Digital intelligent analysis system and method for profile steel structure

Abstract

The invention relates to the technical field of structural engineering, in particular to a digital intelligent analysis system and method for a profile steel structure, and the system comprises an information collection module, a data preprocessing module, a stress analysis module, a fatigue analysis module, a residual life prediction module and an optimization design module. Wherein the information acquisition module is used for acquiring physical parameters of a profile steel structure; the data preprocessing module is used for preprocessing the physical parameters; the stress analysis module is used for performing stress analysis on the profile steel structure by using a finite element method; the fatigue analysis module is used for carrying out fatigue analysis by adopting a mineralogy method and determining the fatigue life of the profile steel structure under the action of multiple loading; and the optimization design module is used for providing optimization design suggestions of the profile steel structure. By integrating real-time data acquisition, accurate stress analysis, fatigue damage evaluation and residual life prediction, the structural safety is improved, the design scheme is optimized, and the service life of the structure is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of structural engineering, and in particular to a digital intelligent analysis system and method for steel structure. Background Art

[0002] Steel structures are widely used in buildings, bridges, machinery and other fields. Due to the external loads and environmental factors, they may experience stress concentration, fatigue damage and material aging during long-term use. Therefore, how to accurately monitor the health of steel structures, evaluate their service life and achieve structural optimization design has become an important issue in the field of structural engineering. At present, many monitoring methods for steel structures mainly rely on traditional manual detection and regular inspections, and these methods are limited by manual capabilities and detection cycles, and cannot reflect the working status of steel structures in real time and comprehensively. In addition, traditional stress analysis methods also rely on simplified models or static calculations, and lack accurate prediction of fatigue damage and remaining life under multiple loading conditions.

[0003] In the prior art, although some monitoring methods use sensor arrays for data collection, these methods generally have problems such as incomplete data processing and inaccurate predictions. For example, the existing stress analysis methods usually only consider the stress conditions under a single working condition, ignoring the long-term impact of complex factors such as multiple loading and environmental changes on the performance of steel structures. At the same time, traditional fatigue analysis methods often rely on empirical formulas or simplified assumptions, and cannot accurately assess the fatigue life of steel structures in long-term use, leading to structural safety hazards. Existing remaining life prediction methods are mostly based on historical data analysis, lack of in-depth integration with actual use conditions, and cannot provide effective optimization suggestions. Therefore, there is an urgent need for a digital intelligent analysis system and method for steel structures to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides a digital intelligent analysis system and method for steel structure.

[0005] The digital intelligent analysis system for steel structures includes information acquisition module, data preprocessing module, stress analysis module, fatigue analysis module, remaining life prediction module and optimization design module; among which:

[0006] Information acquisition module: used to collect physical parameters of steel structures in real time, including stress, strain and displacement data;

[0007] Data preprocessing module: used to preprocess the physical parameters collected by the information acquisition module, including noise removal, interpolation filling and data cleaning;

[0008] Stress analysis module: Based on the pre-processed physical parameters, the finite element method is used to perform stress analysis on the steel structure and calculate the stress distribution data of the steel structure under different load conditions;

[0009] Fatigue analysis module: Based on the stress distribution data calculated by the stress analysis module, the fatigue analysis is performed using the mineralogical method to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree;

[0010] Remaining life prediction module: used to predict the remaining service life of steel structures based on the fatigue damage degree obtained by the fatigue analysis module and the historical usage data of steel structures, combined with the machine learning regression model;

[0011] Optimization design module: It is used to propose optimization design suggestions for steel structures based on the prediction results of the remaining life prediction module and combined with structural safety requirements, including structural size adjustment, material improvement and load distribution optimization.

[0012] Optionally, the information acquisition module includes a stress sensor, a strain sensor, a displacement sensor and a data transmission unit; wherein:

[0013] Stress sensor: It uses strain gauge technology to measure the stress change at a specified position on the steel structure, convert the stress into a resistance change signal, and then convert the signal into digital data output through the circuit;

[0014] Strain sensor: It uses resistance strain gauge technology to measure the deformation degree of the steel structure in real time based on the change in resistance caused by material strain, converts the deformation signal into voltage change, and converts it into a digital signal for subsequent processing;

[0015] Displacement sensor: It uses laser displacement measurement technology to irradiate the surface of the steel structure with a laser beam, measure the changes in the laser reflection echo, and thus calculate the displacement of the structure surface;

[0016] Data transmission unit: used to aggregate the physical parameter data collected by the stress sensor, strain sensor and displacement sensor, and transmit them to the data preprocessing module through a wired or wireless network.

[0017] Optionally, the data preprocessing module includes a filtering unit, an interpolation unit and a data cleaning unit; wherein:

[0018] Filtering unit: used to remove noise from the physical parameter data collected by the information acquisition module. Specifically, the Kalman filter algorithm is used to correct the influence of noise on the data in real time through prediction and update steps, thereby removing high-frequency noise in the data.

