Pipeline leakage detection method and device based on distributed optical fiber sensing signal and characteristic combined input FC-ANN network
By using the FC-ANN network model based on distributed fiber sensing signals and features in pipeline leakage detection, the problems of low detection efficiency and poor positioning accuracy in the prior art are solved, and higher leakage recognition accuracy and positioning are achieved Accuracy.
Patent Information
- Application Number
- CN202410964351.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-18
AI Technical Summary
The existing pipeline leakage detection methods have problems such as low detection efficiency, poor positioning accuracy and slow reaction speed in urban environments. Especially due to the influence of interference events and noise, it is difficult to accurately identify and locate leakage points.
A fully connected artificial neural network (FC-ANN) model based on distributed fiber sensing signals and feature joint inputs is adopted to achieve efficient identification and positioning of leaked signals through filtering preprocessing, feature extraction and neural network training.
It improves the recognition accuracy and positioning accuracy of leakage events, can effectively monitor leakage under multiple interference situations, and improves the signal-to-noise ratio and the learning effect of neural network models.
Smart Images

Figure CN118940169A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of optical fiber sensing, and in particular relates to a pipeline leakage detection method and device based on a distributed optical fiber sensing signal and feature joint input FC-ANN network. Background Art
[0002] In the process of modern urbanization, urban water pipelines, as an important part of the city's lifeline, bear the important responsibility of urban water supply. Their stable and efficient operation is directly related to the quality of residents' daily life and the sustainable development of the urban economy. Water pipelines are composed of multiple sections of pipelines. Pipeline joints may leak due to aging, geological subsidence, construction and other reasons, posing a serious threat to urban safety. Therefore, timely discovery and accurate positioning of pipeline leaks are of vital importance to maintaining urban safety and ensuring water supply services. Traditional pipeline leakage detection methods, such as manual inspections and pressure monitoring, have shortcomings such as low detection efficiency, poor positioning accuracy, and slow response speed, which are difficult to meet the needs of modern urban management.
[0003] With the rapid development of optoelectronic technology, Distributed Optical Fiber Sensing System (DOFS) has been widely used in perimeter security, pipeline leakage monitoring and other fields. Among them, the Phase-Sensitive Optical Time-Domain Reflectometer (φ-OTDR) has the characteristics of high sensitivity, ability to sense vibrations caused by leakage, and distributed sensing, and has shown great application potential in leak detection of urban water supply pipelines. In the pipeline leakage scenario, the water flow impact or pressure change at the leakage point will cause tiny vibrations in the surrounding medium. These vibrations are transmitted to the optical fiber through the soil or pipeline wall, captured by the φ-OTDR system and converted into analyzable data signals.
[0004] However, despite the excellent performance of the φ-OTDR system in data acquisition, it still faces many challenges in data analysis and processing. On the one hand, the identification of pipeline leakage events is easily affected by various interference events and noise. There are various vibration sources in the urban environment, such as traffic vibration, construction noise, geological activities, etc. These interference signals are intertwined with leakage signals, making it extremely difficult to extract effective leakage information from complex backgrounds. The existence of multiple interference events and the unclear characteristics of interference events make the traditional support vector machine (SVM) classifier that uses features for classification low in accuracy. On the other hand, the general artificial neural network (ANN) model has powerful capabilities in the field of signal processing and classification. It can automatically extract and learn features from a large amount of data, thereby achieving high-precision classification and achieving higher accuracy than the SVM classifier. However, when applied to pipeline leakage detection, its feature extraction process often lacks pertinence, resulting in low correlation between the extracted information and the leakage signal features, and the classification effect is also limited.
[0005] Therefore, in order to further improve the accuracy and reliability of fiber optic sensing technology in pipeline leakage detection, it is urgent to develop a more accurate pipeline leakage detection method. Summary of the invention
[0006] In view of the above, the purpose of the present invention is to provide a pipeline leakage detection method and device based on distributed optical fiber sensing signals and features jointly input into an FC-ANN network, which can combine the advantages of a fully connected artificial neural network (FC-ANN) model and a feature extraction method to achieve more accurate classification of interference events with fuzzy features and leakage events with stable features, and is suitable for efficient and accurate identification and positioning of pipeline leakage events.
