Viaduct disease detection and positioning method based on Beidou positioning

Abstract

The invention discloses an elevated bridge disease detection and positioning method based on Beidou positioning, and the method comprises the steps: installing a sensor at a key part of a bridge, collecting the monitoring parameter data of the bridge in real time, and positioning the key part of the bridge through a Beidou satellite navigation system; after the bridge monitoring parameter data are preprocessed, the preprocessed bridge monitoring parameter data are transmitted to a data center in real time through a wireless communication technology to be stored and analyzed; and carrying out deep analysis on the preprocessed bridge monitoring parameter data by utilizing a machine learning algorithm, identifying disease characteristics and development trends of the bridge, generating a disease detection report, and calling and acquiring corresponding disease position information through a Beidou satellite navigation system to complete bridge disease detection and positioning. According to the invention, rapid and accurate detection and positioning of the viaduct bridge diseases are realized, and the risk and cost of manual detection are reduced on the premise of improving the detection precision and efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of bridge positioning detection, and in particular relates to an elevated bridge disease detection and positioning method based on Beidou positioning. Background Art

[0002] Deformation detection and positioning of urban expressways generally use dedicated sensors and equipment to collect observation data in real time or regularly, and then judge the stability and quality of urban expressways to detect abnormal situations and deal with them in time. The application of sensors and equipment needs to take into account their application environment, such as temperature, humidity, electromagnetic interference, etc., in order to obtain accurate and reliable monitoring data. The existing urban expressway deformation detection and positioning methods include:

[0003] (1) Total station monitoring method. The total station method is a non-contact monitoring method used to measure the position, posture and angle changes of the expressway. The total station method requires setting a cooperative target at the target position, using the total station to monitor the positioning information of the cooperative target, calculate the changes in the target, and thus obtain the deformation data of the expressway. The total station method can not only monitor the deformation of a single point, but also monitor the deformation of the entire expressway. The disadvantage of this technology is that it can only detect the coordinate changes of key points, and it is difficult to measure the overall shape changes.

[0004] (2) Vibration sensor monitoring method. The vibration sensor method is a technology used to measure the vibration of the expressway. It can be used to monitor the vibration frequency, amplitude and vibration shape of the expressway. In the vibration sensor method, vibration signals are obtained by installing vibration sensors at different locations on the expressway. The vibration condition of the expressway can be calculated by analyzing the span time of the vibration signal and the amplitude of the signal. The advantage of the vibration sensor method is that it can monitor the deformation of the expressway very sensitively, but its accuracy is affected by the correct installation position of the sensor.

[0005] (3) Fiber Bragg grating monitoring method. Fiber Bragg grating technology is an efficient and accurate technology for monitoring deformation of expressways: Fiber Bragg grating sensors can detect deformation, temperature, strain, etc. of expressway structures, and have the characteristics of wide application range, distributed monitoring, high precision, and maintenance-free. The sensitive nodes of the fiber Bragg grating sensors are distributed in different parts of the expressway. Through the monitoring and analysis of the fiber Bragg grating, the deformation conditions of different parts of the expressway can be obtained, which ensures the safety and reliability of the expressway to a certain extent.

[0006] (4) GPS monitoring method. The GPS measurement method is a popular method for monitoring deformation of expressways in recent years. It uses the global positioning system to measure the coordinate changes of expressways. The GPS measurement method can be used to conveniently carry out real-time monitoring. The development of GPS monitoring technology has made the processing and analysis of monitoring data more convenient, and can make the technology more widely applicable. The disadvantage of the GPS measurement method is that the traditional GPS positioning system has errors in the detection of elevated bridges, which affects the accuracy of the detection results and cannot monitor the deformation of piers and bridges. However, the emergence of the Beidou system can provide high-precision positioning to ensure the accuracy of the detection data. Therefore, it is urgent to propose a method for detecting and positioning elevated bridge defects based on Beidou positioning to improve the positioning accuracy and improve the accuracy of bridge positioning detection. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a method for detecting and locating elevated bridge defects based on Beidou positioning, comprising:

[0008] Install sensors at key parts of the bridge to collect bridge monitoring parameter data in real time, and locate the key parts of the bridge through the Beidou satellite navigation system;

[0009] After preprocessing the bridge monitoring parameter data, the preprocessed bridge monitoring parameter data is transmitted in real time to a data center for storage and analysis through wireless communication technology;

[0010] Using machine learning algorithms, the pre-processed bridge monitoring parameter data is deeply analyzed to identify the characteristics and development trends of bridge defects, generate a defect detection report, and obtain the corresponding defect location information through the Beidou satellite navigation system to complete bridge defect detection and positioning.

