Design method for steel bar component

Abstract

The invention discloses a design method for a steel bar component. According to the method, a large amount of historical design data can be quickly processed and analyzed through the machine learning model, and key factors influencing axial force reinforcement calculation are automatically identified, so that the calculation efficiency is improved. The machine learning model automatically completes calculation through an algorithm, and errors in the calculation process are reduced. The fully trained machine learning model can accurately predict the reinforcing steel bar area based on the input parameters, and the design accuracy is improved. A machine learning model can discover a hidden relationship between data by analyzing historical data, which is particularly important for reinforcement calculation caused by axial force because the axial force is related to various factors, such as structure size, material characteristics and the like. Machine learning is applied to the reinforcement calculation process caused by the axial force, the intelligent level of design can be remarkably improved, the design efficiency and quality are improved, and meanwhile powerful technical support is provided for cost optimization.

Description

Technical Field

[0001] The invention belongs to the technical field of steel bar component design, and in particular relates to a steel bar component design method. Background Art

[0002] In the field of modern construction, steel components play a vital role. They are the skeleton of the building structure and provide solid support for all kinds of buildings. Today, let us walk into the world of steel components and understand its unique charm and the importance of design. Steel components, as the "power" in the building, ensure the stability and safety of the building with its high strength and good ductility. Steel components have good corrosion resistance and can ensure the long service life of the building even in harsh environments. Standardized production of steel components facilitates rapid assembly at the construction site, improves construction efficiency and shortens construction period. Steel component design is not only a technology, but also an art. It integrates multidisciplinary knowledge such as mechanics, materials science, and structural science, injecting unlimited innovative vitality into the construction industry. With the continuous development of construction technology, steel component design will play a more important role in future buildings.

[0003] However, the traditional manual calculation method is prone to errors because the axial force reinforcement calculation involves multiple variables and complex relationships, especially when dealing with large amounts of data and iterative designs. At the same time, traditional reinforcement calculation methods often rely on fixed calculation formulas and empirical rules. For special or complex design situations, these methods may not be flexible enough and cannot provide optimal reinforcement recommendations. Summary of the invention

[0004] The purpose of the present invention is to provide a design method for a steel bar member in order to solve the above-mentioned problem.

[0005] The technical solution adopted by the present invention is as follows: a design method for a steel bar component, the method comprising the following steps:

[0006] S1: Carry out preliminary preparation, determine the design tasks, understand the project requirements, and clarify the purpose, size, shape, and material requirements of the steel components;

[0007] S2: Collect data, including relevant design specifications, standards, atlases, and material performance data. Analyze engineering geological conditions to understand the geological, hydrological, and climatic conditions of the project site, and provide a basis for subsequent design;

[0008] S3: Conduct preliminary design and determine the component type. According to the project requirements, select the appropriate component type, including beams, plates, columns, and walls; determine the component size. According to the force analysis, structural requirements, and construction convenience, determine the cross-sectional size of the component;

[0009] S4: Conduct stress analysis on the components to determine the internal forces, including bending moment, shear force, and axial force. According to the stress analysis results, select the appropriate steel bar and concrete grade;

[0010] S5: Perform reinforcement calculations, determine the cross-sectional area of ​​the reinforcement based on the internal force calculation results, and collect data on historical structural design cases, including structural type, material properties, axial force design values, and reinforcement configuration;

[0011] S6: Process and standardize the data on axial force magnitude, material type, and structural dimensions so that the machine learning model can better understand it;

[0012] S7: Then, RNN feature extraction, input layer processing and output layer processing are performed to extract various data features used for reinforcement calculation of steel component design;

[0013] S8: Perform feature fusion, splicing the steel bar component data features extracted by RNN together to form a new steel bar component data feature vector F, forming a more comprehensive data representation;

[0014] S9: training the steel component data calculation model, using the data training model to predict the optimal shear reinforcement area Asv under a given shear force;

[0015] S10: Then carry out structural design to determine the thickness of the steel bar protective layer; set sufficient steel bar spacing to ensure construction quality; consider construction convenience and reasonably set steel bar hooks and welding structural measures;

[0016] S11: Check and optimize, check the calculation results against the specifications, and check whether the reinforcement calculation results meet the requirements; optimize the design plan under the premise of ensuring safety, economy and rationality;

[0017] S12: Review drawings: Submit the design drawings to the relevant departments for review. Modify and improve the drawings based on the review opinions. Deliver the final confirmed design drawings to the construction party and conduct technical briefing.