[0007] In order to achieve the above-mentioned invention object, the technical solution provided by the present invention is as follows:
[0008] In a first aspect, an embodiment of the present invention provides a pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into an FC-ANN network, comprising the following steps:
[0009] Collect optical fiber signals including pipeline perimeter disturbance and leakage, and perform filtering preprocessing;
[0010] Extracting features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and constructing the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence;
[0011] Construct a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect by combining evaluation indicators;
[0012] The trained fully connected artificial neural network model is used to detect pipeline leaks on the newly collected optical fiber signals.
[0013] Preferably, the acquisition of optical fiber signals including pipeline perimeter disturbance and leakage conditions includes:
[0014] A phase-sensitive distributed optical fiber sensing system is used to collect pipeline perimeter disturbance optical fiber signals, slow leakage optical fiber signals and fast leakage optical fiber signals.
[0015] Preferably, the filtering preprocessing method includes:
[0016] The optical fiber signal with a sampling rate of fs is subjected to a sliding average with a window length of N to estimate its DC and low-frequency components, and then these components are subtracted from the optical fiber signal to remove the DC and low-frequency noise in the signal.
[0017] Preferably, the optical fiber signal after filtering preprocessing is subjected to feature extraction including time domain features and frequency domain features, including:
[0018] Extracting time domain features from the optical fiber signal after filtering preprocessing, the time domain features including at least one of a time domain maximum value, a time domain minimum value, an average value, a peak-to-peak value, an absolute average value, a variance, a standard deviation, a root mean square value, a root square amplitude, a kurtosis, a skewness, a waveform factor, a peak factor, a pulse factor, and a margin factor;
[0019] The optical fiber signal after filtering preprocessing is subjected to Fourier transformation to extract frequency domain features, and the frequency domain features include at least one of average frequency, center of gravity frequency, frequency root mean square and frequency standard deviation.
[0020] Preferably, the method of combining the filtered preprocessed optical fiber signal with the extracted features comprises:
[0021] The optical fiber signal after filtering preprocessing is resampled to obtain a signal sequence with a reduced sequence length after resampling, and then the extracted features are sequentially added to the end of the signal sequence to obtain a joint sequence after the signal and the features are combined.
[0022] Preferably, the network structure of the fully connected artificial neural network model includes:
[0023] The linear input layer, the first dropout layer, the linear hidden layer, the second dropout layer, the linear output layer and the softmax layer are connected in sequence, wherein a ReLU activation function is connected between the linear input layer and the first dropout layer, and between the linear hidden layer and the second dropout layer, and the softmax layer outputs the final pipeline leakage probability result.
[0024] Preferably, the evaluation indicators used in model training include:
[0025] Accuracy, precision, recall, F-score, and cross entropy loss.
[0026] In a second aspect, to achieve the above-mentioned invention object, an embodiment of the present invention further provides a pipeline leakage detection device based on the distributed optical fiber sensing signal and feature joint input FC-ANN network, comprising: a data acquisition and preprocessing module, a signal and feature joint construction module, a neural network model training module and a pipeline leakage detection application module;
[0027] The data acquisition and preprocessing module is used to acquire optical fiber signals including pipeline perimeter disturbance and leakage conditions, and perform filtering preprocessing;
[0028] The signal and feature joint construction module is used to extract features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and construct the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence;
[0029] The neural network model training module is used to construct a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect in combination with the evaluation index;
[0030] The pipeline leakage detection application module is used to perform pipeline leakage detection on newly collected optical fiber signals using a trained fully connected artificial neural network model.
[0031] In a third aspect, in order to achieve the above-mentioned purpose of the invention, an embodiment of the present invention also provides a pipeline leakage detection device based on a distributed optical fiber sensing signal and feature joint input FC-ANN network, comprising a memory and one or more processors, wherein the memory is used to store a computer program, and the processor is used to implement the above-mentioned pipeline leakage detection method based on a distributed optical fiber sensing signal and feature joint input FC-ANN network when executing the computer program.
[0032] In a fourth aspect, in order to achieve the above-mentioned purpose of the invention, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computer, the above-mentioned pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network is implemented.
[0033] Compared with the prior art, the present invention has the following beneficial effects:
[0034] (1) The present invention can effectively remove DC and low-frequency components and retain the effective signal as much as possible by filtering the signal preprocessing. The signal characteristics after filtering are more obvious, which helps to improve the signal-to-noise ratio of positioning and the learning effect of the neural network model, and can realize leakage monitoring in the case of more interference along the water pipeline.
