Description:TECHNICAL FIELD
The present disclosure relates to the field of optical fibers and, in particular, relates to a method for detecting one or more defects in an optical fiber wound on a bobbin.
BACKGROUND
Optical fiber refers to the technology and the medium for the transmission of data as light pulses along an ultrapure strand of glass, which is a thin as a human hair. For many years, optical fibers have been extensively used in high-performance and long-distance data and networking. At the end of the optical fiber production process, the optical fibers of different lengths (like, 25 Km, 50 Km, 60 Km, etc) are wound on bobbins. These bobbins are then sent for quality clearance. Further, along with attenuation tests and other characteristic testing, physical verification is one of the most important tests done for all the bobbins. Any defective bobbins, if passed and sent forward for cable manufacturing can lead to defective product and big loss. Currently, physical verification is a complete manual process where a trained operator does the inspection of each of the bobbins by putting a specific light on the optical fiber and a trained operator looks into it to identify the defects in the optical fiber.
To reduce the need of human dependency and to improve the quality checking accuracy of the physical verification process number of techniques have been employed. A prior art reference “US9581521B2” discloses systems and methods for inspecting wound optical fiber to detect and characterize defects. The reference discloses a method to detect defects in optical fiber using a digital image processing. Another prior art reference “CN204964409U” discloses a utility model for a fully automatic optic fiber winding defect detecting system, including industry camera, light source, moving platform, platform mobility control ware and the computer of installing the industry camera lens, However, all the stated solutions are labour extensive and require continuous and careful manual monitoring to detect defects.
Therefore, there is a need for efficient method for detecting one or more faults in an optical fiber wound on a bobbin that overcomes one or more limitation associated with the prior art.
SUMMARY
In an aspect of the present disclosure, a method for detecting one or more defects in an optical fiber wound over a bobbin is disclosed. The method has steps such as maintaining a relative rotary motion between the bobbin and a primary imaging device of one or more imaging devices. The bobbin has a connecting drum along an axis of the bobbin and first and second side-flanges on both ends of the connecting drum such that the optical fiber is wound on the connecting drum between the first and second side-flanges. The optical fiber has a glass core, a glass cladding and at least one coating layer. The method further has a step of illuminating a predefined region of the bobbin with one or more light sources such that at least one light source of the one or more light sources is placed at a predefined distance from the bobbin. The at least one light source of the one or more light sources points towards the axis. The method further has a step of capturing a first plurality of images by way of the primary imaging device. The primary imaging device, the axis of the bobbin, and the one or more light sources are non-coplanar. The method further has a step of processing the first plurality of images using a machine learning technique. The method further has a step of detecting one or more defects based on the processed first plurality of images.
BRIEF DESCRIPTION OF DRAWINGS
Having thus described the disclosure in general terms, reference will now be made to the accompanying figures, where:
FIG. 1 illustrates a system for detection of one or more defects in an optical fiber wound over a bobbin.
FIG. 2A illustrates an apparatus for detection of the one or more defects in an optical fiber wound over a bobbin.
FIGs. 2B and 2C illustrate different views of the apparatus.
FIGs. 2D and 2E illustrate different views of the apparatus.
FIG. 3 is a block diagram that illustrates an information processing apparatus of FIG. 1.
FIG. 4 illustrates a block diagram of a method for detecting one or more defects in an optical fiber wound over a bobbin.
It should be noted that the accompanying figures are intended to present illustrations of exemplary aspects of the present disclosure. These figures are not intended to limit the scope of the present disclosure. It should also be noted that accompanying figures are not necessarily drawn to scale.
DEFINITIONS
The term “optical fiber” as used herein refers to a light guide medium that provides high-speed data transmission. The optical fiber has one or more glass core regions and one or more glass cladding regions. The light moving through the glass core regions of the optical fiber relies upon the principle of total internal reflection, where the glass core regions have a higher refractive index (n1) than the refractive index (n2) of the glass cladding regions of the optical fiber.
The term “core region” as used herein refers to an inner cylindrical structure present in the optical fiber which is configured to guide the light rays inside the optical fiber.
The term “cladding region” as used herein refers to one or more layered structure covering one or more core regions of an optical fiber from the outside, which is configured to possess a lower refractive index than the refractive index of the core to facilitate total internal reflection of light rays inside the optical fiber. Further, the cladding of the optical fiber may include an inner cladding layer coupled to the outer surface of the one or more core regions of the optical fiber and an outer cladding layer coupled to the inner cladding from the outside.
The term “defects on an optical fiber” as used herein refers to the variety of defects which can occur due to, but not limited to, manufacturing (process related), handling, tampering and/or defective material usage. The defects can be winding errors such as, but not limited to, improper and/or uneven winding, scratch on the fiber, fingerprint mark on fiber, fiber is broken, bubble in fiber, dent in the fiber, bubble in coating, lump, whitish marks, dust, and the like.
DETAILED DESCRIPTION
The detailed description of the appended drawings is intended as a description of the currently preferred aspects of the present disclosure, and is not intended to represent the only form in which the present disclosure may be practiced. It is to be understood that the same or equivalent functions may be accomplished by different aspects that are intended to be encompassed within the spirit and scope of the present disclosure.
