Auxiliary roller control method, system, electronic device and storage medium

Abstract

The present disclosure provides an auxiliary roller control method, device, electronic device and storage medium, and relates to the field of computer technology. The specific implementation scheme is: for the auxiliary roller winding the fiber yarn in the first time period, photograph the surface of the auxiliary roller in contact with the fiber yarn to obtain an auxiliary roller image sequence; cut the auxiliary roller image sequence to obtain multiple sub-image sequences; perform image recognition on each sub-image sequence to obtain the thickness change of the fiber yarn in the second time period corresponding to each sub-image sequence and the axial movement range on the auxiliary roller; based on the thickness change of the fiber yarn in each second time period and the axial movement range on the auxiliary roller, determine the tension change of the fiber yarn in each second time period; when the tension change of the fiber yarn in each second time period does not meet the preset tension change condition, adjust the auxiliary roller speed to adjust the traction tension of the auxiliary roller on the fiber yarn.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more particularly to an auxiliary roller control method, system, electronic device and storage medium. Background Art

[0002] In the production process of chemical fiber DTY (Drawn-texturing yarn) products, a texturing machine is used to stretch, false-twist and wind POY (PRE-ORIENTED YARN) fiber yarns to generate the final DTYDTY spindles, among which rollers and auxiliary rollers are one of the important components in the production process. Summary of the invention

[0003] The present disclosure provides an auxiliary roller control method, system, electronic device and storage medium.

[0004] According to one aspect of the present disclosure, there is provided an auxiliary roller control method, comprising:

[0005] For the auxiliary roller that winds the fiber filament in the first time period, photograph the surface of the auxiliary roller that contacts the fiber filament to obtain an auxiliary roller image sequence;

[0006] Based on the timestamps of each image in the auxiliary roller image sequence, the auxiliary roller image sequence is divided to obtain a plurality of sub-image sequences, wherein the time lengths of the sub-image sequences are the same;

[0007] Performing image recognition on each of the sub-image sequences to obtain a change in thickness of the fiber yarn within a second time period corresponding to each of the sub-image sequences and an axial movement range on the auxiliary roller;

[0008] Determining the change in tension of the fiber filament in each of the second time periods based on the change in thickness of the fiber filament in each of the second time periods and the axial movement range of the auxiliary roller;

[0009] When the tension change of the fiber filament in each of the second time periods does not meet the preset tension change condition, the rotation speed of the auxiliary roller is adjusted to adjust the pulling force of the auxiliary roller on the fiber filament.

[0010] According to another aspect of the present disclosure, there is provided an auxiliary roller control device, comprising:

[0011] An image sequence acquisition module is used to photograph the surface of the auxiliary roller that is in contact with the fiber filament during the first time period to obtain an auxiliary roller image sequence;

[0012] An image sequence segmentation module, used for segmenting the auxiliary roller image sequence based on the timestamp of each image in the auxiliary roller image sequence to obtain a plurality of sub-image sequences, wherein the time length of each sub-image sequence is the same;

[0013] An image recognition module, used for performing image recognition on each of the sub-image sequences to obtain a change in thickness of the fiber yarn within a second time period corresponding to each of the sub-image sequences and an axial movement range on the auxiliary roller;

[0014] a tension determination module, configured to determine a change in the tension of the fiber yarn in each of the second time periods based on a change in the thickness of the fiber yarn in each of the second time periods and an axial movement range on the auxiliary roller;

[0015] A tension adjustment module is used to adjust the auxiliary roller speed to adjust the pulling tension of the auxiliary roller on the fiber yarn when the tension change of the fiber yarn in each of the second time periods does not meet the preset tension change conditions.

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

[0017] at least one processor; and

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

[0019] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any auxiliary roller control method in the embodiments of the present disclosure.

[0020] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any auxiliary roller control method according to the embodiments of the present disclosure.

