Fiber filament oiling control method and device, electronic device and storage medium

Abstract

The present disclosure provides a fiber yarn oiling control method and device, electronic equipment and storage medium, relating to the technical field of computer. The implementation scheme is: an oil wheel for oiling a fiber tow in a first time period is photographed to obtain an oil wheel image sequence; an oil wheel image sequence is identified based on a first image recognition model to obtain an axial movement range of the fiber tow on the oil wheel; in a case where the axial movement range of the fiber tow on the oil wheel exceeds a preset axial movement range, the oil wheel image sequence is identified based on a second image recognition model to obtain a thickness degree of the fiber tow, and the oil wheel image sequence is identified based on a third image recognition model to obtain a surface roughness degree of the oil wheel; a target oiling amount of the fiber tow is determined based on the thickness degree of the fiber tow and the surface roughness degree of the oil wheel; and a spraying operation of the oiling mechanism on the oil wheel is adjusted based on the target oiling amount of the fiber tow.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology. Specifically, it relates to methods, apparatus, electronic devices, and storage media for controlling the oiling of fiber filaments. Background Technology

[0002] During the production of chemical fiber filaments, the filament bundle needs to be oiled to improve its lubricity, cohesion, processing performance, and usability, as well as to eliminate static electricity. The choice of oil type and oiling method has a significant impact on the spinning process and fiber quality. Because oiling with an oiling wheel provides better uniformity of oiling, this method is generally used. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for controlling the oiling of fiber filaments.

[0004] According to one aspect of this disclosure, a method for controlling oiling of fiber filaments is provided, comprising:

[0005] For the oiler that applies oil to the fiber bundle during the first time period, the surface of the oiler in contact with the fiber bundle is photographed to obtain an image sequence of the oiler;

[0006] Based on the first image recognition model, the image sequence of the oil tanker is identified to obtain the axial movement range of the fiber bundle on the oil tanker;

[0007] When the axial movement range of the fiber bundle on the tanker exceeds the preset axial movement range, the tanker image sequence is identified based on the second image recognition model to obtain the thickness of the fiber bundle, and the tanker image sequence is identified based on the third image recognition model to obtain the surface roughness of the tanker.

[0008] The target oil application amount of the fiber bundle is determined based on the thickness of the fiber bundle and the surface roughness of the oil tanker.

[0009] Based on the target oil application amount of the fiber bundle, adjust the oiling mechanism's oil spraying operation on the oil tanker.

[0010] According to another aspect of this disclosure, a fiber oiling control device is provided, comprising:

[0011] The image sequence determination module is used to capture images of the surface of the oiler in contact with the fiber bundle during a first time period, for an oiler that applies oil to the fiber bundle during a first time period, to obtain an image sequence of the oiler.

[0012] An axial range determination module is used to identify the oil tanker image sequence based on a first image recognition model to obtain the axial movement range of the fiber bundle on the oil tanker.

[0013] The degree determination module is used to identify the oil tanker image sequence based on a second image recognition model to obtain the thickness of the fiber bundle when the axial movement range of the fiber bundle on the oil tanker exceeds a preset axial movement range, and to identify the oil tanker image sequence based on a third image recognition model to obtain the surface roughness of the oil tanker.

[0014] The oil application amount determination module is used to determine the target oil application amount of the fiber bundle based on the thickness of the fiber bundle and the surface roughness of the oil tanker;

[0015] The oil injection adjustment module is used to adjust the oil injection operation of the oiling mechanism on the oil tanker based on the target oil amount of the fiber bundle.

[0016] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] The memory is communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any fiber oiling control method in the embodiments of this disclosure.

[0020] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any fiber oiling control method according to an embodiment of this disclosure.

[0021] According to the technology disclosed herein, for an oil tanker that applies oil to fiber bundles during a first time period, images of the surface of the oil tanker in contact with the fiber bundles are captured to obtain an image sequence of the oil tanker. Based on a first image recognition model, the image sequence of the oil tanker is recognized to obtain the axial movement range of the fiber bundles on the oil tanker. If the axial movement range of the fiber bundles on the oil tanker exceeds a preset axial movement range, the image sequence of the oil tanker is recognized based on a second image recognition model to obtain the thickness of the fiber bundles, and the image sequence of the oil tanker is recognized based on a third image recognition model to obtain the surface roughness of the oil tanker. Based on the thickness of the fiber bundles and the surface roughness of the oil tanker, the target amount of oil applied to the fiber bundles is determined. Based on the target amount of oil applied to the fiber bundles, the oiling mechanism adjusts its oil spraying operation on the oil tanker. Thus, by detecting the axial movement range of the fiber bundles through images, if the axial movement range exceeds the preset axial movement range, it means that the amount of oil applied to the fiber bundles is insufficient, and the amount of oil applied needs to be adjusted. Furthermore, by detecting the thickness of the fiber bundles and the surface roughness of the oiler through image analysis, the corresponding target amount of oil can be determined, so that the fiber bundles can be oiled evenly, thereby improving the quality of the oiled fiber bundles.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a schematic diagram of applying oil to a fiber bundle on an oil tanker according to an embodiment of the present disclosure;

[0025] Figure 2 This is a flowchart of a fiber oiling control method according to an embodiment of the present disclosure;

[0026] Figure 3 This is a structural block diagram of a fiber oiling control device according to an embodiment of the present disclosure;

[0027] Figure 4 This is a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] Figure 1 This is a schematic diagram of an embodiment of the present disclosure of a fiber bundle being oiled on an oil tanker.

[0030] like Figure 1 As shown in the figure, the two parallel cylindrical objects are oil rollers 110, and the object in contact with the two oil rollers 110 is a fixed rotating shaft 120. The fiber bundle 130 is oiled by means of the oil rollers, so that the fiber bundle 130 can be oiled evenly and the lubrication of the fiber bundle can be improved.

[0031] Figure 2 This is a flowchart of an auxiliary roller control method according to an embodiment disclosed herein.

[0032] like Figure 2 As shown, the method for controlling the oiling of the fiber filaments may include:

[0033] S210, for the oiler that applies oil to the fiber bundle during the first time period, the surface of the oiler in contact with the fiber bundle is photographed to obtain an image sequence of the oiler;

[0034] S220, based on the first image recognition model, identifies the tanker image sequence to obtain the axial movement range of the fiber bundle on the tanker;

[0035] S230, when the axial movement range of the fiber bundle on the tanker exceeds the preset axial movement range, the tanker image sequence is identified based on the second image recognition model to obtain the thickness of the fiber bundle, and the tanker image sequence is identified based on the third image recognition model to obtain the surface roughness of the tanker.

[0036] S240, based on the thickness of the fiber bundle and the surface roughness of the tanker, determines the target oil application amount of the fiber bundle;

[0037] S250 adjusts the oiling mechanism's oiling operation on the tanker based on the target oiling amount of the fiber bundle.

[0038] For example, the first time period can be 30 seconds, 1 minute, or 2 minutes, and there is no limitation thereto. It should be noted that the amount of oil added during this time period should be adjusted to ensure that the liquid level in the oil tank remains constant.

[0039] For example, a tanker image sequence may include multiple images taken from the same angle and arranged in chronological order.

[0040] For example, the first image recognition model may be a pre-trained model used to identify the position information of fiber bundles in the input image.

[0041] For example, a first training sample set is obtained, wherein the training samples in the first training sample set include the input image and the axial position information of the fiber bundles in the input image on the tanker. Using the first training sample set, a neural network is trained to obtain a first image recognition model. For example, the neural network can be FCN (Fully Convolutional Networks), RefineNet (Multi-Path Thinning Network), or SegNet image segmentation network, etc.

[0042] For example, if the axial movement range of the fiber bundle on the tanker exceeds the preset axial movement range, it means that the amount of oil applied to the fiber bundle is insufficient, causing its position to deviate from the preset axial movement range during oiling. If the axial movement range of the fiber bundle on the tanker does not exceed the preset axial movement range, it means that the amount of oil applied to the fiber bundle is sufficient, and subsequent steps are unnecessary.

[0043] Understandably, the aforementioned axial direction refers to the direction parallel to the tanker's axial direction.

[0044] For example, when the amount of oil applied to the fiber bundle is insufficient, it is necessary to adjust the amount of oil applied to the fiber bundle or adjust the oiling method to increase the amount of oil applied to the fiber bundle.

[0045] For example, the amount of oil required varies depending on the thickness of the fiber bundle. Generally, the thicker the fiber bundle, the greater the daily oil consumption and the larger the amount of oil applied.

[0046] For example, the degree of influence on the amount of oil applied to the fiber bundle varies depending on the surface roughness of the oil tanker. The rougher the surface of the oil tanker, the smaller the frictional contact area between the fiber bundle and the oil tanker, and the less oil can be applied to the fiber bundle. Therefore, when the surface of the oil tanker becomes rougher, it is necessary to increase the amount of oil applied to the fiber bundle.

[0047] For example, the roughness of the fiber bundle and the surface roughness of the tanker can be identified by image recognition.

[0048] For example, the second image recognition model can be a pre-trained model. The second image recognition model is used to identify the roughness of the fiber bundles in the input image.

[0049] For example, a second training sample set is obtained, wherein the training samples in the second training sample set include the input image and the thickness of the fiber bundles in the input image. Using the second training sample set, the neural network is trained to obtain a second image recognition model. For example, the neural network can be FCN (Fully Convolutional Networks), RefineNet (Multi-Path Thinning Network), or SegNet image segmentation network, etc.

[0050] For example, a third training sample set is obtained, where training samples include the input image and the surface roughness of the oil tanker in the input image. Using this third training sample set, the neural network is trained to obtain a third image recognition model. For example, the neural network could be FCN (Fully Convolutional Networks), RefineNet (Multi-Path Refinement Network), or SegNet image segmentation network, etc.

[0051] For example, a mapping function or a table can be used to pre-record the relationship between the thickness of the fiber bundle and the surface roughness of the oiler and the amount of oil applied to the fiber bundle.

[0052] For example, the thickness of the fiber bundle and the surface roughness of the oil tanker can be processed using a mapping function or table to obtain the target oiling amount of the fiber bundle.

[0053] For example, based on the target oiling amount of the fiber bundle, the amount of oil sprayed by the oiling mechanism to the tanker can be directly adjusted, or the oiling angle or oiling distance of the oiling mechanism can be adjusted, thereby indirectly increasing the amount of oil sprayed to the tanker.

[0054] According to the above implementation method, the axial movement range of the fiber bundle is detected by image analysis. If the axial movement range exceeds the preset axial movement range, it means that the amount of oil applied to the fiber bundle is insufficient, and the amount of oil applied needs to be adjusted. Furthermore, the thickness of the fiber bundle and the surface roughness of the oiling wheel are detected by image analysis to determine the corresponding target amount of oil, so that the fiber bundle can be oiled evenly, thereby improving the quality of the oiled fiber bundle.

[0055] In one embodiment, determining the target oiling amount of the fiber bundle based on the thickness of the fiber bundle and the surface roughness of the tanker includes: searching for the corresponding oiling amount in a pre-established database of the relationship between fiber bundle thickness, tanker surface roughness and oiling amount based on the thickness of the fiber bundle and the surface roughness of the tanker; and determining the target oiling amount of the fiber bundle based on the found oiling amount.

[0056] For example, a multivariate function can be used to fit multiple data pairs related to the fiber bundle thickness, the tanker surface roughness, and the amount of oil applied, resulting in a mapping function. Then, by inputting the fiber bundle thickness and the tanker surface roughness into the mapping function and calculating the mapping function, the target amount of oil applied to the fiber bundle can be obtained.

[0057] For example, the least squares method can be used to fit the above multiple data pairs to obtain the above mapping function.

[0058] For example, the found oiling amount is compared with the current oiling amount. If the found oiling amount is greater than the current oiling amount and the difference between the found oiling amount and the current oiling amount is within a first range, then the sum of the product of the first coefficient and the difference and the current oiling amount is taken as the target oiling amount for the fiber bundle. If the difference is within a second range, the found oiling amount is taken as the target oiling amount for the fiber bundle. Here, the first range is greater than the second range, and the first coefficient is greater than 1.

[0059] According to the above implementation method, based on the thickness of the fiber bundle and the surface roughness of the oil tanker, the corresponding oiling amount is searched in a pre-established database of the relationship between fiber bundle thickness, oil tanker surface roughness, and oiling amount; based on the searched oiling amount, the target oiling amount of the fiber bundle is determined. In this way, the required oiling amount of the fiber bundle can be accurately predicted, improving the oiling quality of the fiber bundle.

[0060] In one embodiment, based on a first image recognition model, the image sequence of the oil tanker is identified to obtain the axial movement range of the fiber bundle on the oil tanker, including: based on the first image recognition model, each image in the oil tanker image sequence is identified to obtain the axial position of the fiber bundle on the oil tanker in each image; and based on the axial position of the fiber bundle on the oil tanker in each image, the axial movement range of the fiber bundle on the oil tanker is determined.

[0061] Understandably, the images in the tanker image sequence are taken from the same angle, thus improving the accuracy of determining the axial movement range of the fiber bundle on the tanker.

[0062] For example, the range of axial movement of the fiber bundle on the tanker is determined based on the farthest and nearest positions of the fiber bundle on the tanker in the axial positions of the individual images.

[0063] According to the above embodiments, the axial movement range of the fiber bundle on the tanker can be accurately determined by image recognition.

