A tunnel water leakage detection method and system based on acoustic vibration signals

Abstract

The present application relates to a tunnel water leakage detection method and system based on acoustic vibration signals, and particularly to the field of tunnel engineering technology. The method comprises: adjusting equipment operating parameters using a tunnel water leakage monitoring model based on environmental perception data monitored by environmental sensors through an adaptive module; wherein the tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples, and is used to predict equipment operating parameters under environmental perception data, wherein the equipment operating parameters include operating parameters of acoustic vibration sensors and / or analyzers; after the equipment operating parameters are adjusted, the environmental perception data and acoustic vibration signals collected by the acoustic vibration sensors are analyzed and processed by an analyzer to obtain analysis data; and the analysis data is compared with a tunnel water leakage state change curve by a computer to determine the tunnel water leakage area.

Description

Technical Field

[0001] The present application relates to the field of tunnel engineering technology, and in particular to a method and system for detecting tunnel water leakage based on acoustic vibration signals. Background Art

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

[0003] With the development of technology, tunnel water leakage detection technology based on acoustic vibration signals has been applied. This technology installs diversion troughs in the tunnel to collect water leakage around the perimeter and vault and divert it to a water reservoir. The acoustic vibration signals generated by the leaking water in the reservoir are collected by an acoustic vibration collector, amplified by a power amplifier, and transmitted to an analyzer. The data is then transmitted to a computer through a switch for comparison and analysis with a preset tunnel water seepage status change curve. Finally, a transmitter sends an early warning message to the equipment management personnel in the form of a text message. However, there are still many problems that need to be solved in the actual application of this technology:

[0004] First, the structural design of the water collection shed has limitations. While this typically utilizes a semi-cylindrical structure, which effectively diverts leaking water from regular vaults, it struggles to achieve full coverage when faced with complex tunnel vaults with irregular shapes and localized depressions or protrusions. This prevents some leaking water from being successfully directed into the diversion trough, seriously impacting the integrity and accuracy of the monitoring system.

[0005] Second, the ability to analyze complex leakage signals is insufficient. In actual tunnel water leakage, factors such as changes in leakage velocity and bubble generation can cause acoustic and vibration signals to exhibit complex and variable characteristics. Existing technologies rely solely on simple comparative analysis of acoustic and vibration signal frequency and loudness against curves, lacking the ability to comprehensively process multiple complex signal characteristics and unable to accurately determine leakage status under complex operating conditions.

[0006] Third, the system lacks self-diagnosis and adaptive adjustment capabilities. Existing monitoring systems lack real-time self-diagnosis capabilities, making them unable to promptly detect equipment malfunctions, sensor anomalies, and other issues. Furthermore, when the tunnel environment changes—for example, if leaking water quality changes, affecting the sound source characteristics, or if tunnel structural deformation causes equipment installation position shifts—the system cannot automatically adjust monitoring parameters and equipment operating status, making it difficult to ensure long-term stable operation.

[0007] Fourth, signal interference is a significant issue. Noise generated by vehicles, ventilation equipment, and other mechanical equipment in tunnels can easily mix with acoustic and vibration signals, interfering with signal identification and analysis. Although existing technologies use signal integrity detection algorithms to identify signal anomalies, these algorithms struggle to completely eliminate interference in high-noise environments or when multiple water leaks occur simultaneously. This is especially true when acoustic and vibration signals from multiple leaks overlap, forming complex signal patterns. This makes it impossible to accurately distinguish the signal characteristics of each leak, severely reducing monitoring accuracy and reliability.

[0008] In summary, the existing tunnel water leakage monitoring technology has many defects, and there is an urgent need for a more efficient, accurate and reliable monitoring technology to meet actual engineering needs. Summary of the Invention

[0009] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a tunnel water leakage detection method and system based on acoustic vibration signals, which can realize self-diagnosis and adaptive adjustment, adapt to environmental changes, and ensure system reliability and stability.

[0010] In order to achieve the above objectives, the technical solutions provided in the embodiments of the present application are as follows:

[0011] In the first aspect, the present application provides a tunnel water leakage detection method based on acoustic vibration signals, which is applied to a tunnel water leakage detection system, including: an environmental sensor, an adaptive module, an acoustic vibration sensor, an analyzer and a computer. The method includes: adjusting the equipment operating parameters using a tunnel water leakage monitoring model 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 equipment operating parameters as training samples, and is used to predict the equipment operating parameters under the environmental perception data, and the equipment operating parameters include the operating parameters of the acoustic vibration sensor and / or the analyzer; after the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer to obtain analysis data; the analysis data is compared with the tunnel water leakage state change curve by the computer to determine the tunnel water leakage area.

[0012] As an optional implementation provided in an embodiment of the present application, the tunnel water leakage detection system also includes a hardware status monitoring module; the method also includes: monitoring whether the equipment status parameters are within a preset parameter range through the hardware status monitoring module; the equipment status parameters include the status parameters of at least one device among an environmental sensor, an acoustic vibration sensor, an analyzer and a computer; if so, it is determined that the equipment is in normal working condition.

[0013] As an optional implementation provided in an embodiment of the present application, an adaptive module uses environmental perception data monitored by environmental sensors and a tunnel leakage monitoring model to adjust the equipment operating parameters, including: determining whether the environmental perception data meets preset environmental conditions; if not, inputting the environmental perception data into the tunnel leakage monitoring model to obtain the equipment operating parameters output by the tunnel leakage monitoring model; and adjusting according to the equipment operating parameters.

[0014] As an optional implementation provided in an embodiment of the present application, the tunnel water leakage detection system also includes an anomaly detection module; after the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer, and before obtaining the analysis data, the method also 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; when the environmental perception data and the acoustic vibration signals are normal, using a deep learning model to extract local features and global features of the environmental perception data and the acoustic vibration signals; accordingly, 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 based on the local features and the global features by the analyzer.

[0015] As an optional implementation provided in an embodiment of the present application, the characteristic parameters include frequency; analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal by the abnormality detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining spectrum data of the environmental perception data and the acoustic vibration signal; calculating the frequency based on the spectrum 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 signal are normal.

[0016] As an optional implementation provided in an embodiment of the present application, the characteristic parameters include amplitude; the characteristic parameters of the environmental perception data and the acoustic vibration signal are analyzed by the abnormality detection module 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, determining that the environmental perception data and the acoustic vibration signal are normal.

