Intelligent numerical control method and device for polyester yarn shovel plate equipment and related equipment

Abstract

The invention provides an intelligent numerical control method and device for polyester yarn shovel plate equipment and related equipment, and relates to the technical field of spinning production. The method comprises the steps that a monitoring image of a target spinneret plate is obtained, and the target spinneret plate is one of a plurality of spinneret plates included in a spinning workshop; performing image detection on the monitoring image to obtain an image detection result; and when the image detection result indicates that the target spinneret plate meets the plate shoveling condition, carrying out plate shoveling treatment on the target spinneret plate based on a preset intelligent plate shoveling assembly. According to the invention, the monitoring image of the spinneret plate is collected, the image detection is carried out on the monitoring image, whether the corresponding spinneret plate meets the plate shoveling condition or not is determined according to the image detection result, and if yes, the spinneret plate is shoveled based on the intelligent plate shoveling assembly, so that the working time of the intelligent plate shoveling assembly is more flexible based on the setting, and the working efficiency is improved. And the overall spinning quality of a spinning workshop is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of spinning production, and particularly relates to an intelligent numerical control method, device and related equipment for a polyester filament scraping plate device. Background Art

[0002] The spinneret plate is an important part in the spinning machine of the chemical fiber industry. During the spinning process, the polymer decomposes at high temperature to produce monomers that adhere to the surface of the spinneret plate. In order to ensure the spinnability and quality stability of chemical fiber filaments, it is necessary to regularly scrape the surface of the spinneret plate.

[0003] In the prior art, although the scraping of the adhesive on the surface of the spinneret plate can be completed by an automatic scraping plate device, the scraping plate device usually only performs the scraping work during a preset period, and the preset period is mostly set manually, which has great uncertainty and is prone to the situation where the adhesive has seriously affected the spinning quality, but the scraping plate device still has not worked.

[0004] That is to say, the numerical control scheme provided by the prior art for the scraping plate device lacks effective management of the working time of the scraping plate device. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent numerical control method, device and related equipment for a polyester filament scraping plate device, which is used to solve the technical problem that the numerical control scheme provided by the prior art for the scraping plate device lacks effective management of the working time of the scraping plate device.

[0006] In a first aspect, an embodiment of the present invention provides an intelligent numerical control method for a polyester filament scraping plate device, and the method includes: Obtain a monitoring image of a target spinneret plate, where the target spinneret plate is one of a plurality of spinneret plates included in a spinning workshop; Perform image detection on the monitoring image to obtain an image detection result; When the image detection result indicates that the target spinneret plate meets the scraping condition, perform scraping processing on the target spinneret plate based on a preset intelligent scraping component.

[0007] In one embodiment, the performing image detection on the monitoring image to obtain an image detection result includes: Extract a target image block from the monitoring image based on first position information corresponding to the target spinneret plate, where the first position information is used to represent the position of the image area corresponding to the target spinneret plate in the monitoring image; Mask the pixel regions corresponding to the spinneret holes in the target image block based on the second position information corresponding to the target spinneret plate, to obtain a masked image block, where the second position information is used to represent the positions of the spinneret holes in the target spinneret plate corresponding to the pixel regions in the target image block; Perform image detection on the masked image block to obtain the image detection result.

[0008] In one embodiment, the performing image detection on the masked image block to obtain the image detection result includes: Extract features from the masked image block based on a pre-trained target model to obtain a first feature; Calculate the feature similarity between the first feature and multiple second features respectively to obtain multiple similarity values corresponding one-to-one to the multiple second features, where the second features are used to represent the image features of the spinneret plate under abnormal production conditions, and the larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature; When at least one target similarity value is included in the multiple similarity values, generate an image detection result indicating that the target spinneret plate meets the scraping condition, where the target similarity value is the similarity value greater than or equal to a preset similarity threshold; When the target similarity value is not included in the multiple similarity values, generate an image detection result indicating that the target spinneret plate does not meet the scraping condition.

[0009] In one embodiment, before the extracting features from the masked image block based on a pre-trained target model to obtain a first feature, the method further includes: Obtain multiple abnormal image blocks, where the abnormal image blocks are image blocks of the spinneret plate under abnormal production conditions, and when the reduction in the spinning quality of the spinneret plate is greater than or equal to a set reduction threshold, determine that the spinneret plate is under abnormal production conditions; Extract features from the multiple abnormal image blocks respectively based on the target model to obtain the multiple second features.

