A bridge safety evaluation method and system based on data analysis

Abstract

The present invention discloses a bridge safety evaluation method and system based on data analysis, which relates to the technical field of bridge safety monitoring, including collecting short-term dynamic data and long-term static data of the bridge; extracting short-term state characteristics and long-term state characteristics of the bridge based on the short-term dynamic data and the long-term static data; predicting the short-term state score of the bridge based on the short-term state characteristics of the bridge, and predicting the long-term state score of the bridge based on the long-term state characteristics of the bridge; fusing the short-term state score and the long-term state score to conduct a comprehensive evaluation of the bridge safety; and dividing the bridge safety level and conducting dynamic early warning according to the evaluation results. The present invention dynamically fuses the short-term state score and the long-term state score through an adaptive weight adjustment rule, fully considers the influence of short-term emergencies and long-term aging effects, and significantly enhances the accuracy of bridge safety evaluation and dynamic early warning capability.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge safety monitoring, and in particular to a bridge safety evaluation method and system based on data analysis. Background Art

[0002] With the rapid development of global infrastructure construction, bridges, as important transportation hubs, are directly related to social and economic operations and public safety. Traditional bridge safety evaluation methods mainly rely on regular manual inspections and limited monitoring equipment. Although these methods have played an important role in early bridge maintenance, with the increase in the scale, complexity and service life of bridges, it is difficult to comprehensively and accurately evaluate the health of bridges by simply relying on manual inspections and basic monitoring data. In recent years, bridge monitoring technology based on sensor networks and big data analysis has been gradually applied to bridge safety management. By collecting dynamic data such as stress, vibration, and deformation of bridges, combined with long-term static data such as material aging and environmental impact, the operation status of bridges can be more comprehensively monitored and analyzed. However, the existing monitoring system still has problems such as low data processing efficiency, insufficient prediction accuracy, and lack of dynamic warning, which cannot meet the current needs of bridge safety management.

[0003] The main deficiencies of existing technologies in bridge safety assessment are reflected in the following two aspects. First, most of the existing bridge safety assessment methods rely on a single type of data (such as dynamic stress or static aging data), which makes it difficult to fully reflect the comprehensive state of the bridge, especially the interaction between short-term dynamic state and long-term static state is not fully considered. This leads to low accuracy and reliability of bridge safety assessment results. Secondly, in the process of bridge safety prediction, existing technologies often lack a dynamic early warning mechanism for the trend of bridge state changes, and are unable to capture sudden changes in bridge state in a timely manner, which in turn leads to the failure to timely warn and deal with bridge safety hazards. Therefore, how to improve the accuracy and early warning response capabilities of bridge safety assessment based on multi-source data fusion and dynamic trend prediction has become a problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a bridge safety evaluation method and system based on data analysis to solve the problem of being unable to comprehensively consider the interactive effects of short-term dynamic states and long-term static states.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a bridge safety evaluation method based on data analysis, which includes collecting short-term dynamic data and long-term static data of the bridge; extracting short-term state characteristics and long-term state characteristics of the bridge based on the short-term dynamic data and the long-term static data; predicting the short-term state score of the bridge based on the short-term state characteristics of the bridge, and predicting the long-term state score of the bridge based on the long-term state characteristics of the bridge; fusing the short-term state score and the long-term state score to conduct a comprehensive evaluation of the safety of the bridge; and dividing the bridge safety level and conducting dynamic early warning according to the evaluation results.

[0008] As a preferred solution of the bridge safety evaluation method based on data analysis described in the present invention, wherein: the short-term dynamic data includes stress, deformation, vibration, real-time traffic flow, temperature and humidity of the bridge;

[0009] The long-term static data includes material aging records, historical maintenance records, structural design parameters and historical meteorological data of the bridge.

[0010] As a preferred solution of the bridge safety evaluation method based on data analysis of the present invention, the short-term state characteristics and long-term state characteristics of the bridge are extracted based on short-term dynamic data and long-term static data, and the specific steps are as follows:

[0011] Through time domain analysis, the mean, peak, skewness and rate of change of bridge stress are extracted from the time series of short-term dynamic data;

[0012] The average vibration frequency and vibration intensity in the short-term dynamic data are extracted by fast Fourier transform;

[0013] Extract instantaneous frequency and vibration amplitude from short-term dynamic data using Hilbert-Huang transform analysis;

[0014] Through statistical analysis methods, the aging rate, maintenance frequency, stress accumulation and ambient temperature in long-term static data are extracted.