[0021] According to the technology disclosed in the present invention, for the auxiliary roller winding the fiber yarn in the first time period, the surface of the auxiliary roller in contact with the fiber yarn is photographed to obtain an auxiliary roller image sequence; based on the timestamp of each image in the auxiliary roller image sequence, the auxiliary roller image sequence is segmented to obtain multiple sub-image sequences, wherein the time length of each sub-image sequence is the same; image recognition is performed on each sub-image sequence to obtain the thickness change of the fiber yarn in the second time period corresponding to each sub-image sequence and the axial movement range on the auxiliary roller; based on the thickness change of the fiber yarn in each second time period and the axial movement range on the auxiliary roller, the tension change of the fiber yarn in each second time period is determined; when the tension change of the fiber yarn in each second time period does not meet the preset tension change condition, the auxiliary roller speed is adjusted to adjust the traction tension of the auxiliary roller on the fiber yarn. In this way, the quality of the DTY ingot product finally generated can be improved.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0024] Figure 1 is a structural diagram of a roller and an auxiliary roller according to an embodiment of the present disclosure;

[0025] Figure 2 is a flow chart of an auxiliary roller control method according to an embodiment disclosed herein;

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

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

[0028] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0029] Figure 1 It is a structural diagram of a roller and an auxiliary roller according to an embodiment of the present disclosure.

[0030] like Figure 1 As shown in the structural diagram, a cylindrical roller 110 and a cylindrical auxiliary roller 120 are included. The auxiliary roller 120 is located above the roller 110 . The roller 110 and the auxiliary roller 120 cooperate with each other to wind the fiber filament 130 so that the fiber filament 130 can be stretched and wound on the auxiliary roller 120 .

[0031] Figure 2 4 is a flow chart of an auxiliary roller control method according to an embodiment of the present invention.

[0032] like Figure 2 As shown, the auxiliary roller control method may include:

[0033] S210, photographing the contact surface between the auxiliary roller and the fiber filaments for the auxiliary roller that winds the fiber filaments in the first time period to obtain an auxiliary roller image sequence;

[0034] S220, based on the timestamp of each image in the auxiliary roller image sequence, dividing the auxiliary roller image sequence to obtain a plurality of sub-image sequences, wherein the time length of each sub-image sequence is the same;

[0035] S230, performing image recognition on each sub-image sequence to obtain a change in thickness of the fiber yarn in a second time period corresponding to each sub-image sequence and an axial movement range on the auxiliary roller;

[0036] S240, determining a change in tension of the fiber filament in each second time period based on a change in thickness of the fiber filament in each second time period and an axial movement range of the fiber filament on the auxiliary roller;

[0037] S250, when the tension change of the fiber yarn in each second time period does not meet the preset tension change condition, adjust the rotation speed of the auxiliary roller to adjust the pulling force of the auxiliary roller on the fiber yarn.

[0038] It can be understood that when winding, the fiber filaments are wound around the surface of the auxiliary roller perpendicularly or nearly perpendicularly to the axial direction of the auxiliary roller. The fiber filaments are in contact with a portion of the surface of the auxiliary roller, so the portion of the surface in contact is photographed to obtain an auxiliary roller image sequence.

[0039] Exemplarily, the above steps S210 to S250 may be performed at a preset frequency.

[0040] Exemplarily, the length of the first time period may be 30 seconds or 1 minute.

[0041] Exemplarily, the time length of the first time period is greater than the time length of the second time period. The time lengths of the second time periods are the same, but at least one of the start time and the end time is different.

[0042] Exemplarily, the auxiliary roller image sequence may include multiple images arranged according to timestamps, and each sub-image sequence may include multiple images arranged according to timestamps. At least one of the timestamps of the first image and the last image in each sub-image sequence is different.

[0043] For example, a pre-trained neural network model can be used to perform image recognition on each sub-image sequence to obtain the thickness change of the fiber thread in the second time period corresponding to each sub-image sequence and the axial movement range of the fiber thread on the auxiliary roller. One model or two models can be used to respectively identify the thickness change of the fiber thread in the second time period corresponding to each sub-image sequence and the axial movement range of the fiber thread on the auxiliary roller in the second time period corresponding to each sub-image sequence.

[0044] Exemplarily, the neural network model can be a large language model or a long short-term memory model.

[0045] Exemplarily, the change in thickness may be a thickness that changes over time.

[0046] Exemplarily, the axial movement range may be an axial position that changes with time, and a boundary position of the axial displacement.

