A method and system for realizing the positioning of abnormal points in laser die-cutting processing

Abstract

The present invention relates to the technical field of die processing, and discloses a method and system for abnormal point positioning in laser die processing, including: calculating a feature anomaly index corresponding to a physical quantity feature and identifying abnormal features in the physical quantity feature; analyzing the abnormal evolution context between abnormal features, drawing an abnormal conduction trajectory corresponding to the abnormal features, and determining a region to be detected of the equipment used in laser die processing; calculating the material absorption rate of the die material with respect to the laser; performing point marking on the region to be detected to obtain initial marked points, collecting an image of the laser die in the region to be detected to obtain a regional die image, and analyzing the point anomaly factors corresponding to the initial marked points; performing positioning processing on the point anomaly factors to obtain abnormal factor positioning, and generating a positioning result of abnormal points in laser die processing. The main purpose of the present invention is to solve the problem of poor accuracy in the abnormal point positioning method for laser die processing.

Description

Technical Field

[0001] The present invention relates to a method and system for locating abnormal points in laser knife die machining, belonging to the technical field of knife die machining. Background Art

[0002] Laser knife die machining plays an important role in modern manufacturing. With the increasing market demand for high-precision and complex-shaped products, higher requirements are put forward for the quality and efficiency of laser knife die machining. In order to ensure the accuracy and stability of laser knife die machining, it is crucial to locate abnormal points in a timely manner.

[0003] The existing methods for locating abnormal points in laser knife die machining mainly rely on manual inspection and experience judgment. Inspectors use the naked eye to observe and simple measuring tools to check the machined knife die, and find out the possible abnormal points. However, this method is inefficient, the accuracy is difficult to guarantee, and it is easily affected by the subjective factors of the inspectors. At the same time, for some tiny abnormal points, manual inspection is often difficult to detect, which may lead to product quality problems. Therefore, the existing methods for locating abnormal points in laser knife die machining have the problem of poor accuracy and cannot meet the high-quality and high-efficiency requirements of modern manufacturing for laser knife die machining. Therefore, a method for accurately locating abnormal points in laser knife die machining is needed. Summary of the Invention

[0004] The present invention provides a method and system for locating abnormal points in laser knife die machining, and its main purpose is to solve the problem of poor accuracy in the method for locating abnormal points in laser knife die machining.

[0005] To achieve the above object, a method for locating abnormal points in laser knife die machining provided by the present invention includes:

[0006] Collect physical quantity data of the equipment used in laser knife die machining, extract features from the physical quantity data to obtain physical quantity features, calculate the feature abnormal index corresponding to the physical quantity features, and identify abnormal features in the physical quantity features based on the feature abnormal index;

[0007] Analyze the abnormal evolution context among the abnormal features, draw the abnormal conduction trajectory corresponding to the abnormal features based on the abnormal evolution context, and determine the area to be detected of the equipment used in laser knife die machining based on the abnormal conduction trajectory;

[0008] Obtain the laser performance parameters corresponding to the laser knife die in the area to be detected, query the knife die material corresponding to the laser knife die and its corresponding material optical parameters, and calculate the material absorption rate of the knife die material with respect to the laser based on the laser performance energy and the material optical parameters;

[0009] Combined with the preset reference absorption rate and the material absorption rate, perform point marking on the area to be detected to obtain initial marked points, collect images of the laser knife die of the area to be detected to obtain an area knife die image, and based on the area knife die image, analyze the point anomaly factors corresponding to the initial marked points;

[0010] Perform positioning processing on the point anomaly factors to obtain anomaly factor positioning, and combine the point anomaly factors and the anomaly factor positioning to generate the positioning result of the abnormal points under laser knife die processing.

[0011] Optionally, the extracting physical quantity features from the physical quantity data includes:

[0012] Perform smoothing processing on the physical quantity data to obtain smoothed physical quantity data;

[0013] Analyze the data attributes corresponding to the smoothed physical quantity data, and extract the initial physical quantity features corresponding to the smoothed physical quantity data;

[0014] Parse the physical quantity labels corresponding to the initial physical quantity features, and analyze the correlation between the data attributes and the physical quantity labels;

[0015] Based on the correlation, perform feature selection processing on the initial physical quantity features to obtain physical quantity features.

[0016] Optionally, the calculating the feature anomaly index corresponding to the physical quantity features includes:

[0017] Calculate the feature equilibrium value corresponding to the physical quantity features, and based on the feature equilibrium value, calculate the feature standard deviation corresponding to the physical quantity features;

[0018] Combined with the feature equilibrium value and the feature standard deviation, calculate the feature anomaly index corresponding to the physical quantity features through the following formula:

[0019] ;

[0020] where A represents the feature anomaly index corresponding to the physical quantity features, represents the value corresponding to the a-th feature in the physical quantity features, represents the feature equilibrium value, represents the feature standard deviation, a represents the serial number corresponding to the physical quantity features, and q represents the quantity corresponding to the material quantity features.

[0021] Optionally, the analyzing the abnormal evolution context between the abnormal features includes:

[0022] Perform clustering processing on the abnormal features to obtain clustered abnormal features;

[0023] Calculate the feature distance values between the clustered abnormal features, and analyze the abnormal evolution trend corresponding to the clustered abnormal features based on the feature distance values;

[0024] Perform feature fusion processing on the clustered abnormal features to obtain fused abnormal features;

[0025] Calculate the feature interaction intensity between the fused abnormal features, and determine the associated abnormal features in the fused abnormal features based on the feature interaction intensity;

[0026] Combine the associated abnormal features and the abnormal evolution trend to generate the abnormal evolution context between the abnormal features.

