Fiber Vibration Signal Research Articles

Signal recognition based on transfer learning for Φ-OTDR fiber optic distributed disturbance sensor

Abstract Traditional classification models for optical fiber vibration signals can achieve good recognition results when there are a large number of samples. However, it is difficult to obtain sufficient training samples in real scenes. A method of Φ-OTDR sensor signal recognition based on VGGish transfer learning is proposed in this paper. Firstly, a selection indicator is designed to filter out vibration signals from sparse signals. Then, the VGGish network pretrained for sound classification is used for transfer learning as a feature extractor for optical fiber vibration signals. This method was applied to classify 6 kinds of optical fiber vibration signals. When the number of training samples is reduced to 480 samples, the method can still achieve 84.17% classification accuracy. Compared to the method of training from scratch, this proposed method reduces training time by 73.9%.

Optical fiber vibration signal recognition based on an efficient multidimensional feature extraction network.

In the field of optical fiber vibration signal recognition, one-dimensional signals have few features. People often used the shallow layer of a one-dimensional convolutional neural network (1D-CNN), which results in fewer features being learned by the network, leading to a poor recognition rate. There are also many complex algorithms and data processing methods, which make the whole signal recognition process more complicated. Therefore, an optical vibration signal recognition method based on an efficient multidimensional feature extraction network was proposed. Based on ResNet-50, efficient channel attention (ECA) was used to improve image features extraction ability, and a long short-term memory (LSTM) network was used to enhance the extraction of temporal features. Three different vibration signals were collected using a phase-sensitive optical time-domain reflectometry (Φ-OTDR) optical fiber sensing system. Vibration signals were converted into 128×128 grayscale images, which have more effective vibration information. The experimental results show that the three types of signals can be recognized and classified effectively by the network, and the average recognition rate is 98.67%.

Localizing and tracking of in-pipe inspection robots based on distributed optical fiber sensing

Ensuring the safe transportation of energy relies heavily on the timely safety inspection and pigging of energy pipelines using in-pipe inspection robots known as Smart/Intelligent PIGs. Addressing the potential risks of PIG block incidents and the limitations of excessive speed in the maintenance, real-time localization and tracking of these inspection robots has become imperative. However, traditional localization and tracking methods present a challenge due to their resource-intensive nature, requiring significant manpower and resources. To overcome this limitation and enhance the intelligence of the robot operation monitoring, this paper proposes an innovative artificial intelligence (AI) integration algorithm framework based on distributed optical fiber sensing (DOFS) for real-time localization and tracking of robots. It adopts noise reduction and reconstruction techniques in signal processing, effectively enhancing the quality of optic fiber vibration signals. Notably, the integration of two distinct features that complement each other enables dual verification of tracking detection, ultimately bolstering the system’s effectiveness and trustworthiness. Besides, a logical reasoning-based localization decision strategy further enhances the system’s capabilities, allowing for controlled tracking intervals and step sizes that can be tailored to meet the task requirements under diverse working conditions. The collaboration of three modules makes it feasible to monitor dynamic changes of the detection robot in the pipeline along the direction of operation. The experimental results convincingly demonstrate that the integrated framework possesses several key advantages of remarkable robustness, real-time performance, and minimal error. It underscores the system’s potential to ensure energy pipeline safety efficiently and effectively.

Recognition of Fiber Optic Vibration Signals Based on Laplace Wavelet Transform and Deep Learning

AbstractConvolutional neural networks possess the capability of feature learning and nonlinear mapping, which has significant advantages in classifying and recognizing optical fiber vibration signals. In order to further enhance the recognition rate of vibration signals, this paper combines wavelet transform with convolutional neural networks and designs a convolutional layer based on parameterized wavelets. In this layer, the initial signal is convolved with parameterized Laplace wavelet dictionaries to complete the wavelet transform. Such customized filters make more sense than filters with randomly initialized parameters for traditional CNNs. Simultaneously, we introduce the channel attention mechanism to enhance the features of the filtered signals. Subsequently, standard CNNs are employed to extract and process signal features, ultimately utilizing a multi‐layer perceptron for recognition and classification. The experimental results show that the network model possesses better recognition refinement. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

