Determining Machine Movement Direction to Prevent Cable Breakage Based on Vibration Proximity Monitoring System (VPMS)

Abstract

A system and method for estimating mechanical distance to an optical fiber cable from sensing data collected using distributed optical fiber sensing (DFOS) is disclosed. DFOS is dedicated hardware that uses optical sensor fibers as continuous spatial sensors along with a real-time artificial intelligence (AI) processing unit to detect threats in the vicinity of buried optical fiber cables and identify their direction of movement, thereby effectively mitigating and containing the threat before the buried optical fiber cable is damaged. The disclosed system has the advantage of not requiring prior location knowledge or surveying before performing monitoring.

Description

[Technical Field]

[0001] This application relates generally to distributed fiber optic sensing (DFOS) systems, methods, structures, and related technologies. Specifically, this application relates to determining machine movement direction for cable cut prevention based on vibration proximity monitoring systems (VPMS). [Background technology]

[0002] Fiber optic infrastructure is the foundation of modern communications networks. The reliability of optical fiber in communications networks is crucial to the services offered by network operators and to their customers. One of the challenges for operators is protecting cables from potential catastrophic damage caused by construction and other activities. As is well known, damage to fiber optic networks can occur due to a lack of accurate positioning surveys or a lack of survey information due to old fiber optic cable deployments.

[0003] Damage to fiber optic cables can lead to service interruptions and costly repairs. Therefore, preventing fiber optic cable cuts is extremely important to communications service providers. In situations where machinery such as excavators is operating in the vicinity of fiber optic cables, it is most desirable for service providers to become aware of such machinery's threat to the fiber optic cables before a cut occurs. Summary of the Invention

[0004] An advancement in the art is achieved through aspects of the present disclosure that relate to systems, methods, and structures that estimate mechanical distance to a fiber optic cable from sensing data collected using distributed fiber optic sensing (DFOS).

[0005] An example of DFOS sensing operation is detecting construction machinery operating at a distance of 140 to 170 meters perpendicular to a fiber optic cable. The vibration signals generated by the machinery are detected by DFOS at a distance of, for example, 17,820 to 18,300 meters measured along the fiber optic cable from the DFOS interrogator. DFOS interprets the DFOS vibration signals and generates a visual display. In this visual display, stronger vibration signals caused by machinery approaching the fiber optic cable are displayed, for example, in brighter colors. In this way, operators can quickly observe the visual display to determine whether the operating machinery poses a threat to the fiber optic cable and take preventative measures.

[0006] The system and method of the present invention, i.e., a vibration proximity monitoring system (VPMS) according to an embodiment of the present disclosure, includes dedicated hardware, DFOS, that uses optical sensor fibers as continuous spatial sensors along with a real-time artificial intelligence (AI) processing unit to detect threats in the vicinity of buried fiber optic cables and identify the direction of movement of the threats, thereby effectively mitigating and suppressing the threats before the buried fiber optic cables are damaged. Advantageously, the VPMS according to the present disclosure does not require prior location knowledge or surveying before performing monitoring.

[0007] In contrast to prior art, the VPMS of the present invention provides 24 / 7 continuous monitoring throughout the entire fiber optic cable route, supports monitoring of multiple equipment operating areas, detects imminent threats in real time, and immediately notifies operators.

[0008] Furthermore, VPMS can utilize existing installed cables as a sensing medium for cable self-monitoring, eliminating the need for dedicated new sensors. In addition to monitoring, such cables can advantageously simultaneously carry live communications traffic. Generally, no hardware installation or deployment along the cable is required, no visual display along the cable is required, and multiple AI analysis modes are required to adapt to various environmental and external conditions. [Brief explanation of the drawings]

[0009] [Figure 1(A)] FIG. 1 is a schematic diagram illustrating an exemplary prior art uncoded DFOS system. [Figure 1(B)] FIG. 1 is a schematic diagram illustrating an exemplary prior art coded DFOS system.

[0010] [Figure 2] 1 is a schematic block diagram illustrating exemplary features and exemplary sequences of systems and methods according to aspects of the present disclosure.

[0011] [Figure 3] FIG. 1 is a schematic block diagram illustrating an exemplary system configuration and setup according to aspects of the present disclosure.

[0012] [Figure 4] 1 is a graph showing an illustrative example of waterfall sensing data according to aspects of the present disclosure.

[0013] [Figure 5(A)] 1 illustrates an exemplary Siamese neural network according to aspects of the present disclosure. [Figure 5(B)] 1 illustrates an exemplary Siamese neural network according to aspects of the present disclosure.

[0014] [Figure 6] 1 illustrates a discrete Fourier transform (DFT) according to an embodiment of the present disclosure.

[0015] [Figure 7] FIG. 1 illustrates an exemplary hierarchical feature diagram of a system and method according to aspects of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] The following merely illustrates the principles of the present disclosure, and it will thus be appreciated that those skilled in the art will be able to devise various arrangements which, although not explicitly described or shown herein, embody the principles of the present disclosure and are included within its spirit and scope.