[0017] In a second aspect, the present application provides a tunnel water leakage detection system, the system comprising:

[0018] Environmental sensors, used to monitor environmental perception data;

[0019] An adaptive module for adjusting equipment operating parameters based on environmental perception data using a tunnel water leakage monitoring model. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples. The model is used to predict equipment operating parameters based on environmental perception data, including those of acoustic vibration sensors and / or analyzers.

[0020] An acoustic vibration sensor, used for collecting acoustic vibration signals;

[0021] Analyzer, used to analyze and process environmental perception data and acoustic vibration signals to obtain analytical data after the equipment operating parameters are adjusted;

[0022] The computer is used to compare the analysis data with the tunnel water leakage state change curve to determine the tunnel water leakage area.

[0023] In a third aspect, the present application provides an electronic device comprising: 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, the method for detecting tunnel water leakage based on acoustic vibration signals as described in the first aspect or any one of its optional embodiments is implemented.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, comprising: a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the tunnel water leakage detection method based on acoustic vibration signals as described in the first aspect or any one of its optional embodiments.

[0025] In a fifth aspect, the present application provides a computer program product, comprising: the computer program product includes a computer program, and when the computer program is run on a computer, the computer implements the tunnel water leakage detection method based on acoustic vibration signals as described in the first aspect or any one of its optional embodiments.

[0026] The technical solution provided by the embodiments of the present application has the following advantages compared with the prior art:

[0027] The disclosed embodiments provide a method and system for detecting tunnel water leakage based on acoustic vibration signals, wherein the adaptive module in the method can predict the matching equipment operating parameters based on the current environmental perception data monitored by the environmental sensor using a trained model, and make real-time adjustments. This process enables the system to automatically adjust the equipment operating parameters according to environmental changes, reflecting the self-diagnosis and adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the equipment always operates in the best condition, avoiding the situation where equipment performance deteriorates or malfunctions due to environmental changes. Through the comprehensive analysis of environmental perception data and acoustic vibration sensors, the analysis data obtained is more accurate and reliable. By comparing the analysis data with the tunnel water leakage state change curve, it is possible to more accurately determine whether there is water leakage in the tunnel and the specific location of the water leakage, thereby improving the reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0030] Figure 1 A schematic diagram of the structure of a tunnel water leakage detection system provided in an embodiment of the present application Figure 1 ;

[0031] Figure 2 A schematic flow chart of a method for detecting tunnel water leakage based on acoustic vibration signals provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of the structure of a tunnel water leakage detection system provided in an embodiment of the present application Figure 2 ;

[0033] Figure 4 This is a schematic structural diagram of an electronic device described in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the technical terms required to be used in the embodiments or the description of the prior art will be briefly introduced below.

[0035] Vibroacoustic signals are physical signals that describe the vibration and acoustic field characteristics of an object. When an object vibrates, it generates mechanical vibrations that propagate through the surrounding medium, forming vibration signals. These signals typically contain information such as the frequency, amplitude, and phase of the object's vibrations, reflecting the object's vibration state and characteristics. When an object vibrates, it also causes pressure changes in the surrounding medium, such as the air, generating sound waves. These sound waves propagate through the medium, forming acoustic signals. Acoustic signals also contain a wealth of information, such as frequency, loudness, and timbre. Acoustic sensors, such as microphones, can convert acoustic signals into electrical signals for collection and analysis.

[0036] In order to solve some or all of the technical problems existing in the related art, an embodiment of the present application provides a tunnel water leakage detection method based on acoustic vibration signals, wherein the adaptive module in the method can predict the matching equipment operating parameters based on the current environmental perception data monitored by the environmental sensor using a trained model and make real-time adjustments. This process realizes the function of the system to automatically adjust the equipment operating parameters according to environmental changes, reflecting the self-diagnosis and adaptive adjustment capabilities; this dynamic adjustment mechanism also ensures that the equipment always works in the best state, avoiding the situation where the equipment performance deteriorates or fails due to environmental changes. Through the comprehensive analysis of environmental perception data and acoustic vibration sensors, the analysis data obtained is more accurate and reliable. By comparing the analysis data with the tunnel water leakage state change curve, it is possible to more accurately determine whether there is water leakage in the tunnel and the specific location of the water leakage, thereby improving the reliability of the system.

[0037] In conjunction with the specific system architecture on which the execution of the method for obtaining in-band data from a server depends, the specific system architecture is described herein.

[0038] like Figure 1 As shown, a tunnel water leakage detection system implementing a tunnel water leakage detection method based on acoustic vibration signals includes: an acoustic vibration sensor, an environmental sensor, an analyzer, an adaptive module, and a computer.

[0039] The environmental sensor is used to monitor environmental sensing data. Optionally, the environmental sensing data includes water quality data and temperature and humidity data. Water quality data includes data that can measure water quality changes, such as pH and conductivity.

[0040] The adaptive module uses the tunnel water leakage monitoring model to adjust equipment operating parameters based on environmental perception data to adapt to environmental changes. This tunnel water leakage monitoring model is built based on a machine learning model, using historical acoustic and vibration signals and historical environmental perception data as training samples. It predicts the operating parameters of the acoustic and vibration sensors based on the environmental perception data. These operating parameters include those of the acoustic and vibration sensors and / or the analyzer.

[0041] The acoustic vibration sensor is used to collect acoustic vibration signals. The acoustic vibration sensor can be arranged in a certain pattern.

[0042] The analyzer is used to analyze and process the environmental perception data and acoustic vibration signals to obtain analysis data after the equipment operating parameters are adjusted.

[0043] The computer is used to compare the analysis data with the tunnel leakage status change curve to determine the tunnel leakage area. The tunnel leakage status change curve can be established based on historical data and experience, reflecting the law of tunnel leakage as the environment changes.

[0044] In some embodiments, the adaptive module is specifically used to: first determine 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 equipment working parameters output by the tunnel leakage monitoring model, and then make adjustments according to the equipment working parameters.

[0045] Taking pH as an example of environmental sensing data, the adaptive module first determines whether the pH value detected by the environmental sensor is within the preset pH range. pH fluctuations can affect the characteristics of the sound source. Therefore, if the pH value deviates from the preset range, the operating parameters of the acoustic vibration sensor are adjusted. This operating parameter adjustment range is based on a tunnel water leakage monitoring model. This model accurately predicts the optimal operating parameters based on real-time environmental sensing data, automatically adjusting the settings and improving monitoring accuracy.