A Pattern Recognition Method for Filter Bags in Bag Dust Collectors Based on Φ-Optical Time-Domain Reflectometry

The use of phase-sensitive optical time-domain reflectometry (Φ-OTDR)-distributed fiber vibration sensors to detect and identify damaged bags in bag dust collectors has the potential to overcome the inadequacy of traditional damaged bag detection methods. In our previous study, we verified the feasibility of applying this technique in the field of damaged bag detection in bag filters. However, many problems still occur in engineering applications when using this technology to detect and identify damaged filter bags in pulse-jet dust-cleaning bag dust collectors. Further studies are needed to characterize the fiber vibration signals inside different types of rectangular damaged filter bags. A filter bag damage identification and detection method based on empirical mode decomposition (EMD) and a backpropagation (BP) neural network is proposed. The signal feature differences between intact filter bags and damaged filter bags with different rectangular hole sizes and positions are comparatively analyzed, and optimal feature difference parameters are proposed. Support vector machine (SVM) and a BP neural network are used to recognize different types of filter bag signals, and the comparison results show that the BP neural network algorithm is better at recognizing different types of filter bags, obtaining the highest recognition rate of 97.3%.

Distributed Optical Fiber Vibration Signal Recognition Technology Based on Gramian Angular Field

Distributed Optical Fiber Vibration Signal Recognition Technology Based on Gramian Angular Field

Optical Fiber Vibration Signal Identification Method Based on Improved YOLOv4

In the traditional peripheral-security-early-warning system, the endpoint detection and pattern recognition of the signals generated by the distributed optical fiber vibration sensors is completed step-by-step and in an orderly manner. The method by which these two processes may be placed end-to-end in a network model and processed simultaneously to improve work efficiency has increasingly become the focus of research. In this paper, the target detection algorithm combines the endpoint-detection and pattern-recognition processes of the vibration signal, which can not only quickly locate the start and end vibration positions of the signal but also accurately identify a certain type of signal. You Only Look Once v4 (YOLOv4) is one of the most advanced target detection algorithms, achieving the optimal balance of speed and accuracy. To reduce the complexity of the YOLOv4 model and solve the dataset's unbalanced sample classification problem, we use a deep separable convolution (DSC) network and a focal loss function to improve the YOLOv4 model. In this paper, the five kinds of signals collected in real-time are visualized as two different datasets in oscillograph and time-frequency diagrams as detection objects. According to the experimental results, we obtained 98.50% and 93.48% mean Average Precision (mAP) and 84.8 and 69.9 frames per second (FPS), respectively, which are improved compared to YOLOv4. Comparing the improved algorithm with other optical fiber vibration signal recognition algorithms, the mAP and FPS values were improved, and the detection speed was about 20 times faster than that of other algorithms. The improved algorithm in this paper can quickly and accurately identify the vibration signal of external intrusion, reduce the false-alarm rate of the early-warning system, and improve the real-time detection rate of the system while ensuring high recognition accuracy.

Identification and classification of water absorption profile of distributed optical fiber vibration signal based on XGBoost algorithm

Aiming at the problem that the layered water injection cannot be accurately obtained in the process of oilfield development, this paper proposes an optical fiber vibration signal recognition and classification algorithm based on XGBoost integrated learning. Firstly, the optical fiber vibration signal collected by the optical fiber vibration sensor is denoised by variational mode decomposition and reconstruction. Then generate spectrograms corresponding to different water absorption layers at different times. A dataset containing 3000 spectral images is obtained. The data sets are imported into support vector machine, random forest classifier and XGBoost integrated classifier based on decision tree for recognition and classification. The parameters of the obtained model are optimized and the model is evaluated by cross validation. Finally, the obtained models are compared and tested. The experimental results show that the XGBoost ensemble learning algorithm with decision tree as the base classifier can effectively identify different vibration signals. This method has a certain significance for the identification of layered relative water absorption of water injection profile.

