] S4. Conduct multi-physics coupling simulation on the matching design model, integrating the physical properties of grain, airflow field in the warehouse, temperature and humidity diffusion, and structural mechanics models to simulate different grain storage conditions and extreme working conditions, and generate grain storage safety assessments, full life cycle cost analysis, and risk response recommendations.

[0059] S5. Finally, the simulation results are intelligently screened based on preset multi-dimensional evaluation criteria such as grain storage safety, cost control, and working condition adaptability. Qualified solutions are directly output, and unqualified solutions trigger iterative optimization of model matching and simulation until the design requirements are met.

[0060] In a further embodiment, generating a three-dimensional model of a target granary using building information modeling technology includes the following steps:

[0061] S21. Construction of the BIM 3D model specifically includes: Geometry: Using Revit software, accurately draw the granary's geometry based on the acquired architectural space parameters. Starting with the basic walls, roof, floor, and other major components, determine their shape, size, and relative position.

[0062] Material Property Definition: Define the building material properties for each component in the model. For walls, if C30 concrete is used, set parameters such as compressive strength, density, and thermal conductivity in the software. For insulation, if polystyrene foam board is used, set properties such as thermal insulation performance and bulk density.

[0063] Equipment Layout Planning: Rationally arrange various equipment within the BIM model, such as ventilators, conveyors, and temperature measurement cables. Determine the installation location and quantity of ventilators based on the grain silo's operational needs and process flow to ensure even air circulation within the silo. Plan conveyor routes to efficiently move grain in and out of the silo. Arrange temperature measurement cables to ensure comprehensive and accurate monitoring of grain temperature changes within the silo.

[0064] S22. The implementation of AR / VR interactive functions specifically includes: AR scene overlay: With the help of augmented reality technology, the constructed three-dimensional model is superimposed on the real-life image of the actual site. The corresponding AR application is installed on the mobile terminal device to scan the actual site environment. The program uses the device's camera to obtain the real-life image and accurately superimposes the three-dimensional model on the corresponding position. When design-related personnel conduct field surveys, they can use mobile devices to intuitively see the spatial relationship between the granary model and the surrounding terrain and buildings, and judge whether its layout is reasonable. Virtual reality technology is used to provide users with an immersive experience. In the VR scene, users can walk and observe freely, and view the internal structure and equipment layout of the granary from different angles and distances.

[0065] S23. Parameter linkage module settings, specifically including: Warehouse capacity calculation linkage: In the three-dimensional model interactive interface, set the parameter linkage function related to warehouse capacity calculation. When the user adjusts the building size through interactive operations, the system automatically calls the preset warehouse capacity calculation formula and packaging warehouse calculation formula for real-time calculation, and displays the latest warehouse capacity results on the interface. Establish a linkage mechanism related to cost estimation. According to the adjusted building size and material properties, the system automatically calculates the changes in the amount of building materials, and combines the current market material prices and equipment prices to estimate the changes in cost. For example, when the area of the warehouse body is expanded, the system immediately calculates the increase in the amount of materials such as concrete and steel required, as well as the corresponding cost increase values, and displays them on the interface.

[0066] Multi-physics simulation data linkage: Establishing a data connection with the multi-physics simulation module allows for timely updates of preliminary multi-physics simulation data when building dimensions or equipment layouts change. For example, after adjusting the size and position of vents, the system quickly simulates changes in the airflow field within the warehouse, displaying preliminary simulation results such as airflow velocity and pressure distribution on the interface. Changing the insulation properties of wall materials also updates the simulation data for temperature and humidity diffusion.

[0067] like Figure 2 As shown, in a further embodiment, step S3 of obtaining a target granary design model matching the three-dimensional model from a pre-stored model database specifically includes:

[0068] Step S31: Build a self-iterating model database containing a large amount of historical granary project data. This data covers multiple dimensions, including storage capacity, grain variety, construction cost, operational performance, climate characteristics (such as average annual humidity and frequency of extreme weather events), and grain circulation efficiency (such as inflow and outflow frequency and mechanization requirements). This database has an automatic update mechanism that can incorporate complete data from newly completed projects in real time, including various parameters from the design phase and actual operational performance data from the operational phase, continuously expanding and optimizing the database content.

[0069] This data step covers multiple dimensions, including warehouse capacity (Q1), grain variety (G), construction cost (C), operational performance (P), climate characteristics (such as average annual humidity (H) and frequency of extreme weather events (F), and grain circulation efficiency (such as in-and-out frequency (I) and mechanized operation requirements (M)). The database features an automatic update mechanism that allows it to incorporate complete data from newly completed projects in real time, including parameters from the design phase and actual operational performance data from the operational phase, continuously expanding and optimizing its content.

