Safety monitoring method and monitoring device for steel structure

By calibrating the key nodes and environmental data of the steel structure, a safety monitoring model is built and a safety index is generated, which solves the problem of insufficient monitoring scope and real-time performance in the existing technology, and achieves a comprehensive and accurate safety assessment and early warning of the steel structure.

CN118583415BActive Publication Date: 2024-11-12CCCC THIRD NAVIGATION (NANTONG) OFFSHORE ENG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411075670.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-12
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

The existing steel structure monitoring technology has limited monitoring scope, insufficient data, poor real-time performance, and cannot fully reflect the health status of the steel structure. It especially ignores the influence of key nodes and environmental factors, resulting in insufficient timeliness of safety warning and maintenance.

Method used

By calibrating the endpoints of the main beam, connecting nodes and the middle positions of the beam and column of the steel structure, strain, stress and displacement data are obtained, corrosion rate is measured in combination with the linear polarization resistance method, and safety monitoring model is constructed using a multivariate linear regression model to collect environmental data in real time. Generate security indexes and conduct a comprehensive security assessment.

Benefits of technology

Comprehensive and accurate safety monitoring of steel structures is achieved, real-time and accuracy of monitoring is improved, the importance of key nodes is valued, and the corrosion situation can be promptly warned and predicted, and the risk of structural failure is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118583415B_ABST
    Figure CN118583415B_ABST
Patent Text Reader

Abstract

The present invention provides a safety monitoring method and a monitoring device for a steel structure, and relates to the technical field of safety monitoring of steel structures, and specifically provides a safety monitoring method for a steel structure. The present invention first calibrates and obtains structural response data including strain, stress, and displacement of key nodes, as well as corrosion rate data obtained by testing using a linear polarization resistance method, pre-processes and reversely processes these data to generate a safety index, and collects environmental data such as temperature, rainfall, and wind speed in real time, and inputs them into a safety monitoring model constructed based on a multivariate linear regression model for training; regularly collects and inputs new data into the trained model to output the safety index of each key node; finally, a safety assessment index of the overall steel structure is comprehensively generated in combination with the safety index of each key node, and compared with a safety threshold value to comprehensively judge the current safety status of the steel structure.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of steel structure safety monitoring, in particular to a steel structure safety monitoring method and a monitoring device. Background Art

[0002] In modern steel structure projects, safety monitoring has always been an important part of ensuring structural stability and service life. Traditional steel structure monitoring technology mainly relies on physical sensors such as strain sensors and displacement sensors for point monitoring. However, these traditional methods have problems such as limited monitoring range, insufficient data continuity, and poor real-time performance, making it difficult to fully reflect the health status of steel structures. In addition, with the development of intelligent buildings and big data technologies, higher requirements are placed on the real-time, accuracy, and intelligence of steel structure monitoring. Existing technologies still have deficiencies in data processing, real-time warning, and maintenance decision-making. A more comprehensive, efficient, and intelligent monitoring solution is needed to solve these technical problems.

[0003] Traditional monitoring methods usually rely on static data such as strain, stress, displacement, etc. at limited locations. Although these data provide basic information about the structural status, they often ignore the importance of key nodes (such as main beam endpoints and connection nodes) and the impact of environmental factors on the long-term performance of the structure.

[0004] The prior art has the following deficiencies:

[0005] In the field of steel structure safety monitoring, existing technologies usually rely on data from a single or limited location, and usually ignore the comprehensive coverage of key nodes, especially the importance of main beam endpoints and connection nodes. In addition, traditional methods often lack real-time monitoring of corrosion rates and systematic consideration of environmental factors, which makes the assessment of the safety status of steel structures lack comprehensiveness and accuracy. Existing technologies mainly focus on the acquisition and analysis of static data, and cannot adapt to the dynamic impact of complex and changing environmental conditions on steel structures, resulting in insufficient timeliness of safety warnings and maintenance. These deficiencies will make it impossible for steel structures to respond and warn in a timely manner when facing sudden loads or environmental changes in actual applications, increasing the risk of structural failure.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a safety monitoring method and a monitoring device for a steel structure to solve the problems raised in the above background technology.

