A method and device for detecting the breakage of a thimble, a thin film deposition apparatus, and a storage medium

Abstract

This application relates to the field of flaw detection technology, and discloses a method and apparatus for detecting pin fracture, a thin film deposition equipment, and a storage medium. The pin fracture detection method includes: moving an X-ray detection mechanism to the area to be inspected where the pin is located; performing penetration image recognition on the area to be inspected using the X-ray detection mechanism to obtain an image of the pin containing structural features, wherein the structural features include missing or broken parts, abnormal shapes or contours, and abnormal locations and distributions; preprocessing and evaluating the obtained image to be inspected, and generating a pin fault detection result, wherein the fault detection result includes no damage, defects, strain, or fracture.

Description

Technical Field

[0001] This application relates to the field of flaw detection technology, specifically to a method and apparatus for detecting pin fracture, a thin film deposition equipment, and a storage medium. Background Technology

[0002] Currently, most thin-film deposition equipment used in semiconductor processes operates in a vacuum environment or a sealed lower space. Within the reaction chamber, lift pins are used as a transfer medium to interact with the heating plate and robotic arm for wafer transfer. For example, lift pins typically employ a three- or four-pin mechanism. After the robotic arm transfers the wafer to the reaction chamber, the lift pin lifts it to separate the wafer from the robotic arm. After the robotic arm exits the reaction chamber, the lift pin descends or the heating plate rises, placing the wafer onto the heating plate for semiconductor processing. After the process is complete, the lift pin lifts the wafer from the heating plate, and the robotic arm then transfers the wafer out of the reaction chamber.

[0003] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art:

[0004] If the ejector pin breaks during the above-mentioned movement, the heating plate will not be able to keep level, and may even damage the wafer. Therefore, how to achieve rapid real-time online detection of the ejector pin is a technical problem that urgently needs to be solved.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0007] This disclosure provides a method and apparatus for detecting pin breakage, a thin film deposition equipment, and a storage medium to enable online detection of pins, thereby promptly determining whether the pin rod has malfunctioned, and enabling emergency shutdown of the thin film deposition equipment in the event of pin breakage to prevent wafer damage.

[0008] In some embodiments, the method for detecting the breakage of the ejector pin includes:

[0009] Move the X-ray detection mechanism to the area to be detected where the pin is located;

[0010] The X-ray inspection mechanism performs penetration image recognition on the area to be inspected to obtain the image of the pin containing structural features, wherein the structural features include missing or broken parts, abnormal shapes or contours, and abnormal locations and distributions.

[0011] The acquired image to be detected is preprocessed and evaluated, and a fault detection result is generated, wherein the fault detection result includes no damage, defects, tearing or breakage.

[0012] Optionally, moving the X-ray detection mechanism to the area to be detected where the probe is located includes:

[0013] Based on the first position information of the heating plate in the thin film deposition equipment and the current operating conditions, obtain the second position information of the ejector pin;

[0014] Based on the second position information, the lifting assembly in the thin film deposition equipment is controlled to move the X-ray inspection mechanism to the area to be inspected where the pin is located.

[0015] Optionally, the step of preprocessing and evaluating the acquired image to be detected and generating a pin fault detection result includes:

[0016] The image to be detected is corrected by using a pre-trained image processing model to obtain the corrected image to be detected.

[0017] The pre-trained fracture detection model is used to extract and classify the structural features of the corrected image to be detected.

[0018] The extracted and classified results are evaluated according to the preset pin fault evaluation rules, and the evaluation results are displayed in a visual form, generating corresponding pin fault detection results.

[0019] Optionally, the step of correcting the image to be detected using a pre-trained image processing model to obtain a corrected image to be detected includes:

[0020] The image processing model is used to perform a first correction operation on the structural features of the image to be detected, wherein the first correction operation includes removal, filling, offsetting, scaling and / or filtering.

[0021] The image processing model is used to perform a second correction operation on the structural features of the image to be detected, wherein the second correction operation includes line correction, contour correction and / or position correction.