[0047] For example, the tension change may be a tension magnitude that changes over time.

[0048] For example, physical force simulation is performed on the change in thickness of the fiber filament in the second time period to obtain the initial tension change of the fiber filament in the second time period, and physical force simulation is performed on the axial movement range of the fiber filament on the auxiliary roller in the second time period to obtain the initial tension change of the fiber filament in the second time period. Then, the weighted average of these two initial tension changes can be obtained to obtain the final tension change of the fiber filament in the second time period.

[0049] Exemplarily, the tension change condition may be that the degree of deviation of the fiber yarn's tension change in any second time period from a preset tension change curve exceeds a preset threshold, or that the degree of deviation of the fiber yarn's tension change in any second time period in more than N second time periods from a preset tension change curve exceeds a preset threshold, where N is a positive integer.

[0050] For example, while adjusting the auxiliary roller rotation speed to adjust the pulling force of the auxiliary roller on the fiber filament, the fiber filament wound in the first time period can be removed, so that the quality of the DTY ingot product finally generated can be improved.

[0051] According to the above embodiment, for the auxiliary roller winding the fiber yarn in the first time period, the surface of the auxiliary roller in contact with the fiber yarn is photographed to obtain an auxiliary roller image sequence; based on the timestamp of each image in the auxiliary roller image sequence, the auxiliary roller image sequence is segmented to obtain multiple sub-image sequences, wherein the time length of each sub-image sequence is the same; image recognition is performed on each sub-image sequence to obtain the thickness change of the fiber yarn in the second time period corresponding to each sub-image sequence and the axial movement range on the auxiliary roller; based on the thickness change of the fiber yarn in each second time period and the axial movement range on the auxiliary roller, the tension change of the fiber yarn in each second time period is determined; when the tension change of the fiber yarn in each second time period does not meet the preset tension change condition, the auxiliary roller speed is adjusted to adjust the traction tension of the auxiliary roller on the fiber yarn. In this way, the quality of the DTY ingot product finally generated can be improved.

[0052] In one embodiment, image recognition is performed on each sub-image sequence to obtain the change in thickness of the fiber yarn in the second time period corresponding to each sub-image sequence and the axial movement range on the auxiliary roller, including: based on a first image recognition model, the sub-image sequence is recognized to obtain the change in thickness of the fiber yarn in the second time period corresponding to the sub-image sequence; based on a second image recognition model, the sub-image sequence is recognized to obtain the axial movement range of the fiber yarn on the auxiliary roller in the second time period corresponding to the sub-image sequence.

[0053] Exemplarily, the first image recognition model may be a model generated by pre-training using a large language model or a support vector machine model.

[0054] Exemplarily, the second image recognition model may also be a model generated by pre-training using a large language model or a support vector machine model.

[0055] According to the above embodiment, by using a neural network model to identify the sub-image sequence, the change in thickness of the fiber in the second time period corresponding to the sub-image sequence and the axial movement range of the fiber on the auxiliary roller in the second time period corresponding to the sub-image sequence can be obtained. In this way, the recognition accuracy can be improved.

[0056] In one embodiment, the above method may also include: obtaining a first training sample set, wherein the first training sample set includes multiple first training samples, the first training samples include first image sequence samples, and the thickness of fiber filaments in each image sample in the first image sequence samples; based on each first training sample, generating corresponding first prompt word samples respectively, wherein the input data of the first prompt word sample is the first image sequence sample in the corresponding first training sample and the thickness of fiber filaments in each image sample in the first image sequence samples, and the output data of the first prompt word sample is required to be the change in the thickness of fiber filaments in the first image sequence samples in the input data; based on each first prompt word sample, training a large language model to obtain a first image recognition model.

[0057] For example, a high-resolution industrial camera is used to continuously image fiber filaments in the textile production process to obtain a series of fiber filament image data. The image is denoised and enhanced through image preprocessing technology to improve image quality, laying the foundation for subsequent feature extraction.

[0058] Exemplarily, for the preprocessed fiber image, texture analysis methods such as wavelet transform and gray-level co-occurrence matrix are used to extract texture features that can reflect the changes in the thickness of the fiber, such as the mean and variance of the wavelet coefficients, the contrast and correlation of the gray-level co-occurrence matrix, and obtain a multi-dimensional feature vector of the fiber thickness.

