Large steel structure knowledge and data dual-driven comprehensive performance evaluation method and system

Abstract

The invention belongs to the field of steel structure health monitoring, and provides a knowledge and data dual-driven comprehensive performance evaluation method and system for a large steel structure, and the technical scheme is as follows: simulating a plurality of working conditions under the coupling action of a load and an environment, and obtaining mechanical performance analysis data; a load combination effect is considered, and static performance and stability performance evaluation indexes based on component monitoring data are constructed based on structural component sensitivity analysis; establishing structural dynamic performance indexes based on the structural dynamic characteristics; screening static performance, stability performance evaluation indexes and structural dynamic performance indexes to obtain a large steel structure performance index system; and combining the mechanical property analysis data with the large steel structure performance index system to obtain a steel structure damage grade evaluation result and a steel structure service life prediction result. The problem that unified evaluation standards and specifications are lacked is solved, and intelligent, interactive and comprehensive performance evaluation of the large steel structure is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of steel structure health monitoring, and in particular relates to a comprehensive performance evaluation method and system for large steel structures driven by both knowledge and data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Large steel structures play a pivotal role in modern construction projects due to their excellent mechanical properties and economy, and play an important role in ensuring human life and economic development. Since large steel structures are subject to a variety of load combinations and complex environmental influences during their service, such as corrosion, node damage, component failure and other structural damages, these damages will seriously affect the service performance and safety of the structure. Systematic evaluation of large steel structures to ensure their safety and functionality is a key step in maintaining public safety and extending the life of the structure.

[0004] In actual operation, the evaluation work faces a series of challenges. The large-scale plane size of large steel structures and the large number of components make it unrealistic and unnecessary to conduct comprehensive monitoring and evaluation of all components. Although the performance status of structural components is an important part of the structural evaluation system, considering the cost and efficiency, a more accurate and targeted evaluation method must be adopted.

[0005] Due to the lack of unified evaluation standards and norms, there may be differences in evaluation methods and results in different regions and countries, which further increases the difficulty of evaluation. In addition, the limitations of evaluation technology and the lack of experience of professionals have challenged the accuracy and reliability of evaluation results.

[0006] The performance degradation and safety status of large steel structures show obvious differences in different service stages, operating environments, and geological and weather conditions. This difference increases the complexity of the assessment and makes it difficult to accurately assess the status of large steel structures.

[0007] Existing steel structure performance evaluation methods, such as the one with publication number CN 115034001 A and the invention name "A method, system, equipment and medium for evaluating the bearing performance of corroded steel structures", rely on scanning the corrosion characteristics of local areas of the steel structure to represent the corrosion condition of the entire structure. If the selected local area cannot fully represent the corrosion condition of the entire structure, the evaluation results may be biased. When establishing a random characterization model of the corroded surface, the preset corrosion dynamics model may not cover all actual corrosion conditions, especially for non-uniform corrosion and complex corrosion morphology. As the structure is used and the environment changes, the corrosion situation will continue to develop, and the model needs to be updated and re-evaluated regularly. Environmental factors and the like may have an impact on the corrosion process, but these factors may not be fully considered in the model. Summary of the invention

[0008] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides a comprehensive performance evaluation method and system driven by both knowledge and data of large steel structures. It constructs a diversified hierarchical standardized indicator system based on a structural robustness evaluation method based on sensitivity analysis and practical correction, and realizes intelligent, interactive and comprehensive performance evaluation of large steel structures through new monitoring technology, data fusion analysis and multi-attribute decision-making methods.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: The first aspect of the present invention provides a comprehensive performance evaluation method for large steel structures driven by knowledge and data, comprising the following steps: Simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; Considering the combined effects of loads, analyze the importance of structural components, identify important components, and construct static and stability performance evaluation indicators for important components; Establish structural dynamic performance indicators based on structural dynamic characteristics; The static performance, stability performance evaluation indexes and structural dynamic performance indexes are screened, and a large steel structure performance index system is constructed according to the set multiple dimensions; The steel structure performance evaluation results are obtained by combining the acquired multi-source data, mechanical properties analysis data and large-scale steel structure performance index system.