[0018] In a preferred embodiment, in step S6, the reinforcement calculation caused by bending moment uses the formula: Where M represents the design value of bending moment; fy represents the yield strength of the steel bar; As represents the area of ​​the tensile steel bar; d represents the effective height of the steel bar, which is the distance from the center of the steel bar to the edge of the compression zone;

[0019] The formula for calculating the tensile reinforcement area is:

[0020] In a preferred embodiment, in step S6, the Min-Max normalization method is used to normalize the various data features of the reinforcement calculation, and the specific steps are as follows:

[0021] S1. Calculate the maximum and minimum values: For each feature, find the maximum value (Max) and the minimum value (Min) in the data set;

[0022] S2. Apply transformation formula: For each feature value x in the data set, use the following formula to transform it:

[0023] x-Min

[0024] x norm = Max -Min;

[0025] Among them, x norm is the transformed value;

[0026] S3. Transform the dataset: Apply the above transformation to each feature of the entire dataset;

[0027] After min-max normalization, all features are scaled to the range of 0 to 1.

[0028] In a preferred embodiment, in step S7, the input layer processing of RNN feature extraction includes:

[0029] Use word embedding technology to convert raw data text into word vectors;

[0030] Let xi be the input vector of the i-th time step, V be the embedding matrix, and t be the number of time steps, then xi = V ei, where ei is a one-hot encoded vector representing a word;

[0031] Hidden layer processing for RNN feature extraction includes: using LSTM (Long Short-Term Memory Network) RNN units to process time series data;

[0032] Let hi be the hidden state of the i-th time step and ci be the cell state, then the update formula is:

[0033] fi=σ(Wf·[hi-1,xi]+bf);

[0034] II = σ(Wi · [hi-1, xi] + bi);

[0035] c~i=tanh(Wc·[hi-1,xi]+bc)

[0036] ci=fi·ci-1+i i ·c~i;

[0037] oi=σ(Wo·[hi-1,xi]+bo);

[0038] hi = oi tanh (ci);

[0039] Where Wf, Wi, Wc, Wo are weight matrices, bf, bi, bc, bo are bias terms, and σ is the sigmoid function;

[0040] The output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

[0041] In a preferred embodiment, in step S7, the output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

[0042] In a preferred embodiment, in step S9, the model training process includes:

[0043] Data division: The steel component data feature Fpca is divided into a training set Xtrain, a validation set Xval and a test set Xtest

[0044] Model selection: Select the logistic regression model as the probability discriminant model

[0045] Model training: Use training set Xtrain and label Ytrain for training;

[0046] Let θ be the model parameter and σ be the logistic function, then the model output is:

[0047] Calculate the loss function, the calculation formula is:

[0048]

[0049] Where: L(θ) is the loss function, which represents the difference between the model prediction value and the true value; N is the total number of training samples;

[0050] yi is the true label of the i-th sample, which takes the value of 0 or 1;

[0051] y^i is the predicted probability of the model for the i-th sample, calculated as y^i = σ(θT·Fpca,i), where σ is the logistic function, Fpca,i is the reduced eigenvector of the i-th sample, and θ is the model parameter.

[0052] In a preferred embodiment, in the step S10, the steel bar hook and welding structural measures are reasonably set.

[0053] The formula for calculating the hook length is: lhook = diameter times d

[0054] Welding length calculation: lweld = welding length required by the specification.

[0055] In a preferred embodiment, in step S10, the size, shape and arrangement of the reinforcement of the component are accurately expressed according to the requirements of the structural design; during the drawing process, the plan view, elevation view and section view of the component are respectively produced to ensure that the details of the component are fully displayed from different perspectives; the plan view mainly displays the plane position and reinforcement distribution of the component, the elevation view displays the elevation shape of the component and the elevation arrangement of the reinforcement, and the section view is used to display the detailed position and shape of the reinforcement inside the component.

