Film coating control method and device based on image analysis
By analyzing the images of particle groups sputtered in the magnetron sputtering coating process, the coating defects are predicted and improved, the problem of difficult real-time detection of process abnormalities is solved, and the coating quality is improved.
Patent Information
- Application Number
- CN202510314291.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-17
- Publication Date
- 2025-06-27
AI Technical Summary
In magnetron sputtering coating process, it is difficult to effectively know whether there are abnormalities in the coating process in real time, resulting in coating quality problems, such as deterioration of film adhesion and uneven coating thickness.
By collecting and analyzing the images of sputtered particles, possible coating defects are predicted, and the operating parameters of the magnetron sputtering equipment are adjusted according to the defects or prompt information is issued to improve the defects.
Timely prediction and improvement of coating defects has been achieved and coating quality has been improved.
Smart Images
Figure CN120210758A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of industrial vision detection and control, and particularly relates to a coating control method and device based on image analysis. Background Art
[0002] Magnetron sputtering coating technology has become increasingly common in industrial production processes such as semiconductor wafer coating and fabric coloring due to its advantages of low deposition temperature, wide material applicability, high adhesion, and high controllability.
[0003] In the current magnetron sputtering coating process, since it is difficult to effectively and real-time know whether abnormal conditions occur in the coating process, if the abnormalities cannot be eliminated as soon as possible after they occur, subsequent products may all have quality problems, such as poor film adhesion and uneven coating thickness, and these quality problems are difficult to be known through the detection of semi-finished products or finished products. Summary of the Invention
[0004] To solve the above technical problems, the present invention provides a coating control method and device based on image analysis. By collecting and analyzing the images of the ejected particle clusters, it is possible to roughly predict possible coating defects, thereby being able to timely improve the defects and improve the coating quality.
[0005] The technical solution adopted by the present invention is as follows: A coating control method based on image analysis, comprising the following steps: after installing the target for coating on the target position, controlling the magnetron sputtering equipment to start and operate with preset operating parameters to coat the object to be coated in the sputtering chamber of the magnetron sputtering equipment; during the operation of the magnetron sputtering equipment, real-time collecting the images of the particle clusters ejected from the target in the sputtering chamber; analyzing the images of the particle clusters to predict corresponding coating defects; adjusting the operating parameters of the magnetron sputtering equipment and / or sending a prompt message according to the coating defects to improve the coating defects.
[0006] Analyzing the images of the particle clusters to predict corresponding coating defects specifically includes: converting the images of a continuous plurality of the particle clusters into the HSV space to obtain a continuous plurality of HSV images; obtaining the intra-frame consistency of brightness, average hue, and inter-frame consistency of brightness of a continuous plurality of the HSV images according to the brightness information and hue information of each of the HSV images; predicting corresponding coating defects according to the intra-frame consistency of brightness, average hue, and inter-frame consistency of brightness of each of the HSV images.
[0007] Obtain the intra-frame luminance consistency, average hue, and inter-frame luminance consistency of multiple consecutive HSV images based on the luminance information and hue information of each HSV image, specifically including: calculating the overall luminance average value and overall hue average value of each HSV image; dividing each HSV image into n 2 regions, where n is an integer greater than 1; for each HSV image, calculate the regional luminance average value within each of its regions; for each HSV image, determine whether the difference between the maximum regional luminance average value and the minimum regional luminance average value is greater than a first threshold. If so, determine that the luminance within the frame of this HSV image is inconsistent; otherwise, determine that the luminance within the frame of this HSV image is consistent. If multiple consecutive HSV images are all consistent in luminance within the frame, further determine whether the difference between the maximum overall luminance average value and the minimum overall luminance average value is greater than a second threshold. If so, determine that the luminance between the frames of multiple consecutive HSV images is inconsistent; otherwise, determine that the luminance between the frames of multiple consecutive HSV images is consistent.