[0070] Step S32: Use a gradient boosted decision tree (GBDT) or multi-layer perceptron (MLP) algorithm to deeply train the data in the self-iterative model database and construct a dynamic adaptation model. Through the hidden layer attention mechanism of the neural network, the model automatically learns the weights of how different climate characteristics and operational parameters influence the design. For example, in humid climates, the model will increase the weight of humidity-related parameters on ventilation and moisture-proof design; in scenarios with a high degree of mechanized operations, it will increase the weight of parameters such as the frequency of entering and exiting the warehouse and the adaptability of equipment on the layout design.

[0071] In this step, taking the multilayer perceptron as an example, let the number of neurons in the input layer be n, and the corresponding input feature vector X = (x1, x2...x n ), where x1 is the annual average humidity H, x2 is the frequency of entering and leaving the warehouse I, and x i are multiple dimensional parameters in step S31 of the present invention. The hidden layer has m neurons, and the input of the jth hidden layer neuron is where w ij is the weight from the jth neuron in the input layer to the jth neuron in the hidden layer, b j is the bias. Through the activation function σ(net j )(For example, the ReLU function σ(x)=max(0,x) obtains the hidden layer output h j =σ(net j The number of neurons in the output layer depends on the task. Let the input of the kth neuron in the output layer be net k =∑ j -1 m w jk h j +b k , the final output layer outputs the predicted value The model automatically learns different climate characteristics (such as H) and operation parameters (such as I, M) and building space parameters (such as h) through the hidden layer attention mechanism of the neural network. n 、l n 、w b ), food physical properties (such as h g , ρ) on the design options. For example, in humid climates (high H values), the model will increase the weight of humidity-related parameters on ventilation and moisture-proof design. In scenarios with a high degree of mechanization (large M values) and a high frequency of in-and-out warehouses (large I values), the model will increase the weight of these parameters on layout design.

[0072] Step S33: The characteristic information of the target granary (building space parameter h b 、l b 、w b 、Grain physical properties g ,ρ, climate and environmental conditions H,F, and operation and management requirements I,M) are input into the trained dynamic adaptation model. The model uses complex algorithm calculations to comprehensively consider various dimensional factors and their weights to generate a comprehensive design score S that can fully evaluate the rationality of the design scheme. Assume that the multiple prediction values output by the model are The weights of the factors corresponding to each dimension are α1, α2,…, α s , where α1 corresponds to the weight of the annual average humidity H, α2 corresponds to the weight of the frequency of entering and leaving the warehouse I, etc. The design comprehensive score The score reflects the comprehensive performance of the target granary design in meeting various needs and adapting to specific environmental conditions.

[0073] Step S34: The specific steps of using the cosine similarity algorithm are to compare the calculated design comprehensive score with the existing design scheme scores in the self-iterative model database. Let the target granary design comprehensive score be S t, a design solution in the database is scored as S d , which are represented as vector S t and S d , where S t Contains the h of the target granary b 、l b 、w b 、h g , ρ, H, F, I, M and other parameters are calculated by the model to obtain the score correlation value, S d Similarly, the cosine similarity By calculating the cosine similarity between the score vectors, the design model that best matches the target granary design's overall score is retrieved from the database. For example, if the target granary design's overall score is 85, and a design scheme in the database has the highest cosine similarity with that score, close to 1, then that scheme will be prioritized as the matching model.

[0074] Step S35: The self-iterative model database has incremental learning capabilities. Whenever new completed project data is added, the database automatically triggers the model update mechanism. The machine learning model is retrained using the new data to adjust the model parameters and weights. Taking the multi-layer perceptron as an example, the stochastic gradient descent method is used to update the weight w and bias b. Assuming the learning rate is η and the loss function is L, the weight update formula is: The bias update formula is: The new data contains the building space parameters of newly completed projects (such as h b 、l b 、w b ), food physical properties (such as h g , ρ), climate and environmental conditions (such as H and F), and operational management requirements (such as I and M). Matching rules are optimized by continuously updating model parameters. For example, a newly completed project in a high-altitude area (corresponding to special climate and environmental conditions) adopted a special structural design (involving adjustments to building space parameters) to cope with the low-pressure environment. The database incorporates this information and updates the model, allowing subsequent granary designs in high-altitude areas to be accurately matched to the appropriate design model, continuously improving the database's ability to match design solutions for different regions, different grain varieties, and diverse operational needs.

