WO2021210546A1 - 光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法 - Google Patents
光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法 Download PDFInfo
- Publication number
- WO2021210546A1 WO2021210546A1 PCT/JP2021/015210 JP2021015210W WO2021210546A1 WO 2021210546 A1 WO2021210546 A1 WO 2021210546A1 JP 2021015210 W JP2021015210 W JP 2021015210W WO 2021210546 A1 WO2021210546 A1 WO 2021210546A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fusion
- optical fibers
- optical fiber
- pair
- imaging
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B6/00—Light guides; Structural details of arrangements comprising light guides and other optical elements, e.g. couplings
- G02B6/24—Coupling light guides
- G02B6/255—Splicing of light guides, e.g. by fusion or bonding
- G02B6/2553—Splicing machines, e.g. optical fibre fusion splicer
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B6/00—Light guides; Structural details of arrangements comprising light guides and other optical elements, e.g. couplings
- G02B6/24—Coupling light guides
- G02B6/255—Splicing of light guides, e.g. by fusion or bonding
- G02B6/2551—Splicing of light guides, e.g. by fusion or bonding using thermal methods, e.g. fusion welding by arc discharge, laser beam, plasma torch
Definitions
- the present disclosure relates to a fusion splicing system for an optical fiber, a fusion splicer, a model making device, and a method for fusion splicing an optical fiber.
- Patent Document 1 and Patent Document 2 disclose a fusion splicing system, a fusion splicer, and an optical fiber type discrimination method.
- the fusion splicing system of the present disclosure includes a model creation device and a plurality of fusion splicing machines.
- the model creation device performs machine learning using sample data showing the correspondence between the feature amount obtained from the imaged data of the optical fiber and the type of the optical fiber, and attempts to connect the type of the optical fiber to be connected.
- Each of the plurality of fusion splicers has an imaging unit, a discriminating unit, and a connecting unit.
- the imaging unit captures a pair of optical fibers to generate imaging data.
- the discriminating unit inputs the feature amount obtained from the imaging data provided by the imaging unit into the discriminating model, and discriminates the types of each pair of optical fibers.
- the connection unit fuses and connects the pair of optical fibers to each other under the connection conditions according to the combination of the types of the pair of optical fibers.
- the model creation device classifies a plurality of fusion splicers into two or more groups presumed to have similar tendencies of imaging data, collects sample data for each group, and creates a discrimination model.
- the discriminating unit of each fusion splicer discriminates the type of each pair of optical fibers by using the discrimination model corresponding to the group to which each fusion splicer belongs.
- the fusion splicer of the present disclosure includes an imaging unit, a discriminating unit, and a connecting unit.
- the imaging unit captures a pair of optical fibers to generate imaging data.
- the discriminating unit is a discriminating model for discriminating the type of the optical fiber to be connected based on the imaging data of the optical fiber to be connected, and is a feature amount obtained from the imaging data of the optical fiber and the feature amount.
- the features obtained from the imaging data provided by the imaging unit are input to the discrimination model created by machine learning using the sample data showing the correspondence with the type of optical fiber obtained, and each pair of optical fibers is input. Determine the type of.
- the connection unit fuses and connects the pair of optical fibers to each other under the connection conditions according to the combination of the types of the pair of optical fibers.
- the discrimination model is created by classifying a plurality of fusion splicers into two or more groups in which the tendency of the imaging data is presumed to be similar, and collecting sample data for each group.
- the discriminating unit discriminates the types of each pair of optical fibers by using a discriminant model corresponding to the group to which the fusion splicer belongs.
- the model creation device of the present disclosure includes a discrimination model creation unit.
- the discrimination model creation unit performs machine learning using sample data showing the correspondence between the feature amount obtained from the optical fiber imaging data and the optical fiber type, and attempts to connect the type of optical fiber to be connected. Create a discrimination model for discrimination based on the imaging data of the optical fiber.
- the discrimination model creation unit classifies a plurality of fusion splicers into two or more groups presumed to have similar tendencies of imaging data, collects sample data for each group, and creates a discrimination model.
- the model creation device provides each fusion splicer with a discrimination model corresponding to the group to which each fusion splicer belongs.
- the method of fusion-bonding the optical fibers of the present disclosure includes a step of creating a discrimination model, a step of generating imaging data, a step of discrimination, and a step of fusion-bonding.
- a discrimination model machine learning is performed using the sample data showing the correspondence between the feature amount obtained from the imaged data of the optical fiber and the type of the optical fiber, and the type of the optical fiber to be connected is determined.
- a pair of optical fibers are imaged to generate imaging data.
- the discriminating step the feature amount obtained from the imaging data generated in the step of generating the imaging data is input to the discrimination model, and the types of each pair of optical fibers are discriminated.
- the step of fusion-bonding the pair of optical fibers are fusion-bonded to each other under the connection conditions according to the combination of the types of the pair of optical fibers based on the discrimination result in the step of discrimination.
- two or more fusion splicers that perform the step of generating imaging data, the step of discriminating, and the step of fusion splicing are presumed to have similar tendencies of imaging data. Classify into groups of, collect sample data from multiple fusion splicers, and create a discrimination model for each group.
- the type of each pair of optical fibers is discriminated by using a discriminant model corresponding to the group to which the fusion splicer that performs the discriminating step belongs.
- FIG. 1 is a diagram schematically showing a configuration of an optical fiber fusion splicer system according to an embodiment of the present disclosure.
- FIG. 2 is a perspective view showing the appearance of the fusion splicer, showing the appearance of the windshield cover in a closed state.
- FIG. 3 is a perspective view showing the appearance of the fusion splicer, showing the appearance of the fusion splicer in a state where the windshield cover is opened and the internal structure of the fusion splicer can be seen.
- FIG. 4 is a block diagram showing a functional configuration of the fusion splicer.
- FIG. 5 is a block diagram showing a hardware configuration of the fusion splicer.
- FIG. 6 is a diagram showing the operation of the connection portion.
- FIG. 1 is a diagram schematically showing a configuration of an optical fiber fusion splicer system according to an embodiment of the present disclosure.
- FIG. 2 is a perspective view showing the appearance of the fusion splicer, showing the appearance of the
- FIG. 7 is a diagram showing the operation of the connection portion.
- FIG. 8 is a diagram showing the operation of the connection portion.
- FIG. 9 is a front view of the end face of one of the optical fibers.
- FIG. 10 is a diagram schematically showing the imaging data obtained in the imaging unit.
- FIG. 11 is a block diagram showing a functional configuration of the model creation device.
- FIG. 12 is a block diagram showing a hardware configuration of the model creation device.
- FIG. 13 is a flowchart showing the method according to the embodiment.
- optical fibers There are various types of optical fibers.
- the types of optical fibers are distinguished by, for example, features relating to application and optical properties, as well as structural features.
- Features related to applications and optical characteristics include single mode fiber (SMF: Single Mode Fiber), multimode fiber (MMF: Multi Mode Fiber), general-purpose single mode fiber, and distributed shift single mode fiber (DSF: Dispersion Shifted SMF). It also features non-zero dispersion shift single-mode fiber (NZDSF: Non-Zero DSF).
- Structural features include the diameter of the optical fiber, the core diameter, the material of the core and the clad, and the refractive index distribution in the radial direction.
- the optimum fusion conditions for fusion-connecting the pair of optical fibers change depending on the combination of the types of the pair of optical fibers.