[0046] For example, if the pH value detected by the environmental sensor deviates from a 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 recollects acoustic vibration signals at the adjusted sampling frequency. The preset pH range may be 6.5-7.5.

[0047] In some embodiments, such as Figure 1 As shown in Figure 1, the tunnel water leakage detection system also 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 analyzed data to the computer.

[0048] In some other embodiments, the tunnel water leakage monitoring model is further used to predict the operating parameters of the power amplifier based on the environmental sensing data. Accordingly, the adaptive module is used to adjust the operating parameters of at least one of the acoustic vibration sensor, the analyzer, and the power amplifier based on the environmental sensing data and using the tunnel water leakage monitoring model. For example, if the pH value detected by the environmental sensor deviates from a preset pH range, the operating parameters of the power amplifier (e.g., amplification factor) and the operating parameters of the analyzer (e.g., filtering parameters) are adjusted based on the tunnel water leakage monitoring model.

[0049] The above embodiment monitors changes in the tunnel environment and automatically adjusts the operating parameters of each device in the system to adapt to the new tunnel environment, thereby improving the reliability and long-term stability of the system.

[0050] In some embodiments, such as Figure 1 As shown, the tunnel water leakage detection system also includes a hardware status monitoring module. Each hardware device's corresponding hardware status monitoring module is used to monitor the device status parameters of the corresponding device in real time, including but not limited to power supply voltage, current, and operating temperature, and determine whether the device parameters are within a preset parameter range to determine whether the device is in normal working condition.

[0051] For example, taking the hardware status monitoring module corresponding to the acoustic vibration sensor as an example, the hardware status monitoring module monitors the power supply voltage of the acoustic vibration sensor in real time to determine whether its power supply voltage is within ±5% of the rated voltage. If so, it indicates that the acoustic vibration sensor is in normal working condition; if not, it indicates that there is a power supply problem or internal circuit failure in the acoustic vibration sensor.

[0052] As another example, the hardware status monitoring module corresponding to the acoustic vibration sensor monitors the operating temperature of the acoustic vibration sensor in real time to determine whether its operating temperature is within the normal operating temperature (less than 70°C). If so, it indicates that the acoustic vibration sensor is in a normal operating state; if not, it indicates that the acoustic vibration sensor has poor heat dissipation or an internal component failure.

[0053] In the above embodiment, each device in the system is equipped with an independent hardware status monitoring module. The hardware status monitoring module enables the tunnel water leakage detection system to have a self-diagnosis function and can detect in real time whether each device in the system is operating normally.

[0054] In some embodiments, each device in multiple data transmission links periodically transmits detection signals for verification. For example, an acoustic vibration sensor and a power amplifier, an analyzer and a switch, or a switch and a computer periodically transmit detection signals (such as heartbeat packets) to each other, which are then verified by the receiving end. If the receiving end does not receive the detection signal within a preset time, or if the received detection signal is erroneous, the data transmission link is determined to have failed. Upon detecting a failure in any data transmission link, the link is re-established or a switch is made to a backup link, and a communication failure alert is sent to management personnel. The communication failure alert includes information such as the fault location.

[0055] The above-mentioned embodiment establishes a detection and feedback mechanism for data transmission links, which can quickly determine whether a communication link has failed, realize rapid detection of link failures, avoid problems such as data transmission interruption or loss caused by failures remaining undetected for a long time, and improve the reliability and stability of the system. It helps to reduce the service interruption time caused by link failures and improves the fault tolerance and availability of the system. The automatic recovery process does not require manual intervention and can quickly respond to failures to ensure the continuity of data transmission. Accurate fault location can reduce troubleshooting time, improve maintenance efficiency, and enable technicians to repair faulty links in a targeted manner, reducing the impact on the operation of the entire system. It realizes automated monitoring and management of communication links, reducing the workload of manual inspections and troubleshooting. Managers can promptly understand the system operation status by receiving alarm information and carry out maintenance work in a targeted manner, thereby improving the efficiency and quality of operation and maintenance management and reducing operation and maintenance costs.

[0056] In some embodiments, such as Figure 1 As shown, the tunnel water leakage detection system also includes an anomaly detection module. This module analyzes the characteristic parameters of the environmental sensing data and acoustic and vibroacoustic signals to determine whether they are abnormal. If the environmental sensing data and acoustic and vibroacoustic signals are normal, a deep learning model is used to extract the local and global features of the environmental sensing data and acoustic and vibroacoustic signals. The analyzer then determines analysis data based on the local and global features of the environmental sensing data and acoustic and vibroacoustic signals.

[0057] Optionally, characteristic parameters include but are not limited to frequency, amplitude, and phase.

[0058] For example, the abnormality detection module may obtain spectrum data of the acoustic vibration signal, then calculate the frequency of the acoustic vibration signal based on the spectrum data, and determine whether the frequency of the acoustic vibration signal is within a preset frequency range. If so, the acoustic vibration signal is determined to be normal. The preset frequency range may be 100 Hz - 10 kHz.

[0059] Exemplarily, the abnormality detection module can also obtain the amplitude of the acoustic vibration signal, determine the peak point of the acoustic vibration signal, and then calculate the fluctuation difference between the peak points to determine whether the fluctuation difference is within a preset fluctuation range. If so, it is determined that the acoustic vibration signal is normal.

[0060] The above embodiment uses a signal integrity detection algorithm to analyze the frequency, amplitude, phase and other characteristics of the signal in real time to determine whether the signal is abnormal, thereby accurately determining whether the signal is interfered with. 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 complex characteristics of environmental perception data and acoustic vibration signals in time and frequency are learned through a deep learning model. The comprehensive analysis of local features and global features enables the model to capture various characteristic information of leakage signals more comprehensively and meticulously, avoiding the limitations of a single data source or a single feature analysis, thereby significantly improving the recognition accuracy of complex leakage signals and reducing misjudgments and missed judgments.

[0061] In order to more clearly understand the above-mentioned objectives, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application can also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present application, not all of the embodiments.