[0015] As a preferred solution of the bridge safety evaluation method based on data analysis of the present invention, the specific steps of predicting the short-term status score of the bridge based on the short-term status characteristics of the bridge are as follows:

[0016] By nonlinearly combining multiple dynamic features of the bridge and capturing the complex interactive relationship between the features, the short-term status score of the bridge is predicted. The expression is: ;

[0017] in, is the mean bridge stress, is the peak stress of the bridge, is the rate of change of bridge stress, is the instantaneous vibration frequency of the bridge, represents the average vibration frequency of the bridge during vibration, represents the vibration intensity of the bridge, Represents the short-term condition score of the bridge.

[0018] As a preferred solution of the bridge safety evaluation method based on data analysis of the present invention, the specific steps of predicting the long-term status score of the bridge based on the long-term status characteristics of the bridge are as follows:

[0019] Based on the long-term status characteristics of the bridge, the accelerated effect of bridge deterioration over time is captured by exponential decay, the impact of extreme temperature on the score is smoothed by a logarithmic function, the extreme impact of extreme values ​​on the long-term status score of the bridge is weakened by the fourth root, and the long-term status score of the bridge is predicted by combining the interactive relationship of multiple nonlinear combinations. The expression is: ;

[0020] in, is the long-term condition score of the bridge, is the ambient temperature, represents the rate at which the bridge structure ages over time, is the bridge maintenance frequency, It indicates the stress accumulation of the bridge during long-term use. Represents the comprehensive influencing factors of the environment in which the bridge is located.

[0021] As a preferred solution of the bridge safety evaluation method based on data analysis described in the present invention, the short-term status score and the long-term status score are integrated to conduct a comprehensive evaluation of the bridge safety. The specific steps are as follows:

[0022] By introducing nonlinear adjustment factors and defining adaptive weight adjustment rules, when the long-term status score of the bridge is Below the bridge's short-term condition score When The weight of the bridge's long-term status score is Higher short-term condition rating than bridges When The weight of

[0023] Based on the adaptive weight adjustment rule and nonlinear adjustment factor, the short-term score status and long-term status of the bridge are integrated to dynamically capture the interaction between the short-term status score and the long-term status score, and predict the comprehensive score of bridge safety. The expression is: ;

[0024] in, is the comprehensive score of bridge safety, t is the time is the nonlinear correction parameter of the short-term score, Indicates the short-term status score of the bridge The long-term condition of the bridge is rated The adjustment factor of the influence degree, Indicates the long-term condition score of the bridge The adjustment factor that decays linearly with time t, Indicates the long-term condition score of the bridge Adjustment factor for nonlinear decay over time t.

[0025] As a preferred solution of the bridge safety evaluation method based on data analysis of the present invention, the specific steps of dividing the bridge safety level and performing dynamic early warning according to the evaluation results are as follows:

[0026] Define high safety thresholds based on the remaining structural life of the bridge and safety requirements and low safety threshold ;

[0027] When S ≥ When , the current bridge safety is considered good and no warning is triggered;

[0028] when ≤S< When , the current bridge safety is considered to be general, triggering the primary warning;

[0029] When S< When , it is considered that the current bridge safety is extremely poor and triggers an advanced warning.

[0030] In a second aspect, the present invention provides a bridge safety evaluation system based on data analysis, including a data acquisition module, a feature extraction module, a state scoring module, a comprehensive evaluation module and a dynamic warning module; the data acquisition module is used to collect short-term dynamic data and long-term static data of the bridge; the feature extraction module is used to extract the short-term state characteristics and long-term state characteristics of the bridge based on the short-term dynamic data and the long-term static data; the state scoring module is used to predict the short-term state score of the bridge based on the short-term state characteristics of the bridge, and predict the long-term state score of the bridge based on the long-term state characteristics of the bridge; the comprehensive evaluation module is used to integrate the short-term state score and the long-term state score to conduct a comprehensive evaluation of the bridge safety; the dynamic warning module is used to classify the bridge safety level and conduct dynamic warning according to the evaluation results.

[0031] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the bridge safety assessment method based on data analysis as described in the first aspect of the present invention is implemented.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the bridge safety evaluation method based on data analysis as described in the first aspect of the present invention.

