Large-span bridge vortex-induced vibration event alarm method and system based on multi-index cooperative driving

Abstract

The invention provides a large-span bridge vortex-induced vibration event alarm method and system based on multi-index cooperative driving, a terminal and a storage medium, and belongs to the technical field of bridge monitoring. The method comprises the following steps: acquiring bridge dynamic response data; preprocessing the bridge dynamic response data to obtain bridge dynamic response preprocessing data; vortex vibration characterization processing is conducted on the bridge dynamic response preprocessing data, and vortex vibration characterization parameters are obtained; and the vortex vibration characterization parameters are subjected to early warning recognition through a preset multi-index cooperative driving vortex vibration recognition model, and an early warning recognition result is obtained. Starting from a vortex vibration mechanism, a plurality of indexes capable of reflecting bridge vortex vibration are established; and deep learning is utilized to deeply dig the internal relationship of multiple indexes and make a decision on whether to give an alarm, so that the situation of missing alarm and false alarm of a single index is avoided, and the reliability of vortex vibration alarm is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a method, system, terminal and storage medium for alarming vortex-vibration events of large-span bridges based on multi-indicator collaborative driving. Background Art

[0002] With the rapid development of global transportation infrastructure construction, the safety and stability of bridges, as important transportation hubs connecting water systems, valleys and cities, have become the focus of social attention. However, in recent years, many bridges at home and abroad have frequently encountered vortex-induced vibration (VIV) events. This periodic vibration phenomenon caused by vortex shedding in wind loads not only seriously threatens the structural safety of bridges, but may also cause traffic interruptions, economic losses and even social panic. Therefore, how to effectively identify and warn of bridge VIV has become a key issue that needs to be solved in the field of bridge engineering.

[0003] At present, many long-span bridges are equipped with intelligent monitoring systems, which can obtain real-time information such as the structural response and environmental load of the bridge, providing important data for analyzing the abnormal vibration of the long-span bridge structure. However, the identification method of vortex-induced vibration events mainly relies on the monitoring of a single physical quantity or indicator, such as acceleration, displacement or wind speed. Although these methods can reflect the vibration state of the bridge to a certain extent, they are often difficult to fully capture the complex characteristics of vortex-induced vibration due to the limitations of a single indicator, resulting in a high rate of missed reports and false alarms in practical applications. Missed reports may cause the bridge to suffer continuous vibration damage without knowing it, while false alarms may cause unnecessary panic and waste of resources. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention proposes a method, system, device and storage medium for vortex-vibration event alarm of a large-span bridge based on multi-indicator collaborative drive to solve the technical problems existing in the prior art. Starting from the vortex-vibration mechanism, the present invention establishes multiple indicators that can reflect the vortex-vibration of the bridge; and uses deep learning to dig deep into the internal relationship of multiple indicators and make a decision on whether to alarm, avoiding the situation of single indicator missing or false alarm, and improving the reliability of vortex-vibration alarm.

[0005] The technical solution adopted by the present invention is:

[0006] In the first aspect, a vortex-vibration event alarm method for a large-span bridge based on multi-indicator collaborative driving is provided, comprising:

[0007] Obtain bridge dynamic response data;

[0008] Preprocessing the bridge dynamic response data to obtain bridge dynamic response preprocessing data;

[0009] Perform vortex-vibration characterization processing on the preprocessed data of the dynamic response of the bridge to obtain vortex-vibration characterization parameters;

[0010] The vortex vibration characterization parameters are used for early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain early warning identification results.

[0011] Furthermore, the bridge dynamic response data includes deflection or acceleration.

[0012] Furthermore, the bridge dynamic response data is preprocessed to obtain bridge dynamic response preprocessed data, including:

[0013] The Butterworth bandpass filter is used to filter the bridge dynamic response data to obtain the bridge dynamic response preprocessing data.

[0014] Furthermore, the order of the Butterworth bandpass filter is second order, the lower limit of the cut-off frequency is 0.2 Hz, and the upper limit of the cut-off frequency is 5 Hz.

