Bridge structural state monitoring system and method

Abstract

The invention discloses a bridge structural state monitoring system and method, and belongs to the technical field of wireless communication, and the monitoring system employs a radio frequency signal receiving and transmitting end to broadcast an environment radio frequency signal to a data collection end for energy supply, so as to enable the data collection end to obtain a target transmission signal meeting the passive communication requirement. Loading the target sending signal to the environment radio frequency signal and scattering the target sending signal; and the radio frequency signal receiving and transmitting end demodulates the received superposed signal to obtain a target sending signal, and transmits the target sending signal to the data processing end for structural state identification of the bridge to be monitored. According to the invention, data transmission can be realized without depending on an external power supply, and energy collection and data transmission are carried out by using an environment radio frequency signal, so that the data acquisition end can operate for a long time in a low-energy-consumption environment; and the reflection efficiency of the next monitoring period is adaptively adjusted according to the actual noise level and the actual signal strength of the superposed signal of the current period, so that stable and reliable data transmission under the conditions of low energy and high noise is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of wireless communications, and more specifically, relates to a monitoring system and method for the structural status of a bridge. Background Art

[0002] With the rapid development of modern society, bridges, as important infrastructure, have a direct impact on the normal operation of transportation and the safety of people's lives and property. Traditional bridge monitoring methods mainly rely on regular manual inspections, which is not only time-consuming and labor-intensive, but also difficult to monitor in real time and quickly respond to subtle changes in bridge structures, and cannot predict and prevent the occurrence of structural damage in a timely manner.

[0003] At present, bridge monitoring systems based on image acquisition technology have gradually been applied in practical projects. These systems obtain dynamic and static information of bridges in real time through various image acquisition units installed on the bridge structure, such as acceleration image acquisition units and displacement image acquisition units. Although these methods improve the accuracy and efficiency of monitoring, they often require external power supply support due to the energy consumption of image acquisition units and data transmission equipment.

[0004] Therefore, developing a system that can achieve low-power bridge structure health monitoring has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a monitoring system and method for the structural status of a bridge, which aims to solve the technical problem of high system energy consumption caused by image acquisition units and data transmission equipment in the existing bridge monitoring system.

[0006] To achieve the above object, according to one aspect of the present invention, a monitoring system for the structural state of a bridge is provided, comprising:

[0007] The data acquisition end is deployed at multiple preset positions of the bridge to be monitored and powered by the received environmental radio frequency signal, and is used to collect analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring cycle, and convert the analog image data into a target transmission signal that meets the requirements of passive communication, and then load the target transmission signal into the environmental radio frequency signal to obtain a superimposed signal and scatter it out;

[0008] A radio frequency signal transceiver, which is in communication with the data acquisition end, is used to broadcast the ambient radio frequency signal with the transmission parameters of the current monitoring period, and optimize the transmission parameters of the next monitoring period according to the actual signal strength and the actual noise level corresponding to the superimposed signal; and is also used to receive the superimposed signal and demodulate it using the ambient radio frequency signal to obtain the target transmission signal, and then send the target transmission signal out;

[0009] The data processing end is communicatively connected to the radio frequency signal transceiver end, and is used to receive the target transmission signal sent by the radio frequency signal transceiver end, and use the trained deep neural network to detect the target transmission signal to obtain the identification result corresponding to the structural state of the bridge to be monitored.

[0010] In one embodiment, the data acquisition terminal includes:

[0011] An image acquisition module, used for acquiring a surface image of the bridge to be monitored to generate simulated image data;

[0012] An analog-to-digital conversion module, used for converting the analog image data into digital image data by differential encoding;

[0013] A data processing module, used for converting the digital image data into the target transmission signal in the form of a binary data stream;

[0014] The passive communication module is used to collect energy from the ambient radio frequency signal broadcast by the radio frequency signal transceiver to provide energy, and to carry the target transmission signal on the ambient radio frequency signal to obtain the superimposed signal, and to scatter it in groups.