[0033] The beneficial effects of the present invention are as follows: by collecting short-term dynamic data and long-term static data of the bridge, the short-term and long-term state characteristics of the bridge are fully extracted, and multi-dimensional monitoring of the health status of the bridge is achieved. At the same time, based on the adaptive weight adjustment rule, the short-term state score and the long-term state score are dynamically integrated, and the impact of short-term emergencies and long-term aging effects are fully considered, which significantly enhances the accuracy of bridge safety assessment and dynamic early warning capabilities. Ultimately, the present invention improves the intelligent level of bridge safety management and the timeliness of risk early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0035] Figure 1 This is a flow chart of the bridge safety evaluation method based on data analysis in Example 1.

[0036] Figure 2 This is a system diagram of the bridge safety evaluation method based on data analysis in Example 1. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0040] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a bridge safety evaluation method based on data analysis, comprising the following steps:

[0041] S1: Collect short-term dynamic data and long-term static data of the bridge.

[0042] S1.1: Short-term dynamic data include stresses, deformations, and vibrations of the bridge.

[0043] Furthermore, short-term dynamic data are used to reflect the instantaneous state of the bridge in operation in real time, thereby capturing the changing characteristics of the bridge in a short period of time.

[0044] S1.2: Long-term static data include material aging records, historical maintenance records, structural design parameters, and historical meteorological data of the bridge.

[0045] Furthermore, long-term static data is used to evaluate the long-term performance degradation and maintenance history of the bridge, helping to analyze the risks that gradually accumulate during the long-term use of the bridge. By combining these data, a comprehensive and accurate assessment of the health status of the bridge can be achieved, providing a reliable basis for preventive maintenance and dynamic early warning.

[0046] S2: Extract the short-term state characteristics and long-term state characteristics of the bridge based on short-term dynamic data and long-term static data.

[0047] S2.1: Extract the mean, peak, skewness, and rate of change of bridge stress from the time series of short-term dynamic data through time domain analysis.

[0048] Furthermore, kurtosis is used to measure the sharpness of the data distribution. A higher kurtosis may mean that there is a sudden stress concentration in the bridge structure, expressed as: ;

[0049] in, is the number of samples in the short-term dynamic dataset, is the number of samples in the short-term dynamic dataset, is the mean of the short-term dynamic data set X, is the standard deviation of the data set X, is the kurtosis in the short-term dynamic data set.

[0050] Skewness is a measure of the symmetry of the data distribution. Large values ​​of skewness may indicate that the bridge is subjected to asymmetric stress in one direction and is calculated in the same way as kurtosis.

[0051] The rate of change indicates rapid changes in the bridge structure, especially in vibration and deformation data. Large rates of change may indicate that the bridge is subjected to sudden loads.

[0052] S2.2: Extract the average vibration frequency and vibration intensity from the short-term dynamic data through fast Fourier transform.

[0053] Furthermore, the vibration data of the bridge is collected over a period of time, for example, sampling once per second to obtain 1000 data points. Then, FFT is applied to convert these time domain data into frequency domain data to obtain different frequency components and their corresponding amplitudes. By analyzing the frequency domain results, the frequency with the largest amplitude is found, which is the average vibration frequency of the bridge. For example, 2Hz means that the bridge mainly vibrates at a frequency of 2 times per second. At the same time, the vibration intensity can be measured by the sum of the squares of the amplitudes, and a larger amplitude indicates a stronger vibration. For example, if the amplitude is larger at 2Hz, it means that the bridge vibrates strongly at this frequency.

[0054] S2.3: Extract the instantaneous frequency and vibration amplitude from the short-term dynamic data using Hilbert-Huang transform analysis.

[0055] Furthermore, first, empirical mode decomposition (EMD) is used to decompose the dynamic data of the bridge into several intrinsic mode components (IMFs), which represent different frequency components in the data. For each IMF, the Hilbert transform is applied to convert it into a complex form, so that the instantaneous frequency and instantaneous vibration amplitude at each moment can be calculated. The instantaneous frequency represents the change in the vibration frequency of the bridge at each moment, while the instantaneous amplitude represents the intensity of the vibration at that moment. For example, the instantaneous frequency can indicate that the vibration frequency of the bridge at a certain moment is 3Hz, and the magnitude of the instantaneous amplitude reflects the strength of the vibration of the bridge at that moment.

