Steel structure safety damage prediction method and system

Abstract

The invention relates to the technical field of steel structure damage detection, in particular to a steel structure safety damage prediction method and system.The method comprises the steps that a historical data set of a steel structure is obtained and preprocessed, and the historical data set comprises historical environment data, historical load data, historical damage data and historical maintenance data; constructing a tendency score matching model, and extracting causal relationship factors of steel structure maintenance on steel structure damage under the same environment and load conditions; constructing a steel structure equation relation model, and extracting a causal effect estimation result of the exogenous variables of the steel structure on the endogenous variables according to causal relation factors; predicting the damage development trend of the steel structure under the current condition based on the causal effect estimation result; and acquiring a real-time data set of the steel structure, extracting power spectrum densities of a damaged area and an undamaged area of the steel structure, and optimizing the causal effect estimation model. The objective of the invention is to improve the accuracy of damage prediction of large-scale steel structures such as bridges and added elevator hoistways.

Description

Technical Field

[0001] The present invention relates to the technical field of steel structure damage detection, and in particular to a method and system for predicting safe damage of steel structures. Background Art

[0002] In the field of modern engineering, large steel structures are widely used in various engineering projects as the core load-bearing system for key infrastructure such as elevator shafts, lifting machinery, buildings, bridges, and large venues. These steel structures are exposed to complex and changeable natural environments and dynamic and time-varying loads for a long time. As the service life continues to increase, the material properties gradually deteriorate, and the structure will inevitably suffer various forms of damage, such as crack initiation and expansion, material corrosion, fatigue damage, etc. Accurately predicting the damage state of steel structures and formulating scientific and reasonable maintenance strategies in advance are of vital importance to ensuring the structural safety of steel structures, extending their service life, and ensuring the normal operation of infrastructure. At present, a variety of technical means have been developed for steel structure damage prediction, such as methods based on vibration modal analysis, which identify potential damage by monitoring changes in the vibration characteristics of the structure; methods based on strain monitoring, which use sensors to collect strain data of key parts of the structure in real time, and then evaluate the mechanical properties and damage status of the structure.

[0003] However, the existing technology still exposes many limitations in practical applications, making it difficult for the prediction accuracy of large steel structure damage to meet the actual needs of engineering. On the one hand, most existing methods have obvious deficiencies in data utilization, focusing only on a single or a few data types, such as relying solely on load monitoring data, or relying solely on vibration response analysis, failing to comprehensively consider the complex impact of historical data on the evolution of steel structure damage, and it is difficult to accurately characterize the true service status of steel structures. On the other hand, the existing technology is lacking in causal relationship mining, failing to deeply analyze the intrinsic relationship between various influencing factors, and it is difficult to accurately evaluate the true impact of exogenous variables on the endogenous variable of steel structure damage, resulting in the inability to fully consider the interaction of various factors when constructing a prediction model, and thus causing large deviations in the damage trend prediction process. Especially for complex engineering structures such as large steel structures, due to their complex structural forms and harsh service environments, existing technologies are difficult to accurately predict the development trend of damage and cannot meet the stringent requirements of actual engineering for steel structure safety assurance. Summary of the invention

[0004] In order to improve the accuracy of damage prediction for large steel structures, the present invention provides a method and system for predicting safety damage of steel structures. The technical solutions adopted are as follows: The technical solution of the first aspect of the present invention provides a method for predicting safety damage of a steel structure, the method comprising: Obtaining and preprocessing the historical data set of the steel structure, the historical data set includes historical environmental data, historical load data, historical damage data and historical maintenance data; A propensity score matching model was constructed to extract the causal factors of steel structure maintenance on steel structure damage under the same environmental and load conditions; Construct a steel structure equation relationship model, and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors; Predict the damage development trend of steel structures under current conditions based on the causal effect estimation results; Acquire real-time data sets of steel structures, extract the power spectrum density of damaged and undamaged areas of steel structures, and optimize the causal effect estimation model.

[0005] Furthermore, a propensity score matching model was constructed to extract the causal factors of steel structure maintenance on steel structure damage under the same environmental and load conditions, including: Based on the preprocessed historical data set, the propensity score for maintaining the steel structure under different conditions is calculated; According to the propensity score, the kernel function matching method is used to extract the unmaintained samples corresponding to the maintained samples under the same environmental and load conditions; Bayesian network is used to extract the causal factors of steel structure maintenance on steel structure damage.

