Cable-supported bridge monitoring method, device, storage medium and program product

Abstract

The present application discloses a monitoring method, device, storage medium and program product for a cable-supported bridge, which relates to the field of bridge engineering technology, including: obtaining vibration signals of each bridge cable of the bridge to be detected in the current monitoring period; for any target cable among the bridge cables, performing fast Fourier transform on the target vibration signal to obtain a target spectrum diagram, wherein the target vibration signal is the vibration signal of the target cable; identifying the frequency main peaks of each amplitude value in the target spectrum diagram, and determining the frequency orders of each frequency main peak based on the main peak frequency values ​​of each frequency main peak, and determining the cable force value of the target cable based on each frequency order; performing abnormal detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result. The present application realizes the identification of the cable vibration frequency order, thereby calculating the cable force value of the cable based on the frequency order, improving the accuracy of the cable force value, and thus improving the accuracy of bridge vibration monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of bridge engineering, and in particular to a monitoring method, device, storage medium and program product for a cable-supported bridge. Background Art

[0002] Cable-supported bridges are widely used in modern bridge engineering due to their lightweight structure and large span. In order to ensure the safety and stability of such bridges, regular cable force monitoring is essential. Cable force refers to the tension acting on the bridge cables, which directly reflects the working status of the cables and the overall safety of the bridge.

[0003] Traditional cable tension monitoring methods usually rely on manual on-site measurements or use fixed frequency threshold methods for analysis. These methods are not only inefficient but also easily affected by environmental noise and other nonlinear factors, resulting in inaccurate cable tension monitoring results.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a monitoring method, device, storage medium and program product for a cable-supported bridge, aiming to solve the technical problem of difficulty in identifying the orders of various frequencies of cable vibration in monitoring bridge cables, thereby leading to low accuracy in cable force calculation.

[0006] To achieve the above objectives, the present application proposes a monitoring method for a cable-supported bridge, the method comprising:

[0007] Obtaining vibration signals of each bridge cable of the bridge to be inspected in the current monitoring period;

[0008] For any target cable among the bridge cables, a target vibration signal is subjected to a fast Fourier transform to obtain a target frequency spectrum, wherein the target vibration signal is a vibration signal of the target cable;

[0009] Identify the main frequency peaks of the amplitude values ​​in the target frequency spectrum, determine the frequency orders of the main frequency peaks based on the main peak frequency values ​​of the main frequency peaks, and determine the cable force value of the target cable based on the frequency orders;

[0010] Based on the cable force values ​​of each of the cables, abnormality detection is performed on the bridge to be detected to obtain a monitoring result.

[0011] In one embodiment, the step of performing a fast Fourier transform on the target vibration signal to obtain a target spectrum diagram includes:

[0012] Performing noise reduction processing on the target vibration signal to obtain a noise reduction signal;

[0013] A windowed signal is obtained by multiplying a preset window function with the noise reduction signal, and a fast Fourier transform is performed on the windowed signal to obtain a target spectrum diagram.

[0014] In one embodiment, the step of performing noise reduction processing on the target vibration signal to obtain a noise reduction signal includes:

[0015] The target vibration signal is subjected to noise elimination processing using a preset deep neural network to obtain a noise reduction signal, wherein the deep neural network is trained using the vibration signal as input data and the vibration signal after noise elimination as a label.

[0016] In one embodiment, the deep neural network includes an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer, and the step of performing noise elimination processing on the target vibration signal using a preset deep neural network to obtain a noise reduction signal includes:

[0017] Inputting the target vibration signal into the encoder for processing to obtain a first processing result;

[0018] Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the vibration signal;

[0019] Inputting the second processing result into the decoder for processing to obtain a third processing result;

[0020] Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0021] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a noise reduction signal.

[0022] In one embodiment, the step of determining the frequency order of each of the main frequency peaks based on the main peak frequency value of each of the main frequency peaks comprises:

[0023] The frequency value of the frequency main peak with the smallest amplitude among all frequency main peaks is taken as the fundamental frequency;

[0024] For any target main peak among the frequency main peaks, a frequency multiple is obtained by dividing the frequency value of the target main peak by the base frequency, and the frequency multiple is used as the frequency order of the target main peak.

[0025] In one embodiment, the step of determining the cable force value of the target cable based on each of the frequency orders comprises:

[0026] If the frequency order of the target main peak is the first order, the main peak frequency value of the target main peak is input into a preset fundamental frequency model to obtain the tension value corresponding to the target main peak;

[0027] If the frequency order of the target main peak is not the first order, a preset high-order frequency model is input based on the main peak frequency value of the target main peak to obtain a tension value corresponding to the target main peak;

[0028] The average value of the tension values ​​of the main peaks of the frequencies is calculated, and the average value is used as the cable tension value of the target cable.

[0029] In one embodiment, the step of performing abnormality detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result comprises:

[0030] Traversing each of the cable force values, and determining the difference between the cable force value and the historical cable force value as the cable force value fluctuation value, wherein the historical cable force value is the cable force value in the adjacent historical period of the cable force value;

[0031] If the fluctuation values ​​of the cable force values ​​do not exceed the preset fluctuation value range, it is determined that the stress of the bridge to be inspected is normal;

[0032] If there is an abnormal fluctuation value that exceeds the fluctuation value range among the cable force value fluctuation values, then determining the proportion of the abnormal fluctuation value in the number of the cable force value fluctuation values;

[0033] If the proportion of the number exceeds a preset proportion threshold, it is determined that the stress of the bridge to be detected is abnormal;

[0034] If the number ratio does not exceed the ratio threshold, it is determined that the stress on the bridge to be inspected is normal.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a monitoring device for a cable-supported bridge, the monitoring device for a cable-supported bridge comprising:

[0036] An acquisition module, used to acquire vibration signals of each bridge cable of the bridge to be detected in a current monitoring period;

[0037] A processing module, for performing a fast Fourier transform on a target vibration signal of any target cable among the bridge cables to obtain a target frequency spectrum, wherein the target vibration signal is a vibration signal of the target cable;

[0038] An identification module, used for identifying the main frequency peaks of the amplitude values ​​in the target frequency spectrum, and determining the frequency orders of the main frequency peaks based on the main peak frequency values ​​of the main frequency peaks, and determining the cable force value of the target cable based on the frequency orders;

[0039] The detection module is used to perform abnormal detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the monitoring method of the cable-supported bridge as described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the monitoring method for a cable-supported bridge as described above are implemented.