[0008] Safety monitoring method of steel structure, the specific steps include:

[0009] Step 1: Mark the main beam endpoints, connection nodes, and middle positions of beams and columns of the steel structure as key nodes, and obtain the structural response data of each key node, wherein the structural response data includes strain data, stress data, and displacement data of the steel structure;

[0010] Step 2: Perform linear polarization resistance test on the key nodes of the steel structure, and obtain the corrosion rate data of each key node according to the test results;

[0011] Step 3: Preprocess and reversely process the structural response data and corrosion rate data of each key node of the steel structure to generate a safety index for each key node;

[0012] Step 4: Collect environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, build a safety monitoring model for the steel structure based on a multivariate linear regression model, and use the structural response data, corrosion rate data and environmental data of each key node of the steel structure as a training set, and the safety index of the corresponding key node as a label to train the safety monitoring model;

[0013] Step 5: Regularly collect environmental data, structural response data and corrosion rate data of each key node of the steel structure, input them into the trained safety monitoring model, and output the safety index of each key node of the steel structure;

[0014] Step 6: Based on the type of each key node and the safety index of each key node, a comprehensive safety assessment index of the steel structure to be monitored is generated. The safety assessment index of the steel structure is analyzed and compared with the safety threshold to comprehensively judge the current safety status of the steel structure.

[0015] Furthermore, the specific steps for obtaining the structural response data of the key nodes of the steel structure are as follows:

[0016] The strain is detected by measuring the change of wavelength in the optical fiber through the fiber Bragg grating sensor. When light of a specific wavelength propagates in the optical fiber, it will be reflected when it encounters the Bragg grating, and the reflected wavelength is called the Bragg wavelength. When the optical fiber is subjected to stress changes, the Bragg wavelength will shift. By measuring this shift, the strain data and stress data of the steel structure can be determined;

[0017] The specific formula for obtaining the strain data of the steel structure is:

[0018]

[0019] in, For steel structure The strain of the key node is , For steel structure The change in the Bragg wavelength of a key node, in units of , For steel structure The initial Bragg wavelength of the key nodes, is the strain sensitivity coefficient;

[0020] The specific formula for obtaining stress data of steel structures is:

[0021]

[0022] in, For steel structure The stress of the key node is , is the elastic modulus of steel, in ;

[0023] The specific formula for obtaining displacement data is:

[0024]

[0025] in, For steel structure The displacement of the steel structure at the key node is For the The original length of the steel structure at the key node, in units of .

[0026] Furthermore, the specific logic for obtaining the corrosion rate data of each key node is as follows:

[0027] The linear polarization resistance method applies a small potential offset to the metal electrode and measures the corresponding current response. By analyzing the relationship between potential and current, the polarization resistance can be determined, and then the corrosion rate can be calculated. The specific logic for obtaining the corrosion rate of the steel structure is:

[0028] The potential shift and the corresponding current response are plotted into a polarization curve, and the polarization resistance is calculated from the slope of the polarization curve.

[0029]

[0030] in, For steel structure Key node polarization resistance, It is the first The potential offset applied to the key nodes, It corresponds to Current changes at key nodes;

[0031] The specific formula for calculating the corrosion current density is:

[0032]

[0033] in, For steel structure The corrosion current density of the key nodes is in , for Constant, in units of , For steel structure Key node polarization resistance, unit is ;

[0034] The corrosion current density is converted into the corrosion rate, and the specific formula for obtaining the corrosion rate is:

[0035]

[0036] in, For steel structure The corrosion rate of key nodes, in units of , is the conversion factor in units of , is the equivalent weight of the metal, is the density of the metal in .

[0037] Furthermore, the structural response data and corrosion rate data of each key node of the steel structure are pre-processed and reversely processed, and the specific logic for generating the safety index of each key node is as follows:

[0038] The obtained strain data, stress data, displacement data and corrosion rate data of the steel structure are normalized to the maximum value and scaled to Within the range, reverse processing is performed to calculate the individual safety index of each data. The formula for obtaining each individual safety index is as follows:

[0039]

[0040]

[0041]

[0042]

[0043] Among them, the single safety index , , , Respectively represent the first The strain data, stress data, displacement data and corrosion rate data of key nodes are in the range of , the larger the value, the higher the security;

[0044] The specific formula for obtaining the safety index of key nodes is:

[0045]

[0046] in, For the The safety index of key nodes, , , , are the weights of strain data, stress data, displacement data and corrosion rate data, respectively, and .