[0015] Furthermore, the vortex-vibration characterization parameters include: maximum vibration energy, vibration energy ratio, Hilbert ring inner and outer diameter ratio, amplitude to root mean square ratio and root mean square value. The bridge dynamic response preprocessing data is subjected to vortex-vibration characterization processing to obtain vortex-vibration characterization parameters, including:

[0016] Perform power spectrum density analysis on the preprocessed data of bridge dynamic response to obtain the maximum vibration energy and vibration energy ratio;

[0017] The Hilbert transform analysis is performed on the preprocessed data of the bridge dynamic response to obtain the inner and outer diameter ratio of the Hilbert ring;

[0018] The preprocessed data of bridge dynamic response were statistically analyzed to obtain the ratio of amplitude to RMS and the RMS value.

[0019] Furthermore, the method further comprises:

[0020] Obtain a preset multi-index collaborative drive vortex vibration identification model;

[0021] Obtain the preset multi-index collaborative drive vortex vibration identification model, including:

[0022] Construct a sample data set, where the sample data in the sample data set include maximum vibration energy, vibration energy ratio, inner and outer diameter ratio of the Hilbert ring, amplitude to root mean square ratio and root mean square value and corresponding label information;

[0023] The sample data set is used to adjust the initial model until the loss function corresponding to the initial model converges, and then the preset multi-index collaboratively driven vortex vibration identification model is obtained.

[0024] Further, the method comprises:

[0025] Perform early warning processing based on early warning identification results;

[0026] Perform early warning processing based on the early warning identification results, including:

[0027] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 15cm / s 2 ≦RMS<31.5cm / s 2 , then respond to the first-level warning;

[0028] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 31.5cm / s 2 ≦RMS<50cm / s 2 , then respond to the second-level warning;

[0029] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 50cm / s 2 ≦RMS<80cm / s 2 , then respond to the third-level warning;

[0030] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies RMS ≧ 80cm / s 2 , then respond to the fourth level warning.

[0031] Secondly, a vortex-vibration event alarm system for large-span bridges based on multi-indicator collaborative drive is provided, including:

[0032] A data preprocessing module preprocesses the bridge dynamic response data to obtain bridge dynamic response preprocessing data;

[0033] The analysis module processes the preprocessed data of the bridge dynamic response to characterize the vortex vibration;

[0034] The indicator construction module obtains the vortex vibration characterization processing results of the analysis module and constructs the vortex vibration characterization parameters;

[0035] The decision module uses the vortex vibration characterization parameters through a preset multi-indicator collaboratively driven vortex vibration identification model to perform early warning identification and obtain early warning identification results.

[0036] In a third aspect, a terminal is provided, comprising a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions as in the first aspect of the present application.

[0037] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0038] It can be seen from the above technical solution that the beneficial technical effects of the present invention are as follows:

[0039] 1. The present invention starts from the vortex-vibration mechanism and establishes multiple indicators that can reflect the vortex-vibration of bridges. It also uses deep learning to dig deep into the internal relationship between multiple indicators and make a decision on whether to alarm, thereby avoiding the situation of missing or false alarming of a single indicator and improving the reliability of vortex-vibration alarm.

[0040] 2. The present invention can obtain the dynamic response data of the bridge in real time and perform preprocessing and analysis, and then identify vortex vibration through the trained model. This real-time performance ensures that when vortex vibration occurs, it can respond quickly and issue early warnings in time, providing valuable decision-making time for bridge managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0042] Figure 1 This is a flow chart of an embodiment of the present invention;

[0043] Figure 2 This is a measurement point layout diagram of a large-span cable-stayed bridge according to an embodiment of the present invention;

[0044] Figure 3 This is a graph of deflection data originally measured by the sensor of an embodiment of the present invention;

[0045] Figure 4 The embodiment of the present invention is a diagram of removing obvious abnormal points from the deflection data originally measured by the sensor;

[0046] Figure 5 This is a diagram showing the preprocessing result of the deflection data originally measured by the sensor after removing obvious abnormal points according to an embodiment of the present invention;