[0008] Predict corresponding coating defects based on the intra-frame luminance consistency, average hue, and inter-frame luminance consistency of multiple consecutive HSV images, specifically including: if the overall luminance average value of at least one HSV image is outside the preset luminance range and the overall hue average value is outside the preset hue range, the predicted coating defect is insufficient or excessive sputtering amount; if the luminance within the frame of at least one HSV image is inconsistent, the predicted coating defect is uneven sputtering; if the luminance between the frames of multiple consecutive HSV images is inconsistent, the predicted coating defect is sputtering amount fluctuation.
[0009] Adjust the operating parameters of the magnetron sputtering equipment and / or send a prompt message according to the coating defects, specifically including: if the sputtering amount is insufficient or excessive, adjust at least one of the sputtering power, argon gas pressure, and target-substrate distance, and send a prompt message to check the power supply and gas source; if the sputtering is uneven, adjust the moving speed of the object to be coated, and send a prompt message to check the magnet and target material; if the sputtering amount fluctuates, send a prompt message to check the power supply and gas source.
[0010] A coating control device based on image analysis, comprising a control module, a collection module and an analysis module. The control module is used to install a target for coating on a target position and then control a magnetron sputtering device to start and operate with preset operating parameters, so as to coat an object to be coated in a sputtering chamber of the magnetron sputtering device; the collection module is used to collect images of particle clusters sputtered from the target in real time during the operation of the magnetron sputtering device; the analysis module is used to analyze the images of the particle clusters to predict corresponding coating defects; the control module is further used to adjust the operating parameters of the magnetron sputtering device and / or send a prompt message according to the coating defects, so as to improve the coating defects.
[0011] Specifically, the analysis module is configured to: convert images of a plurality of consecutive particle clusters into the HSV space to obtain a plurality of consecutive HSV images; obtain the intra-frame brightness consistency, average hue of each HSV image and the inter-frame brightness consistency of a plurality of consecutive HSV images according to the brightness information and hue information of each HSV image; predict corresponding coating defects according to the intra-frame brightness consistency, average hue of each HSV image and the inter-frame brightness consistency of a plurality of consecutive HSV images.
[0012] Specifically, the analysis module is configured to: calculate the overall brightness average value and overall hue average value of each HSV image; divide each HSV image into n regions respectively, where n is an integer greater than 1; for each HSV image, calculate the regional brightness average value within each of its regions; for each HSV image, determine whether the difference between the maximum regional brightness average value and the minimum regional brightness average value is greater than a first threshold. If so, it is determined that the intra-frame brightness of this HSV image is inconsistent, otherwise it is determined that the intra-frame brightness of this HSV image is consistent; if a plurality of consecutive HSV images are all intra-frame brightness consistent, further determine whether the difference between the maximum overall brightness average value and the minimum overall brightness average value is greater than a second threshold. If so, it is determined that the inter-frame brightness of a plurality of consecutive HSV images is inconsistent, otherwise it is determined that the inter-frame brightness of a plurality of consecutive HSV images is consistent. 2 Specifically, the analysis module is configured to: when the overall brightness average value of at least one of the HSV images is outside a preset brightness range and the overall hue average value is outside a preset hue range, the predicted coating defect is insufficient or excessive sputtering amount; when the intra-frame brightness of at least one of the HSV images is inconsistent, the predicted coating defect is uneven sputtering; when the inter-frame brightness of a plurality of consecutive HSV images is inconsistent, the predicted coating defect is sputtering amount fluctuation.
[0013]
[0014] The control module is specifically configured to: when the sputtering amount is insufficient or excessive, adjust at least one of the sputtering power, the argon gas pressure, and the target-substrate distance, and send a prompt message for checking the power supply and the gas source; when the sputtering is uneven, adjust the moving speed of the object to be coated, and send a prompt message for checking the magnet and the target; when the sputtering amount fluctuates, send a prompt message for checking the power supply and the gas source.