[0047] Furthermore, the specific logic for constructing the safety monitoring model of steel structures is as follows:

[0048] When obtaining the structural response data and corrosion rate data of the steel structure, the temperature, rainfall and wind speed at the location of the steel structure are collected synchronously to generate a sample training set. The characteristic matrix of the steel structure safety monitoring model is constructed through the sample training set. Each row of the characteristic matrix is ​​the structural response data, corrosion rate and environmental data of each key node at the same time, and each column of the characteristic matrix is ​​an eigenvalue. The calibrated characteristic matrix is , the corresponding target vector For the same moment The safety index of key nodes is calculated and the regression coefficient is estimated using the least squares method. .

[0049] Furthermore, the specific logic for obtaining the safety index of each key node of the steel structure is as follows:

[0050] Environmental data, structural response data and corrosion rate data of each key node of the steel structure are collected regularly and input into the trained safety monitoring model. The specific formula for generating the safety index of each key node is as follows:

[0051]

[0052] in, The output of the safety monitoring model is The safety index of key nodes, is the constant intercept term, is the regression coefficient of each variable after training, , , , They represent the strain data, stress data, displacement data and corrosion rate data of each key node of the steel structure collected regularly. , , They are temperature data, rainfall data and wind speed data collected in real time.

[0053] Furthermore, the specific logic for judging the current safety status of the steel structure is as follows:

[0054] According to the type of each key node and the safety index of each key node, the safety assessment index of the steel structure to be monitored is comprehensively generated. The specific formula for generating the safety assessment index is:

[0055]

[0056] in, is the safety assessment index of the steel structure to be monitored, is the total number of key nodes on the main beam endpoints, , is the total number of key nodes at the connection nodes and the middle positions of beams and columns, , is the weight coefficient of the key node on the main beam endpoint, is the weight coefficient of the key nodes at the connection nodes and the middle positions of beams and columns, and ;

[0057] If the safety assessment index of the steel structure is greater than the safety threshold, it is determined that the steel structure is currently in a safe state. If the safety assessment index of the steel structure is less than the safety threshold, it is determined that the current steel structure may be at risk.

[0058] The present invention further provides a safety monitoring device for a steel structure, the safety monitoring device is used to implement the above safety monitoring method, comprising:

[0059] The structural response data acquisition module marks the main beam endpoints, connection nodes, and the middle positions of beams and columns of the steel structure as key nodes, and obtains the structural response data of each key node, wherein the structural response data includes the strain data, stress data, and displacement data of the steel structure;

[0060] The corrosion rate determination module performs linear polarization resistance method tests on key nodes of steel structures and obtains corrosion rate data for each key node based on the test results;

[0061] Data preprocessing module, which preprocesses and reversely processes the structural response data and corrosion rate data of each key node of the steel structure to generate the safety index of each key node;

[0062] The safety monitoring model building module collects the environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, and builds a safety monitoring model for the steel structure based on a multivariate linear regression model. The structural response data, corrosion rate data and environmental data of each key node of the steel structure are used as training sets, and the safety index of the corresponding key node is used as a label to train the safety monitoring model.

[0063] The safety assessment index acquisition module regularly collects environmental data, structural response data and corrosion rate data of each key node of the steel structure, inputs them into the trained safety monitoring model, and outputs the safety index of each key node of the steel structure;

[0064] The comprehensive safety status analysis module generates a comprehensive safety assessment index for the steel structure to be monitored based on the type of each key node and the safety index of each key node. It analyzes the safety assessment index of the steel structure and compares it with the safety threshold to comprehensively judge the current safety status of the steel structure.

