Tunnel water leakage detection method and system based on acoustic vibration signals

Abstract

The invention relates to a tunnel water leakage detection method and system based on sound vibration signals, in particular to the technical field of tunnel engineering. Comprising the following steps: adjusting equipment working parameters by using a tunnel water leakage monitoring model based on environment sensing data monitored by an environment sensor through a self-adaptive module; wherein the tunnel water leakage monitoring model is established based on a machine learning model, historical environment perception data and historical equipment working parameters are taken as training samples, the tunnel water leakage monitoring model is used for predicting equipment working parameters under the environment perception data, and the equipment working parameters comprise working parameters of an acoustic vibration sensor and / or an analyzer; after the working parameters of the equipment are adjusted, analyzing and processing the environment sensing data and acoustic vibration signals collected by the acoustic vibration sensor through an analyzer to obtain analysis data; and comparing the analysis data with a tunnel water leakage state change curve through a computer, and determining a tunnel water leakage area.

Description

Technical Field

[0001] This application relates to the technical field of tunnel engineering, and particularly to a method and system for detecting tunnel leakage based on acoustic and vibration signals. Background Art

[0002] In the field of tunnel engineering, leakage monitoring is a key link to ensure the structural safety and normal operation of tunnels. At present, tunnel leakage monitoring technologies mainly include traditional manual inspection methods and various conventional monitoring methods. The traditional manual inspection method relies on manual regular inspections, which not only consumes a large amount of manpower, material resources and time costs, but also due to the subjectivity and limitations of manual detection, it is difficult to accurately locate the specific location and direction of leakage, and cannot meet the high-precision requirements of modern tunnel safety monitoring. Conventional monitoring methods such as the pressure water level method and the seepage method have problems such as low monitoring accuracy and great on-site construction difficulty due to the limitations of measurement principles and technologies, and it is difficult to achieve efficient and accurate leakage monitoring in practical applications.

[0003] With the development of technology, existing tunnel leakage detection technologies based on acoustic and vibration signals have been applied. This technology installs diversion troughs in the tunnel to collect leakage from all around and the vault and divert it to a reservoir. The acoustic and vibration signals generated by the leakage in the reservoir are collected by an acoustic and vibration collector, amplified by a power amplifier and then transmitted to an analyzer, and the data is then transmitted to a computer through a switch, compared and analyzed with a preset tunnel leakage state change curve, and finally the warning information is sent to the equipment management personnel in the form of a text message by a transmitter. However, there are still many problems to be solved in the practical application of this technology: First, the structural design of the water receiving shed has limitations. The water receiving shed usually adopts a semi-cylindrical structure, which can effectively divert the leakage from the regular vault. However, in the face of complex situations where the shape of the tunnel vault is irregular, there are local depressions or protrusions, it is difficult to achieve full coverage, resulting in some leakage being unable to be smoothly introduced into the diversion trough, seriously affecting the integrity and accuracy of the monitoring system.

[0004] Second, the ability to analyze complex leakage signals is insufficient. During the actual tunnel leakage process, factors such as changes in leakage speed and the generation of bubbles will make the acoustic and vibration signals show complex and variable characteristics. Existing technologies only rely on simple comparison and analysis of the frequency and loudness of acoustic and vibration signals with curves, lacking the comprehensive processing ability of various complex signal characteristics, and unable to accurately judge the leakage state under complex working conditions.

[0005] Third, the system lacks self-diagnosis and adaptive adjustment functions. Existing monitoring systems do not have real-time self-diagnosis capabilities and cannot detect problems such as equipment operation failures and sensor abnormalities in a timely manner. At the same time, when the tunnel environment changes, such as changes in the quality of leakage water affecting the sound source characteristics and the deformation of the tunnel structure causing the displacement of the equipment installation position, the system cannot automatically adjust the monitoring parameters and the working state of the equipment, and it is difficult to ensure long-term stable operation.

[0006] Fourth, the problem of signal interference is prominent. The noise generated by vehicle driving, ventilation equipment, and operation of other mechanical equipment in the tunnel is extremely likely to be mixed with the acoustic vibration signal, interfering with the identification and analysis of the signal. Although the existing technology uses a signal integrity detection algorithm to judge signal anomalies, in a strong noise environment or when multiple water seepages occur simultaneously, this algorithm is difficult to completely eliminate interference. Especially when the acoustic vibration signals of multiple water seepage points overlap with each other, forming a complex signal pattern, it is impossible to accurately distinguish the signal characteristics of each water seepage point, seriously reducing the monitoring accuracy and reliability.

[0007] In summary, there are many defects in the existing tunnel water seepage monitoring technology, and there is an urgent need for a more efficient, accurate, and reliable monitoring technology to meet the actual engineering needs. Summary of the Invention

[0008] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a tunnel water seepage detection method and system based on acoustic vibration signals, which can realize self-diagnosis and adaptive adjustment, adapt to environmental changes, and ensure the reliability and stability of the system.

[0009] In order to achieve the above object, the technical solutions provided by the embodiments of the present application are as follows: In the first aspect, the present application provides a tunnel water seepage detection method based on acoustic vibration signals, which is applied to a tunnel water seepage detection system, including: an environmental sensor, an adaptive module, an acoustic vibration sensor, an analyzer, and a computer. The method includes: using the tunnel water leakage monitoring model to adjust the device working parameters based on the environmental perception data monitored by the environmental sensor through the adaptive module; wherein, the tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical device working parameters as training samples, and is used to predict the device working parameters under the environmental perception data. The device working parameters include the working parameters of the acoustic vibration sensor and / or the analyzer; after the device working parameters are adjusted, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data; the computer compares the analysis data with the tunnel water seepage state change curve to determine the tunnel water seepage area.

[0010] As an optional implementation manner provided in the embodiments of the present application, the tunnel water seepage detection system further includes a hardware status monitoring module; the method further includes: monitoring whether the device status parameters are within a preset parameter range through the hardware status monitoring module; the device status parameters include the status parameters of at least one device among the environmental sensor, the acoustic vibration sensor, the analyzer, and the computer; if so, it is determined that the device is in a normal working state.

[0011] As an alternative implementation provided in the embodiments of the present application, an adaptive module adjusts the device operating parameters based on the environmental perception data monitored by the environmental sensor by using a tunnel leakage monitoring model, including: determining whether the environmental perception data meets a preset environmental condition; if not, inputting the environmental perception data into the tunnel leakage monitoring model to obtain the device operating parameters output by the tunnel leakage monitoring model; and making adjustments according to the device operating parameters.

[0012] As an alternative implementation provided in the embodiments of the present application, the tunnel leakage detection system further includes an anomaly detection module; after the device operating parameters are adjusted, before the analyzer analyzes and processes the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor to obtain analysis data, the method further includes: analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signals by the anomaly detection module to determine whether the environmental perception data and the acoustic vibration signals are abnormal; in the case where the environmental perception data and the acoustic vibration signals are normal, using a deep learning model to extract the local features and global features of the environmental perception data and the acoustic vibration signals; correspondingly, analyzing and processing the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor by the analyzer to obtain analysis data, including: determining the analysis data by the analyzer based on the local features and global features.