Moreover, although the following description contains many specifics for the purposes of illustration, anyone skilled in the art will appreciate that many variations and/or alterations to said details are within the scope of the present technology. Similarly, although many of the features of the present technology are described in terms of each other, or in conjunction with each other, one skilled in the art will appreciate that many of these features can be provided independently of other features. Accordingly, this description of the present technology is set forth without any loss of generality to, and without imposing limitations upon, the present technology.
FIG. 1 illustrates a system 100 for detection of one or more defects in an optical fiber wound over a bobbin. The system 100 may be configured to automatically detect defects in an optical fiber wound over a bobbin using a machine learning technique. Specifically, the system 100 may be configured to learn and predict the defects on an optical fiber, associate a severity with the predicted defect, and may bypass one or more defects when the severity associated with that defect is very low or negligible. The system 100 may have an apparatus 102, a user device 104, and an information processing apparatus 106.
The apparatus 102, the user device 104, and the information processing apparatus 106 may be configured to communicate with each other and with other entities within the system 100 by way of a communication network 108 and/or through separate communication networks established therebetween.
The communication network 108 may include suitable logic, circuitry, and interfaces that may be configured to provide a plurality of network ports and a plurality of communication channels for transmission and reception of data related to operations of various entities in the system 100. Each network port may correspond to a virtual address (or a physical machine address) for transmission and reception of the communication data. For example, the virtual address may be an Internet Protocol Version 4 (IPV4) (or an IPV6 address) and the physical address may be a Media Access Control (MAC) address. The communication network 108 may be associated with an application layer for implementation of communication protocols based on one or more communication requests from the apparatus 102, the user device 104, and the information processing apparatus 106. The communication data may be transmitted and/or received, via the communication protocols. Examples of the communication protocols may include, but are not limited to, Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), Simple Mail Transfer Protocol (SMTP), Domain Network System (DNS) protocol, Common Management Interface Protocol (CMIP), Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), Long Term Evolution (LTE) communication protocols, or any combination thereof.
In sone aspects of the present disclosure, the communication data may be transmitted or received via at least one communication channel of a plurality of communication channels in the communication network 108. The communication channels may include, but are not limited to, a wireless channel, a wired channel, a combination of wireless and wired channel thereof. The wireless or wired channel may be associated with a data standard which may be defined by one of a Local Area Network (LAN), a Personal Area Network (PAN), a Wireless Local Area Network (WLAN), a Wireless Sensor Network (WSN), Wireless Area Network (WAN), Wireless Wide Area Network (WWAN), a Metropolitan Area Network (MAN), a Satellite Network, the Internet, a Fiber Optic Network, a Coaxial Cable Network, an Infrared (IR) network, a Radio Frequency (RF) network, and a combination thereof. Aspects of the present disclosure are intended to include or otherwise cover any type of communication channel, including known, related art, and/or later developed technologies.
The apparatus 102 may be configured to provide one or more images to the information processing apparatus 106 such that the information processing apparatus 106 processes the received one or more images by way of a machine learning technique to detect one or more defects of an optical fiber that is wound on a bobbin. The apparatus 102 is discussed in detail in FIGs. 2A-2D.
The user device 104 may be adapted to facilitate a user to input data, receive data, and/or transmit data within the system 100. In some aspects of the present disclosure, the user device 104 may be, but is not limited to, a desktop, a notebook, a laptop, a handheld computer, a touch sensitive device, a computing device, a smart phone, a smart watch, and the like. It will be apparent to a person of ordinary skill in the art that the user device 104 may be any device/apparatus that is capable of manipulation by the user. Although FIG. 1 illustrates that the system 100 includes a single user device (i.e., the user device 104), it will be apparent to a person skilled in the art that the scope of the present disclosure is not limited to it. In various other aspects, the system 100 may include multiple user devices without deviating from the scope of the present disclosure. In such a scenario, each user device is configured to perform one or more operations in a manner similar to the operations of the user device 104 as described herein.
The user device 104 may have an interface 110, a processing unit 112, and a memory 114. The interface 110 may have an input interface for receiving inputs from the user. Examples of the input interface may be, but are not limited to, a touch interface, a mouse, a keyboard, a motion recognition unit, a gesture recognition unit, a voice recognition unit, or the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the input interface including known, related art, and/or later developed technologies. The interface 110 may further have an output interface for displaying (or presenting) an output to the user. Examples of the output interface may be, but are not limited to, a display device, a printer, a projection device, and/or a speaker, and the like.
The processing unit 112 may have suitable logic, instructions, circuitry, and/or interfaces for executing various operations, such as one or more operations associated with the user device 104. In some aspects of the present disclosure, the processing unit 112 may be configured to control one or more operations executed by the user device 104 in response to an input received at the user device 104 from the user. Examples of the processing unit 112 may be, but are not limited to, an Application-Specific Integrated Circuit (ASIC) processor, a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Field-Programmable Gate Array (FPGA), a Programmable Logic Control unit (PLC), and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the processing unit 112 including known, related art, and/or later developed technologies.
The memory 114 may be configured to store logic, instructions, circuitry, interfaces, and/or codes of the processing unit 112, data associated with the user device 104, and data associated with the system 100. Examples of the memory 114 may include, but are not limited to, a Read Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (FM), a Removable Storage Drive (RSD), a Hard Disk Drive (HDD), a Solid-State Memory (SSM), a Magnetic Storage Drive (MSD), a Programmable Read Only Memory (PROM), an Erasable PROM (EPROM), and/or an Electrically EPROM (EEPROM). Aspects of the present disclosure are intended to include or otherwise cover any type of the memory 114 including known, related art, and/or later developed technologies.