[0065] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0066] The data collection scope of the present invention includes the main beam endpoints, connection nodes, and the middle positions of beams and columns, covering a wide range, ensuring the comprehensiveness of the monitoring scope, and when evaluating the overall safety status of the steel structure, more attention is paid to the data of the key nodes on the main beam endpoints. This area is the most important part of the load-bearing structure, and the safety assessment is made more accurate by dividing the weights. In addition, the corrosion rate of the steel structure is also measured in the safety assessment. According to the corrosion rate data, the degree of corrosion of the steel structure in the future can be predicted, and the influence of environmental data on the corrosion rate of the steel structure is taken into account. Comprehensive consideration of various data realizes comprehensive monitoring and accurate assessment of the safety status of the steel structure, and improves the accuracy of the safety assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0068] Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0070] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0071] Example:

[0072] See also Figure 1 The present invention provides a safety monitoring method for a steel structure, the specific steps of which include:

[0073] Step 1: Mark the main beam endpoints, connection nodes, and middle positions of beams and columns of the steel structure as key nodes, and obtain the structural response data of each key node, wherein the structural response data includes strain data, stress data, and displacement data of the steel structure;

[0074] In this embodiment, the specific steps for obtaining the structural response data of the key nodes of the steel structure are as follows:

[0075] The strain is detected by measuring the change of wavelength in the optical fiber through the fiber Bragg grating sensor. When light of a specific wavelength propagates in the optical fiber, it will be reflected when it encounters the Bragg grating, and the reflected wavelength is called the Bragg wavelength. When the optical fiber is subjected to stress changes, the Bragg wavelength will shift. By measuring this shift, the strain data and stress data of the steel structure can be determined;

[0076] The specific formula for obtaining the strain data of the steel structure is:

[0077]

[0078] in, For steel structure The strain of the key node is , For steel structure The change in the Bragg wavelength of a key node, in units of , For steel structure The initial Bragg wavelength of the key nodes, is the strain sensitivity coefficient;

[0079] Strain data reflects the deformation of the structure and helps evaluate whether its deformation behavior under load is within the expected range. Areas of strain concentration may be the initiation points of cracks or other damage. Monitoring strain can help detect these potential problems at an early stage.

[0080] The specific formula for obtaining stress data of steel structures is:

[0081]

[0082] in, For steel structure The stress of the key node is , is the elastic modulus of steel, in units of ;

[0083] By measuring the stress in a structure, the actual load conditions it is subjected to can be evaluated to ensure that it is operating within the designed strength range. Long-term stress fluctuations may cause structural fatigue. Regular monitoring of stress changes can help predict and prevent fatigue damage. Abnormal stress distribution may indicate damage or defects inside the structure. Timely detection and treatment of these problems can avoid serious accidents.

[0084] The specific formula for obtaining displacement data is:

[0085]

[0086] in, For steel structure The displacement of the steel structure at the key node is For the The original length of the steel structure at the key node, in units of .

[0087] Displacement data provides information about the overall deformation of the structure, which helps to assess its overall stability and service performance. Displacement monitoring can also detect problems such as foundation settlement or structural tilt, ensuring the stability and safety of the structure.

[0088] Step 2: Perform linear polarization resistance test on the key nodes of the steel structure, and obtain the corrosion rate data of each key node according to the test results;

[0089] In this embodiment, the specific logic for obtaining the corrosion rate data of each key node is:

[0090] The linear polarization resistance method applies a small potential offset to the metal electrode and measures the corresponding current response. By analyzing the relationship between potential and current, the polarization resistance can be determined, and then the corrosion rate can be calculated. The specific logic for obtaining the corrosion rate of the steel structure is:

[0091] The potential shift and the corresponding current response are plotted into a polarization curve, and the polarization resistance is calculated from the slope of the polarization curve.

[0092]

[0093] in, For steel structure Key node polarization resistance, It is the first The potential offset applied to the key nodes, It corresponds to Current changes at key nodes;

[0094] The specific formula for calculating the corrosion current density is:

[0095]

[0096] in, For steel structure The corrosion current density of the key nodes is in , for Constant, in units of , For steel structure Key node polarization resistance, unit is ;

[0097] The corrosion current density is converted into the corrosion rate, and the specific formula for obtaining the corrosion rate is:

[0098]

[0099] in, For steel structure The corrosion rate of key nodes, in units of , is the conversion factor in units of , is the equivalent weight of the metal, is the density of the metal in .

[0100] By monitoring the corrosion rate, the remaining life of the steel structure can be evaluated. Corrosion may cause local failure or overall collapse. Real-time monitoring can provide early warning of potential safety hazards. Corrosion will reduce the strength of the steel structure. Timely acquisition of corrosion data will help evaluate its bearing capacity and ensure operation within a safe range.