- the type of optical fiber already laid is often unknown. Therefore, it is important for the fusion splicer to accurately discriminate the combination of the types of the pair of optical fibers to be connected.
- a discrimination model capable of discriminating the type of the optical fiber from the luminance distribution data in the radial direction of the optical fiber is created by using machine learning.
- machine learning there are mechanical and structural variations in the imaging device included in the fusion splicer. Therefore, even when the same optical fiber is imaged, the obtained imaged data is slightly different for each fusion splicer. Therefore, even if machine learning is performed based on the imaging data obtained from a plurality of fusion splicers, the accuracy of discrimination is limited.
- the fusion splicing system for an optical fiber includes a model making device and a plurality of fusion splicing machines.
- the model creation device performs machine learning using sample data showing the correspondence between the feature amount obtained from the imaged data of the optical fiber and the type of the optical fiber, and attempts to connect the type of the optical fiber to be connected.
- Each of the plurality of fusion splicers has an imaging unit, a discriminating unit, and a connecting unit. The imaging unit captures a pair of optical fibers to generate imaging data.
- the discriminating unit inputs the feature amount obtained from the imaging data provided by the imaging unit into the discriminating model, and discriminates the types of each pair of optical fibers. Based on the discrimination result in the discrimination unit, the connection unit fuses and connects the pair of optical fibers to each other under the connection conditions according to the combination of the types of the pair of optical fibers.
- the model creation device classifies a plurality of fusion splicers into two or more groups presumed to have similar tendencies of imaging data, collects sample data for each group, and creates a discrimination model.
- the discriminating unit of each fusion splicer discriminates the type of each pair of optical fibers by using the discrimination model corresponding to the group to which each fusion splicer belongs.
- the fusion splicer includes an imaging unit, a discriminating unit, and a connecting unit.
- the imaging unit captures a pair of optical fibers to generate imaging data.
- the discriminating unit is a discriminating model for discriminating the type of the optical fiber to be connected based on the imaging data of the optical fiber to be connected, and is a feature amount obtained from the imaging data of the optical fiber and the feature amount.
- the features obtained from the imaging data provided by the imaging unit are input to the discrimination model created by machine learning using the sample data showing the correspondence with the type of optical fiber obtained, and each pair of optical fibers is input. Determine the type of.
- the connection unit fuses and connects the pair of optical fibers to each other under the connection conditions according to the combination of the types of the pair of optical fibers.
- the discrimination model is created by classifying a plurality of fusion splicers into two or more groups in which the tendency of the imaging data is presumed to be similar, and collecting sample data for each group.
- the discriminating unit discriminates the types of each pair of optical fibers using a discriminating model corresponding to the group to which the fusion splicer belongs.
- the method of fusion-bonding the optical fibers includes a step of creating a discrimination model, a step of generating imaging data, a step of discrimination, and a step of fusion-bonding.
- the step of creating the discrimination model machine learning is performed using the sample data showing the correspondence between the feature amount obtained from the imaged data of the optical fiber and the type of the optical fiber, and the type of the optical fiber to be connected is determined.
- a pair of optical fibers are imaged to generate imaging data.
- the discriminating step the feature amount obtained from the imaging data generated in the step of generating the imaging data is input to the discrimination model, and the types of each pair of optical fibers are discriminated.
- the step of fusion-bonding the pair of optical fibers are fusion-bonded to each other under the connection conditions according to the combination of the types of the pair of optical fibers based on the discrimination result in the step of discrimination.
- two or more fusion splicers that perform the step of generating imaging data, the step of discriminating, and the step of fusion splicing are presumed to have similar tendencies of imaging data. Classify into groups of, collect sample data from multiple fusion splicers, and create a discrimination model for each group.
- the type of each pair of optical fibers is discriminated by using a discriminant model corresponding to the group to which the fusion splicer that performs the discriminating step belongs.
- fusion splicing system fusion splicer, and fusion splicing method
- sample data showing the correspondence between the feature amount obtained from the image pickup data of the optical fiber and the type of the optical fiber obtained from the feature amount is used.
- Machine learning is performed using this, and the type of optical fiber is discriminated using the obtained discriminant model. Therefore, high-precision discrimination based on machine learning is possible.
- a plurality of fusion splicers are classified into two or more groups in which the tendency of the imaging data is presumed to be similar, and sample data is collected for each group to create a discrimination model. Then, the type of each pair of optical fibers is discriminated by using the discriminant model corresponding to the group to which the own machine belongs.
- machine learning can be performed only within a group in which there is little mechanical and structural variation in the imaging unit. Therefore, the accuracy of discriminating the optical fiber type based on machine learning can be further improved.
- machine learning may be deep learning. In this case, the accuracy of discriminating the type of optical fiber can be further improved.
- two or more groups shall be at least one of the inspection conditions of each fusion splicer and the inspection result of each fusion splicer. It may be classified based on the similarity. The similarity between the test conditions and the test results is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- two or more groups are obtained by imaging an optical fiber as a reference when inspecting each fusion splicer by an imaging unit. It may be classified based on the similarity of the captured data.
- the similarity of the imaging data obtained by imaging the reference optical fiber at the time of inspection represents the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the similarity of the imaging data may include the similarity of the feature amount obtained from the luminance information in the radial direction of the pair of optical fibers.
- two or more groups have an environment in which an optical fiber, which is a reference when inspecting each fusion splicer, is imaged by an imaging unit. It may be classified based on the similarity of conditions. It is considered that the similarity of the environmental conditions when imaging the reference optical fiber at the time of inspection affects the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the environmental conditions may include at least one of temperature, humidity, and atmospheric pressure.
- two or more groups are classified based on the similarity of at least one of the manufacturer and date and time of manufacture of each fusion splicer. May be good.
- the similarity of at least one of the manufacturer of the fusion splicer and the date and time of manufacture is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the two or more groups are based on the similarity of at least one of the manufacturer and date and time of the imaging unit of each fusion splicer. It may be classified. It is considered that the similarity of at least one of the manufacturer of the imaging unit and the manufacturing date and time affects the similarity of the tendency of the imaging data. Therefore, in these cases, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the imaging unit may have an observation optical unit (lens).
- the two or more groups may be classified based on the similarity of at least one of the manufacturer and the date and time of manufacture of the observation optics of each fusion splicer.
- the similarity of at least one of the manufacturer and the date and time of manufacture of the observation optical unit is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- two or more groups may be classified based on the similarity of environmental conditions at the place of use of each fusion splicer.
- the similarity of environmental conditions at the place of use of the fusion splicer is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the environmental conditions may include at least one of temperature, humidity, and pressure.
- two or more groups may be classified based on the similarity of the deterioration state of each fusion splicing machine.
- the similarity of the deterioration state of the fusion splicer is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the deteriorated state is the elapsed time from the manufacturing date, the usage time, the number of discharges, the connection frequency, the degree of dirt on the discharge electrode, the dimming state of the light source that illuminates the pair of optical fibers from the opposite side of the imaging unit, and the imaging unit. It may include at least one of the degree of dirtiness of the observation optical fiber and the result of device diagnosis.
- two or more groups may be classified based on the similarity of the optical fiber types to be connected in each fusion splicer. good.
- the similarity of the types of optical fibers to be connected is considered to affect the similarity of the tendency of the imaging data. Therefore, in this case, the plurality of fusion splicers can be appropriately classified into two or more groups in which the tendency of the imaging data is presumed to be similar.