[0056] In a preferred embodiment, in step S10, the steel bar number, specification, quantity, spacing information are marked in detail in the drawing, and the strength grade of the concrete, thickness of the protective layer, and important information about the position of embedded parts are also marked; after drawing is completed, the drawing is reviewed to ensure the accuracy, completeness and constructability of the drawing; finally, construction instructions are written according to the drawings, including material requirements, construction methods, quality standards, and acceptance requirements, so that construction personnel can carry out construction according to the design intent and ensure the quality and safety of the project; during the entire process of drawing the construction drawings, close communication with designers and construction personnel is required to ensure that the drawings can accurately reflect the design intent and meet the actual needs of the construction.

[0057] In a preferred embodiment, in step S11, the verification and optimization need to be carried out in accordance with the relevant design specifications, and the reinforcement calculation results are verified in detail to ensure that all calculation results meet the requirements of the specifications; the specific verification points include: first, checking whether the calculation of the bending moment, shear force and axial force internal force is accurate, and whether the cross-sectional area of ​​the steel bars determined thereby is sufficient; second, verifying whether the arrangement of the steel bars is reasonable, including whether the diameter, quantity and spacing of the steel bars meet the minimum diameter and maximum spacing requirements of the specifications; third, confirming whether the anchorage length, lap length and structural details of the steel bars meet the requirements of the specifications; in addition, it is also necessary to check whether the thickness of the concrete cover meets the requirements of corrosion protection and durability.

[0058] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0059] 1. In the present invention, a large amount of historical design data can be quickly processed and analyzed by a machine learning model, and the key factors affecting the calculation of axial force reinforcement can be automatically identified, thereby improving the calculation efficiency. The machine learning model automatically completes the calculation through an algorithm, reducing errors in the calculation process. A fully trained machine learning model can accurately predict the steel bar area based on the input parameters, thereby improving the accuracy of the design. By analyzing historical data, the machine learning model can discover the hidden relationship between the data, which is particularly important for the reinforcement calculation caused by axial force, because the axial force is related to a variety of factors, such as structural size, material properties, etc. Adaptability and generalization ability: The trained machine learning model is not only suitable for specific cases, but also has a certain generalization ability, and can handle similar but different design problems. At any stage of the design, the machine learning model can provide instant calculation results to help make decisions quickly. With the accumulation of more data, the machine learning model can continue to learn and optimize, and continuously improve the accuracy and efficiency of the prediction. Applying machine learning to the reinforcement calculation process caused by axial force can significantly improve the level of intelligence of the design, improve the design efficiency and quality, and provide strong technical support for cost optimization.

[0060] 2. In the present invention, by accurately calculating the bending moment and designing the reinforcement, it is possible to ensure that the performance of the structure in actual use is more reliable, and to improve the durability and service life of the structure. The optimized reinforcement design can reduce the use of unnecessary materials, save natural resources, and reduce environmental pollution. Reasonable reinforcement design can simplify the construction process, improve construction efficiency, and reduce the difficulty of on-site operations. The optimization of the structural design can reduce the cost of later maintenance and repair, and improve the overall economic benefits. The optimized shear reinforcement design can enable the structure to better adapt to different environments and geological conditions, and improve the adaptability and reliability of the structure. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0062] Example:

[0063] A design method for a steel bar component comprises the following steps:

[0064] S1: Carry out preliminary preparation, determine the design tasks, understand the project requirements, and clarify the purpose, size, shape, and material requirements of the steel components;

[0065] S2: Collect data, including relevant design specifications, standards, atlases, material properties, etc., and analyze engineering geological conditions to understand the geological, hydrological, climatic and other conditions of the project site, so as to provide a basis for subsequent design;

[0066] S3: Conduct preliminary design and determine the component type. According to the project requirements, select the appropriate component type, including beams, plates, columns, and walls; determine the component size. According to the force analysis, structural requirements, and construction convenience, determine the cross-sectional size of the component;