[0101] Step 3: Preprocess and reversely process the structural response data and corrosion rate data of each key node of the steel structure to generate a safety index for each key node;

[0102] In this embodiment, the structural response data and corrosion rate data of each key node of the steel structure are preprocessed and reversely processed, and the specific logic based on which the safety index of each key node is generated is:

[0103] The obtained strain data, stress data, displacement data and corrosion rate data of the steel structure are normalized to the maximum value and scaled to Within the range, reverse processing is performed to calculate the individual safety index of each data. The formula for obtaining each individual safety index is as follows:

[0104]

[0105]

[0106]

[0107]

[0108] Among them, the single safety index , , , Respectively represent the first The strain data, stress data, displacement data and corrosion rate data of key nodes are in the range of , the larger the value, the higher the security;

[0109] The reverse processing converts the standardized value into a safety index, which still ranges from 0 to 1, but the larger the single safety index, the safer the structure. , , and The closer it is to 1, the safer the structure is, and the closer it is to 0, the more dangerous the structure is. This representation method is more intuitive and easy to understand, allowing decision makers to more easily understand and evaluate the safety status of the structure. The reverse processing ensures that the calculation method and value range of all single-phase safety indexes are consistent, which facilitates processing in the comprehensive calculation process and avoids the influence of different parameter scales and dimensions.

[0110] The specific formula for obtaining the safety index of key nodes is:

[0111]

[0112] in, For the The safety index of key nodes, , , , are the weights of strain data, stress data, displacement data and corrosion rate data, respectively, and .

[0113] In the above formula, the dependent variable Representative The safety index of a key node is a comprehensive indicator used to evaluate the overall safety status of a steel structure. This index combines multiple key parameters such as strain, stress, displacement and corrosion rate, and is calculated through weighted calculation to reflect the comprehensive safety performance of the structure in the actual working environment. The safety index of a key node increases with the increase of the individual safety indexes of the strain data, stress data, displacement data and corrosion rate data of the node. If the four types of individual safety indexes of the key node decrease, the corresponding safety index of the node will also decrease.

[0114] Step 4: Collect environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, build a safety monitoring model for the steel structure based on a multivariate linear regression model, and use the structural response data, corrosion rate data and environmental data of each key node of the steel structure as a training set, and the safety index of the corresponding key node as a label to train the safety monitoring model;

[0115] In this embodiment, the specific logic for constructing the safety monitoring model of the steel structure is:

[0116] When obtaining the structural response data and corrosion rate data of the steel structure, the temperature, rainfall and wind speed at the location of the steel structure are collected synchronously to generate a sample training set. The characteristic matrix of the steel structure safety monitoring model is constructed through the sample training set. Each row of the characteristic matrix is ​​the structural response data, corrosion rate and environmental data of each key node at the same time, and each column of the characteristic matrix is ​​an eigenvalue. The calibrated characteristic matrix is , the corresponding target vector For the same moment The safety index of key nodes is calculated and the regression coefficient is estimated using the least squares method. .

[0117] The multivariate linear regression model is a simple and intuitive statistical model that is easy to understand and explain. It links multiple input variables (such as stress, strain, corrosion rate, temperature, rainfall, wind speed, etc.) with output variables (such as safety index) through linear relationships, which makes it easy to understand and explain the results of the model. In addition, the multivariate linear regression model has high computational efficiency and can quickly process large amounts of data and generate results, which is especially important for application scenarios that require real-time monitoring and evaluation of the safety status of steel structures. Therefore, the use of the multivariate linear regression model in steel structure safety monitoring can not only provide accurate and timely safety assessments, but also ensure the ease of use and efficiency of the model to meet the needs of practical engineering applications.

[0118] Step 5: Regularly collect environmental data, structural response data and corrosion rate data of each key node of the steel structure, input them into the trained safety monitoring model, and output the safety index of each key node of the steel structure;

[0119] In this embodiment, the specific logic for obtaining the safety index of each key node of the steel structure is:

[0120] Environmental data, structural response data and corrosion rate data of each key node of the steel structure are collected regularly and input into the trained safety monitoring model. The specific formula for generating the safety index of each key node is as follows:

[0121]

[0122] in, The output of the safety monitoring model is The safety index of key nodes, is the constant intercept term, is the regression coefficient of each variable after training, , , , They represent the strain data, stress data, displacement data and corrosion rate data of each key node of the steel structure collected regularly. , , They are temperature data, rainfall data and wind speed data collected in real time;