[0013] As an alternative implementation provided in the embodiments of the present application, the characteristic parameter includes frequency; analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signals by the anomaly detection module to determine whether the environmental perception data and the acoustic vibration signals are abnormal, including: obtaining the spectral data of the environmental perception data and the acoustic vibration signals; calculating the frequency according to the spectral data, and determining whether the frequency is within a preset frequency range; if the frequency is within the preset frequency range, determining that the environmental perception data and the acoustic vibration signals are normal.

[0014] As an alternative implementation provided in the embodiments of the present application, the characteristic parameter includes amplitude; analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signals by the anomaly detection module to determine whether the environmental perception data and the acoustic vibration signals are abnormal, including: obtaining the amplitude of the acoustic vibration signal and determining the peak points of the environmental perception data and the acoustic vibration signals; calculating the fluctuation difference between the peak points; determining whether the fluctuation difference is within a preset fluctuation range; if the fluctuation difference is within the preset fluctuation range, determining that the environmental perception data and the acoustic vibration signals are normal.

[0015] In a second aspect, the present application provides a tunnel leakage detection system, which includes: An environmental sensor for monitoring environmental perception data; An adaptive module, configured to adjust the operating parameters of the device based on the environmental perception data by using a tunnel leakage monitoring model; wherein, the tunnel leakage monitoring model is built based on a machine learning model, with historical environmental perception data and historical device operating parameters as training samples, and is used to predict the device operating parameters under the environmental perception data, and the device operating parameters include the operating parameters of the acoustic vibration sensor and / or the analyzer; An acoustic vibration sensor, configured to collect acoustic vibration signals; An analyzer, configured to analyze and process the environmental perception data and the acoustic vibration signals to obtain analysis data after the device operating parameters are adjusted; A computer, configured to compare the analysis data with the tunnel leakage state change curve to determine the tunnel leakage area.

[0016] In a third aspect, the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where when the computer program is executed by the processor, it implements the tunnel leakage detection method based on acoustic vibration signals as described in the first aspect or any one of its optional implementation manners.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, including: a computer program stored on the computer-readable storage medium, where when the computer program is executed by a processor, it implements the tunnel leakage detection method based on acoustic vibration signals as described in the first aspect or any one of its optional implementation manners.

[0018] In a fifth aspect, the present application provides a computer program product, including: the computer program product includes a computer program, and when the computer program runs on a computer, it causes the computer to implement the tunnel leakage detection method based on acoustic vibration signals as described in the first aspect or any one of its optional implementation manners.

[0019] The technical solution provided by the embodiments of the present application has the following advantages compared with the prior art: The embodiments of the present disclosure provide a tunnel leakage detection method and system based on acoustic vibration signals. In the method, the adaptive module can use the trained model to predict the device operating parameters that match the currently monitored environmental perception data by the environmental sensor and perform real-time adjustment. This process realizes the function of the system to automatically adjust the device operating parameters according to environmental changes, reflecting the self-diagnosis and self-adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the device always operates in the best state, avoiding the situation that the device performance deteriorates or malfunctions due to environmental changes. Through the comprehensive analysis of the environmental perception data and the acoustic vibration sensor, the obtained analysis data is more accurate and reliable. By comparing the analysis data with the tunnel leakage state change curve, it is possible to more accurately determine whether there is leakage in the tunnel and the specific location of the leakage, improving the reliability of the system. Brief Description of the Drawings

[0020] The drawings herein are incorporated into and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0021] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 Structural schematic of a tunnel leakage detection system provided by an embodiment of the present application Figure 1 ; Figure 2 Flow schematic diagram of a tunnel leakage detection method based on acoustic vibration signals provided by an embodiment of the present application; Figure 3 Structural schematic of a tunnel leakage detection system provided by an embodiment of the present application Figure 2 ; Figure 4 Structural schematic diagram of an electronic device according to an embodiment of the present application. Detailed Embodiments

[0023] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the technical terms required for use in the description of the embodiments or the prior art.

[0024] An acoustic vibration signal is a physical signal that describes the vibration characteristics of an object and the acoustic field. When an object vibrates, it generates mechanical vibrations, which propagate in the surrounding medium to form vibration signals. These signals usually contain information such as the frequency, amplitude, and phase of the object's vibration, reflecting the vibration state and characteristics of the object. When an object vibrates, it also causes pressure changes in the surrounding medium such as air, thereby generating sound waves, and these sound waves propagating in the medium form sound signals. Sound signals also contain rich information, such as the frequency, loudness, and timbre of the sound. Through acoustic sensors such as microphones, sound signals can be converted into electrical signals for acquisition and analysis.

[0025] To solve some or all of the technical problems existing in the related art, an embodiment of the present application provides a method for detecting tunnel leakage based on acoustic vibration signals. In this method, the adaptive module can use the trained model to predict the device operating parameters that match the current environmental perception data monitored by the environmental sensor and make real-time adjustments. This process realizes the function of the system to automatically adjust the device operating parameters according to environmental changes, reflecting the self-diagnosis and adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the device always operates in the best state, avoiding the situation where the device performance deteriorates or malfunctions due to environmental changes. Through the comprehensive analysis of the environmental perception data and the acoustic vibration sensor, the obtained analysis data is more accurate and reliable. By comparing the analysis data with the tunnel leakage state change curve, it is possible to more accurately determine whether there is leakage in the tunnel and the specific location of the leakage, improving the reliability of the system.

[0026] Combined with the specific system architecture on which the execution of the method for obtaining in-band data of the server depends, the specific system architecture is described herein.

[0027] As Figure 1 shown, the tunnel leakage detection system implementing the method for detecting tunnel leakage based on acoustic vibration signals includes: an acoustic vibration sensor, an environmental sensor, an analyzer, an adaptive module, and a computer.

[0028] Among them, the environmental sensor is used to monitor environmental perception data. Optionally, the environmental perception data includes water quality data, temperature and humidity data. The water quality data includes data such as acidity and alkalinity, conductivity, etc. that can measure water quality changes.

[0029] The adaptive module is used to adjust the device operating parameters according to the environmental perception data by using the tunnel leakage monitoring model to adapt to environmental changes. The tunnel leakage monitoring model is built based on a machine learning model, using historical acoustic vibration signals and historical environmental perception data as training samples, and is used to predict the operating parameters of the acoustic vibration sensor under environmental perception data. The device operating parameters include the operating parameters of the acoustic vibration sensor and / or the analyzer.

[0030] The acoustic vibration sensor is used to collect acoustic vibration signals. The acoustic vibration sensor can be arranged in a certain pattern.

