Intelligent identification system of surface defects of non-welded bottle containers based on magnetic particle inspection

Abstract

The invention discloses an intelligent discrimination system for surface defects of non-welded bottle containers based on magnetic particle detection, relates to the technical field of intelligent discrimination, and is used to improve the problem of low discrimination accuracy caused by non-surface physical defects in magnetic particle detection. The system comprises collecting images of non-welded bottle containers, screening multiple defect positions according to gray values ​​in the images and obtaining the defect area of ​​each defect position, building a support vector machine model according to the defect area and gray value, calculating the category index and misjudgment rate of each defect position and setting a classification threshold, classifying and displaying each defect position, obtaining the pixel intensity value of each pixel point in the image and then calculating the complex frequency domain signal value, sampling and adjusting the camera in combination with the misjudgment rate, setting a similar range and screening out classified fuzzy positions from all defect positions for marking, obtaining the probability of defects occurring at each marked position and calculating the average gray value of each marked position, and reclassifying the display category of the marked position using a logistic regression algorithm.

Description

Technical Field

[0001] The present invention relates to the field of intelligent identification technology, and more specifically, to an intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection. Background Art

[0002] Intelligent identification technology is a method that uses artificial intelligence and machine learning algorithms to analyze and identify data. The application of intelligent identification technology to the surface defect identification system of non-welded bottle containers by magnetic particle inspection can reduce labor costs and improve identification efficiency and accuracy.

[0003] The prior art has the following deficiencies:

[0004] In the past, when judging the surface defects of containers, the defect position was identified and judged by comparing the grayscale value of each pixel in the sampled image. When the grayscale value was low, the image was black, and the position with low grayscale value was screened out in the image as the basis for defect judgment. However, when non-surface physical defects such as dust appeared on the surface of the container in the sampled image, the grayscale value was also low, which reduced the judgment accuracy and affected the judgment efficacy. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent surface defect identification system for non-welded bottle containers based on magnetic particle detection, which adjusts the image sampling clarity and combines the area of ​​the position with lower grayscale value and the pixel intensity to output the display category of each alternative defect position and performs detection modulation to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The intelligent identification system of surface defects of non-welded bottle containers based on magnetic particle detection includes a data acquisition module, a feature extraction module, a fuzzy detection module and a critical processing module, and the signal connections between the modules;

[0008] The data acquisition module is used to collect images of non-welded bottle containers and pass them to the feature extraction module to extract image features, obtain the pixel intensity value of each pixel in the image and pass it to the fuzzy detection module. When receiving the mark position passed by the critical processing module, the historical data is called to pass the probability of defects at each mark position to the critical processing module;

[0009] After receiving the non-welded bottle container image, the feature extraction module detects the gray value in the image, and selects multiple defect locations and obtains the defect area according to the preset gray threshold. The defect area and gray value in the image are combined to build a support vector machine model to calculate the category index and the misjudgment rate and set the classification threshold. The defect location is classified and displayed using the classification threshold, and the calculated misjudgment rate is passed to the fuzzy detection module. Each defect location and the category index of the corresponding defect location are passed to the critical processing module.

[0010] After receiving the pixel intensity value of each pixel in the image, the blur detection module sets the intensity sequence and calculates the complex frequency domain signal value using Laplace transform, and adjusts the sampling of the sampling camera based on the complex frequency domain signal intensity value and the error rate transmitted by the feature extraction module;

[0011] The critical processing module sets a similarity range, selects multiple classified fuzzy positions from all defect positions according to the similarity range, and marks them. The marked positions are sent to the data acquisition module. After receiving the probability of defects occurring at each marked position, the average grayscale value of each marked position is calculated and the display category of the marked position is reclassified.

[0012] In a preferred embodiment, the categories of classification display are related display, non-related display and pseudo display. The related display is a magnetic trace display formed by the leakage magnetic field generated by defects during magnetic particle inspection and the magnetic powder adsorbs the magnetic powder; the non-related display is a magnetic trace display formed by the leakage magnetic field generated by cross-sectional changes or material permeability changes during magnetic particle inspection and the magnetic powder adsorbs the magnetic powder; the pseudo display is a magnetic trace display formed by the non-leakage magnetic field adsorbing the magnetic powder.

