Hydraulic metal structure design method based on big data technology

Abstract

The invention provides a hydraulic metal structure design method based on a big data technology, and relates to the field of structure design. The hydraulic metal structure design method based on the big data technology specifically comprises the following steps that 1, a structure database is constructed, and structures of the same type in the structure database are obtained and classified according to feature vectors; step 2, acquiring structural data required for associating with external data based on the feature vector, performing association analysis verification according to the identification model, and selecting optimal structural data based on a particle swarm optimization algorithm; and 3, calculating a hydraulic metal structure load factor according to a formula, and establishing a basic standard hydraulic metal structure model based on the load factor. A basic module is formed to independently serve as a basic structure diagram of a corresponding hydraulic metal structure, so that rapid assembly, design and combination are completed; and meanwhile, the load factor analysis verification of the assembled structure body can be quickly carried out, and the intelligent and precise risk assessment verification of the hydraulic structure is realized.

Description

Technical Field

[0001] The present invention relates to the field of structural design, and in particular to a hydraulic metal structure design method based on big data technology. Background Art

[0002] Hydraulic metal structures generally include gates, hoists, trash racks, penstocks and trash cleaning machines. At present, the design method of hydraulic metal structures mainly adopts the allowable stress method specified in the code. First, the type and layout of the hydraulic metal structure are determined according to the overall situation of the hydraulic structure, engineering geological conditions, meteorological conditions, manufacturing, installation and transportation conditions and engineering experience. Then, the hydraulic metal structure is equivalently simplified into various plane structures, and then the structural mechanics and material mechanics methods are used for analysis and verification. The analysis results are then compared with the values ​​specified in the code. If the code requirements are met, the scheme is reasonable and feasible. Similarly, the type and layout of the hydraulic metal structure are adjusted for analysis and verification. Finally, the safety, economy and ecological environment requirements of the hydraulic structure are comprehensively considered to determine a feasible design scheme.

[0003] Prior art (CN113609555B) A method for designing hydraulic metal structures based on big data technology, which can solve the shortcomings of traditional hydraulic metal structure design methods, make up for the shortcomings of human factors, improve the quality and efficiency of hydraulic metal structure design products, and ensure the safety and economy of hydraulic metal structures; because in the prior art, the advantages and disadvantages of machine design schemes and manual design schemes are compared, and cause analysis or manual verification of the design scheme given based on big data technology is carried out to verify the rationality and accuracy of the machine design scheme; in this method, designers still need to rely on their own experience to make preliminary judgments, screen out more suitable schemes, and then carry out preliminary layout, modeling, refinement and other work, and finally determine a suitable structural scheme through quantitative calculation of the model and comprehensive comparative analysis and other methods; the design process implemented by it requires a lot of manpower and material resources, a long time period, high costs, and cannot achieve modular design and speed up work efficiency. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the existing technology, the present invention provides a hydraulic metal structure design method based on big data technology, which solves the problems that the existing technology still needs to invest a lot of manpower and material resources in the design process, has a long time cycle, high cost, and cannot achieve modular design and speed up work efficiency.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a hydraulic metal structure design method based on big data technology, specifically comprising the following steps:

[0008] Step 1: Build a structure database, obtain structures of the same type in the structure database, and classify them according to feature vectors;

[0009] Step 2: Based on the feature vector, the structural data required for associating with the external data is obtained, and the association analysis and verification is performed according to the recognition model, and the optimal structural data is selected based on the particle swarm optimization algorithm;

[0010] Step 3, calculate the load factor of the hydraulic metal structure according to the formula, and build a basic standard hydraulic metal structure model based on the load factor, wherein the basic standard hydraulic metal structure model is generated by generating a training set and a test set based on the structural data in the known database, the training set is used to train the basic standard hydraulic metal structure model, and the test set is used to verify and optimize the basic standard hydraulic metal structure model;

[0011] Step 4: construct a three-dimensional virtual twin model based on the optimal structural data, and transform each component structural data into a transformable module;

[0012] Step 5: Perform structural replacement based on the optimal three-dimensional virtual twin model and the basic standard hydraulic metal structure model, and perform calculation, analysis and verification of the load factor of the replaced pre-selected hydraulic metal structure model, and output the final hydraulic metal structure model after replacing the variable module to meet the basic value of the load factor;

[0013] Step 6: Based on the manual analysis of the final hydraulic metal structure model, after determining the final data, return to the previous step to repeat the calculation, analysis and verification of the load factor, and obtain the optimal hydraulic metal structure model when it is satisfied.