[0056] S2.4: Extract aging rate, maintenance frequency, and stress accumulation from long-term static data through statistical analysis methods.

[0057] Furthermore, the aging rate is determined by analyzing the degradation of material properties over time, such as crack growth or corrosion rate; the maintenance frequency measures the maintenance needs of the bridge by counting the number of historical maintenance events; and the stress accumulation calculates the total stress on the bridge through long-term monitoring of stress data. These indicators can help assess the long-term health of the bridge and provide a basis for predicting future maintenance needs and remaining life.

[0058] S3: Predict the short-term status score of the bridge based on the short-term status characteristics of the bridge, and predict the long-term status score of the bridge based on the long-term status characteristics of the bridge.

[0059] S3.1: By nonlinearly combining multiple short-term state features of the bridge, the complex interactive relationship between the features is captured and the short-term state score of the bridge is predicted. The expression is: ;

[0060] in, is the mean bridge stress, is the peak stress of the bridge, is the rate of change of bridge stress, is the instantaneous vibration frequency of the bridge, represents the average vibration frequency of the bridge during vibration, represents the vibration intensity of the bridge, Represents the short-term condition score of the bridge.

[0061] It should be noted that the complex interaction between the characteristics is captured by nonlinearly combining multiple dynamic characteristics of the bridge, thereby predicting the short-term condition score of the bridge. The stress mean, peak value, rate of change, instantaneous and average vibration frequency, and vibration intensity are comprehensively considered, and the nonlinear interaction of the dynamic characteristics of the bridge is reflected through nonlinear operations such as square root, logarithm, cubic root, and the use of sine function. This method can more comprehensively evaluate the short-term health status of the bridge and improve the accuracy of the prediction.

[0062] S3.2: Based on the long-term status characteristics of the bridge, the accelerated effect of bridge deterioration over time is captured by exponential decay, the impact of extreme temperature on the score is smoothed by a logarithmic function, the extreme impact of extreme values ​​on the long-term status score of the bridge is weakened by the fourth root, and the long-term status score of the bridge is predicted by combining the interactive relationship of multiple nonlinear combinations. The expression is: ;

[0063] in, is the long-term condition score of the bridge, is the ambient temperature, represents the rate at which the bridge structure ages over time, is the bridge maintenance frequency, It indicates the stress accumulation of the bridge during long-term use. It represents the comprehensive influencing factors of the environment in which the bridge is located, such as humidity, corrosion, wind, etc., reflecting the long-term impact of the external environment on the health of the bridge.

[0064] It should be noted that the accelerated effect of bridge aging over time is captured by exponential decay, the impact of extreme temperature on the score is smoothed by a logarithmic function, and the extreme impact of extreme values ​​on the long-term status score of the bridge is weakened by the fourth root. The expression combines the aging rate, maintenance frequency, stress accumulation and environmental factors (such as temperature, humidity, corrosion, etc.) of the bridge, and provides a comprehensive assessment of the long-term health status of the bridge through the interactive relationship of multiple nonlinear combinations. This method can more accurately reflect the long-term deterioration trend of bridges in complex environments and the influence of external factors.

[0065] S4: Integrate the short-term status score and the long-term status score to conduct a comprehensive assessment of bridge safety.

[0066] By introducing nonlinear adjustment factors and defining adaptive weight adjustment rules, when the long-term status score of the bridge is Below the bridge's short-term condition score When The weight of the bridge's long-term status score is Higher short-term condition rating than bridges When The weight of .

[0067] Based on the adaptive weight adjustment rule and nonlinear adjustment factor, the short-term score status and long-term status of the bridge are integrated to dynamically capture the interaction between the short-term status score and the long-term status score, and predict the comprehensive score of bridge safety. The expression is: ;

[0068] in, is the comprehensive score of bridge safety, t is the time, is the nonlinear correction parameter of the short-term score, Indicates the short-term status score of the bridge The long-term condition of the bridge is rated The adjustment factor of the influence degree, Indicates the long-term condition score of the bridge The adjustment factor that decays linearly with time t, Indicates the long-term condition score of the bridge Adjustment factor for nonlinear decay over time t.