[0019] Interpolation unit: used to interpolate and fill in the missing data in the physical parameters collected by the information acquisition module. It uses the cubic spline interpolation method to estimate the missing data points through smooth curve fitting of known data points, and fills the interpolated data into the missing positions;

[0020] Data cleaning unit: used to clean the data after filtering and interpolation processing, remove outliers, and use the standard deviation method to calculate the standard deviation of the data to eliminate outliers that exceed the set threshold.

[0021] Optionally, the stress analysis module includes a finite element modeling unit, a load application unit, a solution unit and a result visualization unit; wherein:

[0022] Finite element modeling unit: used to divide the steel structure into multiple small finite element units, and generate a finite element model by combining node coordinates, material properties and structural geometry information;

[0023] Load application unit: used to apply different types of loads to the finite element model according to different working conditions and external environmental conditions. The load types include static loads, dynamic loads or external loads to simulate the stress conditions of the steel structure under actual use conditions;

[0024] Solving unit: It is used to perform stress analysis on the steel structure by finite element analysis method based on the finite element model after the load is applied, calculate the stress distribution data of the steel structure under different load conditions, and obtain the stress value of each finite element unit;

[0025] Result visualization unit: used to visualize the calculated stress distribution data.

[0026] Optionally, the finite element modeling unit includes:

[0027] Structural division subunit: used to divide the steel structure into multiple small finite element units. The mesh generation algorithm is used to divide the overall structure into several regular finite element units, including triangular units, quadrilateral units or hexahedral units, according to the geometric shape and size of the steel structure.

[0028] Node coordinate acquisition subunit: used to determine the node coordinates of each finite element unit. Based on the geometric information of the steel structure, the coordinate conversion formula is used to convert the structural geometric data in the three-dimensional space into the node coordinates (x i ,y i , z i );

[0029] Material property assignment subunit: used to assign corresponding material properties to each finite element, including elastic modulus and Poisson's ratio;

[0030] Geometric information integration subunit: It is used to combine the geometric information, node coordinates and material properties of the steel structure to generate a finite element model. Specifically, the matrix assembly method is used to assemble the stiffness matrix of each finite element unit into the stiffness matrix K of the overall structure. The expression is: Where n is the total number of finite element units, K e is the stiffness matrix of the e-th finite element unit, that is, the finite element model.

[0031] Optionally, the solving unit includes:

[0032] Boundary condition application subunit: used to apply corresponding boundary conditions to the global stiffness matrix K and node force vector F according to the actual support and constraint conditions of the steel structure; the specific steps include:

[0033] First, determine the fixed nodes and free nodes;

[0034] Then, the stiffness matrix K is modified to reflect the displacement constraints of the fixed nodes, specifically by setting the corresponding stiffness matrix rows and columns to zero and assigning a very large stiffness value K on the diagonal. ii =∞ to achieve, the expression is: K′·u=F′, where K′ is the stiffness matrix after the boundary conditions are applied, u is the node displacement vector, and F′ is the node force vector after the boundary conditions are applied;

[0035] Displacement solving subunit: used to calculate the displacement vector u of each node of the steel structure by solving the linear equation group K′·u=F′. The specific solution method adopts Gaussian elimination method, and its formula is u=·F′ -1 F′, iterates and solves until the displacement vector u reaches the preset convergence accuracy;

[0036] Stress calculation subunit: used to calculate the stress value σ of each finite element unit according to the solved node displacement vector. The specific calculation formula is: ∈=B·u, where B is the strain-displacement matrix; calculate the stress σ according to Hooke's law, the formula is: σ=E·∈, where E is the elastic modulus of the material; summarize the stress values ​​of each finite element unit to generate stress distribution data.

[0037] Optionally, the fatigue analysis module includes a stress amplitude calculation unit, a stress ratio calculation unit, an SN curve fitting unit and a fatigue damage degree calculation unit; wherein:

[0038] The stress amplitude calculation unit is used to calculate the stress amplitude Δσ of the steel structure under multiple loading conditions based on the stress distribution data calculated by the stress analysis module. The formula is: Δσ=σ max -σ min , where σ max is the maximum stress value in the stress distribution, σmin is the minimum stress value;

[0039] Stress ratio calculation unit: used to calculate the stress ratio R of the steel structure under multiple loadings, that is, the ratio of the minimum stress to the maximum stress. The expression is:

[0040] S-N curve fitting unit: The mineralogy method is used to fit the relationship between fatigue life N and stress amplitude Δσ corresponding to different stress amplitudes to generate the SN curve. The fitting formula is: Where N is the fatigue life of the material under the stress amplitude Δσ, a and b are constants of the material;

[0041] Fatigue damage degree calculation unit: used to calculate the fatigue damage degree D of steel structure under multiple loading. The specific calculation steps include:

[0042] First, for each loading cycle i, according to the stress amplitude Δσ i Calculate the fatigue life N under the corresponding cycle i ;

[0043] Then, according to the number of loading times, the damage degree D of the corresponding cycle is calculated. i , the formula is;

[0044] Finally, the total fatigue damage degree D is calculated by accumulating the damage degree of all cycles. total , the formula is: Where n1 is the total number of loading cycles, N i,actual is the number of loading times, N i According to the stress amplitude Δσ i Calculated fatigue life; cumulative damage degree D total It can reflect the fatigue damage degree of the steel structure. When the damage degree is equal to 1, it means that the material has failed.