[0075] like Figure 3 As shown, in a further embodiment, step S4 is to perform a simulation test on the target granary design model to obtain simulation test results including at least grain storage safety, life cycle cost, and adaptability to extreme working conditions; which specifically includes:

[0076] Step S41: construct a multi-physics field coupling simulation model that integrates grain physical property parameters, an airflow field model in a warehouse, a temperature and humidity diffusion model, and a structural mechanics model.

[0077] In terms of the physical properties of grain, the heat generated by grain respiration heat Q resp It can be expressed as Q resp =q resp V grain , where q resp is the respiratory heat production rate per unit volume of grain, V grain is the volume of grain, V g rain=h g A floor ,h g is the grain pile height, A floor is the warehouse bottom area, A flaor =l b w b ,l b and w b are the depth and width of the granary respectively. The specific heat capacity of grain c grain Affects its temperature change, temperature change ΔT grain Satisfy Q=mc grain ΔT grain , m=ρV grain , ρ is the mass density of grain. The airflow field in the silo is simulated by solving the Navier-Stokes equations based on the computational fluid dynamics (CFD) model. In the Cartesian coordinate system, the mass conservation equation is where ρ a ir is the air density, u=(u,v,w) is the air velocity vector, u, v, w are the velocity components in the x, y, and z directions respectively. The momentum conservation equation is p is the pressure, τ is the viscous stress tensor, is the gravitational acceleration vector.

[0078] Temperature and humidity diffusion model, the diffusion of temperature T in the warehouse satisfies the heat conduction equation where c p , air is the specific heat capacity of air at constant pressure, and k is the thermal conductivity. Humidity diffusion is calculated through the mass transfer equation Description, ρ v is the water vapor density, D is the water vapor diffusion coefficient, S v is the water vapor source term, which is related to the moisture content of grain and the ambient humidity, such as S v =f(H,ρ grain ), H is the average annual humidity, ρ grain is the grain mass density. The structural mechanics model discretizes the granary structure into a finite number of units through finite element analysis (FEA). Taking the plane problem of elastic mechanics as an example, the unit node displacement vector d e=[u1,v1,u2,v2,…] T , element stress vector Establish the relationship σ through the elastic matrix D and the geometric matrix B e =DBd e , the equilibrium equation of the overall structure is is the overall stiffness matrix, d is the overall node displacement vector, is the external force vector, which includes gravity, wind pressure, etc. C d Drag coefficient, v wibd Wind speed.

[0079] Step S42: Simulation calculation under different design parameters: for different grain pile heights h g , ventilation structure (vent area A vent 、Ventilation position coordinates (x vent ,y vent ,z vent )) and other design parameters to simulate the granary.

[0080] When simulating ventilation in grain storage structures, the dew point temperature T is calculated based on the wet temperature distribution. dew , using the Antoine equation Among them, A, B, and C are material characteristic constants, and p v is the water vapor partial pressure, calculated from humidity and temperature R is the gas constant, M v is the molar mass of water vapor. When the temperature T at a certain point in the warehouse is lower than T dew There is a risk of condensation.

[0081] Calculate the safety critical pile height h crit , considering the pressure of grain pile on the structure and the ventilation and heat dissipation requirements. Assume that the lateral pressure plateral of grain on the silo wall satisfies Janssen formula plateral=Kρgraingh, where K is the lateral pressure coefficient, g is the acceleration of gravity, and h is the grain height. When the lateral pressure exceeds the design bearing pressure Pallow of the silo wall, there is a safety hazard in the structure. Combined with ventilation and heat dissipation conditions (such as ventilation volume Q vent =A vent v vent , v vent is the wind speed at the ventilation outlet), and the safety critical stack height h is calculated by iteration. crit .

[0082] Analyze the influence of ventilation system on temperature and humidity distribution, ventilation volume Q vent Change the air flow and temperature and humidity exchange in the warehouse. Taking temperature as an example, the temperature change rate in the warehouse The relationship with ventilation volume can be derived through the energy balance equation. Q in and Q out are the heat flowing in and out, respectively, which are related to the ventilation volume and air temperature, such as Q in =Q vent ρ air c pair T in , T in is the temperature of the air flowing into the vent. The temperature and humidity distribution under different ventilation structures are obtained by numerically solving the equation.