[0031] The analyzer is used to analyze and process the environmental perception data and the acoustic vibration signals to obtain analysis data after the device operating parameters are adjusted.

[0032] The computer is used to compare the analysis data with the tunnel leakage state change curve to determine the tunnel leakage area. The tunnel leakage state change curve can be established based on historical data and experience, reflecting the law of tunnel leakage situation changing with the environment.

[0033] In some embodiments, the adaptive module is specifically configured to: first determine whether the environmental perception data meets the preset environmental conditions. If not, the environmental perception data is input into the tunnel leakage monitoring model to obtain the device operating parameters output by the tunnel leakage monitoring model, and then the adjustment is made according to the device operating parameters.

[0034] Taking the pH value as an example of the environmental perception data, the adaptive module first determines whether the pH value detected by the environmental sensor is within the preset pH range. The change in pH value will affect the characteristics of the sound source. Therefore, if the pH value deviates from the preset pH range, the operating parameters of the acoustic vibration sensor are adjusted. The adjustment range of the operating parameters is obtained based on the tunnel leakage monitoring model. Through the tunnel leakage monitoring model, the optimal operating parameters can be accurately predicted according to the real-time collected environmental perception data to automatically adjust the settings and improve the monitoring accuracy.

[0035] Exemplarily, assuming that the pH value detected by the environmental sensor deviates from the preset pH range, the operating parameters of the acoustic vibration sensor, such as the sampling frequency, are adjusted based on the tunnel leakage monitoring model, so that the acoustic vibration sensor re-collects the acoustic vibration signal at the adjusted sampling frequency. Among them, the preset pH range can be 6.5 - 7.5.

[0036] In some embodiments, as Figure 1 shown, the tunnel leakage and seepage detection system further includes a power amplifier and a switch. The power amplifier is used to amplify the acoustic vibration signal and transmit it to the analyzer. The switch is used to transmit the analysis data to the computer.

[0037] In other embodiments, the tunnel leakage monitoring model is further used to predict the operating parameters of the power amplifier under the environmental perception data. Correspondingly, the adaptive module is used to adjust the operating parameters of at least one device among the acoustic vibration sensor, the analyzer, and the power amplifier based on the environmental perception data by using the tunnel leakage monitoring model. For example, assuming that the pH value detected by the environmental sensor deviates from the preset pH range, the operating parameters of the power amplifier (such as the amplification factor) are adjusted based on the tunnel leakage monitoring model, and the operating parameters of the analyzer (such as the filtering parameters) are adjusted.

[0038] The above embodiments monitor the changes in the tunnel environment and automatically adjust the operating parameters of each device in the system to adapt to the new tunnel environment, improving the reliability and long-term stability of the system.

[0039] In some embodiments, as Figure 1 shown, the tunnel leakage and seepage detection system further includes a hardware status monitoring module. The hardware status monitoring module corresponding to each hardware device is used to monitor the device status parameters of the corresponding device in real time, including but not limited to the power supply voltage, current, and operating temperature, and determine whether the device parameters are within the preset parameter range to determine whether the device is in a normal operating state.

[0040] Exemplarily, taking the hardware status monitoring module corresponding to the acoustic vibration sensor as an example, this hardware status monitoring module monitors the power supply voltage of the acoustic vibration sensor in real time, and determines whether its power supply voltage is within ±5% of the rated voltage. If so, it indicates that the acoustic vibration sensor is in a normal working state; if not, it indicates that there is a power supply problem or an internal circuit fault in the acoustic vibration sensor.

[0041] Also exemplarily, the hardware status monitoring module corresponding to the acoustic vibration sensor monitors the working temperature of the acoustic vibration sensor in real time, and determines whether its working temperature is within the normal working temperature (less than 70 °C). If so, it indicates that the acoustic vibration sensor is in a normal working state; if not, it indicates that the acoustic vibration sensor has poor heat dissipation or an internal component fault.

[0042] In the above embodiments, independent hardware status monitoring modules are configured for each device in the system. Through the hardware status monitoring module, the tunnel leakage detection system has a self-diagnosis function and can detect in real time whether each device in the system is operating normally.

[0043] In some embodiments, in multiple data transmission links, each device periodically sends a detection signal and verifies it. For example, the acoustic vibration sensor and the power amplifier, the analyzer and the switch, and the switch and the computer, they periodically send detection signals (such as heartbeat packets) to each other, and the receiving end makes a verification. If the receiving end does not receive the detection signal within the preset time, or the received detection signal is incorrect, it is determined that the data transmission link has a fault. When any data transmission link fault is detected, a connection is re-established or switched to a standby link, and a communication fault alarm is sent to the management personnel. The communication fault alarm contains information such as the fault location.

[0044] The above embodiments establish a detection and feedback mechanism for the data transmission link, which can quickly determine that the communication link has a fault, realizes the rapid detection of the link fault, avoids problems such as data transmission interruption or loss caused by the fault not being discovered for a long time, and improves the reliability and stability of the system. It helps to reduce the service interruption time caused by the link fault, improves the fault tolerance and availability of the system. The automatic recovery process does not require manual intervention, can quickly respond to the fault, and ensures the continuity of data transmission. Accurate fault location can reduce the fault troubleshooting time, improve the maintenance efficiency, enable technicians to repair the faulty link targeted, and reduce the impact on the operation of the entire system. It realizes the automatic monitoring and management of the communication link, reduces the workload of manual inspection and troubleshooting. The management personnel can understand the system operation status in time by receiving the alarm information, carry out maintenance work targeted, improve the efficiency and quality of operation and maintenance management, and reduce the operation and maintenance cost.

[0045] In some embodiments, such as Figure 1As shown in the figure, the tunnel leakage detection system further includes an anomaly detection module; the anomaly detection module is used to analyze the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal; when the environmental perception data and the acoustic vibration signal are normal, a deep learning model is used to extract the local features and global features of the environmental perception data and the acoustic vibration signal. Furthermore, based on the local features and global features of the environmental perception data and the acoustic vibration signal, an analyzer determines the analysis data.

[0046] Optionally, the characteristic parameters include but are not limited to frequency, amplitude, and phase.

[0047] Exemplarily, the anomaly detection module can obtain the spectral data of the acoustic vibration signal, then calculate the frequency of the acoustic vibration signal based on the spectral data, and determine whether the frequency of the acoustic vibration signal is within a preset frequency range. If so, it is determined that the acoustic vibration signal is normal. Among them, the preset frequency range can be 100Hz - 10kHz.

[0048] Exemplarily, the anomaly detection module can also obtain the amplitude of the acoustic vibration signal, determine the peak points of the acoustic vibration signal, then calculate the fluctuation difference between the peak points, and further determine whether the fluctuation difference is within a preset fluctuation range. If so, it is determined that the acoustic vibration signal is normal.

[0049] In the above embodiment, the signal integrity detection algorithm is used to analyze the characteristics such as the frequency, amplitude, and phase of the signal in real time to determine whether the signal is abnormal, so as to accurately determine whether the signal is interfered. By detecting signal anomalies, problems such as data loss, errors, or distortion caused by poor signal quality can be effectively avoided, ensuring the accuracy and integrity of data during transmission and processing, thereby improving the data quality of the entire system. The deep learning model is used to learn the complex characteristics of the environmental perception data and the acoustic vibration signal in time and frequency. The comprehensive analysis of local features and global features enables the model to capture various characteristic information of the leakage signal more comprehensively and meticulously, avoiding the limitations of single data source or single feature analysis, thereby significantly improving the recognition accuracy of complex leakage signals and reducing the situations of misjudgment and missed judgment.

[0050] In order to be able to more clearly understand the above objects, features, and advantages of the present application, the solution of the present application will be further described below. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0051] In the following description, many specific details are set forth in order to fully understand the present application, but the present application can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present application, rather than all the embodiments.

[0052] A method for detecting tunnel leakage based on acoustic vibration signals provided in an embodiment of the present application can be implemented by a tunnel leakage detection system or an electronic device. The electronic device includes, but is not limited to, a personal computer, a laptop computer, a tablet computer, a smart phone, etc. The operating system of the electronic device can include Android, iOS developed by Apple Inc., Windows developed by Microsoft Corporation in the United States, etc., and the embodiments of the present application do not limit this. The electronic device can run independently to implement the present application, or can be connected to a network and implement the present application through interactive operations with other computer devices in the network. Among them, the network where the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0053] It should be noted that the protection scope of a method for detecting tunnel leakage based on acoustic vibration signals described in an embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding or subtracting steps of the prior art and replacing steps according to the principle of the present application is included in the protection scope of the present application.

[0054] As Figure 2 shown, Figure 2 FIG. is a schematic flowchart of a method for detecting tunnel leakage based on acoustic vibration signals according to an embodiment of the present application. This method can be executed by a tunnel leakage detection system, and the tunnel leakage detection system includes an environmental sensor, an adaptive module, an acoustic vibration sensor, an analyzer, and a computer. This method mainly includes the following steps S201 to S203: S201. Based on the environmental perception data monitored by the environmental sensor through the adaptive module, use the tunnel leakage monitoring model to adjust the device working parameters.

[0055] Among them, the environmental sensor monitors the tunnel environment in real time and collects environmental perception data. The environmental sensor includes a water quality sensor, a temperature and humidity sensor, etc. Correspondingly, the environmental perception data includes, but is not limited to, water quality data, temperature and humidity data. The water quality data includes data such as pH value and conductivity that can measure water quality changes.

[0056] In some embodiments, the tunnel leakage detection system further includes a hardware status monitoring module. During the entire process of implementing the method for detecting tunnel leakage based on acoustic vibration signals, the hardware status monitoring module monitors in real time whether the status parameters of other devices in the system are within the preset parameter range. It can monitor the status parameters of devices such as the environmental sensor, the acoustic vibration sensor, the analyzer, and the computer. If the status parameter of a certain device is within the preset parameter range, it is determined that the device is in a normal working state; if the status parameter of a certain device exceeds the preset parameter range, it is determined that the device is in an abnormal working state.

[0057] Among them, the device status parameters include power supply voltage, current, working temperature, etc. The power supply voltage of the acoustic vibration sensor is monitored by the hardware status monitoring module, and then it is judged whether the power supply voltage is within the preset voltage range, such as ±5% of the rated voltage. If so, the acoustic vibration sensor is in a normal working state; if not, the acoustic vibration sensor is abnormal, and there may be a power supply problem or an internal circuit fault. An equipment abnormality or fault alarm can be sent to the management personnel, which contains information indicating which equipment is abnormal or faulty.

[0058] Exemplarily, it is monitored by the hardware status monitoring module whether the working temperature of the acoustic vibration sensor is within the preset temperature range, such as whether it is less than 70°C. If so, it means that the acoustic vibration sensor is in a normal working state; if not, it means that the acoustic vibration sensor has poor heat dissipation or an internal component fault.

[0059] In the above embodiment, the hardware status monitoring module monitors the device status parameters, discovers device faults or abnormalities in a timely manner, issues an alarm before the fault develops to a serious level resulting in equipment downtime or damage, thereby realizing early intervention, ensuring the long-term operation of the system, and further improving the reliability and stability of the entire system.

[0060] In some embodiments, when performing step S201, the adaptive module first judges whether the environmental perception data meets the preset environmental conditions. If not, the environmental perception data is input into the tunnel leakage monitoring model to obtain the device working parameters output by the tunnel leakage monitoring model, and then the adjustment is made according to the device working parameters. Among them, the preset environmental conditions include a preset acid-base range, a preset temperature range, a preset humidity range, and so on.

[0061] The tunnel leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical device working parameters as training samples, and is used to predict the device working parameters under the environmental perception data. The device working parameters include the working parameters of the acoustic vibration sensor, the analyzer, and the power amplifier, etc. For example, the sampling frequency of the acoustic vibration sensor, the filtering parameters of the analyzer, and the amplification factor of the power amplifier.

[0062] The steps for training a tunnel leakage monitoring model include: collecting historical environmental perception data and synchronously recording the working parameters of acoustic vibration sensors, power amplifiers, and analyzers. Then, perform data preprocessing, including data cleaning, data normalization, and data annotation, etc. Label the historical environmental perception data with the corresponding device working parameters as the labels for training the model. Select an initial machine learning model. Considering the complexity of the data and the non-linear relationship between environmental factors and device working parameters, a Multilayer Perceptron (MLP) can be selected. Divide the preprocessed data into a training set, a validation set, and a test set. The training set is used to train the model to learn the relationship between environmental perception data and device working parameters; the validation set is used to evaluate the performance of the model during model training, adjust the hyperparameters of the model, and prevent overfitting; the test set is used to evaluate the generalization ability of the model after the model training is completed. Taking the initial machine learning model as MLP as an example, it includes an input layer, a hidden layer, and an output layer. The number of neurons in the input layer is determined according to the number of input features, including features such as water quality, temperature, and humidity; multiple hidden layers can be set, and each hidden layer contains a certain number of neurons to perform non-linear transformation on the input features and learn the non-linear relationship between environmental perception data and device working parameters; the output layer contains multiple neurons, for example, corresponding to the sampling frequency of the acoustic vibration sensor, the amplification factor of the power amplifier, and the filtering parameters of the analyzer respectively. Select an appropriate loss function to measure the difference between the predicted value and the true value of the model, such as the mean squared error. Update the model parameters through optimization algorithms such as Stochastic Gradient Descent (SGD), Adaptive Moment Estimation (Adam), etc. Input the training set into the model and continuously iterate to update the model parameters, so that the value of the loss function gradually decreases. Monitor the model performance using the validation set during the training process. Use the test set to evaluate the model performance and calculate evaluation metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), etc. According to the evaluation results, adjust the hyperparameters of the model, such as the number of neurons in the hidden layer, the learning rate, the regularization parameter, etc., to improve the performance of the model.

[0063] Deploy the tunnel leakage monitoring model with training convergence to the tunnel seepage and leakage detection system to infer the optimal device operating parameters. If it is determined by the adaptive module whether the pH value monitored by the water quality sensor is within the preset pH range, if not, input the pH value deviating from the preset pH range into the tunnel leakage monitoring model to obtain the device operating parameters output by the tunnel leakage monitoring model. For example, dynamically adjust the sampling frequency of the acoustic vibration sensor between 20 kHz and 50 kHz, and / or adjust the amplification factor of the power amplifier between 500 and 2000 times. Thus, adjust the sampling frequency of the acoustic vibration sensor and / or the amplification factor of the power amplifier to adapt to environmental changes and collect new acoustic vibration signals.

[0064] In some embodiments, the water receiving shed in the present application includes a plurality of semi-cylindrical units, and adjacent units are connected by flexible splicing materials. Solve the problem of irregular shape or local depression and protrusion of the tunnel vault, so as to effectively divert the seepage and leakage water to the diversion trough, which is beneficial to improving the overall detection effect.

[0065] S202. After adjusting the device operating parameters, analyze and process the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor through an analyzer to obtain analysis data.

[0066] In some embodiments, the tunnel seepage and leakage detection system further includes a power amplifier to amplify the acoustic vibration signals collected by the acoustic vibration sensor, and then transmit the amplified acoustic vibration signals to the analyzer.

[0067] In some embodiments, after adjusting the device operating parameters of at least one of the acoustic vibration sensor, the power amplifier, and the analyzer, before the analyzer analyzes the environmental perception data and the acoustic vibration signals, first analyze the characteristic parameters of the environmental perception data and the acoustic vibration signals through an anomaly detection module to determine whether the acoustic vibration signals are abnormal; in the case where the environmental perception data and the acoustic vibration signals are normal, use a deep learning model to extract the local and global features of the environmental perception data and the acoustic vibration signals. Then perform step S202, and determine the analysis data based on the local and global features of the environmental perception data and the acoustic vibration signals through the analyzer.

[0068] Among them, the characteristic parameters of the environmental perception data and the acoustic vibration signals include but are not limited to frequency, amplitude, and phase.

[0069] The deep learning model is pre-trained to learn the pattern features of environmental perception data and acoustic vibration signals in terms of time and frequency. For environmental perception data, the deep learning model can extract features such as the change trends of temperature and humidity, and the changes in the chemical components of water quality; for acoustic vibration signals, it can extract frequency features (such as main frequency, frequency spectrum distribution), amplitude features (such as peak value, mean value), phase features, etc. The deep learning model can be a convolutional neural network, which can extract local features and global features, and can capture various feature information of leakage signals more comprehensively and meticulously, avoiding the limitations of single data source or single feature analysis. After comprehensive analysis, complex leakage signals can be identified, such as acoustic vibration signals caused by rapid changes in leakage speed, and acoustic vibration signals accompanied by the generation of bubbles. The deep learning model can capture the subtle changes and early features of leakage water signals more acutely.

[0070] Optionally, the spectral data of the acoustic vibration signal and the spectral data of the environmental perception data are obtained through the anomaly detection module, and then the frequency of the acoustic vibration signal is calculated based on the spectral data, and the frequency of the environmental perception data is calculated. It is judged whether the frequency of the acoustic vibration signal is within the preset frequency range. If so, it is determined that the acoustic vibration signal is normal. Among them, the preset frequency range can be 100 Hz - 10 kHz. It is judged whether the frequency of the environmental perception data shows frequent and irregular large fluctuations in a short period of time. If so, it indicates that the environmental perception data changes abnormally, which may be due to external interference on the sensor, such as electromagnetic interference, mechanical vibration, etc., or a malfunction of the sensor itself, resulting in distorted collected data.

[0071] Exemplarily, the numpy.fft.fft function is called through the anomaly detection module to perform a fast Fourier transform (FFT) on the acoustic vibration signal signal_data to obtain the spectral data of the acoustic vibration signal signal_data, and then the frequency of the acoustic vibration signal is calculated based on the spectral data, and it is judged whether the frequency of the acoustic vibration signal is within 100 Hz - 10 kHz. Optionally, the amplitude of the acoustic vibration signal and the amplitude of the environmental perception data are obtained through the anomaly detection module, and the peak points of the acoustic vibration signal and the peak points of the environmental perception data are determined, and then the fluctuation difference between the respective peak points is calculated, and then it is judged whether the fluctuation difference is within the preset fluctuation range. If so, it is determined that the acoustic vibration signal is normal. The fluctuation difference can be a difference value, a ratio value, etc.

[0072] Exemplarily, the anomaly detection module calls scipy.signal.find_peaks to obtain the amplitude of the acoustic vibration signal signal_data and determine the peak points of the acoustic vibration signal. Then, calculate the fluctuation ratio between adjacent peak points, and further determine whether the fluctuation ratio is between 0.5 and 2. If the fluctuation ratio exceeds this range, it is considered that the amplitude fluctuation is abnormal. If the amplitude change of the ambient perception data collected at adjacent times, such as temperature and humidity data, is too large, the temperature at the previous moment is 25°C and suddenly changes to 35°C at the next moment, and this change does not conform to the influence of known heat sources, cold sources, etc. in the environment, then this data may be abnormal, possibly due to excessive sensor measurement error or interference by sudden factors.

[0073] When the ambient perception data and the acoustic vibration signal are normal, after extracting the local features and global features, the analyzer comprehensively analyzes and processes the local features and global features of the ambient perception data and the acoustic vibration signal to obtain analysis data. Under different geological conditions and climatic environments, the acoustic vibration characteristics of seepage water may vary. Combining the ambient perception data can more accurately identify these characteristics. Through the comprehensive analysis of these two types of data, a more comprehensive and accurate understanding of the actual situation in the tunnel can be obtained, adapting to various changes that may occur in tunnel engineering.

[0074] The analysis and processing include filtering, positioning, fusion, etc. The analysis data can be a fusion feature vector containing the position information of the acoustic vibration signal after filtering.

[0075] There may be various external noise sources in the tunnel, such as vehicle driving noise, ventilation equipment noise, other mechanical equipment noise, etc. These noises may be mixed with the acoustic vibration signal, resulting in signal interference and affecting the signal recognition and analysis. In this application, the analyzer filters the acoustic vibration signal to reduce the influence of external noise.

[0076] During the actual acquisition process of acoustic-vibration signals, due to multiple water seepage points or interference between sounds during propagation, the received signal is a superposition of multiple signals, that is, the acoustic-vibration signals overlap. This overlap makes the signals received by a single sensor complex, and it is difficult to directly distinguish the characteristics and location information of each water seepage point from them. In this application, an analyzer uses array signal processing technology to locate the acoustic-vibration signals. Specifically, by processing and analyzing the acoustic-vibration signals received by each acoustic-vibration sensor, and using the propagation differences of acoustic-vibration signals between different acoustic-vibration sensors, such as time delay, phase difference, etc., to obtain the direction information of the acoustic-vibration signals and separate the acoustic-vibration signals in different directions; or, perform operations such as weighted summation on the acoustic-vibration signals received by the acoustic-vibration sensor array to enhance the acoustic-vibration signals from a specific direction while suppressing the acoustic-vibration signals in other directions, so as to achieve the separation of acoustic-vibration signals in different directions; or, utilize the spatial correlation and noise characteristics of acoustic-vibration signals, and estimate the direction of arrival of the signals through mathematical operations such as eigen-decomposition on the data received by the acoustic-vibration sensor array, and separate and locate the signals according to the direction information.

[0077] The analyzer uses multi-sensor fusion and data fusion algorithms to fuse the environmental perception data and acoustic-vibration signals. Specifically, select the most representative and discriminative features for water seepage monitoring from a large number of extracted features, remove redundant and irrelevant features, reduce the feature dimension, and improve the fusion efficiency and accuracy. Fuse the environmental perception data features and acoustic-vibration signal features that have been selected and dimension-reduced. The feature vectors can be concatenated to form a new fused feature vector. S203. Compare the analysis data with the tunnel water seepage state change curve through a computer to determine the tunnel water seepage area.

[0078] The analysis data is obtained by comprehensively considering the environmental perception data and acoustic-vibration signals, and contains the location information of the acoustic-vibration signals.

[0079] In some embodiments, the tunnel leakage monitoring model can also be used to predict the change curve of the tunnel seepage and leakage state, which reflects the law of the tunnel seepage and leakage situation changing with the environment. By adding the step of collecting leakage situation data to the above-mentioned steps of training the tunnel leakage monitoring model, the leakage situation at different positions of the tunnel can be recorded through manual inspection, water level monitoring, etc., and marked as static information such as whether there is leakage and the degree of leakage. Record the change of the leakage situation over time at a certain time interval to form time series data of the leakage situation, and thus construct the change curve of the tunnel seepage and leakage state. When annotating the data, label the historical environmental monitoring data and historical acoustic vibration signals according to the corresponding change trend of the leakage situation, and at the same time construct a time series data structure suitable for model input. For example, the environmental monitoring data, acoustic vibration signals and leakage situation within a period of time are used as a sample. A model suitable for processing sequence data can be selected to construct an initial model, such as variants of recurrent neural networks (RNN) such as long short-term memory networks (LSTM) and gated recurrent units (GRU), or a hybrid model combining convolutional neural networks (CNN) and RNN. Then divide the data set, define the loss function, select the optimization algorithm to train the model, and evaluate the model and adjust the model hyperparameters to finally obtain a trained model. Deploy the trained tunnel leakage monitoring model to the tunnel seepage and leakage detection system to generate the change curve of the tunnel seepage and leakage state according to the current environmental perception data and acoustic vibration signals.

[0080] In any of the above embodiments, there is a data transmission link between devices, and the link is verified for faults by periodically sending detection signals. For example, between the acoustic vibration sensor and the power amplifier, by periodically sending detection signals (such as heartbeat packets) to each other and verifying, if the acoustic vibration sensor does not receive the detection signal sent by the power amplifier within the preset time, or the received detection signal is incorrect, it is determined that the data transmission link between the acoustic vibration sensor and the power amplifier has a fault. The present application also establishes a fault feedback mechanism. When any data transmission link fault is detected, a connection is re-established or switched to a standby link, and a communication fault alarm is sent to the management personnel. The communication fault alarm contains information such as the fault location.

[0081] In some embodiments, after executing step S203, it further includes determining whether the tunnel seepage and leakage area is in a risk area or a dangerous area. If so, a warning message is generated and sent to the management personnel, so that the management personnel can quickly take measures to prevent the seepage and leakage problem from deteriorating further and ensure the safety and normal use of the tunnel.

[0082] In the above steps S201 - S203, the system adapts to the changes in the tunnel environment, automatically adjusts the monitoring parameters of each device, improves the flexibility and adaptability of the system, and also improves the accuracy of tunnel leakage detection; reduces manual intervention, lowers labor costs, and improves detection efficiency. By comprehensively analyzing the environmental perception data and the acoustic - vibration signals, it comprehensively identifies the leakage situation, reducing misjudgment and missed judgment.

[0083] As Figure 3 shown, Figure 3 Figure 1 is a schematic structural diagram of a tunnel leakage detection system provided by an embodiment of the present application. Figure 2 The system includes: An environmental sensor 301 for monitoring environmental perception data; An adaptive module 302 for adjusting the device operating parameters based on the environmental perception data using a tunnel leakage monitoring model; wherein, the tunnel leakage monitoring model is built based on a machine - learning model, using historical environmental perception data and historical device operating parameters as training samples, for predicting the device operating parameters under the environmental perception data, and the device operating parameters include the operating parameters of the acoustic - vibration sensor and / or the analyzer; An acoustic - vibration sensor 303 for collecting acoustic - vibration signals; An analyzer 304 for analyzing and processing the environmental perception data and the acoustic - vibration signals to obtain analysis data after the device operating parameters are adjusted; A computer 305 for comparing the analysis data with the tunnel leakage state change curve to determine the tunnel leakage area.

[0084] As an optional implementation manner provided in the embodiment of the present application, the tunnel leakage detection system further includes a hardware status monitoring module; the hardware status monitoring module is used to monitor whether the device status parameters are within a preset parameter range; the device status parameters include the status parameters of at least one device among the environmental sensor, the acoustic - vibration sensor, the analyzer, and the computer; if so, it is determined that the device is in a normal operating state.

[0085] As an optional implementation manner provided in the embodiment of the present application, the adaptive module 302 is specifically used for: determining whether the environmental perception data meets a preset environmental condition; if not, inputting the environmental perception data into the tunnel leakage monitoring model to obtain the device operating parameters output by the tunnel leakage monitoring model; and adjusting according to the device operating parameters.

[0086] As an alternative implementation provided in the embodiments of the present application, the tunnel leakage detection system further includes an anomaly detection module; the anomaly detection module is configured to analyze the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal; in the case where the environmental perception data and the acoustic vibration signal are normal, a deep learning model is used to extract the local features and global features of the environmental perception data and the acoustic vibration signal; correspondingly, the analyzer 304 is specifically configured to: determine the analysis data based on the local features and the global features through the analyzer.