[0013] In a preferred embodiment, the feature extraction module compares the grayscale value of each pixel in the non-welded bottle container image acquisition image with a preset grayscale threshold value, and when the grayscale value of adjacent pixels is lower than the preset grayscale threshold value, the adjacent pixels are merged to obtain the defect position, and after obtaining multiple defect positions, the defect area is calculated according to the pixel size and the number of pixels corresponding to the defect position;

[0014] The average value of the grayscale value of each defect position is calculated as the defect grayscale value of the corresponding defect position, and the defect grayscale value and defect area of ​​each defect position are merged into a grayscale value data set and an area data set respectively.

[0015] In a preferred embodiment, the feature extraction module integrates the gray value data set and the area data set to construct a support vector machine model to calculate the category index of each defect position. The specific steps are as follows:

[0016] Step A1: input the gray value data set and the area data set as analysis features into the support vector machine;

[0017] Step A2: Select the Sigmoid function as the kernel function to transform the input features. The Sigmoid function is: ,in, is the kernel function result after feature conversion, is the hyperbolic tangent function, is a hyperparameter, c is a control constant, x and y are two data corresponding to the defect position in the gray value data set and the area data set respectively; the kernel function result obtained by transforming the corresponding data features in the two data sets where each defect position is located is used as the category index of the corresponding defect position;

[0018] Step A3: Use the percentile method to set two adjustment coefficients to converge and classify the kernel function results. The formula is: , ,in, and are two adjustment coefficients, and are the convergence results of the two kernel functions, is the summed average of all category indices; the two kernel function results after convergence are used as classification thresholds;

[0019] Step A4: Determine the defect category, compare the category index of each defect position with the two classification thresholds, select the maximum value of the two classification thresholds and mark it as a, select the minimum value of the two classification thresholds and mark it as b, mark the defect position with a category index exceeding a as 1, mark the defect position with a category index between a and b as 2, and mark the defect position with a category index lower than b as 3;

[0020] Step A5: Output the judgment result. When the defect position is marked as 1, the defect position is marked as a related display and output; when the defect position is marked as 2, the defect position is marked as a non-related display and output; when the defect position is marked as 3, the defect position is marked as a pseudo display and output; the category index, display category and classification threshold of each defect position are output.

[0021] In a preferred embodiment, the feature extraction module accesses the image library to obtain the magnetic trace results of each defect position in the image, and uses the magnetic trace results of each defect position as a reference data set.

[0022] The specific steps of calculating the misjudgment rate using the support vector machine model based on the display categories of each defect location and the reference data set are as follows:

[0023] Step B1: data preprocessing, sorting and numbering the display categories of each defect position according to the data in the reference data set, and merging the sorted display categories into a discriminant data set;

[0024] Step B2: Setting evaluation rules, comparing the data in the discrimination data set with the corresponding data in the control data set according to the labels, if the display categories are the same, the defect location is marked as correct; if the display categories are different, the defect location is marked as wrong;

[0025] Step B3: Calculate the false positive rate, randomly divide the discrimination data set and the control data set into n subsets of equal size and correspond one to one according to the serial number, select one subset as the test set each time, and the remaining n-1 subsets as the training set, count the number of wrong labels in the test set, and take the ratio of the number of wrong labels to the total amount of test set data as the error rate of the test set; after calculating the error rate of the test set, randomly select a subset from the training set and calculate the error rate and then eliminate it; take the average of all the calculated error rates as the false positive rate for output.

[0026] In a preferred embodiment, after receiving the pixel intensity of each pixel in the image, the blur detection module sets an intensity sequence for the pixel in the defect area and calculates the complex frequency domain signal value by Laplace transform and performs normalization and numerical compression to obtain the complex frequency domain signal compression value;

[0027] The geometric mean method is used to calculate the adjustment correction value based on the comprehensive complex frequency domain signal compression value and the error rate: , where T is the adjustment correction value, f is the complex frequency domain signal compression value, and q is the misjudgment rate.

[0028] In a preferred embodiment, the adjustment correction value is compared with a preset adjustment threshold. When the adjustment correction value exceeds the adjustment threshold, no adjustment is performed. When the adjustment correction value is lower than the adjustment threshold, the camera exposure time and rotation speed are adjusted to the corresponding precise filming gear parameters set in advance, and the adjustment correction value is taken as the inverse to obtain an adjustment ratio marked as t. The filming area of ​​the filming camera is calculated according to the adjustment ratio: ,in, is the adjusted sampling area, is the defect area at the defect location.