[0063] The tunnel water leakage detection method based on acoustic vibration signals provided in the embodiments of the present application can be implemented using a tunnel water leakage detection system or electronic devices, including but not limited to personal computers, laptops, tablet computers, smartphones, and the like. The operating systems of the electronic devices may include Android, the mobile operating system developed by Apple (iOS), the operating system developed by Microsoft (Windows), and the like, but are not limited in the embodiments of the present application. The electronic devices can operate independently to implement the present application, or they can be connected to a network and implement the present application through interactive operations with other computer devices on the network. The networks in which the electronic devices are located include but are not limited to the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0064] It should be noted that the protection scope of the tunnel water leakage detection method based on acoustic vibration signals described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the existing technology based on the principles of the present application are included in the protection scope of the present application.

[0065] like Figure 2 As shown, Figure 2This is a flow chart of a tunnel water leakage detection method based on acoustic vibration signals according to an embodiment of the present application. This method can be performed by a tunnel water leakage detection system, which includes an environmental sensor, an adaptive module, an acoustic vibration sensor, an analyzer, and a computer. The method primarily includes the following steps S201 to S203:

[0066] S201. Adjust equipment operating parameters using a tunnel water leakage monitoring model based on environmental perception data monitored by environmental sensors through an adaptive module.

[0067] Environmental sensors monitor the tunnel environment in real time and collect environmental perception data. These sensors include water quality sensors, temperature and humidity sensors, and other sensors. Accordingly, environmental perception data includes, but is not limited to, water quality data, temperature and humidity data. Water quality data includes data such as pH and conductivity that can measure changes in water quality.

[0068] In some embodiments, the tunnel water leakage detection system further includes a hardware status monitoring module. This module monitors, in real time, whether the status parameters of other devices within the system are within a preset parameter range throughout the implementation of the tunnel water leakage detection method based on acoustic and vibration signals. This module can monitor the status parameters of devices such as environmental sensors, acoustic and vibration sensors, analyzers, and computers. If the status parameters of a device are within the preset parameter range, the device is determined to be operating normally; if the status parameters of a device are outside the preset parameter range, the device is determined to be operating abnormally.

[0069] Device status parameters include power supply voltage, current, and operating temperature. The hardware status monitoring module monitors the acoustic vibration sensor's power supply voltage and determines whether it is within a preset voltage range, such as ±5% of the rated voltage. If so, the acoustic vibration sensor is operating normally. If not, the acoustic vibration sensor is malfunctioning, possibly due to a power supply issue or internal circuit failure. Device abnormality or fault alerts can be sent to management personnel, including information indicating which device is abnormal or faulty.

[0070] For example, the hardware status monitoring module monitors whether the operating temperature of the acoustic vibration sensor is within a preset temperature range, such as less than 70° C. If so, it indicates that the acoustic vibration sensor is in normal working condition; if not, it indicates that the acoustic vibration sensor has poor heat dissipation or an internal component failure.

[0071] The above embodiment monitors the device status parameters through the hardware status monitoring module, detects device failures or anomalies in a timely manner, and issues an alarm before the failure develops to a serious level that causes device shutdown or damage, thereby achieving early intervention, ensuring long-term operation of the system, and thus improving the reliability and stability of the entire system.

[0072] In some embodiments, during step S201, the adaptive module first determines whether the environmental sensing data meets preset environmental conditions. If not, the environmental sensing data is input into the tunnel water leakage monitoring model to obtain the device operating parameters output by the tunnel water leakage monitoring model, and then adjustments are made based on the device operating parameters. Preset environmental conditions include preset acid-base ranges, preset temperature ranges, preset humidity ranges, and the like.

[0073] The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples. The model is used to predict equipment operating parameters based on environmental perception data. Equipment operating parameters include those of the acoustic vibration sensor, analyzer, and power amplifier. For example, the sampling frequency of the acoustic vibration sensor, the filter parameters of the analyzer, and the amplification factor of the power amplifier.

[0074] The steps for training a tunnel water leakage monitoring model include: collecting historical environmental perception data and synchronously recording the operating parameters of the acoustic vibration sensor, power amplifier, and analyzer. Data preprocessing is then performed, including data cleaning, data normalization, and data labeling. The historical environmental perception data is labeled with the corresponding equipment operating parameters and used as labels for the training model. When selecting an initial machine learning model, a multilayer perceptron (MLP) can be selected, considering the complexity of the data and the nonlinear relationship between environmental factors and equipment operating parameters. The preprocessed data is divided into a training set, a validation set, and a test set. The training set is used to train the model, allowing it to learn the relationship between environmental perception data and equipment operating parameters; the validation set is used to evaluate the model's performance during training, adjust the model's hyperparameters, and prevent overfitting; and the test set is used to evaluate the model's generalization ability after model training is complete. Taking the initial machine learning model as an example, an MLP consists of an input layer, hidden layers, and an output layer. The number of neurons in the input layer is determined by the number of input features, such as water quality, temperature, and humidity. Multiple hidden layers can be configured, each containing a certain number of neurons, to perform nonlinear transformations on the input features and learn the nonlinear relationship between environmental perception data and device operating parameters. The output layer contains multiple neurons, corresponding, for example, to the sampling frequency of the acoustic vibration sensor, the amplification factor of the power amplifier, and the filter parameters of the analyzer. An appropriate loss function, such as mean squared error (MSE), is selected to measure the difference between the model's predicted value and the true value. Model parameters are updated using optimization algorithms such as stochastic gradient descent (SGD) and adaptive moment estimation (Adam). The training set is input into the model, and the model parameters are iteratively updated to gradually reduce the loss function. During training, a validation set is used to monitor model performance. The test set is used to evaluate model performance, calculating metrics such as mean squared error (MSE) and mean absolute error (MAE). Based on the evaluation results, adjust the model's hyperparameters, such as the number of neurons in the hidden layer, learning rate, regularization parameters, etc., to improve the model's performance.

[0075] The trained tunnel leakage monitoring model is deployed to the tunnel seepage detection system to infer optimal equipment operating parameters. The adaptive module determines whether the pH value detected by the water quality sensor is within the preset pH range. If not, the pH value that deviates from the preset range is input into the tunnel leakage monitoring model to obtain the equipment operating parameters output by the tunnel leakage monitoring model. For example, the sampling frequency of the acoustic vibration sensor is dynamically adjusted between 20kHz and 50kHz, and / or the amplification factor of the power amplifier is adjusted between 500 and 2000 times. This allows the sampling frequency of the acoustic vibration sensor and / or the amplification factor of the power amplifier to be adjusted to adapt to environmental changes and collect new acoustic vibration signals.