[0045] Optionally, the remaining life prediction module includes a historical usage data input unit, a damage accumulation analysis unit and a remaining life prediction unit; wherein:

[0046] Historical use data input unit: used to receive the historical use data of the steel structure, including the actual use period, load history and environmental factors of the steel structure;

[0047] Damage accumulation analysis unit: based on historical usage data and fatigue damage degree D calculated by fatigue analysis module total, , analyze the damage of the steel structure and calculate its current damage state D current , the formula is: Among them, D totalis the cumulative damage obtained from the fatigue analysis module, D i is the contribution of each usage cycle to damage in the historical usage data, and n2 is the total number of usage cycles;

[0048] Remaining life prediction unit: used to combine fatigue damage degree and historical usage data to predict the remaining service life T of steel structures through machine learning regression model remaining , the formula is:

[0049] Among them, T total is the initial design life of the steel structure, T current is the current service life of the steel structure, λ is the damage accumulation coefficient, D current is the current damage degree of the steel structure.

[0050] Optionally, the optimization design module includes a structure size adjustment unit, a material improvement unit and a load distribution optimization unit; wherein:

[0051] Structural size adjustment unit: used to analyze the size parameters of each component in the steel structure according to the prediction results of the remaining life prediction module, and put forward optimization suggestions;

[0052] The structural size adjustment unit comprises:

[0053] Dimensional analysis subunit: Based on the predicted remaining life and structural safety requirements, the stress concentration and safety factor of each component under the existing size are calculated. The formula is: Among them, σ safe is the safety factor, σ allow is the allowable stress, σ actual is the actual stress;

[0054] Size optimization subunit: used to adjust the cross-sectional dimensions of the component to improve the safety factor according to the size analysis results. The adjusted dimension D new Calculated by the following formula: Among them, D current is the current component size;

[0055] Material improvement unit: used to select alternative materials to enhance the durability and fatigue life of steel structures based on the results of the remaining life prediction module;

[0056] Load distribution optimization unit: used to redistribute the load in the steel structure according to the results of the remaining life prediction module to reduce local stress concentration and extend the service life of the structure.

[0057] The digital intelligent analysis method for steel structure is implemented by the digital intelligent analysis system for steel structure, and comprises the following steps:

[0058] S1: The sensor array installed on the steel structure collects the physical parameter information of the steel structure in real time, including stress, strain and displacement data;

[0059] S2: Preprocess the physical parameter data collected in S1, use filtering algorithm to remove noise data, and use interpolation method to fill in missing data;

[0060] S3: Based on the physical parameters preprocessed in S2, the finite element method is used to perform stress analysis on the steel structure, and the stress distribution data of the steel structure under different load conditions is calculated;

[0061] S4: Based on the stress distribution data calculated in S3, a fatigue analysis is performed using a mineralogical method to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree;

[0062] S5: Based on the fatigue damage degree obtained in S4 and the historical usage data of the steel structure, a machine learning regression model is used to predict the remaining service life of the steel structure;

[0063] S6: Based on the remaining service life results predicted in S5 and combined with the structural safety requirements, put forward optimization design suggestions for the steel structure, including structural size adjustment, material improvement and load distribution optimization.

[0064] Beneficial effects of the present invention:

[0065] The present invention, by adopting a sensor array for real-time monitoring, can comprehensively and accurately collect the physical parameters of the steel structure, avoiding the limitations of traditional manual detection and ensuring the timely reflection of the health status of the structure; at the same time, the data preprocessing module eliminates noise and missing data through filtering algorithms and interpolation methods, thereby improving the quality and reliability of the data; the stress analysis module based on the finite element analysis method, combined with various working conditions, accurately calculates the stress distribution of the steel structure, providing a scientific basis for subsequent fatigue analysis and remaining life prediction.

[0066] The present invention realizes accurate prediction of fatigue damage degree and remaining life of steel structure by combining fatigue analysis and machine learning regression model; through analysis of fatigue damage degree, the service life of steel structure can be effectively predicted, and in combination with structural safety requirements, targeted optimization design suggestions are given, such as structural size adjustment, material improvement and load distribution optimization; the optimization design can improve the use efficiency and safety of steel structure, extend its service life, and reduce maintenance and replacement costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A schematic diagram of a digital intelligent analysis system according to an embodiment of the present invention;

[0069] Figure 2 Schematic diagram of a digital intelligent analysis method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0071] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0072] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0073] like Figure 1 As shown, the digital intelligent analysis system for steel structures includes an information acquisition module, a data preprocessing module, a stress analysis module, a fatigue analysis module, a remaining life prediction module, and an optimization design module; among which:

[0074] Information acquisition module: used to collect physical parameters of steel structures in real time, including stress, strain and displacement data;

[0075] Data preprocessing module: used to preprocess the physical parameters collected by the information acquisition module, including noise removal, interpolation filling and data cleaning to ensure the integrity and accuracy of the data;

[0076] Stress analysis module: Based on the pre-processed physical parameters, the finite element method (FEM) is used to perform stress analysis on the steel structure and calculate the stress distribution data of the steel structure under different load conditions;

[0077] Fatigue analysis module: Based on the stress distribution data calculated by the stress analysis module, the fatigue analysis is performed using the mineralogy method (MinersRule) to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree;

[0078] Remaining life prediction module: used to predict the remaining service life of steel structures based on the fatigue damage degree obtained by the fatigue analysis module and the historical usage data of steel structures, combined with the machine learning regression model;

[0079] Optimization design module: It is used to propose optimization design suggestions for steel structures based on the prediction results of the remaining life prediction module and combined with structural safety requirements, including structural size adjustment, material improvement and load distribution optimization.

[0080] The information acquisition module includes a stress sensor, a strain sensor, a displacement sensor and a data transmission unit; wherein:

[0081] Stress sensor: It uses strain gauge technology to measure the stress change at a specified position on the steel structure, convert the stress into a resistance change signal, and then convert the signal into digital data output through the circuit;

[0082] Strain sensor: It uses resistance strain gauge technology to measure the deformation degree of the steel structure in real time based on the change in resistance caused by material strain, converts the deformation signal into voltage change, and converts it into a digital signal for subsequent processing;

[0083] Displacement sensor: It uses laser displacement measurement technology to irradiate the surface of the steel structure with a laser beam, measure the changes in the laser reflection echo, and thus calculate the displacement of the structure surface;

[0084] Data transmission unit: used to summarize the physical parameter data collected by stress sensors, strain sensors and displacement sensors, and transmit them to the data preprocessing module through wired or wireless networks; through the coordinated work of the above units and sensors, the information acquisition module can realize real-time and accurate collection of the physical parameters of the steel structure, ensuring that the basic data for subsequent data processing and analysis are highly reliable and complete.

[0085] The data preprocessing module includes a filtering unit, an interpolation unit and a data cleaning unit; wherein:

[0086] Filtering unit: used to remove noise from the physical parameter data collected by the information acquisition module. Specifically, the Kalman filter algorithm is used to correct the influence of noise on the data in real time through prediction and update steps, thereby removing high-frequency noise in the data and ensuring the smoothness and accuracy of the data.

[0087] Interpolation unit: used to interpolate and fill in the missing data in the physical parameters collected by the information acquisition module. It uses the cubic spline interpolation method to estimate the missing data points through smooth curve fitting of known data points, and fills the interpolated data into the missing positions to ensure the continuity and integrity of the data.

[0088] Data cleaning unit: used to clean the data after filtering and interpolation processing, remove outliers, and use the standard deviation method to calculate the standard deviation of the data to eliminate outliers that exceed the set threshold, thereby further improving the reliability of the data; through the design of the above-mentioned data preprocessing module, it can effectively remove noise and fill in missing data, ensuring that the physical parameter data obtained from the information acquisition module is of high quality.

[0089] The stress analysis module includes finite element modeling unit, load application unit, solution unit and result visualization unit; among them:

[0090] Finite element modeling unit: used to divide the steel structure into multiple small finite element units, and generate a finite element model by combining node coordinates, material properties and structural geometry information;

[0091] Load application unit: used to apply different types of loads to the finite element model according to different working conditions and external environmental conditions. The load types include static loads, dynamic loads or external loads to simulate the stress conditions of the steel structure under actual use conditions;

[0092] Solving unit: It is used to perform stress analysis on the steel structure by finite element analysis method based on the finite element model after the load is applied, calculate the stress distribution data of the steel structure under different load conditions, and obtain the stress value of each finite element unit;

[0093] Result visualization unit: It is used to visualize the calculated stress distribution data. By generating graphical displays such as stress cloud maps and contour maps, it helps analysts to intuitively understand the stress distribution of steel structures under different load conditions. Through the design of the above stress analysis module, the stress distribution of steel structures under different load conditions can be accurately calculated, providing accurate stress data support for subsequent fatigue analysis and remaining life prediction.

[0094] Finite element modeling units include:

[0095] Structural division subunit: used to divide the steel structure into multiple small finite element units. The mesh generation algorithm is used to divide the overall structure into several regular finite element units, including triangular units, quadrilateral units or hexahedral units, according to the geometric shape and size of the steel structure.