[0042] In the present application, the vibration signals of each bridge cable of the bridge to be inspected within the current monitoring period are obtained; for any target cable among each of the bridge cables, the target vibration signal is subjected to fast Fourier transform to obtain a target spectrum diagram, wherein the target vibration signal is the vibration signal of the target cable; the main frequency peaks of each amplitude value in the target spectrum diagram are identified, and the frequency orders of each main frequency peak are determined based on the main peak frequency values ​​of each main frequency peak, and the cable force value of the target cable is determined based on each frequency order; based on the cable force values ​​of each cable, the bridge to be inspected is subjected to abnormal detection to obtain a monitoring result.

[0043] Compared with the bridge monitoring method based on a fixed frequency threshold, the present application identifies the main frequency peak in the vibration signal spectrum diagram, determines the frequency order based on the main peak frequency value, and then calculates the cable force value. The main frequency peak usually corresponds to the main vibration mode of the cable. The frequency order obtained based on the main peak frequency value can reflect the actual vibration state of the cable. Therefore, calculating the cable force value based on the frequency order can more accurately calculate the cable force, thereby improving the accuracy of bridge monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flow chart of a first embodiment of a monitoring method for a cable-supported bridge of the present application;

[0047] Figure 2 A flow chart of Embodiment 2 of the monitoring method for a cable-supported bridge of the present application;

[0048] Figure 3 A schematic diagram of a brief flow chart of a monitoring method for a cable-supported bridge provided in one embodiment of the present application;

[0049] Figure 4 This is a schematic diagram of the module structure of a monitoring device for a cable-supported bridge according to an embodiment of the present application;

[0050] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the monitoring method of the cable-supported bridge in the embodiment of the present application.

[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the embodiment of the present application is to obtain the vibration signals of each bridge cable of the bridge to be inspected within the current monitoring period; for any target cable among each of the bridge cables, perform fast Fourier transform on the target vibration signal to obtain a target spectrum diagram, wherein the target vibration signal is the vibration signal of the target cable; identify the main frequency peaks of each amplitude value in the target spectrum diagram, and determine the frequency orders of each of the main frequency peaks based on the main peak frequency values ​​of each of the main frequency peaks, and determine the cable force value of the target cable based on each of the frequency orders; perform abnormal detection on the bridge to be inspected based on the cable force values ​​of each of the cables to obtain a monitoring result.

[0055] In this embodiment, for the convenience of description, the following description is made by taking the monitoring equipment of the cable-supported bridge as the execution subject.

[0056] Cable-supported bridges are widely used in modern bridge engineering due to their advantages such as light structure and large span. In order to ensure the safety and stability of such bridges, regular cable force monitoring is essential. Cable force refers to the tension acting on the bridge cables, which directly reflects the working status of the cables and the overall safety of the bridge. Traditional cable force monitoring methods usually rely on manual on-site measurements or use fixed frequency threshold methods for analysis. These methods are not only inefficient, but also easily affected by environmental noise and other nonlinear factors, resulting in inaccurate cable force monitoring results.

[0057] The present application provides a solution. Compared with the bridge monitoring method based on a fixed frequency threshold, the present application identifies the main frequency peak in the vibration signal spectrum diagram, determines the frequency order based on the main peak frequency value, and then calculates the cable force value. The main frequency peak usually corresponds to the main vibration mode of the cable. The frequency order obtained based on the main peak frequency value can reflect the actual vibration state of the cable. Therefore, calculating the cable force value based on the frequency order can more accurately calculate the cable force, thereby improving the accuracy of bridge monitoring.

[0058] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a monitoring device for a cable-supported bridge, etc. The following takes the monitoring device for a cable-supported bridge as an example to illustrate this embodiment and the following embodiments.

[0059] Based on this, the embodiment of the present application provides a monitoring method for a cable-supported bridge, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a monitoring method for a cable-supported bridge of the present application.

[0060] In this embodiment, the cable-supported bridge monitoring method includes steps S10 to S40:

[0061] Step S10, obtaining vibration signals of each bridge cable of the bridge to be detected in the current monitoring period;

[0062] Bridge cables are important components used to support and transfer loads in bridge structures. They play the role of suspending, supporting and stabilizing the structure of the bridge. The performance of bridge cables directly affects the safety and stability of the bridge. It should be noted that sensors for monitoring vibration signals can be set on bridge cables, such as velocity sensors, displacement sensors, etc., and the vibration data of bridge cables can be collected through sensors.

[0063] In this embodiment, a monitoring cycle is preset, and the monitoring device of the cable-supported bridge monitors the bridge according to the monitoring cycle. In each monitoring cycle, the sensor continuously collects the vibration signal of the cable. When it is determined that the monitoring cycle has been reached, the monitoring device of the cable-supported bridge obtains the vibration signal of each bridge cable of the bridge to be detected in the current monitoring cycle. Hereinafter, any one of the monitoring cycles is referred to as the current monitoring cycle.

