Defect detection method, device and equipment of plastic package chip, medium and product

Abstract

The invention discloses a defect detection method, device and equipment for a plastic package chip, a medium and a product, and belongs to the technical field of nondestructive testing and deep learning. The method comprises the following steps: acquiring a to-be-detected image of a target plastic package chip; performing enhancement processing on the to-be-detected image to obtain a target to-be-detected image; and performing defect detection on the target to-be-detected image through a defect detection model to obtain a target defect position and a target defect type. According to the technical scheme, the defect detection accuracy of the plastic package chip can be improved.

Description

Technical Field

[0001] This invention relates to the fields of non-destructive testing and deep learning, and particularly to the field of ultrasonic scanning inspection technology for the packaging process quality of plastic-encapsulated microelectronic chips (integrated circuits). Specifically, it relates to a defect detection method, apparatus, equipment, medium, and product for plastic-encapsulated chips. Background Technology

[0002] As microelectronic packaging technology advances towards higher density and miniaturization, quality control in the molding process becomes crucial. Internal defects such as interface delamination, voids, and bubbles are key factors affecting chip reliability, lifespan, and even eventual failure. Ultrasonic scanning technology, especially C-mode ultrasonic scanning, has become an indispensable standard testing method in this field because it can non-destructively image the internal structure of the package.

[0003] In recent years, the development of this technology has shown a trend of transitioning from "manual interpretation" to "automated and intelligent analysis." Initially, detection relied entirely on technicians' experience in judging ultrasound image features (such as brightness, shape, and location). To improve efficiency and consistency, the industry gradually introduced semi-automatic detection algorithms based on digital image processing, which represent the current mainstream technology level. However, these methods are still essentially still within the scope of "manually defined features." With the breakthrough progress of artificial intelligence, especially deep learning technology, in the field of computer vision, applying it to the automatic analysis of ultrasound images to achieve a higher level of automation and accuracy has become a clear research and development direction in this field. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for defect detection of molded chips, in order to improve the accuracy of defect detection of molded chips.

[0005] According to one aspect of the present invention, a defect detection method for a molded chip is provided, the method comprising:

[0006] Acquire the image of the target molded chip to be inspected;

[0007] The image to be detected is enhanced to obtain the target image to be detected;

[0008] The defect detection model is used to detect defects in the target image to obtain the location and type of the target defect; the defect detection model is deployed in the ultrasonic testing system.

[0009] According to another aspect of the present invention, a defect detection device for molded chips is provided, the device comprising:

[0010] The image acquisition module is used to acquire the image of the target molded chip to be inspected.

[0011] The image enhancement module is used to enhance the image to be detected to obtain the target image to be detected;

[0012] The defect detection module is used to perform defect detection on the target image to be inspected through a defect detection model to obtain the target defect location and target defect type; the defect detection model is deployed in the ultrasonic testing system.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the defect detection method for plastic-encapsulated chips according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the defect detection method for a plastic-encapsulated chip according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the defect detection method for a plastic-encapsulated chip according to any embodiment of the present invention.

[0019] The technical solution of this invention involves acquiring an image of a target molded chip to be inspected; enhancing the image to obtain the target image to be inspected; and using a defect detection model to detect defects in the target image to obtain the location and type of the target defect. This technical solution replaces the manual image feature extraction and rule setting steps of traditional methods with a pre-trained network model. Operators do not need extensive experience in interpreting ultrasound images; they only need to input the acquired ultrasound scan data into the model to automatically obtain defect analysis results. This makes the inspection operation extremely simple and significantly lowers the technical threshold. Non-professionals can operate the system after simple training, effectively solving the problem of enterprises' reliance on high-end inspection experts and simplifying human resource allocation and training costs.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a defect detection method for a plastic-encapsulated chip according to an embodiment of the present invention;