[0035] (2) The present invention jointly inputs the optical fiber signal and feature into the FC-ANN network, and utilizes the feature quantity to effectively reflect the leakage event, so as to assist the neural network in learning more effective leakage event information. At the same time, the signal input assists the neural network in identifying the interference event. Since the time domain waveform of the signal and the time-frequency domain features of the signal are multimodal descriptions of the event to be detected, the joint input of the signal and feature can more accurately reflect the event and improve the performance of the model. Each input data and output data of the FC-ANN network are connected, which is suitable for situations where each input data needs to be fully utilized. In this way, the advantages of the feature, signal and FC-ANN network are fully combined, and a higher leakage identification accuracy rate than the traditional method can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0037] Figure 1 It is a flow chart of a pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into an FC-ANN network provided by an embodiment of the present invention;
[0038] Figure 2 is a schematic diagram of a feature extraction and combination method provided by an embodiment of the present invention;
[0039] Figure 3 is a schematic diagram of the FC-ANN model structure provided by an embodiment of the present invention;
[0040] Figure 4It is a structural schematic diagram of a pipeline leakage detection device based on a distributed optical fiber sensing signal and feature joint input FC-ANN network provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0041] To make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the scope of protection of the present invention.
[0042] The inventive concept of the present invention is: in response to the problem of insufficient accuracy of the fiber optic sensing pipeline leakage detection method in the prior art, the embodiment of the present invention provides a pipeline leakage detection method and device based on the FC-ANN network with joint input of distributed fiber optic sensing signals and features. By combining the fiber optic signal data and features and training a suitable FC-ANN network model, leakage detection of water pipelines along the optical fiber is achieved. Compared with the traditional SVM classifier and the neural network model with only signal input, the accuracy of leakage event identification is effectively improved.
[0043] Figure 1 1 is a flow chart of a pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into an FC-ANN network according to an embodiment of the present invention. Figure 1 As shown, the embodiment provides a pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network, comprising the following steps:
[0044] S1, collects optical fiber signals including pipeline perimeter disturbance and leakage, and performs filtering preprocessing.
[0045] S1.1, Fiber optic signal acquisition. A phase-sensitive distributed optical fiber sensing system (φ-OTDR) is used to collect pipeline perimeter disturbance fiber optic signals, slow leakage fiber optic signals, and fast leakage fiber optic signals.
[0046] In the embodiment, the optical fiber length is 5000m, a spatial point is sampled every 2m, the time sampling rate is 1500Hz, the peripheral disturbance includes but is not limited to background noise, human knocking and human shaking, slow leakage is defined as intermittent discontinuous leakage, and fast leakage is defined as multiple consecutive leakages.
[0047] S1.2, filtering preprocessing. The filtering preprocessing method includes performing sliding average of a window length of N on the optical fiber signal with a sampling rate of fs to estimate its DC and low-frequency components, and then subtracting these components from the optical fiber signal to remove the DC and low-frequency noise in the signal, which is equivalent to performing high-pass filtering of fs / N on the signal. Compared with high-pass filtering directly using a filter, this method can remove the specified low-frequency components to the maximum extent without affecting the high-frequency components that carry the sensing information.
[0048] In the embodiment, a window with a length of 100 is used to perform sliding average processing on the time domain signal, and the processing result is used as the overall fluctuation trend of the signal. Since it is not caused by leakage, the sliding average result is subtracted from the signal to remove the influence of low-frequency noise caused by signal fluctuation.
[0049] S2, extracting features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and constructing the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence.
[0050] S2.1, feature extraction. The time domain features include at least one of the time domain maximum value, time domain minimum value, average value, peak-to-peak value, absolute average value, variance, standard deviation, root mean square value, root amplitude, kurtosis, skewness, waveform factor, peak factor, pulse factor and margin factor. The extracted frequency domain features include at least one of the average frequency, center of gravity frequency, frequency root mean square and frequency standard deviation.
[0051] In the embodiment, Figure 2 As shown, the optical fiber signal after filtering preprocessing is normalized to extract the above 14 time domain features, and the normalized signal is Fourier transformed to extract the above 4 frequency domain features from the result.
[0052] S2.2, signal and feature combination. The optical fiber signal after filtering preprocessing is resampled to obtain a signal sequence with a reduced sequence length after resampling, and then the extracted features are sequentially added to the end of the signal sequence to obtain a joint sequence after the signal and feature are combined.