[0029] In a preferred embodiment, the critical processing module sets a similarity range, filters the category index of each defect area according to the similarity range to filter the defect position, selects the minimum value from the two classification thresholds as the analysis threshold, processes the analysis threshold by a preset comparison difference to obtain a similarity range, adds and subtracts a comparison difference from the analysis threshold to obtain a similarity range, marks the defect area whose category index is within the similarity range, and sends the marked position to the data acquisition module; when the data acquisition module receives the marked position, it calls the historical data to pass the probability of defects at each marked position to the critical processing module.

[0030] In a preferred embodiment, after receiving the probability of a defect at the marked position, the critical processing module counts the grayscale values ​​of each marked area and calculates the average value to obtain the average grayscale value of each area. The display category of the marked position is reclassified using a logistic regression algorithm based on the probability of a defect at each marked position and the average grayscale value, and the logistic regression coefficient is calculated using the logistic regression algorithm: , where L is the logistic regression coefficient of the marking position, e is the natural base, z is the logistic regression parameter and z is the sum of the probability of a defect occurring at the marking position and the average gray value;

[0031] When the logistic regression coefficient exceeds the preset false display discrimination threshold, the suspicious mark is classified as a non-relevant display; when the logistic regression coefficient is lower than the preset false display discrimination threshold, the suspicious mark is classified as a false display.

[0032] The technical effects and advantages of the intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection of the present invention are as follows:

[0033] The present invention collects images of non-welded bottle containers, screens multiple defect positions according to the grayscale value in the image and obtains the defect area of ​​each defect position, calculates the category index and the misjudgment rate of each defect position according to the defect area and the grayscale value, and sets a classification threshold, and classifies and displays each defect position according to the classification threshold. The classification display can improve the accuracy and efficacy of discrimination, and is convenient for subsequent processing according to different classification displays. The pixel intensity value of each pixel point in the image is obtained and then the complex frequency domain signal value is calculated. The camera is sampled and adjusted based on the complex frequency domain signal value and the misjudgment rate of each defect position. A similar range is set and classified fuzzy positions are screened out from all defect positions for marking. The probability of defects occurring at each marked position is obtained, and the average grayscale value of each marked position is calculated to reclassify the display category of the marked position, thereby improving the accuracy of defect classification of non-welded bottle containers and performing timely feedback processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the intelligent identification system of surface defects of non-welded bottle containers based on magnetic particle detection according to the present invention.

[0035] Figure 2 The present invention is a flow chart of the intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The present invention collects images of non-welded bottle containers, screens multiple defect positions according to the grayscale value in the image and obtains the defect area of ​​each defect position, calculates the category index and the misjudgment rate of each defect position according to the defect area and the grayscale value, sets a classification threshold, classifies and displays each defect position according to the classification threshold, obtains the pixel intensity value of each pixel point in the image and then calculates the complex frequency domain signal value, adjusts the camera sampling based on the complex frequency domain signal value and the misjudgment rate of each defect position, sets a similar range and screens out classified fuzzy positions from all defect positions for marking, obtains the probability of defects occurring at each marked position, calculates the average grayscale value of each marked position, and reclassifies the display category of the marked position, thereby improving the defect classification accuracy of the non-welded bottle container and performing timely feedback processing.

[0038] Embodiment, a non-welded bottle container surface defect intelligent identification system based on magnetic particle detection, such as Figure 1 As shown, it includes a data acquisition module, a feature extraction module, a fuzzy detection module and a critical processing module, and the signals between the modules are connected;

[0039] The functions of each module are as follows:

[0040] The data acquisition module is used to collect images of non-welded bottle containers and pass them to the feature extraction module to extract image features, obtain the pixel intensity value of each pixel in the image and pass it to the fuzzy detection module. When receiving the mark position passed by the critical processing module, the historical data is called to pass the probability of defects at each mark position to the critical processing module;

[0041] After receiving the non-welded bottle container image, the feature extraction module detects the gray value in the image, and selects multiple defect positions and obtains the defect area according to the preset gray threshold, constructs a support vector machine model based on the defect area and gray value in the image to calculate the category index and the misjudgment rate and set the classification threshold, and uses the classification threshold to classify the position into three display categories for display, and transmits the calculated misjudgment rate to the fuzzy detection module, and transmits each defect position and the category index of the corresponding defect position to the critical processing module;

[0042] After receiving the pixel intensity value of each pixel in the image, the blur detection module sets the intensity sequence and calculates the complex frequency domain signal value using Laplace transform, and adjusts the sampling of the sampling camera based on the complex frequency domain signal intensity value and the error rate transmitted by the feature extraction module;

[0043] The critical processing module sets a similarity range, selects multiple classified fuzzy positions from all defect positions according to the similarity range, and marks them. The marked positions are sent to the data acquisition module. After receiving the probability of defects occurring at each marked position, the average grayscale value of each marked position is calculated and the display category of the marked position is reclassified.