In some aspects of the present disclosure, the user device 104 may further have one or more computer executable applications configured to be executed by the processing unit 112. The one or more computer executable applications may have suitable logic, instructions, and/or codes for executing various operations associated with the system 100. The one or more computer executable applications may be stored in the memory 114. Examples of the one or more computer executable applications may include, but are not limited to, an audio application, a video application, a social media application, a navigation application, and the like. Preferably, the one or more computer executable applications may include a defect detection application 116. Specifically, one or more operations associated with the defect detection application 116 may be controlled by the information processing apparatus 106.
The user device 104 may further have a communication interface 118. The communication interface 118 may be configured to enable the user device 104 to communicate with the information processing apparatus 106 and other components of the system 100 over the communication network 108. Examples of the communication interface 118 may be, but are not limited to, a modem, a network interface such as an Ethernet Card, a communication port, and/or a Personal Computer Memory Card International Association (PCMCIA) slot and card, an antenna, a Radio Frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a Coder Decoder (CODEC) Chipset, a Subscriber Identity Module (SIM) card, and a local buffer circuit. It will be apparent to a person of ordinary skill in the art that the communication interface 118 may have any device and/or apparatus capable of providing wireless and/or wired communications between the user device 104 and the information processing apparatus 106.
The information processing apparatus 106 may be a network of computers, a framework, and/or a combination thereof, that may provide a generalized approach to create a server implementation. In some aspects of the present disclosure, the information processing apparatus 106 may be a server. Examples of the information processing apparatus 106 may be, but are not limited to, personal computers, laptops, mini-computers, mainframe computers, any non-transient and tangible machine that can execute a machine-readable code, cloud-based servers, distributed server networks, or a network of computer systems. The information processing apparatus 106 may be realized through various web-based technologies such as, but not limited to, a Java web-framework, a .NET framework, a personal home page (PHP) framework, or any other web-application framework. The information processing apparatus 106 may have one or more processing circuitries of which processing circuitry 120 is shown and a non-transitory computer-readable storage medium 122 (hereinafter interchangeably referred to and designated as “the database 122”).
The processing circuitry 120 may be configured to execute various operations associated with the system 100. The processing circuitry 120 may be configured to host and enable the defect detection application 116 running on (and/or installed on) the user devices 104 to execute the one or more operations associated with the system 100 by communicating one or more commands and/or instructions over the communication network 108. Examples of the processing circuitry 120 may be, but not limited to, an ASIC processor, a RISC processor, a CISC processor, a FPGA, and the like. Embodiments of the present disclosure are intended to include and/or otherwise cover any type of the processing circuitry 120 including known, related art, and/or later developed technologies.
The database 122 may be configured to store the logic, instructions, circuitry, interfaces, and/or codes of the processing circuitry 120 for executing various operations. The database 122 may be further configured to store therein, data associated with users registered with the system 100, and the like. It will be apparent to a person having ordinary skill in the art that the database 122 may be configured to store various type of data associated with the system 100, without deviating from the scope of the present disclosure. Examples of the database 122 may be, but are not limited to, a Relational database, a NoSQL database, a Cloud database, an Object-oriented database, and the like. Further, the database 122 may have one or more associated memories that may be, but is not limited to, a ROM, a RAM, a flash memory, a removable storage drive, a HDD, a solid-state memory, a magnetic storage drive, a PROM, an EPROM, and/or an EEPROM. Aspects of the present disclosure are intended to include or otherwise cover any type of the database 122 including known, related art, and/or later developed technologies. In some aspects of the present disclosure, a set of centralized and/or distributed network of peripheral memory devices may be interfaced with the information processing apparatus 106, as an example, on a cloud server.
FIG. 2A illustrates the apparatus 102 for detection of the one or more defects in an optical fiber 200 wound over a bobbin 202. The apparatus 200 may have the bobbin 202, one or more imaging devices 204, one or more light sources 206 (as shown later in FIG. 2B). Specifically, the one or more imaging devices 204 may be coupled to the information processing apparatus 106 by way of one or more communication channels that may include, but are not limited to, a wireless channel, a wired channel, a combination of wireless and wired channel thereof. Aspects of the present disclosure are intended to include or otherwise cover any type of communication channel, including known, related art, and/or later developed technologies.