[0123] Temperature changes, humidity and other environmental conditions will directly affect the physical and mechanical properties of steel. Temperature changes will cause thermal expansion and contraction effects of steel structures, resulting in thermal stress and deformation of the structure. For example, extreme temperatures may cause the material to become brittle or lose toughness, thus affecting its bearing capacity and finishing stability. Rainfall will significantly accelerate the corrosion process of steel structures. Continuous high humidity or frequent rainfall will increase the moisture content on the surface of steel, thereby promoting the formation and expansion of rust and affecting the long-term durability of the structure. Wind speed will impose additional dynamic loads on steel structures, especially for structures exposed to wind such as high-rise buildings or bridges. Wind loads may become one of the main control loads. Therefore, environmental data will affect the safety and stability of the structure. In the safety monitoring of steel structures, considering environmental data will help to fully understand the stress and performance changes of steel structures in the actual use environment, improve the accuracy and comprehensiveness of safety monitoring, and thus better maintain the long-term safety and stability of the structure.

[0124] Step 6: Based on the type of each key node and the safety index of each key node, a comprehensive safety assessment index of the steel structure to be monitored is generated. The safety assessment index of the steel structure is analyzed and compared with the safety threshold to comprehensively judge the current safety status of the steel structure.

[0125] In this embodiment, the specific logic for judging the safety status of the current steel structure is:

[0126] According to the type of each key node and the safety index of each key node, the safety assessment index of the steel structure to be monitored is comprehensively generated. The specific formula for generating the safety assessment index is:

[0127]

[0128] in, is the safety assessment index of the steel structure to be monitored, is the total number of key nodes on the main beam endpoints, , is the total number of key nodes at the connection nodes and the middle positions of beams and columns, , is the weight coefficient of the key node on the main beam endpoint, is the weight coefficient of the key nodes at the connection nodes and the middle positions of beams and columns, and ;

[0129] If the safety assessment index of the steel structure is greater than the safety threshold, it is determined that the steel structure is currently in a safe state. If the safety assessment index of the steel structure is less than the safety threshold, it is determined that the current steel structure may be at risk.

[0130] Dependent Variable It is the safety assessment index of the steel structure to be monitored. This index combines the safety indexes of different key nodes in the steel structure and reflects the safety status of the overall steel structure. As the safety index of key nodes at different locations increases, The higher the value is, the greater it is than the safety threshold, indicating that the safety of the steel structure is better. The lower the value is, the lower it is below the safety threshold, indicating that there may be safety hazards in the steel structure.

[0131] The independent variables include and , representing the safety index of the key nodes and connection nodes at the end points of the main beams and the key nodes in the middle of the beams and columns. These data are comprehensively evaluated by the stress data, strain data, displacement data and corrosion rate data at the corresponding key nodes. They directly reflect the stress state and safety state of the performance changes of the structure in actual use. The safety of the structure is determined by the state of these key nodes. For example, high stress or large displacement at the end points of the main beams may indicate that the structure is overloaded or damaged, while problems at the connection nodes and the middle of the beams and columns may affect the overall stability and bearing capacity. And through the weight coefficient and It reflects the importance of different parts of the structure. The main beam endpoints are usually the most important parts of the load-bearing structure. Although the connection nodes are also key parts, they are usually designed to disperse and transfer loads, and their stress state is relatively uniform. The middle parts of beams and columns are far away from the load concentration area, and their stress levels are relatively low, so the data weights of these locations are relatively small.

[0132] See also Figure 2 The present invention further provides a safety monitoring device for a steel structure, the safety monitoring device is used to implement the above safety monitoring method, comprising:

[0133] The structural response data acquisition module marks the main beam endpoints, connection nodes, and the middle positions of beams and columns of the steel structure as key nodes, and obtains the structural response data of each key node, wherein the structural response data includes the strain data, stress data, and displacement data of the steel structure;

[0134] The corrosion rate determination module performs linear polarization resistance method tests on key nodes of steel structures and obtains corrosion rate data for each key node based on the test results;

[0135] Data preprocessing module, which preprocesses and reversely processes the structural response data and corrosion rate data of each key node of the steel structure to generate the safety index of each key node;

[0136] The safety monitoring model building module collects the environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, and builds a safety monitoring model for the steel structure based on a multivariate linear regression model. The structural response data, corrosion rate data and environmental data of each key node of the steel structure are used as training sets, and the safety index of the corresponding key node is used as a label to train the safety monitoring model.