[0027] Optionally, the calculating the feature interaction intensity between the fused abnormal features includes:

[0028] Perform normalization processing on the fused abnormal features to obtain standard abnormal features;

[0029] Calculate the feature variance corresponding to the fused abnormal features based on the standard abnormal features;

[0030] Measure the feature probability corresponding to the standard abnormal features, and calculate the feature information entropy corresponding to the fused abnormal features based on the feature probability;

[0031] Calculate the covariance matrix between the fused abnormal features, and combine the covariance matrix, the feature variance, and the feature information entropy to calculate the feature interaction intensity between the fused abnormal features through the following formula:

[0032] ;

[0033] where D represents the feature interaction intensity between the fused abnormal features, represents the covariance matrix, represents the feature variance corresponding to the c-th feature in the fused abnormal features, represents the feature variance corresponding to the d-th feature in the fused abnormal features, c and d represent the serial numbers corresponding to the fused abnormal features, represents the balance coefficient, and respectively represent the feature information entropy corresponding to the c-th feature and the d-th feature in the fused abnormal features, and r represents the number of features of the fused abnormal features.

[0034] Optionally, the determining the area to be detected of the equipment used in the laser die-cutting based on the abnormal conduction trajectory includes:

[0035] Query the equipment efficiency corresponding to the equipment used in laser knife mold processing, and analyze the efficiency driving factors and efficiency output factors in the equipment efficiency;

[0036] Combine the efficiency driving factors and the efficiency output factors to analyze the equipment causal relationship between the equipment used in laser knife mold processing;

[0037] Combine the equipment causal relationship and the abnormal conduction trajectory to determine the area to be detected of the equipment used in laser knife mold processing.

[0038] Optionally, the calculating the material absorption rate of the knife mold material with respect to the laser based on the laser performance energy and the material optical parameters includes:

[0039] Extract the photon characteristic scale of the laser from the laser performance energy;

[0040] Based on the material optical parameters, determine the material attenuation coefficient corresponding to the knife mold material;

[0041] Combine the photon characteristic scale and the material attenuation coefficient, and calculate the material absorption rate of the knife mold material with respect to the laser through the following formula:

[0042] ;

[0043] where G represents the material absorption rate, represents the material attenuation coefficient, represents the photon characteristic scale.

[0044] Optionally, the determining the material attenuation coefficient corresponding to the knife mold material based on the material optical parameters includes:

[0045] Schedule the material size information corresponding to the knife mold material, and based on the material size information, determine the material thickness corresponding to the knife mold material;

[0046] Use a preset spectrophotometer to measure the material transmittance corresponding to the knife mold material;

[0047] Combine the material thickness and the material transmittance, and determine the material attenuation coefficient corresponding to the knife mold material through the following formula:

[0048] ;

[0049] where K represents the material attenuation coefficient corresponding to the knife mold material, I represents the material transmittance, and L represents the material thickness.

[0050] Optionally, the analyzing the point anomaly factors corresponding to the initial marking points by combining the regional knife mold image includes:

[0051] According to the initial marked points, segment the die image of the area to obtain a marked point image;

[0052] Perform image noise reduction processing on the marked point image to obtain a noise-reduced point image, and perform image enhancement processing on the noise-reduced point image to obtain an enhanced point image;

[0053] Extract the point color features corresponding to the enhanced point image, perform grayscale processing on the enhanced point image to obtain a point grayscale image;

[0054] Extract the point texture features corresponding to the point grayscale image, and combine the point texture features, the point color features and a preset standard point library to analyze the point abnormal factors corresponding to the initial marked points.

[0055] A system for realizing abnormal point positioning under laser die processing, the system includes:

[0056] An abnormal feature recognition module, configured to collect physical quantity data of the equipment used in laser die processing, extract features from the physical quantity data to obtain physical quantity features, calculate a feature abnormal index corresponding to the physical quantity features, and based on the feature abnormal index, identify abnormal features in the physical quantity features;

[0057] A region division module, configured to analyze the abnormal evolution context between the abnormal features, draw an abnormal conduction trajectory corresponding to the abnormal features based on the abnormal evolution context, and determine a region to be detected of the equipment used in laser die processing based on the abnormal conduction trajectory;

[0058] A material absorption rate calculation module, configured to obtain laser performance parameters corresponding to the laser die of the region to be detected, query the die material corresponding to the laser die and its corresponding material optical parameters, and calculate the material absorption rate of the die material with respect to the laser based on the laser performance energy and the material optical parameters;

[0059] An abnormal factor analysis module, configured to combine a preset reference absorption rate and the material absorption rate, mark points in the region to be detected to obtain initial marked points, collect an image of the laser die in the region to be detected to obtain a die image of the region, and analyze the point abnormal factors corresponding to the initial marked points based on the die image of the region;

[0060] An abnormal positioning module, configured to perform positioning processing on the point abnormal factors to obtain an abnormal factor positioning, and generate a positioning result of the abnormal points under laser die processing by combining the point abnormal factors and the abnormal factor positioning.