[0022] The image processing model performs a third correction operation on the structural features of the image to be detected, wherein the third correction operation includes abnormal density correction and / or color region correction.

[0023] Optionally, the training method for the image processing model includes:

[0024] Acquire sample images of ejector pins under multiple different working conditions;

[0025] Structural feature labeling is performed on multiple thimble sample images to obtain labeled multiple thimble sample images;

[0026] The initial image processing model is trained using multiple labeled pin sample images, and the image processing model is obtained when the training stopping condition is met.

[0027] Optionally, the training method for the fracture detection model includes:

[0028] Obtain a preset pin fault dataset, which includes: structural features, fault type, equipment information, and X-ray images;

[0029] Based on the purpose of fault detection and classification, the relevant features of the thimble fault dataset are split into training set and test set;

[0030] The initial fracture detection model is trained using the training set to generate the trained fracture detection model.

[0031] The trained fracture detection model is adjusted and optimized based on the test set, including modifying feature selection and adjusting model parameters.

[0032] Optionally, after generating the pin fault detection result, the method further includes:

[0033] If the fault detection result is a defect or scratch, the severity of the fault in the thin film deposition equipment is determined to be general, and maintenance prompts are given through the warning device installed on the thin film deposition equipment;

[0034] If the fault detection result indicates a breakage, the severity of the fault in the thin film deposition equipment is determined to be severe. The fault is then indicated by the warning device installed on the thin film deposition equipment, and the thin film deposition equipment is shut down immediately.

[0035] In some embodiments, the fracture detection device for the ejector pin includes:

[0036] The image acquisition module is configured to move the X-ray detection mechanism to the area to be detected where the pin is located;

[0037] The image analysis module is configured to perform penetration image recognition on the area to be detected by the X-ray detection mechanism to obtain the image to be detected corresponding to the thimble containing structural features, wherein the structural features include missing or broken parts, abnormal shapes or contours, and abnormal positions and distributions.

[0038] The detection report module is configured to preprocess and evaluate the acquired image to be detected, and generate a pin fault detection result, wherein the fault detection result includes no damage, defect, tear or breakage.

[0039] In some embodiments, the thin film deposition apparatus includes a processor and a memory storing program instructions, the processor being configured to execute a pin breakage detection method as described in this application when the program instructions are executed.

[0040] In some embodiments, the storage medium stores program instructions that, when executed, perform the pin breakage detection method as described in this application.

[0041] The pin breakage detection method and apparatus, thin film deposition equipment and storage medium provided in this disclosure can achieve the following technical effects:

[0042] X-ray inspection is used to perform penetrating image recognition on the ejector pins. The image containing the structural features of the ejector pins is analyzed and evaluated, and ejector pin fault detection results are generated. This allows for emergency shutdown of the thin film deposition equipment in the event of ejector pin breakage, preventing wafer damage. Simultaneously, real-time online detection of ejector pin defects, scratches, and breaks is achieved, improving the efficiency and accuracy of ejector pin fault detection, reducing manpower input, shortening overall inspection time, and improving production quality and efficiency.

[0043] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0044] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0045] Figure 1 This is a schematic diagram of a method for detecting the breakage of a pin provided in an embodiment of this disclosure;

[0046] Figure 2 This is a schematic diagram of another method for detecting the breakage of a ejector pin provided in an embodiment of this disclosure;

[0047] Figure 3 This is a schematic diagram of another method for detecting the breakage of a ejector pin provided in an embodiment of this disclosure;

[0048] Figure 4 This is a schematic diagram of another method for detecting the breakage of a ejector pin provided in an embodiment of this disclosure;

[0049] Figure 5 This is a schematic diagram of another method for detecting the breakage of a ejector pin provided in an embodiment of this disclosure;

[0050] Figure 6 This is a schematic diagram of a thin film deposition apparatus provided in an embodiment of this disclosure;

[0051] Figure 7 This is a schematic diagram of a storage medium provided in an embodiment of this disclosure. Detailed Implementation

[0052] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0053] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0054] Unless otherwise stated, the term "multiple" means two or more.