[0087] As an alternative implementation provided in the embodiments of the present application, the characteristic parameters include frequency; the anomaly detection module is specifically configured to: obtain the spectrum data of the environmental perception data and the acoustic vibration signal; calculate the frequency according to the spectrum data, and determine whether the frequency is within a preset frequency range; if the frequency is within the preset frequency range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0088] As an alternative implementation provided in the embodiments of the present application, the characteristic parameters include amplitude; the anomaly detection module is specifically configured to: obtain the amplitude of the acoustic vibration signal and determine the peak points of the environmental perception data and the acoustic vibration signal; calculate the fluctuation difference between the peak points; determine whether the fluctuation difference is within a preset fluctuation range; if the fluctuation difference is within the preset fluctuation range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0089] For the specific limitations of the tunnel leakage detection system, reference can be made to the limitations of the tunnel leakage detection method based on the acoustic vibration signal in the above text, which will not be elaborated here. Each module in the above tunnel leakage detection system can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in the processor in the computer device in the form of hardware or independent of it, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0090] The embodiments of the present application also provide an electronic device, such as Figure 4 shown, including a memory 402 and a processor 401. The memory 402 stores a computer program, and the processor 401 is configured to run the computer program to execute the steps in any of the above embodiments of the method for obtaining in-band data of the server. In one embodiment, the present application provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: Based on the environmental perception data monitored by the environmental sensor through the adaptive module, the working parameters of the device are adjusted using the tunnel water leakage monitoring model; among them, the tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical device working parameters as training samples, and is used to predict the device working parameters under the environmental perception data. The device working parameters include the working parameters of the acoustic vibration sensor and / or the analyzer; after the device working parameters are adjusted, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data; the computer compares the analysis data with the tunnel seepage water state change curve to determine the tunnel seepage water area.

[0091] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The tunnel seepage water detection system further includes a hardware status monitoring module; the method further includes: through the hardware status monitoring module, monitoring whether the device status parameters are within the preset parameter range; the device status parameters include the status parameters of at least one device among the environmental sensor, the acoustic vibration sensor, the analyzer, and the computer; if so, it is determined that the device is in a normal working state.

[0092] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Based on the environmental perception data monitored by the environmental sensor through the adaptive module, adjusting the device working parameters using the tunnel water leakage monitoring model includes: determining whether the environmental perception data meets the preset environmental conditions; if not, inputting the environmental perception data into the tunnel water leakage monitoring model to obtain the device working parameters output by the tunnel water leakage monitoring model; and adjusting according to the device working parameters.

[0093] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The tunnel seepage water detection system further includes an anomaly detection module; before the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data after the device working parameters are adjusted, the method further includes: analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal through the anomaly detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal; in the case where the environmental perception data and the acoustic vibration signal are normal, using a deep learning model to extract the local features and global features of the environmental perception data and the acoustic vibration signal; correspondingly, analyzing and processing the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor by the analyzer to obtain analysis data includes: determining the analysis data by the analyzer based on the local features and global features.

[0094] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The characteristic parameter includes frequency; the anomaly detection module analyzes the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining the spectral data of the environmental perception data and the acoustic vibration signal; calculating the frequency according to the spectral data, and determining whether the frequency is within a preset frequency range; if the frequency is within the preset frequency range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0095] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The characteristic parameter includes amplitude; the anomaly detection module analyzes the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining the amplitude of the acoustic vibration signal and determining the peak points of the environmental perception data and the acoustic vibration signal; calculating the fluctuation difference between the peak points; determining whether the fluctuation difference is within a preset fluctuation range; if the fluctuation difference is within the preset fluctuation range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0096] When the processor in the electronic device provided in this application executes the computer program, first, the adaptive module adjusts the device working parameters by using the tunnel leakage monitoring model based on the environmental perception data monitored by the environmental sensor; wherein, the tunnel leakage monitoring model is built based on the machine learning model, and uses the historical environmental perception data and the historical device working parameters as training samples to predict the device working parameters under the environmental perception data, and the device working parameters include the working parameters of the acoustic vibration sensor and / or the analyzer; after the device working parameters are adjusted, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data; the computer compares the analysis data with the tunnel leakage state change curve to determine the tunnel leakage area. In this way, the adaptive module can use the trained model to predict the device working parameters matching the current environmental perception data monitored by the environmental sensor and make real-time adjustments. This process realizes the function of the system automatically adjusting the device working parameters according to the environmental changes, reflecting the self-diagnosis and self-adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the device always works in the best state, avoiding the situation that the device performance deteriorates or malfunctions due to environmental changes. Through the comprehensive analysis of the environmental perception data and the acoustic vibration sensor, the obtained analysis data is more accurate and reliable. By comparing the analysis data with the tunnel leakage state change curve, it is possible to more accurately determine whether there is leakage in the tunnel and the specific location of the leakage, improving the reliability of the system.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a computer, the following steps are implemented: Based on the environmental perception data monitored by the environmental sensor through the adaptive module, the working parameters of the device are adjusted using the tunnel leakage monitoring model; among them, the tunnel leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical device working parameters as training samples to predict the device working parameters under environmental perception data, and the device working parameters include the working parameters of the acoustic vibration sensor and / or the analyzer; after the device working parameters are adjusted, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data; the computer compares the analysis data with the tunnel leakage and water seepage state change curve to determine the tunnel leakage and water seepage area.

[0098] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the tunnel leakage and water seepage detection system further includes a hardware status monitoring module; the method further includes: through the hardware status monitoring module, monitoring whether the device status parameters are within the preset parameter range; the device status parameters include the status parameters of at least one device among the environmental sensor, the acoustic vibration sensor, the analyzer, and the computer; if so, it is determined that the device is in a normal working state.

[0099] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the environmental perception data monitored by the environmental sensor through the adaptive module, adjusting the device working parameters using the tunnel leakage monitoring model, including: determining whether the environmental perception data meets the preset environmental conditions; if not, inputting the environmental perception data into the tunnel leakage monitoring model to obtain the device working parameters output by the tunnel leakage monitoring model; and adjusting according to the device working parameters.

[0100] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the tunnel leakage and water seepage detection system further includes an anomaly detection module; before the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data after the device working parameters are adjusted, the method further includes: analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal through the anomaly detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal; in the case where the environmental perception data and the acoustic vibration signal are normal, using a deep learning model to extract the local features and global features of the environmental perception data and the acoustic vibration signal; correspondingly, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data, including: determining the analysis data by the analyzer based on the local features and global features.

[0101] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The characteristic parameter includes frequency; the anomaly detection module analyzes the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining the spectral data of the environmental perception data and the acoustic vibration signal; calculating the frequency according to the spectral data, and determining whether the frequency is within a preset frequency range; if the frequency is within the preset frequency range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0102] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The characteristic parameter includes amplitude; the anomaly detection module analyzes the characteristic parameters of the environmental perception data and the acoustic vibration signal to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining the amplitude of the acoustic vibration signal and determining the peak points of the environmental perception data and the acoustic vibration signal; calculating the fluctuation difference between the peak points; determining whether the fluctuation difference is within a preset fluctuation range; if the fluctuation difference is within the preset fluctuation range, it is determined that the environmental perception data and the acoustic vibration signal are normal.