[0023] Figure 2 This is a flowchart of a defect detection method for a plastic-encapsulated chip according to an embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of a defect detection device for a plastic-encapsulated chip according to an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the defect detection method for plastic-encapsulated chips according to embodiments of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of relevant data such as the image to be inspected and the original ultrasound image of the encapsulated chip involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0029] The current mainstream defect detection process for molded chips is as follows: data acquisition (e.g., acquiring grayscale images) - preprocessing (e.g., filtering, noise reduction, contrast enhancement) - feature region segmentation (e.g., using threshold segmentation algorithms) - feature extraction and brightening (e.g., calculating area, perimeter, and grayscale), rule judgment with manually set threshold rules, and output of results (pass / fail). While this approach improves detection efficiency to some extent, it is insensitive to small, low-contrast, atypically shaped, or background noise-mixed defects, easily leading to missed detections. Furthermore, artifacts and noise in the image are easily misjudged as defects, resulting in over-detection. The fundamental reason is that manually set features and rules cannot encompass the ever-changing defect morphologies in actual production. The appearance of defects in ultrasonic images is influenced by various factors such as material acoustic properties, interface conditions, and equipment parameters, resulting in extremely complex morphologies. Attempting to accurately describe all defects using a few simple geometric and grayscale features (e.g., area, roundness) has inherent technical limitations. Additionally, the detection effect is highly dependent on the setting of rule thresholds, which in turn relies heavily on the personal experience of the person setting them. Thresholds set by different engineers, or even the same engineer at different times, can vary, leading to fluctuations in testing standards and potentially resulting in different quality conclusions for the same batch of products. The process of translating expert experience into specific numerical rules is itself a subjective and qualitative one, difficult to quantify and transfer precisely. Ensuring objective and consistent testing standards has long been a challenging problem in this field. Furthermore, when chip packaging structures, molding materials, or ultrasonic equipment change, or when entirely new and unforeseen defect types appear in production, the existing rule set may become invalid. This necessitates experts re-analyzing images, adjusting or redesigning feature extraction algorithms and judgment rules—a cumbersome and time-consuming process. The "knowledge" in this approach is fixed and rigid, lacking the ability to learn autonomously from new samples. This makes it difficult to adapt to the rapidly iterating modern electronics manufacturing industry. Before the maturity of deep learning technology, realizing a testing system capable of adaptive evolution and free from frequent human intervention is extremely difficult. In summary, due to its "rule-based" nature, existing technologies have inherent technical bottlenecks in terms of testing accuracy, consistency, adaptability, and ease of use.

[0030] Figure 1This is a flowchart of a defect detection method for a plastic-encapsulated chip according to an embodiment of the present invention. This embodiment is applicable to the defect detection of plastic-encapsulated microelectronic chips. The method can be executed by a defect detection device for plastic-encapsulated chips, which can be implemented in hardware and / or software. This device can be configured in an electronic device that carries the defect detection function of plastic-encapsulated chips, such as a server. Figure 1 As shown, the method includes:

[0031] S110. Obtain the image of the target molded chip to be inspected.

[0032] In this embodiment, the target molded chip refers to the molded chip that needs to be defect-detected. The image to be detected refers to the original ultrasonic scan image of the target molded chip, such as an A-Scan signal or a pre-formed C-Scan image.

[0033] Specifically, the image of the target molded chip to be tested is obtained through ultrasonic scanning hardware.

[0034] S120. Enhance the image to be detected to obtain the target image to be detected.

[0035] In this embodiment, the target image to be inspected refers to the image after enhancement processing.

[0036] Specifically, the image to be inspected can be rotated, scaled, and have its sharpness enhanced to obtain the target image. This improves the accuracy of subsequent defect detection.

[0037] S130. Defect detection is performed on the image to be detected using a defect detection model to obtain the location and type of the target defect.

[0038] In this embodiment, the defect detection model refers to a neural network model used for defect detection of molded chips; optionally, the defect detection model is deployed in an ultrasonic testing system; the ultrasonic testing system is integrated with ultrasonic scanning hardware to form a closed loop. The target defect location refers to the specific location of the defect on the molded chip. The target defect type refers to the specific type of defect, such as voids, delamination, or bubbles.

[0039] Specifically, once the chip to be inspected is scanned, the system automatically invokes the model, inputting the real-time acquired ultrasonic data into it. The model completes calculations in an extremely short time (milliseconds) and outputs defect judgment results (such as "qualified," "unqualified - void defect," etc.), triggering the corresponding sorting mechanism. The defect detection model (especially with GPU acceleration) has an extremely fast inference speed, reducing the time for a single inspection from tens of seconds of manual interpretation to milliseconds. This directly achieves an exponential increase in inspection efficiency, making 100% online full inspection possible and meeting the cycle time requirements of high-speed production lines. The entire process is fully automated; operators only need to perform simple operations such as loading and starting, achieving "one-click" inspection and greatly simplifying operations. The system can work stably 24 hours a day without interruption, saving labor costs and ensuring continuous and stable monitoring of production line quality.

[0040] As an optional approach of the present invention, continuous optimization and incremental learning of the defect detection model can also be achieved. Specifically, the defect detection model can be updated online using the image to be detected, the location of the target defect, and the type of the target defect.

[0041] Specifically, when the online system detects suspected novel defects or cases with low confidence levels, the sample (such as a target image to be inspected) can be submitted to experts for review and confirmation. The confirmed new sample (such as a target image to be inspected) will be added to the original dataset for periodic incremental learning or fine-tuning of the deployed model, enabling continuous model evolution. This step endows the system with self-evolutionary capabilities, enhancing its adaptability and usefulness. When chip packaging processes change or unprecedented defect types emerge, the system does not need to be completely redeveloped; it can quickly adapt to new requirements through incremental learning. This significantly reduces the long-term maintenance costs of the system and increases its lifespan and practical value, creating a virtuous cycle where the more it is used, the "smarter" it becomes.