[0015] Advantages of the present invention: In the magnetron sputtering coating process of the present invention, by collecting the image of the particle cluster sputtered from the target and analyzing the image to predict the corresponding coating defects, and adjusting the operating parameters of the magnetron sputtering equipment and / or sending prompt messages according to the coating defects so as to improve the coating defects. Thus, by collecting and analyzing the image of the sputtered particle cluster, the possible coating defects can be roughly predicted, so that the coating defects can be improved in time and the coating quality can be improved. Description of the drawings
[0016] Figure 1 is a flowchart of the coating control method based on image analysis according to an embodiment of the present invention; Figure 2 is a block diagram of the coating control device based on image analysis according to an embodiment of the present invention. Detailed implementation manners
[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0018] As Figure 1 shown, the coating control method based on image analysis according to an embodiment of the present invention includes the following steps: S1, after installing the target for coating on the target position, control the magnetron sputtering equipment to start and operate with preset operating parameters so as to coat the object to be coated in the sputtering chamber of the magnetron sputtering equipment.
[0019] In a specific embodiment of the present invention, the object to be coated can be a semiconductor wafer, such as a silicon wafer, a gallium nitride wafer, a gallium arsenide wafer, etc. The target, i.e., the coating material, can be a metal such as gold, copper, etc., or a non-conductor or semiconductor material such as silicon dioxide, silicon nitride, zinc sulfide, etc. In another specific embodiment of the present invention, the object to be coated can be a fabric, such as a polyimide fabric, etc. The target, i.e., the coating material, can be selected from metals, compounds, ceramics, etc. according to requirements. In other specific embodiments of the present invention, the object to be coated and the target can also be items and materials suitable for magnetron sputtering coating in other industrial scenarios.
[0020] The operating parameters of the magnetron sputtering equipment include sputtering power (i.e., the electric power applied to the target), the gas pressure of argon, the moving speed of the object to be coated (i.e., the rotation or translation speed of the object to be coated), the target-substrate distance (i.e., the distance between the target and the object to be coated), etc. When the magnetron sputtering equipment is initially operated, it can be operated with preset operating parameters. These preset operating parameters, as initial parameters, can be set according to experience or are stable parameters determined in the previous process, which can basically ensure the successful implementation of coating the object to be coated.
[0021] S2. During the operation of the magnetron sputtering equipment, images of the particle clusters sputtered from the target in the sputtering chamber are collected in real time.
[0022] The particle clusters sputtered from the target in the sputtering chamber refer to the cluster-like particle groups formed in the space that have detached from the target and have not reached the coating position. In an embodiment of the present invention, photos can be taken at a preset frequency in the direction facing the particle clusters on one side of the sputtering chamber to obtain a series of consecutive images, or a video can be taken, and the frame images of the video can be used as the images of the particle clusters to be analyzed subsequently.
[0023] S3. Analyze the images of the particle clusters to predict the corresponding coating defects.
[0024] Specifically, first, a series of consecutive images of the particle clusters can be converted to the HSV space to obtain a series of consecutive HSV images. Then, the intra-frame luminance consistency, average hue, and inter-frame luminance consistency of a series of consecutive HSV images can be obtained according to the luminance information and hue information of each HSV image. Finally, the corresponding coating defects can be predicted based on the intra-frame luminance consistency, average hue, and inter-frame luminance consistency of each HSV image.