- the model creation device includes a discrimination model creation unit.
- the discrimination model creation unit performs machine learning using sample data showing the correspondence between the feature amount obtained from the optical fiber imaging data and the optical fiber type, and attempts to connect the type of optical fiber to be connected. Create a discrimination model for discrimination based on the imaging data of the optical fiber.
- the discrimination model creation unit classifies a plurality of fusion splicers into two or more groups presumed to have similar tendencies of imaging data, collects sample data for each group, and creates a discrimination model.
- the model creation device provides each fusion splicer with a discrimination model corresponding to the group to which each fusion splicer belongs.
- a plurality of fusion splicers are classified into two or more groups in which the tendency of imaging data is presumed to be similar, and sample data is collected for each group to create a discrimination model.
- machine learning can be performed only within a group in which there is little mechanical and structural variation in each fusion splicer. Therefore, the accuracy of discriminating the optical fiber type based on machine learning can be further improved.
- FIG. 1 is a diagram schematically showing a configuration of a fusion splicer connection system 1A according to an embodiment of the present disclosure.
- the fusion splicer system 1A includes a plurality of fusion splicer 10s and a model creation device 20.
- the fusion splicer 10 is a device for fusion splicing optical fibers.
- the model creation device 20 is a device that creates a discrimination model for discriminating the type of optical fiber.
- the model creation device 20 is a computer capable of communicating with a plurality of fusion splicers 10 via the information communication network 30.
- the information communication network 30 is, for example, the Internet.
- the location area of the model creation device 20 is far from the location area of the fusion splicer 10.
- FIGS. 2 and 3 are perspective views showing the appearance of the fusion splicer 10.
- FIG. 2 shows an appearance in a state where the windshield cover is closed
- FIG. 3 shows an appearance in a state where the windshield cover is opened and the internal structure of the fusion splicer 10 can be seen.
- the fusion splicer 10 includes a box-shaped housing 2.
- a connecting portion 3 for fusion-bonding the optical fibers and a heater 4 are provided on the upper portion of the housing 2.
- the heater 4 is a portion that heats and shrinks the fiber reinforcing sleeve that covers the connecting portion between the optical fibers that are fused and connected at the connecting portion 3.
- the fusion splicer 10 includes a monitor 5 that displays a fusion connection status between optical fibers imaged by an imaging unit (described later) arranged inside the housing 2. Further, the fusion splicer 10 is provided with a windshield cover 6 for preventing wind from entering the connecting portion 3.
- the connection portion 3 has a holder mounting portion on which a pair of optical fiber holders 3a can be mounted, a pair of fiber positioning portions 3b, and a pair of discharge electrodes 3c.
- Each of the optical fibers to be fused is held and fixed to the optical fiber holder 3a, and each of the optical fiber holders 3a is placed and fixed to the holder mounting portion.
- the fiber positioning portion 3b is arranged between the pair of optical fiber holders 3a, and positions the tip end portion of the optical fiber held in each of the optical fiber holders 3a.
- the discharge electrode 3c is an electrode for fusing the tips of optical fibers to each other by arc discharge, and is arranged between a pair of fiber positioning portions 3b.
- the windshield cover 6 is connected to the housing 2 so as to cover the connecting portion 3 so as to be openable and closable.
- Each of the side surfaces 6a of the windshield cover 6 is formed with an introduction port 6b for introducing an optical fiber into the connection portion 3, that is, into each of the optical fiber holders 3a.
- FIG. 4 is a block diagram showing a functional configuration of the fusion splicer 10.
- FIG. 5 is a block diagram showing a hardware configuration of the fusion splicer 10.
- the fusion splicer 10 functionally includes a connection unit 3, a communication unit 11, an imaging unit 12, a feature amount extraction unit 13, a discrimination unit 14, and a fusion control unit 15.
- the image pickup unit 12 includes an image pickup element and an observation optical section that outputs a magnified image of an image pickup object to the image pickup device.
- the observation optics include, for example, one or more lenses. As shown in FIG.
- the fusion splicer 10 includes a computer having hardware such as a CPU 10a, a RAM 10b, a ROM 10c, an input device 10d, an auxiliary storage device 10e, and an output device 10f as a control unit.
- a control unit Each function of the fusion splicer 10 is realized by operating these components by a program or the like.
- These elements in the control unit are electrically connected to the connection unit 3, the monitor 5, the wireless communication module as the communication unit 11, and the image pickup unit 12 described above.
- the input device 10d may include a touch panel provided integrally with the monitor 5.
- the communication unit 11 is composed of, for example, a wireless LAN module.
- the communication unit 11 transmits and receives various data to and from the model creation device 20 via an information communication network 30 such as the Internet.
- the imaging unit 12 captures a pair of optical fibers to be connected from the radial direction of the optical fibers via an observation optical unit (lens) with the pair of optical fibers facing each other, and generates imaging data. do.
- the feature amount extraction unit 13 extracts two or more feature amounts for specifying the type of optical fiber from the image pickup data obtained from the image pickup unit 12.
- the feature quantity includes the luminance information in the radial direction of the optical fiber.
- Luminance information in the radial direction of the optical fiber includes, for example, the luminance distribution in the radial direction of the optical fiber, the outer diameter of the optical fiber, the outer diameter of the core, the ratio of the outer diameter of the core to the outer diameter of the optical fiber, and the core and clad of the optical fiber.
- Area ratio, total brightness of optical fiber, position and number of bending points of brightness distribution in the cross section of optical fiber, difference in brightness between core and clad part of optical fiber, and core part having a specific brightness or more. Includes at least one of the widths.
- the imaging data used for extracting the feature amount may include data acquired while discharging a pair of optical fibers to be connected while facing each other.
- the feature amount includes, for example, at least one of the light intensity at the specific position and the time change of the light intensity at the specific position.
- the discrimination unit 14 stores and holds a discrimination model Md for discriminating the type of optical fiber.
- the discrimination unit 14 inputs the feature amount obtained from the feature amount extraction unit 13 into the discrimination model Md, and discriminates the types of each of the pair of optical fibers.
- the determination result by the determination unit 14 is displayed on the monitor 5.
- the user inputs the correct type via the input device 10d and corrects the determination result.
- the user may input each type of the pair of optical fibers via the input device 10d regardless of the discrimination result by the discrimination unit 14. In that case, the input by the user is preferentially adopted, and the type of each optical fiber is specified.
- the input may be replaced with the input of the corresponding type of optical fiber itself.
- the fusion control unit 15 controls the operation of the connection unit 3. That is, the fusion control unit 15 controls the contact operation between the tips of the pair of optical fibers and the arc discharge in the connection unit 3 in response to the operation of the switch by the user.
- the contact operation between the tips of the pair of optical fibers includes the positioning process of the optical fibers by the fiber positioning unit 3b, that is, the control of the tip position of each optical fiber.
- Control of arc discharge includes control of discharge power, discharge start timing and discharge end timing.
- Various connection conditions such as the tip position of the optical fiber and the discharge power are preset for each combination of the types of the pair of optical fibers, and are stored in, for example, the ROM 10c.
- the fusion control unit 15 selects the connection conditions according to the combination of the types of the pair of optical fibers determined by the determination unit 14 or input by the user. That is, the connection unit 3 recognizes a combination of a pair of optical fiber types based on the discrimination result in the discrimination unit 14 or the input result by the user, and connects the pair of optical fibers under the connection conditions according to the combination. Fused and connected to each other.