[0059] For example, based on the continuity and gradual variation of fiber thickness, a convolutional neural network is used to construct a fiber thickness variation trend prediction model. The model is trained and optimized through a large amount of labeled sample data, so that it can accurately capture the spatiotemporal evolution of fiber thickness.

[0060] According to the above implementation, a first image recognition model can be trained to accurately predict the thickness of the fiber filaments in each image sample in the first image sequence sample.

[0061] In one embodiment, the above method may also include: obtaining a second training sample set, wherein the second training sample set includes multiple second training samples, the second training samples include second image sequence samples, and the axial position coordinates of the fiber filaments in each image sample in the second image sequence samples on the auxiliary roller; based on each second training sample, generating corresponding second prompt word samples respectively, wherein the input data of the second prompt word sample is the axial position coordinates of the fiber filaments in the second image sequence samples in the corresponding second training samples and each image sample in the second sequence samples on the auxiliary roller, and the output data of the second prompt word sample is required to be the axial movement range of the fiber filaments in the second image sequence samples in the input data on the auxiliary roller; based on each second prompt word sample, training a large language model to obtain a second image recognition model.

[0062] For example, multiple frames of continuous images of fiber yarns on auxiliary rollers during the DTY production process are obtained to construct a fiber yarn image sequence data set. The image sequence is denoised, enhanced, and standardized by an image preprocessing algorithm to obtain high-quality fiber yarn image sequence samples.

[0063] Exemplarily, in view of the complexity and variability of fiber filament images, a deep learning algorithm based on convolutional neural networks is used to construct a fiber filament image feature extraction model, which automatically learns the multi-scale and multi-directional texture features of fiber filament images to obtain a discriminative fiber filament image feature representation.

[0064] Exemplarily, a fiber filament axial position prediction model is constructed based on the fiber filament axial position coordinate data and the corresponding image sequence, and the image sequence is temporally modeled using a long short-term memory network. The nonlinear mapping relationship between the fiber filament movement law and the image sequence is mined to achieve end-to-end prediction from the image sequence to the axial position.

[0065] For example, during the training process, an active learning strategy is adopted to sample unlabeled data according to the uncertainty of model prediction, select the most informative samples for manual labeling, and iteratively update the training set to reduce the labeling cost while improving the generalization performance of the model.

[0066] According to the above implementation, a second image recognition model can be trained to accurately predict the axial movement range of the fiber filaments on the auxiliary roller in each image sample in the first image sequence sample.

[0067] In one embodiment, based on the change in thickness of the fiber filament in each second time period and the axial movement range of the fiber filament on the auxiliary roller in each second time period, the change in tension of the fiber filament in each second time period is determined, including: based on the change in thickness of the fiber filament in each second time period, respectively determining the first tension change acceleration of the fiber filament in each second time period; based on the axial movement range of the fiber filament on the auxiliary roller in each second time period, respectively determining the second tension change acceleration of the fiber filament in each second time period; based on the first tension change acceleration and the second tension change acceleration of the fiber filament in each second time period, determining the tension change of the fiber filament in each second time period.

[0068] Exemplarily, based on the change in thickness of the fiber filament in the second time period, the acceleration of the change in thickness of the fiber filament in the second time period is determined, thereby, based on the acceleration of the change in thickness of the fiber filament in the second time period, the acceleration of the change in the first tension of the fiber filament in the second time period can be determined;

[0069] Exemplarily, based on the axial movement range of the fiber yarn on the auxiliary roller in the second time period, the axial movement change acceleration of the fiber yarn in the second time period is determined, so that based on the axial movement change acceleration of the fiber yarn in the second time period, the first tension change acceleration of the fiber yarn in the second time period can be determined;

[0070] Exemplarily, the first tension change acceleration and the second tension change acceleration of the fiber filament in the second time period are weighted averaged, or the maximum value of the two is taken to obtain the target tension change acceleration. Based on the thickness of the fiber filament at the initial time in the second time period, the initial tension of the fiber filament at the initial time in the second time period is determined. Based on the target tension change acceleration and the initial tension, the tension change of the fiber filament in the second time period can be calculated.