[0015] In one of the embodiments, the passive communication module has an adaptive adjustment function to automatically adjust the scattering parameters according to the channel level and actual noise level of the ambient radio frequency signal.

[0016] In one of the embodiments, the analog-to-digital conversion module is used to group the analog image data in a multi-channel multiplexing manner to achieve high-precision analog-to-digital conversion through differential encoding to obtain the digital image data.

[0017] In one of the embodiments, the analog-to-digital conversion unit is used to perform differential processing on the analog image data, calculate the difference between each pixel and its adjacent pixels; then map the pixel difference to a preset range and superimpose an offset to make it non-negative; and encode the non-negative difference to obtain the digital image data.

[0018] In one embodiment, the radio frequency signal transceiver includes:

[0019] A transmitting module, used for generating and transmitting the ambient radio frequency signal;

[0020] A receiving module, used for receiving the superposition signal scattered back by the passive communication module;

[0021] An adaptive adjustment module, connected to the transmitting module and the transmitting module; used to compare the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with a preset threshold to determine the transmission parameters of the next monitoring cycle, the transmission parameters including the transmission power, the transmission frequency and the rate; and also used to feed back the transmission parameters of the next monitoring cycle to the transmitting module so that it synchronizes the transmission parameters of the next monitoring cycle with the receiving module;

[0022] The radio frequency signal processing module is connected to the receiving module and is used to demodulate the superimposed signal using the environmental radio frequency signal to obtain the target transmission signal.

[0023] In one embodiment, the adaptive adjustment module compares the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with a preset threshold to determine the transmission parameters of the next monitoring period, including:

[0024] When the actual signal strength of the superimposed signal is lower than the signal strength threshold, the transmit power of the current monitoring period is increased as the transmit power of the next monitoring period, and the increased power value is the difference between the actual signal strength and the signal strength threshold multiplied by the first adjustment coefficient;

[0025] When the actual noise intensity in the actual noise level exceeds the noise tolerance or the signal-to-noise ratio is insufficient, the transmission rate of the current monitoring cycle is reduced as the transmission power of the next monitoring cycle, and the reduced rate value is the difference between the actual noise intensity and the noise tolerance multiplied by the second adjustment coefficient.

[0026] In one embodiment, the data processing end includes:

[0027] An image processing module, configured to obtain edge features by calculating the gradient and direction of pixels in the target transmitted signal, and to obtain texture features by analyzing pixels in the target transmitted signal using a gray level co-occurrence matrix technique;

[0028] The risk assessment module is connected to the image processing module and is used to input the edge features and the texture features into a trained deep learning model to obtain an identification result corresponding to the structural state of the bridge to be monitored.

[0029] In one of the embodiments, the data processing end includes: an alarm prompt module, connected to the risk assessment module, for generating an alarm signal when the identification result corresponding to the structural state of the bridge to be monitored indicates the existence of structural defects.

[0030] According to another aspect of the present invention, a method for monitoring the structural state of a bridge is provided, wherein the monitoring system applied to the structural state of the bridge comprises:

[0031] Broadcasting the ambient radio frequency signal using the radio frequency signal transceiver with the transmission parameters of the current monitoring period;

[0032] The data acquisition terminal uses the received ambient radio frequency signal for energy supply, collects analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring period, converts the analog image data into a target transmission signal that meets the requirements of passive communication, and then loads the target transmission signal into the ambient radio frequency signal to obtain a superimposed signal and scatters it out;

[0033] Receive the superimposed signal by using the radio frequency signal transceiver, optimize the transmission parameters of the next monitoring cycle according to the actual signal strength and the actual noise level corresponding to the superimposed signal; receive the superimposed signal and demodulate it by using the environmental radio frequency signal to obtain the target transmission signal, and then send out the target transmission signal;

[0034] The target transmission signal sent by the radio frequency signal transceiver is received by the data processing end, and the target transmission signal is detected by the trained deep neural network to obtain the recognition result corresponding to the structural state of the bridge to be monitored.