[0006] Furthermore, the expression for calculating the propensity score for maintaining steel structures under different conditions is:

[0007] In the formula, Indicates a given condition The propensity score for maintaining the steel structure is: represents a mapping function; represents the total number of steel structure characteristics considered for calculating the propensity score; Indicates The preset weights of the features; Indicates a given condition Next characteristic functions; express Discount factor for the moment; express Environmental load status at all times Maintenance decision making The reward value of represents the adjustment coefficient that changes over time; Indicates the number of time steps.

[0008] Furthermore, a steel structure equation relationship model is constructed to extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors, including: According to the causal factors, the exogenous and endogenous variables of the steel structure equation relationship model are determined; The maximum likelihood estimation method is used to estimate the causal effect strength between exogenous variables and endogenous variables, and a steel structure equation relationship model between exogenous variables and endogenous variables is established; Based on the strength of causal effect, the causal effect estimation results of steel structure exogenous variables on endogenous variables are extracted.

[0009] Furthermore, the maximum likelihood estimation method is used to estimate the causal effect strength between exogenous variables and endogenous variables, and a steel structure equation relationship model between exogenous variables and endogenous variables is established, including: Establish a linear relationship between the endogenous variable vector and the exogenous variable vector; Calculate the likelihood function and log-likelihood function based on the linear relationship between the endogenous variable vector and the exogenous variable vector; Solving the log-likelihood function yields estimates of the intercept term, the coefficient vector of the exogenous variables, and the variance of the error term.

[0010] Furthermore, based on the causal effect estimation results, the damage development trend of the steel structure under the current conditions is predicted, including: Obtain the current environmental data, load data and maintenance data of the steel structure, and input them into the steel structure equation relationship model; According to the estimated values ​​of the causal effects of each variable in the steel structure equation relationship model, the changes of the damage degree and damage development speed of the steel structure over time under the current conditions are predicted.

[0011] Furthermore, the real-time data set of the steel structure is obtained, the power spectrum density of the damaged and undamaged areas of the steel structure is extracted, and the causal effect estimation model is optimized, including: Obtain status information of damaged and undamaged areas of steel structures; Calculate the power spectral density of the signals in the damaged area and the undamaged area; Based on neural network, the causal effect estimation model is optimized according to the power spectrum density; The final damage development trend is extracted using the optimized causal effect estimation model.

[0012] The technical solution of the second aspect of the present invention provides a steel structure safety damage prediction system, which adopts the steel structure safety damage prediction method described in the technical solution of the first aspect of the present invention, and the system comprises: A data acquisition module is configured to acquire a historical data set of the steel structure and pre-process the historical data set, the historical data set including historical environmental data, historical load data, historical damage data, and historical maintenance data; A causal relationship analysis module, configured to build a propensity score matching model to extract the causal relationship factors of steel structure maintenance on steel structure damage under the same environmental and loading conditions; A causal effect estimation module is configured to construct a steel structure equation relationship model and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors; A damage trend prediction module, configured to predict the damage development trend of the steel structure under the current conditions based on the causal effect estimation results; The optimization module is configured to obtain a real-time data set of the steel structure, extract the power spectral density of the damaged area and the undamaged area of ​​the steel structure, and optimize the causal effect estimation model.

[0013] The technical solution of the third aspect of the present invention provides an electronic device, comprising: a processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the steps of the steel structure safety damage prediction method described in the technical solution of the first aspect of the present invention.

[0014] The technical solution of the fourth aspect of the present invention provides a computer-readable storage medium, on which is stored a program for implementing the method for predicting safety damage to a steel structure. The program for implementing the method for predicting safety damage to a steel structure is executed by a processor to implement the steps of the method for predicting safety damage to a steel structure described in the technical solution of the first aspect of the present invention.