- connection unit 3 The operation of the connection unit 3 is as follows. First, as shown in FIG. 6, the user holds the pair of optical fibers F1 and F2 to be connected in the optical fiber holder 3a, respectively. At this time, the end face F1a of the optical fiber F1 and the end face F2a of the optical fiber F2 are arranged so as to face each other. Next, the user instructs the fusion splicer 10 to start the fusion splicing. This instruction is given, for example, via a switch input. In response to this instruction, as shown in FIG. 7, the fusion control unit 15 positions the optical fibers F1 and F2 based on the positions of the end faces F1a and F2a set as the connection conditions. After that, as shown in FIG. 8, the fusion control unit 15 starts arc discharge between the pair of discharge electrodes 3c.
- the end faces F1a and F2a are separated from each other.
- the arc discharge corresponds to a preliminary discharge for pre-softening the end faces F1a and F2a before fusion.
- the fusion control unit 15 controls the position of the fiber positioning unit 3b to bring the end faces F1a and F2a closer to each other and bring them into contact with each other. Then, the fusion control unit 15 performs the main discharge by continuing the arc discharge. As a result, the end faces F1a and F2a are further softened and fused to each other.
- connection conditions include the positions of the end faces F1a and F2a before the start of discharge, the distance between the end faces F1a and F2a before the start of discharge, the preliminary discharge time, the main discharge time, and the end faces F1a and F2a. At least one of the subsequent pushing amount, the pulling back amount after pushing the end faces F1a and F2a, the preliminary discharge power, the main discharge power, and the discharge power at the time of pulling back is included.
- the positions of the end faces F1a and F2a before the start of discharge are based on the line connecting the central axes of the pair of discharge electrodes 3c at the state shown in FIG. 7, that is, at the start of the preliminary discharge, that is, the discharge central axis. Refers to the positions of the end faces F1a and F2a.
- the distance between the discharge center axis and the end faces F1a and F2a changes according to the positions of these end faces. This increases or decreases the amount of heating, that is, the amount of melting.
- the time required for movement until the end faces F1a and F2a come into contact with each other changes.
- the distance between the end faces F1a and F2a before the start of discharge refers to the state shown in FIG.
- the pre-discharge time is the time from the start of arc discharge in the state shown in FIG. 7 to the start of relative movement of the optical fibers F1 and F2 in order to bring the end faces F1a and F2a into contact with each other.
- the main discharge time refers to the time from when the end faces F1a and F2a come into contact with each other until the end of the arc discharge, in other words, the time from when the application of the voltage to the pair of discharge electrodes 3c is stopped.
- the pre-discharge and the main discharge are performed continuously in time.
- the amount of pushing after the end faces F1a and F2a are in contact with each other means that the optical fibers F1 and F2 are relatively moved to bring the end faces F1a and F2a into contact with each other, and then the optical fibers F1 and F2a are further in the same direction during discharge. It refers to the moving distance of each optical fiber holder 3a when F2 is relatively moved.
- the amount of pullback after pushing the end faces F1a and F2a is the amount of pulling back after the end faces F1a and F2a are brought into contact with each other, and then the end faces F1a and F2a are pushed further.
- the preliminary discharge power is the period from the start of arc discharge in the state shown in FIG. 7 to the start of relative movement of the optical fibers F1 and F2 in order to bring the end faces F1a and F2a into contact with each other. Arc discharge power.
- FIG. 9 is a view of the end surface F2a of one of the optical fibers F2 as viewed from the front, that is, from the direction of the optical axis.
- Arrows MSX and MSY in the figure indicate the imaging direction by the imaging unit 12. That is, in this example, at least two imaging units 12 are installed, and the two imaging units 12 image the end faces F1a and F2a from the radial directions of the optical fibers F1 and F2 and orthogonal to each other.
- a light source for illuminating the optical fibers F1 and F2 is arranged at a position facing the imaging unit 12 with the optical fibers F1 and F2 interposed therebetween.
- the light source is, for example, a light emitting diode.
- FIG. 10 is a diagram schematically showing the imaging data PX obtained by the imaging unit 12 imaged from the direction MSX or the imaging data PY obtained by the imaging unit 12 imaged from the direction MSY.
- the positions and shapes of the optical fibers F1 and F2 are confirmed by the contours of the core CR and the clad CL.
- the core CR is brightened by the illumination light from the light source.
- the clad CL becomes dark due to the refraction of the illumination light from the light source.
- FIG. 11 is a block diagram showing a functional configuration of the model creation device 20.
- FIG. 12 is a block diagram showing a hardware configuration of the model creation device 20.
- the model creation device 20 functionally includes a communication unit 21 and a discrimination model creation unit 22.
- the model creation device 20 includes a computer including hardware such as a CPU 20a, a RAM 20b, a ROM 20c, an input device 20d, a communication module 20e, an auxiliary storage device 20f, and an output device 20g.
- Each function of the model creation device 20 is realized by operating these components by a program or the like.
- the communication unit 21 shown in FIG. 11 communicates with a plurality of fusion splicers 10 via an information communication network 30 (see FIG. 1) such as the Internet.
- the communication unit 21 receives information on the feature quantities extracted from the imaging data PX and PY and the types of the optical fibers F1 and F2 from the plurality of fusion splicers 10 via the information communication network 30.
- the communication unit 21 may receive the imaging data PX, PY itself instead of the feature amount extracted from the imaging data PX, PY. In that case, the model creation device 20 extracts the feature amount from the imaging data PX and PY.
- the information regarding the types of the optical fibers F1 and F2 may be only the information input by the user.
- the communication unit 21 fuses the information regarding the types of the optical fibers F1 and F2 input by the user and the feature amount or the imaging data itself extracted from the imaging data PX and PY of the optical fibers F1 and F2. Received from the incoming connection device 10. For the information regarding the types of optical fibers F1 and F2 input by the user, one of the preset manufacturing conditions for each type of optical fibers F1 and F2 is selected instead of the input of the types of optical fibers F1 and F2 itself. Including the case of The communication unit 21 uses these received information as sample data Da showing the correspondence between the feature quantities obtained from the imaged data PX and PY of the optical fibers F1 and F2 and the types of the optical fibers F1 and F2. It is provided to the preparation unit 22.
- the discrimination model creation unit 22 performs machine learning using the sample data Da provided by the communication unit 21. Then, the discrimination model creation unit 22 creates a discrimination model Md for discriminating the types of the optical fibers F1 and F2 based on the imaging data PX and PY.
- Machine learning is preferably deep learning. As the machine learning technique, various techniques included in so-called supervised learning such as a neural network and a support vector machine can be applied.
- the discrimination model creation unit 22 continuously performs machine learning using a huge amount of sample data Da obtained from a large number of fusion splicers 10 in operation to improve the accuracy of the discrimination model Md.
- the discrimination model creation unit 22 of the present embodiment classifies the plurality of fusion splicers 10 into two or more groups presumed to have similar tendencies of the imaging data PX and PY. Then, the discrimination model creation unit 22 collects sample data Da for each group and creates a discrimination model Md for each group. Creating a discrimination model Md for each group means that machine learning is performed using only sample data Da obtained from a plurality of fusion splicers 10 belonging to a certain group, and the created discrimination model Md belongs to that group. It means that it is provided only to the fusion splicer 10.
- Two or more groups presumed to have similar tendencies in the imaging data PX and PY are classified based on, for example, at least one of the following items (1) to (9).