[0064] In one embodiment, the thickness of the fiber bundle is obtained by recognizing the oil tanker image sequence based on a second image recognition model, including: recognizing each image in the oil tanker image sequence based on the second image recognition model to obtain the thickness of the fiber bundle in each image; and determining the thickness of the fiber bundle based on the thickness of the fiber bundle in each image.

[0065] For example, the thickness of the fiber bundle is obtained by averaging the thickness of the fiber bundle in each image.

[0066] For example, the median is determined from the thickness of the fiber bundle in each image, and this median is used as the thickness of the fiber bundle.

[0067] According to the above embodiments, the thickness of the fiber bundle can be accurately determined by image recognition.

[0068] In one embodiment, the surface roughness of the oil tanker is obtained by recognizing the oil tanker image sequence based on a third image recognition model, including: recognizing each image in the oil tanker image sequence based on the third image recognition model to obtain the surface roughness of the oil tanker in each image; and determining the surface roughness of the oil tanker based on the surface roughness of the oil tanker in each image.

[0069] For example, the surface roughness of the tanker is obtained by averaging the surface roughness of the tanker in each image.

[0070] For example, the median of the surface roughness of the tanker in each image is determined and used as the surface roughness of the tanker.

[0071] According to the above implementation method, the surface roughness of the tanker can be accurately determined by image recognition.

[0072] Figure 3 This is a structural block diagram of a fiber oiling control device according to an embodiment of the present disclosure.

[0073] like Figure 3 As shown, the fiber oiling control device may include:

[0074] The image sequence determination module 310 is used to capture images of the surface of the oiler in contact with the fiber bundle during a first time period, for an oiler that applies oil to the fiber bundle during a first time period, to obtain an image sequence of the oiler.

[0075] The axial range determination module 320 is used to identify the oil tanker image sequence based on the first image recognition model to obtain the axial movement range of the fiber bundle on the oil tanker;

[0076] The degree determination module 330 is used to identify the oil tanker image sequence based on a second image recognition model to obtain the thickness of the fiber bundle when the axial movement range of the fiber bundle on the oil tanker exceeds a preset axial movement range, and to identify the oil tanker image sequence based on a third image recognition model to obtain the surface roughness of the oil tanker.

[0077] The oil application amount determination module 340 is used to determine the target oil application amount of the fiber bundle based on the thickness of the fiber bundle and the surface roughness of the oil tanker.

[0078] The oil injection adjustment module 350 is used to adjust the oil injection operation of the oiling mechanism on the oil tanker based on the target oiling amount of the fiber bundle.

[0079] In one embodiment, the oil application amount determination module includes:

[0080] The oil application amount lookup unit is used to look up the corresponding oil application amount based on the thickness of the fiber bundle and the surface roughness of the oil tanker in a pre-established database of the relationship between fiber bundle thickness, oil tanker surface roughness and oil application amount.

[0081] The target amount determination unit is used to determine the target amount of oil applied to the fiber bundle based on the found amount of oil applied.

[0082] In one embodiment, the axial range determination module includes:

[0083] An axial position determination unit is used to identify each image in the oil tanker image sequence based on the first image recognition model, and obtain the axial position of the fiber bundle in each image on the oil tanker.

[0084] The range determination unit is used to determine the axial movement range of the fiber bundle on the oil tanker based on the axial position of the fiber bundle on the oil tanker in each of the images.

[0085] In one embodiment, the degree determination module 330 includes:

[0086] The first model recognition unit is used to recognize each image in the oil tanker image sequence based on the second image recognition model, and to obtain the thickness of the fiber bundle in each image;

[0087] A thickness determination unit is used to determine the thickness of the fiber bundle based on the thickness of the fiber bundle in each of the images.

[0088] In one embodiment, the degree determination module 330 includes:

[0089] The second model recognition unit is used to recognize each image in the oil tanker image sequence based on the third image recognition model, and to obtain the surface roughness of the oil tanker in each image;

[0090] A roughness determination unit is used to determine the surface roughness of the tanker based on the surface roughness of the tanker in each of the images.

[0091] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0093] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Figure 4 As shown, the electronic device includes a memory 410 and a processor 420. The memory 410 stores a computer program that can run on the processor 420. There can be one or more memories 410 and processors 420. The memory 410 can store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the methods provided in the above-described method embodiments. The electronic device may also include a communication interface 430 for communicating with external devices and performing data exchange and transmission.

[0094] If the memory 410, processor 420, and communication interface 430 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0095] Optionally, in a specific implementation, if the memory 410, processor 420 and communication interface 430 are integrated on a single chip, the memory 410, processor 420 and communication interface 430 can communicate with each other through an internal interface.

[0096] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0097] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAMBUS RAM (DR RAM).

