Exposure machine fault diagnosis method and system based on data processing

Abstract

The invention relates to the field of data processing, in particular to an exposure machine fault diagnosis method and system based on data processing. Comprising the following steps: acquiring a gray exposure image and vibration data; performing Hough curve detection on the gray exposure images to obtain a curve quantity value in each gray exposure image and a vote number corresponding to each curve quantity value; calculating a visual exposure index of the gray exposure image; performing two-dimensional fast Fourier transform on the gray exposure image to obtain a frequency spectrum result; calculating the frequency ratio of the gray exposure image; calculating an exposure formability index of the gray exposure image; when the exposure formability index is smaller than or equal to a preset fault threshold value, a vibration root cause index is calculated according to the vibration data, and the abrasion vibration amount is calculated according to the vibration root cause index; and determining a fault reason of the exposure machine according to the wear vibration quantity. The method can improve the recognition precision of the fault type of the exposure machine.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to an exposure machine fault diagnosis method and system based on data processing. BACKGROUND

[0002] An exposure machine generally refers to a device used for manufacturing semiconductor devices, display screens or pattern transfer in a photolithography process. The exposure machine exposes a predetermined pattern on the wafer surface by irradiating light through a mask onto a photoresist coated wafer. The exposure machine is widely used in microelectronic manufacturing, especially in the photolithography process of the semiconductor industry. The main function of the exposure machine is to irradiate light through a mask (usually a template containing a pattern) onto a photosensitive material (such as photoresist) in order to form a specific micro pattern on a substrate (such as a silicon wafer or a glass substrate). Specific functions include photolithography, resolution control, and pattern transfer. Exposure machine failure can involve many aspects, including hardware failure, software failure, environmental factor changes, etc., resulting in various parameters not meeting expectations during the exposure process.

[0003] Exposure machine failure specifically affects the visibility of the exposure pattern. This includes problems such as blurring, mispositioning, stretching, and distortion of the formed pattern. Pattern visibility problems can be caused by many reasons, such as vibration failure caused by system wear, or mechanical vibration failure caused by unbalance or eccentricity of the stepping motor during operation. In order to achieve fault diagnosis, the actual pattern formation visibility problem needs to be identified, and the corresponding fault reason is comprehensively judged in combination with the actual device operation data, so as to eliminate the reason diagnosis deviation problem caused by multiple reasons resulting in a single effect. SUMMARY

[0004] The present application provides an exposure machine fault diagnosis method and system based on data processing to solve the existing problems.

[0005] The exposure machine fault diagnosis method based on data processing provided by the present application adopts the following technical scheme: One embodiment of the present application provides an exposure machine fault diagnosis method based on data processing, which comprises the following steps: Obtain the gray exposure image corresponding to the exposure image after imaging of the exposure machine and the vibration data in the exposure image formation process of each exposure image; Perform Hough curve detection on the gray exposure image to obtain the number of curves in each gray exposure image and the voting number corresponding to each curve number value; According to the curve number value and the voting number corresponding to each curve number value, calculate the visual exposure index of the gray exposure image; Perform two-dimensional fast Fourier transform on the gray exposure image to obtain the frequency spectrum result; According to the spectrum result, a frequency ratio of the gray exposure image is calculated; According to the visual exposure index and the frequency ratio, an exposure forming property index of the gray exposure image is determined; When the exposure forming property index is greater than a preset failure threshold, it is determined that the exposure machine is in normal operation; when the exposure forming property index is less than or equal to the preset failure threshold, a vibration root cause index is calculated according to the vibration data, and a wear vibration amount is calculated according to the vibration root cause index; According to the wear vibration amount, a failure cause of the exposure machine is determined.

[0006] Optionally, according to the curve quantity value and the number of votes corresponding to each curve quantity value, a visual exposure index of the gray exposure image is calculated, specifically including: For each gray exposure image, the number of votes corresponding to the curve quantity value is summed to obtain a line clarity degree of each gray exposure image; The gray entropy of each gray exposure image is calculated using a gray entropy calculation method; The gray entropy of each gray exposure image is taken as an inverse to obtain a confusion degree of each gray exposure image; The product of the line clarity degree of each gray exposure image, the confusion degree of each gray exposure image, and the curve quantity value of each gray exposure image is calculated to obtain a visual exposure index of each gray exposure image.

