Deep learning-based stamping rib automatic identification and classification method and device, terminal and storage medium

Through the method based on deep learning, the problems of low identification and classification efficiency and high cost in the existing technology are solved, and the rapid and automated identification and classification of stamping ribs are realized, and the optimization design of automotive parts is supported. .

CN118940401APending Publication Date: 2024-11-12CHINA FAW CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410957332.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art has low efficiency and high cost to identify and classify the ripple in automotive simulation analysis, and is especially not suitable for large-capacity data processing.

Method used

Using a deep learning-based method, automatic identification and classification of stamping ribs is achieved through data preparation, label production, model selection and training, model evaluation and optimization, algorithm integration, and continuous monitoring and update. The specific steps include using simulation software to create a data set, selecting appropriate deep learning models for training and optimization, and integrating the models into simulation software for automatic identification and classification.

Benefits of technology

It realizes rapid and automated identification and classification of stamping ribs, improves work efficiency, ensures identification accuracy, and supports the optimized design of automotive parts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940401A_ABST
    Figure CN118940401A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of automobiles, and particularly relates to a stamping rib automatic identification and classification method and device based on deep learning, a terminal and a storage medium. Comprising the steps of S1, data preparation; s2, manufacturing a label; s3, model selection and training; s4, evaluating and optimizing the model; s5, algorithm integration; and S6, continuously monitoring and updating. According to the method, the stamping ribs can be automatically recognized and classified, and powerful support is provided for further achieving optimization design of automobile parts.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of automobile technology, and specifically relates to a method, device, terminal and storage medium for automatic identification and classification of stamping ribs based on deep learning. Background Art

[0002] In the automotive field, stamping ribs are a key manufacturing process that forms local protrusions or ribs on metal sheets to enhance the structural strength and rigidity of automotive parts. This process is widely used in automotive design. The types of stamping ribs include circular ribs, oval ribs, square ribs, etc. These different types of rib designs have different structural characteristics and performance advantages. Identifying the type of stamping ribs is of great significance in automotive simulation design: it not only helps to establish a more accurate simulation model and optimize parameter settings, but also improves the versatility and portability of simulation analysis, providing strong support for the optimization design and improvement of automotive parts.

[0003] At present, in the field of automobile simulation analysis, the identification and classification of stamping ribs mainly involve the following two methods:

[0004] 1) Stamping ribs can be identified based on simulation analysis software (such as ANSA, hypermesh). However, this method requires manual operation of the software to identify stamping ribs, which is inefficient; in addition, this method cannot classify stamping ribs.

[0005] 2) Relying on manpower to identify and classify stamping ribs. However, this method has a very high cost for the identification and classification of stamping ribs and is not suitable for the identification and classification of stamping ribs with large-capacity data.

[0006] Therefore, there is an urgent need to develop a method for rapid identification and classification of stamping ribs. Summary of the invention

[0007] To solve the above problems, the present invention proposes a method, device, terminal and storage medium for automatic identification and classification of stamping ribs based on deep learning, which can automatically identify and classify stamping ribs, providing strong support for further realizing the optimal design of automobile parts.

[0008] The technical solution of the present invention is described as follows in conjunction with the accompanying drawings:

[0009] In a first aspect, an embodiment of the present invention provides a method for automatic identification and classification of stamping ribs based on deep learning, comprising:

[0010] Data preparation;

[0011] Label making;

[0012] Model selection and training;

[0013] Model evaluation and optimization;

[0014] Algorithm integration;

[0015] Continuous monitoring and updating.

[0016] Furthermore, the specific method of data preparation is as follows:

[0017] Use simulation software to take screenshots of the stamping ribs in the automobile data, save them, and create a data set. Then, divide the data set into a training set and a test set in a ratio of 8:2.

[0018] Furthermore, the specific method of making the label is as follows:

[0019] Label and classify the data set according to requirements.

[0020] Furthermore, the specific method of model selection and training is as follows:

[0021] Select a suitable deep learning model and use the training set to train the model. During the training process, continuously adjust the parameters and structure of the model to achieve optimal performance.

[0022] Furthermore, the specific method of model evaluation and optimization is as follows:

[0023] Determine the importance of model prediction accuracy and reliability based on specific application scenarios and business needs;

[0024] Find a balance between prediction accuracy and model complexity;

[0025] If the model's prediction accuracy and reliability do not meet the standards, the model needs to be retrained through data quality checks, feature engineering, model selection and optimization until it meets the standards.