[0076] In some embodiments, the water collection shed in this application includes multiple semi-cylindrical units, with adjacent units connected by flexible splicing materials. This solves the problem of irregular tunnel vault shapes or local depressions and protrusions, thereby effectively diverting leaking water to the diversion trough, which is conducive to improving the overall detection effect.

[0077] S202: After the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer to obtain analysis data.

[0078] In some embodiments, the tunnel water leakage detection system further includes a power amplifier, which amplifies the acoustic vibration signal collected by the acoustic vibration sensor and then transmits the amplified acoustic vibration signal to the analyzer.

[0079] In some embodiments, after adjusting the operating parameters of at least one of the acoustic and vibroacoustic sensors, power amplifiers, and analyzers, and before analyzing the environmental sensing data and acoustic and vibroacoustic signals, the analyzer first analyzes the characteristic parameters of the environmental sensing data and the acoustic and vibroacoustic signals using an anomaly detection module to determine whether the acoustic and vibroacoustic signals are abnormal. If the environmental sensing data and the acoustic and vibroacoustic signals are normal, a deep learning model is used to extract local and global features of the environmental sensing data and the acoustic and vibroacoustic signals. Then, step S202 is executed, where the analyzer determines analysis data based on the local and global features of the environmental sensing data and the acoustic and vibroacoustic signals.

[0080] The characteristic parameters of the environmental perception data and the acoustic vibration signal include but are not limited to frequency, amplitude, and phase.

[0081] Deep learning models are pre-trained to learn the temporal and frequency patterns of environmental perception data and acoustic and vibration signals. For environmental perception data, deep learning models can extract features such as temperature and humidity trends and changes in the chemical composition of water quality. For acoustic and vibration signals, they can extract frequency features (such as dominant frequency and spectral distribution), amplitude features (such as peak value and mean value), and phase features. Deep learning models can be convolutional neural networks, capable of extracting both local and global features. They can more comprehensively and meticulously capture the various characteristic information of leakage signals, avoiding the limitations of single data sources or single feature analysis. Comprehensive analysis can identify complex leakage signals, such as acoustic and vibration signals caused by rapidly changing leakage velocity or those associated with bubbles. Deep learning models can more sensitively capture subtle changes and early characteristics of leaking water signals.

[0082] Optionally, the spectrum data of the acoustic vibration signal and the spectrum data of the environmental perception data are obtained through the anomaly detection module, and then the frequency of the acoustic vibration signal and the frequency of the environmental perception data are calculated based on the spectrum data. Determine whether the frequency of the acoustic vibration signal is within a preset frequency range. If so, determine that the acoustic vibration signal is normal. The preset frequency range can be 100Hz-10kHz. Determine whether the frequency of the environmental perception data fluctuates frequently and irregularly in a short period of time. If so, it indicates that the environmental perception data changes abnormally. It may be that the sensor is subject to external interference, such as electromagnetic interference, mechanical vibration, etc., or the sensor itself has a fault, resulting in distortion of the collected data.

[0083] Exemplarily, the anomaly detection module calls the numpy.fft.fft function to perform a Fast Fourier Transform (FFT) on the acoustic signal signal_data to obtain the spectrum data of the acoustic signal signal_data. The frequency of the acoustic signal is then calculated based on the spectrum data to determine whether the frequency of the acoustic signal is between 100 Hz and 10 kHz. Optionally, the anomaly detection module obtains the amplitude of the acoustic signal and the amplitude of the environmental perception data, determines the peak points of the acoustic signal and the peak points of the environmental perception data, and then calculates the fluctuation difference between the respective peak points to determine whether the fluctuation difference is within a preset fluctuation range. If so, the acoustic signal is determined to be normal. The fluctuation difference can be a difference, a ratio, etc.

[0084] For example, the anomaly detection module calls scipy.signal.find_peaks to obtain the amplitude of the acoustic vibration signal signal_data and determine the peak point of the acoustic vibration signal. The fluctuation ratio between adjacent peak points is then calculated to determine whether the fluctuation ratio is between 0.5 and 2. If the fluctuation ratio exceeds this range, the amplitude fluctuation is considered abnormal. If the environmental perception data collected at adjacent moments, such as temperature and humidity data, changes in amplitude too much, the temperature is 25°C at the previous moment 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 and other factors in the environment, then the data may be abnormal, possibly due to excessive sensor measurement errors or interference from sudden factors.

[0085] Once the environmental sensing data and acoustic and vibration signals are normal and local and global features have been extracted, the analyzer performs a comprehensive analysis of these features to generate analytical data. The acoustic and vibration characteristics of leaking water may vary under different geological conditions and climates, and combining these with environmental sensing data allows for more accurate identification of these characteristics. This combined analysis of these two types of data provides a more comprehensive and accurate understanding of the actual conditions within the tunnel, enabling adaptation to various potential changes in tunnel engineering.

[0086] The analysis process includes filtering, positioning, fusion, etc. The analysis data can be a fused feature vector containing the position information of the acoustic vibration signal after filtering.

[0087] Tunnels may contain a variety of external noise sources, such as vehicle noise, ventilation equipment noise, and other mechanical equipment noise. These noises may mix with the acoustic and vibration signals, causing signal interference and affecting signal recognition and analysis. This application uses an analyzer to filter the acoustic and vibration signals to reduce the impact of external noise.

[0088] In the actual process of collecting acoustic vibration signals, due to the mutual interference of multiple water leaks or sounds during propagation, the received signal is a superposition of multiple signals, that is, the acoustic vibration signals overlap. This overlap makes the signal received by a single sensor complicated, and it is difficult to directly distinguish the characteristics and location information of each water leakage point from it. The present application locates the acoustic vibration signal through the application of array signal processing technology by an analyzer. Specifically, by processing and analyzing the acoustic vibration signals received by each acoustic vibration sensor, the propagation differences of the acoustic vibration signals between different acoustic vibration sensors, such as time delay, phase difference, etc., are used to obtain the direction information of the acoustic vibration signal and separate the acoustic vibration signals in different directions; or, the acoustic vibration signals received by the acoustic vibration sensor array are subjected to weighted summation and other operations to enhance the acoustic vibration signal from a specific direction, while suppressing the acoustic vibration signals in other directions, thereby achieving the separation of acoustic vibration signals in different directions; or, by utilizing the spatial correlation and noise characteristics of the acoustic vibration signal, the data received by the acoustic vibration sensor array are subjected to mathematical operations such as feature decomposition to estimate the direction of arrival of the signal, and the signal is separated and located according to the direction information.