A Fiber Vibration Signal Recognition Method Based on CNN-CBAM-LSTM

By trying to solve the issue of identifying multiple types of intrusion vibration signals collected by distributed vibrating fiber optic sensors, this study investigates the signal identification and feature extraction of intrusion signals, and proposes an optical fiber vibration signal (OFVS) identification method based on deep learning. The external vibration signal is collected by the Sagnac fiber optic interferometer, and then denoised by spectral subtraction. Endpoint detection is carried out by combining the short-time logarithmic energy method and the spectral entropy method. Finally, the equal-length signal containing valid information is intercepted and the corresponding preprocessing is carried out. The method for feature processing incorporates the strong feature learning capability of the long-short-term memory (LSTM) and the great short-term feature extraction capability of the convolutional neural network (CNN). At the same time, to further enhance the signal feature identification, a convolutional block attention module (CBAM) is introduced to perform adaptive feature refinement on the signal. In summary, a network model combining CNN, LSTM, and CBAM is proposed to process the signal features, and finally, the multi-layer perceptron (MLP) is used to complete the task of classification and recognition of multi-type intrusion signals. The experimental findings indicate that the OFVS method of CNN-CBAM-LSTM can effectively identify four kinds of OFVS, and the overall average recognition accuracy reaches 97.9%. Walking and knocking signals among them are recognized with over 99% accuracy.

Optical Fiber Vibration Signal Recognition Based on the Fusion of Multi-Scale Features.

Because of the problem of low recognition accuracy in the recognition of intrusion vibration events by the distributed Sagnac type optical fiber sensing system, this paper combines the traditional optical fiber vibration signal recognition idea and the characteristics of automatic feature extraction by a convolutional neural network (CNN) to construct a new endpoint detection algorithm and a method of fusing multiple–scale features CNN to recognize fiber vibration signals. Firstly, a new endpoint detection algorithm combining spectral centroid and energy spectral entropy product is used to detect the vibration part of the original signal, which is used to improve the detection effect of endpoint detection. Then, CNNs of different scales are used to extract the multi–level and multi–scale features of the signal. Aiming at the problem of information loss in the pooling process, a new method of combining differential pooling features is used. Finally, a multi–layer perceptron (MLP) is used to recognize the extracted features. Experiments show that the method has an average recognition accuracy rate of 98.75% for the four types of vibration signals. Compared with traditional EMD and VMD pattern recognition and 1D–CNN methods, the accuracy of the optical fiber vibration signal recognition is higher.

A preliminary study on wellbore flow interpretation of fiber optic vibration signals based on K-means clustering algorithm

The wellbore flow analysis of optical fiber vibration signal depends on distributed optical fiber logging. Distributed optical fiber logging technology identifies the fluid in the well through distributed optical fiber acoustic sensor (DAS) and distributed optical fiber temperature sensor (DTS). Distributed optical fiber sensor has the advantages of small underground interference, high efficiency and low cost. In this paper, the wellhead data extracted by the distributed optical fiber acoustic sensor is used to calculate the upper bound of the fluid sound frequency band in the pipe by nonlinear least squares fitting. The K-means clustering algorithm is used to cluster the optical fiber vibration signals in the low frequency band. According to the clustering results, the ratio of the optical fiber signal eigenvalues of each production layers is obtained, and the trend of the ratio of the optical fiber signal eigenvalues of each production layers is judged to be close to the trend of the water absorption intensity. Compared with traditional acoustic logging, the wellbore flow analysis using distributed optical fiber acoustic sensor can quickly determine the production contribution of each layer and the change of fluid phase state in the production cycle. Combined with traditional production logging technology, distributed optical fiber logging shows its reliability and accuracy in data collection, logging interpretation and production application. Starting from the principle of distributed optical fiber acoustic sensing technology, this paper briefly expounds the properties of distributed optical fiber acoustic sensor and the principle of injection profile logging, systematically introduces the processing of distributed optical fiber acoustic data, and emphatically introduces the accuracy of K-means clustering algorithm for analyzing distributed optical fiber acoustic signal and qualitative judgment of production layer, which provides a new idea for judging the accuracy of production layers.