[0007] Optionally, according to the spectrum result, a frequency ratio of the gray exposure image is calculated, specifically including: The low-frequency energy and the high-frequency energy are determined from the spectrum result; The ratio of the low-frequency energy and the high-frequency energy is determined as the frequency ratio.

[0008] Optionally, the low-frequency energy and the high-frequency energy are determined from the spectrum result, specifically including: The spectrum region within a preset amplitude range is determined from the spectrum result; The region in which the spectrum region is less than a preset amplitude threshold is determined as a low-frequency region; The region in which the spectrum region is equal to or greater than the preset amplitude threshold is determined as a high-frequency region; The amplitudes in the low-frequency region are summed to obtain the low-frequency energy; The amplitudes in the high-frequency region are summed to obtain the high-frequency energy.

[0009] Optionally, according to the visual exposure index and the frequency ratio, an exposure forming property index of the gray exposure image is determined, specifically including: The ratio of the visual exposure index and the frequency ratio is calculated to obtain an initial exposure forming property index; The initial exposure forming property index is normalized to obtain the exposure forming property index.

[0010] Optionally, the vibration root cause index is calculated according to the vibration data, and specifically includes: The vibration data is converted into a vibration curve using a least square method; The maximum peak value of the vibration curve and a time difference sequence between adjacent maximum peak values are determined from the vibration curve; The vibration root cause index is determined according to the maximum peak value of the vibration curve and the time difference sequence.

[0011] Optionally, the vibration root cause index is determined according to the maximum peak value of the vibration curve and the time difference sequence, and specifically includes: All elements in the time difference sequence are summed to obtain a duration; The outlier value corresponding to the maximum peak value of each vibration curve is calculated using a LOF outlier algorithm; The mean value of the outlier values corresponding to all maximum peak values of each vibration curve is determined as the outlier; The product of the duration and the outlier is calculated to obtain the vibration root cause index.

[0012] Optionally, the wear vibration amount is calculated according to the vibration root cause index, and specifically includes: The vibration data is subjected to discrete Fourier transform to obtain a discrete frequency spectrum; The energy values at different frequencies in the discrete frequency spectrum are integrated to obtain a total spectrum energy; The ratio of the total spectrum energy to the maximum energy component in the discrete frequency spectrum is determined as the vibration periodicity; The product of the vibration root cause index and the vibration periodicity is calculated, and normalized to obtain the wear vibration amount.

[0013] Optionally, the failure cause of the exposure machine is determined according to the wear vibration amount, and specifically includes: When the wear vibration amount is greater than or equal to a preset wear vibration amount, the failure cause is determined as exposure machine motion system failure; When the wear vibration amount is less than the preset wear vibration amount, the failure cause is determined as motor failure.

[0014] The present application provides an exposure machine fault diagnosis system based on data processing, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is executed by the processor to implement the steps of the exposure machine fault diagnosis method based on data processing.

[0015] The technical scheme of the present application has the following advantages: In the embodiment of the present application, by visual analysis of the forming pattern, the relevant discrimination index is established, and the index result is combined with other dimension real-time data to achieve the purpose of exposure machine fault abnormality monitoring. On the basis of ensuring exposure abnormality monitoring, the present application further analyzes the pattern forming visual abnormality type, combines with real-time sensor dimension data, establishes the related diagnostic decision tree, comprehensively judges the exposure machine fault type, realizes the fault abnormality monitoring, and improves the identification accuracy of the exposure machine fault type. In the process of comprehensively judging the fault type combined with the sensor dimension data, the vibration root cause index is different, and the identified fault type is different. In order to achieve accurate identification effect, the present application analyzes and detects the vibration type of the exposure machine, and judges the real-time wear vibration amount according to the monitoring result, and accurately obtains the corresponding red line discrimination value according to the vibration amount. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 The flow chart of the exposure machine fault diagnosis method provided by an embodiment of the present application is shown in the figure. Figure 2 The structural diagram of the exposure machine fault diagnosis system provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0018] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following will combine the drawings and the preferred embodiments to specifically describe the exposure machine fault diagnosis method according to the present application, its specific implementation, structure, features and effects in detail. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0020] The specific scheme of the exposure machine fault diagnosis method provided by the present application will be specifically described below in combination with the drawings.

[0021] The present application provides an exposure machine fault diagnosis method and system based on data processing. Please refer toFigure 1 which shows a flow chart of a data processing-based fault diagnosis method of an exposure machine provided by an embodiment of the present application, the method comprising the following steps: S101, acquiring a gray-scale exposure image corresponding to an exposure image after imaging of the exposure machine and vibration data in an exposure image forming process.

[0022] Exemplarily, during operation of the exposure machine, a data acquisition device is configured with a sensor, mainly including two types: forming pattern image data acquisition and forming process vibration data acquisition. Among them, after the exposure machine is developed, an exposure image is acquired by a high-resolution industrial camera or a microscopic imaging system; the acquisition parameters can be: the resolution is greater than or equal to 2 , the sampling frequency is 5-10 randomly sampled per batch, the lighting conditions and the magnification are consistent; after different patterns are formed, each is detected once; the output data: original gray-scale image and image after standardization processing. In the forming process vibration data acquisition, a three-axis acceleration sensor is installed on the motor base, guide rail or platform to acquire vibration signals in real time during operation of the device; the acquisition parameters: the sampling frequency is greater than or equal to 10 kHz, the range: 50g, the acquisition duration covers one complete forming period; the output data: original vibration waveform.

[0023] The quality of the exposure machine production can be monitored and identified to a certain extent of failure by the direct production result, i.e. the quality of the exposure pattern. The main reason is that in the exposure machine fault type, the abnormal vibration in the device (the cause is the unbalanced motion system), the result caused by this fault is: abnormal vibration affects the stability of the exposure machine, resulting in blurred exposure pattern; uneven photoresist, due to the precision problem of the coating machine, the coating thickness of the photoresist is uneven, resulting in differences in image quality in different areas during pattern transfer, forming a blur effect; mechanical positioning error, failure of the stepping motor, motor or part of the guide rail, transmission shaft, which will cause inaccurate alignment of the exposure machine, resulting in blurred pattern.

[0024] Therefore, the results of multiple causes of failure are all directed to the final exposure forming pattern visual effect, including possible blur, stretching, deformation, etc.

[0025] Therefore, first, analyze the pattern result, then, according to the analysis result, combine real-time multi-dimensional data to perform related fault type diagnosis analysis. First, the exposure pattern result needs to be preliminarily analyzed and identified to obtain general indicators, i.e. exposure forming indicators, which are lower than a certain standard, the exposure failure is identified and needs to be diagnosed and analyzed. Secondly, combined with the change characteristics of other dimensions of the real-time device, a corresponding diagnosis decision tree is established to determine the fault type of the exposure machine.

[0026] Specifically, image data of the forming pattern is acquired, and each forming result has a batch of imaging data results, and the pattern image is a gray image. It should be noted that the blur, deformation or stretching property of the pattern is the main manifestation of the forming result after the exposure machine device has a fault. In the device motion system, wear, aging and loosening occur during use, which will cause noise in the motion system, and then cause random irregular vibration of the device, resulting in a blurred pattern.

[0027] In addition, when the stepping motor is unbalanced or eccentric during operation, periodic mechanical vibration (when the eccentricity occurs, the stepping motor produces a displacement eccentric vibration once per revolution) will occur, which will affect the stability of the exposure machine, and the displacement deviation will occur in the guide rail powered by the stepping motor, so that the final pattern imaging result will have certain stretching and deformation characteristics.

[0028] That is, although the visual effect of the pattern exposure result is caused by vibration, the all-around irregular noise vibration caused by the aging of the components in the device and the periodic vibration caused by the eccentricity (abnormal positioning) of the stepping motor are different, and the fault reasons are also different, so they need to be distinguished.

[0029] Therefore, in the imaging gray pattern, if the blur of the visual effect is high, the corresponding exposure index is biased towards the aging of the motion system of the exposure machine; on the contrary, if the blur is general, but the pattern has obvious stretching or deformation, the exposure index is biased towards the eccentricity (abnormal positioning) of the stepping motor of the exposure machine, and the diagnosis results are different.

[0030] S102, Hough curve detection is performed on the gray exposure image to obtain the number of curves in each gray exposure image and the voting number corresponding to each curve number.

[0031] In this embodiment, the pattern gray imaging result is acquired, and Hough curve (including Hough circle, straight line, etc.) detection is performed on it to obtain the number of curves in the pattern ( The detection result of the first pattern forming is represented by , and the corresponding Hough voting number (prior art) ( The voting number of the first straight line is represented by ), the more the number of straight lines, the higher the voting number, the higher the pattern clarity, and the worse the stretching effect; in addition, the higher the clarity, the lower the image pixel gray entropy (calculated by prior art, which will not be described here) is lower, and more disordered.

[0032] S103、According to the curve quantity value and the vote number corresponding to each curve quantity value, the visual exposure index of the gray exposure image is calculated.

[0033] In this embodiment, the visual exposure index of the gray exposure image is calculated according to the curve quantity value and the vote number corresponding to each curve quantity value, specifically including: For each gray exposure image, the vote numbers corresponding to the curve quantity values are summed to obtain the line clarity degree of each gray exposure image; The gray entropy of each gray exposure image is calculated using a gray entropy calculation method; The gray entropy of each gray exposure image is taken as an inverse to obtain the confusion degree of each gray exposure image; The product of the line clarity degree of each gray exposure image, the confusion degree of each gray exposure image, and the curve quantity value of each gray exposure image is calculated to obtain the visual exposure index of each gray exposure image.

[0034] According to the curve quantity value and the vote number corresponding to each curve quantity value, the visual exposure index of the gray exposure image is calculated, and the calculation method can be:

[0035] Among them, the visual exposure index of the i-th gray exposure image, the curve quantity value of the i-th gray exposure image, the gray entropy of the i-th gray exposure image, the vote number of each curve in the i-th gray exposure image. the line clarity degree of the i-th gray exposure image, the confusion degree of the i-th gray exposure image.

[0036] In the formula, the higher the vote number, the higher the regularity and clarity of the detected line in the image, and the better the pattern effect generated by the corresponding exposure machine equipment; otherwise, the line clarity effect is weaker, the blur and irregularity is higher, and the possibility of exposure machine failure is higher. Further, the visual exposure index is obtained by combining the frequency characteristics. The frequency characteristics can more quantitatively analyze the blur effect in the time domain in addition to the visual effect. When there are many blurred edges or blurred organizations in the time domain, i.e. in the image, the low-frequency region energy proportion is high in the image frequency domain, because the high-frequency region is usually composed of regions with large gray difference such as edges. ​​​​​​

[0037] S104. Perform a two-dimensional fast Fourier transform on the grayscale exposure image to obtain the spectrum result.

[0038] S105. Based on the spectrum results, calculate the frequency ratio of the grayscale exposure image.

[0039] In this embodiment, the frequency ratio of the grayscale exposure image is calculated based on the spectrum results, specifically including: determining the low-frequency energy and high-frequency energy from the spectrum results; and determining the ratio of the low-frequency energy and high-frequency energy as the frequency ratio.

[0040] Determining low-frequency and high-frequency energy from the spectrum results specifically includes: identifying the spectrum region within a preset amplitude range from the spectrum results; defining the region with a spectrum region smaller than a preset amplitude threshold as the low-frequency region; defining the region with a spectrum region equal to or greater than the preset amplitude threshold as the high-frequency region; summing the amplitudes in the low-frequency region to obtain the low-frequency energy; and summing the amplitudes in the high-frequency region to obtain the high-frequency energy.

[0041] For example, performing a two-dimensional FFT (Fast Fourier Transform) on a patterned image yields its spectrum. The frequencies within the spectrum are then considered to be within a specific frequency range. 1 / 3 of the part This region is considered a low-frequency region; the rest are considered high-frequency regions. Here, A preset amplitude threshold is set here. This preset amplitude threshold is based on experience and can be modified according to actual needs; no specific restrictions are imposed here. The sum of the amplitudes corresponding to the frequency values ​​in the low-frequency region is obtained as the low-frequency energy. Others are considered high-frequency energy. .

[0042] The frequency ratio of a grayscale exposure image can be calculated as follows:

[0043] in, Indicates the first The frequency ratio of grayscale exposure images Indicates low-frequency energy. It represents high-frequency energy.

[0044] The higher the frequency ratio, the higher the proportion of low-frequency regions, and the greater the image blurring effect.

[0045] S106. Determine the exposure shaping index of the grayscale exposure image based on the visual exposure index and frequency ratio.

[0046] In this embodiment, the exposure shaping index of the grayscale exposure image is determined based on the visual exposure index and the frequency ratio, specifically including: a ratio of the visual exposure index and the frequency ratio is calculated to obtain an initial exposure formability index; The initial exposure formability index is normalized to obtain an exposure formability index.

[0047] The exposure formability index can be calculated in the following manner:

[0048] wherein, represents the i-th The exposure formability index of the gray exposure image is proportional to the visual exposure index (the higher, the clearer) and inversely proportional to the frequency ratio (the higher, the blurrier).

[0049] In S107, when the exposure formability index is greater than a preset fault threshold, it is determined that the exposure machine is in normal operation; when the exposure formability index is less than or equal to the preset fault threshold, a vibration root cause index is calculated according to the vibration data, and a wear vibration amount is calculated according to the vibration root cause index.

[0050] In this embodiment, the vibration root cause index is calculated according to the vibration data, specifically including: using the least square method to convert the vibration data into a vibration curve; determining the maximum peak value of the vibration curve and the time difference sequence between adjacent maximum peak values from the vibration curve; determining the vibration root cause index according to the maximum peak value of the vibration curve and the time difference sequence.

[0051] According to the maximum peak value of the vibration curve and the time difference sequence, the vibration root cause index is determined, specifically including: summing all elements in the time difference sequence to obtain a duration; using the LOF outlier algorithm to calculate the outlier value corresponding to each maximum peak value of the vibration curve; determining the mean of the outlier values corresponding to all maximum peak values of each vibration curve as the outlier; calculating the product of the duration and the outlier to obtain the vibration root cause index.

[0052] According to the vibration root cause index, the wear vibration amount is calculated, specifically including: performing discrete Fourier transform on the vibration data to obtain a discrete frequency spectrum; integrating the energy values at different frequencies in the discrete frequency spectrum to obtain a total frequency spectrum energy; determining the ratio of the total frequency spectrum energy to the maximum energy component in the discrete frequency spectrum as the vibration periodicity; calculating the product of the vibration root cause index and the vibration periodicity, and normalizing to obtain the wear vibration amount.

[0053] Exemplarily, the preset fault threshold is set to 0.5 here, and the preset fault threshold is set according to experience here, which can be modified according to actual needs, and is not specifically limited here. When the exposure formability index is greater than the preset fault threshold, it is determined that the exposure machine is in normal operation; when the exposure formability index is less than or equal to the preset fault threshold, the vibration root cause index is calculated according to the vibration data, and the wear vibration amount is calculated according to the vibration root cause index. When the exposure formability index is in the range of 0.5 to 1, it is determined that the exposure machine is in normal operation; when the exposure formability index is less than 0.5, the vibration root cause index is calculated according to the vibration data, and the wear vibration amount is calculated according to the vibration root cause index. ​​If the exposure results in a blurry image, it indicates a potential malfunction in the exposure equipment, requiring further analysis to determine the cause; conversely, if the image is within a certain range... At that time, it was considered that the exposure forming was too clear, and no fault diagnosis results were found.

[0054] Furthermore, for cases where the exposure forming is somewhat blurry, it is necessary to analyze the actual operating parameters in the equipment environment to determine the specific cause.

[0055] Specifically, when it is determined that there are visual problems in the pattern forming result, based on the previous analysis of the vibration logic, it may be caused by random vibration generated by the motion system inside the equipment, or it may be caused by periodic regular vibration generated by the eccentricity (positioning abnormality) of the stepper motor.

[0056] In addition, for the identification of photoresist non-uniformity, this part can be directly diagnosed by detecting the photoresist thickness, rather than requiring data analysis to distinguish and diagnose due to the complexity of vibration.

[0057] Therefore, the next step is to analyze real-time vibration data to obtain the corresponding root cause indicators and wear vibration amount.

[0058] Specifically, real-time vibration data collected by sensors is obtained to get the corresponding vibration set: ,in, Indicates the first A collection of vibration data of a grayscale exposure image during the forming process; This indicates the first [number]th ... Vibration value.

[0059] The moving platform, stepper motor, drive shaft, and guide rails of an exposure machine need to maintain high-precision movement. If the moving parts of these components are unbalanced, or if wear, aging, or loosening occurs during use, vibration will occur. This vibration will be irregular and random, resulting in blurred pattern images rather than stretching or deformation. Furthermore, if the stepper motor is eccentric during operation (positioning abnormality), it will cause mechanical vibration (when eccentricity occurs, the stepper motor generates a directional vibration with each revolution), thus affecting the stability of the exposure machine and producing periodic vibrations. The direct result of this is stretching and deformation of the pattern image. Therefore, the distinction between these two types of vibration lies in their randomness, periodicity, and continuity. We will first analyze the random effects of vibration, i.e., the root cause indicators.

[0060] Specifically, the sequence is transformed into an vibration curve using the least squares method, and the vibration data peaks (maximum peaks) of the vibration curve are obtained. (in, The more frequently the peak index changes, and the greater the time difference between peaks... The larger the value, the higher the root cause index of vibration, that is, the higher the randomness of vibration.

[0061] Based on the maximum and peak values ​​and time difference sequence of the vibration curve, the calculation method for determining the root cause index of vibration can be as follows:

[0062] in, Indicates the first Vibration root cause index of grayscale exposure images Indicated by Peak As a sample, the mean of the outlier values ​​(LOF outlier algorithm) for each peak is calculated. The larger this value is, the greater the difference in variation between peaks and the higher the randomness. Represents the first in the time difference sequence One element, Indicates the duration.

[0063] When vibration data originates from the motion system within the exposure machine, including issues such as aging, the vibration changes are highly random. Vibration might be intense one second and slow down the next, with a significant difference in peak values ​​and a relatively long interval between peaks. Therefore, the root cause index value of vibration is obtained by quantifying the aforementioned peak value differences.

[0064] Furthermore, the higher the vibration root cause index, the higher the randomness, and the higher the probability of vibration caused by aging and wear of the motion system, and the higher the corresponding amount of wear vibration.

[0065] The calculation method for wear vibration can be as follows:

[0066] in, Indicates the first The amount of wear and vibration in grayscale exposed images. Indicates the first Vibration root cause index of grayscale exposure images Represents the frequency values ​​in the discrete spectrum The energy value below, This represents the integral over the spectral energy, i.e., the total spectral energy. This represents the maximum energy component in the discrete spectrum. This represents the normalization formula.

[0067] The amount of wear vibration is directly proportional to the magnitude of the vibration root cause index; that is, the higher the randomness of vibration, the higher the amount of wear vibration. Simultaneously, the latter indicates that in the process of analyzing the randomness of vibration, the periodicity of vibration is obtained through spectrum analysis, and when the ratio... The smaller, that is, the higher the proportion of the largest energy component in the total energy, the higher the periodicity of the original sequence, because the frequency domain of the vibration data sequence is concentrated near one data. Therefore, the higher the wear vibration quantity, the higher the possibility of pattern exposure abnormality due to motion system failure; on the contrary, the smaller the wear vibration quantity, the higher the possibility of abnormality due to motor eccentricity (positioning abnormality), because the smaller value means lower randomness and higher periodicity, because the energy is more concentrated near one frequency.

[0068] S108, determining the failure cause of the exposure machine according to the wear vibration quantity.

[0069] In the embodiment, the failure cause of the exposure machine is determined according to the wear vibration quantity, specifically including: when the wear vibration quantity is greater than or equal to a preset wear vibration quantity, determining that the failure cause is exposure machine motion system failure; and when the wear vibration quantity is less than the preset wear vibration quantity, determining that the failure cause is motor failure.

[0070] Exemplarily, the vibration root cause index can be solved by establishing a decision tree. When the wear vibration quantity is greater than or equal to a preset wear vibration quantity, the decision tree considers that the failure cause is the motion system of the exposure machine; on the contrary, when the wear vibration quantity is less than the preset wear vibration quantity, the decision tree considers that the failure cause is the eccentricity (positioning abnormality) of the stepping motor. Here, the preset wear vibration quantity is an actual value calculated according to historical experience, which can be changed according to actual needs, and is not limited in specific numerical value. The above failure identification and judgment is based on the existence of the failure, that is, based on meeting the exposure forming property index discrimination threshold. (0.7 is a preset wear vibration quantity, which can also be called a red line discrimination value), the decision tree considers that the failure cause is the motion system of the exposure machine; on the contrary, when the wear vibration quantity is less than the preset wear vibration quantity, the decision tree considers that the failure cause is the eccentricity (positioning abnormality) of the stepping motor. Here, the preset wear vibration quantity is an actual value calculated according to historical experience, which can be changed according to actual needs, and is not limited in specific numerical value. The above failure identification and judgment is based on the existence of the failure, that is, based on meeting the exposure forming property index discrimination threshold.

[0071] Thus, the present application is completed.

[0072] In summary, in the embodiment of the present application, by performing visual analysis on the formed pattern, relevant discrimination indexes are established, and real-time data in other dimensions are combined according to the index results, to achieve the purpose of exposure machine failure abnormality monitoring. On the basis of ensuring exposure abnormality monitoring, the present application further analyzes the pattern forming visual abnormality type, combines real-time sensor dimension data, establishes a relevant diagnostic decision tree, and comprehensively judges the exposure machine failure type, to realize failure abnormality monitoring and improve the identification accuracy of the exposure machine failure type. In the process of comprehensively judging the failure type in combination with the sensor dimension data, the vibration root cause index is different, and the identified failure type is different. In order to achieve accurate identification effect, the present application performs data analysis and detection on the vibration type of the exposure machine, and judges the real-time wear vibration quantity through the monitoring result, to accurately obtain the corresponding red line discrimination value according to the vibration quantity.

[0073] ​The application further provides an exposure machine fault diagnosis system based on data processing. Figure 2 The figure shows a structure diagram of an exposure machine fault diagnosis system based on data processing, which comprises a data acquisition module 101, a data processing module 102 and a fault detection module 103.

[0074] The data acquisition module 101 is used for acquiring a gray exposure image corresponding to an exposure image after imaging of the exposure machine and vibration data in the imaging process of each image. The data processing module 102 is used for Hough curve detection of the gray exposure image, obtaining a curve number value in each gray exposure image and a voting number corresponding to each curve number value; calculating a visual exposure index of the gray exposure image according to the curve number value and the voting number corresponding to each curve number value; performing two-dimensional fast Fourier transform on the gray exposure image to obtain a frequency spectrum result; calculating a frequency ratio of the gray exposure image according to the frequency spectrum result; determining an exposure forming property index of the gray exposure image according to the visual exposure index and the frequency ratio; when the exposure forming property index is greater than a preset fault threshold, determining that the exposure machine is in normal operation; when the exposure forming property index is less than or equal to the preset fault threshold, calculating a vibration root cause index according to the vibration data and calculating a wear vibration amount according to the vibration root cause index; The fault detection module 103 is used for determining a fault cause of the exposure machine according to the wear vibration amount.

[0075] It should be noted that the system provided in the above embodiment is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the exposure machine fault diagnosis system based on data processing and the exposure machine fault diagnosis method based on data processing provided in the above embodiment belong to the same concept, and the specific implementation process is described in the method embodiment, which will not be repeated here.

[0076] It should be noted that the above-mentioned order of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0077] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

[0078] The above merely provides the preferred embodiment of the present application, and is not used to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the principle of the present application should be included in the protection scope of the present application.

Claims

1. A data processing-based fault diagnosis method for an exposure machine, characterized by, The method comprises the following steps: acquiring a gray exposure image corresponding to an exposure image after imaging of an exposure machine and vibration data in the forming process of each exposure image; performing Hough curve detection on the gray exposure image to obtain a curve number value in each gray exposure image and a voting number corresponding to each curve number value; calculating a visual exposure index of the gray exposure image according to the curve number value and the voting number corresponding to each curve number value; performing two-dimensional fast Fourier transform on the gray exposure image to obtain a frequency spectrum result; calculating a frequency ratio of the gray exposure image according to the frequency spectrum result; determining an exposure forming property index of the gray exposure image according to the visual exposure index and the frequency ratio; when the exposure forming property index is greater than a preset fault threshold, determining that the exposure machine is in normal operation; when the exposure forming property index is less than or equal to the preset fault threshold, calculating a vibration root cause index according to the vibration data and calculating a wear and vibration amount according to the vibration root cause index; determining a fault cause of the exposure machine according to the wear and vibration amount.

2. The exposure apparatus failure diagnosing method based on data processing according to claim 1, characterized by, The calculation of the visual exposure index of the gray exposure image according to the curve number value and the voting number corresponding to each curve number value specifically comprises the following steps: summing the voting numbers corresponding to the curve number value for each gray exposure image to obtain a line clarity degree of each gray exposure image; calculating a gray entropy of each gray exposure image by using a gray entropy calculation method; taking the reciprocal of the gray entropy of each gray exposure image to obtain a confusion degree of each gray exposure image; calculating a product of the line clarity degree of each gray exposure image, the confusion degree of each gray exposure image and the curve number value of each gray exposure image to obtain a visual exposure index of each gray exposure image.

3. The exposure apparatus failure diagnosing method based on data processing according to claim 1, characterized by, The calculation of the frequency ratio of the gray exposure image according to the frequency spectrum result specifically comprises the following steps: determining a low-frequency energy and a high-frequency energy from the frequency spectrum result; determining the frequency ratio as a ratio of the low-frequency energy to the high-frequency energy.

4. The exposure apparatus failure diagnosing method based on data processing according to one of claims 1 to 3, characterized in that, The determination of the low-frequency energy and the high-frequency energy from the frequency spectrum result specifically comprises the following steps: determining a frequency spectrum region within a preset amplitude range from the frequency spectrum result; determining a low-frequency region as a region in which the amplitude of the frequency spectrum region is less than a preset amplitude threshold; determining a high-frequency region as a region in which the amplitude of the frequency spectrum region is equal to or greater than the preset amplitude threshold; summing the amplitudes in the low-frequency region to obtain the low-frequency energy; summing the amplitudes in the high-frequency region to obtain the high-frequency energy.

5. The exposure apparatus failure diagnosing method based on data processing according to one of claims 1, wherein The determination of the exposure forming property index of the gray exposure image according to the visual exposure index and the frequency ratio specifically comprises the following steps: calculating a ratio of the visual exposure index to the frequency ratio to obtain an initial exposure forming property index; normalizing the initial exposure forming property index to obtain the exposure forming property index.

6. The exposure apparatus failure diagnosing method based on data processing according to one of claims 1, wherein The calculation of the vibration root cause index according to the vibration data specifically comprises the following steps: transforming the vibration data into a vibration curve by using a least square method; determining a maximum peak value of the vibration curve and a time difference sequence between adjacent maximum peak values from the vibration curve; According to the maximum peak value of the vibration curve and the time difference sequence, a vibration root cause index is determined.

7. The exposure apparatus failure diagnosing method based on data processing according to one or more of claims 6, wherein The determination of the vibration root cause index according to the maximum peak value of the vibration curve and the time difference sequence specifically comprises: Summing all elements in the time difference sequence to obtain a duration; Using a LOF outlier algorithm to calculate an outlier value corresponding to the maximum peak value of each vibration curve; Determining the mean of the outlier values corresponding to all maximum peak values of each vibration curve as an outlier; Calculating the product of the duration and the outlier to obtain a vibration root cause index.

8. The exposure apparatus failure diagnosing method based on data processing according to one or more of claims 1, wherein The calculation of the wear vibration amount according to the vibration root cause index specifically comprises: Performing a discrete Fourier transform on the vibration data to obtain a discrete frequency spectrum; Integrating energy values at different frequencies in the discrete frequency spectrum to obtain a total frequency spectrum energy; Determining the ratio of the total frequency spectrum energy to the maximum energy component in the discrete frequency spectrum as a vibration periodicity; Calculating the product of the vibration root cause index and the vibration periodicity and performing normalization to obtain the wear vibration amount.

9. The exposure apparatus failure diagnosing method based on data processing according to one or more of the preceding claims 1, wherein The determination of the failure cause of the exposure machine according to the wear vibration amount specifically comprises: When the wear vibration amount is greater than or equal to a preset wear vibration amount, determining that the failure cause is an exposure machine motion system failure; When the wear vibration amount is less than the preset wear vibration amount, determining that the failure cause is a motor failure.

10. A data processing-based fault diagnosis system for an exposure apparatus, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized by, The computer program, when executed by a processor, implements the steps of a data processing-based exposure machine failure diagnosis method according to any one of claims 1-9.

Images