[0011] Preferably, the process of installing sensors at key parts of the bridge includes:

[0012] According to the structural characteristics and detection requirements of the bridge, the geometric shape of the bridge, key parts, and the accuracy requirements of the detection are considered to determine the installation locations of the sensors and Beidou positioning receivers;

[0013] The key parts of the bridge include but are not limited to piers, bridge decks, and connection nodes.

[0014] Preferably, the process of real-time acquisition of bridge monitoring parameter data includes:

[0015] Stress sensors, displacement sensors and vibration sensors are installed in the stress concentration areas and key areas of the connection parts of the bridge to collect the stress data, displacement data and vibration data of the bridge in real time.

[0016] Preferably, the process of preprocessing the bridge monitoring parameter data includes:

[0017] Data cleaning removes outliers and noise from sensor data, and then standardizes the data to make it fit the input requirements of the machine learning algorithm.

[0018] Feature extraction is performed on the bridge stress data, displacement data and vibration data collected in real time to obtain stress changes, displacement changes and vibration frequencies.

[0019] Preferably, the process of removing outliers and noise in sensor data by data cleaning includes:

[0020] Observe the original form of the data, identify the noise and outliers in the data, convert the data into a unified dimension and scale, and then remove the outliers through statistical methods or empirical thresholds;

[0021] After selecting a suitable filter and setting the filter parameters, apply the filter to the data to remove unwanted frequency components;

[0022] Further remove noise from the data based on wavelet transform denoising, adaptive filtering and singular value decomposition denoising, verify the filtering denoising effect through visual inspection and statistical analysis, and optimize and adjust the filter parameters according to the filtering denoising effect;

[0023] Finally, the filtered data is smoothed and interpolated to complete data cleaning.

[0024] Preferably, the process of performing in-depth analysis on the pre-processed bridge monitoring parameter data using a machine learning algorithm includes:

[0025] Constructing a disease recognition model based on the SVM algorithm, training the disease recognition model using the extracted features and historical disease data, and obtaining a target disease recognition model;

[0026] Based on the target disease recognition model, real-time monitoring and early warning of bridge diseases are carried out.

[0027] Preferably, the process of training the disease recognition model using the extracted features and historical disease data includes:

[0028] Divide the model into a training set and a test set, wherein the training set is used for model training and the test set is used for model verification;

[0029] The disease recognition model is trained using the training set data, model parameters are adjusted through grid search and random search to obtain the optimal parameter combination, and the generalization ability of the model is evaluated through K-fold cross validation to optimize the model performance;

[0030] The disease recognition model is evaluated using the test set data, the model indicators are calculated, and the prediction effect of the model is evaluated; wherein the model indicators include but are not limited to accuracy, recall rate, and F1 score.

[0031] Preferably, the disease detection report includes but is not limited to disease type, location, severity, and predicted result information.

[0032] Compared with the prior art, the present invention has the following advantages and technical effects:

[0033] The present invention uses the high-precision positioning technology of the Beidou satellite navigation system to achieve rapid and accurate detection and positioning of elevated bridge defects. By combining sensor technology and data analysis technology, the method not only improves the accuracy and efficiency of detection, but also reduces the risk and cost of manual detection.

[0034] The present invention makes full use of machine learning algorithms to conduct in-depth analysis of sensor data, identify bridge disease characteristics and development trends, generate disease detection reports, and improve the accuracy and efficiency of bridge disease detection.

[0035] The present invention can systematically perform data analysis and disease identification, improve the accuracy and efficiency of bridge disease detection, and ensure the safety and stability of the bridge. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0038] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0039] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] like Figure 1 As shown, this embodiment provides a method for detecting and locating elevated bridge defects based on Beidou positioning, including:

[0041] Install sensors at key parts of the bridge to collect bridge monitoring parameter data in real time, and locate key parts of the bridge through the Beidou satellite navigation system;

[0042] After preprocessing the bridge monitoring parameter data, the preprocessed bridge monitoring parameter data is transmitted to the data center in real time for storage and analysis through wireless communication technology; the data acquisition system is configured to ensure that the data collected by the sensor can be transmitted to the data center in real time. Consider using wireless communication technologies such as Wi-Fi, 4G / 5G, etc. to improve the stability and real-time performance of data transmission.

[0043] Using machine learning algorithms, we conduct in-depth analysis of the pre-processed bridge monitoring parameter data, identify the characteristics and development trends of bridge defects, generate a defect detection report, and obtain the corresponding defect location information through the Beidou satellite navigation system to complete bridge defect detection and positioning.

[0044] Further, the process of installing sensors at key locations of the bridge includes:

[0045] According to the structural characteristics and detection requirements of the bridge, the geometric shape of the bridge, key parts, and the accuracy requirements of the detection are considered to determine the installation locations of the sensors and Beidou positioning receivers;

[0046] The key parts of a bridge include but are not limited to piers, bridge decks, and connection nodes.