[0096] Node coordinate acquisition subunit: used to determine the node coordinates of each finite element unit. Based on the geometric information of the steel structure, the coordinate conversion formula is used to convert the structural geometric data in the three-dimensional space into the node coordinates (x i ,y i , z i ), the formula is as follows:

[0097] Among them, (x0, y0, z0) are the initial node coordinates, Δx, Δy, Δz are the node spacing, and n x ,n y ,n z is the node index;

[0098] Material property assignment subunit: used to assign corresponding material properties to each finite element unit, including elastic modulus E and Poisson's ratio v. The material property assignment unit adopts the material constitutive relationship, such as Hooke's Law, according to the material used in the steel structure. The specific formula is: σ=E·∈; Among them, σ is stress, ∈ is strain, ΔL is the length change, and L0 is the original length;

[0099] Geometric information integration subunit: It is used to combine the geometric information, node coordinates and material properties of the steel structure to generate a finite element model. Specifically, the matrix assembly method is used to assemble the stiffness matrix of each finite element unit into the stiffness matrix K of the overall structure. The expression is: Where n is the total number of finite element units, K e is the stiffness matrix of the e-th finite element unit, that is, the finite element model; through the design of the above sub-units, the steel structure can be accurately divided into multiple finite element units, and the node coordinates, material properties and geometric information of each unit can be accurately calculated. The final generated finite element model provides a solid mathematical foundation for subsequent stress analysis.

[0100] The solving unit includes:

[0101] Boundary condition application subunit: used to apply corresponding boundary conditions to the global stiffness matrix K and node force vector F according to the actual support and constraint conditions of the steel structure; the specific steps include:

[0102] First, determine the fixed nodes and free nodes;

[0103] Then, the stiffness matrix K is modified to reflect the displacement constraints of the fixed nodes, specifically by setting the corresponding stiffness matrix rows and columns to zero and assigning a very large stiffness value K on the diagonal. ii =∞ to achieve, the expression is: K′·u=F′, where K′ is the stiffness matrix after the boundary conditions are applied, u is the node displacement vector, and F′ is the node force vector after the boundary conditions are applied;

[0104] Displacement solving subunit: used to calculate the displacement vector u of each node of the steel structure by solving the linear equation group K′·u=F′. The specific solution method adopts Gaussian elimination method, and its formula is u=K′ -1 F′, iterates and solves until the displacement vector u reaches the preset convergence accuracy;

[0105] Stress calculation subunit: used to calculate the stress value σ of each finite element unit according to the node displacement vector obtained by the solution. The specific calculation formula is: ∈=B·u, where B is the strain-displacement matrix; the stress σ is calculated according to Hooke's law, and the formula is: σ=E·∈, where E is the elastic modulus of the material; the stress value of each finite element unit is summarized to generate stress distribution data; through the design of the above-mentioned solution unit, the stress distribution data of the steel structure under different load conditions can be accurately calculated, which provides solid data support for subsequent fatigue analysis and remaining life prediction.

[0106] The fatigue analysis module includes a stress amplitude calculation unit, a stress ratio calculation unit, an SN curve fitting unit, and a fatigue damage degree calculation unit; among which:

[0107] The stress amplitude calculation unit is used to calculate the stress amplitude Δσ of the steel structure under multiple loading conditions based on the stress distribution data calculated by the stress analysis module. The formula is: Δσ=σ max -σ min , where σ max is the maximum stress value in the stress distribution, σ min is the minimum stress value, and the stress amplitude Δσ is an important parameter in fatigue analysis, which can reflect the degree of stress change of the material under multiple loadings;

[0108] Stress ratio calculation unit: used to calculate the stress ratio R of the steel structure under multiple loadings, that is, the ratio of the minimum stress to the maximum stress. The expression is: Stress ratio R is an important parameter in fatigue life analysis. It can affect the fatigue damage behavior of the material and determine the fatigue strength of the material under different load conditions.

[0109] S-N curve fitting unit: The mineralogy method is used to fit the relationship between fatigue life N and stress amplitude Δσ corresponding to different stress amplitudes to generate the SN curve. The fitting formula is: Where N is the fatigue life of the material under the stress amplitude Δσ, a and b are constants of the material, and their specific values ​​are determined based on experimental data or literature data. The fatigue life of the steel structure under a given stress amplitude can be predicted by fitting the S-N curve.

[0110] Fatigue damage degree calculation unit: used to calculate the fatigue damage degree D of steel structure under multiple loading. The specific calculation steps include:

[0111] First, for each loading cycle i, according to the stress amplitude Δσ i Calculate the fatigue life N under the corresponding cycle i ;

[0112] Then, according to the number of loading times, the damage degree D of the corresponding cycle is calculated. i , the formula is;

[0113] Finally, the total fatigue damage degree D is calculated by accumulating the damage degree of all cycles. total , the formula is: Where n1 is the total number of loading cycles, N i,actual is the number of loading times, N i According to the stress amplitude Δσ i Calculated fatigue life; cumulative damage degree D total It can reflect the fatigue damage degree of the steel structure. When the damage degree is equal to 1, it means material failure. Through the design of the above fatigue analysis module, the fatigue damage of the steel structure under multiple loadings can be accurately analyzed, providing solid data support for the remaining life prediction module.