[0014] Preferably, the structure database in step 1 includes the classification of various hydraulic metal structures; the core design indicators of the structure's size, material, bearing capacity, and service life; and the material properties and application environment.

[0015] The characteristic vectors are classified by using structural function, structural geometry and structural bearing performance as vector values.

[0016] Preferably, the step 2 specifically includes:

[0017] Determine the structural function of external data, and diffuse feature vectors outward with the structural function as the core, including vector search of required shape and required load-bearing performance; the identification model includes key module identification model and module type identification model to analyze the required structural data.

[0018] Preferably, the calculation formula for the hydraulic metal structure load factor in step 3 is:

[0019] Design load = γ G G+γ Q x Q x

[0020] Among them, G is the dead load, Q is the live load, γ G and γ Q is the load factor for dead load and live load, x is the live load number;

[0021] When special loads are included, the calculation formula is:

[0022] Design load = γ G G+γ Q x Q x +γ S ·S

[0023] Among them, S represents other special loads, including water level, wind load and seismic load.

[0024] Preferably, the steps of constructing the basic standard hydraulic metal structure model in step 3 specifically include:

[0025] Step 1: Determine the design parameters, including the structural functional direction, required material strength and structural dimensions;

[0026] Step 2: Perform structural analysis and use finite element analysis to calculate the stress and deformation of the combined structure under load;

[0027] Step 3: Construct a basic standard hydraulic metal structure model based on structural data that meets the parameters and can meet the basic use.

[0028] Preferably, the known database in step 3 includes existing engineering cases, a custom structure database and a known material database; the known database is divided into a training set and a test set in a ratio of 7:3.

[0029] (III) Beneficial effects

[0030] The present invention provides a hydraulic metal structure design method based on big data technology.

[0031] Beneficial effects:

[0032] The present invention provides a hydraulic metal structure design method based on big data technology, which can classify and solidify similar hydraulic metal structures of the same type into fixed basic modules, and uniformly store the basic modules corresponding to different hydraulic metal structures into a basic module library. The basic modules formed in this way can be used alone as the basic structure diagram of the corresponding hydraulic metal structure, so that when performing assembly design, it only needs to call the accessories in the database and make corresponding combinations, which simplifies the design process, reduces the difficulty of drawing, and realizes modular design; at the same time, by obtaining hydraulic structure parameters, constructing a target three-dimensional hydraulic structure model, and using digital twin technology to generate a simulated structure, the current hydraulic structure module is determined, and the load factor analysis and verification of the assembled structure can be quickly performed, thereby realizing intelligent and precise risk assessment of hydraulic structures and improving assessment efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Example:

[0036] like Figure 1 As shown, an embodiment of the present invention provides a hydraulic metal structure design method based on big data technology, which specifically includes the following steps:

[0037] Step 1: Build a structure database, obtain structures of the same type in the structure database, and classify them according to feature vectors;

[0038] The structural database includes the classification of various hydraulic metal structures; the core design indicators of the structure’s size, material, bearing capacity, and service life; the material properties and the application environment;

[0039] The eigenvectors are classified by using structural function, structural geometry and structural load-bearing performance as vector values;

[0040] First, determine the classification standards for hydraulic metal structures (such as dams, bridges, gates, etc.). Each type of structure needs to clarify its basic characteristics and application scenarios, and collect relevant parameters for each structure, including size, material type, bearing capacity, and application environment to complete the construction of the structural database; secondly, according to the function, geometry, and bearing performance of the structure, design feature vectors, and standardize all features to ensure consistency during calculations. Create a database structure that uses tables, including classification tables, material tables, structural characteristics tables, and feature vector tables, and establish appropriate foreign key relationships between tables to facilitate data query and integration;

[0041] Step 2: Based on the feature vector, the structural data required for associating with the external data is obtained, and the association analysis and verification is performed according to the recognition model, and the optimal structural data is selected based on the particle swarm optimization algorithm;

[0042] Specifically include:

[0043] Determine the structural function of external data, and diffuse feature vectors outward with the structural function as the core, including vector selection of required shape and required bearing performance; the identification model includes key module identification model and module type identification model to analyze the required structural data;