[0015] The present invention has the following beneficial effects: The steel structure safety damage prediction method provided by the present invention, by constructing a propensity score matching model, accurately extracts the causal relationship factors of steel structure maintenance on damage under the same environment and load conditions, and realizes the extraction of the intrinsic connection between steel structure maintenance and damage; by constructing a structural equation relationship model, the causal effect estimation results of exogenous variables on endogenous variables are obtained based on the causal relationship factors, thereby providing a more scientific quantitative basis for steel structure damage prediction. Finally, the damage development trend under current conditions is predicted, and the causal effect estimation model is optimized by extracting the power spectrum density of damaged and undamaged areas, so that the model can be continuously adjusted according to the real-time status of the steel structure, and the prediction deviation is continuously corrected, so as to always maintain a high prediction accuracy, effectively improve the damage prediction accuracy of large steel structures, and ensure the safe and stable operation of steel structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A method flow chart of a method for predicting safety damage of a steel structure provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a steel structure safety damage prediction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a steel structure safety damage prediction method and system proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of a steel structure safety damage prediction method and system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a method flow chart of a method for predicting safety damage of a steel structure provided by an embodiment of the present invention, the method comprising: Step S100: Obtain a historical data set of steel structure and pre-process the historical data set, which includes historical environmental data, historical load data, historical damage data and historical maintenance data; specifically, this embodiment takes a large steel structure bridge built in a certain city for 10 years. In the past, due to large traffic flow and humid climate, it has suffered different degrees of damage and has been maintained; this embodiment collects historical data sets of environment, load, maintenance and damage for 12 consecutive months. Specifically, the number, type and speed of passing vehicles can be counted through traffic flow monitoring equipment to obtain historical load data; non-destructive testing technology, such as ultrasonic flaw detectors, are used to regularly detect key nodes and components of bridges, record crack length, width and location, and measure the degree of steel corrosion through corrosion detection equipment to collect historical damage data. At the same time, historical maintenance data such as maintenance time, maintenance method, and materials used for maintenance are extracted from the bridge maintenance archive. In this embodiment, the historical data set is at least cleaned and preprocessed to remove duplicate, erroneous and missing values, and the preprocessed data is sorted according to time sequence and data type to construct a historical data matrix of the steel structure. The rows of the historical data matrix represent different time points, and the columns represent various types of environment, load, damage and maintenance data.

[0022] This embodiment uses comprehensive and systematic data collection and preprocessing to truly reflect the damage evolution process of steel structures under complex environments and loads, as well as the effects of maintenance interventions.

[0023] Step S200: constructing a propensity score matching model to extract causal factors of steel structure maintenance on steel structure damage under the same environment and load conditions; Step S200 specifically includes: Step S210: Based on the preprocessed historical data set, calculate the propensity score for maintaining the steel structure under different conditions; specifically, after completing the preprocessing of the historical data set in step S100 to obtain a high-quality historical data matrix, obtain the environmental load state, maintenance decision and damage state change in the target period; Step S211: This embodiment considers the maintenance cost, damage type and environmental factors to construct a reward function, which can be expressed as:

[0024] In the formula, Indicates environmental load status Maintenance decision making After that, according to the damage status The reward value obtained; It represents the environmental impact coefficient dynamically determined by fuzzy logic based on environmental data; and They represent the weights of crack and corrosion damage, respectively, reflecting the importance of different damage types to structural safety; Represents the cost adjustment factor, which is used to balance the maintenance cost and damage improvement effect; represents the welding repair cost, represents the cost of coating protection; Indicates the change in crack length, that is, the difference between the crack length of this test and the last test; Indicates the change in corrosion area, that is, the difference between the corrosion area of ​​this test and the last test; Step S212: Based on reinforcement learning, the action value function is updated, which can be expressed as:

[0025] In the formula, Represents the learning rate, which ranges from 0 to 1 and is used to control the degree to which new experience updates old estimates; Represents the discount factor, which ranges from 0 to 1 and is used to balance the importance of short-term rewards and long-term rewards; express Always maintain the maximum action value in all possible decisions; Step S213: Based on the action value function, the expression for calculating the propensity score for maintaining the steel structure under different conditions is:

[0026] In the formula, Indicates a given condition The propensity score for maintaining the steel structure under the following conditions shall include at least the environmental load status and damage status; Represents a mapping function, which is used to map the score to the interval from 0 to 1; represents the total number of steel structure characteristics considered for calculating the propensity score; Indicates The preset weights of the features; Indicates a given condition Next characteristic functions; express The discount factor at each moment is used to reflect the importance of reward values ​​at different moments; express Environmental load status at all times Maintenance decision making The reward value of represents the adjustment coefficient that changes over time; represents the number of time steps; The expression of the adjustment coefficient is:

[0027] In the formula, It represents the expected reward value, which can be set based on historical experience or project goals; Step S220: According to the propensity score, the kernel function matching method is used to extract the unmaintained samples corresponding to the maintained samples under the same environment and load conditions; specifically, for each maintained sample, its propensity score is In this embodiment, it is necessary to find matching samples in the unmaintained samples. To maximize the kernel function value, the kernel function can be expressed as:

[0028] In the formula, represents the kernel function, which is used to measure the similarity of the propensity scores of two samples; is the bandwidth parameter, which can be determined by cross-validation. In this way, a corresponding unmaintained sample under the same environment and load conditions can be found for each maintained sample, providing a suitable control sample for subsequent causal relationship analysis. Step S230: Using a Bayesian network to extract the causal relationship factors between steel structure maintenance and steel structure damage; specifically, this embodiment constructs a Bayesian network, in which the nodes include environmental factors, load factors, maintenance factors and damage factors; using the pre-processed historical data and the matched sample data, the maximum likelihood estimation and Bayesian estimation method are combined to estimate the network parameters; for nodes X and Y, their conditional probability distribution Updated through data statistics and Bayesian formula:

[0029] In the formula, It represents the conditional probability of Y occurring under the condition that X occurs; It represents the conditional probability of X occurring under the condition that Y occurs; represents the prior probability of Y occurring; represents the prior probability of X occurring; Taking a large steel structure bridge as an example, the Bayesian network constructed in this embodiment includes the following nodes: Environmental factors (X1): including temperature, humidity, and wind speed; Load factors (X2): such as traffic flow, vehicle weight; Maintenance factors (X3): maintenance method (welding repair, coating protection), maintenance frequency; Damage factors (Y): crack length, corrosion area; This embodiment can deeply analyze the causal relationship between various factors by continuously updating the conditional probability distribution between nodes. For example, by calculating , that is, the probability of damage occurring under the condition of taking certain maintenance measures is If there is a significant difference, it means that the maintenance factor has an important causal effect on the injury factor. Significantly less than , it indicates that the maintenance measure has a positive effect on reducing damage; otherwise, it indicates that the maintenance measure is not effective. In this way, we can accurately extract the causal relationship factors of steel structure maintenance on steel structure damage, and provide a more scientific basis for subsequent damage prediction and maintenance decision-making; In summary, this embodiment constructs a propensity score matching model, comprehensively considers maintenance costs, damage types and environmental factors, and accurately calculates the propensity score for maintaining steel structures under different conditions. The kernel function matching method is used to extract control samples under the same environmental and load conditions, providing a reliable data basis for subsequent causal relationship analysis. The Bayesian network is used to mine the causal relationship factors between steel structure maintenance and damage, which can deeply understand the influence mechanism of various factors on steel structure damage. It effectively improves the analysis accuracy of the causal relationship of steel structure damage, and lays the foundation for the subsequent construction of an accurate structural equation relationship model and the prediction of damage development trends.

[0030] Step S300: constructing a steel structure equation relationship model, and extracting the causal effect estimation results of the steel structure exogenous variables on the endogenous variables according to the causal relationship factors; Step S300 specifically includes: Step S310: Determine the exogenous variables and endogenous variables of the steel structure equation relationship model according to the causal relationship factors; specifically, determine the exogenous variables and endogenous variables according to the causal relationship obtained by Bayesian network analysis, for example: Exogenous variables include: Environmental factors: temperature, humidity, and concentration of atmospheric corrosive media; for example, steel structures are more susceptible to corrosion in hot and humid environments; Load factors: daily traffic volume, frequency and weight of heavy vehicles; for example, frequent heavy vehicle traffic will increase stress on steel structures and accelerate the development of damage; Maintenance factors: maintenance methods (welding repair, coating protection, etc.), maintenance frequency; for example, regular maintenance can effectively delay the damage of steel structures; Endogenous variables: Damage degree: measured by crack length and corrosion area; for example, the longer the crack length, the more serious the damage to the steel structure; Damage development speed: calculated by the ratio of the damage index to the time interval between two adjacent tests; Step S320: using the maximum likelihood estimation method, the causal effect strength between the exogenous variables and the endogenous variables is estimated, and a steel structure equation relationship model between the exogenous variables and the endogenous variables is established; specifically, firstly, a linear relationship between the endogenous variables and the exogenous variables is established:

[0031] In the formula, represents the endogenous variable vector, which is a two-dimensional vector. Indicates the degree of damage. Indicates the speed of injury development; represents the exogenous variable vector; represents the intercept term, which is a constant; is the coefficient vector of the exogenous variables, represents the number of exogenous variables, is the error term, which has a mean of 0 and a variance of Normal distribution of The likelihood function and log-likelihood function are calculated based on the linear relationship between the endogenous variable vector and the exogenous variable vector. The likelihood function can be expressed as:

[0032] In the formula, represents the number of samples; Indicates The endogenous variable value of the sample; Indicates The exogenous variable value of each sample; The log-likelihood function can be expressed as:

[0033] Solve the log-likelihood function to obtain the estimated values ​​of the intercept term, the coefficient vector of the exogenous variable, and the variance of the error term; specifically, by taking the partial derivative of the log-likelihood function and setting it to 0, we can obtain , and Three parameters, which can be solved by Newton-Raphson method; Step S330: Based on the causal effect strength, extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables; specifically, solve the obtained is the estimated value of the causal effect strength of the exogenous variable on the endogenous variable. is the coefficient corresponding to the exogenous variable temperature. When , it means that the temperature increase will lead to an increase in the degree of damage or the speed of damage development; when When the temperature rises, it means that the damage degree or damage development speed will decrease; The larger the value is, the greater the impact of temperature on damage. Based on these estimated values, we can comprehensively analyze the direction and extent of the impact of exogenous variables on endogenous variables. In summary, this embodiment comprehensively considers the influence of exogenous variables such as environmental factors, load factors and maintenance factors on endogenous variables such as damage degree and damage development speed by constructing a steel structure equation relationship model. The maximum likelihood estimation method is used to accurately estimate the causal effect strength between exogenous variables and endogenous variables, which can clearly reveal the direction and degree of influence of each exogenous variable on steel structure damage. This has an in-depth understanding of the formation mechanism of large-scale steel structure damage, and can more accurately consider the comprehensive influence of various factors when predicting damage, avoiding the prediction bias caused by insufficient causal relationship mining in the prior art, and greatly improving the accuracy of the prediction. The constructed structural equation relationship model can predict damage according to the dynamic changes of exogenous variables and adapt to different service stages and environments. For example, when the ambient temperature rises or the traffic flow increases, the model can accurately predict the corresponding changes in the damage degree and damage development speed of the steel structure according to the estimated causal effect strength. Compared with the traditional static prediction method, this dynamic prediction model can better adapt to the damage changes of large steel structures in different service stages and under different environmental conditions, thereby improving the accuracy and reliability of the prediction. The causal effect estimation results can also scientifically guide maintenance decisions, take targeted measures to delay the development of damage, and coordinate in multiple aspects to ensure prediction accuracy and structural safety.

[0034] Step S400: predicting the damage development trend of the steel structure under the current conditions based on the causal effect estimation result; Step S400 specifically includes: Step S410: obtaining the current environmental data, load data and maintenance data of the steel structure, and inputting them into the steel structure equation relationship model; specifically, organizing the obtained current environmental data, load data and maintenance data into vector form, and inputting them into the steel structure equation relationship model established in step S300 as exogenous variable data; Step S420: predicting the change of the damage degree and damage development speed of the steel structure over time under the current conditions according to the estimated value of the causal effect of each variable in the steel structure equation relationship model; Specifically, the steel structure equation relationship model can be expressed as:

[0035] in, yes The damage degree or damage development speed prediction value at the moment; the damage degree can be measured by indicators such as crack length and corrosion area; the damage development speed can be measured by the crack extension length and corrosion area increase per unit time; yes Exogenous variables at the time; represents the intercept term estimate obtained by maximum likelihood estimation; Represents the estimated value of the coefficient vector of the exogenous variable; for example: obtained by step S300 ; , corresponding to the three exogenous variables of temperature, traffic flow and maintenance frequency; , corresponding to a temperature of 35°C, a traffic volume of 100 vehicles per hour, and the last maintenance was one month ago, then we can calculate , this value indicates the current predicted damage level; Secondly, this embodiment takes into account the dynamics of damage development and introduces the autoregressive integrated moving average model (ARIMA) to correct the prediction results. The expression is:

[0036] in, represents the difference operator, is the difference order, used to make the time series data stationary; Represents the autoregressive order, which indicates the number of past values ​​used in the model; represents the moving average order, which indicates the number of past error terms used in the model; and denote the estimated parameters of the first model and the second model, respectively. represents the error term, which follows a normal distribution with a mean of 0; Represents a constant term; This embodiment is to determine the parameters of the ARIMA model , , , the grid search method combined with the AIC (Akaike Information Criterion) criterion can be used to select the model. Based on the historical damage data, try different parameter combinations, select the combination with the smallest AIC value as the optimal parameter, and then obtain the corrected prediction value; This embodiment significantly improves the accuracy and reliability of damage prediction for large steel structures by combining the steel structure equation relationship model and time series analysis. First, the current environment, load and maintenance data are input into the equation relationship model for preliminary prediction, which fully considers the real-time impact of exogenous variables on damage and makes the prediction results more in line with the actual situation. Then, the ARIMA model is introduced to correct the prediction results, which effectively captures the dynamics and time series characteristics of damage development and makes up for the shortcomings of the equation relationship model in dealing with dynamic changes. This comprehensive prediction method can more accurately predict the changes in the degree of damage and the speed of damage development of steel structures over time, provide a more scientific and timely decision-making basis for the maintenance and management of steel structures, and help take measures in advance to prevent further deterioration of damage, ensure the safe and stable operation of large steel structures, and reduce maintenance costs and safety risks.

[0037] Step S500: Acquire a real-time data set of the steel structure, extract the power spectrum density of the damaged area and the undamaged area of ​​the steel structure, and optimize the causal effect estimation model; Step S500 specifically includes: Step S510: Obtain the status information of the damaged area and the undamaged area of ​​the steel structure; specifically, use ultrasonic testing equipment to detect the key connection parts, welds and other areas of the steel structure that may be damaged. When ultrasonic waves encounter damage (such as cracks) during propagation, they will generate reflected waves. By analyzing the characteristics of the reflected waves, the location and approximate size of the damage can be determined. At the same time, the surface of the steel structure is inspected using magnetic particle testing technology. When there are defects on the surface or near the surface of the steel structure, the application of magnetic particles will form obvious magnetic traces at the defects, thereby discovering the damage; then, strain sensors, displacement sensors, etc. are reasonably arranged in the damaged area and undamaged area of ​​the steel structure. Strain sensors can monitor the stress and strain of the steel structure in real time, and displacement sensors are used to measure the displacement changes of the structure. These sensors will collect state information such as stress, strain, and displacement at a certain sampling frequency to form a real-time data set.

[0038] Step S520: Calculate the power spectrum density of the damaged area and the undamaged area signal; use wavelet packet transform to calculate the power spectrum density. , decompose the signal through wavelet packet to get the Tier Wavelet packet coefficients ,Wavelet packet decomposition can refine the analysis of signals at different frequencies and time scales, and can better capture the local characteristics of the signal; No. Tier Wavelet packet coefficients The expression of the power spectral density is:

[0039] in, Indicates the signal length, Represents frequency. By calculating the power spectrum density at different frequencies, the frequency characteristic distribution of the signals in the damaged area and the undamaged area can be obtained. Step S530: Based on the neural network, the causal effect estimation model is optimized according to the power spectrum density; specifically, an MLP neural network with an input layer, a hidden layer and an output layer is constructed. The number of neurons in the input layer is equal to the number of power spectrum density features of the damaged area and the undamaged area; for example, if the power spectrum density at 10 different frequencies is calculated, then the input layer has 20 neurons; the number of neurons in the output layer is equal to the number of parameters of the causal effect estimation model; the calculated power spectrum density features are normalized so that their value range is between [0,1] to improve the training effect of the neural network. Then, the MLP neural network is trained using a real-time data set. During the training process, the back-propagation algorithm is used to update the network weights, and the output of the neural network is made as close as possible to the actual adjustment of the parameters of the causal effect estimation model by continuously adjusting the weights.

[0040] Step S540: Use the optimized causal effect estimation model to extract the final damage development trend; specifically, in step S400, we built a preliminary prediction model, and now recalculate using the optimized parameters. For example, input the current temperature, traffic flow, maintenance frequency and other data into the optimized model, and predict the final steel structure damage development trend based on the output of the model, including the changes in the damage degree and damage development speed over time. We can draw a curve of the damage degree and damage development speed over time to intuitively display the damage development trend of the steel structure.