[0061] Compared with the problems described in the background art, the present invention can extract key feature information from the physical quantity data through feature extraction of the physical quantity data, convert the physical quantity data into more representative features, and lay a basis for subsequent calculation of the feature anomaly index. By analyzing the abnormal evolution context between the abnormal features, the present invention can obtain the evolution law between the abnormal features, and based on the abnormal evolution context, draw the abnormal conduction trajectory corresponding to the abnormal features to obtain the abnormal conduction route corresponding to the abnormal features, thereby providing a basis for subsequent determination of the area to be detected. By obtaining the laser performance parameters corresponding to the laser die mold in the area to be detected, the present invention can obtain the performance description parameters of the laser used in the laser die mold processing, and query the die mold material corresponding to the laser die mold and its corresponding material optical parameters to understand the index information of the response characteristics of the die mold material to light. By combining the preset reference absorption rate and the material absorption rate, the present invention can mark the points in the area to be detected, mark the points with abnormalities in the area to be detected, and collect images of the laser die mold in the area to be detected to obtain the image corresponding to the laser die mold in the area to be detected, so as to improve the recognition accuracy of the subsequent abnormally marked points. By performing positioning processing on the point anomaly factors, the present invention can obtain the specific positions corresponding to the point anomaly factors, and combine the point anomaly factors and the anomaly factor positioning to obtain the accurate positioning result of the abnormal points under the laser die mold processing. Therefore, the present invention proposes a method and system for realizing abnormal point positioning under laser die mold processing to improve the accuracy of abnormal point positioning under laser die mold processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 FIG. is a schematic flowchart of a method for realizing abnormal point positioning under laser die mold processing provided by an embodiment of the present invention;

[0063] Figure 2 FIG. is a functional module diagram of a system for realizing abnormal point positioning under laser die mold processing provided by an embodiment of the present invention.

[0064] The realization of the object, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0066] An embodiment of the present application provides a method for locating abnormal points in laser knife die machining. The execution subject of the method for locating abnormal points in laser knife die machining includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for locating abnormal points in laser knife die machining can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0067] Embodiment 1:

[0068] Referring to Figure 1 As shown in the figure, it is a flowchart of a method for locating abnormal points in laser knife die machining provided by an embodiment of the present invention. In this embodiment, the method for locating abnormal points in laser knife die machining includes:

[0069] S1. Collect physical quantity data of the equipment used in laser knife die machining, extract features from the physical quantity data to obtain physical quantity features, calculate a feature anomaly index corresponding to the physical quantity features, and identify abnormal features in the physical quantity features based on the feature anomaly index.

[0070] By extracting features from the physical quantity data in the present invention, key feature information in the physical quantity data can be obtained, and the physical quantity data can be transformed into more representative features, laying a basis for subsequent calculation of the feature anomaly index.

[0071] It should be explained that the laser knife die is a die for processing various materials, the physical quantity data is a record of the operating state parameters of the equipment used in laser knife die machining, and the physical quantity feature is the key attribute manifestation corresponding to the physical quantity data. Exemplarily, the collection of the physical quantity data of the equipment used in laser knife die machining can be achieved through sensors, such as temperature sensors, pressure sensors, and vibration sensors, etc.

[0072] Specifically, the extracting features from the physical quantity data to obtain physical quantity features includes:

[0073] Perform smoothing processing on the physical quantity data to obtain smoothed physical quantity data;

[0074] Analyze the data attributes corresponding to the smoothed physical quantity data, and extract the initial physical quantity features corresponding to the smoothed physical quantity data;

[0075] Parse the physical quantity labels corresponding to the initial physical quantity features, and analyze the correlation between the data attributes and the physical quantity labels;

[0076] Based on the correlation, feature selection processing is performed on the initial physical quantity feature to obtain a physical quantity feature.

[0077] It should be explained that the smoothed physical quantity data is the data obtained after the noise in the physical quantity data is removed, the data attribute is the data property corresponding to the smoothed physical quantity data, such as statistical properties or data distribution form, etc., the initial physical quantity feature is all the essential characteristics corresponding to the smoothed physical quantity data, the physical quantity label is the characteristic property corresponding to the initial physical quantity feature, and the correlation represents the degree of mutual correlation between the data attribute and the physical quantity label.

[0078] Exemplarily, the smoothing of the physical quantity data can be achieved by a moving average method; the analysis of the data attributes corresponding to the smoothed physical quantity data can be achieved by a principal component analysis method; the extraction of the initial physical quantity features corresponding to the smoothed physical quantity data can be achieved by a feature engineering algorithm; the parsing of the physical quantity labels corresponding to the initial physical quantity features can be achieved by a manual labeling method; the analysis of the synergy between the data attributes and the physical quantity labels can be achieved by a correlation analysis algorithm; based on the level of the synergy, the initial physical quantity features are subjected to feature selection processing to obtain physical quantity features, and the features with high synergy are selected and retained to obtain physical quantity features.

[0079] The present invention calculates the characteristic anomaly index corresponding to the physical quantity feature, and can understand the degree of abnormality corresponding to the physical quantity feature through the characteristic anomaly index, and identify the abnormal features in the physical quantity feature based on the characteristic anomaly index, and then obtain the abnormal feature subset in the material quantity feature, so as to facilitate subsequent abnormal analysis and processing. It should be explained that the characteristic anomaly index represents the degree of abnormality corresponding to the physical quantity feature, and the abnormal feature is the abnormal performance part in the physical quantity feature; exemplarily, based on the comparison result of the characteristic anomaly index and a preset index threshold, the abnormal feature in the physical quantity feature is identified. If the characteristic anomaly index exceeds the preset index threshold, it indicates that the feature has an abnormal situation, and the physical quantity feature is used as the abnormal feature.

[0080] In detail, the calculation of the characteristic anomaly index corresponding to the physical quantity characteristic includes:

[0081] Calculating a characteristic equilibrium value corresponding to the physical quantity characteristic, and calculating a characteristic standard deviation corresponding to the physical quantity characteristic based on the characteristic equilibrium value;

[0082] Combining the characteristic equilibrium value and the characteristic standard deviation, the characteristic anomaly index corresponding to the physical quantity characteristic is calculated by the following formula:

[0083] ;

[0084] Among them, A represents the characteristic anomaly index corresponding to the physical quantity characteristic, represents the value corresponding to the a-th characteristic among the physical quantity characteristics, represents the characteristic equilibrium value, represents the characteristic standard deviation, a represents the serial number corresponding to the physical quantity characteristic, and q represents the quantity corresponding to the material quantity characteristic.