[0071] According to the above embodiment, the tension variation of the fiber filament in each second time period can be accurately obtained.

[0072] Figure 3 It is a structural block diagram of an auxiliary roller control device according to an embodiment of the present disclosure.

[0073] like Figure 3 As shown, the auxiliary roller control device comprises:

[0074] An image sequence acquisition module 310 is used to photograph the surface of the auxiliary roller that is in contact with the fiber filament during the first time period to obtain an auxiliary roller image sequence;

[0075] An image sequence segmentation module 320, configured to segment the auxiliary roller image sequence based on the timestamp of each image in the auxiliary roller image sequence to obtain a plurality of sub-image sequences, wherein the time length of each sub-image sequence is the same;

[0076] An image recognition module 330 is used to perform image recognition on each of the sub-image sequences to obtain a change in thickness of the fiber yarn in a second time period corresponding to each of the sub-image sequences and an axial movement range on the auxiliary roller;

[0077] A tension determination module 340, configured to determine a change in tension of the fiber yarn in each of the second time periods based on a change in thickness of the fiber yarn in each of the second time periods and an axial movement range of the auxiliary roller;

[0078] The tension adjustment module 350 is used to adjust the rotation speed of the auxiliary roller to adjust the pulling tension of the auxiliary roller on the fiber yarn when the tension change of the fiber yarn in each of the second time periods does not meet the preset tension change conditions.

[0079] In one implementation, the image recognition module 330 includes:

[0080] A first recognition unit is used to recognize the sub-image sequence based on a first image recognition model to obtain a change in thickness of the fiber within a second time period corresponding to the sub-image sequence;

[0081] The second recognition unit is used to recognize the sub-image sequence based on a second image recognition model to obtain the axial movement range of the fiber yarn on the auxiliary roller within a second time period corresponding to the sub-image sequence.

[0082] In one embodiment, the above device further comprises:

[0083] A first sample set acquisition module, used to acquire a first training sample set, wherein the first training sample set includes a plurality of first training samples, the first training samples include a first image sequence sample, and the thickness of the fiber in each image sample in the first image sequence sample;

[0084] A first prompt word generation module is used to generate first prompt word samples corresponding to the first training samples, respectively, wherein the input data of the first prompt word samples are the first image sequence samples in the corresponding first training samples and the thickness of the fiber filaments in each image sample in the first image sequence samples, and the output data of the first prompt word samples is required to be the thickness change of the fiber filaments in the first image sequence samples in the input data;

[0085] The first training module is used to train a large language model based on each of the first prompt word samples to obtain the first image recognition model.

[0086] In one embodiment, the above device further comprises:

[0087] A second sample set acquisition module, configured to acquire a second training sample set, wherein the second training sample set includes a plurality of second training samples, and the second training samples include second image sequence samples, and axial position coordinates of fiber filaments in each image sample in the second image sequence samples on the auxiliary roller;

[0088] A second prompt word generation module is used to generate respective corresponding second prompt word samples based on respective second training samples, wherein the input data of the second prompt word samples are the axial position coordinates of the fiber filaments in the second image sequence samples and each image sample in the second sequence samples in the corresponding second training samples on the auxiliary roller, and the output data of the second prompt word samples is required to be the axial movement range of the fiber filaments in the second image sequence samples in the input data on the auxiliary roller;

[0089] The second training module is used to train a large language model based on each of the second prompt word samples to obtain the second image recognition model.

[0090] In one embodiment, the tension determination module 340 includes:

[0091] a first acceleration determination unit, configured to determine a first tension change acceleration of the fiber filament in each of the second time periods based on a change in thickness of the fiber filament in each of the second time periods;

[0092] a second acceleration determination unit, configured to determine the second tension change acceleration of the fiber yarn in each of the second time periods based on the axial movement range of the fiber yarn on the auxiliary roller in each of the second time periods;

[0093] The tension variation unit is used to determine the tension variation of the fiber yarn in each of the second time periods based on the first tension variation acceleration and the second tension variation acceleration of the fiber yarn in each of the second time periods.