[0114] The remaining life prediction module includes a historical usage data input unit, a damage accumulation analysis unit and a remaining life prediction unit; wherein:

[0115] Historical use data input unit: used to receive the historical use data of the steel structure, including the actual use cycle, load history and environmental factors of the steel structure, and use the historical use data as the input of the prediction model; specifically, the load history data records the external loads borne by the steel structure in different time periods, including static loads, dynamic loads, etc.; the environmental factor data records the impact of external factors such as ambient temperature, humidity, corrosion, etc. on the steel structure; the actual use cycle data records the use time and working frequency of the steel structure in actual work;

[0116] Damage accumulation analysis unit: based on historical usage data and fatigue damage degree D calculated by fatigue analysis module total, , analyze the damage of the steel structure and calculate its current damage state D current , the formula is: Among them, Dtotal is the cumulative damage obtained from the fatigue analysis module, D i is the contribution of each use cycle to the damage in the historical use data, n2 is the total number of use cycles, and this unit calculates the current damage state of the steel structure by accumulating the damage of each cycle in the historical use data;

[0117] Remaining life prediction unit: used to combine fatigue damage degree and historical usage data to predict the remaining service life T of steel structures through machine learning regression model remaining , the formula is:

[0118] Among them, T total is the initial design life of the steel structure, T current is the current usage time of the steel structure, λ is the damage accumulation coefficient (set according to material properties and actual usage), D current is the current damage degree of the steel structure; the formula calculates the remaining life through the correction factor of the historical damage degree and the current damage state; through the design of the above-mentioned remaining life prediction module, the historical use data and fatigue damage degree of the steel structure can be comprehensively considered to achieve accurate prediction of the remaining life of the structure, providing data support for subsequent maintenance and overhaul decisions.

[0119] The optimization design module includes a structural size adjustment unit, a material improvement unit, and a load distribution optimization unit; among which:

[0120] Structural size adjustment unit: used to analyze the size parameters of each component in the steel structure according to the prediction results of the remaining life prediction module, and put forward optimization suggestions;

[0121] The structural size adjustment unit includes:

[0122] Dimensional analysis subunit: Based on the predicted remaining life and structural safety requirements, the stress concentration and safety factor of each component at the existing size are calculated using the formula: Among them, σ safe is the safety factor, σ allow is the allowable stress, σ actual is the actual stress;

[0123] Size optimization subunit: used to adjust the cross-sectional dimensions of the component to improve the safety factor according to the size analysis results. The adjusted dimension D new Calculated by the following formula: Among them, D current is the current component size;

[0124] Material improvement unit: used to select alternative materials to enhance the durability and fatigue life of steel structures based on the results of the remaining life prediction module;

[0125] Load distribution optimization unit: It is used to redistribute the load in the steel structure according to the results of the remaining life prediction module, so as to reduce local stress concentration and extend the service life of the structure. Through the design of the above-mentioned optimization design module, it is possible to systematically propose and implement optimization design suggestions for the steel structure according to the remaining life prediction results, which significantly improves the overall performance and application value of the digital intelligent analysis system for steel structures.

[0126] like Figure 2 As shown, the digital intelligent analysis method for steel structure is implemented by the digital intelligent analysis of steel structure, and includes the following steps:

[0127] S1: The sensor array installed on the steel structure collects the physical parameter information of the steel structure in real time, including stress, strain and displacement data;

[0128] S2: Preprocess the physical parameter data collected in S1, use filtering algorithm to remove noise data, and use interpolation method to fill in missing data;

[0129] S3: Based on the physical parameters preprocessed in S2, the finite element method is used to perform stress analysis on the steel structure, and the stress distribution data of the steel structure under different load conditions is calculated;

[0130] S4: Based on the stress distribution data calculated in S3, a fatigue analysis is performed using a mineralogical method to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree;

[0131] S5: Based on the fatigue damage degree obtained in S4 and the historical usage data of the steel structure, a machine learning regression model is used to predict the remaining service life of the steel structure;

[0132] S6: Based on the remaining service life results predicted in S5 and combined with the structural safety requirements, put forward optimization design suggestions for the steel structure, including structural size adjustment, material improvement and load distribution optimization.

[0133] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0134] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The digital intelligent analysis system for steel structures is characterized by: It includes information acquisition module, data preprocessing module, stress analysis module, fatigue analysis module, remaining life prediction module and optimization design module; among which: Information acquisition module: used to collect physical parameters of steel structures in real time, including stress, strain and displacement data; Data preprocessing module: used to preprocess the physical parameters collected by the information acquisition module, including noise removal, interpolation filling and data cleaning; Stress analysis module: Based on the pre-processed physical parameters, the finite element method is used to perform stress analysis on the steel structure and calculate the stress distribution data of the steel structure under different load conditions; Fatigue analysis module: Based on the stress distribution data calculated by the stress analysis module, the fatigue analysis is performed using the mineralogical method to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree; Remaining life prediction module: used to predict the remaining service life of steel structures based on the fatigue damage degree obtained by the fatigue analysis module and the historical usage data of steel structures, combined with the machine learning regression model; Optimization design module: It is used to propose optimization design suggestions for steel structures based on the prediction results of the remaining life prediction module and combined with structural safety requirements, including structural size adjustment, material improvement and load distribution optimization.