[0010] Furthermore, the consideration of the combined action of loads, the importance analysis of structural components, and the determination of important components include: Calculate the maximum displacement ratio under each load combination respectively, take the average value of the maximum displacement ratio under all load combinations, and obtain the comprehensive preliminary importance index of the component; The calculation process of the maximum displacement ratio under each load is: Calculate the maximum displacement of a steel structure under a given load combination in its original state without weakening any components , weaken the cross-section of each key component one by one, simulate its performance degradation or damage, and calculate the maximum displacement of the structure under the same load combination ; For each weakened component, combine and The ratio of the maximum displacement is calculated by the ratio of

[0011] Furthermore, the construction process of the static performance and stability performance evaluation index of important components includes: In the static performance index part, for axial load-bearing members and bending members, the evaluation method for member bearing capacity in the building reliability appraisal standard is used to analyze the force performance of the rods under multiple load combinations, and the static performance strength index of the axial members and bending members is obtained; In the part of stability performance index, axial force and bending are comprehensively considered, and the monitoring data along the main axis direction is determined according to the cross-sectional stress distribution law. The stress-stability relationship is established, and the stability performance strength index of axial components and bending components is calculated.

[0012] Furthermore, the static performance strength index of the axial component is: , The static performance strength index of the bending member is: , in, It is the static strength index of the axial component. It is The load factor for each load combination, It is The axial force under each load combination is is the cross-sectional area of ​​the component, is the number of load combinations, It is the static strength index of the bending member. It is The bending moment under each load combination, is the section modulus; Stability performance indicators of axial components: , Stability performance indicators of bending members: , in, It is the stability performance index of the axial component. is the critical load of the axial member, is the load applied on the axial member; It is the stability performance index of the bending member. is the critical bending moment of the bending member, is the bending moment applied to the bending member.

[0013] Furthermore, the establishment of a structural dynamic performance index based on the structural dynamic characteristics includes: Based on the assumptions of node articulation, mass concentration and rigid body, the steel structure is simplified into a multi-degree-of-freedom system and the free vibration equation is obtained. The free vibration equation is solved according to the quasi-static method to obtain the structural dynamic characteristics. The structural natural vibration frequency in the structural dynamic characteristics is selected to establish the structural dynamic performance index.

[0014] Furthermore, the structural dynamic performance index is: , in, is the minimum natural frequency obtained by solving the eigenvalue problem, is the basic natural frequency.

[0015] Furthermore, when screening static performance, stability performance evaluation indicators, and structural dynamic performance indicators, the indicators are screened according to the importance of each indicator, the degree of correlation between the indicators, and the degree of distinction.

[0016] Furthermore, the performance index system of large steel structures is expressed as: , in, is a safety indicator, is the applicability indicator, is the durability index, It is an economic indicator; Safety indicators It is expressed as: , Suitability indicators It is expressed as: , Durability index It is expressed as: , Economic indicators It is expressed as: .

[0017] Furthermore, the steel structure performance evaluation results obtained by combining the acquired multi-source data, mechanical performance analysis data and large-scale steel structure performance index system include: Combining the perception data, twin data, mechanical performance analysis data and the constructed steel structure status diagnosis model, the structural status knowledge is obtained; Acquire knowledge from multiple sources, including expert knowledge base, national and industry standards, historical reference knowledge, on-site manual preliminary judgment results, and common sense knowledge; The structural state knowledge, knowledge from multiple sources and the performance index system of large steel structures are input into the large language model, and unified knowledge encoding is performed to obtain the steel structure performance evaluation results.