[0094] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0095] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0096] Figure 4 FIG. 1 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, and the memory 410 stores a computer program that can be run on the processor 420. The number of memories 410 and processors 420 can be one or more. The memory 410 can store one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device executes the method provided by the above method embodiment. The electronic device may also include: a communication interface 430, which is used to communicate with external devices and perform data exchange transmission.

[0097] If the memory 410, the processor 420 and the communication interface 430 are implemented independently, the memory 410, the processor 420 and the communication interface 430 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0098] Optionally, in a specific implementation, if the memory 410, the processor 420 and the communication interface 430 are integrated on a chip, the memory 410, the processor 420 and the communication interface 430 can communicate with each other through an internal interface.

[0099] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0100] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of 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, the process or function described in the embodiment of the present disclosure is generated in whole or in part. 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 computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (for example: coaxial cable, optical fiber, data subscriber line (Digital Subscriber Line, DSL)) or wireless (for example: infrared, Bluetooth, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)), etc. It is worth noting that the computer-readable storage medium mentioned in the present disclosure may be a non-volatile storage medium, in other words, a non-transient storage medium.

[0102] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0103] In the description of the embodiments of the present disclosure, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0104] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means or, for example, A / B can mean A or B. "And / or" in this article is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0105] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0106] The above description is only an exemplary embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for controlling an auxiliary roller, characterized in that: include: For the auxiliary roller that winds the fiber filament in the first time period, photograph the surface of the auxiliary roller that contacts the fiber filament to obtain an auxiliary roller image sequence; Based on the timestamps of each image in the auxiliary roller image sequence, the auxiliary roller image sequence is divided to obtain a plurality of sub-image sequences, wherein the time lengths of the sub-image sequences are the same; Performing image recognition on each of the sub-image sequences to obtain a change in thickness of the fiber yarn within a second time period corresponding to each of the sub-image sequences and an axial movement range on the auxiliary roller; Based on the change in thickness of the fiber yarn in each of the second time periods and the axial movement range on the auxiliary roller, determining the change in tension of the fiber yarn in each of the second time periods, including: determining the first tension change acceleration of the fiber yarn in each of the second time periods based on the change in thickness of the fiber yarn in each of the second time periods; determining the second tension change acceleration of the fiber yarn in each of the second time periods based on the axial movement range of the fiber yarn on the auxiliary roller in each of the second time periods; determining the tension change of the fiber yarn in each of the second time periods based on the first tension change acceleration and the second tension change acceleration of the fiber yarn in each of the second time periods; When the tension change of the fiber filament in each of the second time periods does not meet the preset tension change condition, the rotation speed of the auxiliary roller is adjusted to adjust the pulling force of the auxiliary roller on the fiber filament.

2. The method according to claim 1, characterized in that The performing image recognition on each of the sub-image sequences to obtain the thickness change of the fiber yarn in the second time period corresponding to each of the sub-image sequences and the axial movement range on the auxiliary roller includes: Based on the first image recognition model, the sub-image sequence is recognized to obtain the thickness change of the fiber within the second time period corresponding to the sub-image sequence; The sub-image sequence is recognized based on a second image recognition model to obtain an axial movement range of the fiber yarn on the auxiliary roller within a second time period corresponding to the sub-image sequence.

3. The method according to claim 2, characterized in that Also includes: Acquire a first training sample set, wherein the first training sample set includes a plurality of first training samples, the first training samples include a first image sequence sample, and the thickness of the fiber in each image sample in the first image sequence sample; Based on each of the first training samples, respectively generate first prompt word samples corresponding to each other, wherein the input data of the first prompt word samples are the first image sequence samples in the corresponding first training samples and the thickness of the fiber filaments in each image sample in the first image sequence samples, and the output data of the first prompt word samples is required to be the thickness change of the fiber filaments in the first image sequence samples in the input data; Based on each of the first prompt word samples, a large language model is trained to obtain the first image recognition model.