- Similarity of inspection results of the fusion splicer 10 When the inspection results of the fusion splicer 10 and particularly the inspection results of the inspection items related to the imaging unit 12 are similar to each other in the plurality of fusion splicers 10, they are used. It is presumed that the tendencies of the imaging data PX and PY are similar in the fusion splicer 10. For example, the optical fiber that serves as a reference when inspecting each fusion splicer 10 is imaged by the imaging unit 12, and the brightness information such as the brightness distribution in the obtained imaging data PX and PY is obtained by a plurality of fusion splicers 10. For example, when they are similar to each other.
- the difference in the degree of softening of the optical fiber that is, the change in the end face position. This is the case where at least one of the amount and the shape of the softened optical fiber is similar to each other in the plurality of fusion splicers 10.
- the discharge power when the degree of softening of the reference optical fiber is the same is similar to each other in the plurality of fusion splicers 10. Is.
- the deterioration state of the fusion splicer 10 is, for example, the elapsed time from the manufacturing date, the usage time, the number of discharges, the connection frequency, the degree of dirt on the discharge electrode 3c, and the adjustment of the light source that illuminates the optical fiber from the opposite side of the imaging unit 12. It includes at least one of the light state, the degree of contamination of the observation optical unit of the imaging unit 12, and the device diagnosis result.
- optical fibers F1 and F2 which are mainly targeted to be connected in the field where the fusion splicer 10 is used, are similar to each other in the plurality of fusion splicers 10. If so, it is presumed that the tendencies of the imaging data PX and PY are similar in those fusion splicers 10.
- the types of optical fibers F1 and F2 referred to here refer to rough types of optical fibers such as single-mode fiber and multimode fiber, general-purpose fiber and distributed shift fiber, and the like.
- the discharge state of the fusion connector 10 is similar to each other in the plurality of fusion junctions 10. If so, it is presumed that the tendencies of the imaging data PX and PY are similar in those fusion splicers 10.
- the discharge state referred to here can be represented by a feature amount of luminance information obtained from imaging data acquired while discharging without installing a pair of optical fibers. Groups are made according to the similarity of these features.
- the feature amount includes, for example, at least one of the light intensity at a specific point determined with reference to the central axis direction of the discharge electrode 3c and the light intensity distribution shape of the imaging data in the specific direction.
- the specific direction is, for example, a direction orthogonal to the discharge direction or a direction parallel to the discharge direction.
- the discrimination model Md created by collecting the sample data Da for each group in this way is transmitted to the fusion splicer 10 belonging to the corresponding group via the communication unit 21.
- the discrimination unit 14 of each fusion splicer 10 discriminates the types of each of the pair of optical fibers F1 and F2 by using the discrimination model Md corresponding to the group to which the fusion splicer 10 belongs.
- FIG. 13 is a flowchart showing a method of fusion-bonding optical fibers according to the present embodiment. This method can be suitably realized by using the fusion splicing system 1A described above.
- the model creation step ST1 machine learning is performed using sample data Da showing the correspondence between the feature amount obtained from the image pickup data of the optical fiber and the type of the optical fiber.
- a discrimination model Md for discriminating the types of the optical fibers F1 and F2 to be connected based on the imaging data PX and PY of the optical fibers F1 and F2 is created.
- the plurality of fusion splicers 10 are classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- sample data Da is collected for each group to create a discrimination model Md.
- a pair of optical fibers F1 and F2 are imaged to generate imaging data PX and PY.
- the discrimination step ST3 the feature amounts obtained from the image pickup data PX and PY generated in the imaging step ST2 are input to the discrimination model Md, and the types of the pair of optical fibers F1 and F2 are discriminated.
- the types of each of the pair of optical fibers F1 and F2 are discriminated by using the discrimination model Md corresponding to the group to which the fusion splicer 10 performing the discrimination step ST3 belongs.
- connection step ST4 the pair of optical fibers F1 and F2 are fused and connected to each other under the connection conditions according to the combination of the types of the pair of optical fibers F1 and F2 based on the discrimination result in the discrimination step ST3. ..
- the plurality of fusion splicers 10 are classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY, and sample data Da is collected for each group to create a discrimination model Md. .. Then, the types of each of the pair of optical fibers F1 and F2 are discriminated by using the discriminant model Md corresponding to the group to which the own machine belongs. As a result, machine learning can be performed only within the group in which the mechanical and structural variations of the imaging unit 12 are small, so that the accuracy of discriminating the optical fiber type based on the machine learning can be further improved.
- machine learning may be deep learning.
- the accuracy of discriminating the type of optical fiber can be further improved.
- the two or more groups may be classified based on the similarity of at least one of the inspection conditions and results of each fusion splicer 10.
- the similarity of the examination conditions and results is considered to affect the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the above two or more groups are based on the similarity of the imaging data PX and PY obtained by imaging the optical fiber as a reference when inspecting each fusion splicer 10 by the imaging unit 12. It may be classified.
- the similarity of the imaging data PX and PY obtained by imaging the reference optical fiber at the time of inspection represents the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the above two or more groups have similarities in environmental conditions such as temperature, humidity, and atmospheric pressure when the optical fiber, which is a reference when inspecting each fusion splicer 10, is imaged by the imaging unit 12. It may be classified based on. It is considered that the similarity of the environmental conditions when the reference optical fiber is imaged at the time of inspection affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the two or more groups may be classified based on the similarity of at least one of the manufacturer and the date and time of manufacture of each fusion splicer 10. It is considered that the similarity of at least one of the manufacturer and the date and time of manufacture of the fusion splicer 10 affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the two or more groups may be classified based on the similarity of at least one of the manufacturer of the imaging unit 12 and the date and time of manufacture. It is considered that the similarity of at least one of the manufacturer and the date and time of manufacture of the imaging unit 12 affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the two or more groups may be classified based on the similarity of at least one of the manufacturer of the observation optical unit of the imaging unit 12 and the date and time of production. It is considered that the similarity of at least one of the manufacturer and the date and time of manufacture of the observation optical unit of the imaging unit 12 affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the two or more groups may be classified based on the similarity of environmental conditions such as temperature, humidity, and atmospheric pressure at the place of use of each fusion splicer 10. It is considered that the similarity of the environmental conditions at the place where the fusion splicer 10 is used affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the above two or more groups may be classified based on the similarity of the deterioration states of each fusion splicer 10. It is considered that the similarity of the deteriorated state of the fusion splicer 10 affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the above two or more groups may be classified based on the similarity of the types of optical fibers to be connected in each fusion splicer 10.
- the similarity of the types of optical fibers to be connected is considered to affect the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the above two or more groups may be classified based on the similarity of the discharge states of each fusion splicer 10. It is considered that the similarity of the discharge state of each fusion splicer 10 affects the similarity of the tendency of the imaging data PX and PY. Therefore, in this case, the plurality of fusion splicers 10 can be appropriately classified into two or more groups presumed to have similar tendencies of the imaging data PX and PY.
- the model creation device 20 of this embodiment includes a discrimination model creation unit 22.
- the discrimination model creation unit 22 performs machine learning using the sample data Da showing the correspondence between the feature amount obtained from the imaging data PX and PY of the optical fibers F1 and F2 and the types of the optical fibers F1 and F2. Then, a discrimination model Md for discriminating the types of the optical fibers F1 and F2 to be connected based on the imaging data PX and PY of the optical fibers F1 and F2 to be connected is created.