[0083] Step S43, full life cycle cost model analysis: Introduce the full life cycle cost model and comprehensively consider the construction investment C const and operating energy consumption C oper .

[0084] Construction investment includes land cost C land 、Construction material cost C mat , Equipment purchase cost C equip etc., C. const =C land +C mat +C equip .

[0085] Cost of building materials C mat Related to material usage and unit price, such as concrete usage V conc =l·w·h wall (h wall is the wall thickness), then the unit price of concrete is p conc , then the concrete cost C mat,conc =p conc V conc Similar calculation of other material costs and cumulative calculation to get C mat Equipment purchase cost C equip Determined based on the number and unit price of ventilators, conveyors and other equipment, such as the number of ventilators n fan , unit price P fan , then the fan cost C equip,fan =n fan P fan , add up the cost of various equipment to get C equip .

[0086] Operational energy consumption mainly includes ventilation energy consumption E vent , refrigeration energy consumption E cool , lighting energy consumption E light etc., C. oper =E vent +E cool +E light . Ventilation energy consumption E vent =P fan tvent , P fan is the fan power, t vent is the ventilation time, which is related to the air inlet and outlet frequency I, the annual average humidity H, etc., such as t vent =f(I,H). Refrigeration energy consumption E cool According to the indoor temperature control requirements and refrigeration equipment performance calculation, lighting energy consumption E light =P light t light , P light is the lighting equipment power, t light It is the lighting time, which is related to operation and management needs.

[0087] Generate the multi-objective optimization solution set of "capacity-cost-energy consumption" through Pareto optimal algorithm. Let the capacity be Q and the cost be C total =C const +C oper , energy consumption is E total =E vent +E cool +E light The Pareto optimal solution is the solution that satisfies certain constraints and prevents the three objective functions from being improved at the same time. By constructing the objective function vector F = [Q, C total ,E total ], and use the optimization algorithm (such as non-dominated sorting genetic algorithm NSGA-II) to search and obtain a set of Pareto optimal solutions S = {s1, s2, ...}, each solution s i Corresponding to a set of design parameter combinations (such as h g ,A vent etc.), providing designers with a variety of options that take into account different needs.

[0088] Step S44: Preset extreme working condition risk assessment and response suggestion output: Preset extreme working conditions such as earthquakes, rainstorms, and insect pest outbreaks, perform risk assessment on the design model, and output response suggestions.

[0089] Among them, under earthquake conditions, the earthquake response spectrum theory is used to evaluate the mechanical performance of the structure. E =kαG, k is the seismic coefficient, α is the seismic influence coefficient, which is related to the earthquake intensity, site type, etc., and G is the representative value of the total gravity load of the structure. The stress σ of the structure under earthquake action is calculated by finite element analysis. E and displacement δ E , and the allowable stress σ of the structure allow and allowable displacement δ allow Compare and judge whether the structure is safe. E >σ allow or δ E >δ allowOutput structural reinforcement suggestions, such as adding supports, strengthening nodes, etc., and the structural parameters after reinforcement (such as support cross-sectional area A support , node reinforcement S joint ) is determined by structural mechanics calculations.

[0090] Under heavy rain conditions, the drainage capacity of the roof is evaluated. The relationship between rainfall R and time t is R = f(t), and the roof rainwater flow Q rain =C d A roof R, C d is the runoff coefficient, A roof The drainage capacity of the roof drainage system is Q drain The diameter of the drainage pipe d pipe , slope i parameter is determined by Manning formula n is the roughness coefficient, A pipe is the cross-sectional area of the pipe through which water passes, R n Is the hydraulic radius. If Q rain >Q drain , output response suggestions such as increasing the number of drainage pipes, increasing the main pipe diameter, etc. The new drainage pipe parameters are determined through hydraulic calculations.

[0091] Under the condition of pest outbreak, the root condition mutation risk is analyzed by pest transmission model. Assuming the pest transmission rate v infest and grain moisture content w grain , temperature T, humidity H, etc., v infest =f(w grain ,T,H). By establishing pest spread equations, such as the diffusion equation p infest is the pest density, D infest is the pest diffusion coefficient, simulating the spread of pests. When the pest density exceeds the threshold p thresh Output root control suggestions, such as the type and dosage of insecticides to be used pest and fumigation time t fumigate , determined according to the type of pest and the warehouse environment.

[0092] Step S5: The simulation test results are evaluated according to the preset evaluation criteria. When the evaluation results meet the preset qualification conditions, the design scheme of the target granary is output; if not, the design scheme of the target granary is returned to the step of re-obtaining the matching design model from the pre-stored model database until the evaluation results are qualified.