[0041] Step S500 obtains the real-time status information of the steel structure and calculates the power spectrum density of the damaged area and the undamaged area. The power spectrum density can reflect the energy distribution of the signal at different frequencies and contains rich information about the damage state of the steel structure. The neural network has a strong nonlinear mapping ability and can learn the complex relationship between the power spectrum density and the parameters of the causal effect estimation model. Compared with the traditional linear model, it can capture more features and laws hidden in the data, so as to more accurately adjust the parameters of the causal effect estimation model, improve the accuracy of damage prediction, and ultimately significantly improve the accuracy and reliability of steel structure damage prediction.

[0042] As another implementation method, this method is also applicable to the safety damage prediction of elevator steel structures. For example, the temperature, humidity and other environmental data of the machine room are recorded through the elevator operation management system, the load is obtained as load data, the maintenance record provides maintenance data, and the regular inspection record can be used as damage data; when constructing the propensity score matching model, the elevator maintenance cost, different damage types (such as guide rail deformation, car bracket cracks) and the influence of the machine room environmental factors on the maintenance effect and damage development are considered, and then the propensity score is calculated to be reasonable and feasible; the kernel function is used to match samples and the Bayesian network is used to extract causal factors, which is also applicable to analyzing the relationship between elevator maintenance and damage. Construct a steel structure equation relationship model, set the environment, load, maintenance, etc. as exogenous variables, and set the degree of damage and development speed of the elevator steel structure as endogenous variables. Use maximum likelihood estimation to establish a model and extract the causal effect estimation results. In the optimization model stage, the state information of the damaged and undamaged areas of the elevator steel structure is obtained through the detection equipment, the power spectrum density is calculated, and then the neural network is used to optimize the model, which can effectively improve the prediction accuracy and provide strong support for the safe operation and maintenance of the elevator.

[0043] In summary, the introduction of real-time data in this embodiment enables the model to reflect the latest status of the steel structure in a timely manner, and the calculation of the power spectrum density mines the frequency characteristics of the signal, providing richer information for model optimization. The application of neural networks can adaptively adjust the parameters of the causal effect estimation model to better adapt it to the actual damage of the steel structure. The optimized model finally obtained can more accurately predict the damage development trend of the steel structure, provide a more scientific and timely basis for the maintenance decision of the steel structure, help to ensure the safe operation of the steel structure, and reduce maintenance costs and safety risks.

[0044] See also Figure 2 , which shows a schematic diagram of the structure of a steel structure safety damage prediction system provided by the technical solution of the second aspect of the present invention, the system comprising: A data acquisition module is configured to acquire a historical data set of the steel structure and pre-process the historical data set, the historical data set including historical environmental data, historical load data, historical damage data, and historical maintenance data; A causal relationship analysis module, configured to build a propensity score matching model to extract the causal relationship factors of steel structure maintenance on steel structure damage under the same environmental and loading conditions; A causal effect estimation module is configured to construct a steel structure equation relationship model and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors; A damage trend prediction module, configured to predict the damage development trend of the steel structure under the current conditions based on the causal effect estimation results; The optimization module is configured to obtain a real-time data set of the steel structure, extract the power spectral density of the damaged area and the undamaged area of ​​the steel structure, and optimize the causal effect estimation model.

[0045] The technical solution of the third aspect of the present invention provides an electronic device, comprising: a processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the steps of the steel structure safety damage prediction method described in the technical solution of the first aspect of the present invention.

[0046] The technical solution of the fourth aspect of the present invention provides a computer-readable storage medium, on which is stored a program for implementing the method for predicting safety damage to a steel structure. The program for implementing the method for predicting safety damage to a steel structure is executed by a processor to implement the steps of the method for predicting safety damage to a steel structure described in the technical solution of the first aspect of the present invention.

[0047] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] The various embodiments in this specification are described in a progressive manner, and the same parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting safety damage of steel structures, characterized in that: The method comprises: Obtaining and preprocessing the historical data set of the steel structure, the historical data set includes historical environmental data, historical load data, historical damage data and historical maintenance data; A propensity score matching model was constructed to extract the causal factors of steel structure maintenance on steel structure damage under the same environmental and load conditions; Construct a steel structure equation relationship model, and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors; Predict the damage development trend of steel structures under current conditions based on the causal effect estimation results; Acquire real-time data sets of steel structures, extract the power spectrum density of damaged and undamaged areas of steel structures, and optimize the causal effect estimation model.