[0010] In one embodiment, the intelligent scraping component includes a scraper and an audio sensor; The performing scraping processing on the target spinneret plate based on a preset intelligent scraping component includes: Perform scraping processing on the target spinneret plate based on the scraper, and collect the audio to be detected during the operation of the scraper based on the audio sensor; After the performing scraping processing on the target spinneret plate based on a preset intelligent scraping component, the method further includes: Perform audio analysis on the audio to be detected to obtain an analysis result, where the analysis result is used to indicate whether the scraper needs to be replaced or polished.

[0011] In one embodiment, the audio sensor is fixedly arranged on the surface of the driving member corresponding to the scraper.

[0012] In a second aspect, an intelligent numerical control device for a polyester filament scraping plate device according to an embodiment of the present invention includes: An image acquisition module, configured to acquire a monitoring image of a target spinneret plate, where the target spinneret plate is one of a plurality of spinneret plates included in a spinning workshop; An image detection module, configured to perform image detection on the monitoring image to obtain an image detection result; A scraping plate module, configured to perform a scraping plate process on the target spinneret plate based on a preset intelligent scraping plate component when the image detection result indicates that the target spinneret plate meets the scraping plate condition.

[0013] In a third aspect, an electronic device according to an embodiment of the present invention includes a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the intelligent numerical control method for the polyester filament scraping plate device described above are implemented.

[0014] In a fourth aspect, a computer-readable storage medium according to an embodiment of the present invention stores a computer program. When the computer program is executed by a processor, the steps of the intelligent numerical control method for the polyester filament scraping plate device described above are implemented.

[0015] In a fifth aspect, a computer program product according to the present disclosure includes computer instructions. When the computer instructions are executed by a processor, the steps of the intelligent numerical control method for the polyester filament scraping plate device described above are implemented.

[0016] In the embodiment of the present invention, by collecting a monitoring image of the spinneret plate and performing image detection on the monitoring image, it is determined whether the corresponding spinneret plate meets the scraping plate condition according to the image detection result. If it meets the condition, the scraping plate process is performed on the spinneret plate based on the intelligent scraping plate component. Among them, based on the above settings, a more refined scraping plate strategy can be realized, making the working time of the intelligent scraping plate component more flexible and effective, thereby improving the overall spinning quality of the spinning workshop. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic flowchart of an intelligent numerical control method for a polyester filament scraping plate device provided by an embodiment of the present invention; Figure 2 is a schematic structural diagram of an intelligent numerical control device for a polyester filament scraping plate device provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] An embodiment of the present invention provides an intelligent numerical control method for a polyester filament scraping plate device. Refer to Figure 1 , Figure 1 It is a flowchart of the intelligent numerical control method for the polyester filament scraping plate device provided by an embodiment of the present invention. As Figure 1 shown, it includes the following steps: Step 101, obtain a monitoring image of the target spinneret plate.

[0020] Among them, the target spinneret plate is one of the multiple spinneret plates included in the spinning workshop.

[0021] It should be understood that the above monitoring image is: one of the multiple images obtained by periodically photographing the target spinneret plate based on a monitoring device (such as a monitoring camera), where the shooting period corresponding to the monitoring device can be 15 seconds, 60 seconds, half an hour, 2 hours, etc.

[0022] Exemplarily, for the multiple spinneret plates included in the spinning workshop, a monitoring camera can be set for each spinneret plate, and the monitoring camera is set to periodically collect images of the corresponding spinneret plate according to a preset program.

[0023] For the multiple spinneret plates included in the spinning workshop, several intelligent robots (the number of intelligent robots is much less than the number of spinneret plates) can also be set to patrol the spinning workshop periodically according to a preset program, and during the patrol, images of each spinneret plate on the patrol route are collected through the cameras installed on the intelligent robots.

[0024] Step 102, perform image detection on the monitoring image to obtain an image detection result.

[0025] Step 103, when the image detection result indicates that the target spinneret plate meets the scraping plate condition, perform scraping plate processing on the target spinneret plate based on a preset intelligent scraping plate component.

[0026] In an embodiment of the present invention, by collecting a monitoring image of a spinneret plate and performing image detection on the monitoring image, to determine whether the corresponding spinneret plate meets the scraping condition according to the image detection result, and if it meets, perform scraping processing on the spinneret plate based on an intelligent scraping component.

[0027] Based on the above settings, a more refined scraping strategy can be achieved. Specifically, for multiple spinneret plates included in a spinning workshop, when it is detected that some spinneret plates meet the scraping condition while some do not, by performing scraping processing on the part of the spinneret plates that meet the scraping condition, the adhesions on the part of the spinneret plates that meet the scraping condition can be cleaned in time, so that the spinning effect of the multiple spinneret plates included in the spinning workshop can be maintained at a relatively high level.

[0028] And by using the image detection result to determine whether the spinneret plate meets the scraping condition, rather than setting a fixed scraping processing time based on experience, it can avoid the interference of human factors and make the determined scraping processing time more accurate and effective.

[0029] Generally speaking, the intelligent numerical control solution provided by the present invention can make the working time of the intelligent scraping component more flexible and effective through the above settings, and improve the overall spinning quality of the spinning workshop.

[0030] In one embodiment, the performing image detection on the monitoring image to obtain an image detection result includes: Based on the first position information corresponding to the target spinneret plate, extracting a target image block from the monitoring image, where the first position information is used to represent the position of the image area corresponding to the target spinneret plate in the monitoring image; Based on the second position information corresponding to the target spinneret plate, masking the pixel area corresponding to the spinneret holes in the target image block to obtain a masked image block, where the second position information is used to represent the position of the pixel area corresponding to the spinneret holes in the target spinneret plate in the target image block; Performing image detection on the masked image block to obtain the image detection result.

[0031] For the case where the position of the spinneret plate is fixed and the image shooting position is fixed (the position of the fixed camera is fixed and the shooting angle is fixed, or the shooting position and shooting angle of the intelligent robot are fixed), by pre-obtaining the first position information and thus conveniently realizing the operation of extracting the target image block from the monitoring image (which can be understood as cutting / splitting out the image block corresponding to the target spinneret plate from the monitoring image), this can improve the subsequent image detection efficiency while reducing the interference brought by the image background part in the monitoring image and making the image detection result more accurate.

[0032] In one example, multiple images to be processed of the target spinneret plate can be pre-acquired (the shooting parameters of the images to be processed are exactly the same as those of the monitoring images, where the shooting parameters include shooting position, shooting angle, etc.), and then, by means of manual annotation, the corresponding image block positions of the target spinneret plate in each image to be processed are determined; finally, the average value is calculated for the multiple image block positions corresponding to the multiple images to be processed one by one to generate the first position information.

[0033] Similarly, for the case where the positions of the spinneret holes in the spinneret plate are also fixed, by pre-acquiring the second position information and masking the pixel regions corresponding to the spinneret holes in the target image block accordingly, the pixel regions corresponding to the spinneret holes can be shielded during the subsequent image detection process, so as to be more focused on the processing of the surface image content of the spinneret plate during the image detection process, thereby improving the accuracy of the finally output image detection result.

[0034] It should be noted that the reason for performing the masking process of the spinneret holes after extracting the target image block is to improve the masking accuracy of the spinneret holes and avoid including pixel blocks irrelevant to the spinneret holes (such as pixel blocks corresponding to adhesives) in the masking range to ensure the accuracy of the subsequent image detection result.

[0035] In the application, to effectively improve the operation accuracy of the masking process, based on the second position information corresponding to the target spinneret plate, masking the pixel regions corresponding to the spinneret holes in the target image block, the obtained masked image block can be: Enlarge the target image block to obtain an enlarged image block, where the image size of the enlarged image block is larger than the image size of the target image block; Based on the second position information corresponding to the target spinneret plate, mask the pixel regions corresponding to the spinneret holes in the enlarged image block to obtain a masked image block.

[0036] Among them, for the acquisition of the second position information, reference can be made to the description of the example for acquiring the first position information mentioned above. To avoid repetition, it will not be elaborated here.

[0037] In the present invention, the masking process can be understood as: uniformly adjusting the pixel values of each pixel block in the pixel region to be masked to a preset value (such as setting the pixel block black or white).

[0038] In one embodiment, the performing image detection on the masked image block to obtain the image detection result includes: Performing feature extraction on the masked image block based on a pre-trained target model to obtain a first feature; Calculate the feature similarity between the first feature and multiple second features respectively to obtain multiple similarity values corresponding one by one to the multiple second features, where the second feature is used to represent the image feature of the spinneret under abnormal production conditions, and the larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature; When at least one target similarity value is included in the multiple similarity values, generate an image detection result indicating that the target spinneret meets the scraping condition, where the target similarity value is the similarity value greater than or equal to a preset similarity threshold; When the target similarity value is not included in the multiple similarity values, generate an image detection result indicating that the target spinneret does not meet the scraping condition.

[0039] In this embodiment, by extracting image features and performing feature similarity calculation based on the extracted image features with the image features of multiple spinnerets under abnormal production conditions pre-stored in the database to determine whether the target spinneret meets the scraping condition, the determination of the scraping condition can be made more accurate and reliable.

[0040] Exemplarily, the extraction of the first feature and multiple second features can be implemented through a convolutional neural network (CNN). For example: obtaining the deep semantic features of the image through the convolutional layer of a pre-trained model (such as VGG, ResNet, EfficientNet, etc.); the autoencoder extracts the low-dimensional feature representation of the image; the attention mechanism (such as Vision Transformer) enhances the feature expression ability by capturing the key regions in the image.

[0041] Among them, the foregoing similarity value can be calculated by methods such as cosine similarity, Manhattan distance, intersection over union, etc. The present invention does not limit the specific method for calculating the similarity value.

[0042] In one embodiment, before obtaining the first feature by extracting features from the masked image patch based on the pre-trained target model, the method further includes: Obtain multiple abnormal image patches, where the abnormal image patch is an image patch of the spinneret under abnormal production conditions, and when the decrease rate of the spinning quality of the spinneret is greater than or equal to a set decrease rate threshold, it is determined that the spinneret is in an abnormal production condition; Extract features from the multiple abnormal image patches respectively based on the target model to obtain the multiple second features.

[0043] In applications, the spinning quality of the spinneret can be determined by detecting indicators such as the fineness, diameter uniformity, and wire breakage rate of the filaments ejected by the spinneret.

[0044] In this embodiment, an image taken when the spinning quality of the spinneret significantly deteriorates is used as the 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.

[0045] It should be noted that, compared with selecting an image with unqualified spinning quality, selecting an image when the spinning quality of the spinneret significantly deteriorates to extract the second feature and implementing the corresponding image detection scheme can more timely detect the adhesives affecting the normal operation of the spinneret and take corresponding measures to clean the spinneret plate, so that the spinning quality of the spinneret is always maintained at a high level, thereby reducing the overall material consumption in the spinning workshop.

[0046] In one embodiment, the intelligent spinneret cleaning assembly includes a scraper and an audio sensor; The process of performing spinneret cleaning on the target spinneret based on the preset intelligent spinneret cleaning assembly includes: Performing spinneret cleaning on the target spinneret based on the scraper, and collecting the audio to be detected during the operation of the scraper based on the audio sensor; After performing spinneret cleaning on the target spinneret based on the preset intelligent spinneret cleaning assembly, the method further includes: Performing audio analysis on the audio to be detected to obtain an analysis result, where the analysis result is used to indicate whether the scraper needs to be replaced or polished.

[0047] In application, when the analysis result indicates whether the scraper needs to be replaced or polished, it can prompt the staff through methods such as lighting, beeping, and pushing prompt messages, so that the staff can timely maintain the scraper that needs to be replaced or polished.

[0048] In this embodiment, it is automatically determined whether the scraper needs to be replaced or polished through audio analysis, so as to timely detect a scraper with excessive wear, and keep the scraper performing the spinneret cleaning work in a better state of use, so as to ensure that the spinneret can obtain a better spinneret cleaning effect.

[0049] Exemplarily, the process of performing audio analysis on the audio to be detected to obtain an analysis result can be: Extracting audio features from the audio to be detected to obtain audio features to be analyzed; Calculating the similarity between the audio features to be analyzed and the standard audio features to obtain an audio similarity; If the audio similarity is greater than or equal to a preset audio similarity threshold, an analysis result indicating that the scraper does not need to be replaced or polished is output; 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.

[0050] The standard audio feature is used to represent the audio of the scraper in an ideal state (without the need for replacement or polishing) during the operation of scraping the plate.

[0051] In one embodiment, the audio sensor is fixedly arranged on the surface of the driving part corresponding to the scraper.

[0052] Exemplarily, the driving part corresponding to the scraper can be a motor.

[0053] In this embodiment, by fixedly arranging the audio sensor on the surface of the driving part corresponding to the scraper, direct contact between the audio sensor, the scraper, and the driving part corresponding to the scraper is achieved. Accordingly, the noise mixed in during the acquisition of the audio to be detected can be reduced, and the more accurate audio to be detected can be acquired at a lower cost, thereby ensuring the accuracy of the obtained analysis result.

[0054] See Figure 2 , Figure 2 is a schematic structural diagram of an intelligent numerical control device 200 of a polyester filament scraping plate device provided by an embodiment of the present invention. As Figure 2 shown, the intelligent numerical control device 200 of the polyester filament scraping plate device includes: An image acquisition module 201, configured to acquire a monitoring image of a target spinneret plate, where the target spinneret plate is one of the multiple spinneret plates included in the spinning workshop; An image detection module 202, configured to perform image detection on the monitoring image to obtain an image detection result; A scraping plate module 203, configured to perform scraping plate processing on the target spinneret plate based on a preset intelligent scraping plate assembly when the image detection result indicates that the target spinneret plate meets the scraping plate condition.

[0055] In one embodiment, the image detection module 202 includes: An image block extraction unit, configured to extract a target image block from the monitoring image based on the first position information corresponding to the target spinneret plate, where the first position information is used to represent the position of the image area corresponding to the target spinneret plate in the monitoring image; An image block masking unit, configured to mask the pixel area corresponding to the spinneret holes in the target image block based on the second position information corresponding to the target spinneret plate to obtain a masked image block, where the second position information is used to represent the position of the pixel area corresponding to the spinneret holes in the target spinneret plate in the target image block; An image detection unit, configured to perform image detection on the masked image block to obtain the image detection result.

[0056] In one embodiment, the image detection unit is specifically configured to: Calculate the feature similarity between the first feature and multiple second features respectively to obtain multiple similarity values corresponding one by one to the multiple second features, where the second feature is used to represent the image feature of the spinneret under abnormal production conditions, and the greater the similarity value, the higher the feature similarity between the first feature and the corresponding second feature; In the case that at least one target similarity value is included in the multiple similarity values, generate an image detection result indicating that the target spinneret meets the scraping condition, where the target similarity value is the similarity value greater than or equal to a preset similarity threshold; In the case that the target similarity value is not included in the multiple similarity values, generate an image detection result indicating that the target spinneret does not meet the scraping condition.

[0057] In one embodiment, the image detection unit is further configured to: Obtain multiple abnormal image blocks, where the abnormal image block is an image block of the spinneret under abnormal production conditions, and determine that the spinneret is under abnormal production conditions when the decrease in the spinning quality of the spinneret is greater than or equal to a set decrease threshold; Extract features from the multiple abnormal image blocks respectively based on the target model to obtain the multiple second features.

[0058] In one embodiment, the intelligent scraping assembly includes a scraper and an audio sensor; The scraping module 203 is specifically configured to: perform scraping processing on the target spinneret based on the scraper, and collect the audio to be detected during the operation of the scraper based on the audio sensor; The intelligent numerical control device 200 of the polyester filament scraping equipment further includes: A scraper detection module, configured to perform audio analysis on the audio to be detected to obtain an analysis result, where the analysis result is used to indicate whether the scraper needs to be replaced or polished.

[0059] In one embodiment, the audio sensor is fixedly arranged on the surface of the driving member corresponding to the scraper.

[0060] The intelligent numerical control device 200 of the polyester filament scraping equipment can implement each process in the method embodiment of the present invention Figure 1 and achieve the same beneficial effects. To avoid repetition, it will not be elaborated here.

[0061] An embodiment of the present invention further provides an electronic device. Please refer to Figure 3, the electronic device may include a processor 301, a memory 302, and a program 3021 stored on the memory 302 and executable on the processor 301.

[0062] When the program 3021 is executed by the processor 301, it can implement Figure 1 any step in the corresponding method embodiment and achieve the same beneficial effects, which will not be elaborated here.

[0063] Those of ordinary skill in the art can understand that all or part of the steps of implementing the method in the above embodiment can be completed by hardware related to program instructions, and the program can be stored in a readable medium.

[0064] The embodiment of the present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement any step in the above Figure 1 corresponding method embodiment and achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0065] The computer-readable storage medium of the embodiment of the present 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. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, apparatus, or device.

[0066] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program used by or combined with an instruction execution system, apparatus, or device.

[0067] The program code contained on the storage medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the above.

[0068] The computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include 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, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0069] The above is the preferred implementation mode of the embodiments of the present invention. It should be noted that for those of ordinary skill in the art of the present technology, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent numerical control method for a polyester filament shoveling plate device, characterized in that, The method includes: Obtaining a monitoring image of a target spinneret plate, where the target spinneret plate is one of a plurality of spinneret plates 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 plate meets the scraping condition, performing scraping processing on the target spinneret plate based on a preset intelligent scraping component.

2. The method according to claim 1, wherein The performing image detection on the monitoring image to obtain an image detection result includes: Extracting a target image block from the monitoring image based on first position information corresponding to the target spinneret plate, where the first position information is used to represent the position of the image area corresponding to the target spinneret plate in the monitoring image; Masking the pixel area corresponding to the spinneret holes in the target image block based on second position information corresponding to the target spinneret plate to obtain a masked image block, where the second position information is used to represent the position of the pixel area corresponding to the spinneret holes in the target spinneret plate in the target image block; Performing image detection on the masked image block to obtain the image detection result.

3. The method according to claim 2, characterized in that, The performing image detection on the masked image block to obtain the image detection result includes: Extracting features from the masked image block based on a pre-trained target model to obtain a first feature; Calculating the feature similarity between the first feature and a plurality of second features respectively to obtain a plurality of similarity values corresponding one by one to the plurality of second features, where the second features are used to represent the image features of the spinneret plate under abnormal production conditions, and the larger the similarity value, the higher the feature similarity between the first feature and the corresponding second feature; When at least one target similarity value is included in the plurality of similarity values, generating an image detection result indicating that the target spinneret plate meets the scraping condition, where the target similarity value is the similarity value greater than or equal to a preset similarity threshold; When the target similarity value is not included in the plurality of similarity values, generating an image detection result indicating that the target spinneret plate does not meet the scraping condition.

4. The method according to claim 3, wherein Before the extracting features from the masked image block based on a pre-trained target model to obtain a first feature, the method further includes: Obtaining a plurality of abnormal image blocks, where the abnormal image blocks are image blocks of spinneret plates under abnormal production conditions, and when the reduction rate of the spinning quality of the spinneret plate is greater than or equal to a set reduction rate threshold, it is determined that the spinneret plate is under abnormal production conditions; Extracting features from the plurality of abnormal image blocks respectively based on the target model to obtain the plurality of second features.

5. The method according to claim 1, wherein The intelligent scraping component includes a scraper and an audio sensor; The performing scraping processing on the target spinneret plate based on a preset intelligent scraping component includes: Performing scraping processing on the target spinneret plate based on the scraper, and collecting the audio to be detected during the operation of the scraper based on the audio sensor; After the performing scraping processing on the target spinneret plate based on a preset intelligent scraping component, the method further includes: Perform audio analysis on the audio to be detected to obtain an analysis result, where the analysis result is used to indicate whether the scraper needs to be replaced or polished.

6. The method according to claim 5, wherein The audio sensor is fixedly arranged on the surface of the driving part corresponding to the scraper.

7. An intelligent numerical control device for a polyester filament shoveling plate device, characterized in that, The device includes: An image acquisition module, configured to acquire a monitoring image of a target spinneret plate, where the target spinneret plate is one of a plurality of spinneret plates included in a spinning workshop; An image detection module, configured to perform image detection on the monitoring image to obtain an image detection result; A scraping plate module, configured to perform scraping plate processing on the target spinneret plate based on a preset intelligent scraping plate assembly when the image detection result indicates that the target spinneret plate meets the scraping plate condition.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the intelligent numerical control method of the polyester filament scraping plate device according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, A computer program is stored on the readable storage medium. When the computer program is executed by a processor, it implements the steps of the intelligent numerical control method of the polyester filament scraping plate device according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions. When the computer instructions are executed by a processor, it implements the steps of the intelligent numerical control method of the polyester filament scraping plate device according to any one of claims 1 to 6.

Images