Intelligent numerical control method and device for polyester filament splicing equipment and related equipment

Abstract

The application provides a kind of intelligent numerical control method, device and related equipment of dacron silk shovel plate equipment, it is related to the technical field of spinning production.The method comprises: obtaining the monitoring image of target spinneret, wherein the target spinneret is one of the multiple spinnerets included in spinning workshop;Image detection is carried out on the monitoring image to obtain an image detection result;When the image detection result indicates that the target spinneret meets the shovel plate condition, the target spinneret is processed based on the preset intelligent shovel plate component.The application acquires the monitoring image of the spinneret, and carries out image detection on the monitoring image, to determine whether the corresponding spinneret meets the shovel plate condition according to the image detection result, and if it meets, the spinneret is processed based on the intelligent shovel plate component.Based on the above setting, the working time of the intelligent shovel plate component can be more flexible, and the overall spinning quality of the spinning workshop can be improved.

Description

Technical Field

[0001] This invention relates to the technical field of spinning production, specifically to an intelligent numerical control method, device, and related equipment for a polyester filament scraper. Background Technology

[0002] The spinneret is an important part of the spinning machine in the chemical fiber industry. During the spinning process, polymers decompose at high temperatures, producing monomers that adhere to the surface of the spinneret. In order to ensure the spinnability and quality stability of chemical fiber, the surface of the spinneret needs to be scraped regularly.

[0003] In the existing technology, although the scraping of the adhesive on the spinneret surface can be accomplished by an automatic scraping device, the scraping device usually only performs the scraping work during a preset time period. The preset time period is mostly set manually, which has a large degree of uncertainty. It is easy for the adhesive to seriously affect the spinneret quality, but the scraping device is still not working.

[0004] In other words, existing CNC solutions for shovel plate equipment lack effective management of the equipment's working time. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent numerical control method, device, and related equipment for a polyester filament scraper, which solves the technical problem that existing numerical control solutions for scraper equipment lack effective management of the scraper's working time.

[0006] In a first aspect, embodiments of the present invention provide an intelligent numerical control method for a polyester filament scraper device, the method comprising:

[0007] Acquire a monitoring image of the target spinneret, wherein the target spinneret is one of multiple spinnerets included in the spinning workshop;

[0008] The monitored image is subjected to image detection to obtain the image detection result;

[0009] When the image detection result indicates that the target spinneret meets the scraping condition, the target spinneret is scraped based on a preset intelligent scraping component.

[0010] In one embodiment, performing image detection on the monitored image to obtain the image detection result includes:

[0011] Based on the first position information corresponding to the target spinneret, a target image block is extracted from the monitoring image, wherein the first position information is used to indicate the position of the image area corresponding to the target spinneret in the monitoring image;

[0012] Based on the second position information corresponding to the target spinneret, a mask is applied to the pixel region corresponding to the spinneret hole in the target image block to obtain a masked image block. The second position information is used to indicate the position of the pixel region corresponding to the spinneret hole in the target spinneret in the target image block.

[0013] Image detection is performed on the mask image block to obtain the image detection result.

[0014] In one embodiment, performing image detection on the mask image patch to obtain the image detection result includes:

[0015] Based on a pre-trained target model, feature extraction is performed on the mask image patch to obtain the first feature;

[0016] The first feature and the plurality of second features are respectively subjected to feature similarity calculation to obtain a plurality of similarity values ​​corresponding one-to-one with the plurality of second features. The second feature is used to represent the image features of the spinneret under abnormal production conditions. The larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature.

[0017] When at least one target similarity value is included among the plurality of similarity values, an image detection result indicating that the target spinneret meets the scraping condition is generated, wherein the target similarity value is the similarity value that is greater than or equal to a preset similarity threshold;

[0018] If the target similarity value is not included among the plurality of similarity values, an image detection result indicating that the target spinneret does not meet the shovel condition is generated.

[0019] In one embodiment, before extracting features from the mask image patch based on a pre-trained target model to obtain the first feature, the method further includes:

[0020] Multiple abnormal image blocks are acquired, wherein the abnormal image blocks are image blocks of spinnerets under abnormal production conditions. If the decrease in the spinneret quality is greater than or equal to a set decrease threshold, the spinneret is determined to be under abnormal production conditions.

[0021] Based on the target model, feature extraction is performed on the multiple abnormal image blocks to obtain the multiple second features.

[0022] In one embodiment, the smart scraper assembly includes a scraper and an audio sensor;

[0023] The method of scraping the target spinneret using a preset intelligent scraper assembly includes:

[0024] The scraper is used to scrape the target spinneret, and the audio sensor is used to collect the audio to be detected when the scraper is working.

[0025] After the target spinneret is scraped by the preset intelligent scraper assembly, the method further includes:

[0026] The audio to be detected is subjected to audio analysis to obtain analysis results, wherein the analysis results are used to indicate whether the scraper needs to be replaced or polished.

[0027] In one embodiment, the audio sensor is fixedly mounted on the surface of the drive component corresponding to the scraper.

[0028] Secondly, embodiments of the present invention also provide an intelligent numerical control device for a polyester filament scraper equipment, the device comprising:

[0029] The image acquisition module is used to acquire a monitoring image of the target spinneret, wherein the target spinneret is one of the multiple spinnerets included in the spinning workshop;

[0030] The image detection module is used to perform image detection on the monitoring image and obtain the image detection result;

[0031] The scraper module is used to scrape the target spinneret based on a preset intelligent scraper assembly when the image detection result indicates that the target spinneret meets the scraper conditions.

[0032] Thirdly, embodiments of the present invention also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the intelligent numerical control method for the polyester filament shovel plate device described above.

[0033] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent numerical control method for the polyester filament scraper device described above.

[0034] Fifthly, this disclosure provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the intelligent numerical control method for the polyester filament scraper device described above.

[0035] In this embodiment of the invention, by acquiring monitoring images of the spinneret and performing image detection on the monitoring images, it is determined whether the corresponding spinneret meets the conditions for scraping the spinneret based on the image detection results. If it does, the spinneret is scraped based on the intelligent scraping component. Based on the above settings, a more refined scraping strategy can be realized, making the working time of the intelligent scraping component more flexible and effective, thereby improving the overall spinning quality of the spinning workshop. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating an intelligent numerical control method for a polyester filament scraper device provided in an embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram of the structure of an intelligent numerical control device for a polyester filament scraper equipment provided in an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] This invention provides an intelligent numerical control method for a polyester filament scraper device, see [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart of the intelligent numerical control method for the polyester filament scraper equipment provided in the embodiments of the present invention, such as... Figure 1 As shown, it includes the following steps:

[0041] Step 101: Obtain a monitoring image of the target spinneret.

[0042] The target spinneret is one of the multiple spinnerets included in the spinning workshop.

[0043] It should be understood that the above-mentioned monitoring image is one of multiple images obtained by periodically taking pictures of the target spinneret by a monitoring device (such as a monitoring camera). The shooting period of the monitoring device can be 15 seconds, 60 seconds, half an hour, 2 hours, etc.

[0044] For example, for the multiple spinnerets included in the spinning workshop, a monitoring camera can be set up for each spinneret, and the monitoring camera can be set to periodically collect images of the corresponding spinneret according to a preset program.

[0045] For the multiple spinnerets included in the spinning workshop, several intelligent robots (the number of intelligent robots is much smaller than the number of spinnerets) can be set up to conduct periodic patrols in the spinning workshop according to a preset program. During the patrol, the intelligent robots collect images of each spinneret along the patrol route through the cameras mounted on them.

[0046] Step 102: Perform image detection on the monitoring image to obtain the image detection result.

[0047] Step 103: When the image detection result indicates that the target spinneret meets the scraping condition, the target spinneret is scraped based on the preset intelligent scraping component.

[0048] In this embodiment of the invention, by acquiring monitoring images of the spinneret and performing image detection on the monitoring images, it is determined whether the corresponding spinneret meets the conditions for scraping the spinneret based on the image detection results. If it does, the spinneret is scraped based on the intelligent scraping component.

[0049] Based on the above settings, a more refined scraping strategy can be implemented. Specifically, for the multiple spinnerets included in the spinning workshop, when it is detected that some spinnerets meet the scraping conditions while others do not, the scraping treatment is performed on the spinnerets that meet the scraping conditions in order to clean the adhering material on the spinnerets that meet the scraping conditions in a timely manner, so as to maintain the spinning effect of the multiple spinnerets included in the spinning workshop at a high level.

[0050] Furthermore, determining whether the spinneret meets the scraping conditions through image detection results, rather than setting a fixed scraping time based on experience, can avoid interference from human factors and make the determined scraping time more accurate and effective.

[0051] In summary, the intelligent numerical control solution provided by this invention, through the above-mentioned settings, enables the intelligent shovel plate assembly to operate more flexibly and effectively, and improves the overall spinning quality of the spinning workshop.

[0052] In one embodiment, performing image detection on the monitored image to obtain the image detection result includes:

[0053] Based on the first position information corresponding to the target spinneret, a target image block is extracted from the monitoring image, wherein the first position information is used to indicate the position of the image area corresponding to the target spinneret in the monitoring image;

[0054] Based on the second position information corresponding to the target spinneret, a mask is applied to the pixel region corresponding to the spinneret hole in the target image block to obtain a masked image block. The second position information is used to indicate the position of the pixel region corresponding to the spinneret hole in the target spinneret in the target image block.

[0055] Image detection is performed on the mask image block to obtain the image detection result.

[0056] For situations where the spinneret position and image capture position are fixed (the fixed camera position and shooting angle are fixed, or the intelligent robot's shooting position and shooting angle are fixed), by pre-acquiring the first position information, the operation of extracting the target image block from the monitoring image can be conveniently realized (which can be understood as cutting / segmenting the image block corresponding to the target spinneret from the monitoring image). This can speed up the subsequent image detection efficiency while reducing the interference caused by the background part of the image in the monitoring image, making the image detection results more accurate.

[0057] In one example, multiple images of the target spinneret can be pre-acquired (the shooting parameters of the images to be processed are exactly the same as those of the monitoring images, including shooting position, shooting angle, etc.). Then, the position of the image block corresponding to the target spinneret in each image to be processed is determined by manual annotation. Finally, the average value of the multiple image block positions corresponding to the multiple images to be processed is calculated to generate the first position information.

[0058] Similarly, for cases where the position of the spinneret holes within the spinneret plate is also fixed, the second position information is obtained in advance, and the pixel area corresponding to the spinneret hole in the target image block is masked accordingly. In the subsequent image detection process, the pixel area corresponding to the spinneret hole is masked, so that the processing of the spinneret plate surface image content can be more focused during the image detection process, thereby improving the accuracy of the final output image detection result.

[0059] It should be noted that the reason for performing the spinneret masking process after extracting the target image block is to improve the accuracy of the spinneret masking process and avoid including pixel blocks unrelated to the spinneret (such as pixel blocks corresponding to the adhesive) in the masking range, so as to ensure the accuracy of subsequent image detection results.

[0060] In applications, to effectively improve the operational accuracy of mask processing, based on the second position information corresponding to the target spinneret, a mask is applied to the pixel region corresponding to the spinneret hole in the target image block, resulting in a mask image block that can be:

[0061] The target image block is enlarged to obtain an enlarged image block, wherein the image size of the enlarged image block is larger than the image size of the target image block;

[0062] Based on the second position information corresponding to the target spinneret, the pixel area corresponding to the spinneret hole in the magnified image block is masked to obtain a masked image block.

[0063] The acquisition of the second location information can be found in the example of acquiring the first location information mentioned above, and will not be repeated here to avoid repetition.

[0064] In this invention, masking can be understood as: uniformly adjusting the pixel values ​​of each pixel block in the pixel area that needs to be masked to a preset value (such as setting the pixel block to black or white).

[0065] In one embodiment, performing image detection on the mask image patch to obtain the image detection result includes:

[0066] Based on a pre-trained target model, feature extraction is performed on the mask image patch to obtain the first feature;

[0067] The first feature and the plurality of second features are respectively subjected to feature similarity calculation to obtain a plurality of similarity values ​​corresponding one-to-one with the plurality of second features. The second feature is used to represent the image features of the spinneret under abnormal production conditions. The larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature.

[0068] When at least one target similarity value is included among the plurality of similarity values, an image detection result indicating that the target spinneret meets the scraping condition is generated, wherein the target similarity value is the similarity value that is greater than or equal to a preset similarity threshold;

[0069] If the target similarity value is not included among the plurality of similarity values, an image detection result indicating that the target spinneret does not meet the shovel condition is generated.

[0070] In this embodiment, by extracting image features and performing feature similarity calculations with the image features of spinnerets under multiple abnormal production conditions pre-stored in the database, it is determined whether the target spinneret meets the scraping condition, which makes the determination of the scraping condition more accurate and reliable.

[0071] For example, the extraction of the first feature and multiple second features can be achieved through convolutional neural networks (CNNs). For instance, deep semantic features of an image can be obtained through the convolutional layers of a pre-trained model (such as VGG, ResNet, EfficientNet, etc.); autoencoders can extract low-dimensional feature representations of an image through encoders; and attention mechanisms (such as Vision Transformer) can enhance feature representation by capturing key regions in an image.

[0072] The aforementioned similarity values ​​can be calculated using methods such as cosine similarity, Manhattan distance, and intersection-union ratio. This invention does not limit the specific method used for similarity value calculation.

[0073] In one embodiment, before extracting features from the mask image patch based on a pre-trained target model to obtain the first feature, the method further includes:

[0074] Multiple abnormal image blocks are acquired, wherein the abnormal image blocks are image blocks of spinnerets under abnormal production conditions. If the decrease in the spinneret quality is greater than or equal to a set decrease threshold, the spinneret is determined to be under abnormal production conditions.

[0075] Based on the target model, feature extraction is performed on the multiple abnormal image blocks to obtain the multiple second features.

[0076] In applications, the spinneret's spinneret quality can be determined by detecting indicators such as the fineness, diameter uniformity, and breakage rate of the filaments spun out by the spinneret.

[0077] In this embodiment, an image of a spinneret with a significant decrease in spin quality is taken as an image of the spinneret under abnormal production conditions to avoid interference from human factors. Based on this, a second feature is formed, which can more accurately reflect the image characteristics of the spinneret under abnormal production conditions.

[0078] It should be noted that, compared to selecting images when the spinneret quality is substandard, selecting images when the spinneret quality significantly declines to extract the second feature and execute the corresponding image detection scheme can more promptly detect the adhesives affecting the normal operation of the spinneret and take corresponding scraping and cleaning measures, so that the spinneret quality is always maintained at a high level, thereby reducing the overall material consumption in the spinning workshop.

[0079] In one embodiment, the smart scraper assembly includes a scraper and an audio sensor;

[0080] The method of scraping the target spinneret using a preset intelligent scraper assembly includes:

[0081] The scraper is used to scrape the target spinneret, and the audio sensor is used to collect the audio to be detected when the scraper is working.

[0082] After the target spinneret is scraped by the preset intelligent scraper assembly, the method further includes:

[0083] The audio to be detected is subjected to audio analysis to obtain analysis results, wherein the analysis results are used to indicate whether the scraper needs to be replaced or polished.

[0084] In the application, when the analysis results indicate whether the scraper needs to be replaced or sharpened, the staff can be notified by means of lights, beeps, and push notifications, so that the staff can perform timely maintenance on the scraper that needs to be replaced or sharpened.

[0085] In this embodiment, audio analysis is used to automatically determine whether the scraper needs to be replaced or polished, so as to detect scrapers that are worn out in time and keep the scraper performing the scraping work in a better working condition, so as to ensure that the spinneret can obtain a better scraping cleaning effect.

[0086] For example, the process of performing audio analysis on the audio to be detected and obtaining the analysis results can be as follows:

[0087] Audio features are extracted from the audio to be detected to obtain the audio features to be analyzed;

[0088] The similarity between the audio features to be analyzed and the standard audio features is calculated to obtain the audio similarity.

[0089] If the audio similarity is greater than or equal to the preset audio similarity threshold, an analysis result indicating that the scraper does not need to be replaced or polished is output.

[0090] If the audio similarity is less than the audio similarity threshold, an analysis result indicating that the scraper needs to be replaced or polished is output.

[0091] The standard audio characteristics are used to represent the audio of a scraper performing a scraping operation under ideal conditions (without needing to be replaced or polished).