[0042] The technical solution of this invention involves acquiring an image of a target molded chip to be inspected; enhancing the image to obtain the target image to be inspected; and using a defect detection model to detect defects in the target image to obtain the location and type of the target defect. This technical solution replaces the manual image feature extraction and rule setting steps of traditional methods with a pre-trained network model. Operators do not need extensive experience in interpreting ultrasound images; they only need to input the acquired ultrasound scan data into the model to automatically obtain defect analysis results. This makes the inspection operation extremely simple and significantly lowers the technical threshold. Non-professionals can operate the system after simple training, effectively solving the problem of enterprises' reliance on high-end inspection experts and simplifying human resource allocation and training costs.

[0043] Figure 2This is a flowchart of a defect detection method for a molded chip according to an embodiment of the present invention. Based on the above embodiments, this embodiment further elaborates on the training process of the defect detection model and provides an optional implementation scheme. Figure 2 As shown, the method includes:

[0044] S210. Obtain the image of the target molded chip to be inspected.

[0045] S220. Enhance the image to be detected to obtain the target image to be detected.

[0046] S230. Defect detection is performed on the image to be detected using a defect detection model to obtain the location and type of the target defect.

[0047] In one alternative approach, the defect detection model is trained by: acquiring the original ultrasonic image of the sample molded chip; enhancing the original ultrasonic image to obtain the sample ultrasonic image; and training the initial neural network model using the sample ultrasonic image to obtain the defect detection model.

[0048] The sample molded chips are those in a known state, including but not limited to good products and defective products containing various definite defects such as voids, delamination, and bubbles. The raw ultrasound images refer to the original ultrasound scan data, such as A-Scan signals or pre-formed C-Scan images. These data are precisely labeled by experienced experts, with annotation information including the presence, type, and location coordinates of defects within the chip, forming a structured, high-quality training dataset.

[0049] For example, enhancing a raw ultrasound image to obtain a sample ultrasound image includes: standardizing the raw ultrasound image; and performing data enhancement on the processed raw ultrasound image to obtain the sample ultrasound image; wherein the data enhancement includes at least one of rotation, scaling, and adding noise.

[0050] Specifically, the original ultrasound images are standardized, such as by image size normalization. Then, data augmentation is performed on the processed original ultrasound images, such as rotation, scaling, and noise addition, to obtain sample ultrasound images. This increases the diversity of the data and the robustness of the model.

[0051] Then, the initial neural network model is trained using gradient descent with sample ultrasound images to obtain the defect detection model. Specifically, a training set and a validation set can be constructed based on the sample ultrasound images. The model is iteratively trained using the training set, and the internal parameters (weights and biases) of the model are continuously optimized through the backpropagation algorithm until the model's performance on the validation set reaches its optimal level.

[0052] Optionally, the initial neural network model can be a deep neural network model (such as segmentation networks like U-Net, or visual Transformer models) or multiple specialized models; these specialized models can be cascaded or connected in parallel; the specialized models can be defect binary classification models, defect localization models, or defect classification models. In the case of multiple specialized models, a simple classification model can be used first to quickly determine the presence or absence of defects. For samples with defects, a more complex detection model can then be used for precise localization and classification. This approach can improve overall efficiency in certain scenarios.

[0053] As an optional approach of this invention, the defect detection model is deployed on a cloud server; the ultrasonic scanning device only acts as a terminal to collect data, which is then uploaded to the cloud server via the network. The powerful computing resources in the cloud run the model for analysis and return the results to the terminal. This mode facilitates model updates and maintenance.

[0054] The technical solution of this invention involves acquiring an image of a target molded chip to be inspected; enhancing the image to obtain the target image to be inspected; and using a defect detection model to detect defects in the target image to obtain the location and type of the target defect. This technical solution replaces the manual image feature extraction and rule setting steps of traditional methods with a pre-trained network model. Operators do not need extensive experience in interpreting ultrasound images; they only need to input the acquired ultrasound scan data into the model to automatically obtain defect analysis results. This makes the inspection operation extremely simple and significantly lowers the technical threshold. Non-professionals can operate the system after simple training, effectively solving the problem of enterprises' reliance on high-end inspection experts and simplifying human resource allocation and training costs.

[0055] Figure 3 This is a schematic diagram of a defect detection device for a plastic-encapsulated chip according to an embodiment of the present invention. This embodiment is applicable to the defect detection of plastic-encapsulated microelectronic chips. The defect detection device for plastic-encapsulated chips can be implemented in hardware and / or software. This device can be configured in an electronic device that carries the defect detection function of plastic-encapsulated chips, such as a server. Figure 3 As shown, the device includes:

[0056] The image acquisition module 310 is used to acquire the image of the target molded chip to be inspected.