[0069] It should be noted that by introducing nonlinear adjustment factors and adaptive weight adjustment rules, the short-term and long-term status scores of the bridge are effectively integrated, and the interaction between the two is dynamically captured. When the long-term status score is low, the weight of the short-term score is automatically reduced to ensure that the comprehensive score pays more attention to the long-term degradation trend; when the long-term score is high, the impact of short-term status changes on the comprehensive score is enhanced, reflecting the immediate health status of the bridge. At the same time, the nonlinear correction further smoothes the impact of extreme values ​​to ensure the stability and robustness of the score. This method can more accurately evaluate the overall safety of the bridge, taking into account both the immediate status and long-term aging and environmental impacts.

[0070] S5: Based on the evaluation results, bridge safety levels are divided and dynamic warnings are issued.

[0071] Define high safety thresholds based on the remaining structural life of the bridge and safety requirements and low safety threshold .

[0072] When S ≥ When , it is considered that the current bridge safety is good and no warning is triggered.

[0073] when ≤S< When , the current bridge safety is considered to be general, triggering a primary warning.

[0074] When S< When the bridge is in a critical condition, it is considered that the current bridge safety is extremely poor and an advanced warning is triggered.

[0075] Furthermore, based on the remaining structural life and safety requirements of the bridge, it is necessary to evaluate the actual use of the bridge within its design life, the degree of material degradation, and environmental impact. The remaining structural life reflects the time the bridge can continue to operate safely without major failures, usually affected by fatigue, corrosion, stress accumulation, etc. Safety requirements refer to the safety standards that the bridge needs to meet under specific operating conditions, including bearing capacity, seismic performance, etc. By considering these factors, a reasonable safety threshold can be set to ensure that the bridge can meet the safe operation requirements within its remaining life, and preventive maintenance measures can be taken according to changes in status.

[0076] The present embodiment also provides a bridge safety evaluation system based on data analysis, including: a data acquisition module, a feature extraction module, a state scoring module, a comprehensive evaluation module and a dynamic warning module; the data acquisition module is used to collect short-term dynamic data and long-term static data of the bridge; the feature extraction module is used to extract the short-term state characteristics and long-term state characteristics of the bridge based on the short-term dynamic data and the long-term static data; the state scoring module is used to predict the short-term state score of the bridge based on the short-term state characteristics of the bridge, and predict the long-term state score of the bridge based on the long-term state characteristics of the bridge; the comprehensive evaluation module is used to integrate the short-term state score and the long-term state score to conduct a comprehensive evaluation of the bridge safety; the dynamic warning module is used to classify the bridge safety level and conduct dynamic warning according to the evaluation results.

[0077] This embodiment also provides a computer device, which is suitable for the case of a bridge safety evaluation method based on data analysis, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the bridge safety evaluation method based on data analysis proposed in the above embodiment.

[0078] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0079] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the bridge safety evaluation method based on data analysis as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0080] In summary, the present invention realizes multi-dimensional monitoring of the health status of bridges by: collecting short-term dynamic data and long-term static data of bridges, and comprehensively extracting short-term and long-term status characteristics of bridges. At the same time, based on the adaptive weight adjustment rules, the short-term status score and the long-term status score are dynamically integrated, fully considering the impact of short-term emergencies and long-term aging effects, and significantly enhancing the accuracy of bridge safety assessment and dynamic early warning capabilities. Finally, the present invention improves the intelligent level of bridge safety management and the timeliness of risk early warning.

[0081] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a bridge safety evaluation method based on data analysis are provided.

[0082] This experiment aims to verify the advantages of the present invention by comparing the health status of bridge A (based on the monitoring method of the present invention) with that of bridge B and bridge C (using the bridge monitoring methods of prior art 1 and prior art 2, respectively).

[0083] The test objects are three bridges with the same service life and material, all of which have been in operation for 15 years. All of them are reinforced concrete structures and are located under similar traffic and environmental conditions. In order to monitor the health status of the bridge, Bridge A adopts the bridge health monitoring method in the invention, and Bridge B and Bridge C use the existing technical solution 1 and technical solution 2 respectively. The test data are divided into short-term dynamic data and long-term static data, and the test period is 6 months.