2. The digital intelligent analysis system for steel structures according to claim 1 is characterized in that: The information acquisition module includes a stress sensor, a strain sensor, a displacement sensor and a data transmission unit; wherein: Stress sensor: It uses strain gauge technology to measure the stress change at a specified position on the steel structure, convert the stress into a resistance change signal, and then convert the signal into digital data output through the circuit; Strain sensor: It uses resistance strain gauge technology to measure the deformation degree of the steel structure in real time based on the change in resistance caused by material strain, converts the deformation signal into voltage change, and converts it into a digital signal for subsequent processing; Displacement sensor: It uses laser displacement measurement technology to irradiate the surface of the steel structure with a laser beam, measure the changes in the laser reflection echo, and thus calculate the displacement of the structure surface; Data transmission unit: used to aggregate the physical parameter data collected by the stress sensor, strain sensor and displacement sensor, and transmit them to the data preprocessing module through a wired or wireless network.

3. The digital intelligent analysis system for steel structures according to claim 1 is characterized in that: The data preprocessing module includes a filtering unit, an interpolation unit and a data cleaning unit; wherein: Filtering unit: used to remove noise from the physical parameter data collected by the information acquisition module. Specifically, the Kalman filter algorithm is used to correct the influence of noise on the data in real time through prediction and update steps, thereby removing high-frequency noise in the data. Interpolation unit: used to interpolate and fill in the missing data in the physical parameters collected by the information acquisition module. It uses cubic spline interpolation method to estimate the missing data points through smooth curve fitting of known data points, and fills the interpolated data into the missing positions; Data cleaning unit: used to clean the data after filtering and interpolation processing, remove outliers, and use the standard deviation method to calculate the standard deviation of the data to eliminate outliers that exceed the set threshold.

4. The digital intelligent analysis system for steel structures according to claim 1 is characterized in that: The stress analysis module includes a finite element modeling unit, a load application unit, a solution unit and a result visualization unit; wherein: Finite element modeling unit: used to divide the steel structure into multiple small finite element units, and generate a finite element model by combining node coordinates, material properties and structural geometry information; Load application unit: used to apply different types of loads to the finite element model according to different working conditions and external environmental conditions. The load types include static loads, dynamic loads or external loads to simulate the stress conditions of the steel structure under actual use conditions; Solving unit: It is used to perform stress analysis on the steel structure by finite element analysis method based on the finite element model after the load is applied, calculate the stress distribution data of the steel structure under different load conditions, and obtain the stress value of each finite element unit; Result visualization unit: used to visualize the calculated stress distribution data.

5. The digital intelligent analysis system for steel structures according to claim 4 is characterized in that: The finite element modeling unit comprises: Structural division subunit: used to divide the steel structure into multiple small finite element units. The mesh generation algorithm is used to divide the overall structure into several regular finite element units, including triangular units, quadrilateral units or hexahedral units, according to the geometric shape and size of the steel structure. Node coordinate acquisition subunit: used to determine the node coordinates of each finite element unit. Based on the geometric information of the steel structure, the coordinate conversion formula is used to convert the structural geometric data in the three-dimensional space into the node coordinates (x i ,y i , z i ); Material property assignment subunit: used to assign corresponding material properties to each finite element, including elastic modulus and Poisson's ratio; Geometric information integration subunit: It is used to combine the geometric information, node coordinates and material properties of the steel structure to generate a finite element model. Specifically, the matrix assembly method is used to assemble the stiffness matrix of each finite element unit into the stiffness matrix K of the overall structure. The expression is: Where n is the total number of finite element units, K e is the stiffness matrix of the e-th finite element unit, that is, the finite element model.

6. The digital intelligent analysis system for steel structures according to claim 5 is characterized in that: The solution unit comprises: Boundary condition application subunit: used to apply corresponding boundary conditions to the global stiffness matrix K and node force vector F according to the actual support and constraint conditions of the steel structure; the specific steps include: First, determine the fixed nodes and free nodes; Then, the stiffness matrix K is modified to reflect the displacement constraints of the fixed nodes, specifically by setting the corresponding stiffness matrix rows and columns to zero and assigning a very large stiffness value K on the diagonal. ii =∞ to achieve, the expression is: K′·u=F′, where K′ is the stiffness matrix after the boundary conditions are applied, u is the node displacement vector, and F′ is the node force vector after the boundary conditions are applied; Displacement solving subunit: used to calculate the displacement vector u of each node of the steel structure by solving the linear equation group K′·u=F′. The specific solution method adopts Gaussian elimination method, and its formula is u=K′ -1 ·F′, iterate and solve until the displacement vector u reaches the preset convergence accuracy; Stress calculation subunit: used to calculate the stress value σ of each finite element unit according to the solved node displacement vector. The specific calculation formula is: ∈=B·u, where B is the strain-displacement matrix; calculate the stress σ according to Hooke's law, the formula is: σ=E·∈, where E is the elastic modulus of the material; summarize the stress values ​​of each finite element unit to generate stress distribution data.