[0026] Furthermore, the specific method of the algorithm integration is as follows:

[0027] Integrate the trained model into the simulation software. When the simulation software loads new geometric data, use the trained model to automatically identify and classify stamping ribs, including:

[0028] a) Open the geometry data;

[0029] b) Obtain all stamping ribs and put them into the first variable;

[0030] c) Determine whether the first variable is empty; if the first variable is not empty, proceed to the next step; if the first variable is empty, end.

[0031] d) Assign the first element of the first variable to the second variable.

[0032] e) Display data processing functions separately, take screenshots and save them;

[0033] f) Use the trained model parameters to identify and classify the punching rib screenshots;

[0034] g) Delete the first element in the first variable.

[0035] Furthermore, the specific method of continuous monitoring and updating is as follows:

[0036] Update deep learning models regularly at a custom time, monitor the performance of the models in actual applications, and make necessary adjustments or optimizations based on feedback.

[0037] In a second aspect, an embodiment of the present invention further provides a device for automatic identification and classification of stamping ribs based on deep learning, comprising:

[0038] Preparation module, used for data preparation;

[0039] Production module, used for label production;

[0040] Training module, used for model selection and training;

[0041] Optimization module, used for model evaluation and optimization;

[0042] Integration module, used for algorithm integration;

[0043] Update module, used for continuous monitoring and updating.

[0044] In a third aspect, a terminal is provided, including:

[0045] one or more processors;

[0046] a memory for storing the one or more processor-executable instructions;

[0047] Wherein, the one or more processors are configured to:

[0048] Execute the method described in the first aspect of the embodiment of the present invention.

[0049] In a fourth aspect, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method described in the first aspect of an embodiment of the present invention.

[0050] In a fifth aspect, an application product is provided. When the application product is running on a terminal, the terminal executes the method described in the first aspect of the embodiment of the present invention.

[0051] The beneficial effects of the present invention are:

[0052] 1) The present invention can identify all stamping ribs.

[0053] 2) The present invention can classify stamping ribs.

[0054] 3) The present invention makes the identification and classification of stamping ribs a fully automated process, which can greatly improve work efficiency while ensuring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 It is a flow chart of a method for automatic identification and classification of stamping ribs based on deep learning according to the present invention;

[0057] Figure 2 This is a schematic diagram of the geometric data of a certain automobile body in white;

[0058] Figure 3 is a schematic diagram of the data set;

[0059] Figure 4 It is a schematic diagram of the algorithm integration and application process;

[0060] Figure 5 It is a structural schematic diagram of a device for automatic identification and classification of stamping ribs based on deep learning according to the present invention;

[0061] Figure 6 The present invention is a schematic block diagram of a terminal structure. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0064] Embodiment 1

[0065] This embodiment provides a method for automatic identification and classification of stamping ribs based on deep learning. The method can be performed by a device for automatic identification and classification of stamping ribs based on deep learning in an embodiment of the present invention. The device can be implemented in software and / or hardware, as follows:

[0066] See also Figure 1 , a deep learning-based automatic identification and classification method for stamping ribs, based on ANSA software and implemented in Python programming language, including:

[0067] S1. Data preparation, as follows:

[0068] a) Use ANSA software to open the vehicle body-in-white geometry data (body-in-white geometry data such as Figure 2 This step can be automated using the ansa.base.Open(filename) function in the ANSA software API manual, where filename is the path to the vehicle geometry data.

[0069] Take screenshots of the stamping ribs in the automobile data, save them, and create a data set (data set such as Figure 3As shown). This step can be automated by combining the related functions in the ANSA software API manual. Use the ansa.base.SetEntityCardValues() function in the ANSA software API manual to set the part color; use the ansa.base.CollectEntities() function in the ANSA software API manual to obtain all parts in the vehicle data; use the ansa.FeatureHandler.get_features_of_part() function in the ANSA software API manual to obtain all features of each part; use Python's if statement to determine whether the feature is a stamped rib (the keyword for stamped ribs in the ANSA software API manual is STAMP); use the ansa.base.Or() function in the ANSA software API manual to display stamped ribs separately; use the ansa.base.ZoomAll() function in the ANSA software API manual The function performs screen adaptive scaling on the currently displayed stamping rib; use the ansa.utils.SnapShot(filename,image_format,red,green,blue) function in the ANSA software API manual to take a screenshot and save the stamping rib, where filename is the screenshot save path, image_format is the screenshot save format, and red, green, and blue are the components of the red, green, and blue channels of the screenshot background color, respectively; use the ansa.base.GetEntityCardValues() function in the ANSA software API manual to obtain the ID of the stamping rib in the simulation software, and write this ID into the filename in the stamping rib screenshot and save functions to ensure that the stamping rib screenshot corresponds to the stamping rib geometric data in the ANSA software.