[0017] Furthermore, all examples and conditional language set forth herein are intended to be for educational purposes only to aid the reader in understanding the concepts contributed by the inventors to further the principles and techniques of the present disclosure, and should not be construed as being limited to such specifically recited examples and conditions.

[0018] Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, such equivalents are intended to include both currently known equivalents as well as equivalents developed in the future, i.e., elements developed that perform the same function, regardless of structure.

[0019] Thus, for example, it will be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative circuitry embodying the principles of the disclosure.

[0020] Unless otherwise specified herein, the figures comprising the drawings are not drawn to scale.

[0021] As some additional background, note that a distributed fiber optic sensing system interconnects an optoelectronic integrator to an optical fiber (or cable), transforming the fiber into an array of sensors distributed along the fiber. In effect, the fiber becomes the sensor, and the interrogator generates / injects laser light energy into the fiber to sense / detect events along the fiber.

[0022] As those skilled in the art will understand and appreciate, DFOS technology can be deployed to continuously monitor vehicle movement, human traffic, drilling activity, seismic activity, temperature, structural integrity, liquid and gas leaks, and many other conditions and activities. It is used worldwide to monitor power plants, communication networks, railroads, roads, bridges, borders, critical infrastructure, onshore and offshore power lines and pipelines, and downhole applications in oil, gas, and enhanced geothermal power generation. Advantageously, distributed fiber optic sensing is not constrained by line of sight or remote power access and, depending on the system configuration, can be deployed over continuous lengths of more than 30 miles, with sensing / detection possible at every point along that length. Therefore, the cost per sensing point over long distances is typically incomparable to competing technologies.

[0023] Distributed fiber optic sensing measures changes in the "backscatter" of light that occurs within an optical sensing fiber when the fiber encounters environmental changes, including vibration, strain, or temperature change events. As previously mentioned, the optical sensing fiber acts as a sensor along its entire length, providing real-time information about the physical and environmental surroundings and the integrity and security of the fiber. Furthermore, distributed fiber optic sensing data pinpoints the precise location of events and conditions occurring on or near the sensing fiber.

[0024] A schematic diagram illustrating the generalized arrangement and operation of a distributed optical fiber sensing system that may advantageously include artificial intelligence / machine learning (AI / ML) analysis is illustratively shown in Figure 1(A). Referring to Figure 1(A), it can be seen that the optical sensing fiber is connected to an interrogator. Although not shown in detail, the interrogator can include a coded DFOS system that can employ a coherent receiver arrangement known in the art, such as that shown in Figure 1(B).

[0025] As is well known, a modern interrogator is a system that generates an input signal into an optical sensing fiber and detects and analyzes the reflected / backscattered signal that is then received. The received signal is analyzed and an output is generated that is indicative of the environmental conditions encountered along the fiber. The received backscattered signal may be due to reflections within the fiber, such as Raman backscattering, Rayleigh backscattering, or Brillouin backscattering.

[0026] As will be appreciated, modern DFOS systems include an interrogator that periodically generates optical pulses (or any coded signal) and launches them into an optical sensing fiber, which transmits the optical pulse signal along the optical fiber.

[0027] At each location along the fiber, a small portion of the signal is backscattered / reflected and transmitted back and forth to the interrogator, where it is received. The backscattered / reflected signal carries information that the interrogator uses to detect, such as changes in power level that indicate mechanical vibrations.

[0028] The received backscattered signal is converted to the electrical domain and processed within the interrogator. Based on the time of pulse incidence and the time the received signal is detected, the interrogator can determine from which location along the optical sensing fiber the received signal returned, thereby sensing activity at each location along the optical sensing fiber. Classification methods may also be used to detect and locate events or other environmental conditions, including acoustic and / or vibration and / or heat, along the optical sensing fiber.

[0029] This additional background is provided to introduce distributed acoustic sensing. When DAS techniques are used, the receiver / interrogator is located at the far end of the transmitter-receiver configuration.

[0030] Systems, methods, and structures according to aspects of the present disclosure are further shown and described below.

[0031] 2 is a schematic block diagram illustrating exemplary features and an exemplary sequence of a system and method according to an embodiment of the present disclosure. As shown in this figure, a DFOS system (DAS / DVS) is connected to an optical sensor fiber used for a particular test operation.

[0032] As previously described, the DFOS operates by receiving vibration signals from optical sensor fibers deployed in the field, including, for example, ambient noise, normal road traffic, road construction, and traffic patterns generated along the road and optical sensor fibers.

[0033] Traffic patterns are recognized by AI methods and normal traffic conditions are filtered out. An AI engine is used for machine distance prediction using VPMS.

[0034] If the machine approaches the optical sensor fiber cable according to a predetermined condition, the determined machine position is reported to the operator.

[0035] FIG. 3 is a schematic block diagram illustrating an exemplary system configuration and setup according to an embodiment of the present disclosure.

[0036] Simulates a moving machine.

[0037] As can be seen in this diagram, sensing "layers" of optical sensors are layered on top of the testbed fiber. DFOS can be distributed acoustic sensing (DAS) and / or distributed vibration sensing (DVS), and a controller / interrogator / analyzer can be installed at a control / central station for remote monitoring of the entire cable route. Note that control / analysis functions can also be located remotely, i.e., in the "cloud."

[0038] As mentioned above, the DFOS system is connected to an optical sensor fiber to provide long-term, real-time sensing capabilities. This fiber can be dark fiber or a service provider's operational fiber. This evaluation focuses on the direction of machine movement, where the machine continues to approach the fiber and potentially poses a threat to the underground fiber optic cable.

[0039] Obtain sensing data from DFOS.

[0040] The signal received from DFOS is represented as a waterfall trace, and this data is processed as an image to extract information for further processing.

[0041] Get input data.

[0042] Part of the inventive system and method according to aspects of the present disclosure is an analytical algorithm that processes input data to determine the direction of movement of a vibration source, such as a construction machine.

[0043] Among all analysis algorithm steps, the first general operation is the acquisition of input data. In an exemplary embodiment, the input data is a two-dimensional (time x distance) vibration intensity data snapshot from the waterfall (vibration intensity at each sensing point along the cable over time). A sample snapshot is shown in FIG. 4, which is a graph illustrating an illustrative example of waterfall sensing data according to aspects of the present disclosure.

[0044] Data processing.

[0045] The input data is processed differently by each analysis algorithm:

[0046] Siamese Neural Network: This method uses a pairwise comparison model in a triplet setup. A: A random snapshot from class A B: Another snapshot from class A C: Snapshot from a class other than Class A

[0047] A deep learning model was deployed, specifically a five-layer convolutional neural network (CNN) using a triplet setup as shown in Figures 5(A) and 5(B), which illustrate an exemplary Siamese neural network according to an embodiment of the present disclosure.

number

[0048] If B is of the same class as A, the label will be 1 (or the same class), otherwise the label will be 0 or some other class. We evaluate various models that evaluate this criterion and select the best model.

[0049] To put that into context, in real-time evaluation, the model compares new snapshots with old ones. If the model assesses that the new snapshot is not of the same class as the previous snapshot, it flags it. Further analysis can predict whether the machine is approaching (approach) or moving away (departure) from the cable's location.

[0050] Bayesian inference: In this method, the decision outcome for each input snapshot when movement is detected is binary, so the semi-binomial probability distribution function can be used to quantify the probability of approaching or leaving the buried cable. Unlike the binomial distribution, the leaving probability

number

number

[0051] Power Spectrum Analysis: In this method, a snapshot of the observed 1D waveform data is used as the input for real-time analysis instead of a 2D snapshot. The waveform is decomposed using the Discrete Fourier Transform (DFT) and Discrete Cosine Transform (DCT). The idea is that because vibrations vary with distance from the cable, the energy decay pattern varies with frequency, allowing the direction of movement to be detected. A sample DFT in Figure 6 shows eight waveforms and their amplitudes and corresponding frequency responses. It can be seen that the energy density is lower for the same vibration frequency at sensing points at farther distances (fifo0 and fifo7).

[0052] FIG. 7 is an exemplary hierarchical feature diagram of systems and methods according to aspects of the present disclosure.

[0053] While the present disclosure has been presented above using some specific examples, those skilled in the art will recognize that the present teachings are not so limited. Accordingly, the present disclosure should be limited only by the scope of the claims appended hereto.

Claims

1. 1. A method for determining the direction of movement of a machine in the cable cutting direction, comprising: operating a distributed fiber optic sensing system (DFOS) to obtain sensing data indicative of machine operation; and determining from the sensing data indicative of machine operation whether the machine is approaching or moving away from the sensor fiber of the DFOS.

2. The method of claim 1 , wherein the acquired sensing data is DFOS waterfall data.

3. The method of claim 2 , wherein the decision to move towards or away from is made by a convolutional neural network (CNN).

4. 4. The method of claim 3, wherein the CNN is trained based on a Siamese neural network (SNN) and one or more of triplet loss and contrast loss.

5. The method of claim 2 , wherein the decision to move towards or away from the object is made by Bayesian inference and maximum likelihood modeling (MLM).

6. 6. The method of claim 5, wherein a binomial probability distribution is developed in which the outcome is either approach (p) or departure (q), where p and q are implicit functions of the vibration strength.

7. The method of claim 2 , wherein the approaching or moving away determination is made by power spectrum-based analysis using frequency component decomposition of the received waveform.

8. 8. The method of claim 7, wherein the analysis of the power spectrum using frequency component decomposition of the received waveform is based on the discrete Fourier transform (DFT) and the discrete cosine transform (DCT), and predicts whether the vibration source is approaching or moving away by utilizing the variation in attenuation of different frequencies with distance caused by mechanical movement of the vibration source.

Images