[0085] It should be explained that the characteristic equilibrium value is the average value corresponding to the physical quantity characteristic, and the characteristic standard deviation is a description of the degree of dispersion corresponding to the physical quantity characteristic. Exemplarily, the calculation of the characteristic equilibrium value corresponding to the physical quantity characteristic can be realized through an average function; the calculation of the characteristic standard deviation corresponding to the physical quantity characteristic can be realized through a standard deviation formula.

[0086] S2. Analyze the abnormal evolution context among the abnormal characteristics. Based on the abnormal evolution context, draw the abnormal conduction trajectory corresponding to the abnormal characteristics. Based on the abnormal conduction trajectory, determine the area to be detected of the equipment used in laser die cutting.

[0087] Through analyzing the abnormal evolution context among the abnormal characteristics, the present invention can obtain the evolution law among the abnormal characteristics, and based on the abnormal evolution context, draw the abnormal conduction trajectory corresponding to the abnormal characteristics, and can obtain the abnormal conduction route corresponding to the abnormal characteristics, thereby providing a basis for the subsequent determination of the area to be detected.

[0088] It should be explained that the abnormal evolution context is the abnormal evolution trend or evolution law among the abnormal characteristics, and the abnormal conduction trajectory is the abnormal conduction path corresponding to the abnormal characteristics. Exemplarily, based on the abnormal evolution context, draw the abnormal conduction trajectory corresponding to the abnormal characteristics, and combine with drawing software, taking time as the axis, connect the abnormal characteristics in sequence to form an abnormal conduction trajectory.

[0089] Specifically, the analysis of the abnormal evolution context among the abnormal characteristics includes:

[0090] Perform clustering processing on the abnormal characteristics to obtain clustered abnormal characteristics;

[0091] Calculate the characteristic distance values among the clustered abnormal characteristics, and based on the characteristic distance values, analyze the abnormal evolution trend corresponding to the clustered abnormal characteristics;

[0092] Perform feature fusion processing on the clustered abnormal characteristics to obtain fused abnormal characteristics;

[0093] Calculate the feature interaction intensity between the fused abnormal features, and determine the associated abnormal features in the fused abnormal features based on the feature interaction intensity;

[0094] Combine the associated abnormal features and the abnormal evolution trend to generate the abnormal evolution context between the abnormal features.

[0095] It should be explained that the clustered abnormal features are the feature sets obtained by clustering the features of the same nature in the abnormal features, the feature distance value represents the separation degree between the clustered abnormal features, the abnormal evolution trend is the change trend corresponding to the clustered abnormal features, the fused abnormal features are the features obtained by merging the features in the clustered abnormal features, the feature interaction intensity represents the mutual influence degree between the fused abnormal features, and the associated abnormal features are the features with an associated relationship in the fused abnormal features.

[0096] Exemplarily, the clustering process of the abnormal features can be implemented by a clustering algorithm, such as the K-Means algorithm; the feature distance value between the clustered abnormal features can be implemented by the Euclidean distance algorithm; based on the feature distance value, analyze the abnormal evolution trend corresponding to the clustered abnormal features. For example, if the feature distance value between two clustered abnormal features gradually increases, it may indicate that the abnormality is developing in different directions and the difference is expanding. If the feature distance value gradually decreases, it may mean that the abnormality has a convergent evolution trend; the feature fusion process of the clustered abnormal features can be implemented by an autoencoder; when the feature interaction intensity is greater than a preset intensity, determine the associated abnormal features in the fused abnormal features. The preset intensity can be set to 0.8, or it can be set according to the specific application scenario.

[0097] Further, as an optional embodiment of the present invention, the calculating the feature interaction intensity between the fused abnormal features includes:

[0098] Perform normalization processing on the fused abnormal features to obtain standard abnormal features;

[0099] Based on the standard abnormal features, calculate the feature variance corresponding to the fused abnormal features;

[0100] Measure the feature probability corresponding to the standard abnormal features, and based on the feature probability, calculate the feature information entropy corresponding to the fused abnormal features;

[0101] Calculate the covariance matrix between the fused abnormal features, and combine the covariance matrix, the feature variance, and the feature information entropy to calculate the feature interaction intensity between the fused abnormal features through the following formula:

[0102] ;

[0103] Among them, D represents the feature interaction intensity between abnormal fusion features. represents the covariance matrix. represents the feature variance corresponding to the c-th feature in the abnormal fusion features. represents the feature variance corresponding to the d-th feature in the abnormal fusion features. c and d represent the serial numbers corresponding to the abnormal fusion features. represents the balance coefficient. and respectively represent the feature information entropy corresponding to the c-th feature and the d-th feature in the abnormal fusion features. r represents the number of features of the abnormal fusion features.

[0104] It should be explained that the standard abnormal features are the features obtained after eliminating the differences between the abnormal fusion features. The feature information entropy represents the amount of information corresponding to the abnormal fusion features. The covariance matrix is the covariance value between the abnormal fusion features. The balance coefficient is used to balance and adjust the role of the information entropy. It can be set by the empirical method. According to the processing experience of previous similar problems or the suggestions of domain experts, an initial value is set, and then through continuous experiments and adjustments, observing the result changes of the feature interaction intensity to find a more appropriate value. For example, it can be first tried to be set to 0.5, and observe whether the calculated feature interaction intensity meets the expectations. If not, the value can be gradually increased or decreased until a satisfactory result is obtained. Exemplarily, the normalization processing of the abnormal fusion features can be achieved through the normalization method; the calculation of the feature variance corresponding to the abnormal fusion features can be achieved through the variance calculation formula; the feature probability corresponding to the standard abnormal features can be achieved through statistical methods; the feature information entropy corresponding to the abnormal fusion features can be achieved through the Shannon entropy algorithm; the calculation of the covariance matrix between the abnormal fusion features can be achieved through software or libraries for matrix operations (such as the NumPy library in Python).

[0105] The present invention determines the area to be detected of the equipment used in the laser die-cutting processing based on the abnormal conduction trajectory, which can clarify the area where abnormalities will occur in the laser die-cutting processing, thereby narrowing the positioning range of the abnormal points. It should be explained that the area to be detected is the high-incidence area within the processing area corresponding to the equipment used in the laser die-cutting processing.

[0106] Specifically, the determining the area to be detected of the equipment used in the laser die-cutting processing based on the abnormal conduction trajectory includes:

[0107] Query the equipment efficiency corresponding to the equipment used in the laser die-cutting processing, and analyze the efficiency driving factors and efficiency output factors in the equipment efficiency.

[0108] Analyze the equipment causal relationship among the equipment used in laser die - cutting based on the above - mentioned performance - driving factors and performance - output factors;

[0109] Based on the equipment causal relationship and the abnormal conduction trajectory, determine the area to be detected for the equipment used in laser die - cutting.

[0110] It should be noted that the equipment performance is the equipment function description information corresponding to the equipment used in laser die - cutting. The performance - driving factor and the performance - output factor are respectively the function input and function output in the equipment performance. The equipment causal relationship is the processing logic relationship among the equipment used in laser die - cutting. Exemplarily, the equipment performance corresponding to the equipment used in laser die - cutting can be obtained by querying the official website information of the equipment manufacturer; the analysis of the performance - driving factor and the performance - output factor in the equipment performance can be realized through semantic analysis methods, identifying the description characters in the equipment performance, and determining the performance - driving factor and the performance - output factor according to the semantic meaning of the description characters; the analysis of the equipment causal relationship among the equipment used in laser die - cutting can be realized through the fish - bone diagram method, constructing a fish - bone diagram between the performance - driving factor and the performance - output factor to analyze the equipment causal relationship; according to the equipment causal relationship, determine the associated equipment in the equipment, identify the abnormal equipment according to the abnormal conduction trajectory, combine the abnormal equipment and the associated equipment to determine the final abnormal equipment, obtain the equipment processing area corresponding to the final abnormal equipment, and use the equipment processing area as the area to be detected for the equipment used in laser die - cutting.

[0111] S3. Obtain the laser performance parameters corresponding to the laser die in the area to be detected, query the die material corresponding to the laser die and its corresponding material optical parameters, and calculate the material absorption rate of the die material with respect to the laser based on the laser performance energy and the material optical parameters.

[0112] By obtaining the laser performance parameters corresponding to the laser die in the area to be detected, the present invention can obtain the performance description parameters of the laser used in the laser die - cutting process, and by querying the die material corresponding to the laser die and its corresponding material optical parameters, it can understand the index information of the response characteristics of the die material to light.

[0113] It should be noted that the laser performance parameters are the performance description parameters corresponding to the laser die in the area to be detected. The die material is the material used for the laser die, and the material optical parameters are the index information of the response characteristics of the die material to light. Exemplarily, the laser performance parameters corresponding to the laser die in the area to be detected can be obtained through the control panel of the laser generator in this area; the die material corresponding to the laser die and its corresponding material optical parameters can be queried from the Internet through a human - machine interaction method.

[0114] Based on the laser performance energy and the material optical parameters, the present invention calculates the material absorption rate of the die material with respect to the laser, and a quantitative index of the absorption degree of the die material to the laser can be obtained, laying a foundation for subsequent point marking of the area to be detected. It should be noted that the material absorption rate represents the absorption degree of the die material to the laser.

[0115] Specifically, the calculating the material absorption rate of the die material with respect to the laser based on the laser performance energy and the material optical parameters includes:

[0116] Extracting the photon characteristic scale of the laser from the laser performance energy;

[0117] Based on the material optical parameters, determining the material attenuation coefficient corresponding to the die material;

[0118] Combining the photon characteristic scale and the material attenuation coefficient, calculating the material absorption rate of the die material with respect to the laser through the following formula:

[0119] ;

[0120] where G represents the material absorption rate, represents the material attenuation coefficient, represents the photon characteristic scale.

[0121] It should be noted that the photon characteristic scale is the wavelength of the laser in the laser performance energy, and the material attenuation coefficient represents the absorption ability of the die material to the laser. Exemplarily, extracting the photon characteristic scale of the laser from the laser performance energy can be achieved through an extraction function, and the extraction function is compiled by a scripting language, such as the JS scripting language.

[0122] Furthermore, as an optional embodiment of the present invention, the determining the material attenuation coefficient corresponding to the die material based on the material optical parameters includes:

[0123] Scheduling the material size information corresponding to the die material, and based on the material size information, determining the material thickness corresponding to the die material;

[0124] Using a preset spectrophotometer to measure the material transmittance corresponding to the die material;

[0125] Combining the material thickness and the material transmittance, determining the material attenuation coefficient corresponding to the die material through the following formula:

[0126] ;

[0127] Wherein, K represents the material attenuation coefficient corresponding to the die material, I represents the material transmittance, and L represents the material thickness.

[0128] It should be explained that the material size information is a description of the material physical properties corresponding to the die material. The spectrophotometer is a scientific instrument used to measure the transmission degree of a substance to light of different wavelengths. The material transmittance represents the laser transmission ability of the die material. Exemplarily, the scheduling of the material size information corresponding to the die material can be realized through a material database, and the material database is a database used to store the basic information corresponding to the die material.

[0129] S4. Combine the preset reference absorption rate and the material absorption rate, mark points on the area to be detected to obtain initial marked points, collect an image of the laser die in the area to be detected to obtain an area die image, and analyze the point anomaly factors corresponding to the initial marked points in combination with the area die image.

[0130] In the present invention, by combining the preset reference absorption rate and the material absorption rate, points are marked on the area to be detected, so that the points with anomalies in the area to be detected can be marked out. By collecting an image of the laser die in the area to be detected, an image corresponding to the laser die in the area to be detected can be obtained, which is convenient for improving the recognition accuracy of subsequent anomaly marked points. It should be explained that the preset reference absorption rate is the reference standard corresponding to the material absorption rate. If the actually measured material absorption rate differs greatly from the preset reference absorption rate, it indicates that there is an abnormal situation in the absorption of the die material to the laser in this area, which may be caused by problems with the material itself, improper laser parameter settings, or other factors during the processing. The initial marked points are the points corresponding to the laser where the material absorption rate in the area to be detected is not within the range of the preset reference absorption rate. The area die image is a visual image corresponding to the laser die in the area to be detected. Further, the point marking of the area to be detected can be realized through manual annotation; the image collection of the laser die in the area to be detected can be realized through an industrial camera.

[0131] In the present invention, by combining the area die image, the point anomaly factors corresponding to the initial marked points are analyzed, thereby understanding the abnormal reasons corresponding to the initial marked points, providing a basis for improving the accuracy of identifying anomaly marked points from the initial marked points subsequently. It should be explained that the point anomaly factors are the abnormal reasons corresponding to the initial marked points.

[0132] Specifically, the analysis of the point anomaly factors corresponding to the initial marked points by combining the area die image includes:

[0133] Segment the regional die-cutting image according to the initial marking points to obtain a marking point image;

[0134] Perform image noise reduction processing on the marking point image to obtain a noise-reduced marking point image, and perform image enhancement processing on the noise-reduced marking point image to obtain an enhanced marking point image;

[0135] Extract the point color features corresponding to the enhanced marking point image, and perform grayscale processing on the enhanced marking point image to obtain a point grayscale image;

[0136] Extract the point texture features corresponding to the point grayscale image, and combine the point texture features, the point color features, and a preset standard point library to analyze the point anomaly factors corresponding to the initial marking points.

[0137] It should be explained that the marking point image is the image corresponding to the initial marking points in the regional die-cutting image, the noise-reduced marking point image is the image obtained after noise suppression in the marking point image, the enhanced marking point image is the image obtained after enhancement processing of the noise-reduced marking point image, the point color features are the color attributes corresponding to the enhanced marking point image, the point grayscale image is the image expressed by only a single color of the enhanced marking point image, the point texture features are the microscopic structure characterizations corresponding to the point grayscale image, and the preset standard point library is a set storing various feature information of specific points on multiple normal regional die-cutting images.

[0138] Exemplarily, the segmentation processing of the regional die-cutting image can be realized by the threshold segmentation method; the image noise reduction processing of the marking point image can be realized by a low-pass filter; the image enhancement processing of the noise-reduced marking point image can be realized by the histogram equalization method; the extraction of the point color features corresponding to the enhanced marking point image can be realized by the color histogram method; the grayscale processing of the enhanced marking point image can be realized by the average value method, and the average value of the values of the three channels of the enhanced marking point image is taken as the grayscale value; the extraction of the point texture features corresponding to the point grayscale image can be realized by the gray-level co-occurrence matrix method; calculate the feature similarity between the point texture features, the point color features and the corresponding features in the preset standard point library respectively, and determine the corresponding point anomaly factors according to the feature similarity. If the feature similarity is within a reasonable range, it means that the laser die-cutting is normal, and the point anomaly factor is laser anomaly. If the feature similarity is not within a reasonable range, the point anomaly factor is that there are anomaly factors in the laser die-cutting.

[0139] S5. Perform positioning processing on the point anomaly factors to obtain anomaly factor positioning, and combine the point anomaly factors and the anomaly factor positioning to generate the positioning result of the abnormal points under laser die-cutting processing.

[0140] By performing location processing on the abnormal factors of the points, the specific positions corresponding to the abnormal factors of the points can be obtained. Combining the abnormal factors of the points and the location of the abnormal factors, an accurate location result of the abnormal points under laser die cutting can be obtained. It should be noted that the location of the abnormal factors is the specific location information corresponding to the abnormal factors of the points. Exemplarily, the location processing of the abnormal factors of the points can be achieved through the time location method. According to the time stamp corresponding to the abnormal factors of the points, the time when the abnormal points appear is determined, and then the location processing of the abnormal factors of the points is achieved to obtain the location of the abnormal factors. For example, in a production line, the processing time of different materials is recorded. When abnormal points appear in a certain area, it is found according to the time stamp that the abnormality occurs when a specific material enters the processing link, and then it is located that the problem may lie in this material, resulting in the abnormal points.

[0141] Compared with the problems described in the background art, by performing feature extraction on the physical quantity data, the key feature information in the physical quantity data can be obtained, and the physical quantity data is transformed into more representative features, laying a basis for the subsequent calculation of the feature anomaly index. By analyzing the abnormal evolution context between the abnormal features, the evolution law between the abnormal features can be obtained, and based on the abnormal evolution context, the abnormal conduction trajectory corresponding to the abnormal features can be drawn, and the abnormal conduction route corresponding to the abnormal features can be obtained, thereby providing a basis for the subsequent determination of the area to be detected. By obtaining the laser performance parameters corresponding to the laser die cutting of the area to be detected, the performance description parameters of the laser used in the laser die cutting process can be obtained, and by querying the die cutting material corresponding to the laser die cutting and its corresponding material optical parameters, the index information of the response characteristics of the die cutting material to light can be understood. By combining the preset reference absorption rate and the material absorption rate, point marking is performed on the area to be detected, and the abnormal points in the area to be detected can be marked. By performing image acquisition on the laser die cutting of the area to be detected, an image corresponding to the laser die cutting of the area to be detected can be obtained, so as to improve the recognition accuracy of the subsequent abnormally marked points. By performing location processing on the abnormal factors of the points, the specific positions corresponding to the abnormal factors of the points can be obtained. Combining the abnormal factors of the points and the location of the abnormal factors, an accurate location result of the abnormal points under laser die cutting can be obtained. Therefore, the method for realizing the location of abnormal points under laser die cutting proposed by the present invention is used to improve the accuracy of the location of abnormal points under laser die cutting.