[0035] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0036] (1) The present invention provides a monitoring system for the structural status of a bridge, comprising a data acquisition terminal, a radio frequency signal transceiver terminal and a data processing terminal connected in sequence; the radio frequency signal transceiver terminal broadcasts the environmental radio frequency signal with the transmission parameters of the current monitoring cycle to power the data acquisition terminal, so that it obtains a target transmission signal that meets the requirements of passive communication, and loads it onto the environmental radio frequency signal and scatters it out; the radio frequency signal transceiver terminal demodulates the received superposition signal to obtain the target transmission signal and transmits it to the data processing terminal for structural status identification of the bridge to be monitored. The present invention can realize data transmission without relying on an external power supply, and uses the environmental radio frequency signal for energy collection and data transmission, so that the data acquisition terminal can operate for a long time in a low-energy consumption environment. The radio frequency signal transceiver terminal adaptively adjusts the reflection efficiency of the next monitoring cycle according to the actual noise level and actual signal strength of the superposition signal of the current cycle, ensuring stable and reliable data transmission under low energy and high noise conditions.

[0037] (2) The data acquisition end described in this scheme includes: an image acquisition module, an analog-to-digital conversion module, a data processing module and a passive communication module connected in sequence. It uses environmental radio frequency signals for power supply, has a simple structure and low energy consumption, and is suitable for application scenarios for long-term monitoring of the structural status of bridges.

[0038] (3) The passive communication module described in this solution has an adaptive adjustment function, which automatically adjusts the scattering parameters according to the channel level and actual noise level of the ambient RF signal, thereby improving the communication stability and sustainability of the monitoring system for the structural status of the bridge.

[0039] (4) This solution utilizes multi-channel multiplexing to group the analog image data for high-precision analog-to-digital conversion, which can improve the analog-to-digital conversion rate and further improve the operating efficiency of the entire bridge structural status monitoring system.

[0040] (5) The analog-to-digital conversion unit described in this solution is used to perform differential encoding on the analog image data to achieve analog-to-digital conversion, with high accuracy and low computational complexity.

[0041] (6) In this solution, the adaptive adjustment module in the RF signal transceiver compares the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with the preset threshold to determine the transmission parameters of the next monitoring cycle, and feeds back the transmission parameters of the next monitoring cycle to the transmitting module so that it synchronizes the transmission parameters of the next monitoring cycle with the receiving module; the reflection efficiency of the next monitoring cycle can be adaptively feedback-adjusted and synchronized with the transmitting module and the receiving module to ensure that the monitoring system of the structural status of the bridge is in a stable and healthy communication environment.

[0042] (7) This scheme provides a complete strategy on how to adjust the transmission parameters of the next monitoring period according to the actual signal strength and noise level of the superimposed signal of the current detection period, with low computational complexity and high adjustment efficiency.

[0043] (8) The edge features and texture features of the data processing end described in this solution can well reflect the structural defects of the bridge to be monitored. By integrating advanced image analysis algorithms and deep learning technology, the system can efficiently process and analyze large-scale image data and identify cracks and structural defects on the bridge surface. Through historical data analysis models and machine learning technology, the system can predict structural change trends and provide accurate and reliable monitoring results, thereby enhancing the intelligence level of bridge safety assessment.

[0044] (9) The data processing end described in this solution includes: an alarm prompt module, which is used to generate an alarm signal when the identification result indicates that the monitored bridge has structural defects, so as to avoid safety accidents and improve safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of the overall structure of the monitoring system for the structural state of a bridge provided in Example 1 of the present invention;

[0046] Figure 2It is a structural schematic diagram of a data acquisition terminal in a monitoring system for a bridge structural state provided in Example 1 of the present invention;

[0047] Figure 3 It is a schematic diagram of the communication process between the data acquisition end and the radio frequency signal transceiver end provided in Embodiment 1 of the present invention;

[0048] Figure 4 is a schematic diagram of the deployment of a monitoring system for the structural state of a bridge provided in Example 1 of the present invention;

