System for measuring coil position and length of airborne fiber cable using distributed fiber sensing

Abstract

A distributed fiber optic sensing (DFOS) / distributed acoustic sensing (DAS) system and method uses a fiber optic sensor cable to collect vibration data of individual utility poles that suspend the fiber optic sensor cable and stores the vibration data at a central office (CO). A machine learning (ML) model is built, trained, and used to analyze the vibration signature of the utility pole and determine its integrity. Additionally, the DFOS / DAS system and method according to the present disclosure determines the location of fiber coils present along the fiber optic sensor cable.

Description

[Technical Field]

[0001] This application relates generally to distributed fiber optic sensing (DFOS) / distributed acoustic sensing (DAS) systems, methods, structures, and machine learning (ML) techniques, and more particularly to utility pole integrity assessment using DAS, machine learning using environmental noise data, and determining the location of fiber coils along airborne fiber optic cables. [Background technology]

[0002] Utility pole integrity is critical to both utility infrastructure operations and public safety. Currently, utility pole integrity inspections require well-trained inspectors / staff to conduct on-site inspections, including visual inspections, hammer tests, excavation around the pole, and drilling holes into the pole for sampling. This inspection procedure must be performed individually for every utility pole. Therefore, it is labor-intensive, time-consuming, subjective, highly dependent on the inspector's experience, and highly invasive to the pole structure.

[0003] Additionally, aerial fiber optic cables are used to deliver communication services to both residential and commercial premises of service provider customers. During deployment, telecommunications service providers often leave fiber optic cable unused as coils distributed along the fiber optic cable route to accommodate future drop points, branches, and repairs. However, the recorded lengths and locations of these fiber coils are often inaccurate or outdated. Therefore, it is beneficial for telecommunications operators to accurately determine the location of these coils without undergoing time-consuming and labor-intensive tasks. Summary of the Invention

[0004] An advancement in the art is achieved according to aspects of the present disclosure relating to a distributed fiber optic sensing (DFOS) / distributed acoustic sensing (DAS) system and method that collects vibration data from individual utility poles and stores the vibration data at a central office (CO). A machine learning (ML) model is developed and utilized to analyze the vibration signature of utility poles and determine the integrity of the utility poles. Additionally, the DFOS / DAS system and method according to the present disclosure determines the location of fiber coils present along the fiber optic cable.

[0005] In a significant departure from the prior art, systems and methods according to aspects of the present disclosure provide for autonomous determination of utility pole integrity through ML models, thereby advantageously eliminating human-induced subjectivity, resulting in more efficient, less costly, and more objective utility pole inspection and integrity determination.

[0006] The systems and methods disclosed herein advantageously assess the integrity of utility poles by using existing communication fiber optic cables, allowing for simultaneous handling of live communication traffic, random environmental noise, DFOS / DAS techniques, and machine learning models.

[0007] Operationally, random environmental noise induces vibrations in the target utility pole, and the vibration signals are picked up by a fiber optic cable attached to the target utility pole, which are then detected and recorded by the DFOS / DAS. By applying the designed machine learning model to the DAS signals, the integrity status of the target utility pole can be obtained.

[0008] The machine learning model is trained using the known integrity of the pole being trained and DAS signals excited by random environmental noise. The machine learning model classifies the DAS signals into corresponding integrity classes for the pole. The pre-trained model is then used to assess the integrity of the pole by classifying the DAS signals from the test pole into different integrity classes.

[0009] Viewed from another aspect, systems and methods are disclosed herein that advantageously distinguish the location of fiber coils along an aerial fiber optic cable and provide accurate length and location results for the coils. [Brief explanation of the drawings]

[0010] [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.

[0011] [Figure 2] FIG. 1 is a schematic diagram illustrating an example operation of model training and utility pole integrity assessment according to aspects of the present disclosure.

[0012] [Figure 3] 1 is a schematic diagram illustrating exemplary vibration generation and DFOS / DAS detection according to an embodiment of the present disclosure. FIG.

[0013] [Figure 4] FIG. 1 is a schematic diagram illustrating exemplary operational features of a system and method for utility pole integrity assessment according to aspects of the present disclosure.

[0014] [Figure 5] 10A-10C are schematic diagrams illustrating exemplary operations of model training and coil location detection according to aspects of the present disclosure.