[0067] S4: Perform stress analysis on the components to determine the internal forces, including bending moment, shear force, and axial force. According to the stress analysis results, select the appropriate steel bar and concrete grade;

[0068] S5: Perform reinforcement calculations, determine the cross-sectional area of ​​the reinforcement based on the internal force calculation results, and collect data on historical structural design cases, including structural type, material properties, axial force design values, and reinforcement configuration;

[0069] S6: Process and standardize the data on axial force magnitude, material type, and structural dimensions so that the machine learning model can better understand it;

[0070] S7: Then, RNN feature extraction, input layer processing and output layer processing are performed to extract various data features used for reinforcement calculation of steel component design;

[0071] S8: Perform feature fusion, splicing the steel bar component data features extracted by RNN together to form a new steel bar component data feature vector F, forming a more comprehensive data representation;

[0072] S9: training the steel component data calculation model, using the data training model to predict the optimal shear reinforcement area Asv under a given shear force;

[0073] S10: Then carry out structural design to determine the thickness of the steel bar protective layer; set sufficient steel bar spacing to ensure construction quality; consider construction convenience and reasonably set steel bar hooks and welding structural measures;

[0074] S11: Check and optimize, check the calculation results against the specifications, and check whether the reinforcement calculation results meet the requirements. Optimize the design plan under the premise of ensuring safety, economy and rationality;

[0075] S12: Review drawings: Submit the design drawings to the relevant departments for review. Modify and improve the drawings based on the review opinions. Deliver the final confirmed design drawings to the construction party and conduct technical briefing.

[0076] In step S6, the reinforcement calculation caused by bending moment uses the formula: Where M represents the design value of bending moment; fy represents the yield strength of the steel bar; As represents the area of ​​the tensile steel bar; d represents the effective height of the steel bar, which is the distance from the center of the steel bar to the edge of the compression zone;

[0077] The formula for calculating the tensile reinforcement area is:

[0078] In step S6, the Min-Max normalization method is used to normalize the various data features of the reinforcement calculation. The specific steps are as follows:

[0079] 1. Calculate the maximum and minimum values: For each feature, find the maximum value (Max) and minimum value (Min) in the data set;

[0080] 2. Apply the transformation formula: For each feature value x in the data set, use the following formula to transform it:

[0081] x-Min

[0082] x norm = Max -Min;

[0083] Among them, x norm is the transformed value;

[0084] 3. Transform the dataset: Apply the above transformation to each feature of the entire dataset.

[0085] After min-max normalization, all features are scaled to the range of 0 to 1.

[0086] In step S7, the input layer processing of RNN feature extraction includes:

[0087] Use word embedding technology to convert raw data text into word vectors;

[0088] Let xi be the input vector of the i-th time step, V be the embedding matrix, and t be the number of time steps, then xi = V ei, where ei is a one-hot encoded vector representing a word;

[0089] Hidden layer processing for RNN feature extraction includes: using LSTM (Long Short-Term Memory Network) RNN units to process time series data;

[0090] Let hi be the hidden state of the i-th time step and ci be the cell state, then the update formula is:

[0091] fi=σ(Wf·[hi-1,xi]+bf);

[0092] II = σ(Wi · [hi-1, xi] + bi);

[0093] c~i=tanh(Wc·[hi-1,xi]+bc)

[0094] ci=fi·ci-1+i i ·c~i;

[0095] oi=σ(Wo·[hi-1,xi]+bo);

[0096] hi = oi tanh (ci);

[0097] Where Wf, Wi, Wc, Wo are weight matrices, bf, bi, bc, bo are bias terms, and σ is the sigmoid function;

[0098] The output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

[0099] In step S7, the output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

[0100] In step S9, the model training process includes:

[0101] Data division: The steel component data feature Fpca is divided into a training set Xtrain, a validation set Xval and a test set Xtest;

[0102] Model selection: Select the logistic regression model as the probability discriminant model;

[0103] Model training: Use training set Xtrain and label Ytrain for training;

[0104] Let θ be the model parameter and σ be the logistic function, then the model output is:

[0105] Calculate the loss function, the calculation formula is:

[0106]

[0107] Where: L(θ) is the loss function, which represents the difference between the model prediction value and the true value; N is the total number of training samples;

[0108] yi is the true label of the i-th sample, which takes the value of 0 or 1;

[0109] y^i is the predicted probability of the model for the i-th sample, calculated as y^i = σ(θT·Fpca,i), where σ is the logistic function, Fpca,i is the reduced eigenvector of the i-th sample, and θ is the model parameter.