[0053] In the embodiment, the time domain signal at the location where leakage or other disturbance occurs is segmented to obtain data with a data length of 1 / 3s, and the data size obtained by segmentation is 1×500. The signal is then resampled to obtain a signal with a sampling rate of 1200 Hz and a length of 400. Finally, 18 extracted features are added to the end of the signal sequence in sequence to obtain a one-dimensional joint sequence of signal + feature.
[0054] S3, build a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect by combining evaluation indicators.
[0055] S3.1, model construction. Figure 3 As shown in the figure, the network structure of the FC-ANN model includes: a linear input layer, a first dropout layer, a linear hidden layer, a second dropout layer, a linear output layer and a softmax layer connected in sequence, wherein a ReLU activation function is connected between the linear input layer and the first dropout layer, and between the linear hidden layer and the second dropout layer, and the final pipeline leakage probability result is output by the softmax layer. Among them, the ReLU activation function is used to introduce nonlinear fitting capabilities to the model, the first dropout layer and the second dropout layer are used to reduce the risk of overfitting of the model, the linear hidden layer is used to transform and process the input data, so as to better divide the input data, and the softmax layer is used to normalize the linear output layer data to obtain the probability result.
[0056] S3.2, model training. In the embodiment, the following Figure 3 The FC-ANN model shown is trained and tested based on the joint sequence as the training set and test set, with 50 training rounds, a learning rate of 0.001, and a batch size of 100. Accuracy, precision, recall, F-score, and cross entropy loss are used as evaluation indicators to measure model performance, and the model with the best performance on the test set is selected as the pipeline leakage recognition and detection model.
[0057] S4, using the trained fully connected artificial neural network model to perform pipeline leakage detection on the newly collected optical fiber signal.
[0058] In the embodiment, the model is deployed in the pipeline leakage monitoring equipment to identify the data with energy anomalies, and judge whether there is a leakage and provide leakage speed information based on the identification result.
[0059] In summary, a pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network can effectively remove DC and low-frequency components and retain effective signal quantities. The signal characteristics after filtering are more obvious, which helps to improve the signal-to-noise ratio of positioning and the learning effect of the neural network model, and can realize leakage monitoring in the case of more interference along the water pipeline. It can also use the effective reflection of the feature quantity on the leakage event to assist the neural network in learning more effective leakage event information, and fully combine the advantages of features, signals and FC-ANN networks to achieve a higher leakage identification accuracy than traditional methods.
[0060] Based on the same inventive concept, Figure 4As shown, an embodiment of the present invention also provides a pipeline leakage detection device 400 based on the distributed optical fiber sensing signal and feature joint input FC-ANN network, including: a data acquisition and preprocessing module 410, a signal and feature joint construction module 420, a neural network model training module 430 and a pipeline leakage detection application module 440.
[0061] The data acquisition and preprocessing module 410 is used to acquire optical fiber signals including pipeline perimeter disturbance and leakage conditions, and perform filtering preprocessing.
[0062] The signal and feature joint construction module 420 is used to extract features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and construct the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence.
[0063] The neural network model training module 430 is used to construct a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect in combination with evaluation indicators.
[0064] The pipeline leakage detection application module 440 is used to perform pipeline leakage detection on the newly collected optical fiber signal using the trained fully connected artificial neural network model.
[0065] Based on the same inventive concept, an embodiment of the present invention also provides a pipeline leakage detection device based on a distributed optical fiber sensing signal and feature joint input FC-ANN network, comprising a memory and one or more processors, the memory being used to store a computer program, and the processor being used to implement the above-mentioned pipeline leakage detection method based on a distributed optical fiber sensing signal and feature joint input FC-ANN network when executing the computer program.
[0066] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer, the above-mentioned pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network is implemented.
[0067] It should be noted that the pipeline leakage detection device based on the distributed optical fiber sensing signal and feature joint input FC-ANN network, the pipeline leakage detection equipment based on the distributed optical fiber sensing signal and feature joint input FC-ANN network and the computer-readable storage medium provided in the above embodiments all belong to the same inventive concept as the pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network. The specific implementation process is detailed in the embodiment of the pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network, which will not be repeated here.