[0103] When the computer program in the computer-readable storage medium provided by the present application executes the computer program, first, the adaptive module adjusts the device working parameters by using the tunnel leakage monitoring model based on the environmental perception data monitored by the environmental sensor; wherein, the tunnel leakage monitoring model is built based on the machine learning model, and the historical environmental perception data and the historical device working parameters are used as training samples to predict the device working parameters under the environmental perception data, and the device working parameters include the working parameters of the acoustic vibration sensor and / or the analyzer; after the device working parameters are adjusted, the analyzer analyzes and processes the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor to obtain analysis data; the computer compares the analysis data with the tunnel leakage and water seepage state change curve to determine the tunnel leakage and water seepage area. In this way, the adaptive module can predict the device working parameters matching the current environmental perception data monitored by the environmental sensor by using the trained model and make real-time adjustments. This process realizes the function of the system automatically adjusting the device working parameters according to the environmental changes, reflecting the self-diagnosis and self-adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the device always works in the best state, avoiding the situation that the device performance deteriorates or fails due to environmental changes. Through the comprehensive analysis of the environmental perception data and the acoustic vibration sensor, the obtained analysis data is more accurate and reliable. By comparing the analysis data with the tunnel leakage and water seepage state change curve, it is possible to more accurately judge whether there is leakage and water seepage in the tunnel and the specific location of the leakage and water seepage, improving the reliability of the system.

[0104] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0105] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the apparatus, method, and computer program product according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0106] In the present application, the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc.

[0107] In the present application, the memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0108] In this application, computer-readable media include both permanent and non-permanent, removable and non-removable storage media. The storage media can implement information storage by any method or technology, and the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory media such as modulated data signals and carrier waves.

[0109] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0110] The above are only specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting tunnel leakage based on acoustic and vibration signals, characterized in that Applied to a tunnel seepage and leakage detection system, including: an environmental sensor, an adaptive module, a sound and vibration sensor, an analyzer, and a computer. The method includes: Based on the environmental perception data monitored by the environmental sensor through the adaptive module, using a tunnel leakage monitoring model to adjust the device operating parameters; wherein, the tunnel leakage monitoring model is built based on a machine learning model, with historical environmental perception data and historical device operating parameters as training samples, and is used to predict the device operating parameters under environmental perception data. The device operating parameters include the operating parameters of the sound and vibration sensor and / or the analyzer; After the device operating parameters are adjusted, analyze and process the environmental perception data and the sound and vibration signals collected by the sound and vibration sensor through the analyzer to obtain analysis data; Compare the analysis data with the tunnel seepage and leakage state change curve through the computer to determine the tunnel seepage and leakage area.

2. The method according to claim 1, characterized in that, The tunnel seepage and leakage detection system further includes a hardware status monitoring module; The method further includes: Through the hardware status monitoring module, monitor whether the device status parameters are within the preset parameter range; the device status parameters include the status parameters of at least one device among the environmental sensor, the sound and vibration sensor, the analyzer, and the computer; If so, determine that the device is in a normal operating state.

3. The method according to claim 1, wherein The step of adjusting the device operating parameters based on the environmental perception data monitored by the environmental sensor through the adaptive module using the tunnel leakage monitoring model includes: Judge whether the environmental perception data meets the preset environmental conditions; If not, input the environmental perception data into the tunnel leakage monitoring model to obtain the device operating parameters output by the tunnel leakage monitoring model; Adjust according to the device operating parameters.

4. The method according to claim 1, wherein The tunnel seepage and leakage detection system further includes an anomaly detection module; Before analyzing and processing the environmental perception data and the sound and vibration signals collected by the sound and vibration sensor through the analyzer after the device operating parameters are adjusted to obtain analysis data, the method further includes: Analyze the characteristic parameters of the environmental perception data and the sound and vibration signals through the anomaly detection module to judge whether the environmental perception data and the sound and vibration signals are abnormal; In the case where the environmental perception data and the sound and vibration signals are normal, use a deep learning model to extract the local features and global features of the environmental perception data and the sound and vibration signals; Correspondingly, the step of analyzing and processing the environmental perception data and the sound and vibration signals collected by the sound and vibration sensor through the analyzer to obtain analysis data includes: determining the analysis data through the analyzer based on the local features and the global features.

5. The method according to claim 4, characterized in that The characteristic parameters include frequency; The step of analyzing the characteristic parameters of the environmental perception data and the sound and vibration signals through the anomaly detection module to judge whether the environmental perception data and the sound and vibration signals are abnormal includes: Obtain the spectrum data of the environmental perception data and the sound and vibration signals; Calculate the frequency according to the spectrum data and judge whether the frequency is within the preset frequency range; If the frequency is within the preset frequency range, it is determined that the environmental perception data and the acoustic-vibration signal are normal.

6. The method according to claim 4, characterized in that The characteristic parameters include amplitude. The abnormal detection module analyzes the characteristic parameters of the environmental perception data and the acoustic-vibration signal to determine whether the environmental perception data and the acoustic-vibration signal are abnormal, including: Obtaining the amplitude of the acoustic-vibration signal and determining the peak points of the environmental perception data and the acoustic-vibration signal; Calculating the fluctuation difference between the peak points; Judging whether the fluctuation difference is within a preset fluctuation range; If the fluctuation difference is within the preset fluctuation range, it is determined that the environmental perception data and the acoustic-vibration signal are normal.

7. A tunnel leakage detection system, characterized in that Including: An environmental sensor for monitoring environmental perception data; An adaptive module for adjusting the device working parameters based on the environmental perception data by using a tunnel water leakage monitoring model; wherein, the tunnel water leakage monitoring model is built based on a machine learning model, with historical environmental perception data and historical device working parameters as training samples, and is used to predict the device working parameters under the environmental perception data. The device working parameters include the working parameters of an acoustic-vibration sensor and / or an analyzer; An acoustic-vibration sensor for collecting acoustic-vibration signals; An analyzer for analyzing and processing the environmental perception data and the acoustic-vibration signal to obtain analysis data after the device working parameters are adjusted; A computer for comparing the analysis data with the tunnel water seepage state change curve to determine the tunnel water seepage area.

8. An electronic device, characterized in that, Including: A processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the tunnel water seepage detection method based on an acoustic-vibration signal according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Including: A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the tunnel water seepage detection method based on an acoustic-vibration signal according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Including: The computer program product includes a computer program. When the computer program runs on a computer, it enables the computer to implement the tunnel water seepage detection method based on an acoustic-vibration signal according to any one of claims 1 to 6.

Images