[0142] Embodiment 2:

[0143] As Figure 2 shown, it is a functional module diagram of a system for realizing the location of abnormal points under laser die cutting provided by an embodiment of the present invention.

[0144] The abnormal point positioning system 100 for laser die processing according to the present invention can be installed in an electronic device. According to the functions implemented, the abnormal point positioning system 100 for laser die processing can include an abnormal feature recognition module 101, a region division module 102, a material absorption rate calculation module 103, an abnormal factor analysis module 104, and an abnormal positioning module 105. The modules in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0145] In this embodiment, the functions of each module / unit are as follows:

[0146] The abnormal feature recognition module 101 is used to collect physical quantity data of the equipment used in laser die processing, extract features from the physical quantity data to obtain physical quantity features, calculate the feature abnormal index corresponding to the physical quantity features, and based on the feature abnormal index, identify the abnormal features in the physical quantity features;

[0147] The region division module 102 is used to analyze the abnormal evolution context between the abnormal features, draw the abnormal conduction trajectory corresponding to the abnormal features based on the abnormal evolution context, and determine the area to be detected of the equipment used in laser die processing based on the abnormal conduction trajectory;

[0148] The material absorption rate calculation module 103 is used to obtain the laser performance parameters corresponding to the laser die in the area to be detected, query the die material corresponding to the laser die and its corresponding material optical parameters, and calculate the material absorption rate of the die material with respect to the laser based on the laser performance energy and the material optical parameters;

[0149] The abnormal factor analysis module 104 is used to combine the preset reference absorption rate and the material absorption rate, mark the points in the area to be detected to obtain the initial marked points, collect images of the laser die in the area to be detected to obtain the area die image, and analyze the point abnormal factors corresponding to the initial marked points based on the area die image;

[0150] The abnormal positioning module 105 is used to perform positioning processing on the point abnormal factors to obtain the abnormal factor positioning, and generate the positioning result of the abnormal points in laser die processing by combining the point abnormal factors and the abnormal factor positioning.

[0151] Specifically, each module in the abnormal point positioning system 100 for laser die processing described in the embodiments of the present application adopts the same as the above Figure 1The same technical means as those described in [a method for locating abnormal points in laser die-cutting processing] and capable of achieving the same technical effects will not be elaborated here.

[0152] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention. It should be noted that the content in the brackets in the translation of is for reference only, and you need to fill in the correct content according to the actual situation.

Claims

1. A method for realizing the positioning of abnormal points in laser die-cutting processing, characterized in that, The method includes: Collecting physical quantity data of the equipment used in laser die - cutting processing, extracting features from the physical quantity data to obtain physical quantity features, calculating a feature anomaly index corresponding to the physical quantity features, and identifying abnormal features in the physical quantity features based on the feature anomaly index; Analyzing the abnormal evolution context among the abnormal features, drawing an abnormal conduction trajectory corresponding to the abnormal features based on the abnormal evolution context, and determining a detection - required area of the equipment used in laser die - cutting processing based on the abnormal conduction trajectory; Obtaining laser performance parameters corresponding to the laser die in the detection - required area, querying the die material corresponding to the laser die and its corresponding material optical parameters, and calculating the material absorption rate of the die material with respect to the laser based on the laser performance parameters and the material optical parameters; Combining a preset reference absorption rate and the material absorption rate to mark points in the detection - required area to obtain initial marked points, collecting an image of the laser die in the detection - required area to obtain a regional die image, and analyzing the point - position abnormal factors corresponding to the initial marked points based on the regional die image; Performing a positioning process on the point - position abnormal factors to obtain an abnormal - factor positioning, and generating a positioning result of the abnormal points in laser die - cutting processing by combining the point - position abnormal factors and the abnormal - factor positioning.

2. The method for abnormal point positioning in laser die processing according to claim 1, wherein The extracting features from the physical quantity data to obtain physical quantity features includes: Performing a smoothing process on the physical quantity data to obtain smoothed physical quantity data; Analyzing the data attributes corresponding to the smoothed physical quantity data and extracting initial physical quantity features corresponding to the smoothed physical quantity data; Parsing the physical quantity labels corresponding to the initial physical quantity features and analyzing the correlation between the data attributes and the physical quantity labels; Performing a feature - selection process on the initial physical quantity features based on the correlation to obtain physical quantity features.

3. The method for abnormal point positioning in laser knife mold processing according to claim 1, characterized in that The calculating the feature anomaly index corresponding to the physical quantity features includes: Calculating a feature equilibrium value corresponding to the physical quantity features and calculating a feature standard deviation corresponding to the physical quantity features based on the feature equilibrium value; Combining the feature equilibrium value and the feature standard deviation to calculate the feature anomaly index corresponding to the physical quantity features through the following formula: Among them, A represents the characteristic anomaly index corresponding to the physical quantity characteristic, and B a represents the value corresponding to the a-th characteristic in the physical quantity characteristics, represents the characteristic equilibrium value, and σ B represents the characteristic standard deviation. a represents the serial number corresponding to the physical quantity characteristic, and q represents the quantity corresponding to the material quantity characteristic.