[0064] Step S20, for any target cable among the bridge cables, performing fast Fourier transform on the target vibration signal to obtain a target frequency spectrum, wherein the target vibration signal is a vibration signal of the target cable;

[0065] The vibration signal of each cable is subjected to a fast Fourier transform to convert the time domain signal into a frequency domain signal to obtain a spectrum diagram. Hereinafter, any cable in the bridge cable is referred to as a target cable, and the spectrum diagram corresponding to the target cable is referred to as a target spectrum diagram. The fast Fourier transform process is not described in detail here, and the conventional Fourier transform process can be referred to.

[0066] It can be understood that the fast Fourier transform can analyze the components of the signal at different frequencies, which helps to identify the natural frequency and main frequency of the cable and provide a basis for the subsequent calculation process.

[0067] Step S30, identifying the main frequency peaks of the amplitude values ​​in the target frequency spectrum, and determining the frequency orders of the main frequency peaks based on the main peak frequency values ​​of the main frequency peaks, and determining the cable force value of the target cable based on the frequency orders;

[0068] Identify the main frequency in the spectrum diagram, and determine the cable force value according to the frequency order of the main frequency. It should be noted that the frequency order is the multiple relationship between the main frequency and the fundamental frequency. Calculating the cable force value by the frequency order improves the accuracy of the measurement.

[0069] Cable force refers to the amount of tension or tension that a bridge cable bears under specific conditions. It is an important indicator for measuring the working status and performance of the cable. The cable force directly affects the stability and safety of the bridge structure. By comparing the changes in cable force at different time points, the health status of the cable and potential safety risks can be evaluated.

[0070] Step S40: performing abnormality detection on the bridge to be inspected based on the cable force values ​​of each of the cables to obtain a monitoring result.

[0071] The calculated cable force value of each cable is compared with a preset threshold value or historical data to detect whether each cable is abnormal, thereby determining the health status of the bridge. Exemplarily, in one feasible implementation, a cable force threshold value may be preset, and the cable force value of each cable is compared with the cable force threshold value. If the cable force value exceeds the cable force threshold value, it is determined that the bridge is abnormally stressed. If the cable force value does not exceed the cable force threshold value, it is determined that the bridge is normally stressed. Exemplarily, in another feasible implementation, the cable force value of the current monitoring period may be compared with the historical cable force value to detect the cable force value fluctuation value. If the cable force value fluctuation value exceeds the preset fluctuation range, it is determined that the bridge is abnormally stressed. If the cable force value fluctuation value does not exceed the preset range, it is determined that the bridge is normally stressed. The cable force value fluctuation value may be determined by calculating the difference between the cable force value of the current monitoring period and the historical cable force value, and using the difference as the cable force value fluctuation value.

[0072] Compared with the bridge monitoring method based on a fixed frequency threshold, in this embodiment, the main frequency peak in the vibration signal spectrum diagram is identified, and the frequency order is determined based on the main peak frequency value, and then the cable force value is calculated. The main frequency peak usually corresponds to the main vibration mode of the cable. The frequency order obtained based on the main peak frequency value can reflect the actual vibration state of the cable. Therefore, calculating the cable force value based on the frequency order can more accurately calculate the cable force, thereby improving the accuracy of bridge monitoring.

[0073] In a feasible implementation manner, the step S30: the step of determining the frequency order of each of the main frequency peaks based on the main peak frequency value of each of the main frequency peaks, comprises:

[0074] Step S301, taking the frequency value of the frequency main peak with the smallest amplitude among all frequency main peaks as the fundamental frequency;

[0075] Identify all the main frequency peaks in the spectrum graph, and select the frequency value of the main frequency peak with the smallest amplitude as the fundamental frequency (also called the first-order frequency or natural frequency). First, identify the frequency point with a larger amplitude as the main frequency peak in the spectrum graph; sort all the main frequency peaks from small to large in amplitude, and select the main frequency peak with the smallest amplitude; determine the frequency value of the main frequency peak with the smallest amplitude as the fundamental frequency of the cable.

[0076] It can be understood that in the spectrum diagram, the fundamental frequency usually corresponds to the lowest vibration mode of the cable. Determining the fundamental frequency can provide a basis for subsequent frequency order calculations and improve the accuracy of the frequency order.

[0077] Step S302 : for any target main peak among the frequency main peaks, a frequency multiple is obtained by dividing the frequency value of the target main peak by the fundamental frequency, and the frequency multiple is used as the frequency order of the target main peak.

[0078] The frequency order is calculated for each frequency main peak. For example, for any target main peak among the frequency main peaks, the specific calculation process of the frequency order can be: dividing the frequency value of the target main peak by the fundamental frequency value to obtain the frequency multiple; rounding the frequency multiple or taking the integer part as the frequency order of the target main peak.

[0079] By calculating the frequency order, the vibration characteristics of different cables can be standardized and compared, which is convenient for analyzing the health of the cables. In addition, the frequency order can provide additional information about the vibration mode of the cables, which helps to diagnose whether the cables are loose, corroded or have other potential problems, and improve the accuracy of bridge monitoring results.

[0080] In a feasible implementation manner, the step S30: determining the cable force value of the target cable based on each of the frequency orders, comprises:

[0081] Step 303: if the frequency order of the target main peak is the first order, inputting the main peak frequency value of the target main peak into a preset fundamental frequency model to obtain the tension value corresponding to the target main peak;

[0082] The first-order frequency is the fundamental frequency, which is usually closely related to the inherent properties of the structure (such as mass, stiffness, etc.). For any target main peak among the frequency main peaks, if the frequency order of the target main peak is the first order, the calculation process of the target main peak tension value can be: input the main peak frequency value into the preset fundamental frequency model, and the model outputs the tension value corresponding to the target main peak. The fundamental frequency model can be:

[0083]

[0084] Among them, T is the tension value, f1 is the main peak frequency value, L is the cable length, ρ is the cable density, and A is the cable cross-sectional area.