[0092] In one embodiment, the audio sensor is fixedly mounted on the surface of the drive component corresponding to the scraper.

[0093] For example, the drive component corresponding to the scraper can be a motor.

[0094] In this embodiment, the audio sensor is fixedly mounted on the surface of the drive component corresponding to the scraper, so as to achieve direct contact between the audio sensor and the scraper and the drive component corresponding to the scraper. This reduces the noise mixed in during the acquisition of the audio to be detected, and acquires more accurate audio to be detected at a lower cost, thereby ensuring the accuracy of the obtained analysis results.

[0095] See Figure 2 , Figure 2 This is a schematic diagram of the structure of an intelligent CNC device 200 for a polyester filament scraper equipment provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the intelligent CNC device 200 of the polyester filament scraper equipment includes:

[0096] Image acquisition module 201 is used to acquire a monitoring image of the target spinneret, wherein the target spinneret is one of the multiple spinnerets included in the spinning workshop;

[0097] Image detection module 202 is used to perform image detection on the monitoring image and obtain image detection results;

[0098] The scraper module 203 is used to scrape the target spinneret based on a preset intelligent scraper assembly when the image detection result indicates that the target spinneret meets the scraper conditions.

[0099] In one embodiment, the image detection module 202 includes:

[0100] An image block extraction unit is used to extract target image blocks from the monitoring image based on the first position information corresponding to the target spinneret, wherein the first position information is used to indicate the position of the image area corresponding to the target spinneret in the monitoring image;

[0101] An image block masking unit is used to mask the pixel region corresponding to the spinneret hole in the target image block based on the second position information corresponding to the target spinneret, to obtain a masked image block, wherein the second position information is used to indicate the position of the pixel region corresponding to the spinneret hole in the target image block;

[0102] An image detection unit is used to perform image detection on the mask image block and obtain the image detection result.

[0103] In one embodiment, the image detection unit is specifically used for:

[0104] The first feature and the plurality of second features are respectively subjected to feature similarity calculation to obtain a plurality of similarity values ​​corresponding one-to-one with the plurality of second features. The second feature is used to represent the image features of the spinneret under abnormal production conditions. The larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature.

[0105] When at least one target similarity value is included among the plurality of similarity values, an image detection result indicating that the target spinneret meets the scraping condition is generated, wherein the target similarity value is the similarity value that is greater than or equal to a preset similarity threshold;

[0106] If the target similarity value is not included among the plurality of similarity values, an image detection result indicating that the target spinneret does not meet the shovel condition is generated.

[0107] In one embodiment, the image detection unit is further configured to:

[0108] Multiple abnormal image blocks are acquired, wherein the abnormal image blocks are image blocks of spinnerets under abnormal production conditions. If the decrease in the spinneret quality is greater than or equal to a set decrease threshold, the spinneret is determined to be under abnormal production conditions.

[0109] Based on the target model, feature extraction is performed on the multiple abnormal image blocks to obtain the multiple second features.

[0110] In one embodiment, the smart scraper assembly includes a scraper and an audio sensor;

[0111] The scraper module 203 is specifically used for: scraping the target spinneret based on the scraper, and collecting the audio to be detected when the scraper is working based on the audio sensor;

[0112] The intelligent numerical control device 200 of the polyester filament scraper equipment also includes:

[0113] The scraper detection module is used to perform audio analysis on the audio to be detected and obtain analysis results, wherein the analysis results are used to indicate whether the scraper needs to be replaced or sharpened.

[0114] In one embodiment, the audio sensor is fixedly mounted on the surface of the drive component corresponding to the scraper.

[0115] The intelligent numerical control device 200 of the polyester filament scraper equipment can realize the embodiment of the present invention. Figure 1 The various processes in the method embodiments, and the ways to achieve the same beneficial effects, will not be repeated here to avoid repetition.

[0116] This invention also provides an electronic device. Please refer to [link to relevant documentation]. Figure 3 The electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and capable of running on the processor 301.