The one or more imaging devices 204 may have a primary imaging device 204a and one or more secondary imaging devices 204b of which first and second secondary imaging devices 204ba and 204bb are shown. As illustrated, the primary imaging device 204a may be disposed above the bobbin 202. In some aspects of the present disclosure, the primary imaging device 204a may be placed perpendicular to an axis (X) of the bobbin 202. In other words, the primary imaging device 204a is placed parallel to the one or more light sources 206. In some aspects of the present disclosure, the primary imaging device 204a may be disposed at a predefined acute angle with respect to a plane (YZ) perpendicular to the axis (X) of the bobbin 202. When the primary imaging device 204a is disposed above one of first and second side flanges 202a and 202b, the primary imaging device 204a may be disposed at the predefined acute angle with respect to the plane (YZ) which is perpendicular to the axis (X) of the bobbin 202. In some aspects of the present disclosure, the predefined acute angle may be in a range of 15 degrees to 45 degrees. Preferably, the predefined acute angle may be 30 degrees. In some aspects of the present disclosure, the primary imaging device 204a may be disposed at a first distance (D1) from the axis (X) of the bobbin 202. In some aspects of the present disclosure, the first distance (D1) may be in a range of 20 centimetres (cm) to 40 cm. The primary imaging device 204a may be configured to capture a first plurality of images at a predefined interval such that at least 20 images are captured per second. The first plurality of images are captured in a significant quantity to avoid negligence of any uncaptured defects in the optical fiber 200. The first plurality of images captured by way of the primary imaging device 204a may be facilitate in identification of one or more defects in the optical fiber 200 such as, but not limited to, a scratch, a bubble, a dent, a fingerprint, and the like. If the predefined acute angle is out of the above disclosed ranges which is 15 degrees to 45 degrees, this leads to increase in the light reflection from the optical fiber 200 that creates distortions in the captured first plurality of images.
The one or more secondary imaging devices 204b may be disposed on both sides of the bobbin 202 along the axis (X) of the bobbin 202. Specifically, the first and second secondary imaging devices 204ba and 204bb may be disposed near first and second side flanges 202a and 202b, respectively, of the bobbin 202. In some aspects of the present disclosure, the one or more secondary imaging devices 204b may be disposed along the axis (X) of the bobbin 202 at a second distance (D2) from the first and second side flanges 202a and 202b. In some aspects of the present disclosure, the second distance (D2) may be in a range of 10 cm to 20 cm. In some aspects of the present disclosure, the one or more secondary imaging devices 204b (i.e., the first and second secondary imaging devices 204ba and 204bb) may be configured to capture a second plurality of images at a predefined interval such that at least 15 images are captured per second. The second plurality of images are captured in a significant quantity to avoid negligence of any uncaptured defects in the optical fiber 200 and bobbin 202. The second plurality of images captured by way of the one or more secondary imaging devices 204b (i.e., the first and second secondary imaging devices 204ba and 204bb) may facilitate in identification of one or more defects in the bobbin 202 such as, but not limited to a damage in the bobbin 202, and the like. Further, the second plurality of images captured by way of the one or more secondary imaging devices 204b (i.e., the first and second secondary imaging devices 204ba and 204bb) may facilitate in scanning a barcode (not shown) or any known identification tag that may be disposed on a side flange of the first and second side flanges 202a and 202b of the bobbin 202 to identify information associated with the bobbin 202. In some aspects of the present disclosure, the information may be, but not limited to, a name, a number, details of an optical fiber wound over the bobbin 202. Specifically, the information may facilitate the system 100 to maintain a record of the bobbin 202 with a defect report that has one or more detected defects, a type of the detected defects, a severity of the detected defects, and one or more suggested remedy and/or actions corresponding to the detected defects. In some aspects of the present disclosure, the second plurality of images captured by way of the one or more secondary imaging devices 204b (i.e., the first and second secondary imaging devices 204ba and 204bb) may facilitate in detection of presence or absence of bottom end length of the optical fiber 200. In some aspects of the present disclosure the bottom end length of the optical fiber 200 may be wound on a secondary drum 208 (as shown in Fig. 2B) outside of the side flange of the first and second side flanges 202a and 202b of the bobbin 202. The presence of the bottom end length of the optical fiber 202is highly important and a mandatory requirement for bidirectional testing of the optical fiber 200 wound over the bobbin 202. Although FIG. 2A illustrates that the one or more secondary imaging devices 204b has two secondary imaging devices (i.e., the first and second secondary imaging devices 204ba and 204bb), it will be apparent to a person skilled in the art that the scope of the present disclosure is not limited to it. In various other aspects, the one or more secondary imaging devices 204b may have any number of secondary imaging devices, without deviating from the scope of the present disclosure. In such a scenario, each secondary imaging device is configured to perform one or more operations in a manner similar to the operations of the first and second secondary imaging devices 204ba and 204bb as described herein. In some aspects of the present disclosure, the plurality of imaging devices 204 may be, but not limited to, a compact camera, a mirrorless camera, a Digital Single-Lens Reflex Camera (DSLR) camera, and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the plurality of imaging devices 204 capable of capturing images, known to a person having ordinary skill in the art, without deviating from the scope of the present disclosure.
The bobbin 202 may have the first and second side flanges 202a and 202b. Further, the bobbin 202 may have a connecting drum 202c that may be disposed between the first and second side flanges 202a and 202b such that the optical fiber 200 is wound and/or wrapped onto the connecting drum 202c. In some aspects of the present disclosure, the bobbin 202 may be configured to rotate along the axis (X) of the bobbin 202 at a predefined speed. Specifically, the bobbin 202 may be rotated along the axis (X) of the bobbin 202 by way of a mechanism (not shown). In some aspects of the present disclosure, the mechanism may have one or more rollers (not shown) and a motor (not shown) that may enable the one or more rollers to rotate thus enabling a rotation of the bobbin 202. The mechanism may be configured to maintain a relative rotary motion between the bobbin 202 and the primary imaging device 204a of the one or more imaging devices 204. In some aspects of the present disclosure, the predefined speed may be in a range of 15 Rotations Per Minute (RPM) to 30 RPM.