[0085] Step S304, if the frequency order of the target main peak is not the first order, inputting a preset high-order frequency model based on the main peak frequency value of the target main peak to obtain a tension value corresponding to the target main peak;

[0086] When the frequency order of the target main peak is not the first order, the main peak frequency value is input into a preset high-order frequency model, and the model outputs the tension value corresponding to the target main peak, wherein the high-order frequency model can be:

[0087]

[0088] Where, fn is the nth natural frequency of the cable, L is the length of the cable, n is the frequency order, and EI is the bending stiffness of the cable.

[0089] Step S305, calculating an average value of the tension values ​​of the main frequency peaks, and using the average value as the cable force value of the target cable.

[0090] The final tension value of the target cable is obtained by combining the tension values ​​of the main peaks of each frequency. Specifically, the average value can be calculated to reduce the influence of the single main peak estimation error on the final result. It can be understood that by averaging the tension values ​​corresponding to each main peak, the robustness and accuracy of the tension estimation can be improved. For the case of multi-peak vibration signals, all available information can be fully utilized to optimize the tension estimation result.

[0091] In a feasible implementation manner, the step S40: the step of performing abnormality detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result, comprises:

[0092] Step S401, traversing each of the cable force values, and determining the difference between the cable force value and the historical cable force value as the cable force value fluctuation value, wherein the historical cable force value is the cable force value in the adjacent historical period of the cable force value;

[0093] It should be noted that the historical cable force value refers to the cable force value in the historical monitoring cycle before the monitoring cycle of the cable force value and adjacent to the monitoring cycle of the cable force value.

[0094] Traverse all monitored cable force values, and compare each cable force value with its cable force value in the adjacent historical period, calculate the difference between them, that is, the cable force fluctuation value, assuming that the cable force value of the current period is F_current, and the cable force value of the adjacent historical period is F_history, then the cable force fluctuation value ΔF = F_current - F_history. It can be understood that by calculating the cable force fluctuation value, the change of the cable force over time can be quantified, providing a basis for the subsequent judgment of the stress state of the bridge.

[0095] Step S402: if the fluctuation values ​​of the cable forces do not exceed the preset fluctuation value range, it is determined that the stress of the bridge to be inspected is normal;

[0096] The fluctuation value range is preset. The fluctuation value range refers to the interval between the maximum and minimum values ​​of the cable force fluctuation allowed. The fluctuation value range can be set according to the characteristics of the bridge structure and the monitoring requirements, or it can be determined according to the fluctuation values ​​monitored historically. There is no restriction here. If all cable force fluctuation values ​​are within the preset range, it is considered that the cable forces of the bridge are normal, that is, it is determined that the bridge is under normal stress.

[0097] Step S403, if there is an abnormal fluctuation value that exceeds the fluctuation value range among the cable force value fluctuation values, determining the proportion of the abnormal fluctuation value in the cable force value fluctuation values;

[0098] If there are cable force fluctuation values ​​that exceed the preset range, the quantitative proportion of these abnormal fluctuation values ​​in all cable force fluctuation values ​​is determined. The quantitative proportion refers to the proportion of abnormal fluctuation values ​​in all cable force fluctuation values. The proportion reflects the degree of abnormal change in the cable force of the bridge. If the quantitative proportion is high, it may mean that there are multiple safety hazards in the bridge structure. It can be understood that by calculating the quantitative proportion of abnormal fluctuation values, the abnormal degree of the overall stress state of the bridge structure can be evaluated, providing a basis for subsequent judgment of whether the bridge is abnormally stressed.

[0099] Step S404, if the number ratio exceeds a preset ratio threshold, determining that the stress of the bridge to be detected is abnormal;

[0100] It should be noted that the proportion threshold refers to the critical value of the proportion of abnormal fluctuation values ​​used to determine whether the bridge stress is normal. It can be set according to the characteristics of the bridge structure and monitoring requirements, and is not limited here. If the proportion of the number of abnormal fluctuation values ​​exceeds the preset proportion threshold, it is determined whether the bridge stress is abnormal.

[0101] Step S405: If the number ratio does not exceed the ratio threshold, it is determined that the stress on the bridge to be inspected is normal.

[0102] If the proportion of abnormal fluctuation values ​​does not exceed the preset proportion threshold, it is determined that the abnormal degree of bridge stress is low, and the bridge stress is determined to be normal. It can be understood that by determining the stress state of the bridge, the safety hazards of the bridge structure can be discovered in time, providing a scientific basis for the maintenance and management of the bridge, and ensuring the safe operation of the bridge.

[0103] Compared with the bridge monitoring method based on a fixed frequency threshold, in this embodiment, the main frequency peak in the vibration signal spectrum diagram is identified, and the frequency order is determined based on the main peak frequency value, and then the cable force value is calculated. The main frequency peak usually corresponds to the main vibration mode of the cable. The frequency order obtained based on the main peak frequency value can reflect the actual vibration state of the cable. Therefore, calculating the cable force value based on the frequency order can more accurately calculate the cable force, thereby improving the accuracy of bridge monitoring.

[0104] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The step S20: performing fast Fourier transform on the target vibration signal to obtain a target spectrum diagram comprises:

[0105] Step S201, performing noise reduction processing on the target vibration signal to obtain a noise reduction signal;

[0106] In order to reduce the noise component in the target vibration signal, thereby improving the signal-to-noise ratio of the signal and providing a more accurate data basis for subsequent signal analysis, the vibration signal is subjected to noise reduction processing. The specific process of noise reduction processing is not limited here and can be set according to actual needs. For example, wavelet transform noise reduction, filter noise reduction (such as bandpass filter, low-pass filter, high-pass filter, etc.) and noise reduction methods based on deep learning can be used.