[0049] Figure 5 It is a flow chart of the method for monitoring the structural status of a bridge provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0051] Example 1

[0052] The present embodiment provides a monitoring system for the structural state of a bridge, including: a data acquisition end, a radio frequency signal transceiver end, and a data processing end. The data acquisition end is deployed at multiple preset positions of the bridge to be monitored and powered by the received environmental radio frequency signal. It is used to collect analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring period, and convert the analog image data into a target transmission signal that meets the requirements of passive communication, and then load the target transmission signal into the environmental radio frequency signal to obtain a superimposed signal and scatter it out. The radio frequency signal transceiver end is connected to the data acquisition end in communication, and is used to broadcast the environmental radio frequency signal with the transmission parameters of the current monitoring period, and optimize the transmission parameters of the next monitoring period according to the actual signal strength and actual noise level corresponding to the superimposed signal; it is also used to receive the superimposed signal and demodulate it using the environmental radio frequency signal to obtain the target transmission signal, and then send the target transmission signal out. The data processing end is connected to the radio frequency signal transceiver end in communication, and is used to receive the target transmission signal sent by the radio frequency signal transceiver end, and detect the target transmission signal using a trained deep neural network to obtain the recognition result corresponding to the structural state of the bridge to be monitored.

[0053] Among them, the image acquisition module at the data acquisition end captures the physical quantity of the bridge surface characteristics and receives the bridge pre-observation surface image, generates analog image data based on the bridge predicted surface image, and converts the analog image data into a target transmission signal that meets the requirements of passive communication. For example, the image acquisition module can be a temperature and humidity image acquisition module AHT10 and a camera module OV2640, etc., to obtain bridge crack pictures and environmental data, and convert the collected analog image data into digital image data.

[0054] Furthermore, the RF signal transceiver includes: a transmitting module, a receiving module, an adaptive adjustment module and a RF signal processing module. The transmitting module is used to generate and transmit an environmental RF signal; the receiving module is used to receive the superposition signal scattered back by the passive communication module; the adaptive adjustment module is connected to the transmitting module and the transmitting module; it is used to compare the actual signal strength and actual noise level of the superposition signal received by the receiving module with the preset threshold to determine the transmission parameters of the next monitoring cycle, and the transmission parameters include transmission power, transmission frequency and rate; it is also used to feed back the transmission parameters of the next monitoring cycle to the transmitting module so that it synchronizes the transmission parameters of the next monitoring cycle with the receiving module; the RF signal processing module is connected to the receiving module and is used to demodulate the superposition signal using the environmental RF signal to obtain the target transmission signal.

[0055] Furthermore, the adaptive adjustment module compares the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with the preset threshold to determine the transmission parameters of the next monitoring cycle, including: when the actual signal strength of the superimposed signal is lower than the signal strength threshold, increasing the transmission power of the current monitoring cycle as the transmission power of the next monitoring cycle, and the increased power value is the difference between the actual signal strength and the signal strength threshold multiplied by the first adjustment coefficient; when the actual noise intensity in the actual noise level exceeds the noise tolerance or the signal-to-noise ratio is insufficient, reducing the transmission rate of the current monitoring cycle as the transmission power of the next monitoring cycle, and the reduced rate value is the difference between the actual noise intensity and the noise tolerance multiplied by the second adjustment coefficient.

[0056] The RF signal transceiver has an adaptive adjustment function. By receiving the collected environmental data, the communication parameters such as frequency, power and transmission rate are dynamically adjusted to optimize the effect of energy collection and data transmission. An environmental RF signal with a specific frequency and power is generated to drive the data acquisition end to work normally. The RF switch models that can be used in this embodiment are ADG902 and ADG904.