4. The method according to claim 2, characterized in that: Also includes: Acquire a second training sample set, wherein the second training sample set includes a plurality of second training samples, the second training samples include second image sequence samples, and axial position coordinates of fiber filaments in each image sample in the second image sequence samples on the auxiliary roller; Based on each of the second training samples, respectively generate corresponding second prompt word samples, wherein the input data of the second prompt word sample is the axial position coordinates of the fiber filaments in the second image sequence sample and each image sample in the second image sequence sample in the corresponding second training sample on the auxiliary roller, and the output data of the second prompt word sample is required to be the axial movement range of the fiber filaments in the second image sequence sample in the input data on the auxiliary roller; Based on each of the second prompt word samples, a large language model is trained to obtain the second image recognition model.

5. An auxiliary roller control device, characterized in that: include: An image sequence acquisition module is used to photograph the surface of the auxiliary roller that is in contact with the fiber filament during the first time period to obtain an auxiliary roller image sequence; An image sequence segmentation module, used for segmenting the auxiliary roller image sequence based on the timestamp of each image in the auxiliary roller image sequence to obtain a plurality of sub-image sequences, wherein the time length of each sub-image sequence is the same; An image recognition module, used for performing image recognition on each of the sub-image sequences to obtain a change in thickness of the fiber yarn within a second time period corresponding to each of the sub-image sequences and an axial movement range on the auxiliary roller; a tension determination module, configured to determine a change in the tension of the fiber yarn in each of the second time periods based on a change in the thickness of the fiber yarn in each of the second time periods and an axial movement range on the auxiliary roller; A tension adjustment module, used for adjusting the rotation speed of the auxiliary roller to adjust the pulling tension of the auxiliary roller on the fiber filament when the tension change of the fiber filament in each of the second time periods does not meet the preset tension change condition; Wherein, the tension determination module comprises: a first acceleration determination unit, configured to determine a first tension change acceleration of the fiber filament in each of the second time periods based on a change in thickness of the fiber filament in each of the second time periods; a second acceleration determination unit, configured to determine the second tension change acceleration of the fiber yarn in each of the second time periods based on the axial movement range of the fiber yarn on the auxiliary roller in each of the second time periods; The tension variation unit is used to determine the tension variation of the fiber yarn in each of the second time periods based on the first tension variation acceleration and the second tension variation acceleration of the fiber yarn in each of the second time periods.

6. The device according to claim 5, characterized in that The image recognition module comprises: A first recognition unit is used to recognize the sub-image sequence based on a first image recognition model to obtain a change in thickness of the fiber within a second time period corresponding to the sub-image sequence; The second recognition unit is used to recognize the sub-image sequence based on a second image recognition model to obtain the axial movement range of the fiber yarn on the auxiliary roller within a second time period corresponding to the sub-image sequence.

7. The device according to claim 5, characterized in that Also includes: A first sample set acquisition module, used to acquire a first training sample set, wherein the first training sample set includes a plurality of first training samples, the first training samples include a first image sequence sample, and the thickness of the fiber in each image sample in the first image sequence sample; A first prompt word generation module is used to generate first prompt word samples corresponding to the first training samples, respectively, wherein the input data of the first prompt word samples are the first image sequence samples in the corresponding first training samples and the thickness of the fiber filaments in each image sample in the first image sequence samples, and the output data of the first prompt word samples is required to be the thickness change of the fiber filaments in the first image sequence samples in the input data; The first training module is used to train a large language model based on each of the first prompt word samples to obtain a first image recognition model.

8. The device according to claim 5, characterized in that Also includes: A second sample set acquisition module, configured to acquire a second training sample set, wherein the second training sample set includes a plurality of second training samples, and the second training samples include second image sequence samples, and axial position coordinates of fiber filaments in each image sample in the second image sequence samples on the auxiliary roller; A second prompt word generation module is used to generate respective corresponding second prompt word samples based on respective second training samples, wherein the input data of the second prompt word samples are the axial position coordinates of the fiber filaments in the second image sequence samples and each image sample in the second image sequence samples in the corresponding second training samples on the auxiliary roller, and the output data of the second prompt word samples is required to be the axial movement range of the fiber filaments in the second image sequence samples in the input data on the auxiliary roller; The second training module is used to train a large language model based on each of the second prompt word samples to obtain a second image recognition model.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed 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 according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-4.

Images