[0107] Step S202: multiplying the noise reduction signal by a preset window function to obtain a windowed signal, and performing a fast Fourier transform on the windowed signal to obtain a target spectrum.

[0108] The signal after noise reduction is subjected to windowing processing and subjected to a fast Fourier transform (FFT) to obtain a spectrum diagram of the signal. It can be understood that the windowing processing is to reduce the spectrum leakage phenomenon in the fast Fourier transform process. The specific process of the windowing processing can be: multiplying the preset window function with the signal after noise reduction to obtain a windowed signal, wherein the preset window function can be a rectangular window, a Hanning window, a Hamming window, etc., which is not limited here and can be set according to actual needs.

[0109] It can be understood that windowing can significantly reduce the spectrum leakage phenomenon in the fast Fourier transform process, making the spectrum diagram more accurate, thereby making the subsequent spectrum diagram more accurate, improving the accuracy of the frequency order, thereby improving the accuracy of the cable force value and the accuracy of bridge anomaly detection.

[0110] In one feasible implementation, the step S201: performing noise reduction processing on the target vibration signal to obtain a noise reduction signal, comprises:

[0111] Step S2011, using a preset deep neural network to perform noise elimination processing on the target vibration signal to obtain a noise reduction signal, wherein the deep neural network is trained using the vibration signal as input data and the vibration signal after noise elimination as a label.

[0112] A deep neural network is trained with historical vibration signals as input data and historical vibration signals after noise elimination as labels. The vibration signal is processed by the trained deep neural network and a noise-reduced signal is output. The structure and training process of the deep neural network are not limited here and can be set according to actual needs.

[0113] It is understandable that through the training and learning of deep neural networks, high-precision noise reduction processing can be achieved, making the output noise reduction signal purer, providing strong support for subsequent signal analysis and processing. In addition, the structure and parameters of deep neural networks can be adjusted and optimized according to specific problems to meet different noise reduction requirements.

[0114] In a feasible implementation manner, the deep neural network includes an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer, and the step S2011: the step of performing noise elimination processing on the target vibration signal using a preset deep neural network to obtain a noise reduction signal includes:

[0115] Step S20111, inputting the target vibration signal into the encoder for processing to obtain a first processing result;

[0116] The preset deep neural network may include an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer. Among them, the encoder layer is used to extract data features and downsample the input target vibration signal; the recurrent neural network module is used to process the results output by the encoder layer, and the results of processing the target vibration signal of the previous frame will be used in the processing process, so as to use the information of the historical frame to eliminate noise in the current frame; the attention mechanism module is used to focus on the key signals and key frequency bands in the target vibration signal; the decoder is used to upsample the results output by the recurrent neural network; the fully connected layer is used to process the results output by the decoder and output the noise-reduced signal after eliminating noise. The deep neural network can be trained in advance through a training data set, and the training method can adopt a conventional neural network training method, which will not be repeated here.

[0117] Step S20112, inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the vibration signal;

[0118] When performing noise elimination, the received target vibration signal is processed in a time sequence. In this embodiment, the previous frame signal of the currently processed target vibration signal is called the previous frame signal, and the processing result of the encoder on the previous frame signal is called the previous frame processing result.

[0119] In this embodiment, the first processing result is input into the recurrent neural network module for processing to obtain the second processing result. It can be understood that when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result using the recurrent neural network module.

[0120] Step S20113, inputting the second processing result into the decoder for processing to obtain a third processing result;

[0121] The role of the decoder is to convert the output of the recurrent neural network module (i.e., the second processing result) back into a form similar to the input signal (i.e., the third processing result). By working in collaboration with the encoder, the decoder can learn how to extract useful information from the input signal and remove noise.

[0122] Step S20114, inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0123] The attention mechanism module is used to enhance the model's attention to the important parts of the input signal while suppressing the unimportant parts. Here, it combines the output of the encoder and the output of the decoder to further optimize the denoising effect.

[0124] In a specific implementation, an attention weight matrix representing the degree of attention to the information in the first processing result may be calculated based on the first processing result and the third processing result, and the first processing result may be weighted by the attention weight matrix to obtain the fourth processing result. The attention mechanism module performs weighted processing on the first processing result to achieve weight allocation of features in the first processing result, thereby filtering important information in the first processing result and enhancing important information, so that the deep neural network pays attention to key information during the decoding process, thereby improving the accuracy of noise elimination.

[0125] Step S20115, connecting the third processing result and the fourth processing result, and inputting the connected result into the fully connected layer for processing to obtain a noise reduction signal.

[0126] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a noise reduction signal.

[0127] It can be understood that by introducing the attention mechanism module to perform weighted processing on the first processing result, weight allocation is achieved for the features in the first processing result, thereby screening out important information in the first processing result and enhancing the important information, so that the deep neural network focuses on key information during the decoding process, thereby improving the accuracy of noise elimination.

[0128] Compared with the bridge monitoring method based on a fixed frequency threshold, in this embodiment, the main frequency peak in the vibration signal spectrum diagram is identified, and the frequency order is determined based on the main peak frequency value, and then the cable force value is calculated. The main frequency peak usually corresponds to the main vibration mode of the cable. The frequency order obtained based on the main peak frequency value can reflect the actual vibration state of the cable. Therefore, calculating the cable force value based on the frequency order can more accurately calculate the cable force, thereby improving the accuracy of bridge monitoring.