FIGs. 2B and 2C illustrate different views of the apparatus 102 for detection of the one or more defects in the optical fiber 200 wound over the bobbin 202. The apparatus 102 may have the bobbin 202, the plurality of imaging devices 204, and the one or more light sources 206. As illustrated, the one or more light sources 206 has at least one light source 206 (hereinafter referred to and designated as “the light source 206”) that may be disposed above the bobbin 202 in such a way that the light source 206 points towards the axis (X) of the bobbin 202. In some aspects of the present disclosure, the one or more light sources 206 may be disposed a predefined distance (D) from the axis (X) of the bobbin 202. The light sources 206 may be adapted to illuminate a predefined region of the bobbin 202 on which the optical fiber 200 is wound such that the plurality of imaging devices 204 can capture clear images (i.e., the first and second plurality of images). In some aspects of the present disclosure, the predefined region may have a width of 30 centimetres (cm) to 60 cm and a length of 20 cm to 40 cm. In some aspects of the present disclosure, the one or more light sources 206 may be a Light Emitting Diode (LED) bulb. In some aspects of the present disclosure, the LED bulb may be one of not limited to a cylindrical rod shape, or a cuboid shape. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the one or more light sources 206, without deviating from the scope of the present disclosure. In some aspects of the present disclosure, the optical fiber 200 may be a colourless optical fiber. In some other aspects of the present disclosure, the optical fiber 200 may be a coloured optical fiber. The optical fiber 200 may have one or more glass cores, one or more glass claddings and at least one coating layer or at least one colored coating layer. As illustrated in FIGs. 2B and 2C, the one or more light sources 206 (e.g., the light source 206) may be disposed parallel to the axis (X) of the bobbin 202. Specifically, when the optical fiber 200 is a colourless optical fiber, the one or more light sources 206 (e.g., the light source 206) may be disposed parallel to the axis (X) of the bobbin 202 for detecting defects on the colourless optical fiber. Specifically, the the light source 206 disposed parallel to the axis (X) of the bobbin 202 may create a light reflection aligning to a winding of the optical fiber 200 across the bobbin 202. As illustrated, the primary imaging device 204a (as shown in FIG. 2A), the axis (X) of the bobbin 202, and the one or more light sources 206 are non-coplanar. In other words, the primary imaging device 204a, the axis (X) of the bobbin 202, and the one or more light sources 206 may not be occupying a linear plane.
FIGs. 2D and 2E illustrate different views of the apparatus 102 for detection of the one or more defects in the optical fiber 200 wound over the bobbin 202. As illustrated in FIGs. 2D and 2E, the one or more light sources 206 (e.g., the light source 206) may be disposed perpendicular to the axis (X) of the bobbin 202. Specifically, when the optical fiber 200 is a coloured optical fiber, the one or more light sources 206 (e.g., the light source 206) may be disposed perpendicular to the axis (X) of the bobbin 202 for detecting defects on the coloured optical fiber. Specifically, the one or more light sources 206 (e.g., the light source 206) disposed perpendicular to the axis (X) of the bobbin 202 may facilitate to identify color variations in the optical fiber 200 when the optical fiber 200 is a coloured optical fiber. In some aspects of the present disclosure, the light source 206 may be actuated by an automatic mechanism to rotate by 90 degree angle, when the apparatus is performing defect detection on a coloured optical fiber wound over the bobbin 202.
FIG. 3 is a block diagram that illustrates the information processing apparatus 106 of FIG. 1. As discussed, the information processing apparatus 106 has the processing circuitry 120 and the database 122. Further, the information processing apparatus 106 may include a network interface 300 and an input/output (I/O) interface 302. The processing circuitry 120, the database 122, the network interface 300, and the I/O interface 302 may communicate with each other by way of a first communication bus 304. In some aspects of the present disclosure, the processing circuitry 120 may have a registration engine 306, a data collection engine 308, a data processing engine 310, and a display engine 312. The registration engine 306, the data collection engine 308, the data processing engine 310, and the display engine 312 may communicate with each other by way of a second communication bus 314. It will be apparent to a person having ordinary skill in the art that the information processing apparatus 106 is for illustrative purposes and not limited to any specific combination of hardware circuitry and/or software.
The network interface 300 may have suitable logic, circuitry, and interfaces that may be configured to establish and enable a communication between the information processing apparatus 106 and different components of the system 100 (e.g., the user device 104), via the communication network 108. The network interface 300 may be implemented by use of various known technologies to support wired and/or wireless communication of the information processing apparatus 106 with the communication network 108. The network interface 300 may have, but is not limited to, an antenna, a RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC chipset, a SIM card, a local buffer circuit, and the like.
The I/O interface 302 may have suitable logic, circuitry, interfaces, and/or code that may be configured to receive inputs and transmit server outputs (i.e., one or more outputs generated by the information processing apparatus 106) via a plurality of data ports in the information processing apparatus 106. The I/O interface 302 may have various input and output data ports for different I/O devices. Examples of such I/O devices may be, but are not limited to, a touch screen, a keyboard, a mouse, a joystick, a projector audio output, a microphone, an image-capture device, a liquid crystal display (LCD) screen and/or a speaker, and the like.