Feature Extraction Algorithm of Optical Fiber Vibration Signal Based on Compensation Distance Estimation

Feature Extraction Algorithm of Optical Fiber Vibration Signal Based on Compensation Distance Estimation

A Fiber Vibration Signal Identification Method Based on the Combination of EWT-FE and LSTM

As the optical fiber perimeter security system is widely used in real life, how to identify the types of intrusion events in a timely and effective manner is becoming a major research hotspot. At present, in this field, various signal feature extraction algorithms are usually used to extract intrusion signal features to form feature vectors, and then machine learning algorithms are used to classify the feature vectors to achieve the role of identifying the types of intrusion events. As a common signal feature extraction algorithm, the EMD algorithm has been widely used in the feature extraction of various vibration signals, but it will have the problem of modal aliasing and affect the feature extraction effect of the signal. Therefore, EWT, VMD and other algorithms have been successively used proposed to improve modal aliasing. On the basis of fully comparing the existing algorithms, this paper proposes a fiber vibration signal identification method that decomposes the signal through the empirical wavelet transform (EWT) algorithm and then extracts the fuzzy entropy (FE) of each component, and uses LSTM for classification. The final experiment shows that the method can identify four kinds of fiber intrusion signals in time and effectively, with an average recognition accuracy rate of 97.87%, especially for flap and knock recognition rate of 100%.

An Improved High-Intelligence Method of Gas and Oil Pipeline Prewarning System in Real Soil Environment

With the development of technology, the total extent of global pipeline transportation is also increased. However, the traditional long-distance optical fiber prewarning system has poor real-time performance and high false alarm rate when recognizing events threatening pipeline safety. The same vibration signal would vary greatly when collected in different soil environments and this problem would reduce the signal recognition accuracy of the prewarning system. In this paper, we studied this effect theoretically and analyzed soil vibration signals under different soil conditions. Then we studied the signal acquisition problem of long-distance gas and oil pipeline prewarning system in real soil environment. Ultimately, an improved high-intelligence method was proposed for optimization. This method is based on the real application environment, which is more suitable for the recognition of optical fiber vibration signals. Through experiments, the method yielded high recognition accuracy of above 95%. The results indicate that the method can significantly improve signal acquisition and recognition and has good adaptability and real-time performance in the real soil environment.

Pattern Recognition of Grating Perimeter Intrusion Behavior in Deep Learning Method

An intrusion behavior recognition method based on deep learning is proposed in this paper in order to improve the recognition accuracy of raster perimeter intrusion behavior. The Mach–Zehnder fiber optic interferometer was used to collect the external vibration signal sensing unit, capture the external vibration signal, use the cross-correlation characteristic method to obtain the minimum frame length of the fiber vibration signal, and preprocess the intrusion signal according to the signal strength. The intrusion signals were superimposed and several sections of signals were intercepted by fixed window length; the spectrum information is obtained by Fourier transform of the intercepted stationary signals. The convolution neural network was introduced into the pattern recognition of the intrusion signals in the optical fiber perimeter defense zone, and the different characteristics of the intrusion signals were extracted, so as to realize the accurate identification of different intrusion signals. Experimental results showed that this method was highly sensitive to intrusion events, could effectively reduce the false alarm rate of intrusion signals, and could improve the accuracy and efficiency of intrusion signal recognition.

Use AF-CNN for End-to-End Fiber Vibration Signal Recognition

Traditional optical fiber vibration signal (OFVS) recognition research focuses on signal endpoint detection and feature extraction. These two aspects directly determine the success of OFVS recognition. The traditional method relies on artificially designed features and has a strong pertinence to the classification target, resulting in poor stability and flexibility. In response to the above problems, this paper combines the traditional OFVS recognition ideas (time-frequency analysis and feature extraction) and the characteristics of deep learning automatic learning parameters to construct an end-to-end adaptive filtering convolutional neural network (AF-CNN), which can directly get the classification results through the iterative update of the network. In modeling the original signal, the following steps were taken to make the network interpretable. First, we use a one-dimensional (1-D) convolution on the original OFVS. The convolution kernel can adaptively treat the original signal perform filtering to obtain filtered signals of different frequency bands. Second, using a general convolutional neural network (CNN) to extract the filtered signal features. Finally, a multi-layer perceptron (MLP) is used for classification. This paper compares the AF-CNN network with three traditional pattern recognition methods and proves that the AF-CNN network's accuracy is better than traditional pattern recognition methods. The average accuracy can reach 96.7%, and it can effectively distinguish OFVS with weaker energy and similar waveforms.