[0129] For example, in order to help understand the implementation process of the cable-supported bridge monitoring method obtained by combining this embodiment with the above embodiments, please refer to Figure 3 , Figure 3 A brief schematic diagram of a monitoring method for a cable-supported bridge is provided, specifically:

[0130] Acquire vibration signals, and acquire vibration signals of each bridge cable of the bridge to be detected in the current monitoring period;

[0131] Frequency domain conversion: for any target cable among the bridge cables, the target vibration signal is subjected to denoising to obtain a denoised signal, a windowed signal is obtained by multiplying the denoised signal with a preset window function, and a fast Fourier transform is performed on the windowed signal to obtain a target spectrum diagram. Among them, the process of obtaining the noise reduction signal can be: using a preset deep neural network to perform noise elimination processing on the target vibration signal to obtain the noise reduction signal, the deep neural network includes an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer, the target vibration signal is input into the encoder for processing to obtain a first processing result; the first processing result is input into the recurrent neural network module for processing to obtain a second processing result, wherein, when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result is the result obtained by the encoder processing the previous frame signal of the vibration signal; the second processing result is input into the decoder for processing to obtain a third processing result; the first processing result and the third processing result are input into the attention mechanism module for processing to obtain a fourth processing result; the third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain the noise reduction signal.

[0132] Determine the frequency order, identify the frequency main peaks of each amplitude value in the target spectrum graph, take the frequency value of the frequency main peak with the smallest amplitude among the frequency main peaks as the fundamental frequency, for any target main peak among the frequency main peaks, divide the frequency value of the target main peak by the fundamental frequency to obtain the frequency multiple, and take the frequency multiple as the frequency order of the target main peak.

[0133] The cable force value is determined based on the frequency order. If the frequency order of the target main peak is the first order, the main peak frequency value of the target main peak is input into a preset fundamental frequency model to obtain the tension value corresponding to the target main peak; if the frequency order of the target main peak is not the first order, a preset high-order frequency model is input based on the main peak frequency value of the target main peak to obtain the tension value corresponding to the target main peak; the average value of the tension values ​​of each of the frequency main peaks is calculated, and the average value is used as the cable force value of the target cable.

[0134] Abnormality detection: Based on the cable force values ​​of each cable, abnormality detection is performed on the bridge to be detected to obtain a monitoring result.

[0135] In the cable force monitoring of the cable-supported bridge structure of the cable-supported bridge, the calculation of the cable force first needs to correctly determine the order corresponding to each order of natural frequency. When the vibration is weak and the interference is obvious, the order of each frequency is very difficult to judge. In this embodiment, by determining several maximum main peaks on the spectrum diagram corresponding to the cable vibration signal, the precise frequency of each main peak is calculated by scale-space theory, and then the frequency order of each main peak is determined based on the frequency value of each main peak. In addition, in the early stage of bridge monitoring, each cable can also be manually measured to obtain the initial cable force value, and the cable force value is used as a reference threshold to detect abnormal cable force values.

[0136] This application also provides a monitoring device for a cable-supported bridge, please refer to Figure 4 , the monitoring device for the cable-supported bridge comprises:

[0137] An acquisition module 10 is used to acquire vibration signals of each bridge cable of the bridge to be detected in a current monitoring period;

[0138] The processing module 20 is used for performing a fast Fourier transform on a target vibration signal of any target cable among the bridge cables to obtain a target spectrum diagram, wherein the target vibration signal is a vibration signal of the target cable;

[0139] An identification module 30, for identifying the main frequency peaks of the amplitude values ​​in the target frequency spectrum, and determining the frequency orders of the main frequency peaks based on the main peak frequency values ​​of the main frequency peaks, and determining the cable force value of the target cable based on the frequency orders;

[0140] The detection module 40 is used to perform abnormal detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result.

[0141] Optionally, the processing module 20 is used to:

[0142] Performing noise reduction processing on the target vibration signal to obtain a noise reduction signal;

[0143] A windowed signal is obtained by multiplying a preset window function with the noise reduction signal, and a fast Fourier transform is performed on the windowed signal to obtain a target spectrum diagram.

[0144] Optionally, the processing module 20 is used to:

[0145] The target vibration signal is subjected to noise elimination processing using a preset deep neural network to obtain a noise reduction signal, wherein the deep neural network is trained using the vibration signal as input data and the vibration signal after noise elimination as a label.

[0146] Optionally, the deep neural network includes an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer, and the processing module 20 is used to:

[0147] Inputting the target vibration signal into the encoder for processing to obtain a first processing result;

[0148] Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the vibration signal;

[0149] Inputting the second processing result into the decoder for processing to obtain a third processing result;

[0150] Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0151] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a noise reduction signal.

[0152] Optionally, the identification module 30 is used to:

[0153] The frequency value of the frequency main peak with the smallest amplitude among all frequency main peaks is taken as the fundamental frequency;

[0154] For any target main peak among the frequency main peaks, a frequency multiple is obtained by dividing the frequency value of the target main peak by the base frequency, and the frequency multiple is used as the frequency order of the target main peak.

[0155] Optionally, the identification module 30 is used to:

[0156] If the frequency order of the target main peak is the first order, the main peak frequency value of the target main peak is input into a preset fundamental frequency model to obtain the tension value corresponding to the target main peak;

[0157] If the frequency order of the target main peak is not the first order, a preset high-order frequency model is input based on the main peak frequency value of the target main peak to obtain a tension value corresponding to the target main peak;

[0158] The average value of the tension values ​​of the main peaks of the frequencies is calculated, and the average value is used as the cable tension value of the target cable.