[0098] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line, DSL) or wireless (e.g., infrared, Bluetooth, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer, or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)). It is worth noting that the computer-readable storage media mentioned in this disclosure can be non-volatile storage media; in other words, it can be non-transient storage media.

[0099] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0100] In the description of the embodiments of this disclosure, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0101] In the description of the embodiments disclosed herein, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0102] In the description of embodiments of this disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0103] The above description is merely an exemplary embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A method of controlling oiling of a fiber filament, characterized by, The method comprises: An oil wheel image sequence is obtained by photographing the surface of the oil wheel in contact with the fiber tow during the first time period; An axial movement range of the fiber tow on the oil wheel is obtained by identifying the oil wheel image sequence based on a first image recognition model; In a case where the axial movement range of the fiber tow on the oil wheel exceeds a preset axial movement range, a thickness of the fiber tow is obtained by identifying the oil wheel image sequence based on a second image recognition model, and a surface roughness of the oil wheel is obtained by identifying the oil wheel image sequence based on a third image recognition model; A target oiling amount of the fiber tow is determined based on the thickness of the fiber tow and the surface roughness of the oil wheel; The oiling operation of the oil wheel by the oiling mechanism is adjusted based on the target oiling amount of the fiber tow.

2. The method of claim 1, wherein, The target oiling amount of the fiber tow is determined based on the thickness of the fiber tow and the surface roughness of the oil wheel, and the method comprises: The corresponding oiling amount is searched in a pre-established relationship database between the thickness of the fiber tow, the surface roughness of the oil wheel and the oiling amount based on the thickness of the fiber tow and the surface roughness of the oil wheel; The target oiling amount of the fiber tow is determined based on the searched oiling amount.

3. The method of claim 1, wherein, The axial movement range of the fiber tow on the oil wheel is obtained by identifying the oil wheel image sequence based on the first image recognition model, and the method comprises: The axial position of the fiber tow on the oil wheel in each of the images is obtained by identifying each of the images in the oil wheel image sequence based on the first image recognition model; The axial movement range of the fiber tow on the oil wheel is determined based on the axial position of the fiber tow on the oil wheel in each of the images.

4. The method of claim 1, wherein, The thickness of the fiber tow is obtained by identifying the oil wheel image sequence based on the second image recognition model, and the method comprises: The thickness of the fiber tow in each of the images is obtained by identifying each of the images in the oil wheel image sequence based on the second image recognition model; The thickness of the fiber tow is determined based on the thickness of the fiber tow in each of the images.

5. The method of claim 1, wherein, The surface roughness of the oil wheel is obtained by identifying the oil wheel image sequence based on the third image recognition model, and the method comprises: The surface roughness of the oil wheel in each of the images is obtained by identifying each of the images in the oil wheel image sequence based on the third image recognition model; The surface roughness of the oil wheel is determined based on the surface roughness of the oil wheel in each of the images.

6. A fiber oiling control device characterized by, The method comprises: An oil wheel image sequence is obtained by photographing the surface of the oil wheel in contact with the fiber tow during the first time period; An axial movement range of the fiber tow on the oil wheel is obtained by identifying the oil wheel image sequence based on a first image recognition model; a degree determination module, configured to, in a case where an axial movement range of the fiber tow on the oil roller exceeds a preset axial movement range, identify the oil roller image sequence based on a second image recognition model to obtain a thickness degree of the fiber tow, and identify the oil roller image sequence based on a third image recognition model to obtain a surface roughness degree of the oil roller; an oiling amount determination module, configured to determine a target oiling amount of the fiber tow based on the thickness degree of the fiber tow and the surface roughness degree of the oil roller; an oil injection adjustment module, configured to adjust oil injection operation of the oiling mechanism on the oil roller based on the target oiling amount of the fiber tow.

7. The apparatus of claim 6, wherein, The oiling amount determination module comprises: an oiling amount searching unit, configured to search for a corresponding oiling amount in a pre-established relationship database between fiber tow thickness degrees, oil roller surface roughness degrees, and oiling amounts, based on the thickness degree of the fiber tow and the surface roughness degree of the oil roller; a target amount determination unit, configured to determine the target oiling amount of the fiber tow based on the searched oiling amount.

8. The apparatus of claim 6, wherein, The axial range determination module comprises: an axial position determination unit, configured to identify each image in the oil roller image sequence based on the first image recognition model to obtain an axial position of the fiber tow on the oil roller in each image; a range determination unit, configured to determine the axial movement range of the fiber tow on the oil roller based on the axial position of the fiber tow on the oil roller in each image.

9. An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

10. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-5.

Images