[0047] Figure 6 For the embodiment of the present invention Figure 5 Data chart for the first 60 minutes;

[0048] Figure 7 For selection Figure 6 The power spectrum analysis results of the data are shown in the figure. Figure 7 (a) is the power spectrum analysis result diagram of the vortex-free data a; Figure 7 (b) is the power spectrum analysis result diagram of the selected vortex vibration formation data b; Figure 7 (c) is the power spectrum analysis result diagram of the selected vortex vibration stability data c; Figure 7(d) is the power spectrum analysis result diagram of selected vortex vibration extinction data d;

[0049] Figure 8 For selection Figure 6 The result of Hilbert transform of the data in the figure is as follows: Figure 8 (a) is the Hilbert transform result diagram of the vortex-free data a; Figure 8 (b) is the Hilbert transform result diagram of the selected vortex vibration formation data b; Figure 8 (c) is the Hilbert transform result diagram of the selected vortex-oscillation stability data c; Figure 8 (d) is the Hilbert transform result diagram of the selected vortex vibration extinction data d;

[0050] Fig. 9 This is a system framework diagram of an embodiment of the present invention;

[0051] Fig.10 Schematic diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0053] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0054] Example

[0055] This embodiment provides a vortex vibration event alarm method for a large-span bridge based on multi-indicator collaborative driving, such as Figure 1 As shown, including:

[0056] S01: Obtain bridge dynamic response data;

[0057] S02: preprocessing the bridge dynamic response data to obtain bridge dynamic response preprocessing data;

[0058] S03: performing vortex-vibration characterization processing on the bridge dynamic response preprocessing data to obtain vortex-vibration characterization parameters;

[0059] S04: The vortex vibration characterization parameters are subjected to early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain an early warning identification result.

[0060] Acceleration, deflection and other sensors are deployed on the long-span bridge to collect the dynamic response of the bridge in real time. As a monitoring system, it can provide data analysis for the bridge vortex vibration analysis in this embodiment. Figure 2As shown in the figure, acceleration and deflection sensors are arranged at the mid-span, 1 / 4 span and 3 / 4 span upstream and downstream of the main span.

[0061] This embodiment takes disturbance monitoring data as an example:

[0062] Get the original deflection data measured by the original sensor, the interception time is 240 minutes, such as Figure 3 As shown;

[0063] Preprocessing the bridge dynamic response data to obtain bridge dynamic response preprocessing data;

[0064] exist Figure 3 The black box in the middle shows obvious abnormal points. After removing the abnormal points, the Figure 4 As shown in the figure, in this embodiment, the data after the abnormal points are removed is preprocessed by using a Butterworth bandpass filter. The filter order is second order and the bandpass frequency range is 0.2Hz to 5Hz. The upper and lower limits of the bandpass frequency range should be able to simultaneously envelop the main frequency of the pulsating wind in the bridge area and the corresponding main beam resonant frequency of the large-span bridge. The result after preprocessing is shown in the figure. Figure 5 shown.

[0065] Various vortex-induced mechanical models and engineering experience show that when vortex vibration occurs, due to its frequency locking characteristics, the bridge deck vibration displacement u can be approximately expressed as a narrow-band harmonic model, showing a single-mode vibration characteristic. The vertical vibration displacement u can be expressed as:

[0066] u=u a sin(ωt+φ)

[0067] Where: t is time, ω is the bridge vibration frequency during vortex vibration, φ is the phase, u a is the vortex amplitude.

[0068] Compared with random vibration under environmental excitation, the spectrum characteristics of single-mode vibration are as follows: most of the vibration energy is concentrated in a certain frequency, and the spectrum value is much larger than the other frequencies; if the data is Hilbert transformed, its trajectory diagram is approximately a ring, and the radial change is smaller than the axial change.

