Tunnel structure health monitoring intelligent analysis system

Abstract

The invention relates to the technical field of tunnel structure monitoring, in particular to a tunnel structure health monitoring intelligent analysis system which comprises a data acquisition module, a data transmission module, a data processing and analysis module, an alarm and decision support module and a user interaction module. The data acquisition module is used for acquiring tunnel structure data in real time, the data transmission module transmits the acquired data to the data processing and analysis module, the data processing and analysis module analyzes the data in real time through an isolated forest algorithm and identifies potential damage and abnormity, and the alarm and decision support module triggers multi-level alarms when detecting abnormity. The user interaction module displays the monitoring data, the analysis result and the alarm information in real time through the display screen and the control terminal, the accuracy and the real-time performance of tunnel structure health monitoring can be remarkably improved, an intelligent anomaly detection and early warning mechanism is provided, and safe operation of a tunnel and long-term stability of the structure are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel structure monitoring, and in particular to an intelligent analysis system for tunnel structure health monitoring. Background Art

[0002] As an important transportation infrastructure, the safe operation of tunnels is crucial to the safety of people's lives and property and economic development. The health of tunnel structures is affected by many factors, including geological conditions, construction quality, environmental erosion and traffic load. Traditional tunnel inspection methods mainly rely on regular manual inspections, which is not only time-consuming and labor-intensive, but also has great subjectivity and lag, and cannot timely discover and deal with potential problems of tunnel structures. With the advancement of science and technology, the use of advanced sensing technology and data analysis methods to conduct real-time monitoring and intelligent analysis of tunnels has become an important development direction for tunnel structure health monitoring.

[0003] Although some progress has been made in tunnel structure health monitoring, there are still some significant shortcomings. First, most existing systems rely on only a single or a small number of sensors, with limited data dimensions, making it difficult to fully reflect the actual health status of the tunnel structure. Second, the data analysis method is relatively simple, usually using basic statistical analysis, which is difficult to process complex time series data, resulting in insufficient accuracy and real-time performance of anomaly detection. In addition, the existing system lacks an effective early warning and decision support mechanism, and cannot provide detailed maintenance and repair suggestions in a timely manner, making it difficult to effectively prevent and deal with potential damage and anomalies in the tunnel structure. Summary of the invention

[0004] Based on the above objectives, the present invention provides an intelligent analysis system for monitoring the health of tunnel structures.

[0005] The intelligent analysis system for tunnel structure health monitoring includes a data acquisition module, a data transmission module, a data processing and analysis module, an alarm and decision support module and a user interaction module, among which;

[0006] The data acquisition module is used to collect stress, vibration and displacement data of the tunnel structure in real time;

[0007] The data transmission module uses a combination of wired and wireless communication technology to transmit the collected stress, vibration and displacement data to the data processing and analysis module;

[0008] The data processing and analysis module includes a data preprocessing unit, an anomaly detection unit and a prediction analysis unit. The data preprocessing unit is used to clean, filter and format the received data. The anomaly detection unit performs real-time analysis on the processed data based on an anomaly detection algorithm to identify potential damage and anomalies of the tunnel structure. The prediction analysis unit combines historical data and real-time data and uses a deep learning model to predict the health status of the tunnel structure under different load conditions.

[0009] The alarm and decision support module includes an alarm generation unit and a decision suggestion unit, wherein the alarm generation unit is used to issue an alarm in time when an abnormality is detected, and the decision suggestion unit provides maintenance suggestions and repair suggestions based on the analysis results of the prediction analysis unit;

[0010] The user interaction module includes a display screen and a control terminal, which are used to display real-time monitoring data, analysis results and alarm information, and allow users to operate and manage the system.

[0011] Optionally, the data acquisition module specifically includes:

[0012] Strain gauge: pasted or embedded on the surface or inside of the tunnel structure. When the tunnel structure is subjected to external force, the resistance value of the strain gauge changes, generating an electrical signal;

[0013] Accelerometer: Installed at key locations of the tunnel structure, the accelerometer generates vibration data by measuring the acceleration changes of the tunnel structure in different directions;

[0014] Laser displacement sensor: Installed at key nodes in the tunnel, the laser displacement sensor measures displacement changes in real time and generates displacement data.