[0044] It should be noted that the three display categories are relevant display, non-relevant display and pseudo-display. The relevant display is the magnetic trace display formed by the leakage magnetic field generated by defects during magnetic particle inspection and the adsorption of magnetic particles, for example, surface cracks in non-welded bottle containers; the non-relevant display is the magnetic trace display formed by the leakage magnetic field generated by cross-sectional changes or material magnetic permeability changes during magnetic particle inspection and the adsorption of magnetic particles, for example, the magnetic permeability between folds is inconsistent with the normal state due to high-temperature spinning during manufacturing; the pseudo-display is the magnetic trace display formed by the non-leakage magnetic field adsorbing magnetic particles, for example, foreign objects such as wool and soil adsorbed on the bottle body.

[0045] The data acquisition module saves the non-welded bottle container image uploaded by the camera and transmits it to the feature extraction module. The data acquisition module imports the saved non-welded bottle container image into the open source library to obtain the pixel intensity value of each pixel point in the image and transmits it to the fuzzy detection module.

[0046] It should be noted that the open source library refers to a software library that is open to the public for users to view, use, modify and distribute. In this example, it is used to obtain the pixel intensity value of each pixel in the non-welded bottle container image.

[0047] After receiving the non-welded bottle container image, the feature extraction module uses the edge detection algorithm to obtain the grayscale value of each pixel in the image. In the processing of the non-welded bottle container image, the grayscale value of each pixel is compared with the preset grayscale threshold. When the grayscale value of adjacent pixels is lower than the preset grayscale threshold, the adjacent pixels are merged to obtain the defect position. After obtaining multiple defect positions, the defect area is calculated according to the pixel size and the number of pixels corresponding to the defect position.

[0048] It should be noted that the grayscale threshold is set after professionals in the field confirm the display effect of the magnetic trace features in the image, and will not be elaborated here.

[0049] The feature extraction module calculates the average value of the grayscale value of each defect position as the defect grayscale value of the corresponding defect position, and merges the defect grayscale value and defect area of ​​each defect position into a grayscale value data set and an area data set respectively;

[0050] The feature extraction module integrates the gray value data set and the area data set to build a support vector machine model to calculate the category index of each defect location. The specific steps are as follows:

[0051] Step A1: input the gray value data set and the area data set as analysis features into the support vector machine;

[0052] Step A2: Select the Sigmoid function as the kernel function to transform the input features. The Sigmoid function is: ,in, is the kernel function result after feature conversion, is the hyperbolic tangent function, is a hyperparameter, c is a control constant, x and y are two data corresponding to the defect position in the gray value data set and the area data set respectively; the kernel function result obtained by transforming the corresponding data features in the two data sets where each defect position is located is used as the category index of the corresponding defect position;

[0053] Step A3: Use the percentile method to set two adjustment coefficients to converge and classify the kernel function results. The formula is: , ,in, and are two adjustment coefficients, and are the convergence results of the two kernel functions, is the summed average of all category indices; the two kernel function results after convergence are used as classification thresholds;

[0054] Step A4: Determine the defect category, compare the category index of each defect position with the two classification thresholds, select the maximum value of the two classification thresholds and mark it as a, select the minimum value of the two classification thresholds and mark it as b, mark the defect position with a category index exceeding a as 1, mark the defect position with a category index between a and b as 2, and mark the defect position with a category index lower than b as 3;

[0055] Step A5: Output the judgment result. When the defect position is marked as 1, the defect position is marked as a related display and output; when the defect position is marked as 2, the defect position is marked as a non-related display and output; when the defect position is marked as 3, the defect position is marked as a pseudo display and output; the category index, display category and classification threshold of each defect position are output.

[0056] It should be noted that the Sigmoid function is used to convert input features into data that is easy to analyze and process, the hyperparameters are used to adjust the values ​​of the grayscale value data set and to modify the grayscale value so that it is in a correct correlation with the output result, and the control constants can be set according to actual conditions such as defect identification requirements, which will not be elaborated here.

