Defective product detection method, device and equipment in optical cable production line and storage medium

Abstract

The invention relates to a defective product detection method and device in an optical cable production line, equipment and a storage medium, and the method comprises the steps: obtaining the image data of an optical cable, carrying out the preprocessing of the image data, and obtaining the preprocessed image data; transmitting the preprocessed image data to a pre-trained detection model for analysis to obtain an analysis result; comparing the analysis result with a preset quality standard to obtain data of defective optical cables; and marking and sorting the corresponding optical cables according to the data of the defective optical cables. The method has the effect of improving the detection accuracy of defective products in the optical cable production line.

Description

Technical Field

[0001] The present application relates to the technical field of optical cable production, and in particular to a method, device, equipment and storage medium for detecting defective products in an optical cable production line. Background Art

[0002] Currently, because optical cable production involves multiple complex processes, such as drawing, coating, and twisting, surface defects such as scratches, bubbles, and dimensional unevenness are prone to appearing. These defects not only affect the appearance of the cable but, more importantly, can cause light attenuation and scattering, reducing transmission performance and, in turn, the stability of the entire communication system. Currently, the optical cable production industry generally relies on manual visual inspection or simple mechanical testing to identify defective products on the production line. This method is inefficient and prone to errors, and cannot meet the needs of modern, efficient production. Existing methods for detecting defective products on optical cable production lines rely heavily on operator experience and visual judgment.

[0003] The above-mentioned existing technical solutions have the following defects: manual detection is subjective and fatigue-prone, resulting in high false detection and missed detection rates, so there is room for improvement. Summary of the Invention

[0004] In order to improve the accuracy of defective product detection in an optical cable production line, the present application provides a method, device, equipment and storage medium for detecting defective products in an optical cable production line.

[0005] The above-mentioned invention objective of this application is achieved through the following technical solutions: A method for detecting defective products in an optical cable production line, comprising: Acquiring image data of the optical cable and preprocessing the image data to obtain preprocessed image data; The pre-processed image data is transmitted to a pre-trained detection model for analysis to obtain analysis results; Comparing the analysis results with the preset quality standards to obtain defective optical cable data; According to the defective optical cable data, the corresponding optical cables are marked and sorted.

[0006] By adopting the above technical solution, image data of the optical cable is obtained, and the image data is preprocessed to obtain preprocessed image data. The preprocessed image data is clearer, which helps to improve the accuracy of the subsequent detection model; the preprocessed image data is transmitted to a pre-trained detection model for analysis to obtain an analysis result. The detection model can analyze the image data and identify whether there are defects or damage on the surface of the optical cable, thereby improving the accuracy of optical cable detection; the analysis result is compared with the preset quality standard to obtain optical cable defective product data, ensuring that only optical cables that meet the standards will be accepted, and optical cables that do not meet the standards will be identified as defective products, thereby improving the accuracy of optical cable screening; according to the optical cable defective product data, the corresponding optical cables are marked and sorted. Through automated marking and sorting, production efficiency is improved, product quality is ensured, and the cost and errors of manual inspection are reduced.

[0007] In a preferred example, the present application may be further configured as follows: the acquiring of image data of the optical cable and preprocessing of the image data to obtain the preprocessed image data include: Using a multispectral camera to acquire surface and internal images of the optical cable at different wavelengths to obtain image data of the optical cable; Performing denoising on the image data using an adaptive median filtering algorithm to obtain denoised image data; The denoised image data is processed using contrast enhancement and edge sharpening algorithms to obtain enhanced image data, and the enhanced image data is corrected through geometric correction and color correction to obtain the preprocessed image data.

[0008] By adopting the above technical solution, a multispectral camera is used to capture the surface and internal images of the optical cable at different wavelengths to obtain image data of the optical cable. This data can reveal the surface defects, internal structure and material properties of the optical cable to provide accurate image data; the acquired image data is preprocessed and the image data is denoised using an adaptive median filtering algorithm. The denoised image data is smoother while retaining important image features, which helps to improve the accuracy of subsequent analysis; the denoised image data is processed using contrast enhancement and edge sharpening algorithms to enhance the contrast of the image, making the image details more prominent and the edges clearer. The enhanced image data is easier to analyze and identify, which helps to improve the accuracy of subsequent image analysis; the enhanced image data is geometrically corrected and color corrected. The corrected image data has higher quality and usability, providing a reliable basis for subsequent image analysis; after the above steps, the final preprocessed image data is obtained. The preprocessed image data provides high-quality input for optical cable quality detection, which helps to improve the accuracy and efficiency of detection.

[0009] In a preferred example, the present application may be further configured as follows: before transmitting the pre-processed image data to a pre-trained detection model for analysis to obtain the analysis result, the method for detecting defective products in an optical cable production line further includes: Collecting an optical cable defect image dataset, and preprocessing and labeling the optical cable defect image dataset to obtain a training set; The training set is used to perform forward propagation and back propagation training on the detection model constructed based on the convolutional neural network and the support vector machine, and the detection model after the forward propagation and back propagation training is optimized using a transfer learning method to obtain the pre-trained detection model.

[0010] By adopting the above technical solution, image data containing optical cable defects is collected to provide a basis for model training, enabling the model to learn to identify different types of optical cable defects. The collected image data is preprocessed by cleaning, formatting, standardization and other preprocessing operations, and labeled. The preprocessed and labeled data is organized into a training set, which will be used to train the machine learning model. The preprocessed and labeled data is more suitable for training the machine learning model, which helps to improve the accuracy and generalization ability of the model. The training set is used to perform forward propagation and backpropagation training on the detection model built based on the convolutional neural network and support vector machine. Through forward propagation and backpropagation, the model learns how to identify optical cable defects from images, and the detection model trained by forward propagation and backpropagation is optimized using the transfer learning method. Transfer learning can accelerate the training process and improve model performance. After training and optimization, a pre-trained detection model is finally obtained. This model can be used to automatically detect optical cable defects, improve detection efficiency and accuracy, and reduce the cost and errors of manual inspection.

[0011] In a preferred example, the present application may be further configured as follows: the pre-processed image data is transmitted to a pre-trained detection model for analysis, and the analysis results obtained include: Classify and identify the pre-processed image data to obtain defect type information; Locating the position of the defect on the optical cable using a target detection algorithm according to the defect type information to obtain defect position information; Score the severity of defects in the pre-processed image data according to the data in the pre-trained detection model to obtain severity information; The defect type information, the defect location information and the severity information are combined for analysis to obtain the analysis result.

[0012] By adopting the above technical solution, the pre-processed optical cable image data is analyzed to identify the defect type in the image. Through classification and identification, the system can determine the category of the defects in the image. The defect type information provides the basis for subsequent defect location and severity assessment. The target detection algorithm is applied to determine the exact location of the defect on the optical cable. The target detection algorithm outputs the coordinates or location information of the defect. The defect location information helps to accurately identify and record the defect, providing accurate data for maintenance and quality control. Based on the data in the pre-trained detection model, the defects in the image are scored to assess their severity. The severity score provides a quantitative assessment of the possible impact of the defect on the optical cable performance, helping to determine the priority of the repair work. The defect type information, location information and severity information are combined and analyzed to form a complete analysis result. The analysis result provides a comprehensive view, showing detailed information on the optical cable defects, providing a basis for subsequent maintenance decisions and quality improvement.

[0013] In a preferred example, the present application may be further configured as follows: comparing the analysis result with a preset quality standard to obtain the optical cable defective product data includes: Setting quality standard parameters, wherein the quality standard parameters include scratch depth, bubble size, surface roughness and cable diameter uniformity; Comparing the analysis results with the quality standards using a weighted scoring algorithm to calculate a comprehensive quality score; Whether the optical cable is defective is determined based on the comprehensive score, and the results are classified into qualified, requiring further testing, and unqualified. The required further testing and unqualified results are integrated to obtain the optical cable defective product data.

[0014] By adopting the above technical solution, a series of quality standard parameters are defined for evaluating the quality of optical cables. These quality standard parameters include scratch depth, bubble size, surface roughness, and cable diameter uniformity, providing clear standards for optical cable quality assessment and ensuring consistency and accuracy of the assessment. A weighted scoring algorithm is applied to score the analysis results based on the preset quality standard parameters. The weighted scoring algorithm assigns different weights to each parameter based on its importance. Through weighted scoring, the influence of each quality parameter can be comprehensively considered to calculate the comprehensive quality score of the optical cable. The various quality parameters in the analysis results are compared with the preset quality standards, and the comprehensive quality score of the optical cable is calculated according to the weighted scoring algorithm. The comprehensive quality score is compared with the preset threshold to determine whether the optical cable meets the quality standard. The optical cable can be divided into three categories: qualified, requiring further testing, and unqualified. The cables requiring further testing and unqualified are integrated to obtain the defective optical cable data. The integrated data helps to track and manage optical cables that do not meet the quality standards, providing a basis for subsequent processing and improvement.

[0015] In a preferred example, the present application may be further configured as follows: the method for detecting defective products in an optical cable production line further includes: Record the inspection results, defect types, inspection time and location of the optical cable within a preset time period, and generate an inspection report based on the inspection results, defect types, inspection time and location; Feeding the inspection report back to the production control system, adjusting the optical cable production parameters in real time according to the inspection report, optimizing the process flow, and reducing the defective product rate in subsequent production; The feedback data is used to optimize and adjust the pre-trained detection model to improve detection performance and stability.

[0016] By adopting the above technical solution, within a preset time period, the system records the inspection results of the optical cable, including the defect type, inspection time and location information. Based on the recorded inspection results, defect type, inspection time and location, the system generates a comprehensive inspection report. The inspection report provides important information for the quality control of the optical cable production, which is convenient for production personnel to understand the quality status of the product and take corresponding measures; the generated inspection report is transmitted to the optical cable production control system, and according to the quality feedback in the inspection report, the production control system adjusts the production parameters of the optical cable in real time. Through real-time adjustment, the process flow can be optimized, defects in production can be reduced, and the defective rate in subsequent production can be reduced; the feedback data collected during the production process is used to optimize and adjust the pre-trained inspection model. Through continuous learning and adjustment, the performance and stability of the inspection model are improved, making the inspection results more accurate and reliable.

[0017] The second object of the present invention is achieved through the following technical solutions: A device for detecting defective products in an optical cable production line, comprising: An image data acquisition module is used to acquire image data of the optical cable and preprocess the image data to obtain preprocessed image data; A model analysis module is used to transmit the pre-processed image data to a pre-trained detection model for analysis to obtain analysis results; A comparison module, configured to compare the analysis results with a preset quality standard to obtain defective optical cable data; The sorting module is used to mark and sort the corresponding optical cables according to the defective optical cable data. By adopting the above technical solution, image data of the optical cable is obtained, and the image data is preprocessed to obtain preprocessed image data. The preprocessed image data is clearer, which helps to improve the accuracy of the subsequent detection model; the preprocessed image data is transmitted to a pre-trained detection model for analysis to obtain an analysis result. The detection model can analyze the image data and identify whether there are defects or damage on the surface of the optical cable, thereby improving the accuracy of optical cable detection; the analysis result is compared with the preset quality standard to obtain optical cable defective product data, ensuring that only optical cables that meet the standards will be accepted, and optical cables that do not meet the standards will be identified as defective products, thereby improving the accuracy of optical cable screening; according to the optical cable defective product data, the corresponding optical cables are marked and sorted. Through automated marking and sorting, production efficiency is improved, product quality is ensured, and the cost and errors of manual inspection are reduced.

[0018] The third objective of this application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for detecting defective products in an optical cable production line when executing the computer program.

[0019] The fourth objective of this application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for detecting defective products in an optical cable production line.

[0020] In summary, this application includes at least one of the following beneficial technical effects: 1. Obtain image data of the optical cable and preprocess it to obtain preprocessed image data. The preprocessed image data is clearer and helps improve the accuracy of subsequent detection models. The preprocessed image data is transmitted to a pre-trained detection model for analysis to obtain analysis results. The detection model can analyze the image data and identify whether there are defects or damage on the surface of the optical cable, thereby improving the accuracy of optical cable detection. 2. Compare the analysis results with the preset quality standards to obtain the data of defective optical cables, ensuring that only optical cables that meet the standards will be accepted, and optical cables that do not meet the standards will be identified as defective, thereby improving the accuracy of optical cable screening; based on the defective optical cable data, the corresponding optical cables are marked and sorted. Through automated marking and sorting, production efficiency is improved, product quality is ensured, and the cost and errors of manual inspection are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1This is a flow chart of a method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in the method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S20 in the method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S20 in the method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S30 in the method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 6 This is a flowchart of a method for detecting defective products in an optical cable production line in one embodiment of the present application; Figure 7 This is a principle block diagram of a defective product detection device in an optical cable production line in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application is further described in detail below with reference to the accompanying drawings.

[0023] In one embodiment, if Figure 1 As shown, the present application discloses a method for detecting defective products in an optical cable production line, which specifically includes the following steps: S10: Acquire image data of the optical cable, and preprocess the image data to obtain preprocessed image data.

[0024] Specifically, a high-speed camera or scanning device is used to obtain image data of the optical cable surface. The image data contains characteristic information of the optical cable surface, such as color, texture, shape, etc. The collected image data is preprocessed, which may include denoising, contrast enhancement, brightness adjustment, cropping irrelevant areas, scaling, and other operations. The preprocessed image data is clearer, which helps to improve the accuracy of subsequent detection models, and ultimately obtains preprocessed image data.

[0025] S20: The pre-processed image data is transmitted to a pre-trained detection model for analysis to obtain analysis results.

[0026] Specifically, the preprocessed image data is input into a pre-trained machine vision model, which may be an image recognition model based on deep learning. The detection model can analyze the image data and identify whether there are defects or damage on the surface of the optical cable. The detection model outputs the analysis result, which may be a classification result, such as "qualified" or "defective", to provide a clear judgment basis for the quality of the optical cable.

[0027] S30: Compare the analysis result with the preset quality standard to obtain the optical cable defective product data.

[0028] Specifically, the output of the detection model is compared with the preset quality standards to determine whether the optical cable meets the quality requirements, ensuring that only optical cables that meet the standards are accepted, and optical cables that do not meet the standards will be identified as defective products. Based on the comparison results, the system records the data of the optical cables identified as defective products for subsequent marking and sorting operations.

[0029] S40: Mark and sort the corresponding optical cables according to the defective optical cable data.

[0030] Specifically, the system automatically marks the corresponding optical cables based on the defective product data and sorts them on the production line to separate them from qualified products. Through automated marking and sorting, production efficiency is improved, product quality is ensured, and the cost and errors of manual inspection are reduced.

[0031] By adopting the above technical solution, the image data of the optical cable is obtained, and the image data is preprocessed to obtain preprocessed image data. The preprocessed image data is clearer, which helps to improve the accuracy of the subsequent detection model; the preprocessed image data is transmitted to the pre-trained detection model for analysis to obtain the analysis results. The detection model can analyze the image data and identify whether there are defects or damages on the surface of the optical cable, thereby improving the accuracy of optical cable detection; the analysis results are compared with the preset quality standards to obtain optical cable defective product data, ensuring that only optical cables that meet the standards will be accepted, and optical cables that do not meet the standards will be identified as defective products, thereby improving the accuracy of optical cable screening; according to the optical cable defective product data, the corresponding optical cables are marked and sorted. Through automated marking and sorting, production efficiency is improved, product quality is ensured, and the cost and errors of manual inspection are reduced. In one embodiment, if Figure 2 As shown, in step S10, the image data of the optical cable is obtained and preprocessed to obtain the preprocessed image data, which specifically includes: S11: Use a multispectral camera to obtain surface and internal images of the optical cable at different wavelengths to obtain image data of the optical cable.

[0032] Specifically, a multispectral camera is used to capture the surface and internal images of the optical cable at different wavelengths. The multispectral camera is capable of capturing images beyond the visible spectrum of the human eye, such as infrared and ultraviolet light. These images contain detailed information about the optical cable, and the image data of the optical cable is obtained. This data can reveal the surface defects, internal structure and material properties of the optical cable.

[0033] S12: Using an adaptive median filtering algorithm to perform denoising on the image data to obtain denoised image data.

[0034] Specifically, an adaptive median filtering algorithm is used to denoise the image data. This algorithm can dynamically adjust the filtering strength according to the local characteristics of the image, effectively removing noise, especially salt and pepper noise. The denoised image data is smoother while retaining important image features such as edges and textures, ultimately obtaining denoised image data.

[0035] S13: Processing the denoised image data using contrast enhancement and edge sharpening algorithms to obtain enhanced image data, and correcting the enhanced image data through geometric correction and color correction to obtain preprocessed image data.

[0036] Specifically, contrast enhancement and edge sharpening algorithms are used to process the denoised image data. These algorithms can enhance the contrast of the image, making the details of the image more prominent and the edges clearer. The enhanced image data is easier to analyze and identify, which helps to improve the accuracy of subsequent image analysis. The enhanced image data is subjected to geometric correction and color correction. Geometric correction ensures that the objects in the image are consistent with their actual physical positions, and color correction ensures that the colors of the image are accurate. After the above steps are processed, the final pre-processed image data is obtained.

[0037] In one embodiment, if Figure 3 As shown, before step S20, that is, before the pre-processed image data is transmitted to the pre-trained detection model for analysis and before obtaining the analysis results, the method for detecting defective products in the optical cable production line further includes: S201: Collect an optical cable defect image dataset, and preprocess and label the optical cable defect image dataset to obtain a training set.

[0038] Specifically, image data containing optical cable defects are collected. These data may come from actual optical cable production lines or maintenance sites. The collected image data are preprocessed by cleaning, formatting, standardization, and other operations, and labeled. The annotation may include indicating the location and type of defects in the image. The preprocessed and labeled data are organized into a training set, which will be used to train the machine learning model.

[0039] S202: Perform forward propagation and back propagation training on the detection model built based on the convolutional neural network and the support vector machine using the training set, and optimize the detection model trained by the forward propagation and back propagation using a transfer learning method to obtain a pre-trained detection model.

[0040] Specifically, the training set is used to perform forward and back propagation training on the detection model built based on the convolutional neural network and support vector machine. The prediction results are calculated and the model parameters are adjusted according to the difference between the prediction results and the actual results. The model learns how to identify optical cable defects from images, and a transfer learning method is used to apply a specific optical cable dataset that has been extracted for other image recognition tasks to the current model for optimization. After training and optimization, a detection model with good performance is obtained, which can identify optical cable defects, that is, the pre-trained detection model.

[0041] In one embodiment, if Figure 4 As shown, in step S20, the pre-processed image data is transmitted to a pre-trained detection model for analysis to obtain analysis results, which specifically include: S21: Classify and identify the pre-processed image data to obtain defect type information.

[0042] Specifically, image processing and machine learning techniques are used to analyze the pre-processed optical cable image data to identify the types of defects in the image. Through classification and recognition, the system can determine which category the defects in the image belong to, such as cracks, scratches, dents, etc. The classification and recognition process outputs the type information of the defect, which provides the basis for subsequent defect location and severity assessment.

[0043] S22: Based on the defect type information, a target detection algorithm is used to locate the position of the defect on the optical cable to obtain defect position information.

[0044] Specifically, target detection algorithms, such as convolutional neural networks, are applied to determine the exact location of defects on optical cables. The target detection algorithm outputs the coordinates or location information of the defect, indicating the specific location of the defect in the image. The defect location information helps to accurately identify and record defects, providing accurate data for maintenance and quality control.

[0045] S23: Score the severity of defects in the pre-processed image data according to the data in the pre-trained detection model to obtain severity information.

[0046] Specifically, based on the data from the pre-trained detection model, the defects in the image are scored to assess their severity. The severity score provides a quantitative assessment of the impact that the defect may have on the performance of the optical cable, helping to determine the priority of repair work and ultimately obtaining severity information.

[0047] S24: Analyze the defect type information, defect location information, and severity information to obtain an analysis result.

[0048] Specifically, the defect type, location, and severity information are integrated and analyzed to form a complete analysis result. The analysis result provides a comprehensive view, showing the detailed information of the optical cable defects, and provides a basis for subsequent maintenance decisions and quality improvements.

[0049] In one embodiment, if Figure 5 As shown, in step S30, the analysis results are compared with the preset quality standards to obtain the optical cable defective product data, which specifically includes: S31: Set quality standard parameters, including scratch depth, bubble size, surface roughness and cable diameter uniformity.

[0050] Specifically, a series of quality standard parameters are defined to evaluate the quality of optical cables. These parameters include scratch depth, bubble size, surface roughness and cable diameter uniformity, providing clear standards for optical cable quality assessment and ensuring consistency and accuracy of the assessment.

[0051] S32: Use a weighted scoring algorithm to compare the analysis results with the quality standards and calculate a comprehensive quality score.

[0052] Specifically, a weighted scoring algorithm is applied to score the analysis results according to preset quality standard parameters. The weighted scoring algorithm will give different weights according to the importance of each parameter. Through weighted scoring, the influence of various quality parameters can be comprehensively considered to calculate the comprehensive quality score of the optical cable.

[0053] S33: Determine whether the optical cable is defective based on the comprehensive score, and classify the results into qualified, requiring further testing, and unqualified. The required further testing and unqualified scores are integrated to obtain optical cable defective product data.

[0054] Specifically, the comprehensive quality score is compared with the preset threshold to determine whether the optical cable meets the quality standards. Through this judgment, the optical cables can be divided into three categories: qualified, requiring further testing, and unqualified. The optical cables that require further testing and are judged to be unqualified are integrated to form the optical cable defective product data. The integrated data helps to track and manage those optical cables that do not meet the quality standards, providing a basis for subsequent processing and improvement.

[0055] In one embodiment, if Figure 6 As shown, the defective product detection method in the optical cable production line also includes: S50: Recording the detection results, defect types, detection time and location of the optical cable within a preset time period, and generating a detection report based on the detection results, defect types, detection time and location.

[0056] Specifically, within a preset time period, the system records the inspection results of the optical cable, including information such as defect type, inspection time and location. Based on the recorded inspection results, defect type, inspection time and location, the system generates a comprehensive inspection report to facilitate production personnel to understand the quality status of the product and take appropriate measures.

[0057] S60: Feedback the inspection report to the production control system, adjust the optical cable production parameters in real time according to the inspection report, optimize the process flow, and reduce the defective rate in subsequent production.

[0058] Specifically, the generated test report is transmitted to the optical cable production control system. Based on the quality feedback in the test report, the production control system adjusts the production parameters of the optical cable in real time. The production control system can adjust the production parameters in real time according to the data in the test report, such as adjusting the material ratio, improving the production process or optimizing the equipment settings. Through real-time adjustment, the process flow can be optimized, defects in production can be reduced, and thus the defective rate in subsequent production can be reduced.

[0059] S70: Use feedback data to optimize and adjust the pre-trained detection model to improve detection performance and stability.

[0060] Specifically, feedback data collected during the production process is used to optimize and adjust the pre-trained detection model. Through continuous learning and adjustment, the performance and stability of the detection model are improved, making the detection results more accurate and reliable.

[0061] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] In one embodiment, a device for detecting defective products in an optical cable production line is provided, and the device for detecting defective products in an optical cable production line corresponds one-to-one to the method for detecting defective products in an optical cable production line in the above embodiment. Figure 7 As shown in FIG, the defective product detection device in the optical cable production line includes an image data acquisition module, a model analysis module, a comparison module, and a sorting module. The detailed description of each functional module is as follows: An image data acquisition module is used to acquire image data of the optical cable and preprocess the image data to obtain preprocessed image data; The model analysis module is used to transmit the pre-processed image data to the pre-trained detection model for analysis to obtain the analysis results; The comparison module is used to compare the analysis results with the preset quality standards to obtain the defective optical cable data; The sorting module is used to mark and sort the corresponding optical cables according to the defective optical cable data.

[0063] Optionally, the defective product detection device in the optical cable production line further includes: The recording module is used to record the detection results, defect types, detection time and location of the optical cable within a preset time period, and generate a detection report based on the detection results, defect types, detection time and location; Feedback module, used to feed back the inspection report to the production control system, adjust the optical cable production parameters in real time according to the inspection report, optimize the process flow, and reduce the defective rate in subsequent production; The model optimization module is used to optimize and adjust the pre-trained detection model using feedback data to improve detection performance and stability.

[0064] A training data collection module is used to collect a data set of optical cable defect images, and preprocess and label the data set of optical cable defect images to obtain a training set; The model training module is used to use the training set to perform forward propagation and back propagation training on the detection model constructed based on the convolutional neural network and the support vector machine, and to optimize the detection model after the forward propagation and back propagation training using the transfer learning method to obtain the pre-trained detection model.

[0065] Optionally, the image data acquisition module includes: an image acquisition submodule, configured to use a multispectral camera to acquire surface and internal images of the optical cable at different wavelengths to obtain image data of the optical cable; a denoising submodule, configured to perform denoising on the image data using an adaptive median filtering algorithm to obtain denoised image data; The correction submodule is used to process the denoised image data using contrast enhancement and edge sharpening algorithms to obtain enhanced image data, and to correct the enhanced image data through geometric correction and color correction to obtain the preprocessed image data.

[0066] Optional model analysis modules include: A type determination submodule is used to classify and identify the pre-processed image data to obtain defect type information; a position determination submodule, configured to locate the position of the defect on the optical cable using a target detection algorithm according to the defect type information to obtain defect position information; a scoring submodule, configured to score the severity of defects in the pre-processed image data based on the data in the pre-trained detection model to obtain severity information; The combined analysis submodule is used to combine the defect type information, the defect location information and the severity information to perform analysis and obtain the analysis result.

[0067] Optional comparison modules include: A parameter setting submodule is used to set quality standard parameters, including scratch depth, bubble size, surface roughness and cable diameter uniformity; A calculation submodule, configured to compare the analysis result with the quality standard using a weighted scoring algorithm to calculate a comprehensive quality score; The data integration submodule is used to determine whether the optical cable is defective according to the comprehensive score, and classify the results into qualified, need further testing and unqualified, and integrate the need further testing and unqualified to obtain the optical cable defective data.

[0068] The specific limitations of the defective product detection device in an optical cable production line can be found in the limitations of the defective product detection method in an optical cable production line described above and will not be repeated here. Each module in the above-mentioned defective product detection device in an optical cable production line can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0069] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a method for detecting defective products in an optical cable production line.

[0070] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed: Acquiring image data of the optical cable and preprocessing the image data to obtain preprocessed image data; The pre-processed image data is transmitted to the pre-trained detection model for analysis to obtain the analysis results; Compare the analysis results with the preset quality standards to obtain the defective optical cable data; According to the defective optical cable data, the corresponding optical cables are marked and sorted.

[0071] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Acquiring image data of the optical cable and preprocessing the image data to obtain preprocessed image data; The pre-processed image data is transmitted to the pre-trained detection model for analysis to obtain the analysis results; Compare the analysis results with the preset quality standards to obtain the defective optical cable data; According to the defective optical cable data, the corresponding optical cables are marked and sorted.

[0072] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0073] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0074] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for detecting defective products in an optical cable production line, characterized in that: The method for detecting defective products in the optical cable production line comprises: Acquiring image data of the optical cable and preprocessing the image data to obtain preprocessed image data; The pre-processed image data is transmitted to a pre-trained detection model for analysis to obtain analysis results; Comparing the analysis results with the preset quality standards to obtain defective optical cable data; According to the defective optical cable data, the corresponding optical cables are marked and sorted.

2. The method for detecting defective products in an optical cable production line according to claim 1, wherein: The acquiring image data of the optical cable and preprocessing the image data to obtain the preprocessed image data comprises: Using a multispectral camera to acquire surface and internal images of the optical cable at different wavelengths to obtain image data of the optical cable; Performing denoising on the image data using an adaptive median filtering algorithm to obtain denoised image data; The denoised image data is processed using contrast enhancement and edge sharpening algorithms to obtain enhanced image data, and the enhanced image data is corrected through geometric correction and color correction to obtain the preprocessed image data.

3. The method for detecting defective products in an optical cable production line according to claim 1, wherein: Before transmitting the pre-processed image data to a pre-trained detection model for analysis to obtain an analysis result, the method for detecting defective products in an optical cable production line further includes: Collecting an optical cable defect image dataset, and preprocessing and labeling the optical cable defect image dataset to obtain a training set; The training set is used to perform forward propagation and back propagation training on the detection model constructed based on the convolutional neural network and the support vector machine, and the detection model after the forward propagation and back propagation training is optimized using a transfer learning method to obtain the pre-trained detection model.

4. The method for detecting defective products in an optical cable production line according to claim 1, wherein: The pre-processed image data is transmitted to a pre-trained detection model for analysis, and the analysis results are obtained, including: Classify and identify the pre-processed image data to obtain defect type information; Locating the position of the defect on the optical cable using a target detection algorithm according to the defect type information to obtain defect position information; Score the severity of defects in the pre-processed image data according to the data in the pre-trained detection model to obtain severity information; The defect type information, the defect location information and the severity information are combined for analysis to obtain the analysis result.

5. The method for detecting defective products in an optical cable production line according to claim 1, wherein: Comparing the analysis results with the preset quality standards to obtain the optical cable defective product data includes: Setting quality standard parameters, wherein the quality standard parameters include scratch depth, bubble size, surface roughness and cable diameter uniformity; Comparing the analysis results with the quality standards using a weighted scoring algorithm to calculate a comprehensive quality score; Whether the optical cable is defective is determined based on the comprehensive score, and the results are classified into qualified, requiring further testing, and unqualified. The required further testing and unqualified results are integrated to obtain the optical cable defective product data.

6. The method for detecting defective products in an optical cable production line according to claim 1, wherein: The method for detecting defective products in the optical cable production line further comprises: Record the inspection results, defect types, inspection time and location of the optical cable within a preset time period, and generate an inspection report based on the inspection results, defect types, inspection time and location; Feeding the inspection report back to the production control system, adjusting the optical cable production parameters in real time according to the inspection report, optimizing the process flow, and reducing the defective product rate in subsequent production; The feedback data is used to optimize and adjust the pre-trained detection model to improve detection performance and stability.

7. A defective product detection device in an optical cable production line, characterized in that: The defective product detection device in the optical cable production line comprises: An image data acquisition module is used to acquire image data of the optical cable and preprocess the image data to obtain preprocessed image data; A model analysis module is used to transmit the pre-processed image data to a pre-trained detection model for analysis to obtain analysis results; A comparison module, configured to compare the analysis results with a preset quality standard to obtain defective optical cable data; The sorting module is used to mark and sort the corresponding optical cables according to the defective optical cable data.

8. The defective product detection device in the optical cable production line according to claim 7, characterized in that: A recording module is used to record the detection results, defect types, detection time and location of the optical cable within a preset time period, and generate a detection report based on the detection results, defect types, detection time and location; A feedback module is used to feed back the inspection report to the production control system, adjust the optical cable production parameters in real time according to the inspection report, optimize the process flow, and reduce the defective product rate in subsequent production; The model optimization module is used to optimize and adjust the pre-trained detection model using feedback data to improve detection performance and stability.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for detecting defective products in an optical cable production line according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting defective products in an optical cable production line according to any one of claims 1 to 6 are implemented.

Images