[0015] Optionally, the data transmission module specifically includes:

[0016] Wired communication technology: The stress, vibration and displacement data collected by the data acquisition module are transmitted to the data processing and analysis module outside the tunnel through optical fiber lines;

[0017] Wireless communication technology: When the optical fiber line is interrupted or unavailable, it automatically switches to the cellular network and transmits the stress, vibration and displacement data collected by the data acquisition module to the data processing and analysis module through 4G / 5G signals;

[0018] Data Encryption: Use secure encryption protocols to ensure the security and integrity of stress, vibration, and displacement data during transmission.

[0019] Optionally, the data preprocessing unit specifically includes:

[0020] Data cleaning: Perform data cleaning on the received stress, vibration and displacement data, including noise removal and missing value filling;

[0021] Data filtering: High-pass filtering is used to filter the received stress, vibration and displacement data;

[0022] Data formatting: Format the received stress, vibration and displacement data, including unit conversion, time alignment and data standardization.

[0023] Optionally, the anomaly detection unit performs real-time analysis on the processed data based on an isolation forest algorithm to identify potential damage and anomalies of the tunnel structure, specifically including:

[0024] Data input: receiving the cleaned, filtered and formatted stress, vibration and displacement data from the data preprocessing unit;

[0025] Model training: Use the isolation forest algorithm to build an isolation forest model, and use historical data to train the isolation forest model;

[0026] Real-time analysis: Input the stress, vibration and displacement data collected in real time into the isolation forest model to calculate the anomaly score for each data point;

[0027] Abnormality determination: According to the preset threshold, the data point is judged as abnormal. If the abnormality score exceeds the threshold, it is judged as abnormal.

[0028] Alarm mechanism: When an abnormal situation is detected, the alarm mechanism is triggered and a warning signal is generated.

[0029] Optionally, the prediction analysis unit specifically includes:

[0030] Data preparation: Collect pre-processed historical data and real-time data, including stress, vibration and displacement data of tunnel structures;

[0031] Data annotation: Based on stress, vibration and displacement data, the health status of the tunnel structure is classified into healthy, slightly damaged and severely damaged, and the data is annotated;

[0032] Feature extraction: extract features from labeled data, including time series features and statistical features;

[0033] Build the model: Select the long short-term memory network model as the deep learning model and build the model, including the input layer, long short-term memory network layer, fully connected layer and output layer;

[0034] Model training: Divide historical data and corresponding target labels into training sets and validation sets, and use the training set data to train the long short-term memory network model;

[0035] Real-time prediction: real-time data is input into the trained long short-term memory network model, and the model output is the predicted health status of the tunnel structure, which is classified into healthy, slightly damaged and severely damaged;

[0036] Result analysis: Analyze the prediction results and generate a health status report, which includes damage location, damage development trend and remaining life of the structure.

[0037] Optionally, the alarm generating unit specifically includes:

[0038] Receiving the warning signal: the alarm generation unit receives the warning signal generated by the abnormality detection unit, and triggers the alarm mechanism when receiving the warning signal;

[0039] Receiving health status: the alarm generation unit receives the tunnel structure health status report predicted by the prediction analysis unit, and triggers the alarm mechanism when the health status is slightly damaged or seriously damaged;

[0040] Alarm mechanism: Alarm types include sound alarms, visual alarms (such as warning lights) and electronic alarms (such as text message or email notifications). Alarm information includes the type of abnormality, location and time.

[0041] Optionally, the decision suggestion unit specifically includes:

[0042] Maintenance recommendations: Obtain health status reports from the predictive analysis unit and generate maintenance recommendations based on the health status reports, such as recommendations for detailed inspections of specific locations, and recommended inspection times and frequencies;

[0043] Repair Recommendations: Provide repair recommendations based on health status classification, such as recommending specific reinforcement materials, estimated repair time and required resources.