[0069] In this embodiment, the interception Figure 4 For the first 60 minutes of data, the data analysis interval is 2 minutes. Figure 6 As shown in the figure, four representative data, namely, no vortex vibration (data in period a), vortex vibration formation (data in period b), vortex vibration stability (data in period c), and vortex vibration disappearance (data in period d), are selected for power spectrum analysis. The power spectrum analysis results of each data are shown in Figure 7 As shown in , according to the power spectrum analysis, when vortex vibration occurs, the energy at the locked frequency is large, with an order of magnitude of 1E4, which is much larger than the energy without vortex vibration. Figure 6The results of Hilbert transform are selected for four representative data: no vortex vibration (data in period a), vortex vibration formation (data in period b), vortex vibration stability (data in period c), and vortex vibration disappearance (data in period d). Figure 8 As shown in Figure 1, when vortex vibration occurs, the result of the Hilbert transform is a ring.

[0070] The bridge dynamic response preprocessing data is processed for vortex vibration characterization to obtain vortex vibration characterization parameters, specifically:

[0071] In order to quantitatively describe the changes in vortex sine waves: the following five indicators are defined:

[0072] Indicator 1: Maximum vibration energy MVE. Perform power spectral density (PSD) analysis on the preprocessed signal and select the peak value of energy distribution in the vibration signal. This indicator can reflect the magnitude of energy. When vortex vibration occurs, the energy at the locked frequency is relatively large. Preferably, the maximum vibration energy MVE is more than 3 orders of magnitude of the normal energy.

[0073] Index 2: Vibration Energy Ratio Re. Perform power spectrum density analysis on the processed signal and select the ratio of the maximum amplitude to the second maximum amplitude. This index can reflect the relative concentration of energy. The larger the ratio, the more concentrated the energy. When vortex vibration occurs, the energy is relatively concentrated. Preferably, the vibration energy ratio Re value is greater than 10.

[0074] Indicator 3: Hilbert ring inner and outer diameter ratio Rr. Perform Hilbert transform on the processed signal, and calculate the ratio of the minimum radius to the maximum radius. Considering the influence of measurement error and other environments, 5% and 95% of the radius data are used as the minimum radius and maximum radius respectively. When vortex vibration occurs, the narrower the ring, the larger the radius ratio. Preferably, the Hilbert ring inner and outer diameter ratio Rr value is greater than 0.3.

[0075] Indicator 4: RAS ratio of amplitude to root mean square. The processed signal is statistically analyzed to obtain the amplitude and root mean square value. The RAS of the standard simple harmonic wave is 1.414. When vortex vibration occurs, the closer the signal is to the simple harmonic wave, the smaller the RAS value is. Preferably, the RAS ratio of amplitude to root mean square is less than 2.

[0076] Indicator 5: Root mean square value RMS. The processed signal is statistically analyzed to obtain the root mean square value RMS, which mainly reflects the intensity of vortex vibration. In this embodiment, it is used to formulate a graded warning based on the model recognition result and the intensity of vortex vibration.

[0077] In this implementation, if the identification result is that vortex vibration exists and the root mean square value RMS meets 15cm / s 2 ≦RMS<31.5cm / s 2, then respond to the first-level warning;

[0078] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 31.5cm / s 2 ≦RMS<50cm / s 2 , then respond to the second-level warning;

[0079] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 50cm / s 2 ≦RMS<80cm / s 2 , then respond to the third-level warning;

[0080] If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies RMS ≧ 80cm / s 2 , then respond to the fourth level warning.

[0081] In this embodiment, different levels of warning responses (level one to level four warnings) are set according to the results of vortex-induced vibration identification and different ranges of RMS values. This graded warning mechanism can take corresponding countermeasures according to different degrees of vortex-induced vibration, thereby improving the pertinence and effectiveness of the warning.

[0082] The vortex vibration characterization parameters are used for early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain an early warning identification result;

[0083] In this embodiment, the training process of the multi-index collaboratively driven vortex vibration identification model includes:

[0084] Constructing a sample data set, wherein the sample data in the sample data set includes maximum vibration energy MVE, vibration energy ratio Re, inner and outer diameter ratio of Hilbert ring Rr, amplitude to root mean square ratio RAS and root mean square value RMS and corresponding label information (whether there is vortex vibration), and the label information is obtained through bridge deck video information and artificial perception;

[0085] The sample data set is used to adjust the initial model until the loss function corresponding to the initial model converges, thereby obtaining a multi-index collaboratively driven vortex vibration identification model.