[0057] Image enhancement module 320 is used to enhance the image to be detected to obtain the target image to be detected;

[0058] The defect detection module 330 is used to perform defect detection on the target image to be inspected through the defect detection model, and to obtain the target defect location and target defect type; the defect detection model is deployed in the ultrasonic testing system.

[0059] The technical solution of this invention involves acquiring an image of a target molded chip to be inspected; enhancing the image to obtain the target image to be inspected; and using a defect detection model to detect defects in the target image to obtain the location and type of the target defect. This technical solution replaces the manual image feature extraction and rule setting steps of traditional methods with a pre-trained network model. Operators do not need extensive experience in interpreting ultrasound images; they only need to input the acquired ultrasound scan data into the model to automatically obtain defect analysis results. This makes the inspection operation extremely simple and significantly lowers the technical threshold. Non-professionals can operate the system after simple training, effectively solving the problem of enterprises' reliance on high-end inspection experts and simplifying human resource allocation and training costs.

[0060] Optionally, the device also includes a model training module for:

[0061] Obtain the raw ultrasound image of the sample's encapsulated chip;

[0062] The original ultrasound image is enhanced to obtain the sample ultrasound image;

[0063] The initial neural network model was trained using sample ultrasound images to obtain a defect detection model.

[0064] Optional, model training module, specifically used for:

[0065] Standardize the original ultrasound images;

[0066] The original processed ultrasound image is subjected to data augmentation processing to obtain a sample ultrasound image; wherein, data augmentation includes at least one of the following processing methods: rotation, scaling and adding noise.

[0067] Optionally, the ultrasonic testing system can be integrated with ultrasonic scanning hardware.

[0068] Optionally, the device also includes a model update module for:

[0069] The defect detection model is updated online using the image to be detected, the location of the target defect, and the type of the target defect.

[0070] Optionally, the initial neural network model can be a deep neural network model or multiple specialized models; wherein, the multiple specialized models are cascaded or connected in parallel; the specialized models can be a defect binary classification model, a defect localization model, or a defect classification model.

[0071] The defect detection device for molded chips provided in this embodiment of the invention can execute the defect detection method for molded chips provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0072] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0073] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the defect detection method for plastic-encapsulated chips according to embodiments of the present invention. Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0074] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0075] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as defect detection methods for molded chips.

[0077] In some embodiments, the defect detection method for molded chips can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the defect detection method for molded chips described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the defect detection method for molded chips by any other suitable means (e.g., by means of firmware).

[0078] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0084] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0085] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A defect detection method for a plastic-encapsulated chip, characterized in that, include: Acquire the image of the target molded chip to be inspected; The image to be detected is enhanced to obtain the target image to be detected; Defect detection is performed on the target image to be inspected using a defect detection model to obtain the location and type of the target defect. The defect detection model is deployed in the ultrasonic testing system.

2. The method according to claim 1, characterized in that, The defect detection model is trained in the following manner: Obtain the raw ultrasound image of the sample's encapsulated chip; The original ultrasound image is enhanced to obtain a sample ultrasound image; The initial neural network model was trained using the sample ultrasound images to obtain a defect detection model.

3. The method according to claim 2, characterized in that, The enhancement process of the original ultrasound image to obtain a sample ultrasound image includes: The original ultrasound images are standardized. The processed original ultrasound image is subjected to data augmentation processing to obtain a sample ultrasound image; wherein, the data augmentation includes at least one of the following processing methods: rotation, scaling and adding noise.

4. The method according to claim 1, characterized in that, The ultrasonic testing system is integrated with ultrasonic scanning hardware.

5. The method according to claim 1, characterized in that, Also includes: The defect detection model is updated online using the image to be detected, the location of the target defect, and the type of the target defect.

6. The method according to any one of claims 2-4, characterized in that, The initial neural network model is a deep neural network model or multiple specialized models; wherein, the multiple specialized models are cascaded or connected in parallel; the specialized models are defect binary classification models, defect localization models, or defect classification models.

7. A defect detection device for molded chips, characterized in that, include: The image acquisition module is used to acquire the image of the target molded chip to be inspected. The image enhancement module is used to enhance the image to be detected to obtain the target image to be detected; The defect detection module is used to perform defect detection on the target image to be inspected using a defect detection model, and to obtain the target defect location and target defect type. The defect detection model is deployed in the ultrasonic testing system.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the defect detection method for the plastic-encapsulated chip according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the defect detection method for the plastic-encapsulated chip according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the defect detection method for a plastic-encapsulated chip according to any one of claims 1-6.

Images