[0044] Optionally, the user interaction module specifically includes:

[0045] Display screen: The display screen is used to display real-time monitoring data, analysis results and alarm information to ensure that users understand the health status of the tunnel structure;

[0046] Control terminal: The control terminal is used by users to operate and manage the system, ensuring that users can effectively monitor and maintain the tunnel structure.

[0047] Beneficial effects of the present invention:

[0048] In the present invention, the data processing and analysis module significantly improves the accuracy and real-time performance of tunnel structure health monitoring through the isolation forest algorithm and the long short-term memory network model. By integrating multiple sensor technologies, stress, vibration and displacement data are collected, and the isolation forest algorithm is used to detect abnormal conditions in the data in real time, ensuring early identification of potential damage to the tunnel structure. In addition, the long short-term memory network model can process complex time series data, predict the health status of the tunnel structure in the future, and achieve a comprehensive grasp and efficient management of the health status of the tunnel structure.

[0049] In the present invention, the alarm and decision support module realizes intelligent anomaly detection and early warning functions. When the system detects potential damage or abnormal conditions in the tunnel structure, the alarm generation unit immediately triggers multi-level alarms, including sound alarms, visual alarms, and electronic alarms, to ensure that maintenance personnel can be informed in time and respond quickly. Based on the analysis results of the predictive analysis unit, the decision recommendation unit provides detailed maintenance and repair suggestions, including damage type, location, development trend, and specific maintenance measures. Through intelligent anomaly detection and early warning mechanisms, the system can effectively prevent accidents and ensure the safe operation of the tunnel and the long-term stability of the structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of the data processing and analysis module flow in an embodiment of the present invention;

[0053] Figure 3 Schematic diagram of the prediction analysis unit process of an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0055] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0056] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0057] like Figure 1-Figure 3 As shown, the intelligent analysis system for tunnel structure health monitoring includes a data acquisition module, a data transmission module, a data processing and analysis module, an alarm and decision support module and a user interaction module, wherein;

[0058] The data acquisition module is used to collect the stress, vibration and displacement data of the tunnel structure in real time;

[0059] The data transmission module uses a combination of wired and wireless communication technology to transmit the collected stress, vibration and displacement data to the data processing and analysis module;

[0060] The data processing and analysis module includes a data preprocessing unit, an anomaly detection unit and a prediction analysis unit. The data preprocessing unit is used to clean, filter and format the received data. The anomaly detection unit performs real-time analysis on the processed data based on the anomaly detection algorithm to identify potential damage and anomalies of the tunnel structure. The prediction analysis unit combines historical data and real-time data and uses a deep learning model to predict the health status of the tunnel structure under different load conditions.

[0061] The alarm and decision support module includes an alarm generation unit and a decision suggestion unit. The alarm generation unit is used to issue an alarm in time when an abnormality is detected. The decision suggestion unit provides maintenance suggestions and repair suggestions based on the analysis results of the prediction analysis unit.

[0062] The user interaction module includes a display screen and a control terminal, which are used to display real-time monitoring data, analysis results and alarm information, and allow users to operate and manage the system.

[0063] The data acquisition module specifically includes:

[0064] Strain gauge: pasted or embedded on the surface or inside of the tunnel structure. When the tunnel structure is subjected to external force, the resistance value of the strain gauge changes, generating an electrical signal;

[0065] Accelerometer: Installed at key locations of the tunnel structure, the accelerometer generates vibration data by measuring the acceleration changes of the tunnel structure in different directions;

[0066] Laser displacement sensor: installed at key nodes of the tunnel, the laser displacement sensor measures displacement changes in real time and generates displacement data;

[0067] The data acquisition module can realize real-time collection of stress, vibration and displacement data of tunnel structures, providing a basis for subsequent data processing and analysis.