[0025] For obtaining the intra-frame consistency of brightness, the average hue, and the inter-frame consistency of brightness for consecutive HSV images in each HSV image, first, the overall brightness average value and the overall hue average value of each HSV image can be calculated, that is, the average value of the brightness values of all pixels in each HSV image and the average value of the hue values of all pixels in each HSV image. Then, each HSV image is respectively divided into n 2 regions, where n is an integer greater than 1. Specifically, each HSV image can be equally divided into a rectangular region of n rows and n columns. It should be understood that the larger the value of n, the more accurate the analysis result, but the computing power level of the processor executing the method of the embodiment of the present invention should also be considered. For each HSV image, the regional brightness average value within each of its regions can be calculated, that is, the average value of the brightness values of the pixels within each region is calculated. And, for each HSV image, it can be determined whether the difference between the largest regional brightness average value and the smallest regional brightness average value is greater than a first threshold. If so, it is determined that the brightness within the HSV image frame is inconsistent; otherwise, it is determined that the brightness within the HSV image frame is consistent. If consecutive HSV images are all intra-frame brightness consistent, it is further determined whether the difference between the largest overall brightness average value and the smallest overall brightness average value is greater than a second threshold. If so, it is determined that the inter-frame brightness of consecutive HSV images is inconsistent; otherwise, it is determined that the inter-frame brightness of consecutive HSV images is consistent. The first threshold and the second threshold here are both preset values, which need to be preset for each actual process scenario and are not conveniently limited to a specific value here.
[0026] If the overall brightness average value of at least one HSV image is outside the preset brightness range and the overall hue average value is outside the preset hue range, the predicted coating defect is insufficient or excessive sputtering amount. For target materials of different materials, the preset brightness range and the preset hue range are different, and both also need to be preset for each actual process scenario. And, according to the size relationship between the overall brightness average value and the minimum boundary value and the maximum boundary value of the preset brightness range, and the size relationship between the overall hue average value and the minimum boundary value and the maximum boundary value of the preset hue range, it can be determined whether the sputtering amount is insufficient or excessive. Insufficient or excessive sputtering amount will cause problems such as too small or too large film thickness, insufficient adhesion, and poor film layer quality.
[0027] If the intra-frame brightness of at least one HSV image is inconsistent, the predicted coating defect is uneven sputtering. Uneven sputtering will cause problems such as uneven film thickness.
[0028] If the inter-frame brightness of consecutive HSV images is inconsistent, the predicted coating defect is sputtering amount fluctuation. Sputtering amount fluctuation will cause problems such as insufficient film adhesion and poor film layer quality.
[0029] S4. Adjust the operating parameters of the magnetron sputtering equipment and / or send a prompt message according to the coating defects, so as to improve the coating defects.
[0030] In an embodiment of the present invention, if the sputtering amount is insufficient or excessive, at least one of the sputtering power, the argon gas pressure, and the target-substrate distance can be adjusted, and a prompt message for checking the power supply and the gas source is sent. For example, when the sputtering amount is insufficient, the sputtering power can be increased, the argon gas pressure can be increased to increase the sputtering amount, or the target-substrate distance can be decreased to increase the deposition strength and speed, so as to reduce or avoid too small film thickness. The above adjustments may not be able to eliminate the corresponding coating defects. Therefore, by checking the power supply and the gas source, problems such as inaccurate parameters and faults of the power supply and the gas source can be fundamentally found, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0031] If the sputtering is uneven, the moving speed of the object to be coated can be adjusted, and a prompt message for checking the magnet and the target is sent. Specifically, the moving speed of the object to be coated can be increased to improve the film thickness uniformity. The above adjustments may not be able to eliminate the corresponding coating defects. Therefore, by checking the magnet and the target, problems such as the offset of the magnetic field position of the magnet, the roughness and contamination of the target surface can be fundamentally found, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0032] If the sputtering amount fluctuates, a prompt message for checking the power supply and the gas source can be sent. By checking the power supply and the gas source, problems such as output fluctuations of the power supply and the gas source can be fundamentally found, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0033] In addition, it should be noted that the above adjustments to the operating parameters of the magnetron sputtering equipment can be adjusted by a preset adjustment amount every time a coating defect is predicted, or can be continuously fine-tuned until no coating defect is analyzed. After the adjustment is completed, the subsequent magnetron sputtering equipment continues to operate with the adjusted operating parameters until a coating defect is analyzed again.