[0018] The second aspect of the present invention provides a comprehensive performance evaluation system for large steel structures driven by both knowledge and data, including: Mechanical analysis module, which is used to simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; The index system construction module is used to consider the combined effects of loads, analyze the importance of structural components, determine important components, and construct static performance and stability performance evaluation indicators of important components; establish structural dynamic performance indicators based on structural dynamic characteristics; screen static performance, stability performance evaluation indicators, and structural dynamic performance indicators, and construct a large-scale steel structure performance index system according to the set multiple dimensions; The performance evaluation module is used to combine the acquired multi-source data, mechanical performance analysis data and large-scale steel structure performance index system to obtain steel structure performance evaluation results.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention proposes a structural robustness assessment method based on importance analysis and practical correction, providing an overall mechanical performance information basis of "transforming points into fields" for comprehensive performance evaluation; establishing a diversified hierarchical standardized indicator system for long-term service performance evaluation of large steel structures, forming a scientific construction process for the evaluation indicator system including discussions of units participating in the entire life cycle of steel structures, consultation with field experts and analysis of national industry standards, and studying multi-level screening of the indicator system and structural optimization methods.

[0020] 2. In view of the complexity of large-scale steel structures and the diversity of construction scenarios, establishing a comprehensive structural performance index system during the design and operation of large-scale steel structures is the key to ensuring structural safety, functional applicability, durability and economic efficiency.

[0021] 3. The invention provides a new monitoring method, intelligent detection technology, data fusion analysis and result evaluation for large-scale steel structure operation and maintenance standards, proposes a comprehensive performance evaluation method for large-scale steel structures, and constructs a steel structure status diagnosis, evaluation and early warning smart engine to achieve intelligent, interactive and comprehensive performance evaluation of large-scale steel structures.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 It is a comprehensive performance evaluation framework diagram of large steel structure knowledge and data dual-driven provided by an embodiment of the present invention; Figure 2 It is a flow chart of a comprehensive performance evaluation method for large steel structures driven by both knowledge and data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0028] Aiming at the problem that the status of large steel structures mentioned in the background technology is difficult to accurately evaluate. The present invention integrates the digital twin "full-field virtual perception" technology of key point monitoring and global finite element analysis, proposes a structural robustness evaluation method based on sensitivity analysis and practical correction, and provides an overall mechanical performance information basis of "transforming points into fields" for comprehensive performance evaluation; establishes a diversified hierarchical standardized indicator system for long-term service performance evaluation of large steel structures, forms a scientific construction process of the evaluation indicator system including discussions of units participating in the entire life cycle of steel structures, consultation with experts in the field and analysis of national industry standards, and studies multi-level screening and structural optimization methods of the indicator system; on this basis, revise the operation and maintenance standards of large steel structures including new monitoring methods, intelligent detection technologies, data fusion analysis and result evaluation, propose a comprehensive performance evaluation method for large steel structures based on multi-attribute decision-making, and build a steel structure status diagnosis, evaluation and early warning smart engine to achieve intelligent, interactive and comprehensive performance evaluation of large steel structures.

[0029] Embodiment 1 like Figure 1 and Figure 2 As shown, this embodiment provides a comprehensive performance evaluation method for large steel structures driven by knowledge and data, including the following steps: Step 1: Simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; Large steel structures are subject to various load combinations and complex environmental influences, and are very prone to structural damage such as corrosion, node damage, and component failure, which affects the service performance of the structure.

[0030] In this embodiment, a method combining experiments and numerical analysis is used to simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data, which specifically includes the following steps: Step 101, using a control variable method to conduct an acetic acid salt spray accelerated corrosion test on the steel structure under different load combinations, and summarizing the development law of the corrosion morphology of the steel structure; Step 102, performing a variety of tests on the corroded steel, including a mass loss test (to measure the mass reduction caused by corrosion), a scanning electron microscope test (to observe the microscopic corrosion morphology), an ultra-depth of field three-dimensional microscope observation (to obtain the three-dimensional morphology of the corrosion surface), and a three-dimensional laser scanning characterization test (to accurately measure the shape and size of the corrosion surface), and obtaining a model of steel corrosion changing over time based on the results of the various tests; Step 103, analyzing the corrosion mechanism, simplifying the model of steel corrosion changing with time, and analyzing the depth of structural steel corrosion pits at different corrosion times based on the simplified model of steel corrosion changing with time; Step 104: Based on the corrosion morphology development law obtained in step 103, the law of the change of corrosion characteristic parameters of different structural steels over time is analyzed to establish a corrosion spatial distribution model; Step 105: Conduct uniaxial tensile tests on the corroded structures (such as truss structures and grid structures) that have been treated with different corrosion times, establish a stress-strain relationship model for structural steel after corrosion, analyze the relationship between corrosion time and the development of the real stress-strain curve of the structural steel, summarize the development law of material properties, and select multiple characteristic parameters such as elastic modulus, yield strength, ultimate strength, yield strain, ultimate strain, elongation after fracture and fracture strain.