The processing circuitry 120 may be configured to perform one or more operations associated with the system 100 by way of the registration engine 306, the data collection engine 308, the data processing engine 310, and the display engine 312. In some aspects of the present disclosure, the registration engine 306 may be configured to enable a user to register into the system 100 by providing registration data through a registration menu (not shown) of the defect detection application 116 displayed through the user devices 104. The registration data may be, but is not limited to, a name, a demographic, a contact number, an address, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the registration data associated with the user, without deviating from the scope of the present disclosure. In some aspects of the present disclosure, the registration engine 306 may be further configured to enable the users to create a login identifier and a password that may enable the users to subsequently login into the system 100. The registration engine 306 may be configured to store the registration data associated with the users, the login and the password associated with the users in the database 122.
The data collection engine 308 may be configured to receive the plurality of images (i.e., the first and second plurality of images) from the plurality of imaging devices 204 (i.e., the primary imaging device 204a and the first and second secondary imaging devices 204ba and 204bb). Further, the data collection engine 310 may be configured to store the plurality of images (i.e., the first and second plurality of images) in the database 122.
The data processing engine 310 may be configured to train a machine learning model by way of the captured first and second plurality of images, feedback provided by an operator for each defect, and a new severity assigned for each defect by an operator. For example, the display engine 314 may be configured to display a defect report based on the detected one or more defects in the optical fiber 200 by way of the user device 104. In such scenario, the display engine 314 may enable an operator to provide feedback for each defect of the one or more defects of the defect report. Further, the display engine 314 may be configured to enable the operator to assign a new severity for each defect by way of the user device 104 associated with the operator. Once the operator provides the feedback and assigns new severity to each defect, data having the feedback and the assigned new severity to each defect may be provided to the data processing engine 310 such that the data processing engine 310 trains the machine learning model based on the received data. The machine learning model may be trained by pre-processing of the captured plurality of images, employing a plethora of tailored methods, each suited to the unique characteristics of the plurality of images. The pre-processing encompasses diverse image processing tasks, including not limited to noise reduction but also tasks like edge detection, histogram equalization, and contrast enhancement, all orchestrated through the sophisticated architectures of deep neural networks. The pre-processing of the captured plurality of images is a multi-faceted endeavour, encompassing deterministic operations not limited to resizing, and extending to the augmentation of training data through randomized operations, such as random cropping. These operations ensure that the machine learning model, which may include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), Long Short-Term Memory networks (LSTMs) etc. are exposed to a rich and diverse dataset, enhancing their adaptability and robustness for defect identification in the optical fiber 200. The machine learning model may determine heterogeneity in defect types by employing a multitude of models and techniques, encompassing, Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), Decision Trees, Random Forests, Multilayer Perceptrons (MLPs) etc.. This diverse ensemble ensures that the machine learning model may effectively identify a wide range of one or more categories of the defects. The machine learning model us trained using a diverse array of computational resources, including Graphics Processing Units (GPUs), Central Processing Units (CPUs), high-performance computing clusters, and the scalable infrastructure of cloud-based platforms. In some aspects of the present disclosure, the data processing engine 310 trains the machine learning model to learn a change in behavior of the one or more defects. For example, the data processing engine 310 trains the machine learning model based on the received data such that a defect such as scratch and/or a bubble with very negligible amount which will not affect the performance of the optical fiber 200 can be passed and should not be considered as a defect. In other words, when the trained machine learning model consequently encounters such defect in the machine learning model can give a very negligible defect a test pass as an outcome. The data processing engine 310 may be further configured to process the first plurality of images using a machine learning technique (by utilizing the machine learning model) to detect one or more defects. Specifically, the data processing engine 310 may be configured to categorize the one or more defects into one or more categories. In some aspects of the present disclosure, the one or more categories may be, but not limited to, a process defect, a winding defect, and other defects. Each defect of the one or more categories may have a predefined category threshold. Specifically, the data processing engine 310 may be configured to compare each of the one or more defects with the predefined category threshold to quantify severity of the one or more defects. In other words, to determine an associated severity of a defect, the data processing engine 310 may be configured to compare each of the one or more defects with the predefined category threshold. The predefined category threshold may be based on the amount of impact of the one or more defects during the practical application of the optical fiber during cabling and deployment of the cabled optical fiber. In some aspects of the present disclosure, the severity may be, but not limited to, a high severity, a medium severity, and a low severity. For example, when the category assigned to a defect of the one or more defects is “a process defect”, the severity associated with that defect may be “a high severity”. Similarly, when the category assigned to a defect of the one or more defects is “a winding defect”, the severity associated with that defect may be “a medium severity”. Similarly, when the category assigned to a defect of the one or more defects is “other defects”, the severity associated with that defect may be “a low severity”.
Further, the data processing engine 310 may be configured to assign one or more sub-categories to each of the one or more defects based on the severity associated with each defect. In some aspects of the present disclosure, the one or more sub-categories may be, a scratch, a bubble, a dent, an uneven winding, a cross winding, a bobbin defect, a negligible amount of scratch and/or bubble. Specifically, when the category assigned to a defect of the one or more defects is “a process defect” and the sub-category is assigned from one of, a scratch, a bubble, a dent, the data processing engine 310 may be configured to assign a severity associated with that defect as “a high severity”. Similarly, when the category assigned to a defect of the one or more defects is “a winding defect” and the sub-category is assigned from one of, an uneven winding, a cross winding, the data processing engine 310 may be configured to assign a severity associated with that defect as “a medium severity”. Similarly, when the category assigned to a defect of the one or more defects is “other defects” and the sub-category selected from one of, a bobbin defect, a negligible amount of scratch and/or bubble, the data processing engine 310 may be configured to assign a severity associated with that defect as “a low severity”. Similarly, when the category assigned to one or more defects is “bobbin defect” and the sub-category assigned to the defect is one of bobbin damage defect and/or absence of bottom end of the optical fiber 200, these defects may be assigned one of the high, medium or low severity based on the impact of the defects.