[0034] According to the coating control method based on image analysis of the embodiment of the present invention, in the magnetron sputtering coating process, by collecting the image of the particle cluster sputtered from the target, analyzing the image to predict the corresponding coating defects, and adjusting the operating parameters of the magnetron sputtering equipment and / or sending a prompt message according to the coating defects, so as to improve the coating defects. Thus, by collecting and analyzing the image of the sputtered particle cluster, the possible coating defects can be roughly predicted, so that the coating defects can be improved in time and the coating quality can be improved.
[0035] Corresponding to the coating control method based on image analysis of the above embodiment, the present invention also proposes a coating control device based on image analysis.
[0036] As Figure 2 shown, the coating control device based on image analysis according to an embodiment of the present invention includes a control module 10, an acquisition module 20, and an analysis module 30. Among them, the control module 10 is used to install the target for coating on the target position, and then control the magnetron sputtering device to start and operate with preset operating parameters, so as to coat the object to be coated in the sputtering chamber of the magnetron sputtering device; the acquisition module 20 is used to collect the images of the particle clusters sputtered from the target in the sputtering chamber in real time during the operation of the magnetron sputtering device; the analysis module 30 is used to analyze the images of the particle clusters to predict corresponding coating defects; the control module 10 is further used to adjust the operating parameters of the magnetron sputtering device and / or send a prompt message according to the coating defects, so as to improve the coating defects.
[0037] In a specific embodiment of the present invention, the object to be coated can be a semiconductor wafer, such as a silicon wafer, a gallium nitride wafer, a gallium arsenide wafer, etc. The target, that is, the material for coating, can be a metal such as gold or copper, or a non-conductor or semiconductor material such as silicon dioxide, silicon nitride, zinc sulfide, etc. In another specific embodiment of the present invention, the object to be coated can be a fabric, such as a polyimide fabric, etc. The target, that is, the material for coating, can be selected according to requirements from materials such as metals, compounds, and ceramics. In other specific embodiments of the present invention, the object to be coated and the target can also be other items and materials suitable for magnetron sputtering coating in other industrial scenarios.
[0038] The operating parameters of the magnetron sputtering device include sputtering power (i.e., the electric power applied to the target), the gas pressure of argon, the moving speed of the object to be coated (i.e., the rotation or translation speed of the object to be coated), the target-substrate distance (i.e., the distance between the target and the object to be coated), etc. When the magnetron sputtering device starts to operate initially, the control module 10 can control it to operate with the preset operating parameters. These preset operating parameters, as the initial parameters, can be set according to experience or the stable parameters determined in the previous process, and can basically ensure the successful implementation of coating the object to be coated.
[0039] In an embodiment of the present invention, the acquisition module 20 can be a camera. The particle clusters sputtered from the target in the sputtering chamber refer to the cluster-like particle groups formed in the space that have detached from the target and have not reached the coating position. Photos can be taken at a preset frequency in the direction facing the particle clusters on one side of the sputtering chamber to obtain a series of continuous images, or a video can be taken, and the frame images of the video can be used as the images of the particle clusters to be analyzed subsequently.
[0040] The analysis module 30 can first convert the images of a continuous plurality of particle clusters into the HSV space to obtain a continuous plurality of HSV images, and then obtain the in-frame luminance consistency, average hue of each HSV image, and the inter-frame luminance consistency of the continuous plurality of HSV images according to the luminance information and hue information of each HSV image. Then, the corresponding coating defects are predicted according to the in-frame luminance consistency, average hue of each HSV image, and the inter-frame luminance consistency of the continuous plurality of HSV images.
[0041] For the analysis module 30 to obtain the in-frame luminance consistency, average hue of each HSV image, and the inter-frame luminance consistency of the continuous plurality of HSV images, first, the analysis module 30 can calculate the overall luminance average value and overall hue average value of each HSV image, that is, the average value of the luminance values of all pixels in each HSV image and the average value of the hue values of all pixels in each HSV image. Then, the analysis module 30 divides each HSV image into n 2 regions, where n is an integer greater than 1. Specifically, each HSV image can be equally divided into a rectangular region of n rows and n columns. It should be understood that the larger the value of n, the more accurate the analysis result, but the computing power level of the processor executing the method of the embodiment of the present invention should also be considered. For each HSV image, the regional luminance average value within each region can be calculated, that is, the average value of the luminance values of the pixels within each region. And, for each HSV image, it can be determined whether the difference between the largest regional luminance average value and the smallest regional luminance average value is greater than a first threshold. If so, it is determined that the in-frame luminance of the HSV image is inconsistent, otherwise it is determined that the in-frame luminance of the HSV image is consistent. If the continuous plurality of HSV images are all in-frame luminance consistent, it is further determined whether the difference between the largest overall luminance average value and the smallest overall luminance average value is greater than a second threshold. If so, it is determined that the inter-frame luminance of the continuous plurality of HSV images is inconsistent, otherwise it is determined that the inter-frame luminance of the continuous plurality of HSV images is consistent. The first threshold and the second threshold here are both preset values, which need to be preset for each actual process scenario and are not limited to a specific value here.
[0042] If the overall luminance average value of at least one HSV image is outside the preset luminance range and the overall hue average value is outside the preset hue range, the predicted coating defect is insufficient or excessive sputtering amount. For target materials of different materials, the preset luminance range and the preset hue range are different, and both also need to be preset for each actual process scenario. And, according to the size relationship between the overall luminance average value and the minimum boundary value and maximum boundary value of the preset luminance range, and the size relationship between the overall hue average value and the minimum boundary value and maximum boundary value of the preset hue range, it can be determined whether the sputtering amount is insufficient or excessive. Insufficient or excessive sputtering amount will cause problems such as too small or too large film thickness, insufficient adhesion, and poor film layer quality.
[0043] If the in-frame brightness of at least one HSV image is inconsistent, the predicted coating defect is uneven sputtering. Uneven sputtering can cause problems such as uneven film thickness.
[0044] If the inter-frame brightness of multiple consecutive HSV images is inconsistent, the predicted coating defect is sputtering amount fluctuation. Sputtering amount fluctuation can cause problems such as insufficient film adhesion and poor film layer quality.
[0045] In an embodiment of the present invention, if the sputtering amount is insufficient or excessive, the control module 10 can adjust at least one of the sputtering power, the argon gas pressure, and the target-substrate distance, and issue a prompt message to check the power supply and the gas source. For example, when the sputtering amount is insufficient, the sputtering power can be increased, and the argon gas pressure can be increased in order to increase the sputtering amount. Also, the target-substrate distance can be reduced to increase the deposition strength and speed, in order to reduce or avoid too small film thickness. The above adjustments may not necessarily eliminate the corresponding coating defects. Therefore, by checking the power supply and the gas source, problems such as inaccurate parameters and faults of the power supply and the gas source can be fundamentally discovered, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0046] If the sputtering is uneven, the control module 10 can adjust the moving speed of the object to be coated, and issue a prompt message to check the magnet and the target material. Specifically, by increasing the moving speed of the object to be coated, the uniformity of the film thickness can be improved. The above adjustments may not necessarily eliminate the corresponding coating defects. Therefore, by checking the magnet and the target material, problems such as the offset of the magnetic field position of the magnet, the roughness and contamination of the target material surface can be fundamentally discovered, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0047] If the sputtering amount fluctuates, the control module 10 can issue a prompt message to check the power supply and the gas source. By checking the power supply and the gas source, problems such as output fluctuations of the power supply and the gas source can be fundamentally discovered, and the problems causing the corresponding coating defects can be solved through means such as maintenance and replacement.
[0048] In addition, it should be noted that the above adjustments to the operating parameters of the magnetron sputtering equipment can be made with a preset adjustment amount every time a coating defect is predicted, or can be continuously fine-tuned until no coating defect is analyzed. After the adjustment is completed, the subsequent magnetron sputtering equipment will continuously operate with the adjusted operating parameters until a coating defect is analyzed again.