- the discrimination model creation unit 22 classifies the plurality of fusion splicers 10 into two or more groups presumed to have similar tendencies of the imaging data PX and PY, and collects and discriminates sample data Da for each group. Create model Md.
- the model creation device 20 provides each fusion splicer 10 with a discrimination model Md corresponding to the group to which each fusion splicer 10 belongs.
- machine learning can be performed only within a group having little mechanical and structural variation of each fusion splicer 10. Therefore, it is possible to further improve the discriminating accuracy of the types of optical fibers F1 and F2 based on machine learning.
- the fusion splicing system for the optical fiber, the fusion splicer, the model making apparatus, and the method for fusion splicing the optical fiber according to the present disclosure are not limited to the above-described embodiment, and various other modifications are possible. It is possible.
- the method of classifying two or more groups in which the tendency of the imaging data is presumed to be similar is not limited to that exemplified in the above embodiment.
- Output device 21 ... Communication unit 22 . Discrimination model creation unit 30 ... Information communication network CL ... Clad CR ... Core Da ... Sample data F1, F2 ... Optical fiber F1a, F2a ... End face Md ... Discrimination model MSX, MSY ... Direction PX, PY ... Imaging data ST1 ... Model creation process ST2 ... Imaging process ST3 ... Discrimination process ST4 ... Connection process
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Plasma & Fusion (AREA)
- General Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Mechanical Coupling Of Light Guides (AREA)
Abstract
Description
光ファイバには様々な種類が存在する。光ファイバの種類は、例えば、用途及び光学特性に関する特徴、並びに構造的な特徴によって区別される。用途及び光学特性に関する特徴としては、シングルモードファイバ(SMF:Single Mode Fiber)、マルチモードファイバ(MMF:Multi Mode Fiber)、汎用シングルモードファイバ、分散シフト・シングルモードファイバ(DSF:Dispersion Shifted SMF)、及び非零分散シフト・シングルモードファイバ(NZDSF:Non-Zero DSF)、といった特徴がある。構造的な特徴としては、光ファイバの直径、コア径、コア及びクラッドの材質、径方向の屈折率分布等がある。そして、一対の光ファイバ同士を融着接続する際の最適な融着条件、例えば放電時間及び光ファイバ同士の相対位置は、一対の光ファイバの種類の組み合わせに応じて変化する。しかしながら、既に敷設された光ファイバの種類は不明であることが多い。したがって、接続対象である一対の光ファイバの種類の組み合わせを、融着接続機において正確に判別することが重要となる。
本開示によれば、光ファイバ種類の判別精度を高めることができる光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法を提供することが可能となる。
最初に、本開示の実施形態を列記して説明する。一実施形態に係る光ファイバのための融着接続システムは、モデル作成装置と複数の融着接続機とを備える。モデル作成装置は、光ファイバの撮像データから得られる特徴量と前記光ファイバの種類との対応関係を示すサンプルデータを用いて機械学習を行い、接続しようとする光ファイバの種類を前記接続しようとする光ファイバの撮像データに基づいて判別するための判別モデルを作成する。複数の融着接続機のそれぞれは、撮像部と判別部と接続部とを有する。撮像部は、一対の光ファイバを撮像して撮像データを生成する。判別部は、撮像部から提供された撮像データから得られる特徴量を判別モデルに入力し、一対の光ファイバそれぞれの種類を判別する。接続部は、判別部における判別結果に基づいて、一対の光ファイバの種類の組み合わせに応じた接続条件にて一対の光ファイバを相互に融着接続する。モデル作成装置は、複数の融着接続機を撮像データの傾向が類似していると推定される二以上のグループに分類して、グループ毎にサンプルデータを集めて判別モデルを作成する。各融着接続機の判別部は、前記各融着接続機が属するグループに対応する判別モデルを用いて一対の光ファイバそれぞれの種類を判別する。
本開示の、光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法の具体例を、以下に図面を参照しつつ説明する。なお、本発明はこれらの例示に限定されるものではなく、請求の範囲によって示され、請求の範囲と均等の意味及び範囲内でのすべての変更が含まれることが意図される。以下の説明では、図面の説明において同一の要素には同一の符号を付し、重複する説明を省略する。
融着接続機10の検査結果、特に撮像部12に関する検査項目における検査結果が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。例えば、各融着接続機10の検査の際に基準となる光ファイバを撮像部12により撮像し、得られた撮像データPX,PYにおける輝度分布等の輝度情報が、複数の融着接続機10において互いに類似している場合等である。また、例えば、各融着接続機10の検査の際に基準となる光ファイバを撮像部12により撮像して得られた撮像データPX,PYにおいて、光ファイバの軟化度合いの相違すなわち端面位置の変化量、及び軟化後の光ファイバの形状のうち少なくとも一方が、複数の融着接続機10において互いに類似している場合等である。また、例えば、各融着接続機10の検査の際に、基準となる光ファイバの軟化度合いを同程度としたときの放電パワーが、複数の融着接続機10において互いに類似している場合等である。
融着接続機10の検査条件、特に撮像部12に関する検査項目における検査条件が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。例えば、各融着接続機10の検査の際に基準となる光ファイバを撮像部12により撮像した際の環境条件が、複数の融着接続機10において互いに類似している場合等である。環境条件は、例えば、温度(気温)、湿度、及び気圧のうち少なくとも1つを含む。
融着接続機10の製造者及び製造日時のうち少なくとも一方が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。製造日時が類似しているとは、例えばロットが同じであることを意味してもよい。製造者が類似しているとは、例えば同じ製造者又は同じ工場において製造されたことを意味してもよい。
撮像部12の製造者及び製造日時のうち少なくとも一方が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。製造日時が類似しているとは、例えばロットが同じであることを意味してもよい。また、製造者が類似しているとは、例えば同じ製造者又は同じ工場において製造されたことを意味してもよい。
撮像部12の観察用光学部(レンズ)の製造者及び製造日時のうち少なくとも一方が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。製造日時が類似しているとは、例えば製造ロットが同じであることを意味してもよい。また、製造者が類似しているとは、例えば同じ製造者又は同じ工場において製造されたことを意味してもよい。
融着接続機10の使用場所における環境条件が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。環境条件は、例えば、温度(気温)、湿度、及び気圧のうち少なくとも1つを含む。例えば、高温多湿地域において使用されている複数の融着接続機10をまとめて1つのグループとし、寒冷地域において使用されている複数の融着接続機10をまとめて別のグループとし、高地において使用されている複数の融着接続機10をまとめて更に別のグループとする等の分類が考えられる。
融着接続機10の劣化状態が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。融着接続機10の劣化状態は、例えば、製造日からの経過時間、使用時間、放電回数、接続頻度、放電電極3cの汚れ具合、撮像部12の反対側から光ファイバを照明する光源の調光状態、撮像部12の観察用光学部の汚れ具合、及び機器診断結果のうち少なくとも1つを含む。