[0055] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0056] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0057] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0058] Combination Figure 1 As shown, this disclosure provides a method for detecting the breakage of a pin, including:

[0059] Step 101: Move the X-ray inspection mechanism to the area to be inspected where the probe is located.

[0060] Step 102: The X-ray inspection mechanism performs penetration image recognition on the area to be inspected to obtain the image of the pin containing structural features, including missing or broken parts, abnormal shapes or contours, and abnormal locations and distributions.

[0061] Step 103: Preprocess and evaluate the acquired image to be detected, and generate pin fault detection results, including no damage, defects, tearing or breakage.

[0062] In the embodiments of this application, the ejector pin can be a circular, rectangular, or irregularly shaped metal casting or sheet metal part, etc. The X-ray inspection mechanism of this application utilizes the ability of X-rays to penetrate the material of the ejector pin for penetration image recognition. Due to the different absorption and scattering effects of the ejector pin material on X-rays, the film exposure is different, thus forming images of different densities on the image to be inspected (film), which can be used to determine material defects. Of course, X-rays can also be replaced with gamma rays or other high-energy rays, and this application does not specifically limit them.

[0063] The pin fracture detection method provided in this disclosure utilizes an X-ray inspection mechanism to perform penetration image recognition on the pin, analyzes and evaluates the image to be inspected containing structural features, and generates pin fault detection results. This improves the efficiency and accuracy of pin fault detection, enabling emergency shutdown of the thin film deposition equipment in the event of pin fracture to prevent wafer damage. Simultaneously, it achieves real-time online detection of pin defects, scratches, and fractures, reducing manpower input and shortening the overall inspection time, thereby improving production quality and efficiency.

[0064] Combination Figure 2 As shown, this disclosure provides a method for detecting the breakage of a pin, including:

[0065] Step 201: Based on the first position information of the heating plate in the thin film deposition equipment and the current operating conditions, obtain the second position information of the ejector pin.

[0066] Step 202: Based on the second position information, control the lifting assembly in the thin film deposition equipment to move the X-ray detection mechanism to the area to be detected where the pin is located.

[0067] Step 203: The X-ray inspection mechanism performs penetration image recognition on the area to be inspected to obtain the image of the pin containing structural features, including missing or broken parts, abnormal shapes or contours, and abnormal locations and distributions.

[0068] Step 204: Correct the image to be detected using a pre-trained image processing model to obtain the corrected image to be detected.

[0069] Step 205: Extract and classify the structural features of the corrected image to be detected using a pre-trained fracture detection model.

[0070] Step 206: Evaluate the extraction and classification results according to the preset pin fault evaluation rules, display the evaluation results in a visual form, and generate the corresponding pin fault detection results.

[0071] In the embodiments of this application, for thin film deposition equipment, the ejector pin is often located inside the reaction chamber and is relatively small, making it impossible to directly determine its specific position. However, the ejector pin often needs to be used in conjunction with a heating plate, which is relatively large, and its specific position can be accurately obtained through sensors. Therefore, this application can calculate the second position information of the ejector pin based on the first position information of the heating plate in the thin film deposition equipment and the current operating conditions (e.g., whether coating is in progress, whether pressure is being increased / decreased, or whether heating / cooling is being performed). Based on the first position information of the heating plate and the current operating conditions, the lifting assembly in the thin film deposition equipment can be controlled to move the X-ray detection mechanism to the area to be detected where the ejector pin is located.

[0072] In one embodiment of this application, the structural features of this application specifically include: missing or broken lines appearing in the image to be detected, indicating a breakage of the ejector pin component; abnormal shapes or contours appearing in the image to be detected, indicating deformation, damage, or material abnormalities of the ejector pin; and abnormal locations and distributions including the specific locations and distributions of the faults in the image to be detected. These structural features can be used to identify whether a fault exists in the image to be detected of the ejector pin, and can be used to assess the severity of the fault and the urgency of repair.