[0057] Among them, the ambient RF signal can be defined as f0 is the center frequency of the signal. Define the channel between the signal source and the data acquisition end as h1, let the reflection coefficient of the data acquisition end be Γ, let the channel between the data acquisition end and the receiving module be h2, then the received signal is: The passive communication module at the data acquisition end uses backscattering technology to reflect the processed superimposed signal back to the receiving module at the RF signal transceiver end. The backscattering technology uses the broadcast environment RF signal of the transmitting module at the RF signal transceiver end as the environmental RF signal, and scatters or absorbs the incident signal by selecting whether to match the antenna impedance through impedance. The passive communication module scatters the superimposed signal so that the RF signal transceiver end can receive it, and the transmission power is for: Wherein, ε is the backscattering efficiency of the transmitting antenna, satisfying 0<ε≤1.

[0058] It should be noted that the data acquisition terminal can be deployed at various key positions of the bridge to be monitored, and the RF signal transceiver can be deployed on the automatic inspection device. The automatic inspection device can inspect the complete path of the bridge to be monitored, and the location of the structural defects on the bridge to be monitored can be determined by the tags of each sensor in the data acquisition terminal and the positioning information of the automatic inspection device. Among them, the automatic inspection device arranges the RF signal transceiver on the unmanned vehicle to realize automatic inspection, monitor the visual blind spots on the bridge, and facilitate the change of scenes. According to the detection results and environmental changes, the system can automatically adjust the detection parameters and the unmanned vehicle inspection path to adapt to different detection needs and environmental conditions, which is convenient and fast.

[0059] Furthermore, the data acquisition end includes: an image acquisition module, an analog-to-digital conversion module, a data processing module and a passive communication module connected in sequence; the image acquisition module is used to acquire the surface image of the bridge to be monitored to generate analog image data; the analog-to-digital conversion module is used to perform analog-to-digital conversion on the analog image data to obtain digital image data; the data processing module is used to convert the digital image data into a target transmission signal in the form of a binary data stream; the passive communication module is used to collect energy from the ambient RF signal broadcast by the RF signal transceiver to power the data acquisition end, and to carry the target transmission signal on the ambient RF signal to obtain a superimposed signal, and to scatter it in groups.

[0060] Furthermore, the passive communication module has an adaptive adjustment function, which automatically adjusts the scattering parameters of the next monitoring cycle according to the channel level of the ambient radio frequency signal and the actual noise level.

[0061] Furthermore, the analog-to-digital conversion module is used to perform high-precision analog-to-digital conversion on the analog image data in groups by using a multi-channel multiplexing method to obtain digital image data.

[0062] Specifically, the analog-to-digital conversion module converts the analog signal captured by the image acquisition module into a high-precision digital signal to generate digital image data. Environmental noise and interference are filtered out during the signal conversion process. Through a multi-channel processor, multiple analog signal channels are processed simultaneously to improve the efficiency of signal conversion and the system response speed; time-slicing processing of multiple channels is realized, and multi-channel signal conversion is completed on a single high-speed digital-to-analog converter, and signal synchronization is achieved through a shared clock signal and hardware trigger mechanism.

[0063] Furthermore, the analog-to-digital conversion unit is used to perform differential processing on the analog image data, calculate the difference between each pixel and its adjacent pixels; then map the pixel difference to a preset range and superimpose an offset to make it non-negative; and encode the non-negative difference to obtain digital image data.

[0064] Specifically, the analog image data is first read and stored in the form of a matrix, and then the analog image data is differentially processed to calculate the difference between each pixel and its adjacent pixels. Differential value mapping is used to map the calculated differential value to an appropriate range, and an offset is added to the differential value so that all values ​​are non-negative. The processed differential value is encoded. These differential values ​​are represented by integers. The data sent is: Wherein a one-dimensional image data sequence I={I1,I2,I3,...,I n}, the data to be sent is D={D1,D2,D3,...,D n}, and then use Huffman coding to encode the differential value to achieve further data compression. The encoded differential value is converted into a binary data stream to obtain the compressed target transmission data that meets the requirements of passive communication.