In some aspects of the present disclosure, the data processing engine 310 may be further configured to predict using the machine learning technique (by utilizing the machine learning model) and based on the learning of the new severity, a performance impact of the optical fiber 200. The data processing engine 310 may be further configured to generate a defect test outcome. Specifically, by utilizing the machine learning technique (by utilizing the machine learning model), the data processing engine 310 may be configured to identify defect test outcome. The defect test outcome may be one of, pass and fail. Thus, the data processing engine 310 may be further configured to generate the defect test outcome that specifies whether a defect of the one or more defects has the defect test outcome of pass or fail. Further, the data processing engine 310 may be configured to generate the defect report, The defect report may have, but not limited to, the one or more detected defects, a category associated with each defect of the one or more defects, a severity associated with each defect of the one or more defects, a sub-category associated with each defect of the one or more defects, and one or more suggested remedies and/or actions corresponding to each defect of the one or more defects.
The display engine 312 may be configured to generate a display signal that may be transmitted to the user device 104 over the communication network 108. The display signal may have the defect report. Specifically, the display signal may enable the user device 104 to display the defect report by way of the interface 110 of the user device 104.
FIG. 4 illustrates a block diagram of a method 400 for detecting one or more defects in the optical fiber 200 wound over the bobbin 202.
At step 402, an operator may open a cover (not shown) of the apparatus 102 and put the bobbin 202 on the rollers and close the cover.
At step 404, the operator may press a start button of the apparatus 102 such that a motor of the apparatus 102 is activated to rotate the roller for 1 Second. In some aspects of the present disclosure, the bobbin 202, by way of the rollers, may be configured to rotate 360 Degrees in 1 second. Specifically, the motor may maintain a relative rotary motion between the bobbin 202 (as shown in FIG. 2A) and the primary imaging device 204a (as shown in FIG. 2A). The bobbin 202 has the connecting drum 202c along the axis (X) of the bobbin 202 and the first and second side-flanges 202a and 202b (as shown in FIG. 2A) on both ends of the connecting drum 202c (as shown in FIG. 2A) such that the optical fiber 200 is wound on the connecting drum 202c. The optical fiber 200 may have a glass core, a glass cladding and at least one coating layer.
At step 406, the plurality of imaging devices 204 may initiate capturing one or more images of the bobbin 202. Specifically, the primary imaging device 204a of the plurality of imaging devices 204 may be configured to capture the first plurality of images of the optical fiber 200 would over the bobbin 202 to identify the one or more defects. Further, the one more secondary imaging device 204b (i.e., the first and second secondary imaging device 204ba and 204bb) of the plurality of imaging devices 204 may be configured to capture the second plurality of images of a barcode and/or a label of the bobbin 202 to record the information associated with the bobbin 202 to identify the one or more defects. Furthermore, the second plurality of images may be used to check for bobbin defects, damaged portion on the bobbin 202, a certain portion of the optical fiber 200 at a starting end is wound over the flanges 202a and 202b and/or kept in the side of the connecting drum 202c. Prior to capturing the first and second plurality of images, a predefined region of the bobbin 202 may be illuminated with one or more light sources 206 (as shown in FIGs. 2B-2E) such that at least one light source of the one or more light sources 206 is placed at the predefined distance (D) from the bobbin 202. Specifically, the at least one light source of the one or more light sources 206 points towards the axis (X). The primary imaging device 204a, the axis (X) of the bobbin 202, and the one or more light sources 206 may be non-coplanar.
At step 408, the first and second plurality of images may be transmitted to the processing circuitry 120 of the information processing apparatus 106 for processing by way of a machine learning technique.
At step 410, the processing circuitry 120 may process the first and second plurality of images using the machine learning technique to identify the one or more defects in (i) the optical fiber 200 wound over the bobbin 202 and (ii) the bobbin 202.
At step 412, the processing circuitry 120 may categorize the one or more detected defects and generate the defect report. The defect report may be stored in the database 122.
At step 414, the defect report may be displayed on user device 104 by way of the defect detection application 116. In some aspects of the present disclosure, the processing circuitry 120 may be configured to notify the operator by way of an email communication such that the email communication has the defect report. In some aspects of the present disclosure, the defect report may include one or more tags associated with the bobbin 202. The one or more tags may be perfectly failed, perfectly passed and/or doubtful. These tags may be associated for entire bobbin 202 or for a particular type of defect present in the optical fiber 200. These tags are helpful for an operator to provide feedback and examine the final quality approval of the bobbin 202.
At step 416, the operator may acknowledge each defect of the one or more defects via the defect report and generate feedback such that the feedback provides information about a status of each defect as one of, correct and in-correct. Specifically, the feedback may be used by the processing circuitry 120 to train the machine learning model.