[0044] According to the key module identification model, the key module identification is performed on the required hydraulic structure model in the external data, and the key module identification range in the target hydraulic structure model is identified; the key module identification model uses the key module identification target value as a standard to identify the structure data in the structure database, and performs type identification according to the data in the key module identification range to obtain the type identification result of the target structure model; wherein, the module type identification model is configured with a module type target value and a key module identification target value, and the module type target value and the key module identification target value are analyzed and identified by a genetic algorithm to obtain a final result;

[0045] Step 3, calculate the load factor of the hydraulic metal structure according to the formula, and build a basic standard hydraulic metal structure model based on the load factor, wherein the basic standard hydraulic metal structure model is generated by generating a training set and a test set based on the structural data in the known database, the training set is used to train the basic standard hydraulic metal structure model, and the test set is used to verify and optimize the basic standard hydraulic metal structure model;

[0046] Calculation formula for load factor of hydraulic metal structure:

[0047] Design load = γ G G+γ Q x Q x

[0048] Among them, G is the dead load, Q is the live load, γ G and γ Q is the load factor for dead load and live load, x is the live load number;

[0049] When special loads are included, the calculation formula is:

[0050] Design load = γ G G+γ Q x Q x +γ S ·S

[0051] Among them, S represents other special loads, including water level, wind load, and earthquake load;

[0052] Specifically, the constant load factor γ G Usually 1.2; live load factor γ Q Usually 1.5;

[0053] Assuming that the dead load of the hydraulic metal structure is 100kN and the live load is 50kN, the standard load factor is used:

[0054] Design load = 1.2*100kN+1.5*50kN=195kN;

[0055] Specifically, the known database includes existing engineering cases, custom structure database and known material database, among which the construction steps of the basic standard hydraulic metal structure model specifically include:

[0056] Step 1: Determine the design parameters, including the structural functional direction, required material strength and structural dimensions;

[0057] Step 2: Perform structural analysis and use finite element analysis to calculate the stress and deformation of the combined structure under load;

[0058] It is confirmed that the design stress does not exceed the tensile or compressive strength of the material;

[0059] Step 3: construct a basic standard hydraulic metal structure model based on the structural data that meets the parameters and can meet the basic use;

[0060] Specifically, the known database is divided into a training set and a test set at a ratio of 7:3, that is, the training optimization of the basic standard hydraulic metal structure model specifically includes:

[0061] Input the training set, ensure that the training data set is cleaned and preprocessed, perform feature selection, select features related to the load factor, and perform standardization; then use the training set containing the load factor related data to input the first neural network-based support vector machine (NN-SVM) model, perform model training, perform validation analysis in a cross-validation manner, and adjust hyperparameters to optimize model performance;

[0062] Step 4: construct a three-dimensional virtual twin model based on the optimal structural data, and transform each component structural data into a transformable module;

[0063] Organize the collected data into a software format suitable for modeling, ensure that the data can be seamlessly imported into the modeling software, select suitable modeling software to build a virtual twin model, build a virtual model based on the optimal structural data, accurately model through the functions of the software, and decompose each component structure into variable modules according to function or shape; for example, foundation, support, retaining wall, gate, etc. Each module should have independent properties and characteristics to facilitate subsequent changes and optimizations, introduce virtual twin technology, and update the three-dimensional model through real-time data stream feedback;

[0064] Step 5: Perform structural replacement based on the optimal three-dimensional virtual twin model and the basic standard hydraulic metal structure model, and perform calculation, analysis and verification of the load factor of the replaced pre-selected hydraulic metal structure model, and output the final hydraulic metal structure model after replacing the variable module to meet the basic value of the load factor;

[0065] 1. In the modeling software, the corresponding parts of the basic standard hydraulic metal structure model will be replaced by the modules extracted from the optimal 3D virtual twin model;

[0066] 2. According to the design standards and actual usage, define the basic value of the load factor, use SAP2000 to perform load analysis on the newly constructed hydraulic metal structure model, input material properties (such as strength, elastic modulus, etc.) and replaced structural characteristics (such as size, shape, etc.), apply the defined load conditions, and perform static and dynamic analysis of the model. After the analysis is completed, extract the calculation results of the load factor and compare them with the design requirements. If the basic value of the load factor does not meet the requirements, the hydraulic metal structure model needs to be adjusted according to the analysis results;