[0086] In this embodiment, the initial model used is a long short-term memory (LSTM) model. LSTM is a special recurrent neural network (RNN).

[0087] In the problem of vortex vibration identification, since the vortex vibration phenomenon is often related to the synergistic effect of multiple indicators (such as maximum vibration energy MVE, vibration energy ratio Re, Hilbert ring inner and outer diameter ratio Rr, amplitude to root mean square ratio RAS and root mean square value RMS), and these indicators may change over time, the LSTM model can well capture the time dependence and nonlinear relationship between these indicators.

[0088] In this embodiment, the loss function adopts binary cross-entropy loss (Binary Cross-Entropy Loss), and the formula is expressed as follows:

[0089]

[0090] Among them, y i is the true label of the i-th sample, is the probability that the model predicts that the sample is a positive class (vortex vibration), and N is the total number of samples.

[0091] The multi-indicator collaboratively driven vortex-vibration identification model is deployed in the bridge monitoring system. The system can receive the dynamic response data of the bridge in real time, and pre-process the dynamic response data of the bridge to obtain the pre-processed dynamic response data of the bridge. The pre-processed dynamic response data of the bridge is subjected to vortex-vibration characterization processing to obtain vortex-vibration characterization parameters. The vortex-vibration characterization parameters are input into the multi-indicator collaboratively driven vortex-vibration identification model for vortex-vibration detection and intensity prediction. Once the vortex-vibration phenomenon is detected, the system will immediately issue an alarm and the corresponding level, and provide corresponding maintenance suggestions to ensure the safe operation of the bridge.

[0092] Recommended measures for different warning levels:

[0093] In response to the first level warning, take measures:

[0094] Strengthen real-time monitoring: increase the number of monitoring points and improve the frequency of data collection to ensure data accuracy and real-time performance.

[0095] Detailed analysis: Analyze the duration of vortex vibration and the wind control conditions that cause vortex vibration; use computer-aided engineering software to conduct numerical simulation analysis of the bridge to provide a basis for formulating targeted treatment plans.

[0096] Information release: Issue early warning information to bridge management departments and related units to remind them to pay attention.

[0097] In response to the second-level warning, take measures:

[0098] Continuous attention: Bridge management departments or relevant units should continue to pay attention to changes in bridges.

[0099] Special inspection: Conduct a comprehensive and detailed special inspection on the bridge, including the condition of dampers and bearings, etc.

[0100] Prepare emergency plans: Develop emergency plans for bridges, including emergency response plans, personnel evacuation plans, etc.

[0101] In response to the Level 3 warning, take measures:

[0102] Traffic restriction: remind vehicles to limit their speed, etc.

[0103] Bridge treatment: Initiate bridge treatment plans, such as adding damping devices, adding spoilers, etc., to mitigate the damage of vortex vibration to the bridge structure.

[0104] In response to the Level 4 warning, take measures:

[0105] Closed bridge: The bridge is completely closed to prohibit any vehicles and pedestrians from passing through to ensure the safety of people.

[0106] Bridge treatment: Initiate bridge treatment plans, such as adding damping devices, adding spoilers, etc., to mitigate the damage of vortex vibration to the bridge structure.

[0107] Professional assessment: Invite a qualified organization to conduct an overall assessment of the bridge to determine its safety.

[0108] The present invention helps bridge management personnel to take timely intervention measures to protect the safety of the bridge structure by timely and accurately identifying vortex-vibration events and issuing early warnings.

[0109] In one embodiment, if Fig. 9 As shown, a vortex-vibration event alarm system for a large-span bridge based on multi-indicator collaborative driving is provided, including:

[0110] A data preprocessing module preprocesses the bridge dynamic response data to obtain bridge dynamic response preprocessing data;

[0111] The analysis module processes the preprocessed data of the bridge dynamic response to characterize the vortex vibration;

[0112] The indicator construction module obtains the vortex vibration characterization processing results of the analysis module and constructs the vortex vibration characterization parameters;

[0113] The decision module uses the vortex vibration characterization parameters to perform early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain an early warning identification result.

[0114] In one embodiment, if Fig.10 As shown, a terminal is provided, including a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the step instructions in the aforementioned embodiments.

[0115] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the foregoing embodiments.

[0116] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A vortex vibration event alarm method for a large-span bridge based on multi-index collaborative driving, characterized in that: include: Obtain bridge dynamic response data; Preprocessing the bridge dynamic response data to obtain bridge dynamic response preprocessing data; Perform vortex-vibration characterization processing on the preprocessed data of the dynamic response of the bridge to obtain vortex-vibration characterization parameters; The vortex vibration characterization parameters are used for early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain an early warning identification result.

2. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative driving according to claim 1 is characterized in that: The bridge dynamic response data includes deflection or acceleration.

3. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative driving according to claim 2 is characterized in that: The preprocessing of the bridge dynamic response data to obtain bridge dynamic response preprocessing data includes: The bridge dynamic response data is filtered using a Butterworth bandpass filter to obtain bridge dynamic response preprocessing data.

4. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative driving according to claim 3 is characterized in that: The order of the Butterworth bandpass filter is second order, the lower limit of the cut-off frequency is 0.2 Hz, and the upper limit of the cut-off frequency is 5 Hz.

5. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative drive according to any one of claims 1 to 4, characterized in that: The vortex-vibration characterization parameters include: maximum vibration energy, vibration energy ratio, Hilbert ring inner and outer diameter ratio, amplitude to root mean square ratio and root mean square value. The vortex-vibration characterization parameters obtained by performing vortex-vibration characterization processing on the bridge dynamic response preprocessing data include: Performing power spectrum density analysis on the preprocessed data of the dynamic response of the bridge to obtain the maximum vibration energy and the vibration energy ratio; Performing Hilbert transform analysis on the preprocessed data of the dynamic response of the bridge to obtain the inner and outer diameter ratio of the Hilbert ring; The preprocessed data of the dynamic response of the bridge are statistically analyzed to obtain the ratio of amplitude to root mean square and the root mean square value.

6. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative driving according to claim 5 is characterized in that: The method further comprises: Acquire the preset multi-index collaborative drive vortex vibration identification model; The obtaining of the preset multi-index collaborative drive vortex vibration identification model includes: Constructing a sample data set, wherein the sample data in the sample data set includes maximum vibration energy, vibration energy ratio, inner and outer diameter ratio of Hilbert ring, amplitude to root mean square ratio and root mean square value and corresponding label information; The sample data set is used to adjust the initial model until the loss function corresponding to the initial model converges, thereby obtaining a preset multi-index collaboratively driven vortex vibration identification model.

7. The method for vortex-vibration event alarm of a large-span bridge based on multi-index collaborative driving according to claim 1 or 6, characterized in that: The method comprises: Perform early warning processing based on early warning identification results; The warning processing based on the warning identification result includes: If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 15cm / s 2 ≦RMS<31.5cm / s 2 , then respond to the first-level warning; If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 31.5cm / s 2 ≦RMS<50cm / s 2 , then respond to the second-level warning; If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies 50cm / s 2 ≦RMS<80cm / s 2 , then respond to the third-level warning; If the identification result shows that vortex vibration exists and the root mean square value RMS satisfies RMS ≧ 80cm / s 2 , then respond to the fourth level warning.

8. A vortex vibration event alarm system for large-span bridges based on multi-index collaborative drive, characterized in that: include: A data preprocessing module preprocesses the bridge dynamic response data to obtain bridge dynamic response preprocessing data; The analysis module processes the preprocessed data of the bridge dynamic response to characterize the vortex vibration; The indicator construction module obtains the vortex vibration characterization processing results of the analysis module and constructs the vortex vibration characterization parameters; The decision module uses the vortex vibration characterization parameters to perform early warning identification through a preset multi-index collaboratively driven vortex vibration identification model to obtain an early warning identification result.

9. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images