[0065] Furthermore, the data processing end includes: an image processing module and a risk assessment module. The image processing module is used to obtain edge features by calculating the gradient and direction of the pixel points in the target transmission signal, and to obtain texture features by analyzing the pixel points in the target transmission signal using the gray level co-occurrence matrix technology; the risk assessment module is connected to the image processing module and is used to input the edge features and texture features into the trained deep learning model to obtain the recognition results corresponding to the structural status of the bridge to be monitored.

[0066] Furthermore, the data processing end includes: an alarm prompt module, which is connected to the risk assessment module and is used to generate an alarm signal when the identification result corresponding to the structural state of the bridge to be monitored indicates the existence of structural defects.

[0067] Example 2

[0068] The present embodiment provides a monitoring method for the structural state of a bridge, which is applied to the monitoring system for the structural state of the bridge, and includes: using a radio frequency signal transceiver to broadcast an ambient radio frequency signal with the transmission parameters of the current monitoring period; using a data acquisition end to use the received ambient radio frequency signal for energy, and collecting analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring period, and converting the analog image data into a target transmission signal that meets the requirements of passive communication, and then loading the target transmission signal into the ambient radio frequency signal to obtain a superimposed signal and scatter it out; using the radio frequency signal transceiver to receive the superimposed signal, and optimizing the transmission parameters of the next monitoring period according to the actual signal strength and actual noise level corresponding to the superimposed signal; receiving the superimposed signal and demodulating it with the ambient radio frequency signal to obtain the target transmission signal, and then sending the target transmission signal out; using the data processing end to receive the target transmission signal sent by the radio frequency signal transceiver, and using a trained deep neural network to detect the target transmission signal to obtain an identification result corresponding to the structural state of the bridge to be monitored.

[0069] In the first step, the transmitter module of the RF signal transmitter generates and transmits environmental RF signals according to the preset initial parameters, including transmission power and frequency. These signals carry basic communication information and propagate within the monitoring area to ensure coverage of all predetermined monitoring points.

[0070] In the second step, after the data acquisition end receives the ambient RF signal from the transmitting module, it uses the built-in image acquisition module to encode the structural health information of the bridge into the ambient RF signal, and then the signal carrying this information is reflected back to the adaptive adjustment module.

[0071] In the third step, the adaptive adjustment module automatically adjusts the reflection parameters according to the channel status and noise level. The receiving module is equipped with an environmental perception function, which monitors the signal strength and noise level in real time through the low-power image acquisition module to obtain the RF conditions of the current environment. The receiving module analyzes the environmental data and dynamically adjusts the communication parameters according to the preset analysis standards including signal strength threshold, noise tolerance and signal-to-noise ratio. These parameters include but are not limited to transmission power and transmission rate. Let the transmission power be P transmit , the transmission rate is R transmit , when the actual signal strength S actual Below the signal strength threshold S threshold When the transmission power is increased:

[0072] P transmit,new =P transmit,old +k1(S threshold -S actual );

[0073] Where k1 is the adjustment coefficient, which is used to control the increase in transmit power. actualExceeding the noise tolerance N tolerance Or when the signal-to-noise ratio is insufficient, reduce the transmission rate:

[0074]

[0075] Wherein, k2 is an adjustment coefficient used to control the reduction amount of the transmission rate.

[0076] In the fourth step, the adaptive adjustment module transmits the adjusted communication parameters to the transmitting module of the RF signal transmitting end. The transmitting module makes corresponding adjustments based on the received parameters to further optimize signal transmission in the next monitoring cycle. The transmitting module also synchronizes the transmission parameters to the receiving module.

[0077] In the fifth step, the RF signal transmitter transmits the demodulated target signal to the data processing end, analyzes the target signal according to the preset analysis standards, such as signal strength threshold, noise tolerance and signal-to-noise ratio, and dynamically adjusts communication parameters such as frequency, power and transmission rate. Specifically, the data processing end identifies cracks and potential defects on the bridge surface through edge detection, texture analysis and deep learning technology, and combines time series analysis and big data technology to predict structural changes, optimize the crack detection process, and improve the accuracy and efficiency of the monitoring system.