[0110] In step S10, in the process of reasonably setting the steel bar hook and welding structural measures:

[0111] The formula for calculating the hook length is: lhook = diameter times d

[0112] Welding length calculation: lweld = welding length required by the specification.

[0113] In step S10, it is also necessary to use computer-aided design (CAD) software or manual drawing methods to accurately express the size, shape and arrangement of the components according to the requirements of the structural design. During the drawing process, the plan view, elevation view and section view of the component will be made separately to ensure that the details of the component are fully displayed from different perspectives. The plan view mainly shows the plane position and steel bar distribution of the component, the elevation view shows the elevation shape of the component and the elevation arrangement of the steel bar, and the section view is used to show the detailed position and shape of the steel bar inside the component.

[0114] In step S10, in the drawing, the steel bar number, specification, quantity, spacing and other information are marked in detail. For example, "#8@200" means a steel bar with a diameter of 8mm and a spacing of 200mm. In addition, important information such as the strength grade of the concrete, the thickness of the protective layer, the position of the embedded parts, etc. need to be marked. After the drawing is completed, the drawings are reviewed to ensure the accuracy, completeness and constructability of the drawings. Finally, construction instructions are written according to the drawings, including material requirements, construction methods, quality standards, acceptance requirements, etc., so that construction personnel can carry out construction according to the design intent and ensure the quality and safety of the project. During the entire process of drawing the construction drawings, close communication with designers and construction personnel is required to ensure that the drawings can accurately reflect the design intent and meet the actual needs of the construction.

[0115] In step S11, verification and optimization are key steps to ensure that the structural design scheme is both safe and economical. In this process, it is necessary to check the reinforcement calculation results in detail in accordance with the relevant design specifications to ensure that all calculation results meet the requirements of the specifications. Specific verification points include: first, check whether the calculation of internal forces such as bending moment, shear force and axial force is accurate, and whether the cross-sectional area of ​​the steel bars determined thereby is sufficient; second, verify whether the arrangement of the steel bars is reasonable, including whether the diameter, quantity, spacing, etc. of the steel bars meet the requirements of the specifications such as the minimum diameter and maximum spacing; third, confirm whether the structural details such as the anchorage length and lap length of the steel bars meet the requirements of the specifications; in addition, check whether the thickness of the concrete cover meets the requirements of corrosion protection and durability. In terms of optimization, the economy and rationality of the design scheme are considered under the premise of ensuring structural safety. The optimization points include: adjusting the steel bar configuration, reducing the amount of steel bars and reducing costs by using higher-strength steel bars or optimizing the steel bar layout; optimizing concrete design, such as adjusting the concrete strength grade to reduce material costs; considering the use of new materials or structural systems to improve structural performance or reduce construction difficulty; at the same time, multiple design schemes must be compared, and through iterative calculations and evaluations, the optimal design scheme that meets the structural function, safety and economic requirements can be found. Through this series of verifications and optimizations, it can be ensured that the design scheme meets the requirements of the specifications while achieving safe, economical and reasonable design goals.

[0116] In the present invention, a large amount of historical design data can be quickly processed and analyzed by a machine learning model, and the key factors affecting the calculation of axial force reinforcement can be automatically identified, thereby improving the calculation efficiency. The machine learning model automatically completes the calculation through an algorithm, reducing errors in the calculation process. A fully trained machine learning model can accurately predict the steel bar area based on the input parameters, thereby improving the accuracy of the design. By analyzing historical data, the machine learning model can discover the hidden relationship between the data, which is particularly important for the reinforcement calculation caused by axial force, because the axial force is related to a variety of factors, such as structural size, material properties, etc. Adaptability and generalization ability: The trained machine learning model is not only suitable for specific cases, but also has a certain generalization ability, and can handle similar but different design problems. At any stage of the design, the machine learning model can provide instant calculation results to help make decisions quickly. With the accumulation of more data, the machine learning model can continue to learn and optimize, and continuously improve the accuracy and efficiency of the prediction. Applying machine learning to the reinforcement calculation process caused by axial force can significantly improve the level of intelligence of the design, improve the design efficiency and quality, and provide strong technical support for cost optimization.