[0117] When program 3021 is executed by processor 301, it can achieve the following: Figure 1 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0118] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0119] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 1Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0120] The computer-readable storage medium of this invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0121] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0122] The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0123] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent numerical control method for polyester filament splicing equipment, characterized in that, The method comprises: acquiring a monitoring image of a target spinneret, wherein the target spinneret is one spinneret in a plurality of spinnerets included in a spinning workshop; performing image detection on the monitoring image to obtain an image detection result; when the image detection result indicates that the target spinneret meets a plate scraping condition, performing plate scraping processing on the target spinneret based on a preset intelligent plate scraping assembly; the image detection on the monitoring image to obtain an image detection result comprises: extracting a target image block from the monitoring image based on first position information corresponding to the target spinneret, wherein the first position information is used to indicate the position of the image area corresponding to the target spinneret in the monitoring image; masking a pixel area corresponding to a spinneret hole in the target image block based on second position information corresponding to the target spinneret, wherein the second position information is used to indicate the position of the spinneret hole in the target spinneret in the pixel area corresponding to the target spinneret in the target image block; performing image detection on the mask image block to obtain the image detection result; the image detection on the mask image block to obtain the image detection result comprises: performing feature extraction on the mask image block based on a pre-trained target model to obtain first features; performing feature similarity calculation on the first features and a plurality of second features respectively to obtain a plurality of similarity values corresponding one-to-one to the plurality of second features, wherein the second features are used to represent image features of a spinneret under abnormal production conditions, and the greater the similarity value, the higher the feature similarity between the first features and the corresponding second features; in the case where the plurality of similarity values include at least one target similarity value, generating an image detection result indicating that the target spinneret meets the plate scraping condition, wherein the target similarity value is a similarity value greater than or equal to a preset similarity threshold; in the case where the plurality of similarity values do not include the target similarity value, generating an image detection result indicating that the target spinneret does not meet the plate scraping condition; before the feature extraction on the mask image block based on the pre-trained target model to obtain the first features, the method further comprises: acquiring a plurality of abnormal image blocks, wherein the abnormal image blocks are image blocks of spinnerets under abnormal production conditions, and in the case where the decrease in spinneret spinning quality is greater than or equal to a set decrease threshold, it is determined that the spinneret is under abnormal production conditions; performing feature extraction on the plurality of abnormal image blocks based on the target model to obtain the plurality of second features.

2. The method of claim 1, wherein, The intelligent plate scraping assembly comprises a scraper and an audio sensor; the plate scraping processing on the target spinneret based on the preset intelligent plate scraping assembly comprises: performing plate scraping processing on the target spinneret based on the scraper, and collecting a to-be-detected audio when the scraper is working based on the audio sensor; after the plate scraping processing on the target spinneret based on the preset intelligent plate scraping assembly, the method further comprises: The audio analysis is performed on the audio to be detected to obtain an analysis result, wherein the analysis result is used to indicate whether the doctor blade needs to be replaced or polished.

3. The method of claim 2, wherein, The audio sensor is fixedly arranged on the surface of the driving member corresponding to the doctor blade.

4. An intelligent numerical control device for polyester filament splicing equipment, characterized in that, The device is used to implement the method of any one of claims 1-3, and the device comprises: An image acquisition module is configured to acquire a monitoring image of a target spinneret, wherein the target spinneret is one of a plurality of spinnerets included in a spinning workshop. An image detection module is configured to perform image detection on the monitoring image to obtain an image detection result. A shovel plate module is configured to perform shovel plate processing on the target spinneret based on a preset intelligent shovel plate assembly when the image detection result indicates that the target spinneret meets a shovel plate condition.

5. An electronic device, comprising: A processor, a memory, and a computer program stored on the memory and executable on the processor are included, and the computer program, when executed by the processor, implements the steps of the intelligent numerical control method of the polyester filament shovel plate device according to any one of claims 1 to 3.

6. A readable storage medium characterized by, The computer program is stored on the readable storage medium, and when executed by the processor, the computer program implements the steps of the intelligent numerical control method of the polyester filament shovel plate device according to any one of claims 1 to 3.

7. A computer program product, characterised in that, The computer program is stored on the readable storage medium, and when executed by the processor, the computer program implements the steps of the intelligent numerical control method of the polyester filament shovel plate device according to any one of claims 1 to 3. The computer program is stored on the readable storage medium, and when executed by the processor, the computer program implements the steps of the intelligent numerical control method of the polyester filament shovel plate device according to any one of claims 1 to 3.

Images