[0089] The analyzer utilizes multi-sensor fusion and data fusion algorithms to fuse environmental perception data and acoustic and vibroacoustic signals. Specifically, the most representative and discriminative features for water leakage monitoring are selected from the large number of extracted features. Redundant and irrelevant features are removed, and feature dimensionality is reduced to improve fusion efficiency and accuracy. The selected and reduced environmental perception data features are then fused with the acoustic and vibroacoustic signal features. Feature vectors can be concatenated to form a new fused feature vector. S203: The analyzed data is compared with the tunnel water leakage status curve via a computer to determine the tunnel leakage area.

[0090] The analysis data is obtained by integrating environmental perception data and acoustic vibration signals, and includes the location information of the acoustic vibration signals.

[0091] In some embodiments, the tunnel leakage monitoring model can also be used to predict a tunnel leakage status curve. This curve reflects how tunnel leakage changes with environmental changes. In addition to the aforementioned training steps for the tunnel leakage monitoring model, the collection of leakage data can be added. Leakage conditions at different locations in the tunnel can be recorded through manual inspections, water level monitoring, and other methods, with static information such as leakage status and leakage degree marked. Leakage changes over time are recorded at regular intervals to form time series data, which is then used to construct a tunnel leakage status curve. During data annotation, historical environmental monitoring data and historical acoustic and vibration signals are annotated according to corresponding leakage trends. A time series data structure suitable for model input is also constructed. For example, environmental monitoring data, acoustic and vibration signals, and leakage conditions over a period of time are used as a sample. The initial model can be constructed using a model suitable for processing sequential data, such as recurrent neural network (RNN) variants such as long short-term memory networks (LSTMs) and gated recurrent units (GRUs), or a hybrid model combining convolutional neural networks (CNNs) and RNNs. The trained model is then divided into datasets, a loss function is defined, an optimization algorithm is selected for model training, and the model is evaluated and hyperparameters are adjusted, ultimately yielding a trained model. The trained tunnel leakage monitoring model is then deployed to the tunnel leakage detection system, generating a tunnel leakage status curve based on current environmental perception data and acoustic vibration signals.

[0092] In any of the above-described embodiments, a data transmission link exists between the devices, and a detection signal is periodically sent to verify whether the link is faulty. For example, an acoustic vibration sensor and a power amplifier periodically send detection signals (such as heartbeat packets) to each other for verification. If the acoustic vibration sensor does not receive the detection signal sent by the power amplifier within a preset time, or if the received detection signal is erroneous, the data transmission link between the acoustic vibration sensor and the power amplifier is determined to be faulty. This application also establishes a fault feedback mechanism that, upon detecting a failure in any data transmission link, reestablishes the link or switches to a backup link, and sends a communication failure alert to management personnel. The communication failure alert includes information such as the fault location.

[0093] In some embodiments, after executing step S203, it also includes determining whether the tunnel water leakage area is in a risk area or a dangerous area. If so, an early warning message is generated and sent to the management personnel so that the management personnel can take quick measures to prevent the water leakage problem from further deteriorating and ensure the safety and normal use of the tunnel.

[0094] In steps S201-S203, the system adapts to changes in the tunnel environment and automatically adjusts the monitoring parameters of each device, improving the system's flexibility and adaptability, and also enhancing the accuracy of tunnel leakage monitoring. This reduces manual intervention, lowers labor costs, and improves detection efficiency. Comprehensive analysis of environmental perception data and acoustic and vibration signals allows for comprehensive identification of leakage, reducing false positives and missed detections.

[0095] like Figure 3 As shown, Figure 3 A schematic diagram of the structure of a tunnel water leakage detection system provided in an embodiment of the present application Figure 2 , the system comprises:

[0096] Environmental sensor 301, used to monitor environmental perception data;

[0097] Adaptive module 302, configured to adjust equipment operating parameters based on environmental perception data using a tunnel water leakage monitoring model. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples to predict equipment operating parameters based on environmental perception data. The equipment operating parameters include operating parameters of the acoustic vibration sensor and / or analyzer.

[0098] Acoustic vibration sensor 303, used to collect acoustic vibration signals;

[0099] Analyzer 304, used to analyze and process the environmental sensing data and acoustic vibration signals to obtain analysis data after the equipment operating parameters are adjusted;

[0100] The computer 305 is used to compare the analysis data with the tunnel water leakage state change curve to determine the tunnel water leakage area.

[0101] As an optional implementation provided in an embodiment of the present application, the tunnel water leakage detection system also includes a hardware status monitoring module; the hardware status monitoring module is used to monitor whether the equipment status parameters are within a preset parameter range; the equipment status parameters include the status parameters of at least one device among an environmental sensor, an acoustic vibration sensor, an analyzer and a computer; if so, it is determined that the equipment is in normal working condition.

[0102] As an optional implementation provided in the embodiment of the present application, the adaptive module 302 is specifically used to: determine 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 equipment working parameters output by the tunnel leakage monitoring model; and make adjustments according to the equipment working parameters.

[0103] As an optional implementation provided in an embodiment of the present application, the tunnel water leakage detection system also includes an anomaly detection module; the anomaly detection module is used to analyze characteristic parameters of environmental perception data and acoustic vibration signals to determine whether the environmental perception data and acoustic vibration signals are abnormal; when the environmental perception data and acoustic vibration signals are normal, a deep learning model is used to extract local features and global features of the environmental perception data and acoustic vibration signals; accordingly, the analyzer 304 is specifically used to: determine analysis data based on the local features and global features through the analyzer.

[0104] As an optional implementation provided in an embodiment of the present application, the characteristic parameter includes frequency; the abnormality detection module is specifically used to: obtain spectrum data of the environmental perception data and the acoustic vibration signal; calculate the frequency based on the spectrum data, and determine whether the frequency is within a preset frequency range; if the frequency is within the preset frequency range, determine that the environmental perception data and the acoustic vibration signal are normal.