[0117] In the present invention, by accurately calculating the bending moment and designing the reinforcement, it is possible to ensure that the performance of the structure in actual use is more reliable, and to improve the durability and service life of the structure. The optimized reinforcement design can reduce unnecessary material use, save natural resources, and reduce environmental pollution. Reasonable reinforcement design can simplify the construction process, improve construction efficiency, and reduce the difficulty of on-site operations. The optimization of the structural design can reduce the cost of later maintenance and repair, and improve the overall economic benefits. The optimized shear reinforcement design can enable the structure to better adapt to different environments and geological conditions, and improve the adaptability and reliability of the structure.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A design method for a steel member, characterized in that: The method comprises the following steps: S1: Carry out preliminary preparation, determine the design tasks, understand the project requirements, and clarify the purpose, size, shape, and material requirements of the steel components; S2: Collect data, including relevant design specifications, standards, atlases, and material performance data. Analyze engineering geological conditions to understand the geological, hydrological, and climatic conditions of the project site, and provide a basis for subsequent design; S3: Conduct preliminary design and determine the component type. According to the project requirements, select the appropriate component type, including beams, plates, columns, and walls; determine the component size. According to the force analysis, structural requirements, and construction convenience, determine the cross-sectional size of the component; S4: Conduct stress analysis on the components to determine the internal forces, including bending moment, shear force, and axial force. According to the stress analysis results, select the appropriate steel bar and concrete grade; S5: Perform reinforcement calculations, determine the cross-sectional area of ​​the reinforcement based on the internal force calculation results, and collect data on historical structural design cases, including structural type, material properties, axial force design values, and reinforcement configuration; S6: Process and standardize the data on axial force magnitude, material type, and structural dimensions so that the machine learning model can better understand it; S7: Then, RNN feature extraction, input layer processing and output layer processing are performed to extract various data features used for reinforcement calculation of steel component design; S8: Perform feature fusion, splicing the steel bar component data features extracted by RNN together to form a new steel bar component data feature vector F, forming a more comprehensive data representation; S9: training the steel component data calculation model, using the data training model to predict the optimal shear reinforcement area Asv under a given shear force; S10: Then carry out structural design to determine the thickness of the steel bar protective layer; set sufficient steel bar spacing to ensure construction quality; consider construction convenience and reasonably set steel bar hooks and welding structural measures; S11: Check and optimize, check the calculation results against the specifications, and check whether the reinforcement calculation results meet the requirements; optimize the design plan under the premise of ensuring safety, economy and rationality; S12: Review drawings: Submit the design drawings to the relevant departments for review. Modify and improve the drawings based on the review opinions. Deliver the final confirmed design drawings to the construction party and conduct technical briefing.

2. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S6, the reinforcement calculation caused by bending moment uses the formula: Where M represents the design value of the bending moment; fy represents the yield strength of the steel bar; As represents the area of ​​the tensile steel bar; d represents the effective height of the steel bar, which is the distance from the center of the steel bar to the edge of the compression zone; The formula for calculating the tensile reinforcement area is:

3. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S6, the Min-Max standardization method is used to normalize the various data features of the reinforcement calculation. The specific steps are as follows: S1. Calculate the maximum and minimum values: For each feature, find the maximum value (Max) and the minimum value (Min) in the data set; S2. Apply transformation formula: For each feature value x in the data set, use the following formula to transform it: x-Min x norm = Max -My; Among them, x norm is the transformed value; S3. Transform the dataset: Apply the above transformation to each feature of the entire dataset; After min-max normalization, all features are scaled to the range of 0 to 1.

4. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S7, the input layer processing of RNN feature extraction includes: Use word embedding technology to convert raw data text into word vectors; Let xi be the input vector of the i-th time step, V be the embedding matrix, and t be the number of time steps, then xi = V ei, where ei is a one-hot encoded vector representing a word; Hidden layer processing for RNN feature extraction includes: using LSTM (Long Short-Term Memory Network) RNN units to process time series data; Let hi be the hidden state of the i-th time step and ci be the cell state, then the update formula is: fi=σ(Wf·[hi-1,xi]+bf); II = σ(Wi · [hi-1, xi] + bi); c~i=tanh(Wc·[hi-1,xi]+bc) ci=fi·ci-1+i i ·c~i; oi=σ(Wo·[hi-1,xi]+bo); hi = oi tanh (ci); Where Wf, Wi, Wc, Wo are weight matrices, bf, bi, bc, bo are bias terms, and σ is the sigmoid function; The output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

5. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S7, the output layer processing of RNN feature extraction includes: using the hidden state ht of the last time step as the output feature.

6. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S9, the model training process includes: Data division: The steel component data feature Fpca is divided into a training set Xtrain, a validation set Xval and a test set Xtest Model selection: Select the logistic regression model as the probability discriminant model Model training: Use the training set Xtrain and label Ytrain for training; Let θ be the model parameter and σ be the logistic function, then the model output is: Calculate the loss function, the calculation formula is: Where: L(θ) is the loss function, which represents the difference between the model prediction value and the true value; N is the total number of training samples; yi is the true label of the i-th sample, which takes the value of 0 or 1; y^i is the predicted probability of the model for the i-th sample, calculated as y^i = σ(θT·Fpca,i), where σ is the logistic function, Fpca,i is the reduced eigenvector of the i-th sample, and θ is the model parameter.

7. A design method for a steel bar member as claimed in claim 1, characterized in that: In the step S10, the calculation formula for the length of the hook is as follows: lhook = diameter multiple d Welding length calculation: lweld = welding length required by the specification.

8. A design method for a steel bar member as claimed in claim 1, characterized in that: In the step S10, the size and shape of the component and the arrangement of the steel bars are accurately expressed according to the requirements of the structural design; During the drawing process, the plan view, elevation view and section view of the component will be made separately to ensure that the details of the component are fully displayed from different perspectives; the plan view mainly shows the plane position and steel bar distribution of the component, the elevation view shows the elevation shape of the component and the elevation arrangement of the steel bars, and the section view is used to show the detailed position and shape of the steel bars inside the component.

9. A design method for a steel bar member as claimed in claim 1, characterized in that: In step S10, the steel bar number, specification, quantity, spacing information are marked in detail in the drawing, and the strength grade of the concrete, thickness of the protective layer, and important information about the position of the embedded parts are also marked; after the drawing is completed, the drawing is reviewed to ensure the accuracy, completeness and constructability of the drawing; finally, the construction instructions are written according to the drawings, including material requirements, construction methods, quality standards, and acceptance requirements, so that the construction personnel can carry out the construction according to the design intent and ensure the quality and safety of the project; during the entire process of drawing the construction drawings, close communication with the designers and construction personnel is required to ensure that the drawings can accurately reflect the design intent and meet the actual needs of the construction.

10. A design method for a steel bar member according to claim 1, characterized in that: In the step S11, the verification and optimization need to be carried out in accordance with the relevant design specifications, and the reinforcement calculation results are verified in detail to ensure that all calculation results meet the requirements of the specifications; the specific verification points include: first, check whether the calculation of the bending moment, shear force and axial force internal force is accurate, and whether the cross-sectional area of ​​the steel bars determined thereby is sufficient; second, verify whether the arrangement of the steel bars is reasonable, including whether the diameter, quantity and spacing of the steel bars meet the minimum diameter and maximum spacing requirements of the specifications; third, confirm whether the anchorage length, lap length and structural details of the steel bars meet the requirements of the specifications; in addition, check whether the thickness of the concrete cover meets the requirements of corrosion protection and durability.

Images