[0031] Based on the results of uniaxial tensile tests, the time-varying law of the residual mechanical properties of different structural steels after corrosion is established, the relationship between their corrosion behavior and mechanical property degradation is quantitatively analyzed, and an evaluation method for the residual mechanical properties of different structural steels after corrosion is established to obtain mechanical property analysis data.

[0032] Large steel structures have large plane dimensions and a large number of components. The performance status of structural components is an important component of the structural evaluation system. However, due to the characteristics of large steel structures, it is neither realistic nor necessary to monitor and evaluate all components.

[0033] Step 2: Considering the combined effects of loads and based on the importance analysis of structural components, static performance and stability performance evaluation indicators based on component monitoring data are constructed.

[0034] Step 201: constructing a preliminary importance index of steel structure components; Combining monitoring data, design experience and finite element simulation results, the important components are preliminarily selected by weakening the component cross-section and considering the structural displacement. The preliminary selection importance index is defined by analyzing the maximum displacement ratio of the structure, and the influence of component damage on the overall response of the structure under load is studied. The specific steps include: Step 2011: Calculate the maximum displacement of the steel structure under a given load combination in the original state without weakening any components. , weaken the cross-section of each key component one by one, simulate its performance degradation or damage, and calculate the maximum displacement of the structure under the same load combination ; Step 2012: For each weakened component, the change ratio of the maximum displacement is calculated as: , in, It weakens The maximum displacement after the component is the maximum displacement in the original state.

[0035] Step 2013: Define the importance index based on the maximum displacement change ratio , primary importance index Defined as the structure weakening the The maximum displacement ratio after the component is weakened. This ratio reflects the impact of weakening the component on the overall response of the structure: , in, Indicates The initial importance index of each component, It is the ratio of the maximum displacement after weakening the component to the maximum displacement in the original state.

[0036] Step 2014: If the structure is subjected to multiple load combinations, repeat steps 2011 to 2013 for each load combination and calculate the maximum displacement ratio under each load combination. ,in Represents the load combination number; take the average value of the maximum displacement ratio under all load combinations to obtain the comprehensive preliminary importance index of the component: , in, is the number of load combinations.

[0037] Step 202: Determine important components based on the preliminary importance index, and construct static performance index and stability performance index of the important components; According to the design specifications, the permanent loads and variable loads of the structure are selected to form a multi-condition analysis model that takes into account the load combination coefficient. The stress value and sensitivity of the preliminary selected components under the most unfavorable conditions are studied and analyzed to determine the important components.

[0038] According to the different stress states of different components, strength and stability analysis is carried out in combination with monitoring data to form static performance indicators and stability performance indicators; In the static performance index part, for axial load-bearing components and bending components, the evaluation method for component bearing capacity in the building reliability appraisal standard is referenced to establish the analysis method and calculation logic of the rod force performance under multiple load combinations, and form the static performance strength index of axial components and bending components to guide the component performance evaluation; Among them, the static performance strength index of the axial component is: , in, It is the static strength index of the axial component. It is The load factor for each load combination, It is The axial force under each load combination is is the cross-sectional area of ​​the component, is the number of load combinations; The static performance strength index of the bending member is: , in, It is the static strength index of the bending member. It is The load factor for each load combination, It is The bending moment under each load combination, is the section modulus, is the number of load combinations; The implementation method of the stability performance index is similar. It comprehensively considers axial force and bending, determines the monitoring data along the main axis according to the cross-sectional stress distribution law, establishes the stress-stability relationship, and calculates the stability performance strength index of axial components and bending components to guide component performance evaluation. Based on the calculation method derived from the structural reliability analysis, the evaluation criteria for main components and general components are determined.

[0039] Among them, the stability performance index of the axial component is: , in, It is the stability performance index of the axial component. is the critical load of the axial member, is the load applied on the axial member; Stability performance indicators of bending members: , in, It is the stability performance index of the bending member. is the critical bending moment of the bending member, is the bending moment applied to the bending member.

[0040] Step 3: Establish the dynamic performance index of steel structure; In this embodiment, based on the node articulation, mass concentration, and rigid body assumptions, the free vibration equation is solved according to the quasi-static method to obtain the structural dynamic characteristics, focusing on the structural natural frequency to establish the structural dynamic performance index.

[0041] The specific steps include: Step 301, based on the node articulation, mass concentration, and rigid body assumptions, the structure can be simplified into a multi-degree-of-freedom system, and the free vibration equation can be expressed as: , in, is the mass matrix, is the damping matrix, is the stiffness matrix, is the displacement vector, and are the second and first order time derivatives of the displacement vector, respectively; Step 302: Perform and solve the free vibration equation according to the quasi-static method to obtain the structural dynamic characteristics, focusing on the structural natural frequency to establish the structural dynamic performance index; For an undamped or lightly damped system, the equation simplifies to: , Its solution can be expressed as: ,in, It is The vibration shape vector of the mode, It is The natural frequency of the mode, is the phase angle, is the number of degrees of freedom.

[0042] The structural dynamic performance index mainly focuses on the natural frequency of the structure, which can be determined by solving the eigenvalue problem of the above equation. The eigenvalue problem can be expressed as: , Solving this equation gives the natural frequency of the system .

[0043] Natural frequency With natural frequency The relationship is: , The structural dynamic performance index can be defined as the basic natural frequency of the structure , which reflects the response characteristics of the structure to dynamic loads.

[0044] Therefore, the specific formula of the structural dynamic performance index is: , in It is the minimum natural frequency obtained by solving the eigenvalue problem, the dynamic performance index of the structure, that is, the basic natural frequency .

[0045] Step 4: Construct a performance index system for large steel structures; The specific steps include: Step 401, screening static performance, stability performance evaluation index, and structural dynamic performance index; The index system initially constructed based on steps 2 and 3 already has the principle of comprehensiveness, but the correlation between indicators is high, the independence is not strong, and there will be duplication and conflict. Therefore, a multi-level screening and structural optimization method of the index system is studied. The indicators are screened according to their importance, the degree of correlation between indicators, and the degree of distinction to obtain the final indicators.

[0046] The calculation formula of the indicator importance is: , in: It is The importance score of each indicator, It is Experts on The weight of the indicator, It is Experts on The ratings of the indicators, is the number of experts.

[0047] The calculation formula for the correlation between indicators is: , in, It is and The correlation between the indicators It is The indicator is The observed value, It is The average value of the indicators, is the number of observations.

[0048] Use ANOVA to measure the degree of discrimination of the indicators: , in: It is The degree of differentiation of the indicators, It is The sum of squares between groups of indicators, is the total sum of squares.

[0049] Taking into account the importance, relevance and differentiation of the indicators, a comprehensive scoring formula can be constructed: , in: It is The comprehensive score of the indicators, It is The importance score of each indicator, It is The average correlation of the indicators, It is The degree of differentiation of the indicators.