[0049] The coating control device based on image analysis according to an embodiment of the present invention, in the magnetron sputtering coating process, collects images of particle clusters sputtered from a target, analyzes the images to predict corresponding coating defects, and adjusts the operating parameters of the magnetron sputtering equipment and / or issues prompt information according to the coating defects, so as to improve the coating defects. Thus, by collecting and analyzing the images of the sputtered particle clusters, the possible coating defects can be roughly predicted, so that the coating defects can be improved in time and the coating quality can be improved.
[0050] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The meaning of "a plurality" is two or more, unless otherwise specifically defined.
[0051] In the present invention, unless otherwise clearly defined and limited, the terms such as "installation", "connection", "connection", "fixation" and the like should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral body; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.
[0052] In the present invention, unless otherwise clearly defined and limited, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath" and "under" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.
[0053] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0054] Any process or method description represented in the flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a manner that may not be shown or discussed in the order, including in a substantially simultaneous manner according to the functions involved or in the reverse order, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.
[0055] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in connection with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.
[0056] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
[0057] Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.
[0058] In addition, each functional unit in various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0059] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.
Claims
1. A coating control method based on image analysis, characterized in that: The following steps are involved: After the target material for coating is installed at the target position, the magnetron sputtering device is controlled to start and operate with preset operating parameters so as to coat the object to be coated in the sputtering chamber of the magnetron sputtering device; During the operation of the magnetron sputtering device, real-time acquisition of images of particle clusters sputtered from the target material in the sputtering chamber; Analyzing the image of the particle cluster to predict corresponding coating defects; According to the coating defect, the operating parameters of the magnetron sputtering device are adjusted and / or prompt information is issued to improve the coating defect.
2. The coating control method based on image analysis according to claim 1, characterized in that: The image of the particle cluster is analyzed to predict the corresponding coating defects, specifically including: Converting a plurality of continuous images of the particle clusters into HSV space to obtain a plurality of continuous HSV images; Obtaining brightness intra-frame consistency, average hue, and brightness inter-frame consistency of a plurality of consecutive HSV images according to brightness information and hue information of each HSV image; The corresponding coating defects are predicted according to the brightness intra-frame consistency, the average hue of each HSV image and the brightness inter-frame consistency of a plurality of consecutive HSV images.
3. The coating control method based on image analysis according to claim 2, characterized in that: Obtaining the brightness intra-frame consistency, average hue, and brightness inter-frame consistency of each HSV image according to the brightness information and hue information of each HSV image, specifically including: Calculate the overall brightness average and the overall hue average of each of the HSV images; Each of the HSV images is divided into n 2 regions, where n is an integer greater than 1; For each of the HSV images, calculate the average regional brightness within each region thereof; For each of the HSV images, determine whether the difference between the maximum regional brightness average value and the minimum regional brightness average value is greater than a first threshold value; if so, determine that the brightness within the HSV image frame is inconsistent; otherwise, determine that the brightness within the HSV image frame is consistent; If the brightness of multiple consecutive HSV images is consistent within the frame, it is further determined whether the difference between the maximum overall brightness average value and the minimum overall brightness average value is greater than a second threshold. If so, it is determined that the brightness between the multiple consecutive HSV image frames is inconsistent; otherwise, it is determined that the brightness between the multiple consecutive HSV image frames is consistent.
4. The coating control method based on image analysis according to claim 3, characterized in that: Predicting corresponding coating defects according to the brightness intra-frame consistency, average hue and brightness inter-frame consistency of a plurality of consecutive HSV images of each HSV image specifically includes: If the overall brightness average value of at least one of the HSV images is outside the preset brightness range, and the overall hue average value is outside the preset hue range, the predicted coating defect is insufficient or excessive sputtering; If the brightness within the frame of at least one of the HSV images is inconsistent, the predicted coating defect is uneven sputtering; If the brightness between a plurality of consecutive HSV image frames is inconsistent, the predicted coating defect is a sputtering amount fluctuation.