[0015] [Figure 6] 1 is a schematic diagram illustrating exemplary operational features of a system and method for fiber coil position detection 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. Additionally, 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 backscatter, Rayleigh backscatter, or Bullion backscatter.

[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 then transmits the optical pulse signal along the optical fiber.

[0027] At certain locations along the fiber, a small portion of the signal is backscattered / reflected back 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 further 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] 2 is a schematic diagram illustrating an exemplary operation of model training and utility pole integrity assessment according to an embodiment of the present disclosure. With reference to this figure, it should be noted that to assess the integrity of the utility pole, a DFOS / DAS interrogator located within a central office (CO) and optically connected to one end of the fiber optic sensor cable continuously interrogates the fiber optic sensor cable to detect strain changes occurring along the fiber optic sensor cable due to environmental activity, including vibration activity of the utility pole from which the fiber optic sensor cable is suspended.

[0030] Target utility poles deployed in the field are constantly vibrating due to "environmental noise" generated by random events occurring in the surrounding environment, such as weather, traffic, earthquakes, construction, and other human activities that impart mechanical vibrations to the target utility poles. Because the optical fiber sensor cables are suspended / attached / fixed to the utility poles, such vibrations of the utility poles also induce vibrations in the optical fiber sensor cables suspended / attached / fixed to the utility poles, which in turn induce strain changes in the optical fiber sensor cables and are detected as DFOS / DAS signals. These detected signals are stored in a storage server at a central station or other location. The DFOS / DAS interrogator operates to collect DFOS / DAS vibration signal data from each utility pole along the optical fiber sensor cables for a certain period of time. This DFOS / DAS vibration signal data collection can be continuous or intermittent.

[0031] The stored DFOS / DAS signals are then used to train machine learning models or for utility pole integrity assessment. During model training, DFOS / DAS signals from target utility poles, along with their known integrity status, are used to train the machine learning model. For utility pole integrity assessment, the DAS signals from target utility poles are input into a pre-trained machine learning model, and the model outputs the integrity status of those poles. This process can be repeated multiple times to improve the assessment accuracy. Advantageously, a single DFOS / DAS interrogator can capture vibration data signals from all utility poles in vibration communication with the fiber optic sensor cables suspended on the poles. Even more advantageously, DFOS / DAS interrogation and signal capture can be performed on multiple utility poles simultaneously.

[0032] 3 is a schematic diagram illustrating exemplary vibration generation and DFOS / DAS detection according to an embodiment of the present disclosure. As shown in this figure, a series of utility poles suspend airborne fiber optic sensor cables, which are in optical communication with a DFOS / DAS interrogator.

[0033] Random environmental conditions, such as weather (i.e., wind), traffic, or other vibration sources not specifically shown, cause the utility pole to react to such environmental conditions with vibration activity that is mechanically transmitted to the airborne fiber optic sensor cable suspended from the utility pole. During operation, the DFOS / DAS interrogates the airborne fiber optic sensor cable and detects the resulting strain / stress on the fiber optic sensor cable as a DFOS / DAS vibration signal. These DFOS / DAS vibration signals are transmitted to a storage server for DFOS / DAS signal processing, including training of ML models, and subsequent utility pole integrity decisions.

[0034] An overview of the operating procedure according to an aspect of the present disclosure can be described as follows.

[0035] The DFOS / DAS interrogator is connected to one end of the optical fiber sensor cable, and the interrogator is operated to detect vibrations in the optical fiber sensor cable and record them as DFOS / DAS signals.

[0036] The DFOS / DAS interrogator records ambient DFOS / DAS vibration signals received from fiber optic sensor cable segments in close proximity to each target utility pole. In typical operation, the length of time DFOS / DAS vibration data is recorded from each utility pole is typically two hours or more and can be continuous or intermittent. As previously mentioned, DFOS / DAS vibration data recording from individual utility poles can be performed simultaneously or individually.

[0037] To train a utility pole integrity assessment model, DFOS / DAS vibration data collection must be performed on multiple utility poles with known integrity conditions. The DFOS / DAS signals from these "known" utility poles and their integrity conditions are used to train a machine learning model for utility pole integrity classification. This results in a pre-trained model for utility pole integrity assessment. Advantageously, the utility poles exhibiting known integrity conditions and used in training the ML model may be located on different fiber routes that are geographically separated from each other.

[0038] Once the ML model is pre-trained and ready, received DFOS / DAS signals originating from one of the tested utility poles can be fed to the pre-trained model. The pre-trained model can advantageously classify the received DFOS / DAS signals into different utility pole integrity classes. In this ingenious manner, the integrity status of the tested utility pole is obtained. Once the model is pre-trained, additional training may not be necessary.

[0039] FIG. 4 is a schematic diagram illustrating exemplary operational features of a system and method for utility pole integrity assessment according to an embodiment of the present disclosure.

[0040] FIG. 5 is a schematic diagram illustrating an example operation of model training and coil location detection according to an embodiment of the present disclosure.

[0041] To detect the coil's position and length, a DFOS / DAS interrogator located within a central office (CO) is optically connected to the near end of the fiber optic sensor cable and continuously interrogates and monitors strain changes occurring along the fiber optic sensor cable. The fiber optic sensor cable is subjected to constant vibrations caused by environmental noise resulting from random events occurring in the surrounding environment, such as weather, earthquakes, traffic, construction, and other human activities. This vibration is received by the operating DFOS / DAS interrogator as vibration signals from positions along the fiber optic sensor cable and then stored in a storage server located at the CO. The DFOS / DAS interrogator collects such vibration signal data from positions along the fiber optic sensor cable for a certain period of time. Such data collection can be continuous or intermittent.

[0042] The stored DFOS / DAS signals are preprocessed using a short-time Fourier transform and converted into segmented spectral data, which are then used to present the DFOS / DAS signal spectral features to a machine learning model.

[0043] During the model training procedure, the segmented spectral data from each location along the fiber optic sensor cable, along with an identification of whether the corresponding location is part of a coil of optical fiber or part of a straight fiber optic cable, are used to train a machine learning model to distinguish between coil locations and straight cable locations.

[0044] In the coil location procedure, the segmented spectral data is input into a pre-trained coil location model, and the trained model outputs whether each location on the target cable is part of a coil or a straight fiber. Therefore, it is possible to know which parts of the target cable are coils, and consequently, their locations and lengths on the target fiber optic sensor cable.

[0045] FIG. 6 is a schematic diagram illustrating exemplary operational features of systems and methods for fiber coil position detection according to embodiments of the present disclosure. At this point, while the present disclosure has been presented using certain 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 a position of a coil in a fiber optic cable using a distributed fiber optic sensing (DFOS) system, the method comprising: an optical fiber sensor, at least a portion of which is coil-shaped; an optical interrogator in optical communication with the fiber optic sensor, the optical interrogator configured to generate optical pulses from a laser light, inject the optical pulses into the fiber optic sensor, and receive backscattered signals from the fiber optic sensor, the received backscattered signals originating at a location of the fiber optic sensor and resulting from environmental activity occurring at the location of the fiber optic sensor; an analyzer configured to store and analyze the backscattered signals received from locations along the fiber optic sensor; and providing the DFOS system, comprising: operating the optical interrogator for a predetermined period of time and storing the backscattered signals received from the locations along the fiber optic sensor; preprocessing the stored backscattered signals using a short-time Fourier transform to generate transformed segmented spectral data for the position along the fiber optic sensor; training a machine learning model using the transformed segmented spectral data for the positions along the fiber optic sensor and an identification of whether the corresponding positions are part of a coil of fiber optic sensor or part of a straight fiber optic sensor; operating the optical interrogator in a coil position detection mode to generate detection mode backscatter signals for positions along the optical fiber sensor; and converting the detection mode backscatter signals into detection mode converted segmented spectral data for positions along the optical fiber sensor; determining a position of a coil of the fiber optic sensor from the trained machine learning model and the detection mode segmented spectral data of positions along the fiber optic sensor.

2. The method of claim 1 , wherein said operation of said optical interrogator for a predetermined time is continuous operation.

3. The method of claim 1 , wherein said operation of said optical interrogator for a predetermined time period is intermittent operation.

4. The method of claim 1 , wherein the DFOS system is a distributed acoustic sensing (DAS) system.

Images