[0073] This enables better real-time online detection of missing or broken ejector pins, abnormal shapes or contours, and abnormal locations and distributions, reducing manpower and inspection time and improving coating efficiency.

[0074] Optionally, combined Figure 3 As shown, in step 204, the image to be detected is corrected using a pre-trained image processing model to obtain the corrected image to be detected, including:

[0075] Step 301: Perform a first correction operation on the structural features of the image to be detected using an image processing model, wherein the first correction operation includes removal, filling, offsetting, scaling and / or filtering.

[0076] Step 302: Perform a second correction operation on the structural features of the image to be detected using an image processing model, wherein the second correction operation includes line correction, contour correction and / or position correction.

[0077] Step 303: Perform a third correction operation on the structural features of the image to be detected using an image processing model, wherein the third correction operation includes abnormal density correction and / or color region correction.

[0078] In the embodiments of this application, a pre-trained image processing model is used to correct the image to be detected, resulting in a corrected image. Specifically, the image processing model can perform matching detection on the image to be detected to obtain information such as the position, angle, distortion, and deformation of the image, and then perform transformation processing on the image to correct its lines, contours, and positions. Then, the image processing model performs operations such as removal, filling, offsetting, scaling, and / or filtering on the image to be detected, thereby correcting its lines, contours, and / or positions.

[0079] This allows for better analysis and evaluation of the image to be tested on the pin, thereby improving the efficiency and accuracy of fault detection in the image to be tested.

[0080] Optionally, combined Figure 4 As shown, this application provides a method for training the image processing model in step 204, including:

[0081] Step 401: Obtain sample images of ejector pins under multiple different working conditions.

[0082] Step 402: Perform structural feature labeling on multiple thimble sample images to obtain multiple labeled thimble sample images.

[0083] Step 403: Train the initialized image processing model using multiple labeled pin sample images. Once the training stopping condition is met, the image processing model is obtained.

[0084] Optionally, combined Figure 5 As shown, this application provides a method for training the fracture detection model in step 204, including:

[0085] Step 501: Obtain a preset pin fault dataset, which includes: structural features, fault type, equipment information and X-ray images.

[0086] Step 502: Based on the purpose of fault detection and classification, split the relevant features of the pin fault dataset into training set and test set.

[0087] Step 503: Train the initialized fracture detection model using the training set to generate the trained fracture detection model.

[0088] Step 504: Adjust and optimize the trained fracture detection model based on the test set.

[0089] In the embodiments of this application, the fault dataset is divided into a training set and a test set, and data processing operations such as scaling, dimensionality reduction, and deduplication are performed. Then, machine learning algorithms such as the pocket algorithm, standard linear regression algorithm, and Naive Bayes classification algorithm are used to train the initialized fracture detection model, determine the model parameters and the number of decisions, and generate the trained fracture detection model. Further, the trained fracture detection model is adjusted and optimized using the test set. The adjustment and optimization metrics include precision, recall, and F1 score to evaluate the model's performance and accuracy. The adjustment and optimization methods include modifying feature selection and adjusting model parameters. Finally, the adjusted and optimized fracture detection model is deployed to the software system of the thin film deposition equipment to realize online detection of the ejector pin, thereby timely determining whether the ejector pin has failed, so as to realize emergency shutdown of the thin film deposition equipment in the event of ejector pin breakage and prevent wafer damage.

[0090] In one embodiment of this application, after generating the pin fault detection result, the method further includes:

[0091] If the fault detection result is a defect or scratch, the severity of the fault in the thin film deposition equipment is determined to be general, and maintenance prompts are given through the warning device installed on the thin film deposition equipment;

[0092] If the fault detection result indicates a breakage, the severity of the fault in the thin film deposition equipment is determined to be severe. The fault is then indicated by the warning device installed on the thin film deposition equipment, and the thin film deposition equipment is shut down immediately.

[0093] In this way, based on the fault detection results of the ejector pin, the present application can promptly and conspicuously remind the engineer through the warning device on the thin film deposition equipment, so that if the fault detection result is a defect or scratch, the engineer can be notified in a timely manner to carry out controllable repairs on the thin film deposition equipment; and if the fault detection result is a breakage, the thin film deposition equipment can be directly shut down in an emergency, thereby avoiding wafer damage and breakage.