[0159] Optionally, the detection module 40 is used to:

[0160] Traversing each of the cable force values, and determining the difference between the cable force value and the historical cable force value as the cable force value fluctuation value, wherein the historical cable force value is the cable force value in the adjacent historical period of the cable force value;

[0161] If the fluctuation values ​​of the cable force values ​​do not exceed the preset fluctuation value range, it is determined that the stress of the bridge to be inspected is normal;

[0162] If there is an abnormal fluctuation value that exceeds the fluctuation value range among the cable force value fluctuation values, then determining the proportion of the abnormal fluctuation value in the number of the cable force value fluctuation values;

[0163] If the proportion of the number exceeds a preset proportion threshold, it is determined that the stress of the bridge to be detected is abnormal;

[0164] If the number ratio does not exceed the ratio threshold, it is determined that the stress on the bridge to be inspected is normal.

[0165] The monitoring device for a cable-supported bridge provided by the present application adopts the monitoring method for a cable-supported bridge in the above-mentioned embodiment, and can solve the technical problem that it is difficult to identify the order of each frequency of cable vibration in monitoring bridge cables, thereby resulting in low accuracy in cable force calculation. Compared with the prior art, the beneficial effects of the monitoring device for a cable-supported bridge provided by the present application are the same as the beneficial effects of the monitoring method for a cable-supported bridge provided by the above-mentioned embodiment, and other technical features of the monitoring device for a cable-supported bridge are the same as the features disclosed in the above-mentioned embodiment method, which will not be described in detail here.

[0166] The present application provides a monitoring device for a cable-supported bridge, the monitoring device for a cable-supported bridge comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the monitoring method for the cable-supported bridge in the above-mentioned embodiments.

[0167] Reference below Figure 5 , which shows a schematic diagram of the structure of a monitoring device for a cable-supported bridge suitable for implementing an embodiment of the present application. The monitoring device for a cable-supported bridge in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The monitoring device for the cable-supported bridge shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0168] like Figure 5 As shown, the monitoring device for a cable-supported bridge may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In RAM 1004, various programs and data required for the operation of the monitoring device for a cable-supported bridge are also stored. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the monitoring device of the cable-supported bridge to communicate with other devices wirelessly or by wire to exchange data. Although the monitoring device of the cable-supported bridge with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0169] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0170] The monitoring device for a cable-supported bridge provided by the present application adopts the monitoring method for a cable-supported bridge in the above-mentioned embodiment, which can solve the technical problem that it is difficult to identify the order of each frequency of cable vibration in monitoring bridge cables, thereby resulting in low accuracy in cable force calculation. Compared with the prior art, the beneficial effects of the monitoring device for a cable-supported bridge provided by the present application are the same as the beneficial effects of the monitoring method for a cable-supported bridge provided by the above-mentioned embodiment, and other technical features of the monitoring device for a cable-supported bridge are the same as the features disclosed in the method of the previous embodiment, which will not be described in detail here.

[0171] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0172] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0173] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the monitoring method for a cable-supported bridge in the above-mentioned embodiment.

[0174] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0175] The computer-readable storage medium may be included in the monitoring device for the cable-supported bridge; or may exist independently without being assembled into the monitoring device for the cable-supported bridge.

[0176] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the monitoring equipment of the cable-supported bridge, the monitoring equipment of the cable-supported bridge: obtains the vibration signals of each bridge cable of the bridge to be detected within the current monitoring period; for any target cable among each of the bridge cables, performs fast Fourier transform on the target vibration signal to obtain a target spectrum diagram, wherein the target vibration signal is the vibration signal of the target cable; identifies the frequency main peaks of each amplitude value in the target spectrum diagram, and determines the frequency orders of each frequency main peak based on the main peak frequency values ​​of each frequency main peak, and determines the cable force value of the target cable based on each frequency order; performs abnormal detection on the bridge to be detected based on the cable force values ​​of each cable to obtain a monitoring result.

[0177] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0178] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0179] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0180] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned cable-supported bridge monitoring method, and can solve the technical problem that the order of each frequency of cable vibration is difficult to identify in the monitoring of bridge cables, thereby resulting in low accuracy in cable force calculation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the cable-supported bridge monitoring method provided by the above-mentioned embodiment, and will not be repeated here.

[0181] The present application also provides a computer program product, including a computer program, which implements the steps of the monitoring method for a cable-supported bridge as described above when the computer program is executed by a processor.

[0182] The computer program product provided by the present application can solve the technical problem that it is difficult to identify the order of each frequency of cable vibration in monitoring bridge cables, thereby resulting in low accuracy in cable force calculation. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the monitoring method for cable-supported bridges provided in the above-mentioned embodiment, and will not be described in detail here.