[0047] Furthermore, the process of real-time acquisition of bridge monitoring parameter data includes:

[0048] Stress sensors, displacement sensors and vibration sensors are installed in the stress concentration areas and key areas of the connection parts of the bridge to collect the stress data, displacement data and vibration data of the bridge in real time.

[0049] Furthermore, the process of preprocessing the bridge monitoring parameter data includes:

[0050] Data cleaning removes outliers and noise from sensor data, and then standardizes the data to make it fit the input requirements of the machine learning algorithm.

[0051] Feature extraction is performed on the bridge stress data, displacement data and vibration data collected in real time to obtain stress changes, displacement changes and vibration frequencies.

[0052] Furthermore, the process of removing outliers and noise from sensor data through data cleaning includes:

[0053] Observe the original form of the data, identify the noise and outliers in the data, convert the data into a unified dimension and scale, and then remove the outliers through statistical methods or empirical thresholds;

[0054] After selecting a suitable filter and setting the filter parameters, apply the filter to the data to remove unwanted frequency components;

[0055] Furthermore, based on the characteristics of the data and application requirements, the appropriate filter types include:

[0056] Low-pass filter: used to remove high-frequency noise and retain low-frequency signals.

[0057] High-pass filter: used to remove low-frequency noise and retain high-frequency signals.

[0058] Bandpass filter: used to retain signals within a specific frequency range and remove noise at other frequencies.

[0059] Band-stop filter: used to remove signals within a specific frequency range and retain signals at other frequencies.

[0060] The filter parameters include cutoff frequency, filter order, etc., to meet specific filtering requirements.

[0061] Cutoff Frequency: Determines the filter's cutoff frequency, which is the dividing point between what is retained and what is removed.

[0062] Filter order: Determines the order of the filter. The higher the order, the more obvious the filtering effect, but the higher the calculation complexity.

[0063] Apply filters to the data to remove unwanted frequency components including:

[0064] Time domain filtering: Filter the data directly in the time domain, such as moving average filtering, median filtering, etc.

[0065] Frequency domain filtering: Convert the data to the frequency domain, apply a filter, and then convert back to the time domain, such as Fourier transform filtering.

[0066] Further remove the noise in the data based on wavelet transform denoising, adaptive filtering and singular value decomposition denoising, verify the filtering denoising effect through visual inspection and statistical analysis, and optimize and adjust the filter parameters according to the filtering denoising effect;

[0067] Among them, wavelet transform denoising uses wavelet transform to perform multi-scale analysis on data to remove noise.

[0068] Adaptive filtering dynamically adjusts filter parameters according to the characteristics of the data to improve the denoising effect.

[0069] Singular value decomposition denoising uses singular value decomposition technology to remove outliers and noise in data.

[0070] Visual inspection observes the data graphs after filtering and compares the changes before and after filtering. Statistical analysis evaluates the filtering effect and ensures the improvement of data quality by calculating the statistical indicators of the filtered data, such as mean, variance, etc.

[0071] Finally, the filtered data is smoothed and interpolated to complete data cleaning.

[0072] Data smoothing reduces the fluctuation of filtered data, and data interpolation restores the integrity of the data by interpolating the data that may be lost during the filtering process.

[0073] Furthermore, this embodiment ensures that sensor data can be transmitted to the data center in real time by building a stable communication network, and considers using a combination of wired and wireless communication technologies to improve the stability of data transmission.

[0074] This embodiment designs an efficient data storage solution, which ensures that a large amount of sensor data can be stored safely and reliably by using cloud storage technology, and improves the flexibility and scalability of data storage. It also uses encryption technology and access control technology to improve data security and ensure that data during transmission and storage is not illegally accessed or tampered with.

[0075] Furthermore, the process of in-depth analysis of the pre-processed bridge monitoring parameter data using machine learning algorithms includes:

[0076] Construct a disease recognition model based on the SVM algorithm, use the extracted features and historical disease data to train the disease recognition model, and obtain the target disease recognition model;

[0077] Real-time monitoring and early warning of bridge defects are carried out based on the target defect identification model.

[0078] Furthermore, the process of training the disease recognition model using the extracted features and historical disease data includes:

[0079] Divide the training set and test set. The training set is used for model training, and the test set is used for model verification.

[0080] Use the training set data to train the disease recognition model, adjust the model parameters through grid search and random search to obtain the optimal parameter combination, and use K-fold cross validation to evaluate the generalization ability of the model and optimize the model performance;

[0081] Use the test set data to evaluate the disease recognition model, calculate the model indicators, and evaluate the prediction effect of the model; among which, the model indicators include but are not limited to accuracy, recall rate, and F1 score.