[0137] The safety assessment index acquisition module regularly collects environmental data, structural response data and corrosion rate data of each key node of the steel structure, inputs them into the trained safety monitoring model, and outputs the safety index of each key node of the steel structure;

[0138] The comprehensive safety status analysis module generates a comprehensive safety assessment index for the steel structure to be monitored based on the type of each key node and the safety index of each key node. It analyzes the safety assessment index of the steel structure and compares it with the safety threshold to comprehensively judge the current safety status of the steel structure.

[0139] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0140] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A safety monitoring method for a steel structure, characterized in that: The specific steps include: Step 1: Mark the main beam endpoints, connection nodes, and middle positions of beams and columns of the steel structure as key nodes, and obtain the structural response data of each key node, wherein the structural response data includes strain data, stress data, and displacement data of the steel structure; Step 2: Perform linear polarization resistance test on the key nodes of the steel structure, and obtain the corrosion rate data of each key node according to the test results; Step 3: Preprocess and reversely process the structural response data and corrosion rate data of each key node of the steel structure to generate a safety index for each key node; Step 4: Collect environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, build a safety monitoring model for the steel structure based on a multivariate linear regression model, and use the structural response data, corrosion rate data and environmental data of each key node of the steel structure as a training set, and the safety index of the corresponding key node as a label to train the safety monitoring model; Step 5: Regularly collect environmental data, structural response data and corrosion rate data of each key node of the steel structure, input them into the trained safety monitoring model, and output the safety index of each key node of the steel structure; Step 6: Based on the type of each key node and the safety index of each key node, a safety assessment index of the steel structure to be monitored is comprehensively generated, the safety assessment index of the steel structure is analyzed, and compared with the safety threshold to comprehensively judge the safety status of the current steel structure; The strain is detected by measuring the change of wavelength in the optical fiber through the fiber Bragg grating sensor. When light of a specific wavelength propagates in the optical fiber, it will be reflected when it encounters the Bragg grating. The reflected wavelength is called the Bragg wavelength. When the optical fiber is subjected to stress changes, the Bragg wavelength will shift. By measuring this shift, the strain data and stress data of the steel structure can be determined. The specific formula for obtaining the strain data of the steel structure is: Among them, ε i is the strain of the i-th key node of the steel structure, in M, is the change in the Bragg wavelength of the i-th key node of the steel structure, in nm, is the initial Bragg wavelength of the i-th key node of the steel structure, K ε is the strain sensitivity coefficient; The specific formula for obtaining stress data of steel structures is: s i =E·e i Among them, σ i is the stress of the i-th key node of the steel structure, in N, and E is the elastic modulus of the steel, in GPa; The specific formula for obtaining displacement data is: x i =e i ·L i Among them, x i is the displacement of the steel structure at the i-th key node of the steel structure, L i is the original length of the steel structure at the location of the i-th key node, in M; The linear polarization resistance method applies a small potential offset to the metal electrode and measures the corresponding current response. By analyzing the relationship between potential and current, the polarization resistance can be determined and the corrosion rate can be calculated. The potential shift and the corresponding current response are plotted into a polarization curve. The specific formula for calculating the polarization resistance through the slope of the polarization curve is: in, is the polarization resistance of the i-th key node of the steel structure, △E i is the potential offset applied to the i-th key node of the steel structure, △I i is the current change corresponding to the i-th key node; The specific formula for calculating the corrosion current density is: in, is the corrosion current density of the i-th key node of the steel structure, in μA / cm 2 , B is the Stern-Geary constant, in V, is the polarization resistance of the i-th key node of the steel structure, in Ω·cm 2 ; The corrosion current density is converted into the corrosion rate, and the specific formula for obtaining the corrosion rate is: Among them, CR i is the corrosion rate of the i-th key node of the steel structure, in mm / year, and K is the conversion factor, in μA / cm 2 , EW is the equivalent weight of the metal, ρ is the density of the metal, the unit is g / cm 2 ; The obtained strain data, stress data, displacement data and corrosion rate data of the steel structure are normalized to the maximum value, scaled to the range of [0,1], and then reversely processed to calculate the single safety index of each data. The formula for obtaining each single safety index is: Among them, the single safety index They represent the strain data, stress data, displacement data and corrosion rate data of the i-th key node after preprocessing, respectively, and the value range is (0,1). The larger the value, the higher the safety. The specific formula for obtaining the safety index of key nodes is: Among them, y i is the safety index of the i-th key node, w e 、w s 、w d 、w v are the weights of strain data, stress data, displacement data and corrosion rate data, respectively, and w e +w s +w d +w v =1; When obtaining the structural response data and corrosion rate data of the steel structure, the temperature, rainfall and wind speed at the location of the steel structure are collected synchronously to generate a sample training set. The characteristic matrix of the steel structure safety monitoring model is constructed through the sample training set. Each row of the characteristic matrix is ​​the structural response data, corrosion rate and environmental data of each key node at the same time. Each column of the characteristic matrix is ​​an eigenvalue. The calibrated characteristic matrix is ​​X, and the corresponding target vector Y i is the safety index of the i-th key node at the same time, and the least squares method is used to estimate the regression coefficient b.