[0093] Specific evaluation criteria include: the condensation area must not exceed 5% of the total warehouse area, calculated by comparing the dew point temperature with the actual warehouse temperature. The pest density must not exceed 10 per cubic meter during storage, as determined by a pest transmission model. The grain mold rate must not exceed 2% during storage, as determined by a grain quality deterioration model.

[0094] Cost Control: Construction investment cannot exceed 110% of the budget, which includes land, materials, equipment, and other costs. Annual operating energy consumption must be between 90% and 110% of the average energy consumption of similar granaries. Operating energy consumption includes ventilation, cooling, lighting, and other energy consumption.

[0095] Adaptability to working conditions: During an earthquake, the maximum structural displacement must not exceed 1.2 times the allowable displacement, and the stress must not exceed the allowable stress, calculated according to earthquake response spectrum theory. During heavy rain, the roof drainage system must drain rainwater at a 50-year rainfall intensity within one hour, calculated based on rainfall volume and drainage capacity. During high winds, structural deformation and stress in key areas must remain within normal ranges at the design wind speed, analyzed using wind pressure formulas combined with structural mechanics.

[0096] The simulation test results are then compared against the aforementioned standards one by one. For example, this includes calculating the percentage of condensation area and calculating construction investment. If all criteria are met, the project is deemed qualified; if any one item is not met, the project is deemed unqualified. If the evaluation is qualified, a design plan is output, including architectural drawings, a bill of materials, an equipment configuration list, and operational management recommendations. If the evaluation is unqualified, the system automatically returns to the step of obtaining a matching design model from the model database, recalculating the score, selecting models, performing simulation tests, and conducting the evaluation until a qualified plan is output.

[0097] like Figure 4 As shown, a device for implementing a granary design method based on a three-dimensional model provided in a specific embodiment of the present invention is introduced, and the device includes:

[0098] A preprocessing module 201 is used to obtain original feature information of the target granary and preprocess the original feature information to obtain preprocessed feature information;

[0099] A construction module 202 is configured to generate a three-dimensional model of a target granary using building information modeling technology based on the pre-processed feature information;

[0100] A matching module 203 is used to obtain a target granary design model that matches the three-dimensional model from a pre-stored model database;

[0101] A testing module 204 is configured to perform a simulation test on the target granary design model to obtain simulation test results that include at least grain storage safety, full life cycle cost, and adaptability to extreme working conditions;

[0102] Evaluation module 205 is used to evaluate the simulation test results according to preset evaluation criteria. If the evaluation results meet the preset eligibility criteria, the design scheme for the target granary is output. If not, the design scheme returns to the step of retrieving a matching design model from the pre-stored model database until the evaluation results are qualified.

[0103] Figure 5 According to an embodiment of this specification, a hardware structure diagram of a computing device 30 for a 3D model-based granary design method is shown. The computing device 30 may include at least one processor 301, a memory 302 (e.g., a non-volatile memory), a storage 303, and a communication interface 304. The at least one processor 301, the storage 302, the storage 303, and the communication interface 304 are connected together via a bus 305. The at least one processor 301 executes at least one computer-readable instruction stored or encoded in the storage 302.

[0104] It should be understood that the computer executable instructions stored in the memory 302, when executed, cause the at least one processor 301 to perform the above combined operations in the various embodiments of this specification. Figure 1-4 Describes the various operations and functions.

[0105] In the embodiments of the present specification, the computing device 30 may include, but is not limited to, a personal computer, a server computer, a workstation, a desktop computer, a laptop computer, a notebook computer, a mobile computing device, a smart phone, a tablet computer, a cellular phone, a personal digital assistant (PDA), a handheld system, a messaging device, a wearable computing device, a consumer electronic device, and the like.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0107] The functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0108] The above detailed description of the specific embodiments of the invention is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions of the invention are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A granary design method based on a three-dimensional model, characterized in that: The design method includes: Acquiring original feature information of the target granary, and preprocessing the original feature information to obtain preprocessed feature information; Based on the pre-processed feature information, a three-dimensional model of the target granary is generated using building information modeling technology; Acquire a target granary design model that matches the three-dimensional model from a pre-stored model database; Conducting simulation tests on the target granary design model to obtain simulation test results that include at least grain storage safety, full life cycle cost, and adaptability to extreme working conditions; The simulation test results are judged according to preset judging criteria. When the judging results meet the preset qualification conditions, the design scheme of the target granary is output; if not, the process returns to the step of re-obtaining the matching design model from the pre-stored model database until the judging results are qualified.

2. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: The original characteristic information at least includes building height, building depth, building width, grain stack height, grain mass density, climate characteristics and grain circulation efficiency, wherein the building height, building depth and building width data are collected by sensors, grain mass density and annual average humidity data are obtained from historical data records, and data related to grain circulation efficiency are obtained through user input; preprocessing the original characteristic information includes using a sliding window filtering algorithm to filter outliers in the spatial dimension data, the sliding window size is dynamically adjusted according to historical project data, and the original characteristic information is filtered outliers to obtain the preprocessed characteristic information.

3. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: The step of obtaining the target granary design model from the model database includes: Obtain historical granary project data and use machine learning algorithms to train the pre-processed historical granary project data, including storage capacity, grain variety, construction cost, operating results, climate characteristics, and grain circulation efficiency; Constructing a neural network model comprising an input layer, a hidden layer, and an output layer, inputting the preprocessed target granary feature information into the neural network model, and calculating a comprehensive design score; Based on the comprehensive design score, the target granary design model is matched from the model database using a cosine similarity algorithm, and the model database is self-iteratively optimized using an incremental learning algorithm.

4. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: The steps of performing simulation testing on the target granary design model include: Constructing a multi-physics field coupling simulation model, the model including physical property parameters of pre-processed grain, an airflow field model in the warehouse, a temperature and humidity diffusion model, and a structural mechanics model; Based on the multi-physics field coupling simulation model, the load-bearing capacity of the walls and roof is evaluated through finite element analysis. The heat diffusion process of grain respiration is simulated through the heat conduction equation. The temperature and humidity distribution cloud map and structural stress-strain curve are output. The risk of grain condensation at different grain stacking heights is simulated, and the critical stacking height safety threshold is calculated. A full life cycle cost model is introduced, which includes the pre-processed construction investment function, operation energy consumption function, and maintenance cost function. The Pareto optimal algorithm is used to generate a multi-objective optimization solution set of "warehouse capacity-cost-energy consumption".

5. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: The method further includes constructing a digital twin model of the target granary based on the preprocessed BIM modeling parameters, wherein the digital twin model includes a full-factor mapping of geometric information, material properties, and equipment layout; Use augmented reality technology to achieve superimposed display of 3D models and real scenes, and use virtual reality technology to achieve immersive roaming interaction; A parameter linkage module is set in the three-dimensional model interface to adjust the pre-processed building size parameters, and to synchronously update the calculation results of the warehouse capacity calculation formula, cost estimation and simulation test data in real time.

6. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: In the simulation test execution step, natural disaster conditions and sudden changes in grain conditions are preset, and the structural mechanical properties of the target granary design model under natural disaster conditions are evaluated through finite element analysis. The risk factors of the target granary design model under sudden changes in grain conditions are analyzed through a fault tree model, and reinforcement suggestions for weak links in the structure are output based on the finite element analysis and fault tree model.

7. The granary design method based on a three-dimensional model according to claim 1 is characterized in that: In the test result evaluation step, the preset evaluation criteria include a grain storage safety index, a full life cycle cost index, and an extreme working condition adaptability index.

8. A granary design device based on a three-dimensional model, which is applied to the granary design method based on a three-dimensional model as claimed in any one of claims 1 to 7, characterized in that: The granary design device based on the three-dimensional model includes: A preprocessing module is used to obtain original feature information of the target granary, preprocess the original feature information, and obtain preprocessed feature information; A construction module, wherein the construction module is used to generate a three-dimensional model of the target granary based on the pre-processed feature information using building information modeling technology; A matching module, the matching module is used to obtain a target granary design model that matches the three-dimensional model from a pre-stored model database; A testing module, wherein the testing module is used to perform simulation testing on the target granary design model to obtain simulation test results including at least grain storage safety, full life cycle cost, and adaptability to extreme working conditions; The evaluation module is used to evaluate the simulation test results according to preset evaluation criteria. When the evaluation results meet the preset qualification conditions, the design scheme of the target granary is output; if not, the design scheme of the target granary is returned to the step of re-obtaining the matching design model from the pre-stored model database until the evaluation results are qualified.

9. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, it implements the granary design method based on a three-dimensional model as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores program instructions, which, when executed by a processor, can implement the granary design method based on a three-dimensional model as described in any one of claims 1 to 7.

Images