[0105] As an optional implementation provided in an embodiment of the present application, the characteristic parameters include amplitude; the abnormality detection module is specifically used 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, determine that the environmental perception data and the acoustic vibration signal are normal.

[0106] The specific limitations of the tunnel water leakage detection system can be found in the limitations of the tunnel water leakage detection method based on acoustic vibration signals above and will not be further elaborated here. Each module in the aforementioned tunnel water leakage detection system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the aforementioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each of the aforementioned modules.

[0107] The embodiment of the present application also provides an electronic device, such as Figure 4 As shown, it includes a memory 402 and a processor 401. The memory 402 stores a computer program. The processor 401 is configured to run the computer program to perform the steps of any of the above-mentioned server in-band data acquisition method embodiments. In one embodiment, the present application provides an electronic device including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0108] An adaptive module uses the environmental perception data monitored by environmental sensors and a tunnel water leakage monitoring model to adjust the equipment operating parameters. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples to predict the equipment operating parameters under environmental perception data. The equipment operating parameters include the operating parameters of the acoustic vibration sensor and / or analyzer. After the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer to obtain analysis data. The analysis data is compared with the tunnel water leakage state change curve by a computer to determine the tunnel water leakage area.

[0109] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the tunnel water leakage detection system also includes a hardware status monitoring module; the method also includes: monitoring whether the equipment status parameters are within a preset parameter range through the hardware status monitoring module; the equipment status parameters include status parameters of at least one device among an environmental sensor, an acoustic vibration sensor, an analyzer and a computer; if so, it is determined that the equipment is in normal working condition.

[0110] In one embodiment, when the processor executes the computer program, it also implements the following steps: adjusting the equipment operating parameters using the tunnel leakage monitoring model based on the environmental perception data monitored by the environmental sensor through the adaptive module, 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 equipment operating parameters output by the tunnel leakage monitoring model; and adjusting according to the equipment operating parameters.

[0111] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the tunnel water leakage detection system also includes an abnormality detection module; after the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor are analyzed and processed by the analyzer, and before obtaining the analysis data, the method also includes: analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal by the abnormality detection module 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, using a deep learning model to extract local features and global features of the environmental perception data and the acoustic vibration signal; accordingly, 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, including: determining the analysis data based on the local features and the global features by the analyzer.

[0112] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the characteristic parameters include frequency; the characteristic parameters of the environmental perception data and the acoustic vibration signal are analyzed by the abnormality detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining spectrum data of the environmental perception data and the acoustic vibration signal; calculating the frequency based on the spectrum 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 signal are normal.

[0113] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the characteristic parameters include amplitude; the characteristic parameters of the environmental perception data and the acoustic vibration signal are analyzed by the abnormality detection module 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, determining that the environmental perception data and the acoustic vibration signal are normal.

[0114] When a processor in an electronic device provided herein executes a computer program, an adaptive module first uses a tunnel water leakage monitoring model to adjust device operating parameters based on environmental sensing data monitored by environmental sensors. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental sensing data and historical device operating parameters as training samples to predict device operating parameters based on the environmental sensing data. The device operating parameters include operating parameters of an acoustic vibration sensor and / or an analyzer. After the device operating parameters are adjusted, the analyzer analyzes and processes the environmental sensing data and acoustic vibration signals collected by the acoustic vibration sensor to obtain analysis data. The computer compares the analysis data with a tunnel water leakage status curve to determine the tunnel water leakage area. In this way, the adaptive module can use the trained model to predict matching device operating parameters based on the current environmental sensing data monitored by the environmental sensors and make real-time adjustments. This process enables the system to automatically adjust device operating parameters based on environmental changes, demonstrating its self-diagnosis and adaptive adjustment capabilities. This dynamic adjustment mechanism also ensures that the device always operates in optimal conditions, avoiding performance degradation or malfunction due to environmental changes. Through the comprehensive analysis of environmental sensing data and acoustic vibration sensors, the resulting analysis data is more accurate and reliable. By comparing and analyzing the data and the tunnel leakage status change curve, it is possible to more accurately determine whether there is water leakage in the tunnel and the specific location of the water leakage, thereby improving the reliability of the system.

[0115] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by the computer program, implements the following steps:

[0116] An adaptive module uses the environmental perception data monitored by environmental sensors and a tunnel water leakage monitoring model to adjust the equipment operating parameters. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples to predict the equipment operating parameters under environmental perception data. The equipment operating parameters include the operating parameters of the acoustic vibration sensor and / or analyzer. After the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer to obtain analysis data. The analysis data is compared with the tunnel water leakage state change curve by a computer to determine the tunnel water leakage area.

[0117] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the tunnel water leakage detection system also includes a hardware status monitoring module; the method also includes: monitoring whether the equipment status parameters are within a preset parameter range through the hardware status monitoring module; the equipment status parameters include status parameters of at least one device among an environmental sensor, an acoustic vibration sensor, an analyzer and a computer; if so, it is determined that the equipment is in normal working condition.

[0118] In one embodiment, when the processor executes the computer program, it also implements the following steps: adjusting the equipment operating parameters using the tunnel leakage monitoring model based on the environmental perception data monitored by the environmental sensor through the adaptive module, 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 equipment operating parameters output by the tunnel leakage monitoring model; and adjusting according to the equipment operating parameters.

[0119] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the tunnel water leakage detection system also includes an abnormality detection module; after the equipment operating parameters are adjusted, the environmental perception data and the acoustic vibration signal collected by the acoustic vibration sensor are analyzed and processed by the analyzer, and before obtaining the analysis data, the method also includes: analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal by the abnormality detection module 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, using a deep learning model to extract local features and global features of the environmental perception data and the acoustic vibration signal; accordingly, 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, including: determining the analysis data based on the local features and the global features by the analyzer.

[0120] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the characteristic parameters include frequency; the characteristic parameters of the environmental perception data and the acoustic vibration signal are analyzed by the abnormality detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal, including: obtaining spectrum data of the environmental perception data and the acoustic vibration signal; calculating the frequency based on the spectrum 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 signal are normal.

[0121] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the characteristic parameters include amplitude; the characteristic parameters of the environmental perception data and the acoustic vibration signal are analyzed by the abnormality detection module 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, determining that the environmental perception data and the acoustic vibration signal are normal.