[0084] First, the experimental objects are three reinforced concrete bridges that have been in operation for 15 years, namely Bridge A (based on the monitoring method of the invention), Bridge B (prior art 1) and Bridge C (prior art 2). By installing sensors at key locations on the bridges, short-term dynamic data of the bridges are collected in real time, including information such as stress, deformation, vibration, traffic flow, temperature and humidity, and combined with long-term static data such as historical maintenance records of the bridges and material aging data, the health status of the bridges is fully recorded.

[0085] Secondly, Bridge A uses the monitoring method in the invention, which can extract dynamic features such as stress mean, peak value, skewness, and rate of change through time domain analysis, and use fast Fourier transform and Hilbert-Huang transform for frequency domain and instantaneous frequency analysis. Bridges B and C use existing technologies 1 and 2 respectively, which can collect some data, but are inferior to the invention in data collection frequency and processing depth, making it difficult to capture the instantaneous change characteristics of the bridge.

[0086] Then, the experiment statistically analyzed the long-term static data of the bridge, extracted the aging rate, stress accumulation and maintenance frequency of the bridge, and combined with the short-term dynamic data to calculate the short-term and long-term status scores of the bridge. Bridge A uses the complex nonlinear combination model of the invention content to dynamically adjust the weights of the short-term and long-term scores to obtain a more accurate comprehensive safety score, while the existing technology scores used by Bridges B and C are relatively simple and difficult to accurately reflect the actual health status of the bridge.

[0087] The prior art 1 adopts a bridge monitoring method based on traditional time domain analysis, which mainly collects basic parameters such as stress and vibration through sensors, and uses simple time domain data processing techniques such as mean and peak analysis to evaluate the health status of the bridge.

[0088] The existing technology 2 adopts a bridge monitoring method based on basic frequency domain analysis, which analyzes the response characteristics of the bridge at different frequencies by performing a simple frequency domain conversion on the dynamic data such as the vibration frequency and stress of the bridge.

[0089] The details are shown in Table 1 below:

[0090] Table 1 Comparison of bridge health status monitoring data

[0091]

[0092] Through the data analysis of the above table, it can be clearly seen that Bridge A (based on the monitoring method of the invention) is superior to Bridge B and Bridge C in multiple key parameters. For example, the mean stress of Bridge A is 5.1 MPa, which is significantly lower than 6.2 MPa of Bridge B and 6.5 MPa of Bridge C, indicating that the method of the present invention more effectively disperses the stress concentration of the bridge and delays material fatigue. In addition, the aging rate of Bridge A is 0.75% / year, which is significantly lower than 1.1% / year of Bridge B and 1.3% / year of Bridge C, further proving the advantages of the method of the present invention in long-term degradation control. In terms of comprehensive scoring, Bridge A scored 0.81, which is much higher than 0.67 of Bridge B and 0.61 of Bridge C, indicating that the invention can more accurately capture the short-term dynamic changes and long-term health trends of the bridge, thereby significantly improving the safety and service life of the bridge.