[0094] Combination Figure 6 As shown, this disclosure provides a device for detecting the breakage of a ejector pin, comprising:

[0095] The image acquisition module 601 is configured to move the X-ray detection mechanism to the area to be detected where the pin is located;

[0096] The image analysis module 602 is configured to perform penetration image recognition on the area to be detected through the X-ray detection mechanism to obtain the image to be detected corresponding to the pin, which includes structural features, including missing or broken parts, abnormal shapes or contours, and abnormal locations and distributions.

[0097] The inspection report module 603 is configured to preprocess and evaluate the acquired image to be inspected and generate pin fault detection results, wherein the fault detection results include no damage, defects, tearing or breakage.

[0098] Optionally, the image acquisition module 601 is specifically configured as follows:

[0099] Based on the first position information of the heating plate in the thin film deposition equipment and the current operating conditions, obtain the second position information of the ejector pin;

[0100] Based on the second position information, the lifting assembly in the thin film deposition equipment is controlled to move the X-ray inspection mechanism to the area to be inspected where the pin is located.

[0101] Optionally, the test report module 603 is specifically configured as follows:

[0102] The image to be detected is corrected by using a pre-trained image processing model to obtain the corrected image to be detected.

[0103] The pre-trained fracture detection model is used to extract and classify the structural features of the corrected image to be detected.

[0104] The extracted and classified results are evaluated according to the preset pin fault evaluation rules, and the evaluation results are displayed in a visual form, generating corresponding pin fault detection results.

[0105] Optionally, the test report module 603 is specifically configured as follows:

[0106] Based on the image processing model, the structural features of the image to be detected are corrected by operations such as removal, filling, offsetting, scaling or filtering.

[0107] Based on the image processing model, the lines, contours, and positions of the image to be detected are corrected;

[0108] Based on the image processing model, abnormal density and color region corrections are performed on the image to be detected.

[0109] Optionally, the pin breakage detection device of this application further includes an alarm module 604:

[0110] The alarm module 604 is specifically configured as follows:

[0111] If the fault detection result is a defect or scratch, the severity of the fault in the thin film deposition equipment is determined to be general, and maintenance prompts are given through the warning device installed on the thin film deposition equipment;

[0112] If the fault detection result indicates a breakage, the severity of the fault in the thin film deposition equipment is determined to be severe. The fault is then indicated by the warning device installed on the thin film deposition equipment, and the thin film deposition equipment is shut down immediately.

[0113] The pin fracture detection device provided in this embodiment uses an X-ray inspection mechanism to perform penetration image recognition on the pin, analyzes and evaluates the image to be inspected containing structural features, and generates pin fault detection results. This improves the efficiency and accuracy of pin fault detection, enabling emergency shutdown of the thin film deposition equipment in the event of pin fracture to prevent wafer damage. Simultaneously, it achieves real-time online detection of pin defects, scratches, and fractures, reducing manpower input and shortening the overall inspection time, thereby improving production quality and efficiency.

[0114] Combination Figure 7 As shown, this disclosure provides a thin film deposition apparatus, including a processor 700 and a memory 701. Optionally, the apparatus may further include a communication interface 702 and a bus 703. The processor 700, communication interface 702, and memory 701 can communicate with each other via the bus 703. The communication interface 702 can be used for information transmission. The processor 700 can call logical instructions in the memory 701 to execute the pin breakage detection method of the above embodiment.

[0115] Furthermore, the logic instructions in the aforementioned memory 701 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0116] The memory 701, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 700 executes functional applications and data processing by running the program instructions / modules stored in the memory 701, thereby implementing the pin breakage detection method in the above embodiments.

[0117] The memory 701 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 701 may include high-speed random access memory and may also include non-volatile memory.

[0118] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described pin breakage detection method.