Pattern Recognition of Optical Fiber Vibration Signal of the Submarine Cable for Its Safety

Submarine cables are the main sources of power supply for oil rigs; in this regard, they must be assessed and effectively secured. Monitoring of the environment of submarine cables is rare, and cable faults generally require interventions. This article develops the detection and recognition of shock events on submarine cables using the vibration signals of its optical fiber sensor. The vibration signals from the optical fiber are detected by means of phase-sensitive optical time-domain reflectometry ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Phi $ </tex-math></inline-formula> -OTDR). An effective fiber vibration pattern recognition scheme based on the time-frequency-domain characteristics (TFDC) and Support vector machine (SVM) is proposed. The scheme uses the TFDC for the recognition of the fiber vibrations, and the SVM to determine the magnitude of the event. Three different groups of data are collected and processed in real-time. Experimental results from multiple tests carried out on data samples show that the proposed method is valid and reliable for recognizing and determining the magnitude of events on the submarine cable.

Research on Noise Reduction of Φ-OTDR Signal Based on Blind Source Separation Algorithm

Optical fiber sensing has become an important means of health and safety monitoring of large buildings and facilities due to its better sensing characteristics. Undesirable noise signals are inevitably generated during actual sensor data acquisition. This paper focuses on the noise reduction processing of optical fiber Φ-OTDR vibration signal. Firstly, the acquired signal is preprocessed with data, then the data is independently correlated, and finally the FastICA algorithm in blind source separation is used to filter the noise signal. In this paper, the traditional wavelet transform algorithm is compared to reduce noise. The experimental results show that the blind source separation algorithm has better separation effect on fiber vibration signals.

Research and Software Design of an Φ-OTDR-Based Optical Fiber Vibration Recognition Algorithm

Distributed optical fiber vibration signal plays a significant role in the communication and safety of any perimeter security monitoring system. It uses light as an information carrier and optical fiber as a means of signal transmission and communication. Phase-sensitive optical time-domain reflectometry (Φ-OTDR) is used to detect the signals generated during events (intrusions or nonintrusion). This paper proposes the time-frequency characteristic (TFC) method for the recognition of the fiber vibration signal and designs and implements the corresponding software function module. The combination of time-domain features and time-frequency-domain features is called TFC; and it is based on the Hilbert transform and on the empirical mode decomposition (EMD) of time-frequency entropy and center-of-gravity frequency that is described. A feature vector is formed, and multiple types of probabilistic neural networks (PNNs) are performed on it to determine whether intrusion events occur. The experimental simulation results show that the monitoring system software can intelligently display the data collected in real time, which demonstrates that the proposed method is effective and reliable in identifying and classifying accurately the types of events. The data processing time is less than 2 s, and the accuracy of the system identification can reach 99%, which ensures the system’s validity.

Pattern recognition algorithm and software design of an optical fiber vibration signal based on Φ-optical time-domain reflectometry.

A phase-sensitive optical time-domain reflectometry with a detection distance of 10 km is used in this paper to recognize and to detect in real time events along the perimeter security monitoring system. To optimize the signal processing in the software system and achieve the design of distributed optical fiber vibration signal of the perimeter security monitoring system, a two-level vibration pattern recognition scheme based on the power spectral estimation is proposed. The monitoring system software of the proposed algorithm is designed and implemented, as well as the functional modules involved in the design of the software system. The experimental tests of the whole system show that the proposed algorithm can effectively identify in real time any intrusion event along the sensing cable, with an intrusion detection rate greater than 95%, including false alarms. Also, the corresponding monitoring system software can display the data collected in real time, with a processing time of around 1.6 s, which proves its reliability, thereby ensuring the system's validity.