At step 418, the processing circuitry 120 may be configured to periodically generate a performance report of the system 100.
Thus, the system 100 of the present disclosure provide the apparatus 102 with unique placement of the one or more imaging devices 204 to detect one or more defects in the optical fiber 200, winding defects as well as defects on the bobbin 202. Further, the apparatus 102 has a unique placement of the one or more light sources 206 that can detect defects in coloured as well as colourless optical fibers. Furthermore, the system 100 of the present disclosure facilitates in reduction of human dependency and errors, improves quality check accuracy, increase a speed of defect detection of defect in the optical fiber 200 and the bobbin 202, creating a digital log of the one or more defects to further train machine learning model by way of the processing circuitry 120.
The foregoing descriptions of specific aspects of the present technology have been presented for the purpose of illustration and description. They are not intended to be exhaustive or to limit the present technology to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. The aspects were chosen and described in order to best explain the principles of the present technology and its practical application, to thereby enable others skilled in the art to best utilize the present technology and various aspects with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstance may suggest or render expedient, but such are intended to cover the application or implementation without departing from the spirit or scope of the claims of the present technology.
While several possible aspects of the invention have been described above and illustrated in some cases, it should be interpreted and understood as to have been presented only by way of illustration and example, but not by limitation. Thus, the breadth and scope of a preferred aspect should not be limited by any of the above-described exemplary aspects. , Claims:I/We Claim(s):
1. A method (400) for detecting one or more defects in an optical fiber (200) wound over a bobbin (202), the method (400) comprising:
maintaining a relative rotary motion between the bobbin (202) and a primary imaging device (204a) of one or more imaging devices (204), where the bobbin (202) has a connecting drum (202c) along an axis (X) of the bobbin (202) and first and second side-flanges (202a, 202b) on both ends of the connecting drum (202c), such that the optical fiber (200) is wound on the connecting drum (202c) between the first and second side-flanges (202a, 202b), where the optical fiber (200) has a glass core, a glass cladding and at least one coating layer;
illuminating a predefined region of the bobbin (202) with one or more light sources (206) such that at least one light source of the one or more light sources (206) is placed at a predefined distance (D) from the bobbin (202), where the at least one light source of the one or more light sources (206) points towards the axis (X);
capturing a first plurality of images by way of the primary imaging device (204a), where the primary imaging device (204a), the axis (X) of the bobbin (202), and the one or more light sources (206) are non-coplanar;
processing the first plurality of images using a machine learning technique; and
detecting one or more defects based on the processed first plurality of images.

2. The method (400) of claim 1, where, for detecting the one or more defects, the method (400) further comprising:
categorizing the one or more defects into one or more categories, where each of one or more categories has a predefined category threshold;
comparing each of the one or more defects with the predefined category threshold to determine severity of the one or more defects; and
assigning one or more sub-categories to each of the one or more defects based on the severity.

3. The method (400) of claim 1, where for capturing the first plurality of images by way of the primary imaging device (204a), the primary imaging device (204a) is placed at a predefined acute angle with respect to a plane (YZ) perpendicular to the axis (X) of the bobbin (202).

4. The method (400) of claim 1, where the at least one light source of the one or more light sources (206) is a Light Emitting Diode (LED) tube rod.

5. The method (400) of claim 1, where the primary imaging device (204a) is disposed at a first distance (D1) from the axis (X) of the bobbin (202), where the first distance (D1) is in a range of 20 centimetres (cm) to 40 cm.

6. The method (400) of claim 1, further comprising illuminating a predefined region, where the predefined region has a width between30 cm to 60 cm and a length between 20 cm to 40 cm.

7. The method (400) of claim 1, further comprising capturing, a second plurality of images by way of one more secondary imaging devices (204b), where the one more secondary imaging devices (204b) are disposed along the axis (X) at a second distance (D2) from the first and second side flanges (202a, 202b) of the bobbin (202), where the second distance (D2) is in a range of 10 cm to 20 cm.

8. The method (400) of claim 1, where the bobbin (202) rotates along the axis (X) of the bobbin (202) at a predefined speed that is in a range of 15 Rotations Per Minute (RPM) to 30 RPM.

9. The method (400) of claim 1, where, when the optical fiber (200) is a colourless optical fiber, the at least one light source of the one or more light sources (206) is disposed parallel to the axis (X) for detecting defects on the colourless optical fiber.

10. The method (400) of claim 1, where, when the optical fiber (200) is a coloured optical fiber, the at least one light source of the one or more light sources (206) is disposed perpendicular to the axis (X) for detecting defects on the coloured optical fiber.

11. The method (400) of claim 1, further comprising capturing the first and second plurality of images at a predefined interval such that at least 15 images are captured per second.

12. The method (400) of claim 1, of claim 1, further comprising training, a machine learning model by using:
the captured first and second plurality of images;
a feedback provided by an operator for each defects of the one or more defects; and
a severity assigned for each defect of the one or more defects by the operator.

13. The method (400) of claim 12, further comprising predicting, based on the learning of the severity, a performance impact of the optical fiber (200) prior to generating a defect test outcome.

14. The method (400) of claim 12, where the machine learning model is trained using one or more images captured from the one or more imaging devices (204) to learn a change in behavior of the one or more defects.