融着接続機10が使用される現場において主に接続対象とされている光ファイバF1,F2の種類が、複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。ここでいう光ファイバF1,F2の種類とは、例えばシングルモードファイバとマルチモードファイバ、或いは汎用ファイバと分散シフトファイバ等といった、光ファイバの大まかな種類を指す。
撮像データPX,PYとして放電した状態のものを使用する場合は、融着接続機10の放電状態が複数の融着接続機10において互いに類似している場合、それらの融着接続機10においては撮像データPX,PYの傾向が類似していると推定される。ここでいう放電状態とは、一対の光ファイバを設置していない状態で放電を行いつつ取得された撮像データから得られる輝度情報の特徴量で代表され得る。この特徴量の類似度でグループ分けがなされる。この場合、特徴量は、例えば、放電電極3cの中心軸方向を基準として定められた特定点における光強度、及び特定方向における撮像データの光強度分布形状のうち少なくとも一つを含む。特定方向とは、例えば、放電方向と直交する方向、又は放電方向と平行な方向である。
2…筐体
3…接続部
3a…光ファイバホルダ
3b…ファイバ位置決め部
3c…放電電極
4…加熱器
5…モニタ
6…風防カバー
6a…側面
6b…導入口
10…融着接続機
10a…CPU
10b…RAM
10c…ROM
10d…入力装置
10e…補助記憶装置
10f…出力装置
11…通信部
12…撮像部
13…特徴量抽出部
14…判別部
15…融着制御部
20…モデル作成装置
20a…CPU
20b…RAM
20c…ROM
20d…入力装置
20e…通信モジュール
20f…補助記憶装置
20g…出力装置
21…通信部
22…判別モデル作成部
30…情報通信網
CL…クラッド
CR…コア
Da…サンプルデータ
F1,F2…光ファイバ
F1a,F2a…端面
Md…判別モデル
MSX,MSY…方向
PX,PY…撮像データ
ST1…モデル作成工程
ST2…撮像工程
ST3…判別工程
ST4…接続工程
Claims (18)
- 光ファイバの撮像データから得られる特徴量と前記光ファイバの種類との対応関係を示すサンプルデータを用いて機械学習を行い、接続しようとする光ファイバの種類を前記接続しようとする光ファイバの撮像データに基づいて判別するための判別モデルを作成するモデル作成装置と、
一対の光ファイバを撮像して撮像データを生成する撮像部、前記撮像部から提供された撮像データから得られる特徴量を前記判別モデルに入力し、前記一対の光ファイバそれぞれの種類を判別する判別部、及び、前記判別部における判別結果に基づいて、前記一対の光ファイバの種類の組み合わせに応じた接続条件にて前記一対の光ファイバを相互に融着接続する接続部を有する複数の融着接続機と、
を備え、
前記モデル作成装置は、前記複数の融着接続機を撮像データの傾向が類似していると推定される二以上のグループに分類してグループ毎に前記サンプルデータを集めて前記判別モデルを作成し、
各融着接続機の前記判別部は、前記各融着接続機が属する前記グループに対応する前記判別モデルを用いて前記一対の光ファイバそれぞれの種類を判別する、光ファイバのための融着接続システム。 - 前記機械学習は深層学習である、請求項1に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の検査の条件及び各融着接続機の検査の結果のうち少なくとも一方の類似性に基づいて分類される、請求項1又は請求項2に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の検査の際に基準となる光ファイバを前記撮像部により撮像して得られた撮像データの類似性に基づいて分類される、請求項3に記載の融着接続システム。
- 前記撮像データの類似性は、前記一対の光ファイバの径方向における輝度情報から求めた特徴量の類似性を含む、請求項4に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の検査の際に基準となる光ファイバを前記撮像部により撮像した際の環境条件の類似性に基づいて分類される、請求項3から請求項5のいずれか1項に記載の融着接続システム。
- 前記環境条件は、温度、湿度、及び気圧のうち少なくとも1つを含む、請求項6に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の製造者及び製造日時のうち少なくとも一方の類似性に基づいて分類される、請求項1から請求項7のいずれか1項に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の前記撮像部の製造者及び製造日時のうち少なくとも一方の類似性に基づいて分類される、請求項1から請求項8のいずれか1項に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の観察用光学部の製造者及び製造日時のうち少なくとも一方の類似性に基づいて分類される、請求項1から請求項9のいずれか1項に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の使用場所における環境条件の類似性に基づいて分類される、請求項1から請求項10のいずれか1項に記載の融着接続システム。
- 前記環境条件は、温度、湿度、及び気圧のうち少なくとも1つを含む、請求項11に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機の劣化状態の類似性に基づいて分類される、請求項1から請求項12のいずれか1項に記載の融着接続システム。
- 前記劣化状態は、製造日からの経過時間、使用時間、放電回数、接続頻度、放電電極の汚れ具合、前記撮像部の反対側から前記一対の光ファイバを照明する光源の調光状態、前記撮像部の観察用光学部の汚れ具合、及び機器診断結果のうち少なくとも1つを含む、請求項13に記載の融着接続システム。
- 前記二以上のグループは、各融着接続機において接続対象とされる光ファイバ種類の類似性に基づいて分類される、請求項1から請求項14のいずれか1項に記載の融着接続システム。
- 一対の光ファイバを撮像して撮像データを生成する撮像部と、
接続しようとする光ファイバの種類を前記接続しようとする光ファイバの撮像データに基づいて判別するための判別モデルであって、光ファイバの撮像データから得られる特徴量と前記特徴量を得た光ファイバの種類との対応関係を示すサンプルデータを用いた機械学習により作成された前記判別モデルに、前記撮像部から提供された撮像データから得られる特徴量を入力し、前記一対の光ファイバそれぞれの種類を判別する判別部と、
前記判別部における判別結果に基づいて、前記一対の光ファイバの種類の組み合わせに応じた接続条件にて前記一対の光ファイバを相互に融着接続する接続部と、
を備え、
前記判別モデルは、複数の融着接続機を撮像データの傾向が類似していると推定される二以上のグループに分類してグループ毎に前記サンプルデータを集めて作成されたものであり、
前記判別部は、当該融着接続機が属する前記グループに対応する前記判別モデルを用いて前記一対の光ファイバそれぞれの種類を判別する、融着接続機。 - 光ファイバの撮像データから得られる特徴量と前記光ファイバの種類との対応関係を示すサンプルデータを用いて機械学習を行い、接続しようとする光ファイバの種類を前記接続しようとする光ファイバの撮像データに基づいて判別するための判別モデルを作成する判別モデル作成部を備え、
前記判別モデル作成部は、複数の融着接続機を撮像データの傾向が類似していると推定される二以上のグループに分類してグループ毎に前記サンプルデータを集めて前記判別モデルを作成し、
各融着接続機が属する前記グループに対応する前記判別モデルを各融着接続機に提供する、モデル作成装置。 - 光ファイバの撮像データから得られる特徴量と前記光ファイバの種類との対応関係を示すサンプルデータを用いて機械学習を行い、接続しようとする光ファイバの種類を前記接続しようとする光ファイバの撮像データに基づいて判別するための判別モデルを作成する工程と、
一対の光ファイバを撮像して撮像データを生成する工程と、
前記撮像データを生成する工程において生成された撮像データから得られる特徴量を前記判別モデルに入力し、前記一対の光ファイバそれぞれの種類を判別する工程と、
前記判別する工程における判別結果に基づいて、前記一対の光ファイバの種類の組み合わせに応じた接続条件にて前記一対の光ファイバを相互に融着接続する工程と、
を含み、
前記判別モデルを作成する工程では、前記撮像データを生成する工程、前記判別する工程、及び前記融着接続する工程を行う複数の融着接続機を、撮像データの傾向が類似していると推定される二以上のグループに分類して、前記複数の融着接続機から前記サンプルデータを集めて前記判別モデルをグループ毎に作成し、
前記判別する工程では、前記判別する工程を行う前記融着接続機が属する前記グループに対応する前記判別モデルを用いて前記一対の光ファイバそれぞれの種類を判別する、光ファイバを融着接続する方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180027320.4A CN115362399A (zh) | 2020-04-17 | 2021-04-12 | 用于光纤的熔接系统、熔接机、模型制作装置以及熔接光纤的方法 |
KR1020227039189A KR20230003501A (ko) | 2020-04-17 | 2021-04-12 | 광파이버를 위한 융착 접속 시스템, 융착 접속기, 모델 작성 장치, 및 광파이버를 융착 접속하는 방법 |
EP21788759.5A EP4137851A4 (en) | 2020-04-17 | 2021-04-12 | FUSION SPLICING SYSTEM FOR OPTICAL FIBERS, FUSION SPLICING DEVICE, TEMPLATE CREATION DEVICE AND METHOD FOR FUSION SPLICING OF OPTICAL FIBERS |
JP2022515378A JPWO2021210546A1 (ja) | 2020-04-17 | 2021-04-12 | |
US17/907,686 US20230126843A1 (en) | 2020-04-17 | 2021-04-12 | Fusion splicing system for optical fibers, fusion splicer, model creation device, and method for fusion splicing optical fibers |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/016860 WO2021210162A1 (ja) | 2020-04-17 | 2020-04-17 | 光ファイバのための融着接続システム、融着接続機、及び光ファイバを融着接続する方法 |