[0057] The feature extraction module accesses the image library to obtain the determined magnetic trace results of each defect position in the image, and uses the determined magnetic trace results of each defect position as a reference data set. It should be explained that the determined magnetic trace results in the historical image are display categories corresponding to the magnetic trace categories identified by professionals.

[0058] The specific steps of calculating the misjudgment rate using the support vector machine model based on the display categories of each defect location and the reference data set are as follows:

[0059] Step B1: data preprocessing, sorting and numbering the display categories of each defect position according to the data in the reference data set, and merging the sorted display categories into a discriminant data set;

[0060] Step B2: Setting evaluation rules, comparing the data in the discrimination data set with the corresponding data in the control data set according to the labels, if the display categories are the same, the defect location is marked as correct; if the display categories are different, the defect location is marked as wrong;

[0061] Step B3: Calculate the false positive rate, randomly divide the discrimination data set and the control data set into n subsets of equal size and correspond one to one according to the serial number, select one subset each time as the test set, and the remaining n-1 subsets as the training set, count the number of wrong labels in the test set, and take the ratio of the number of wrong labels to the total amount of test set data as the error rate of the test set; after calculating the error rate of the test set, randomly select a subset from the training set and calculate the error rate and then remove it; take the average of all the calculated error rates as the false positive rate and output it;

[0062] It should be noted that when calculating the misjudgment rate, the number of divisions n is not unique and can be set by yourself, for example, n can be set to 5, etc., which will not be analyzed here.

[0063] After receiving the pixel intensity of each pixel in the image, the blur detection module sets the intensity sequence for the pixel in the defect area and calculates the complex frequency domain signal value by Laplace transform and performs normalization to obtain the complex frequency domain signal compression value. The geometric mean method is used to calculate the adjustment correction value based on the complex frequency domain signal compression value and the misjudgment rate: , where T is the adjustment correction value, f is the complex frequency domain signal compression value, and q is the misjudgment rate;

[0064] The adjustment correction value is compared with the preset adjustment threshold. When the adjustment correction value exceeds the adjustment threshold, no adjustment is performed. When the adjustment correction value is lower than the adjustment threshold, the camera exposure time and rotation speed are adjusted to the corresponding precise shooting gear parameters. The adjustment correction value is taken inversely to obtain the adjustment ratio, which is marked as t. The shooting area of ​​the shooting camera is calculated according to the adjustment ratio: ,in, is the adjusted sampling area, is the defect area at the defect location.

[0065] It should be noted that Laplace transform is a method applied to signal processing, system analysis and image processing. It is used to quantify image data and analyze image blur. The larger the complex frequency domain signal value, the larger the adjustment correction value and the clearer the image. The error rate is a reflection of the accuracy of model resolution. The higher the error rate, the smaller the adjustment correction value and the blurrier the image, and the more it is necessary to expand the sampling area. The precise sampling gear parameters corresponding to the camera exposure time and rotation speed are set by professionals according to actual conditions.

[0066] The critical processing module sets a similarity range, and screens the category index of each defect area according to the similarity range to screen the defect position. The minimum value is selected from the two classification thresholds as the analysis threshold, and the analysis threshold is processed by a preset comparison difference to obtain a similarity range. The analysis threshold is added or subtracted by a comparison difference to obtain a similarity range, and the defect area with a category index within the similarity range is marked, and the marked position is sent to the data acquisition module; when the data acquisition module receives the marked position, the historical data is called to pass the probability of defects at each marked position to the critical processing module;

[0067] It should be noted that, if the defects mentioned above are magnetic marks of non-false display classification, then the probability of defects occurring at each marking position is the probability of occurrence of magnetic marks of non-false display classification at the marking position, for example, the probability of occurrence of magnetic marks of non-false display classification at the bottle mouth.

[0068] After receiving the probability of defects at the marked position, the critical processing module counts the grayscale values ​​of each marked area and calculates the average grayscale value of each area. The display category of the marked position is reclassified using the logistic regression algorithm based on the probability of defects at each marked position and the average grayscale value, and the logistic regression coefficient is calculated using the logistic regression algorithm: , where L is the logistic regression coefficient of the marking position, e is the natural base, z is the logistic regression parameter and z is the sum of the probability of a defect occurring at the marking position and the average gray value;

[0069] When the logistic regression coefficient exceeds the preset false display discrimination threshold, the suspicious mark is classified as a non-relevant display; when the logistic regression coefficient is lower than the preset false display discrimination threshold, the suspicious mark is classified as a false display.