2. The method for predicting safety damage of steel structure according to claim 1, characterized in that: A propensity score matching model was constructed to extract the causal factors of steel structure maintenance on steel structure damage under the same environmental and load conditions, including: Based on the preprocessed historical data set, the propensity score for maintaining the steel structure under different conditions is calculated; According to the propensity score, the kernel function matching method is used to extract the unmaintained samples corresponding to the maintained samples under the same environmental and load conditions; Bayesian network is used to extract the causal factors of steel structure maintenance on steel structure damage.

3. The method for predicting safety damage of steel structure according to claim 2, characterized in that: The expression for calculating the propensity score for maintaining steel structures under different conditions is: In the formula, Indicates a given condition The propensity score for maintaining the steel structure is: represents a mapping function; represents the total number of steel structure characteristics considered for calculating the propensity score; Indicates The preset weights of the features; Indicates a given condition Next characteristic functions; express Discount factor for the moment; express Environmental load status at all times Maintenance decision The reward value of represents the adjustment coefficient that changes over time; Indicates the number of time steps.

4. The method for predicting safety damage of steel structure according to claim 1, characterized in that: Construct a steel structure equation relationship model, and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors, including: According to the causal factors, the exogenous and endogenous variables of the steel structure equation relationship model are determined; The maximum likelihood estimation method is used to estimate the causal effect strength between exogenous variables and endogenous variables, and a steel structure equation relationship model between exogenous variables and endogenous variables is established; Based on the strength of causal effect, the causal effect estimation results of steel structure exogenous variables on endogenous variables are extracted.

5. The method for predicting safety damage of steel structure according to claim 4, characterized in that: The maximum likelihood estimation method is used to estimate the causal effect strength between exogenous variables and endogenous variables, and a steel structure equation relationship model between exogenous variables and endogenous variables is established, including: Establish a linear relationship between the endogenous variable vector and the exogenous variable vector; Calculate the likelihood function and log-likelihood function based on the linear relationship between the endogenous variable vector and the exogenous variable vector; Solving the log-likelihood function yields estimates of the intercept term, the coefficient vector of the exogenous variables, and the variance of the error term.

6. The method for predicting safety damage of a steel structure according to any one of claims 1 to 5, characterized in that: Based on the causal effect estimation results, the damage development trend of the steel structure under the current conditions is predicted, including: Obtain the current environmental data, load data and maintenance data of the steel structure, and input them into the steel structure equation relationship model; According to the estimated values ​​of the causal effects of each variable in the steel structure equation relationship model, the changes of the damage degree and damage development speed of the steel structure over time under the current conditions are predicted.

7. The method for predicting safety damage of steel structure according to claim 6, characterized in that: Acquire real-time data sets of steel structures, extract power spectrum density of damaged and undamaged areas of steel structures, and optimize causal effect estimation models, including: Obtain status information of damaged and undamaged areas of steel structures; Calculate the power spectral density of the signals in the damaged area and the undamaged area; Based on neural network, the causal effect estimation model is optimized according to the power spectrum density; The final damage development trend is extracted using the optimized causal effect estimation model.

8. Steel structure safety damage prediction system, characterized by: The method for predicting safety damage of a steel structure according to any one of claims 1 to 7 is adopted, wherein the system comprises: A data acquisition module is configured to acquire a historical data set of the steel structure and pre-process the historical data set, the historical data set including historical environmental data, historical load data, historical damage data, and historical maintenance data; A causal relationship analysis module, configured to build a propensity score matching model to extract the causal relationship factors of steel structure maintenance on steel structure damage under the same environmental and loading conditions; A causal effect estimation module is configured to construct a steel structure equation relationship model and extract the causal effect estimation results of the steel structure exogenous variables on the endogenous variables based on the causal relationship factors; A damage trend prediction module, configured to predict the damage development trend of the steel structure under the current conditions based on the causal effect estimation results; The optimization module is configured to obtain a real-time data set of the steel structure, extract the power spectral density of the damaged area and the undamaged area of ​​the steel structure, and optimize the causal effect estimation model.

9. An electronic device, characterized in that: The electronic device includes: a processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the steps of the steel structure safety damage prediction method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for implementing the method for predicting safety damage to a steel structure, and the program for implementing the method for predicting safety damage to a steel structure is executed by a processor to implement the steps of the method for predicting safety damage to a steel structure as described in any one of claims 1 to 7.

Images