[0122] When the computer program in the computer-readable storage medium provided by the present application is executed, the adaptive module first uses a tunnel water leakage monitoring model to adjust the equipment operating parameters based on the environmental perception data monitored by the environmental sensors. The tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples to predict the equipment operating parameters under the environmental perception data, including the operating parameters of the acoustic vibration sensor and / or analyzer. After the equipment operating parameters are adjusted, 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 computer compares the analysis data with the tunnel water leakage state change curve to determine the tunnel water leakage area. In this way, the adaptive module can use the trained model to predict the matching equipment operating parameters based on the current environmental perception data monitored by the environmental sensors and make real-time adjustments. This process enables the system to automatically adjust the equipment operating parameters according to environmental changes, demonstrating its self-diagnosis and adaptive adjustment capabilities. This dynamic adjustment mechanism also ensures that the equipment always operates in an optimal state, avoiding the situation where environmental changes may cause equipment performance degradation or failure. Through comprehensive analysis of environmental perception data and acoustic vibration sensors, the resulting data is more accurate and reliable. By comparing this data with the tunnel leakage status curve, the presence of water leakage in the tunnel and its specific location can be more accurately determined, improving the reliability of the system.

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device 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 devices, methods, and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0125] In this application, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0126] In this application, memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0127] In this application, computer-readable media includes permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, 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 technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0128] It should be noted that, in this document, relational terms such as "first" and "second" are used only 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 terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0129] The above are merely specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to these embodiments herein, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A tunnel water leakage detection method based on acoustic vibration signals, characterized in that: The system is applied to a tunnel water leakage detection system, comprising: an environmental sensor, an adaptive module, an acoustic vibration sensor, an analyzer, and a computer. The method includes: The adaptive module adjusts the equipment operating parameters using a tunnel water leakage monitoring model based on the environmental perception data monitored by the environmental sensor; wherein the tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples, and is used to learn the nonlinear relationship between the environmental perception data and the equipment operating parameters to predict the equipment operating parameters under the environmental perception data, wherein the equipment operating parameters include the operating parameters of the acoustic vibration sensor and / or the analyzer; After the operating parameters of the device are adjusted, the environmental perception data and the acoustic vibration signals collected by the acoustic vibration sensor are analyzed and processed by the analyzer to obtain analysis data; The computer compares the analysis data with a tunnel water leakage state change curve to determine the tunnel water leakage area; the tunnel water leakage state change curve is established based on historical data and experience, and reflects the law of tunnel water leakage as the environment changes; The tunnel water leakage detection system also includes an abnormality detection module; After the operating parameters of the device are adjusted, the environmental perception data and the acoustic and vibroacoustic signals collected by the acoustic and vibroacoustic sensors are analyzed and processed by the analyzer. Before obtaining the analysis data, the method further includes: analyzing characteristic parameters of the environmental perception data and the acoustic and vibroacoustic signals by an anomaly detection module to determine whether the environmental perception data and the acoustic and vibroacoustic signals are abnormal; and if the environmental perception data and the acoustic and vibroacoustic signals are normal, extracting local and global features of the environmental perception data and the acoustic and vibroacoustic signals using a deep learning model; 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 based on the local features and the global features by the analyzer.

2. The method according to claim 1, characterized in that The tunnel water leakage detection system also includes a hardware status monitoring module; The method further comprises: Monitoring, by means of a hardware status monitoring module, whether a device status parameter is within a preset parameter range; the device status parameter includes a status parameter of at least one of the environmental sensor, the acoustic vibration sensor, the analyzer, and the computer; If so, the device is in normal working condition.

3. The method according to claim 1, characterized in that The step of adjusting the equipment operating parameters by using the adaptive module based on the environmental perception data monitored by the environmental sensor and utilizing the tunnel water leakage monitoring model includes: Determining whether the environmental perception data meets preset environmental conditions; If not, inputting the environmental sensing data into the tunnel water leakage monitoring model to obtain the equipment operating parameters output by the tunnel water leakage monitoring model; Adjust according to the equipment operating parameters.

4. The method according to claim 1, wherein The characteristic parameters include frequency; The analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal by the abnormality detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal includes: Acquiring the environmental perception data and spectrum data of the acoustic vibration signal; Calculating a frequency based on the spectrum 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.

5. The method according to claim 1, wherein The characteristic parameters include amplitude; The analyzing the characteristic parameters of the environmental perception data and the acoustic vibration signal by the abnormality detection module to determine whether the environmental perception data and the acoustic vibration signal are abnormal includes: Acquiring 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.

6. A tunnel water leakage detection system, characterized in that: include: Environmental sensors, used to monitor environmental perception data; an adaptive module for adjusting equipment operating parameters based on the environmental perception data using a tunnel water leakage monitoring model; wherein the tunnel water leakage monitoring model is built based on a machine learning model, using historical environmental perception data and historical equipment operating parameters as training samples, and is used to learn the nonlinear relationship between the environmental perception data and the equipment operating parameters to predict the equipment operating parameters under the environmental perception data, wherein the equipment operating parameters include the operating parameters of the acoustic vibration sensor and / or the analyzer; An acoustic vibration sensor, used for collecting acoustic vibration signals; an analyzer, configured to analyze and process the environmental perception data and the acoustic vibration signal to obtain analysis data after the operating parameters of the device are adjusted; a computer for comparing the analysis data with a tunnel water leakage state change curve to determine the tunnel water leakage area; the tunnel water leakage state change curve is established based on historical data and experience and reflects the law of tunnel water leakage as the environment changes; The tunnel water leakage detection system further includes an anomaly detection module; the anomaly detection module is configured to analyze 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; and, if the environmental perception data and the acoustic vibration signal are normal, to extract local and global features of the environmental perception data and the acoustic vibration signal using a deep learning model; The analyzer is specifically configured to determine the analysis data based on the local features and the global features.

7. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for detecting tunnel water leakage based on acoustic vibration signals according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that include: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting tunnel water leakage based on acoustic vibration signals according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that include: The computer program product includes a computer program, and when the computer program is run on a computer, the computer is enabled to implement the tunnel water leakage detection method based on acoustic vibration signals according to any one of claims 1 to 5.

Images