[0070] c) Divide the dataset into training set and test set in a ratio of 8:2.

[0071] S2. Label production, as follows:

[0072] In this example, stamping ribs are classified into 21 categories, and the mainstream labeling tool LabelImg is used to draw a bounding box on each screenshot of the dataset and assign a corresponding label to it. The label list is shown in Table 1.

[0073] Table 1 Label list

[0074]

[0075]

[0076] S3, model selection and training, as follows:

[0077] Select a suitable deep learning model (such as convolutional neural network CNN, recurrent neural network RNN, Transformer, generative adversarial network GAN, etc.), use the training set to train the model, and continuously adjust the parameters and structure of the model during the training process to optimize its performance. This example builds a deep learning model based on PyTorch, and uses the trained model to

[0078] The torch.save(model.state_dict(),model_path) function saves the trained model parameters, where model_path is the model parameter save path.

[0079] S4. Model evaluation and optimization, as follows:

[0080] Use the test set to predict the trained model and evaluate the model's prediction accuracy and reliability. First, determine the importance of model prediction accuracy and reliability based on specific application scenarios and business needs; in some cases, even if the model's prediction accuracy is slightly lower, if it can meet business needs, the model can be considered usable. Secondly, while pursuing prediction accuracy, the complexity of the model should also be considered; overly complex models may lead to overfitting and reduce the reliability of the model. Therefore, it is necessary to find a balance between prediction accuracy and model complexity. If the model's prediction accuracy and reliability do not meet the standards, it is necessary to retrain the model through data quality checks, feature engineering, model selection and optimization, etc. until it meets the standards; among them, solving the problem of model prediction accuracy and reliability not meeting the standards may be an iterative process that requires continuous attempts and adjustments.

[0081] S5, algorithm integration, as follows:

[0082] By writing Python scripts, the trained model is integrated into the ANSA software. When the ANSA software loads new geometric data, the trained model can be used to automatically identify and classify stamping ribs. Figure 4 The steps are detailed as follows:

[0083] a) Open the geometry data; this step can be automated using the ansa.base.Open(filename) function in the ANSA software API manual, where filename is the path to the geometry data.

[0084] b) Get all stamping ribs and put them into list_stamp. Use ansa.base.CollectEntities() in the ANSA software API manual to get all parts in the car data; use ansa.FeatureHandler.get_features_of_part() in the ANSA software API manual to get all features of each part; use Python's if statement to determine whether the feature is a stamping rib (the keyword for stamping ribs in the ANSA software API manual is STAMP), and use Python's append() method to put the stamping ribs into the variable list_stamp.

[0085] c) Determine whether list_stamp is empty. If list_stamp is not empty, proceed to the next step; if list_stamp is empty, end.

[0086] d) Assign the first element of list_stamp to cur_stamp.

[0087] e) Display cur_stamp separately, take a screenshot and save it. Use the ansa.base.Or() function in the ANSA software API manual to display the stamped rib cur_stamp separately; use the ansa.base.ZoomAll() function in the ANSA software API manual to perform screen adaptive scaling of cur_stamp; use the ansa.utils.SnapShot(filename,image_format,red,green,blue) function in the ANSA software API manual to take a screenshot and save cur_stamp, where filename is the screenshot save path, image_format is the screenshot save format, and red, green, and blue are the components of the three channels of the screenshot background color, red, green, and blue, respectively; use the ansa.base.GetEntityCardValues() function in the ANSA software API manual to obtain the ID of cur_stamp in the simulation software, and write this ID into the filename in the cur_stamp screenshot and save functions to ensure that the cur_stamp screenshot corresponds to the cur_stamp geometric data in the ANSA software.