[0067] 3. According to the feedback obtained from the analysis, adjust the size, shape or material properties of the replacement module, re-analyze the load, and ensure that the load factors of all replacement modules meet the basic numerical requirements; after all replacements and adjustments are completed, conduct a final check to ensure that the strength of the joints of each module meets the design requirements and the overall structure is stable, export the final hydraulic metal structure model into a standard format, and generate necessary documents and reports to record all calculation processes, load analysis results, and the basis for model modification, and provide complete information;

[0068] Step 6: Based on the manual analysis of the final hydraulic metal structure model, after determining the final data, return to the previous step to repeat the calculation, analysis and verification of the load factor, and obtain the optimal hydraulic metal structure model after meeting the requirements;

[0069] The load factor obtained by repeated calculation will be compared with the previous calculation results to check the consistency and rationality of the values ​​to ensure that the load factor meets the design benchmark. If any non-compliance is found, a retrospective check is required and necessary model adjustments are made. Based on the repeated verification results of the load factor, the model is optimized as much as possible to complete the design of the optimal hydraulic metal structure model.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A hydraulic metal structure design method based on big data technology, characterized in that: The specific steps include: Step 1: Build a structure database, obtain structures of the same type in the structure database, and classify them according to feature vectors; Step 2: Based on the feature vector, the structural data required for associating with the external data is obtained, and the association analysis and verification is performed according to the recognition model, and the optimal structural data is selected based on the particle swarm optimization algorithm; Step 3, calculate the load factor of the hydraulic metal structure according to the formula, and build a basic standard hydraulic metal structure model based on the load factor, wherein the basic standard hydraulic metal structure model is generated by generating a training set and a test set based on the structural data in the known database, the training set is used to train the basic standard hydraulic metal structure model, and the test set is used to verify and optimize the basic standard hydraulic metal structure model; Step 4: construct a three-dimensional virtual twin model based on the optimal structural data, and transform each component structural data into a transformable module; Step 5: Perform structural replacement based on the optimal three-dimensional virtual twin model and the basic standard hydraulic metal structure model, and perform calculation, analysis and verification of the load factor of the replaced pre-selected hydraulic metal structure model, and output the final hydraulic metal structure model after replacing the variable module to meet the basic value of the load factor; Step 6: Based on the manual analysis of the final hydraulic metal structure model, after determining the final data, return to the previous step to repeat the calculation, analysis and verification of the load factor, and obtain the optimal hydraulic metal structure model when it is satisfied.

2. The hydraulic metal structure design method based on big data technology according to claim 1 is characterized by: The structure database in step 1 includes the classification of various hydraulic metal structures; the core design indicators of the structure's size, material, bearing capacity, and service life; and the material properties and application environment. The characteristic vectors are classified by using structural function, structural geometry and structural bearing performance as vector values.

3. The hydraulic metal structure design method based on big data technology according to claim 1 is characterized by: The step 2 specifically includes: Determine the structural function of external data, and diffuse feature vectors outward with the structural function as the core, including vector search of required shape and required load-bearing performance; the identification model includes key module identification model and module type identification model to analyze the required structural data.

4. The hydraulic metal structure design method based on big data technology according to claim 1 is characterized by: The calculation formula for the load factor of hydraulic metal structures in step 3 is: Design load = γ G G+γ Q x Q x Among them, G is the dead load, Q is the live load, γ G and γ Q is the load factor for dead load and live load, x is the live load number; When special loads are included, the calculation formula is: Design load = γ G G+γ Q x Q x +γ S ·S Among them, S represents other special loads, including water level, wind load and seismic load.

5. The hydraulic metal structure design method based on big data technology according to claim 1 is characterized by: The steps of constructing the basic standard hydraulic metal structure model in step 3 specifically include: Step 1: Determine the design parameters, including the structural functional direction, required material strength and structural dimensions; Step 2: Perform structural analysis and use finite element analysis to calculate the stress and deformation of the combined structure under load; Step 3: Construct a basic standard hydraulic metal structure model based on structural data that meets the parameters and can meet the basic use.

6. The hydraulic metal structure design method based on big data technology according to claim 1 is characterized by: The known database in step 3 includes existing engineering cases, a custom structure database, and a known material database; the known database is divided into a training set and a test set in a ratio of 7:3.

Images