[0068] The data transmission module specifically includes:

[0069] Wired communication technology: The stress, vibration and displacement data collected by the data acquisition module are transmitted to the data processing and analysis module outside the tunnel through optical fiber lines;

[0070] Wireless communication technology: When the optical fiber line is interrupted or unavailable, it automatically switches to the cellular network and transmits the stress, vibration and displacement data collected by the data acquisition module to the data processing and analysis module through 4G / 5G signals;

[0071] Data encryption: Use secure encryption protocols to ensure the security and integrity of stress, vibration and displacement data during transmission;

[0072] Practical application examples:

[0073] Sensor nodes inside the tunnel: strain gauges, accelerometers and laser displacement sensors are connected to the data acquisition module through optical fiber lines;

[0074] Data acquisition module: The data acquisition module collects the data from strain gauges, accelerometers and laser displacement sensors and transmits them to the relay node in the tunnel through the optical fiber line. The relay node transmits the data to the data processing and analysis module outside the tunnel through the optical fiber line.

[0075] Relay node: If the optical fiber line is interrupted or fails, it automatically switches to 4G / 5G cellular communication and transmits data to the data processing and analysis module outside the tunnel through the cellular network;

[0076] Through the communication technology combining optical fiber communication and cellular communication, the data transmission module can ensure stable and reliable data transmission of the tunnel structure health monitoring system.

[0077] The data preprocessing unit specifically includes:

[0078] Data cleaning: Perform data cleaning on the received stress, vibration and displacement data, including noise removal and missing value filling;

[0079] Noise removal: Based on the statistical method, the mean (μ) and standard deviation (σ) are used to identify and remove obvious noise. The noise removal formula is calculated as:

[0080] x clean ={x i ∣|x i -μ|≤3σ};

[0081] Among them, x i is the original data point, μ is the mean of the data, σ is the standard deviation of the data, x clean is the cleaned data;

[0082] Missing value filling: Linear interpolation is performed based on adjacent data points. The linear interpolation formula is calculated as:

[0083]

[0084] Among them, t i is the time point, x i-1 and x i+1 are adjacent known data points;

[0085] Data filtering: High-pass filtering is used to filter the received stress, vibration and displacement data;

[0086] The high-pass filter design formula is as follows:

[0087] Normalized cutoff frequency, expressed as:

[0088] The filter transfer function is expressed as:

[0089] Among them, ω c is the cut-off angular frequency;

[0090] Data formatting: Format the received stress, vibration and displacement data, including unit conversion, time alignment and data standardization;

[0091] Unit conversion formula, calculated as: x new =x old ×k;

[0092] Where k is the unit conversion factor, for example, when converting stress from MPa to Pa, k = 10 6 ;

[0093] The time alignment formula is calculated as:

[0094] Among them, t i is the time point, x i-1 and x i+1 are adjacent known data points;

[0095] The data normalization formula is calculated as:

[0096] Among them, x min and x max are the minimum and maximum values ​​of the data, μ is the mean, and σ is the standard deviation;

[0097] The data preprocessing unit can effectively clean, filter and format the received data to ensure the accuracy and consistency of the data, providing a reliable data basis for subsequent anomaly detection and predictive analysis.

[0098] The anomaly detection unit uses the isolation forest algorithm to analyze the processed data in real time to identify potential damage and anomalies in the tunnel structure, including:

[0099] Data input: receiving the cleaned, filtered and formatted stress, vibration and displacement data from the data preprocessing unit;

[0100] Model training: Use the isolation forest algorithm to build an isolation forest model, and use historical data to train the isolation forest model. The training process steps are as follows:

[0101] (1) Constructing an isolation forest: Randomly select a subset of sample data and construct multiple random trees. Each tree splits the data by randomly selecting features and split points until each sample data is isolated.