[0050] Step 402: construct a large steel structure performance index system based on the selected indicators according to the four main dimensions of safety, applicability, durability and economy; In this embodiment, the performance index system of large steel structures is expressed as , in, is a safety indicator, is the applicability indicator, is the durability index, It is an economic indicator; Safety indicators It is expressed as: , Bearing capacity and stability are the basis of structural safety. Bearing capacity, as the basic ability to evaluate the structure's resistance to external forces, is directly related to the overall safety of the structure, while stability evaluates the structure's balance and deformation capacity under various load combinations. In order to meet the challenges of dynamic loads such as earthquakes, energy dissipation capacity indicators are proposed to evaluate the ability of structures to absorb and dissipate energy through plastic deformation and other means, which is crucial to reducing the impact of disasters such as earthquakes on structures. Vulnerability indicators focus on the sensitivity of structures to damage in various extreme events and evaluate the ease with which structures are damaged. Self-restoration is an innovative evaluation indicator that aims to measure the ability of steel structures to automatically restore their initial state after the dynamic load disappears, which not only affects the recovery of the structure's functional use, but also determines the complexity and cost of subsequent maintenance. Redundancy, seismic resistance and fire resistance are supplementary evaluations of structural performance under specific disaster conditions to ensure the safety of structures under extreme conditions.

[0051] Suitability indicators It is expressed as: , Amplitude and deflection mainly measure the deformation of the structure during service, while lateral displacement and inter-story displacement angle control the overall deformation of large steel structures under horizontal loads to prevent excessive deformation or collapse risks of the structure. Crack width is an important indicator in steel structures, and controlling crack development is crucial to maintaining structural durability. Air circulation, thermal comfort and noise control mainly consider closed large steel structure facilities. Involving the internal environmental quality of the building, these indicators have a direct impact on improving the living or use comfort of the building. Air circulation ensures good ventilation and air quality, and thermal comfort involves the regulation of thermal comfort in winter and summer. Noise control further improves the use comfort of steel structure facilities.

[0052] Durability index It is expressed as: , The durability dimension index comprehensively evaluates and analyzes the performance of the structure during long-term service. Stress relaxation reflects the stress attenuation of steel under long-term loads. Fatigue strength and vibration fatigue are the fatigue resistance of the structure under repeated loads. Corrosion fatigue and weather resistance focus on the durability of steel structures under different environmental conditions. Corrosion fatigue assesses the risk of fatigue damage to steel in a corrosive environment, while weather resistance involves the aging and performance degradation of materials under various climatic conditions. The stiffness degradation rate measures the trend of structural stiffness over time, which is of great significance for evaluating the service life and safety of steel structures. Environmental adaptability is a comprehensive evaluation of the adaptability of the structure to extreme environments (such as extreme cold, high salt, high humidity, etc.), ensuring the stability and durability of the structure under different natural conditions.

[0053] Economic indicators It is expressed as: , The economic dimension indicators mainly involve two indicators: maintainability and service life. Maintainability involves the maintenance cost and difficulty of the structure throughout its life cycle, while service life is a prediction of the overall life of the steel structure. The setting of economic indicators not only takes into account the cost, but also includes the subsequent operation and maintenance costs. By building a comprehensive steel structure performance evaluation system, a scientific basis and indicator support are provided for the comprehensive performance evaluation of the structure.

[0054] Step 5: Combine the mechanical properties analysis data, the acquired multi-source data, and the constructed comprehensive performance evaluation index system to obtain the evaluation results of the steel structure damage level and the prediction results of the steel structure service life; The performance degradation of steel structures and their corresponding safety status at different service stages, different operating environments, and different geological and weather conditions are often different, and the status of large steel structures is difficult to accurately assess.

[0055] In this embodiment, knowledge and data are integrated to achieve dual drive, and finally a comprehensive knowledge evaluation engine is constructed to realize intelligent, interactive and comprehensive performance evaluation of large steel structures. Specifically, the following steps are included: Step 501: Combining the perception data, twin data, and mechanical performance analysis data with the constructed steel structure state diagnosis model based on machine learning to obtain structural state knowledge; In this embodiment, the collected perception data, twin data and mechanical property analysis data are cleaned to remove outliers and noise, and the data are normalized to ensure that different parameters are compared at the same level; a stacked autoencoder is used to perform feature encoding on the steel structure operating environment, mechanical property analysis results, and stress, strain, displacement and other data monitored by sensors, and input into a state diagnosis model based on machine learning models such as deep neural networks and gradient boosting trees. Knowledge is extracted from the model output, and the multi-feature parameter analysis results are converted into the knowledge required to describe the structural state, thereby realizing the conversion from original detection data to steel structure state knowledge.

[0056] Step 502: Acquire knowledge from multiple sources (including expert knowledge base, national and industry standards, historical reference knowledge, on-site manual preliminary judgment results, common sense knowledge, etc.); Step 503: input the acquired structural state knowledge, knowledge from multiple sources, and the large-scale steel structure performance index system constructed in step 4 into the large language model, perform unified knowledge encoding, and obtain the steel structure performance evaluation result; In this embodiment, the large language model used can be implemented by an existing model; the large language model is used to understand and process the knowledge in the natural language text and convert the knowledge into a structured form. The model can capture the complexity and diversity of the language, so as to understand and represent different types of knowledge to a certain extent. In this way, the knowledge in the text can be converted into a format that can be used by machine learning and data analysis algorithms.

[0057] In this embodiment, the steel structure performance assessment results include qualitative and quantitative evaluations of safety status level, damage level, complete warning information, impact range, development trend, etc., providing a scientific reference for the formulation of maintenance and repair plans for large steel structures and safety warnings.

[0058] Embodiment 2 This embodiment provides a comprehensive performance evaluation system for large steel structures driven by knowledge and data, including: Mechanical analysis module, which is used to simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; The index system construction module is used to consider the combined effects of loads, analyze the importance of structural components, determine important components, and construct static performance and stability performance evaluation indicators of important components; establish structural dynamic performance indicators based on structural dynamic characteristics; screen static performance, stability performance evaluation indicators, and structural dynamic performance indicators, and construct a large-scale steel structure performance index system according to the set multiple dimensions; The performance evaluation module is used to combine the acquired multi-source data, mechanical performance analysis data and large-scale steel structure performance index system to obtain steel structure performance evaluation results.

[0059] Embodiment 3 This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the comprehensive performance evaluation method of large-scale steel structures driven by both knowledge and data as described above are implemented.

[0060] Embodiment 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the comprehensive performance evaluation method for large steel structures driven by both knowledge and data as described above are implemented.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A comprehensive performance evaluation method driven by knowledge and data for large steel structures, characterized by: The steps include: Simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; Considering the combined effects of loads, analyze the importance of structural components, identify important components, and construct static and stability performance evaluation indicators for important components; Establish structural dynamic performance indicators based on structural dynamic characteristics; The static performance, stability performance evaluation indexes and structural dynamic performance indexes are screened, and a large steel structure performance index system is constructed according to the set multiple dimensions; The steel structure performance evaluation results are obtained by combining the acquired multi-source data, mechanical properties analysis data and large-scale steel structure performance index system.

2. The large-scale steel structure knowledge and data dual-driven comprehensive performance evaluation method according to claim 1 is characterized in that: The above-mentioned consideration of the combined action of loads, analysis of the importance of structural components, and determination of important components include: Calculate the maximum displacement ratio under each load combination respectively, take the average value of the maximum displacement ratio under all load combinations, and obtain the comprehensive preliminary importance index of the component; The calculation process of the maximum displacement ratio under each load is: Calculate the maximum displacement of a steel structure under a given load combination in its original state without weakening any components , weaken the cross-section of each key component one by one, simulate its performance degradation or damage, and calculate the maximum displacement of the structure under the same load combination ; For each weakened component, combine and The ratio of the maximum displacement is calculated by the ratio of 3. The comprehensive performance evaluation method for large steel structures driven by knowledge and data as claimed in claim 1 is characterized in that: The construction process of static performance and stability performance evaluation index of important components includes: In the static performance index part, for axial load-bearing members and bending members, the evaluation method for member bearing capacity in the building reliability appraisal standard is used to analyze the force performance of rods under multiple load combinations, and the static performance strength index of axial members and bending members is obtained; In the part of stability performance index, axial force and bending are comprehensively considered, and the monitoring data along the main axis direction is determined according to the cross-sectional stress distribution law. The stress-stability relationship is established, and the stability performance strength index of axial components and bending components is calculated.

4. The comprehensive performance evaluation method for large steel structures driven by knowledge and data as claimed in claim 3 is characterized in that: The static performance strength index of the axial component is: ， The static performance strength index of the bending member is: ， in, It is the static strength index of the axial component. It is The load factor for each load combination, It is The axial force under each load combination is is the cross-sectional area of ​​the component, is the number of load combinations, It is the static strength index of the bending member. It is The bending moment under each load combination, is the section modulus; Stability performance indicators of axial components: ， Stability performance indicators of bending members: ， in, It is the stability performance index of the axial component. is the critical load of the axial member, is the load applied on the axial member; It is the stability performance index of bending members. is the critical bending moment of the bending member, is the bending moment applied to the bending member.

5. The large-scale steel structure knowledge and data dual-driven comprehensive performance evaluation method according to claim 1 is characterized in that: The establishing of structural dynamic performance indicators based on structural dynamic characteristics includes: Based on the assumptions of node articulation, mass concentration and rigid body, the steel structure is simplified into a multi-degree-of-freedom system and the free vibration equation is obtained. The free vibration equation is solved according to the quasi-static method to obtain the structural dynamic characteristics. The structural natural vibration frequency in the structural dynamic characteristics is selected to establish the structural dynamic performance index.

6. The comprehensive performance evaluation method for large steel structures driven by knowledge and data as claimed in claim 5 is characterized in that: The structural dynamic performance indicators are: ， in, is the minimum natural frequency obtained by solving the eigenvalue problem, is the basic natural frequency.

7. The comprehensive performance evaluation method for large steel structures driven by knowledge and data as claimed in claim 1 is characterized in that: When screening static performance, stability performance evaluation indicators, and structural dynamic performance indicators, the indicators are screened based on the importance of each indicator, the degree of correlation between the indicators, and the degree of distinction.

8. The large-scale steel structure knowledge and data dual-driven comprehensive performance evaluation method according to claim 1 is characterized in that: The performance index system of large steel structures is expressed as: ， in, is a safety indicator, is the applicability indicator, is the durability index, It is an economic indicator; Safety indicators It is expressed as: ， Suitability indicators It is expressed as: ， Durability index It is expressed as: ， Economic indicators It is expressed as: 。 9. The large-scale steel structure knowledge and data dual-driven comprehensive performance evaluation method according to claim 1 is characterized in that: The steel structure performance evaluation results obtained by combining the acquired multi-source data, mechanical performance analysis data and large-scale steel structure performance index system include: Combining the perception data, twin data, mechanical performance analysis data and the constructed steel structure status diagnosis model, the structural status knowledge is obtained; Acquire knowledge from multiple sources, including expert knowledge base, national and industry standards, historical reference knowledge, on-site manual preliminary judgment results, and common sense knowledge; The structural state knowledge, knowledge from multiple sources and the performance index system of large steel structures are input into the large language model, and unified knowledge encoding is performed to obtain the steel structure performance evaluation results.

10. A comprehensive performance evaluation system driven by knowledge and data for large steel structures, characterized by: include: Mechanical analysis module, which is used to simulate various working conditions under the coupling of load and environment to obtain mechanical performance analysis data; Index system construction module, which is used to consider the combined effects of loads, analyze the importance of structural components, determine important components, and construct static performance and stability performance evaluation indicators for important components; Establish structural dynamic performance indicators based on structural dynamic characteristics; The static performance, stability performance evaluation indexes and structural dynamic performance indexes are screened, and a large steel structure performance index system is constructed according to the set multiple dimensions; The performance evaluation module is used to combine the acquired multi-source data, mechanical performance analysis data and large-scale steel structure performance index system to obtain steel structure performance evaluation results.

Images