[0068] The specific implementation methods described above provide a detailed description of the technical solutions and beneficial effects of the present invention. It should be understood that the above is only the most preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, supplements and equivalent substitutions made within the scope of the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into FC-ANN network, characterized in that: The following steps are involved: Collect optical fiber signals including pipeline perimeter disturbance and leakage, and perform filtering preprocessing; Extracting features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and constructing the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence; Construct a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect by combining evaluation indicators; The trained fully connected artificial neural network model is used to detect pipeline leaks on the newly collected optical fiber signals.
2. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: The acquisition includes optical fiber signals of pipeline perimeter disturbance and leakage, including: A phase-sensitive distributed optical fiber sensing system is used to collect pipeline perimeter disturbance optical fiber signals, slow leakage optical fiber signals and fast leakage optical fiber signals.
3. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: The filter preprocessing methods include: The optical fiber signal with a sampling rate of fs is subjected to a sliding average with a window length of N to estimate its DC and low-frequency components, and then these components are subtracted from the optical fiber signal to remove the DC and low-frequency noise in the signal.
4. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: The optical fiber signal after filtering preprocessing is subjected to feature extraction including time domain features and frequency domain features, including: Extracting time domain features from the optical fiber signal after filtering preprocessing, the time domain features including at least one of a time domain maximum value, a time domain minimum value, an average value, a peak-to-peak value, an absolute average value, a variance, a standard deviation, a root mean square value, a root square amplitude, a kurtosis, a skewness, a waveform factor, a peak factor, a pulse factor, and a margin factor; The optical fiber signal after filtering preprocessing is subjected to Fourier transformation to extract frequency domain features, and the frequency domain features include at least one of average frequency, center of gravity frequency, root mean square frequency and frequency standard deviation.
5. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: Methods for combining the filtered preprocessed optical fiber signal with the extracted features include: The optical fiber signal after filtering preprocessing is resampled to obtain a signal sequence with a reduced sequence length after resampling, and then the extracted features are sequentially added to the end of the signal sequence to obtain a joint sequence after the signal and the features are combined.
6. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: The network structure of the fully connected artificial neural network model includes: The linear input layer, the first dropout layer, the linear hidden layer, the second dropout layer, the linear output layer and the softmax layer are connected in sequence, wherein a ReLu activation function is connected between the linear input layer and the first dropout layer, and between the linear hidden layer and the second dropout layer, and the softmax layer outputs the final pipeline leakage probability result.
7. The pipeline leakage detection method based on the distributed optical fiber sensing signal and feature joint input FC-ANN network according to claim 1 is characterized in that: The evaluation indicators used in model training include: Accuracy, precision, recall, F-score, and cross entropy loss.
8. A pipeline leakage detection device based on distributed optical fiber sensing signals and features combined input into FC-ANN network, characterized in that: include: Data acquisition and preprocessing module, signal and feature joint construction module, neural network model training module and pipeline leakage detection application module; The data acquisition and preprocessing module is used to acquire optical fiber signals including pipeline perimeter disturbance and leakage conditions, and perform filtering preprocessing; The signal and feature joint construction module is used to extract features including time domain features and frequency domain features from the optical fiber signal after filtering preprocessing, and construct the optical fiber signal after filtering preprocessing and the extracted features into a joint sequence; The neural network model training module is used to construct a fully connected artificial neural network model, input the joint sequence into the fully connected artificial neural network model for model training, and optimize the model training effect in combination with the evaluation index; The pipeline leakage detection application module is used to perform pipeline leakage detection on newly collected optical fiber signals using a trained fully connected artificial neural network model.
9. A pipeline leakage detection device based on the joint input of distributed optical fiber sensing signals and features into an FC-ANN network, comprising a memory and one or more processors, wherein the memory is used to store a computer program, characterized in that: The processor is used to implement the pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network as described in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer, the pipeline leakage detection method based on the joint input of distributed optical fiber sensing signals and features into the FC-ANN network as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Time sequence signal efficient denoising and high-precision reconstruction modeling method and system
CN111046824A
Pipeline safety monitoring method based on distributed optical fiber sensor and deep learning
CN114857504A
Tunnel lining void detection method and system based on impact echo signal
CN115980189A
Distributed optical fiber sensing disturbance identification method
CN116863251A
Composite interference signal recognition method and system
WO2023092923A1
Cited By
Water supply pipeline explosion and leakage monitoring and early warning method using existing communication optical cable
CN122447660A