2. The safety monitoring method for steel structure according to claim 1, characterized in that: The specific logic for obtaining the safety index of each key node of the steel structure is: Environmental data, structural response data and corrosion rate data of each key node of the steel structure are collected regularly and input into the trained safety monitoring model. The specific formula for generating the safety index of each key node is as follows: in, is the safety index of the i-th key node output by the safety monitoring model, β0 is the constant intercept term, β1, β2, β3, β4, β5, β6, β7 are the regression coefficients of the trained variables, They represent the strain data, stress data, displacement data and corrosion rate data of each key node of the steel structure collected regularly, T p , R f , W s They are temperature data, rainfall data and wind speed data collected in real time.

3. The safety monitoring method for steel structure according to claim 2, characterized in that: The specific logic for judging the current safety status of the steel structure is: According to the type of each key node and the safety index of each key node, the safety assessment index of the steel structure to be monitored is comprehensively generated. The specific formula for generating the safety assessment index is: Wherein, Y is the safety assessment index of the steel structure to be monitored, n is the total number of key nodes at the end points of the main beam, a∈n, m is the total number of key nodes at the connection nodes and the middle positions of the beams and columns, b∈m, α is the weight coefficient of the key nodes at the end points of the main beam, β is the weight coefficient of the key nodes at the connection nodes and the middle positions of the beams and columns, α+β=1 and α>β>0; If the safety assessment index of the steel structure is greater than the safety threshold, it is determined that the steel structure is currently in a safe state. If the safety assessment index of the steel structure is less than the safety threshold, it is determined that the current steel structure may be at risk.

4. Safety monitoring device for steel structure, characterized by: The safety monitoring device is used to implement the safety monitoring method according to any one of claims 1 to 3, comprising: The structural response data acquisition module marks the main beam endpoints, connection nodes, and the middle positions of beams and columns of the steel structure as key nodes, and obtains the structural response data of each key node, wherein the structural response data includes the strain data, stress data, and displacement data of the steel structure; The corrosion rate determination module performs linear polarization resistance method tests on key nodes of steel structures and obtains corrosion rate data for each key node based on the test results; Data preprocessing module, which preprocesses and reversely processes the structural response data and corrosion rate data of each key node of the steel structure to generate the safety index of each key node; The safety monitoring model building module collects the environmental data of the location of the steel structure in real time, including temperature, rainfall and wind speed, and builds a safety monitoring model for the steel structure based on a multivariate linear regression model. The structural response data, corrosion rate data and environmental data of each key node of the steel structure are used as training sets, and the safety index of the corresponding key node is used as a label to train the safety monitoring model. The safety assessment index acquisition module regularly collects environmental data, structural response data and corrosion rate data of each key node of the steel structure, inputs them into the trained safety monitoring model, and outputs the safety index of each key node of the steel structure; The comprehensive safety status analysis module generates a comprehensive safety assessment index for the steel structure to be monitored based on the type of each key node and the safety index of each key node. It analyzes the safety assessment index of the steel structure and compares it with the safety threshold to comprehensively judge the current safety status of the steel structure.