JPPCT/JP2020/016860 | 2020-04-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021210546A1 true WO2021210546A1 (ja) | 2021-10-21 |
Family
ID=78084817
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/016860 WO2021210162A1 (ja) | 2020-04-17 | 2020-04-17 | 光ファイバのための融着接続システム、融着接続機、及び光ファイバを融着接続する方法 |
PCT/JP2021/015210 WO2021210546A1 (ja) | 2020-04-17 | 2021-04-12 | 光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法 |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/016860 WO2021210162A1 (ja) | 2020-04-17 | 2020-04-17 | 光ファイバのための融着接続システム、融着接続機、及び光ファイバを融着接続する方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20230126843A1 (ja) |
EP (1) | EP4137851A4 (ja) |
JP (1) | JPWO2021210546A1 (ja) |
KR (1) | KR20230003501A (ja) |
CN (1) | CN115362399A (ja) |
WO (2) | WO2021210162A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4325261A1 (en) * | 2022-08-16 | 2024-02-21 | Fiberfox, Inc. | Apparatus and method for verifying optical fiber work using artificial intelligence |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567745A (zh) * | 2011-12-29 | 2012-07-11 | 北京航天时代光电科技有限公司 | 一种光纤熔接质量的自动检测方法 |
JP2015172736A (ja) * | 2014-02-19 | 2015-10-01 | ヤマハ株式会社 | 音声解析装置 |
JP2016097228A (ja) * | 2014-11-26 | 2016-05-30 | 株式会社日立システムズ | 行動分類システム、行動分類装置及び行動分類方法 |
JP2016152011A (ja) * | 2015-02-19 | 2016-08-22 | ファナック株式会社 | 制御装置の故障予測システム |
JP2019118940A (ja) * | 2018-01-09 | 2019-07-22 | ファナック株式会社 | ファイバレーザ装置及び機械学習装置 |
JP2020020997A (ja) | 2018-08-02 | 2020-02-06 | 古河電気工業株式会社 | 融着接続システム、融着接続機及び光ファイバ種判別方法 |
JP2020020998A (ja) | 2018-08-02 | 2020-02-06 | 古河電気工業株式会社 | 融着接続システム、融着接続機及び光ファイバの回転角判定方法 |
-
2020
- 2020-04-17 WO PCT/JP2020/016860 patent/WO2021210162A1/ja active Application Filing
-
2021
- 2021-04-12 JP JP2022515378A patent/JPWO2021210546A1/ja active Pending
- 2021-04-12 WO PCT/JP2021/015210 patent/WO2021210546A1/ja unknown
- 2021-04-12 US US17/907,686 patent/US20230126843A1/en active Pending
- 2021-04-12 EP EP21788759.5A patent/EP4137851A4/en active Pending
- 2021-04-12 KR KR1020227039189A patent/KR20230003501A/ko active Search and Examination
- 2021-04-12 CN CN202180027320.4A patent/CN115362399A/zh active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567745A (zh) * | 2011-12-29 | 2012-07-11 | 北京航天时代光电科技有限公司 | 一种光纤熔接质量的自动检测方法 |
JP2015172736A (ja) * | 2014-02-19 | 2015-10-01 | ヤマハ株式会社 | 音声解析装置 |
JP2016097228A (ja) * | 2014-11-26 | 2016-05-30 | 株式会社日立システムズ | 行動分類システム、行動分類装置及び行動分類方法 |
JP2016152011A (ja) * | 2015-02-19 | 2016-08-22 | ファナック株式会社 | 制御装置の故障予測システム |
JP2019118940A (ja) * | 2018-01-09 | 2019-07-22 | ファナック株式会社 | ファイバレーザ装置及び機械学習装置 |
JP2020020997A (ja) | 2018-08-02 | 2020-02-06 | 古河電気工業株式会社 | 融着接続システム、融着接続機及び光ファイバ種判別方法 |
JP2020020998A (ja) | 2018-08-02 | 2020-02-06 | 古河電気工業株式会社 | 融着接続システム、融着接続機及び光ファイバの回転角判定方法 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4325261A1 (en) * | 2022-08-16 | 2024-02-21 | Fiberfox, Inc. | Apparatus and method for verifying optical fiber work using artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN115362399A (zh) | 2022-11-18 |
EP4137851A4 (en) | 2023-09-20 |
JPWO2021210546A1 (ja) | 2021-10-21 |
KR20230003501A (ko) | 2023-01-06 |
WO2021210162A1 (ja) | 2021-10-21 |
US20230126843A1 (en) | 2023-04-27 |
EP4137851A1 (en) | 2023-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6943820B2 (ja) | 融着接続システム、融着接続機及び光ファイバの回転角判定方法 | |
JP4367597B2 (ja) | 融着接続装置および融着接続方法 | |
US20200056960A1 (en) | Fusion splicing system, fusion splicer and method of determining type of optical fiber | |
WO2021210546A1 (ja) | 光ファイバのための融着接続システム、融着接続機、モデル作成装置、及び光ファイバを融着接続する方法 | |
SE511966C2 (sv) | Förfarande och anordning för att hopskarva ändarna hos två optiska fibrer av olika typ med varandra | |
JP2012083635A (ja) | 光ファイバ融着接続方法 | |
TW463062B (en) | Determining optical fiber types | |
US11144603B2 (en) | Fusion condition providing system | |
WO2021210552A1 (ja) | 融着接続機、融着接続システム、及び光ファイバを融着接続する方法 | |
US7690850B2 (en) | Apparatus for splicing optical fibers | |
JP4032960B2 (ja) | 光ファイバ融着接続装置 | |
EP4105697A1 (en) | Optical fiber fusion splicer and method for fusion splicing optical fiber | |
Jackson | Mass fusion splicing of optical ribbon fiber: manufacturing process development | |
JP2003207682A (ja) | 光ファイバカプラ製造方法及び製造装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21788759 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022515378 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20227039189 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2021788759 Country of ref document: EP Effective date: 20221117 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |