AI-driven Cable Mapping System (CMS) using fiber sensing and machine learning

Abstract

This AI-driven cable mapping system uses distributed fiber optic sensing (DFOS) fiber sensing and machine learning to autonomously determine and map the location of optical fiber cables. The AI ​​algorithms designed to operate in the system and method provide a simple solution for cable mapping in GIS systems, automatically mapping using landmark and manhole locations and employing supervised learning algorithms. Vehicle-assisted operation is used, with vehicles equipped with global positioning system (GPS) devices traveling along roads that trace the optical fiber cable route. Data pairing synchronizes time between the DFOS system and the vehicle GPS devices, automatically pairing fiber length and GPS coordinate data from traffic trajectories over time to provide additional critical location information.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63 / 415,394, filed October 12, 2022, the entire contents of which are incorporated by reference as if set forth herein.

[0002] This application relates to distributed fiber optic sensing (DFOS) / distributed acoustic sensing (DAS) systems, methods, and structures, as well as artificial intelligence and machine learning (ML) techniques. More specifically, this application relates to an artificial intelligence-driven cable mapping system (CMS) using fiber optic sensing and machine learning. [Background technology]

[0003] Fiber optic mapping (mapping / locating fiber optics on a map) is an ongoing challenge for telecommunications and cable operators, as there are now millions of miles of fiber optics across the country that carry numerous services, including 5G. In many cases, routing information for deployed fiber optics relies on prior information and knowledge about the placement and orientation of the fiber optic cable, which may come from construction maps of the deployment site or notes and photographs taken during construction / deployment. However, in most cases, such information is not up to date.

[0004] If such location information does not exist or is unavailable, it would be extremely time-consuming and costly for operators / service providers to identify the exact location of fiber optic cables. Unfortunately, no system / method exists for automatically locating and mapping fiber optic cables deployed in the field. Summary of the Invention

[0005] Aspects of the present disclosure directed to an AI-driven cable mapping system using fiber sensing and machine learning solve the above problems and advance the art.

[0006] In contrast to the prior art, systems and methods according to aspects of the present disclosure autonomously locate and map fiber optic cables using optical fiber sensing technology and environmental landmarks integrated with vehicle-assisted methods for fiber optic cable location and path mapping. Advantageously, the inventors' designed AI algorithms operating in the systems and methods of the present invention provide a simple solution for cable mapping in GIS systems, automatically mapping using landmark and manhole locations, and employing supervised learning algorithms.

[0007] As shown and described below, the present invention further discloses a vehicle assistance method in which vehicles are equipped with Global Positioning System (GPS) devices to travel along roads that follow the path of the fiber optic cable, and data pairing in which time is synchronized between the DFOS system and the vehicle GPS devices to automatically pair fiber length data from traffic trajectories with GPS coordinates in time series, providing further important location information.

[0008] In further contrast to the prior art, the system and method of the present invention uses field reference points that can advantageously use landmarks (buildings / roads / manholes, etc.) as reference points to facilitate self-calibration using GPS coordinates from landmarks (e.g., start central office / end central office of a route, etc.).

[0009] Finally, the deep neural network (DNN) of the present invention is trained end-to-end along the entire length of the DFOS sensor fiber, producing accurate results while simultaneously applying generalized solutions from trained paths to new paths. As those skilled in the art will understand and appreciate, this disclosure describes the combination of the DFOS system and AI / ML techniques as an integrated solution for automatically mapping optical fibers along the entire path of a fiber optic cable, a challenge that has heretofore been faced in the art. [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] 1 is a schematic flow diagram illustrating an exemplary prior art method for locating and mapping fiber optic cables.

[0012] [Figure 3] FIG. 1 is a schematic flow diagram illustrating an exemplary method for determining and mapping the location of fiber optic cables according to aspects of the present disclosure.

[0013] [Figure 4] FIG. 1 is a schematic diagram illustrating an exemplary system configuration for determining and mapping the location of fiber optic cables according to aspects of the present disclosure.

[0014] [Figure 5] FIG. 1 is a schematic diagram illustrating an example field operation of an AI-driven cable mapping system, including a fiber route map, sensing data received from a DFOS system, and GPS coordinates from a GPS device, according to an embodiment of the present disclosure.

[0015] [Figure 6(A)] 1A-1C are a series of diagrams illustrating operational data for an automated AI-driven CMS according to the present disclosure, showing sensing data (waterfall traces) received from a DFOS system including a survey vehicle and road traffic according to an embodiment of the present disclosure. [Figure 6(B)] 10A-10C are a series of diagrams illustrating operational data for an automated AI-driven CMS according to the present disclosure, showing GPS information and DFOS sensing points adjusted based on timestamps according to aspects of the present disclosure, with field reference points shown as dots on a map. [Figure 6(C)] 10A-10C are a series of diagrams illustrating operational data for an automated AI-driven CMS according to the present disclosure, including trajectory diagrams for coincident field reference points according to aspects of the present disclosure. [Figure 6(D)] 10A-10C are a series of diagrams illustrating operational data for an automated AI-driven CMS according to the present disclosure, showing trajectory diagrams when two field reference points coincide according to an embodiment 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 optical fiber 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 location 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 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 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. According to aspects of the present disclosure, 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 flow diagram illustrating an exemplary prior art method for locating and mapping fiber optic cables. With reference to this diagram, various drawbacks may become apparent.

[0030] In step 210, the DFOS system is connected from a central control station (CO) to the deployed fiber optic cables to be monitored. Such fiber optic cables become sensor cables associated with DFOS.

[0031] In step 220, for example, a field technician applies mechanical vibration to the manhole cover.

[0032] In step 230, the DFOS system receives a vibration signal from the field.

[0033] In step 240, the Al algorithm recognizes the vibration pattern and reports the location of the slack fiber along the fiber optic cable.

[0034] Finally, in step 250, the AI ​​algorithm is used to perform data pairing of the cable distance with the GPS coordinates of the field device / location generating the vibration.

[0035] As those skilled in the art will understand and appreciate, such operations can be particularly labor intensive and operationally expensive for service providers.

[0036] 3 is a schematic flow diagram illustrating an exemplary method for determining and mapping the location of a fiber optic cable according to an embodiment of the present disclosure, with reference to which the fiber optic locator and mapping operations of the present invention can be understood.

[0037] In step 310, a DFOS system, possibly located at a central control station, is connected to deployed fiber optic cables that serve as DFOS sensor fibers to be used in the field survey.

[0038] In step 320, a vehicle equipped with a GPS device is driven along a route to generate detectable field traffic patterns for the field survey.

[0039] In step 330, during DFOS operation, vibration signals are received from the field including ambient noise, normal road traffic, road construction, and traffic patterns created along the fiber cable route.

[0040] In step 340, traffic patterns are recognized by the AI ​​algorithm with synchronized timestamps and cable distances associated with GPS coordinates.

[0041] In step 350, landmarks (e.g., central stations, manholes, etc.) are used to correlate the cable distance data with the location data (GPS coordinates) to generate correlated location data.

[0042] In step 360, the location of the survey is determined, located and mapped on a GIS system.

[0043] 4 is a schematic diagram illustrating an exemplary system configuration for locating and mapping fiber optic cables according to an embodiment of the present disclosure. As illustratively shown in this figure, a sensing layer is "overlaid" on an existing deployed fiber optic network. A distributed fiber optic sensing system (DFOS) (101), which may be configured as distributed acoustic sensing (DAS) and / or distributed vibration sensing (DVS), is installed in a central office / control station (CO) (100) for remotely monitoring the entire fiber optic cable route.

[0044] The DFOS system is optically connected to optical sensing / sensor fibers deployed in the field, providing sensing capabilities. As can be easily understood, the optical sensing fiber can be dark fiber (no traffic) or operational telecommunications fiber owned / operated / used by a service provider to provide one or more telecommunications services. A vehicle (201) is utilized for the survey and is equipped with a GPS device (202) that is time-synchronized with the data pairing system (102). By matching the timestamps of the GPS device and the DFOS system, the geographic location of the target location can be paired with the distance of the optical sensor fiber from the waterfall data and GPS coordinates of the AI ​​platform (103).

[0045] 5 is a schematic diagram illustrating an example field operation of an AI-driven cable mapping system, including a fiber route map, sensing data received from a DFOS system, and GPS coordinates from a GPS device, according to an embodiment of the present disclosure. It should be noted that, in this diagram, the operation and requirements of an AI-driven automated CMS (Cable Mapping System) can be realized.

[0046] First, regarding route maps that may be provided by service providers / carriers, it does not matter if such maps are not up to date. The route maps simply guide the vehicle drivers on where to drive during the survey. Second, the vehicles are equipped with GPS and travel along the (fiber) route. During the travel, the GPS is synchronized with the DFOS system according to the timestamp. The corresponding fiber sensing data shown in the exemplary waterfall diagram includes the traffic trajectory of the survey vehicle.

[0047] GPS points (at least two) are matched with the waterfall data. The GPS coordinates are known coordinates relative to landmarks (302) and are collected from the vehicle's GPS device. The GPS coordinates include at least two known locations selected as field reference points. These field reference points are advantageously two central stations that define the two end points of the fiber optic sensor, i.e., the start and end points of the fiber optic sensor path, respectively.

[0048] Figures 6(A), 6(B), 6(C), and 6(D) are a series of diagrams illustrating operational data of an automated AI-driven CMS according to the present disclosure. Figure 6(A) illustrates sensing data (waterfall trace) received from a DFOS system including a survey vehicle and road traffic according to an embodiment of the present disclosure. Figure 6(B) illustrates GPS information and DFOS sensing points adjusted based on timestamps according to an embodiment of the present disclosure, with field reference points shown as dots on a map. Figure 6(C) is a trajectory diagram when field reference points coincide according to an embodiment of the present disclosure. Figure 6(D) is a trajectory diagram when two field reference points coincide according to an embodiment of the present disclosure.

[0049] From the operational data plots, it is noted that in Figure 6(A), the sensing data (waterfall trace) received from the DFOS system includes both survey vehicles and road traffic.

[0050] Figure 6(B) shows the GPS information and DFOS sensing points adjusted based on the timestamp. The surveyed field reference points are pinpointed on the plot with dots. The plot trajectory that matches 100 field reference points (green line) is determined to be the ground truth for this survey. Figure 3(C) shows the plot trajectory when the survey matches only one field reference point (the central station at the fiber start location). Figure 3(D) shows the plot trajectory when the survey matches only two field reference points, the central stations at the fiber start and end locations.

[0051] These results show that the accuracy of only one field control point is poor in this study, but the accuracy can be significantly improved by applying two field control points.

[0052] centre When only one field control point is used, the mapping error is 3.4%. However, when two or more field control points are applied, the mapping error can be reduced to less than 0.4%. Furthermore, the cable mapping error is smaller for buried cable sections than for aerial cable sections. From these results, the average mapping error can be expressed as follows:

number

[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. operating a distributed fiber optic sensing (DFOS) system configured to sense a path of interest; driving a vehicle including a global positioning system receiver such that a traffic pattern is generated; detecting, by the DFOS, a vibration signal from the target path; identifying a traffic pattern from the detected vibration signals and a location along the target route by GPS coordinates; and mapping the identified locations on a graphical information system (GIS).

2. The method of claim 1 , further comprising identifying traffic patterns from the detected vibration signals with an artificial intelligence (AI) algorithm.

3. 3. The method of claim 2, further comprising identifying a traffic pattern from the detected vibration signal by an AI algorithm with synchronized time stamps and identifying a DFOS optical sensor fiber cable distance associated with the GPS coordinate.

4. The method of claim 3 , further comprising correlating the determined cable distance with the GPS coordinates using landmarks along the route of interest, thereby generating correlated location data.

5. The method of claim 4 further comprising mapping the correlated location data onto the GIS.

6. The method of claim 5 , wherein the vibration signals include ambient noise, road traffic, road construction, and traffic patterns created along the target route.

7. The method of claim 6 , wherein the landmarks include buildings, manholes, man-made structures, and natural structures.

8. The method of claim 7 , wherein the Al algorithm is executed by a deep neural network trained end-to-end on the DFOS optical sensor fiber cable.

Images