[0070] It should be noted that the historical data is the probability of each mark in the historical database being suspected of having defects, and is used to reclassify the display category of the suspicious mark. The larger the average grayscale value, the lower the brightness of the image, the easier it is for magnetic marks to appear at the mark position, the greater the probability of defects at the mark position or the larger the average grayscale value, the larger the logistic regression coefficient, and the greater the probability that the mark position is a non-false display.

[0071] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0072] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0073] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0075] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Intelligent identification system of surface defects of non-welded bottle containers based on magnetic particle detection, characterized in that: It includes a data acquisition module, a feature extraction module, a fuzzy detection module and a critical processing module, and the signals between the modules are connected; The data acquisition module is used to collect images of non-welded bottle containers and pass them to the feature extraction module to extract image features, obtain the pixel intensity value of each pixel in the image and pass it to the fuzzy detection module. When receiving the mark position passed by the critical processing module, the historical data is called to pass the probability of defects at each mark position to the critical processing module; After receiving the non-welded bottle container image, the feature extraction module detects the gray value in the image, and selects multiple defect locations and obtains the defect area according to the preset gray threshold. The defect area and gray value in the image are combined to build a support vector machine model to calculate the category index and the misjudgment rate and set the classification threshold. The defect location is classified and displayed using the classification threshold, and the calculated misjudgment rate is passed to the fuzzy detection module. Each defect location and the category index of the corresponding defect location are passed to the critical processing module. After receiving the pixel intensity value of each pixel in the image, the blur detection module sets the intensity sequence and calculates the complex frequency domain signal value using Laplace transform, and adjusts the sampling of the sampling camera based on the complex frequency domain signal intensity value and the error rate transmitted by the feature extraction module; The critical processing module sets a similarity range, selects multiple classified fuzzy positions from all defect positions according to the similarity range, and marks them. The marked positions are sent to the data acquisition module. After receiving the probability of defects at each marked position, the average gray value of each marked position is calculated and the display category of the marked position is reclassified. After receiving the pixel intensity of each pixel in the image, the blur detection module sets an intensity sequence for the pixel in the defect area and calculates the complex frequency domain signal value by Laplace transform and performs normalization and numerical compression to obtain the complex frequency domain signal compression value; The geometric mean method is used to calculate the adjustment correction value based on the comprehensive complex frequency domain signal compression value and the error rate: , where T is the adjustment correction value, f is the complex frequency domain signal compression value, and q is the misjudgment rate; The intensity sequence is a combination of pixel intensities of the pixels in the defect area. Laplace transform is used to calculate the complex frequency domain signal value based on the pixel intensity combination. The complex frequency domain signal is a parameter that reflects the clarity of the image. The adjustment correction value is compared with the preset adjustment threshold. When the adjustment correction value exceeds the adjustment threshold, no adjustment is performed. When the adjustment correction value is lower than the adjustment threshold, the camera exposure time and rotation speed are adjusted to the corresponding precise shooting gear parameters set in advance. The adjustment correction value is taken as the inverse to obtain the adjustment ratio, which is marked as t. The shooting area of ​​the shooting camera is calculated according to the adjustment ratio: ,in, is the adjusted sampling area, is the defect area at the defect location.

2. According to claim 1, the intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection is characterized in that: The categories of classified display are relevant display, non-relevant display and pseudo display. The relevant display is the magnetic trace display formed by the leakage magnetic field generated by the defect during magnetic particle inspection and the magnetic powder adsorbs the magnetic powder; the non-relevant display is the magnetic trace display formed by the leakage magnetic field generated by the cross-section change or the material permeability change during magnetic particle inspection and the magnetic powder adsorbs the magnetic powder; the pseudo display is the magnetic trace display formed by the non-leakage magnetic field adsorbing the magnetic powder.

3. The intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection according to claim 1 is characterized in that: The feature extraction module collects the grayscale value of each pixel in the image of the non-welded bottle container and compares the grayscale value of each pixel with the preset grayscale threshold. When the grayscale value of adjacent pixels is lower than the preset grayscale threshold, the adjacent pixels are merged to obtain the defect position. After obtaining multiple defect positions, the defect area is calculated according to the pixel size and the number of pixels corresponding to the defect position. The average value of the grayscale value of each defect position is calculated as the defect grayscale value of the corresponding defect position, and the defect grayscale value and defect area of ​​each defect position are merged into a grayscale value data set and an area data set respectively.