7. The digital intelligent analysis system for steel structures according to claim 1 is characterized in that: The fatigue analysis module includes a stress amplitude calculation unit, a stress ratio calculation unit, an SN curve fitting unit and a fatigue damage degree calculation unit; wherein: The stress amplitude calculation unit is used to calculate the stress amplitude Δσ of the steel structure under multiple loading conditions based on the stress distribution data calculated by the stress analysis module. The formula is: Δσ=σ max -σ min , where σ max is the maximum stress value in the stress distribution, σ min is the minimum stress value; Stress ratio calculation unit: used to calculate the stress ratio R of the steel structure under multiple loadings, that is, the ratio of the minimum stress to the maximum stress. The expression is: S-N curve fitting unit: The mineralogy method is used to fit the relationship between fatigue life N and stress amplitude Δσ corresponding to different stress amplitudes to generate the SN curve. The fitting formula is: Where N is the fatigue life of the material under the stress amplitude Δσ, a and b are constants of the material; Fatigue damage degree calculation unit: used to calculate the fatigue damage degree D of steel structure under multiple loading. The specific calculation steps include: First, for each loading cycle i, according to the stress amplitude Δσ i Calculate the fatigue life N under the corresponding cycle i ; Then, according to the number of loading times, the damage degree D of the corresponding cycle is calculated. i , the formula is; Finally, the total fatigue damage degree D is calculated by accumulating the damage degree of all cycles. total , the formula is: Where n1 is the total number of loading cycles, N i,actual is the number of loading times, N i According to the stress amplitude Δσ i Calculated fatigue life; cumulative damage degree D total It can reflect the fatigue damage degree of the steel structure. When the damage degree is equal to 1, it means that the material has failed.

8. The digital intelligent analysis system for steel structures according to claim 7 is characterized in that: The remaining life prediction module includes a historical usage data input unit, a damage accumulation analysis unit and a remaining life prediction unit; wherein: Historical use data input unit: used to receive the historical use data of the steel structure, including the actual use period, load history and environmental factors of the steel structure; Damage accumulation analysis unit: based on historical usage data and fatigue damage degree D calculated by fatigue analysis module total , analyze the damage of the steel structure and calculate its current damage state D current , the formula is: Among them, D total is the cumulative damage obtained from the fatigue analysis module, D i is the contribution of each usage cycle to damage in the historical usage data, and n2 is the total number of usage cycles; Remaining life prediction unit: used to combine fatigue damage degree and historical usage data to predict the remaining service life T of steel structures through machine learning regression model remaining , the formula is: Among them, T total is the initial design life of the steel structure, T current is the current service life of the steel structure, λ is the damage accumulation coefficient, D current is the current damage degree of the steel structure.

9. The digital intelligent analysis system for steel structures according to claim 1 is characterized in that: The optimization design module includes a structure size adjustment unit, a material improvement unit and a load distribution optimization unit; wherein: Structural size adjustment unit: used to analyze the size parameters of each component in the steel structure according to the prediction results of the remaining life prediction module, and put forward optimization suggestions; The structural size adjustment unit comprises: Dimensional analysis subunit: Based on the predicted remaining life and structural safety requirements, the stress concentration and safety factor of each component under the existing size are calculated. The formula is: Among them, σ safe is the safety factor, σ allow is the allowable stress, σ actual is the actual stress; Size optimization subunit: used to adjust the cross-sectional dimensions of the component to improve the safety factor according to the size analysis results. The adjusted dimension D new Calculated by the following formula: Among them, D current is the current component size; Material improvement unit: used to select alternative materials to enhance the durability and fatigue life of steel structures based on the results of the remaining life prediction module; Load distribution optimization unit: used to redistribute the load in the steel structure according to the results of the remaining life prediction module to reduce local stress concentration and extend the service life of the structure.

10. A digital intelligent analysis method for steel structure, implemented by a digital intelligent analysis system for steel structure according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: The sensor array installed on the steel structure collects the physical parameter information of the steel structure in real time, including stress, strain and displacement data; S2: Preprocess the physical parameter data collected in S1, use filtering algorithm to remove noise data, and use interpolation method to fill in missing data; S3: Based on the physical parameters preprocessed in S2, the finite element method is used to perform stress analysis on the steel structure, and the stress distribution data of the steel structure under different load conditions is calculated; S4: Based on the stress distribution data calculated in S3, a fatigue analysis is performed using a mineralogical method to determine the fatigue life of the steel structure under multiple loadings and calculate the fatigue damage degree; S5: Based on the fatigue damage degree obtained in S4 and the historical usage data of the steel structure, a machine learning regression model is used to predict the remaining service life of the steel structure; S6: Based on the remaining service life results predicted in S5 and combined with the structural safety requirements, put forward optimization design suggestions for the steel structure, including structural size adjustment, material improvement and load distribution optimization.

Images