[0093] The data analysis-based bridge safety evaluation method of the present invention can not only capture the instantaneous dynamic changes of the bridge in operation in real time and accurately analyze the changing trends of key parameters such as stress and vibration, but also evaluate the aging rate, maintenance requirements and stress accumulation of the bridge through comprehensive analysis of long-term static data. This reflects the significant advantages of the present invention in comprehensive monitoring and integrated evaluation of the short-term state and long-term degradation trend of the bridge, and can more accurately predict the health status of the bridge, ensuring the safety of the bridge and extending its service life.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A bridge safety evaluation method based on data analysis, characterized in that: include, Collect short-term dynamic data and long-term static data of bridges; Extract the short-term state characteristics and long-term state characteristics of the bridge based on short-term dynamic data and long-term static data; Predicting the short-term status score of the bridge based on the short-term status characteristics of the bridge, and predicting the long-term status score of the bridge based on the long-term status characteristics of the bridge; The short-term condition score and the long-term condition score are integrated to conduct a comprehensive assessment of bridge safety; According to the evaluation results, the bridge safety level is divided and dynamic warning is carried out; The specific steps of predicting the short-term status score of the bridge based on the short-term status characteristics of the bridge are as follows: By nonlinearly combining multiple dynamic features of the bridge and capturing the complex interactive relationship between the features, the short-term status score of the bridge is predicted. The expression is: in, is the mean bridge stress, is the peak stress of the bridge, is the rate of change of bridge stress, is the instantaneous vibration frequency of the bridge, represents the average vibration frequency of the bridge during vibration, represents the vibration intensity of the bridge, Indicates the short-term condition score of the bridge; The specific steps of predicting the long-term status score of the bridge based on the long-term status characteristics of the bridge are as follows: Based on the long-term status characteristics of the bridge, the accelerated effect of bridge deterioration over time is captured by exponential decay, the impact of extreme temperature on the score is smoothed by a logarithmic function, the extreme impact of extreme values ​​on the long-term status score of the bridge is weakened by the fourth root, and the long-term status score of the bridge is predicted by combining the interactive relationship of multiple nonlinear combinations. The expression is: in, is the long-term condition score of the bridge, is the ambient temperature, represents the rate at which the bridge structure ages over time, is the bridge maintenance frequency, It indicates the stress accumulation of the bridge during long-term use. Indicates the comprehensive influencing factors of the environment where the bridge is located; The short-term status score and the long-term status score are integrated to conduct a comprehensive assessment of bridge safety. The specific steps are as follows: By introducing nonlinear adjustment factors and defining adaptive weight adjustment rules, when the long-term status score of the bridge is Below the bridge's short-term condition score When The weight of the bridge's long-term status score is Higher short-term condition rating than bridges When The weight of Based on the adaptive weight adjustment rule and nonlinear adjustment factor, the short-term score status and long-term status of the bridge are integrated to dynamically capture the interaction between the short-term status score and the long-term status score, and predict the comprehensive score of bridge safety. The expression is: in, is the comprehensive score of bridge safety, t is the time, is the nonlinear correction parameter of the short-term score, Indicates the short-term status score of the bridge The long-term condition of the bridge is rated The adjustment factor of the influence degree, Indicates the long-term condition score of the bridge The adjustment factor that decays linearly with time t, Indicates the long-term condition score of the bridge Adjustment factor for nonlinear decay over time t.

2. The bridge safety evaluation method based on data analysis according to claim 1, characterized in that: The short-term dynamic data include stress, deformation and vibration of the bridge; The long-term static data includes material aging records, historical maintenance records, structural design parameters and historical meteorological data of the bridge.

3. The bridge safety evaluation method based on data analysis according to claim 2, characterized in that: The short-term state characteristics and long-term state characteristics of the bridge are extracted based on the short-term dynamic data and the long-term static data. The specific steps are as follows: Through time domain analysis, the mean, peak, skewness and rate of change of bridge stress are extracted from the time series of short-term dynamic data; The average vibration frequency and vibration intensity in the short-term dynamic data are extracted by fast Fourier transform; Extract instantaneous frequency and vibration amplitude from short-term dynamic data using Hilbert-Huang transform analysis; Through statistical analysis methods, the aging rate, maintenance frequency, stress accumulation and ambient temperature in long-term static data are extracted.

4. The bridge safety evaluation method based on data analysis according to claim 3 is characterized in that: According to the evaluation results, the bridge safety level is divided and dynamic warning is carried out. The specific steps are as follows: Define high safety thresholds based on the remaining structural life of the bridge and safety requirements and low safety threshold ; When S ≥ When , the current bridge safety is considered good and no warning is triggered; when ≤S< When , the current bridge safety is considered to be average, triggering the primary warning; When S< When , it is considered that the current bridge safety is extremely poor and triggers an advanced warning.

5. A bridge safety evaluation system based on data analysis, based on the bridge safety evaluation method based on data analysis according to any one of claims 1 to 4, characterized in that: Including data collection module, feature extraction module, status scoring module, comprehensive evaluation module and dynamic warning module; Data acquisition module: used to collect short-term dynamic data and long-term static data of the bridge; Feature extraction module: used to extract short-term state features and long-term state features of the bridge based on short-term dynamic data and long-term static data; State scoring module: used to predict the short-term state score of the bridge based on the short-term state characteristics of the bridge, and to predict the long-term state score of the bridge based on the long-term state characteristics of the bridge; Comprehensive evaluation module: used to integrate short-term status scores and long-term status scores to conduct a comprehensive evaluation of bridge safety; Dynamic warning module: used to classify bridge safety levels and provide dynamic warnings based on evaluation results.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the bridge safety evaluation method based on data analysis described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the bridge safety evaluation method based on data analysis described in any one of claims 1 to 4 are implemented.

Images