[0119] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0120] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0121] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0122] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0123] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for detecting the breakage of a pin, characterized in that, include: Move the X-ray inspection mechanism to the area to be inspected where the probe is located; The X-ray detection mechanism performs penetration image recognition on the area to be detected to obtain the image of the pin containing structural features, wherein the structural features include missing or broken parts, abnormal shapes or contours, and abnormal positions and distributions. The acquired image to be detected is preprocessed and evaluated, and a fault detection result is generated, wherein the fault detection result includes no damage, defects, tearing or breakage.

2. The fracture detection method according to claim 1, characterized in that, Moving the X-ray detection mechanism to the area to be detected where the probe is located includes: Based on the first position information of the heating plate in the thin film deposition equipment and the current operating conditions, obtain the second position information of the ejector pin; Based on the second position information, the lifting assembly in the thin film deposition equipment is controlled to move the X-ray inspection mechanism to the area to be inspected where the pin is located.

3. The fracture detection method according to claim 1, characterized in that, The step of preprocessing and evaluating the acquired image to be detected, and generating a pin fault detection result, includes: The image to be detected is corrected by using a pre-trained image processing model to obtain the corrected image to be detected. The pre-trained fracture detection model is used to extract and classify the structural features of the corrected image to be detected. The extracted and classified results are evaluated according to the preset pin fault evaluation rules, and the evaluation results are displayed in a visual form, generating the corresponding pin fault detection results.

4. The fracture detection method according to claim 3, characterized in that, The step of correcting the image to be detected using a pre-trained image processing model to obtain a corrected image to be detected includes: The image processing model is used to perform a first correction operation on the structural features of the image to be detected, wherein the first correction operation includes removal, filling, offsetting, scaling and / or filtering. The image processing model is used to perform a second correction operation on the structural features of the image to be detected, wherein the second correction operation includes line correction, contour correction and / or position correction. The image processing model performs a third correction operation on the structural features of the image to be detected, wherein the third correction operation includes abnormal density correction and / or color region correction.

5. The fracture detection method according to claim 3, characterized in that, The training method for the image processing model includes: Acquire sample images of ejector pins under multiple different working conditions; Structural feature labeling is performed on multiple thimble sample images to obtain labeled multiple thimble sample images; The initial image processing model is trained using multiple labeled pin sample images, and the image processing model is obtained when the training stopping condition is met.

6. The fracture detection method according to claim 3, characterized in that, The training method for the fracture detection model includes: Obtain a preset pin fault dataset, which includes: structural features, fault type, equipment information, and X-ray images; Based on the purpose of fault detection and classification, the relevant features of the thimble fault dataset are split into training set and test set; The initial fracture detection model is trained using the training set to generate the trained fracture detection model. The fracture detection model was adjusted and optimized based on the test set.

7. The fracture detection method according to claim 1, characterized in that, After generating the pin fault detection result, the process also includes: If the fault detection result is a defect or scratch, the severity of the fault in the thin film deposition equipment is determined to be general, and maintenance prompts are given through the warning device installed on the thin film deposition equipment; If the fault detection result indicates a breakage, the severity of the fault in the thin film deposition equipment is determined to be severe. The fault is then indicated by the warning device installed on the thin film deposition equipment, and the thin film deposition equipment is shut down immediately.

8. A device for detecting the breakage of a ejector pin, characterized in that, include: The image acquisition module is configured to move the X-ray detection mechanism to the area to be detected where the pin is located; The image analysis module is configured to perform penetration image recognition on the area to be detected through the X-ray detection mechanism to obtain the image to be detected corresponding to the thimble containing structural features, wherein the structural features include missing or broken parts, abnormal shapes or contours, and abnormal positions and distributions. The detection report module is configured to preprocess and evaluate the acquired image to be detected, and generate a pin fault detection result, wherein the fault detection result includes no damage, defect, tear or breakage.

9. A thin film deposition apparatus, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the pin breakage detection method as described in any one of claims 1 to 7 when running the program instructions.

10. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the pin breakage detection method as described in any one of claims 1 to 7.

Images