5. The coating control method based on image analysis according to claim 4, characterized in that: Adjusting the operating parameters of the magnetron sputtering device and / or issuing prompt information according to the coating defects specifically includes: If the sputtering amount is insufficient or excessive, at least one of the sputtering power, the pressure of the argon gas, and the target-substrate distance is adjusted, and a prompt message for checking the power supply and gas source is issued; If the sputtering is uneven, the moving speed of the object to be coated is adjusted, and a prompt message is issued to check the magnet and target material; If the sputtering amount fluctuates, a prompt message is issued to check the power supply and gas supply.
6. A coating control device based on image analysis, characterized in that: It includes control module, acquisition module and analysis module. The control module is used to control the magnetron sputtering device to start and operate with preset operating parameters after the target material for coating is installed at the target position, so as to coat the object to be coated in the sputtering chamber of the magnetron sputtering device; The acquisition module is used to acquire images of particle clusters sputtered by the target material in the sputtering chamber in real time during the operation of the magnetron sputtering device; The analysis module is used to analyze the image of the particle cluster to predict the corresponding coating defects; The control module is also used to adjust the operating parameters of the magnetron sputtering equipment and / or issue prompt information according to the coating defects, so as to improve the coating defects.
7. The coating control device based on image analysis according to claim 6, characterized in that: The analysis module is specifically used for: Converting a plurality of continuous images of the particle clusters into HSV space to obtain a plurality of continuous HSV images; Obtaining brightness intra-frame consistency, average hue, and brightness inter-frame consistency of a plurality of consecutive HSV images according to brightness information and hue information of each HSV image; The corresponding coating defects are predicted according to the brightness intra-frame consistency, the average hue of each HSV image and the brightness inter-frame consistency of a plurality of consecutive HSV images.
8. The coating control device based on image analysis according to claim 7, characterized in that: The analysis module is specifically used for: Calculate the overall brightness average and the overall hue average of each of the HSV images; Each of the HSV images is divided into n 2 regions, where n is an integer greater than 1; For each of the HSV images, calculate the average regional brightness within each region thereof; For each of the HSV images, determine whether the difference between the maximum regional brightness average value and the minimum regional brightness average value is greater than a first threshold value; if so, determine that the brightness within the HSV image frame is inconsistent; otherwise, determine that the brightness within the HSV image frame is consistent; If the brightness of multiple consecutive HSV images is consistent within the frame, it is further determined whether the difference between the maximum overall brightness average value and the minimum overall brightness average value is greater than a second threshold. If so, it is determined that the brightness between the multiple consecutive HSV image frames is inconsistent; otherwise, it is determined that the brightness between the multiple consecutive HSV image frames is consistent.
9. The coating control device based on image analysis according to claim 8, characterized in that: The analysis module is specifically used for: When the overall brightness average value of at least one of the HSV images is outside the preset brightness range, and the overall hue average value is outside the preset hue range, the predicted coating defect is insufficient or excessive sputtering amount; When the brightness within a frame of at least one of the HSV images is inconsistent, the predicted coating defect is uneven sputtering; When the brightness between a plurality of consecutive HSV image frames is inconsistent, the predicted coating defect is a sputtering amount fluctuation.
10. The coating control device based on image analysis according to claim 9, characterized in that: The control module is specifically used for: When the sputtering amount is insufficient or excessive, at least one of the sputtering power, the pressure of the argon gas, and the target-substrate distance is adjusted, and a prompt message for checking the power supply and the gas source is issued; When sputtering is uneven, the moving speed of the object to be coated is adjusted, and a prompt message to check the magnet and target is issued; When the sputtering amount fluctuates, a prompt message is issued to check the power supply and gas source.