[0078] Specifically, the data processing end obtains pixel information in the image data from the image acquisition module or camera through CPU processing to capture changes in the bridge surface, including cracks and potential defects. Using the image analysis algorithm, it is determined whether there is potential structural damage or cracks in the acquired image based on the preset crack identification parameters and the image analysis algorithm. Including image preprocessing, using image enhancement, preprocessing the image before analysis, and using histogram equalization technology to improve the contrast of the image to make cracks and other features more obvious. The purpose of histogram equalization is to expand the dynamic range of the image. Feature processing is then performed, using the Canny edge detection algorithm to identify the edges in the image by calculating the gradient and direction of the pixels in the image. These features are usually manifested as obvious edges in the image. Using texture analysis, the image texture is analyzed using grayscale co-occurrence matrix technology. Grayscale co-occurrence matrix technology is used to measure the grayscale spatial relationship between pixels. Its calculation formula can be expressed as a matrix (P(i,j|d,θ), which represents the transition probability of grayscale value i to j in the direction of distance d and angle θ. Cracks usually change the consistency of local textures, and texture analysis helps to identify the texture features of crack areas. Crack detection and classification, through deep learning models, use convolutional neural networks for deeper image feature learning, and automatically learn the hierarchical features of images through multi-layer filters. The convolutional neural network model operation can be expressed by the following formula:

[0079] a l+1 =σ(W l *al +b l );

[0080] where a l is the activation of layer l, * denotes the convolution operation, W l and b l are the convolution kernel and bias, and σ is the activation function ReLU. The convolutional neural network model matches and classifies the extracted features to identify cracks and other structural defects in the image. The model classifies and marks cracks based on their shape, size, and location. Finally, the processed crack images and bridge temperature and humidity information can be displayed on a PC visualization platform or a mobile phone APP.

[0081] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A monitoring system for the structural status of a bridge, characterized in that: include: The data acquisition end is deployed at multiple preset positions of the bridge to be monitored and powered by the received environmental radio frequency signal, and is used to collect analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring cycle, and convert the analog image data into a target transmission signal that meets the requirements of passive communication, and then load the target transmission signal into the environmental radio frequency signal to obtain a superimposed signal and scatter it out; A radio frequency signal transceiver, which is in communication with the data acquisition end, is used to broadcast the ambient radio frequency signal with the transmission parameters of the current monitoring period, and optimize the transmission parameters of the next monitoring period according to the actual signal strength and the actual noise level corresponding to the superimposed signal; and is also used to receive the superimposed signal and demodulate it using the ambient radio frequency signal to obtain the target transmission signal, and then send the target transmission signal out; The data processing end is communicatively connected to the radio frequency signal transceiver end, and is used to receive the target transmission signal sent by the radio frequency signal transceiver end, and use the trained deep neural network to detect the target transmission signal to obtain the identification result corresponding to the structural state of the bridge to be monitored.

2. The monitoring system for the structural status of a bridge according to claim 1, characterized in that: The data acquisition terminal includes: An image acquisition module, used for acquiring a surface image of the bridge to be monitored to generate simulated image data; An analog-to-digital conversion module, used for performing analog-to-digital conversion on the analog image data to obtain digital image data; A data processing module, used for converting the digital image data into the target transmission signal in the form of a binary data stream; The passive communication module is used to collect energy from the ambient RF signal broadcast by the RF signal transceiver to power the data acquisition terminal, and to carry the target transmission signal on the ambient RF signal to obtain the superimposed signal, and to scatter it in groups.

3. The monitoring system for the structural status of a bridge according to claim 2, characterized in that: The passive communication module has an adaptive adjustment function, and automatically adjusts the scattering parameters of the next monitoring cycle according to the channel level and the actual noise level of the ambient radio frequency signal.

4. The monitoring system for the structural status of a bridge according to claim 2, characterized in that: The analog-to-digital conversion module is used to perform high-precision analog-to-digital conversion on the analog image data in groups by multi-channel multiplexing to obtain the digital image data.

5. The monitoring system for the structural status of a bridge according to claim 2, characterized in that: The analog-to-digital conversion unit is used to perform differential processing on the analog image data to calculate the difference between each pixel and its adjacent pixels; Then map the pixel difference to a preset range and add an offset to make it non-negative; The non-negative difference is encoded to obtain the digital image data.

6. The monitoring system for the structural condition of a bridge according to claim 1, characterized in that: The radio frequency signal transceiver comprises: A transmitting module, used for generating and transmitting the ambient radio frequency signal; A receiving module, used for receiving the superposition signal scattered back by the passive communication module; An adaptive adjustment module, connected to the transmitting module and the transmitting module; used to compare the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with a preset threshold to determine the transmission parameters of the next monitoring cycle, the transmission parameters including the transmission power, the transmission frequency and the rate; and also used to feed back the transmission parameters of the next monitoring cycle to the transmitting module so that it synchronizes the transmission parameters of the next monitoring cycle with the receiving module; The radio frequency signal processing module is connected to the receiving module and is used to demodulate the superimposed signal using the environmental radio frequency signal to obtain the target transmission signal.

7. The monitoring system for the structural condition of a bridge according to claim 6, characterized in that: The adaptive adjustment module compares the actual signal strength and the actual noise level of the superimposed signal received by the receiving module with a preset threshold to determine the transmission parameters of the next monitoring cycle, including: When the actual signal strength of the superimposed signal is lower than the signal strength threshold, the transmit power of the current monitoring period is increased as the transmit power of the next monitoring period, and the increased power value is the difference between the actual signal strength and the signal strength threshold multiplied by the first adjustment coefficient; When the actual noise intensity in the actual noise level exceeds the noise tolerance or the signal-to-noise ratio is insufficient, the transmission rate of the current monitoring cycle is reduced as the transmission power of the next monitoring cycle, and the reduced rate value is the difference between the actual noise intensity and the noise tolerance multiplied by the second adjustment coefficient.

8. The monitoring system for the structural condition of a bridge according to claim 1, characterized in that: The data processing end includes: An image processing module, configured to obtain edge features by calculating the gradient and direction of pixels in the target transmitted signal, and to obtain texture features by analyzing pixels in the target transmitted signal using a gray level co-occurrence matrix technique; The risk assessment module is connected to the image processing module and is used to input the edge features and the texture features into a trained deep learning model to obtain an identification result corresponding to the structural state of the bridge to be monitored.

9. The monitoring system for the structural condition of a bridge according to claim 8, characterized in that: The data processing end includes: an alarm prompt module, which is connected to the risk assessment module and is used to generate an alarm signal when the identification result corresponding to the structural state of the bridge to be monitored indicates that there is a structural defect.

10. A method for monitoring the structural status of a bridge, characterized in that: A monitoring system for the structural state of a bridge according to any one of claims 1 to 9, comprising: Broadcasting the ambient radio frequency signal using the radio frequency signal transceiver with the transmission parameters of the current monitoring period; The data acquisition terminal uses the received ambient radio frequency signal for energy supply, collects analog image data corresponding to the structural state of the bridge to be monitored at each preset position in the current monitoring period, converts the analog image data into a target transmission signal that meets the requirements of passive communication, and then loads the target transmission signal into the ambient radio frequency signal to obtain a superimposed signal and scatters it out; Receive the superimposed signal by using the radio frequency signal transceiver, optimize the transmission parameters of the next monitoring cycle according to the actual signal strength and the actual noise level corresponding to the superimposed signal; receive the superimposed signal and demodulate it by using the environmental radio frequency signal to obtain the target transmission signal, and then send out the target transmission signal; The target transmission signal sent by the radio frequency signal transceiver is received by the data processing end, and the target transmission signal is detected by the trained deep neural network to obtain the recognition result corresponding to the structural state of the bridge to be monitored.

Images