[0082] Furthermore, the disease detection report includes, but is not limited to, disease type, location, severity, and predicted result information.

[0083] Furthermore, this embodiment can also select other appropriate machine learning algorithms, such as decision trees, random forests, neural networks, etc., according to the characteristics of bridge disease detection. And as time goes by and data accumulates, the machine learning model is continuously updated and optimized to improve the prediction performance of the model, and the model is retrained and verified regularly to ensure that the model can adapt to new data and environmental changes.

[0084] The method of the present invention can realize rapid and accurate detection and positioning of elevated bridge defects.

[0085] The specific effects are as follows:

[0086] (1) Significantly improved detection efficiency: By utilizing Beidou positioning and sensor technology, the detection cycle is greatly shortened, enabling real-time monitoring.

[0087] (2) Significantly improved detection accuracy: Through high-precision positioning and data analysis technology, it is possible to accurately identify subtle changes in bridge defects and improve detection reliability.

[0088] (3) Comprehensive coverage of the inspection range: Combined with the mobile inspection platform, it can cover all key parts of the bridge, including hidden parts and hard-to-reach areas.

[0089] (4) Safety is significantly improved: reducing manual high-altitude operations and reducing safety risks during the inspection process.

[0090] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application 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.

Claims

1. A method for detecting and locating elevated bridge defects based on Beidou positioning, characterized in that: include: Install sensors at key parts of the bridge to collect bridge monitoring parameter data in real time, and locate the key parts of the bridge through the Beidou satellite navigation system; After preprocessing the bridge monitoring parameter data, the preprocessed bridge monitoring parameter data is transmitted in real time to a data center for storage and analysis through wireless communication technology; Using machine learning algorithms, the pre-processed bridge monitoring parameter data is deeply analyzed to identify the characteristics and development trends of bridge defects, generate a defect detection report, and obtain the corresponding defect location information through the Beidou satellite navigation system to complete bridge defect detection and positioning.

2. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 1 is characterized in that: The process of installing sensors at key locations on the bridge includes: According to the structural characteristics and detection requirements of the bridge, the geometric shape of the bridge, key parts, and the accuracy requirements of the detection are considered to determine the installation locations of the sensors and Beidou positioning receivers; The key parts of the bridge include but are not limited to piers, bridge decks, and connection nodes.

3. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 1 is characterized in that: The process of real-time acquisition of bridge monitoring parameter data includes: Stress sensors, displacement sensors and vibration sensors are installed in the stress concentration areas and key areas of the connection parts of the bridge to collect the stress data, displacement data and vibration data of the bridge in real time.

4. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 1 is characterized in that: The process of preprocessing the bridge monitoring parameter data includes: Data cleaning removes outliers and noise from sensor data, and then standardizes the data to make it fit the input requirements of the machine learning algorithm. Feature extraction is performed on the bridge stress data, displacement data and vibration data collected in real time to obtain stress changes, displacement changes and vibration frequencies.

5. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 4 is characterized in that: The process of removing outliers and noise from sensor data through data cleaning includes: Observe the original form of the data, identify the noise and outliers in the data, convert the data into a unified dimension and scale, and then remove the outliers through statistical methods or empirical thresholds; After selecting a suitable filter and setting the filter parameters, apply the filter to the data to remove unwanted frequency components; Further remove noise from the data based on wavelet transform denoising, adaptive filtering and singular value decomposition denoising, verify the filtering denoising effect through visual inspection and statistical analysis, and optimize and adjust the filter parameters according to the filtering denoising effect; Finally, the filtered data is smoothed and interpolated to complete data cleaning.

6. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 1 is characterized in that: The process of performing in-depth analysis on the pre-processed bridge monitoring parameter data using a machine learning algorithm includes: Constructing a disease recognition model based on the SVM algorithm, training the disease recognition model using the extracted features and historical disease data, and obtaining a target disease recognition model; Based on the target disease recognition model, real-time monitoring and early warning of bridge diseases are carried out.

7. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 6 is characterized in that: The process of training the disease recognition model using the extracted features and historical disease data includes: Divide the model into a training set and a test set, wherein the training set is used for model training and the test set is used for model verification; The disease recognition model is trained using the training set data, model parameters are adjusted through grid search and random search to obtain the optimal parameter combination, and the generalization ability of the model is evaluated through K-fold cross validation to optimize the model performance; The disease recognition model is evaluated using the test set data, the model indicators are calculated, and the prediction effect of the model is evaluated; wherein the model indicators include but are not limited to accuracy, recall rate, and F1 score.

8. The elevated bridge disease detection and positioning method based on Beidou positioning according to claim 1 is characterized in that: The disease detection report includes but is not limited to disease type, location, severity, and predicted result information.

Images