[0102] (2) Isolation tree construction process: For each data point, randomly select a feature from the data set, and randomly select a split point within the range of the feature. The data set is divided into two parts according to the split point, and the above operation is recursively performed until each data point is isolated;

[0103] (3) Path length calculation:

[0104] Path length h(x): the path length of data point x in the tree;

[0105] Average path length E(h(x)): the average of the path lengths in all trees;

[0106] (4) Normalization factor:

[0107] Where H is the harmonic number, H(n-1) is the n-1th harmonic number, c(n) is the normalization factor used to standardize the path length in the isolation forest, and n is the number of data points;

[0108] Real-time analysis: Input the stress, vibration and displacement data collected in real time into the isolation forest model to calculate the anomaly score for each data point;

[0109] Anomaly score s(x,n) calculation: The anomaly score of data point x is calculated as:

[0110] Where n is the number of data points;

[0111] Abnormality determination: According to the preset threshold, the data point is judged as abnormal. If the abnormality score exceeds the threshold, it is judged as abnormal.

[0112] Abnormality determination: According to the set threshold T, the data point is abnormally determined, which is expressed as:

[0113] ifs(x,n)>T,thenxis an anomaly;

[0114] Alarm mechanism: When an abnormal situation is detected, the alarm mechanism is triggered and a warning signal is generated.

[0115] The predictive analysis unit specifically includes:

[0116] Data preparation: Collect pre-processed historical data and real-time data, including stress, vibration and displacement data of tunnel structure. Historical data refers to the stress, vibration and displacement data of tunnel structure in the past period of time (such as one year), and real-time data refers to the real-time stress, vibration and displacement data currently collected.

[0117] Data annotation: Based on stress, vibration and displacement data, the health status of the tunnel structure is classified into healthy, slightly damaged and severely damaged, and the data is annotated;

[0118] Feature extraction: Extract features from labeled data, including time series features and statistical features, among which;

[0119] Time series features: Sort historical data by time, construct time series data, and use time series data as time series features;

[0120] Statistical features: calculate the mean μ, standard deviation σ, maximum and minimum values ​​within the time window;

[0121] The mean is calculated as: Among them, x i is the data of the i-th time point, and t is the total number of time points;

[0122] The standard deviation is calculated as: Among them, x i is the data of the i-th time point, t is the total number of time points, and μ is the mean;

[0123] Maximum value: the maximum data value in the time window;

[0124] Minimum value: the minimum data value in the time window;

[0125] Build the model: Select the long short-term memory network model as the deep learning model and build the model, including the input layer, long short-term memory network layer, fully connected layer and output layer;

[0126] Model training: Divide historical data and corresponding target labels into training sets and validation sets, and use the training set data to train the long short-term memory network model;

[0127] Real-time prediction: real-time data is input into the trained long short-term memory network model, and the model output is the predicted health status of the tunnel structure, which is classified into healthy, slightly damaged and severely damaged;

[0128] Result analysis: Analyze the prediction results and generate a health status report, which includes damage location, damage development trend and remaining life of the structure;

[0129] The predictive analysis unit can combine historical data and real-time data, and use the long-short-term memory network model to classify and predict the health status of the tunnel structure, providing scientific decision-making support for tunnel operation and maintenance.

[0130] The alarm generation unit specifically includes:

[0131] Receiving the warning signal: the alarm generation unit receives the warning signal generated by the abnormality detection unit, and triggers the alarm mechanism when receiving the warning signal;

[0132] Receiving health status: the alarm generation unit receives the tunnel structure health status report predicted by the prediction analysis unit, and triggers the alarm mechanism when the health status is slightly damaged or seriously damaged;

[0133] Alarm mechanism: Alarm types include sound alarms, visual alarms (such as warning lights) and electronic alarms (such as text messages or email notifications). Alarm information includes the type, location and time of the abnormality.

[0134] Example:

[0135] Health status: severe damage, triggering alarm generation;

[0136] Alert mechanism:

[0137] Sound alarm: siren;

[0138] Visual alarm: red warning light flashes;

[0139] Electronic alerts: send SMS and email notifications to the maintenance team;

[0140] Alarm message: Serious damage detected, location is in section 3 of tunnel, time is year-month-day-hour-minute.

[0141] The decision-making recommendation unit specifically includes:

[0142] Maintenance recommendations: Obtain health status reports from the predictive analysis unit and generate maintenance recommendations based on the health status reports, such as recommendations for detailed inspections of specific locations, and recommended inspection times and frequencies;

[0143] Repair recommendations: Provide repair recommendations based on health status classification, such as recommending specific reinforcement materials, estimating repair time and required resources;

[0144] Example:

[0145] Health status report: The potential damage location is in the third section of the tunnel, the damage development trend is accelerating, and the remaining life of the structure is estimated to be 2 months;

[0146] Generate maintenance recommendations: It is recommended to conduct a detailed inspection of Section 3 of the tunnel on 2024-08-02 and inspect it once a week until the damage is repaired;

[0147] Generate repair suggestions: It is recommended to use carbon fiber reinforcement materials for reinforcement. The estimated repair time is 2 days. The required resources include carbon fiber reinforcement materials and a professional repair team.

[0148] Through the collaborative work of the alarm generation unit and the decision suggestion unit, the alarm and decision support module can issue an alarm in time when an abnormality in the tunnel structure is detected, and provide specific maintenance and repair suggestions to ensure the safety and stability of the tunnel structure.

[0149] The user interaction module specifically includes:

[0150] Display screen: The display screen is used to display real-time monitoring data, analysis results and alarm information to ensure that users understand the health status of the tunnel structure, including;

[0151] Real-time monitoring data: Display real-time data of stress, vibration, and displacement parameters, and provide charts and graphical interfaces (such as line charts and bar charts) to show data change trends;

[0152] Analysis results: Displays the analysis results of the prediction analysis unit, including health status classification (healthy, slightly damaged, seriously damaged), potential damage location, damage development trend and remaining life of the structure;

[0153] Alarm information: displays the alarm information of the alarm generating unit, including the abnormality type, location and time;

[0154] Control terminal: The control terminal is used by users to operate and manage the system, ensuring that users can effectively monitor and maintain the tunnel structure, including:

[0155] System operation: Provides a user interface to allow users to operate the system, such as starting or stopping monitoring, adjusting monitoring frequency, etc.;

[0156] System Management: Allows users to set and adjust system parameters, such as alarm thresholds;

[0157] Maintenance management: Provides maintenance suggestions and repair recommendations, allows users to view and record maintenance activities, and provides a maintenance log that records the details and results of each maintenance.

[0158] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0159] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Tunnel structure health monitoring intelligent analysis system, characterized by: It includes data acquisition module, data transmission module, data processing and analysis module, alarm and decision support module and user interaction module, among which; The data acquisition module is used to collect stress, vibration and displacement data of the tunnel structure in real time; The data transmission module uses a combination of wired and wireless communication technology to transmit the collected stress, vibration and displacement data to the data processing and analysis module; The data processing and analysis module includes a data preprocessing unit, an anomaly detection unit, and a prediction and analysis unit. The data preprocessing unit is used to clean, filter, and format the received data. The anomaly detection unit uses an anomaly detection algorithm to perform real-time analysis on the processed data to identify potential damage and anomalies in the tunnel structure. The prediction and analysis unit combines historical data and real-time data and uses a deep learning model to predict the health status of the tunnel structure under different load conditions. The alarm and decision support module includes an alarm generation unit and a decision suggestion unit. The alarm generation unit is used to issue an alarm in time when an abnormality is detected. The decision suggestion unit provides maintenance suggestions and repair suggestions based on the analysis results of the prediction analysis unit. The user interaction module includes a display screen and a control terminal, which are used to display real-time monitoring data, analysis results and alarm information, and allow users to operate and manage the system.

2. The tunnel structure health monitoring intelligent analysis system according to claim 1 is characterized in that: The data acquisition module specifically includes: Strain gauge: When the tunnel structure is subjected to external force, the resistance value of the strain gauge changes, generating an electrical signal; Accelerometer: The accelerometer generates vibration data by measuring the acceleration changes of the tunnel structure in different directions; Laser displacement sensor: The laser displacement sensor measures displacement changes in real time and generates displacement data.

3. The tunnel structure health monitoring intelligent analysis system according to claim 2 is characterized in that: The data transmission module specifically includes: Wired communication technology: The stress, vibration and displacement data collected by the data acquisition module are transmitted to the data processing and analysis module outside the tunnel via optical fiber lines; Wireless communication technology: When the optical fiber line is interrupted or unavailable, it automatically switches to the cellular network and transmits the stress, vibration and displacement data collected by the data acquisition module to the data processing and analysis module via 4G / 5G signals; Data Encryption: Secure encryption protocols are used to ensure the security and integrity of stress, vibration, and displacement data during transmission.

4. The tunnel structure health monitoring intelligent analysis system according to claim 3 is characterized in that: The data preprocessing unit specifically includes: Data cleaning: Perform data cleaning on the received stress, vibration and displacement data, including noise removal and missing value filling; Data filtering: High-pass filtering is used to filter the received stress, vibration and displacement data; Data formatting: Format the received stress, vibration and displacement data, including unit conversion, time alignment and data standardization.

5. The tunnel structure health monitoring intelligent analysis system according to claim 4 is characterized in that: The anomaly detection unit performs real-time analysis on the processed data based on the isolation forest algorithm to identify damage and anomalies in the tunnel structure, specifically including: Data input: receiving cleaned, filtered and formatted stress, vibration and displacement data from the data pre-processing unit; Model training: Use the isolation forest algorithm to build an isolation forest model, and use historical data to train the isolation forest model; Real-time analysis: Input the real-time collected stress, vibration and displacement data into the isolation forest model to calculate the anomaly score for each data point; Anomaly determination: Based on the preset threshold, the data point is judged as abnormal. If the anomaly score exceeds the threshold, it is determined to be abnormal; Alarm mechanism: When an abnormal situation is detected, the alarm mechanism is triggered and an early warning signal is generated.

6. The tunnel structure health monitoring intelligent analysis system according to claim 5 is characterized in that: The prediction analysis unit specifically includes: Data preparation: Collect pre-processed historical data and real-time data, including stress, vibration, and displacement data of tunnel structures; Data annotation: Based on stress, vibration, and displacement data, the health status of the tunnel structure is classified as healthy, slightly damaged, or severely damaged, and the data is annotated; Feature extraction: extract features from labeled data, including time series features and statistical features; Model construction: Select the long short-term memory network model as the deep learning model and construct the model, including the input layer, long short-term memory network layer, fully connected layer, and output layer; Model training: Divide historical data and corresponding target labels into training sets and validation sets, and use the training set data to train the long short-term memory network model; Real-time prediction: Real-time data is input into the trained long-short-term memory network model, and the model outputs the predicted health status of the tunnel structure within a certain period of time in the future. The health status is classified into healthy, slightly damaged, and severely damaged; Result analysis: Analyze the prediction results and generate a health status report, which includes damage location, damage development trend and remaining life of the structure.

7. The tunnel structure health monitoring intelligent analysis system according to claim 6 is characterized in that: The alarm generating unit specifically includes: Receiving the warning signal: the alarm generation unit receives the warning signal generated by the anomaly detection unit, and triggers the alarm mechanism upon receiving the warning signal; Receiving health status: The alarm generation unit receives the tunnel structure health status report predicted by the prediction analysis unit, and triggers the alarm mechanism when the health status is slightly damaged or seriously damaged; Alarm mechanism: Alarm types include sound alarms, visual alarms and electronic alarms, and alarm information includes abnormality type, location and time.

8. The tunnel structure health monitoring intelligent analysis system according to claim 7, characterized in that: The decision suggestion unit specifically includes: Maintenance recommendations: Obtain health status reports from the predictive analysis unit and generate maintenance recommendations based on the health status reports; Repair suggestions: Provide repair suggestions based on health status classification.

9. The tunnel structure health monitoring intelligent analysis system according to claim 1, characterized in that: The user interaction module specifically includes: Display screen: The display screen is used to display real-time monitoring data, analysis results and alarm information to ensure that users understand the health status of the tunnel structure; Control terminal: The control terminal is used by users to operate and manage the system, ensuring that users can effectively monitor and maintain the tunnel structure.

Images