4. The intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection according to claim 3 is characterized in that: The feature extraction module integrates the gray value data set and the area data set to build a support vector machine model to calculate the category index of each defect location. The specific steps are as follows: Step A1: input the gray value data set and the area data set as analysis features into the support vector machine; Step A2: Select the Sigmoid function as the kernel function to transform the input features. The Sigmoid function is: ,in, is the kernel function result after feature conversion, is the hyperbolic tangent function, is a hyperparameter, c is a control constant, x and y are two data corresponding to the defect position in the gray value data set and the area data set respectively; the kernel function result obtained by transforming the corresponding data features in the two data sets where each defect position is located is used as the category index of the corresponding defect position; Step A3: Use the percentile method to set two adjustment coefficients to converge and classify the kernel function results. The formula is: , ,in, and are two adjustment coefficients, and are the convergence results of the two kernel functions, is the summed average of all category indices; the two kernel function results after convergence are used as classification thresholds; Step A4: Determine the defect category, compare the category index of each defect position with the two classification thresholds, select the maximum value of the two classification thresholds and mark it as a, select the minimum value of the two classification thresholds and mark it as b, mark the defect position with a category index exceeding a as 1, mark the defect position with a category index between a and b as 2, and mark the defect position with a category index lower than b as 3; Step A5: Output the discrimination result. When the defect position is marked as 1, the defect position is marked as a relevant display and output; when the defect position is marked as 2, the defect position is marked as a non-relevant display and output; when the defect position is marked as 3, the defect position is marked as a pseudo display and output; output the category index, display category and classification threshold of each defect position; The Sigmoid function is used to convert input features into kernel function processing data types.

5. The intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection according to claim 4 is characterized in that: The feature extraction module accesses the image library to obtain the magnetic trace results of each defect position in the image, and uses the magnetic trace results of each defect position as a reference data set. The specific steps of calculating the misjudgment rate using the support vector machine model based on the display categories of each defect location and the reference data set are as follows: Step B1: data preprocessing, sorting and numbering the display categories of each defect position according to the data in the reference data set, and merging the sorted display categories into a discriminant data set; Step B2: Set the evaluation rules, compare the data in the discrimination data set with the corresponding data in the control data set according to the labels, and if the displayed categories are the same, mark the defect location as correct; If the display categories are not the same, the defect location is marked as an error; Step B3: Calculate the false positive rate, randomly divide the discrimination data set and the control data set into n subsets of equal size and correspond one to one according to the serial number, select one subset as the test set each time, and the remaining n-1 subsets as the training set, count the number of wrong labels in the test set, and take the ratio of the number of wrong labels to the total amount of test set data as the error rate of the test set; after calculating the error rate of the test set, randomly select a subset from the training set and calculate the error rate and then remove it; take the average of all the calculated error rates as the false positive rate and output it; The magnetic trace results determined in the historical image are the display categories corresponding to the identified magnetic trace categories.

6. The intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection according to claim 4 is characterized in that: The critical processing module sets a similarity range, and screens the category index of each defect area according to the similarity range to screen the defect location. The minimum value is selected as the analysis threshold from the two classification thresholds, and the analysis threshold is processed by a preset comparison difference to obtain a similarity range. The analysis threshold is added or subtracted by a comparison difference to obtain a similarity range, and the defect area with a category index within the similarity range is marked, and the marked position is sent to the data acquisition module; When the data acquisition module receives the marked position, it calls the historical data to pass the probability of defects occurring at each marked position to the critical processing module.

7. The intelligent identification system for surface defects of non-welded bottle containers based on magnetic particle detection according to claim 6 is characterized by: After receiving the probability of defects at the marked position, the critical processing module counts the grayscale values ​​of each marked area and calculates the average grayscale value of each area. The display category of the marked position is reclassified using the logistic regression algorithm based on the probability of defects at each marked position and the average grayscale value, and the logistic regression coefficient is calculated using the logistic regression algorithm: , where L is the logistic regression coefficient of the marking position, e is the natural base, z is the logistic regression parameter and z is the sum of the probability of a defect occurring at the marking position and the average gray value; When the logistic regression coefficient exceeds the preset false display discrimination threshold, the mark forgery is classified as non-relevant display; when the logistic regression coefficient is lower than the preset false display discrimination threshold, the mark forgery is classified as false display.

Images