[0183] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A monitoring method for a cable-supported bridge, characterized in that: The monitoring method of the cable-supported bridge comprises: Obtaining vibration signals of each bridge cable of the bridge to be inspected in the current monitoring period; For any target cable among the bridge cables, a target vibration signal is subjected to noise elimination processing using a preset deep neural network to obtain a noise reduction signal, and the noise reduction signal is subjected to a fast Fourier transform to obtain a target spectrum diagram, wherein the target vibration signal is a vibration signal of the target cable; Identify the main frequency peaks of each amplitude value in the target frequency spectrum, and determine the frequency orders of each main frequency peak based on the main peak frequency values ​​of each main frequency peak, input the main peak frequency values ​​of each main frequency peak into the model corresponding to the frequency order of the main frequency peak to obtain the tension value of each main frequency peak, and determine the average value of the tension value of each main frequency peak as the cable force value of the target cable, wherein when the frequency order is the first order, the corresponding model is the fundamental frequency model, and when the frequency order is not the first order, the corresponding model is a high-order frequency model; Wherein, the fundamental frequency model is: , where T is the tension value, f1 is the main peak frequency value, L is the cable length of the bridge cable, ρ is the cable density of the bridge cable, and A is the cable cross-sectional area of ​​the bridge cable; the high-order frequency model is: , where f n is the nth order natural frequency of the bridge cable, L is the cable length of the bridge cable, n is the frequency order, EI is the bending stiffness of the inclined cable of the bridge cable, W is the cable weight per unit length of the bridge cable, and g is the free fall acceleration; Traversing each of the cable tension values, determining the difference between the cable tension value and the historical cable tension value as the cable tension value fluctuation value, if there is an abnormal fluctuation value exceeding the fluctuation value range in each of the cable tension value fluctuation values ​​and the number of the abnormal fluctuation values ​​in each of the cable tension value fluctuation values ​​exceeds a preset proportion threshold, then determining that the stress of the bridge to be detected is abnormal, wherein the historical cable tension value is the cable tension value in the adjacent historical period of the cable tension value; If the number ratio does not exceed the ratio threshold or the abnormal fluctuation value does not exist in the cable force fluctuation values, it is determined that the stress of the bridge to be inspected is normal; Wherein, the step of determining the frequency order of each of the main frequency peaks based on the main peak frequency value of each of the main frequency peaks comprises: The frequency value of the frequency main peak with the smallest amplitude among all frequency main peaks is taken as the fundamental frequency; For any target main peak among the frequency main peaks, a frequency multiple is obtained by dividing the frequency value of the target main peak by the base frequency, and the frequency multiple is used as the frequency order of the target main peak.

2. The cable-supported bridge monitoring method according to claim 1, characterized in that: The step of performing fast Fourier transform on the noise reduction signal to obtain a target spectrum diagram comprises: A windowed signal is obtained by multiplying a preset window function with the noise reduction signal, and a fast Fourier transform is performed on the windowed signal to obtain a target spectrum diagram.

3. The cable-supported bridge monitoring method according to claim 1, characterized in that: The step of inputting the main peak frequency values ​​of each of the main frequency peaks into the model corresponding to the frequency order of the main frequency peak to obtain the tension value of the main frequency peak comprises: If the frequency order of the target main peak is the first order, the main peak frequency value of the target main peak is input into a preset fundamental frequency model to obtain the tension value corresponding to the target main peak; If the frequency order of the target main peak is not the first order, a preset high-order frequency model is input based on the main peak frequency value of the target main peak to obtain the tension value corresponding to the target main peak.

4. The cable-supported bridge monitoring method according to claim 3, characterized in that: The deep neural network includes an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer. The step of performing noise elimination processing on the target vibration signal using a preset deep neural network to obtain a noise reduction signal includes: Inputting the target vibration signal into the encoder for processing to obtain a first processing result; Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the vibration signal; Inputting the second processing result into the decoder for processing to obtain a third processing result; Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result; The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a noise reduction signal.

5. A monitoring device for a cable-supported bridge, characterized in that: The monitoring device of the cable-supported bridge comprises: An acquisition module, used to acquire vibration signals of each bridge cable of the bridge to be detected in a current monitoring period; A processing module is used for, for any target cable among the bridge cables, performing noise elimination processing on a target vibration signal using a preset deep neural network to obtain a noise reduction signal, and performing fast Fourier transform on the noise reduction signal to obtain a target spectrum diagram, wherein the target vibration signal is a vibration signal of the target cable; An identification module is used to identify the main frequency peaks of each amplitude value in the target frequency spectrum, and determine the frequency orders of each main frequency peak based on the main peak frequency values ​​of each main frequency peak, respectively input the main peak frequency values ​​of each main frequency peak into the tension values ​​of each main frequency peak of the model corresponding to the frequency order of the main frequency peak, and determine the average value of the tension values ​​of each main frequency peak as the cable force value of the target cable, wherein when the frequency order is the first order, the corresponding model is the fundamental frequency model, and when the frequency order is not the first order, the corresponding model is a high-order frequency model; Wherein, the fundamental frequency model is: , where T is the tension value, f1 is the main peak frequency value, L is the cable length of the bridge cable, ρ is the cable density of the bridge cable, and A is the cable cross-sectional area of ​​the bridge cable; the high-order frequency model is: , where f n is the nth order natural frequency of the bridge cable, L is the cable length of the bridge cable, n is the frequency order, EI is the bending stiffness of the inclined cable of the bridge cable, W is the cable weight per unit length of the bridge cable, and g is the free fall acceleration; A detection module is used to traverse each of the cable tension values, determine the difference between the cable tension value and the historical cable tension value as the cable tension value fluctuation value, and determine that the stress of the bridge to be detected is abnormal if there is an abnormal fluctuation value exceeding the fluctuation value range in each of the cable tension value fluctuation values ​​and the number of the abnormal fluctuation values ​​in each of the cable tension value fluctuation values ​​exceeds a preset proportion threshold, wherein the historical cable tension value is the cable tension value in the adjacent historical period of the cable tension value; The detection module is further configured to determine that the stress of the bridge to be detected is normal if the number ratio does not exceed the ratio threshold or the abnormal fluctuation value does not exist in the fluctuation values ​​of the cable forces; The identification module is further configured to use the frequency value of the frequency main peak with the smallest amplitude among the frequency main peaks as the fundamental frequency; The identification module is further configured to obtain a frequency multiple of any target main peak among the frequency main peaks by dividing the frequency value of the target main peak by the fundamental frequency, and use the frequency multiple as the frequency order of the target main peak.

6. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the cable-supported bridge monitoring method according to any one of claims 1 to 4 are implemented.

7. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the monitoring method for a cable-supported bridge according to any one of claims 1 to 4 are implemented.

Images