4. The method for abnormal point positioning in laser knife die processing according to claim 1, wherein The analyzing the abnormal evolution context among the abnormal features includes: Performing a clustering process on the abnormal features to obtain clustered abnormal features; Calculating a feature distance value among the clustered abnormal features and analyzing the abnormal evolution trend corresponding to the clustered abnormal features based on the feature distance value; Performing a feature - fusion process on the clustered abnormal features to obtain fused abnormal features; Calculating the feature interaction intensity among the fused abnormal features and determining associated abnormal features in the fused abnormal features based on the feature interaction intensity; Combining the associated abnormal features and the abnormal evolution trend to generate the abnormal evolution context among the abnormal features.

5. The method for abnormal point positioning under laser knife die machining according to claim 4, wherein The calculating the feature interaction intensity among the fused abnormal features includes: Performing a normalization process on the fused abnormal features to obtain standard abnormal features; Calculate the feature variance corresponding to the fused anomaly feature based on the standard anomaly feature; Measure the feature probability corresponding to the standard anomaly feature, and calculate the feature information entropy corresponding to the fused anomaly feature based on the feature probability; Calculate the covariance matrix between the fused anomaly features, and combine the covariance matrix, the feature variance, and the feature information entropy to calculate the feature interaction strength between the fused anomaly features through the following formula: Among them, D represents the feature interaction intensity between abnormal features, and E cd represents the covariance matrix, and F c represents the feature variance corresponding to the c-th feature in the abnormal features, and F d represents the feature variance corresponding to the d-th feature in the abnormal features. c and d represent the sequence numbers corresponding to the abnormal features, α represents the balance coefficient, H(c) and H(d) respectively represent the feature information entropy corresponding to the c-th feature and the d-th feature in the abnormal features, and r represents the number of features of the abnormal features.

6. The method for abnormal point positioning in laser knife die machining according to claim 1, wherein Based on the anomaly conduction trajectory, determine the area to be detected of the equipment used in laser die cutting, including: Query the equipment efficiency corresponding to the equipment used in laser die cutting, and analyze the efficiency driving factors and efficiency output factors in the equipment efficiency; Combine the efficiency driving factors and the efficiency output factors to analyze the equipment causal relationship between the equipment used in laser die cutting; Combine the equipment causal relationship and the anomaly conduction trajectory to determine the area to be detected of the equipment used in laser die cutting.

7. The method for abnormal point positioning in laser die-cutting processing according to claim 1, wherein Based on the laser performance parameters and the material optical parameters, calculate the material absorption rate of the die material with respect to the laser, including: Extract the photon feature scale of the laser from the laser performance parameters; Based on the material optical parameters, determine the material attenuation coefficient corresponding to the die material; Combine the photon feature scale and the material attenuation coefficient to calculate the material absorption rate of the die material with respect to the laser through the following formula: where G represents the material absorption rate, represents the material attenuation coefficient, and β represents the photon characteristic scale.

8. The method for abnormal point positioning in laser die processing according to claim 7, characterized in that Based on the material optical parameters, determine the material attenuation coefficient corresponding to the die material, including: Schedule the material size information corresponding to the die material, and based on the material size information, determine the material thickness corresponding to the die material; Use a preset spectrophotometer to measure the material transmittance corresponding to the die material; Combine the material thickness and the material transmittance to determine the material attenuation coefficient corresponding to the die material through the following formula: Where K represents the material attenuation coefficient corresponding to the die material, I represents the material transmittance, and L represents the material thickness.

9. The method for abnormal point positioning in laser die processing according to claim 1, characterized in that Combining the regional die image, analyze the point anomaly factors corresponding to the initial marking points, including: According to the initial marking points, perform segmentation processing on the regional die image to obtain a marked point image; Perform image noise reduction processing on the marked point image to obtain a noise-reduced point image, and perform image enhancement processing on the noise-reduced point image to obtain an enhanced point image; Extract the point color features corresponding to the enhanced point image, and perform gray-scale processing on the enhanced point image to obtain a point gray-scale image; Extract the point texture features corresponding to the point gray-scale image, and combine the point texture features, the point color features, and a preset standard point library to analyze the point anomaly factors corresponding to the initial marking points.

10. An abnormal point positioning system for realizing laser knife mold processing, characterized in that, The system includes: Anomaly feature recognition module, used to collect the physical quantity data of the equipment used in laser die cutting, perform feature extraction on the physical quantity data to obtain physical quantity features, calculate the feature anomaly index corresponding to the physical quantity features, and identify the anomaly features in the physical quantity features based on the feature anomaly index; The area division module is used to analyze the abnormal evolution context among the abnormal features, draw the abnormal conduction trajectory corresponding to the abnormal features based on the abnormal evolution context, and determine the area to be detected of the equipment used in the laser die cutting based on the abnormal conduction trajectory; The material absorption rate calculation module is used to obtain the laser performance parameters corresponding to the laser die of the area to be detected, query the die material corresponding to the laser die and its corresponding material optical parameters, and calculate the material absorption rate of the die material with respect to the laser based on the laser performance parameters and the material optical parameters; The abnormal factor analysis module is used to combine the preset reference absorption rate and the material absorption rate, mark the points in the area to be detected to obtain the initial marked points, collect the image of the laser die in the area to be detected to obtain the area die image, and analyze the point abnormal factors corresponding to the initial marked points based on the area die image; The abnormal positioning module is used to perform positioning processing on the point abnormal factors to obtain the abnormal factor positioning, and generate the positioning result of the abnormal points in the laser die cutting in combination with the point abnormal factors and the abnormal factor positioning.

Images