[0088] f) Use the trained model parameters to identify and classify the stamping rib screenshots. Use PyTorch's model.load_state_dict(torch.load(model_path)) function to load the trained deep learning model, where model is the deep learning model and model_path is the deep learning model parameter path; use PyTorch's outputs=model(inputs) to identify and classify stamping ribs, where model is the deep learning model, inputs is the tensor converted from the stamping rib screenshot, and outputs is the predicted tensor; use PyTorch's predicted_labels=torch.argmax(outputs,dim=1) function to obtain the category label corresponding to the predicted tensor outputs, where the category label is an integer between 0 and 20, and the category it represents can be referred to Table 1.

[0089] g) Delete the first element of list_stamp. Use Python's list_stamp.pop(0) function to delete the first element of list_stamp.

[0090] S6. Continuous monitoring and updating, as follows:

[0091] The categories of stamping ribs can be expanded, and the deep learning model can be retrained and updated to perform refined classification of stamping ribs; the number of data sets can also be expanded, and the deep learning model can be retrained and updated to improve its recognition and classification accuracy.

[0092] In summary, the present invention uses Python programming language, based on machine learning library PyTorch, and is implemented in ANSA software, integrating deep learning models into ANSA software, breaking through the limitations of existing functions of ANSA software, and realizing automatic identification and classification of stamping ribs based on deep learning. The technical solution of the present invention can be referred to and implemented in other programming languages ​​(such as Java), other machine learning libraries (such as TensorFlow), and other simulation software (such as hypermesh).

[0093] Embodiment 2

[0094] See also Figure 5 This embodiment provides a device for automatic identification and classification of stamping ribs based on deep learning, including:

[0095] Preparation module, used for data preparation;

[0096] Production module, used for label production;

[0097] Training module, used for model selection and training;

[0098] Optimization module, used for model evaluation and optimization;

[0099] Integration module, used for algorithm integration;

[0100] Update module, used for continuous monitoring and updating.

[0101] Embodiment 3

[0102] Figure 6 1 is a block diagram of a terminal provided in an embodiment of the present application, and the terminal may be a terminal in the above embodiment. The terminal may be a portable mobile terminal, such as a smart phone or a tablet computer. The terminal may also be referred to as a user device, a portable terminal, or other names.

[0103] Typically, the terminal includes: a processor 301 and a memory 302 .

[0104] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0105] The memory 302 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement a deep learning-based automatic identification and classification method for stamping ribs provided in this application.

[0106] In some embodiments, the terminal may further include: a peripheral device interface 303 and at least one peripheral device. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304 , a touch display screen 305 , a camera 306 , an audio circuit 307 , a positioning component 308 and a power supply 309 .

[0107] The peripheral device interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the peripheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the peripheral device interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0108] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 304 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0109] The touch display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. The touch display screen 305 also has the ability to collect touch signals on the surface or above the surface of the touch display screen 305. The touch signal can be input to the processor 301 as a control signal for processing. The touch display screen 305 is used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the touch display screen 305 can be one, and the front panel of the terminal is set; in other embodiments, the touch display screen 305 can be at least two, which are respectively set on different surfaces of the terminal or are folded; in some other embodiments, the touch display screen 305 can be a flexible display screen, which is set on the curved surface or folded surface of the terminal. Even, the touch display screen 305 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The touch display screen 305 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0110] The camera assembly 306 is used to capture images or videos. Optionally, the camera assembly 306 includes a front camera and a rear camera. Typically, the front camera is used to realize video calls or selfies, and the rear camera is used to realize the shooting of photos or videos. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, and a wide-angle camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, and the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting functions. In some embodiments, the camera assembly 306 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0111] The audio circuit 307 is used to provide an audio interface between the user and the terminal. The audio circuit 307 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 301 for processing, or input them into the radio frequency circuit 304 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 301 or the radio frequency circuit 304 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 307 may also include a headphone jack.

[0112] The positioning component 308 is used to locate the current geographical location of the terminal to implement navigation or LBS (Location Based Service). The positioning component 308 can be a positioning component based on the US GPS (Global Positioning System) or China's Beidou system.

[0113] The power supply 309 is used to power various components in the terminal. The power supply 309 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 309 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0114] Those skilled in the art will understand that Figure 6 The structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0115] Embodiment 4

[0116] In an exemplary embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the program is executed by a processor, a method for automatic identification and classification of stamping ribs based on deep learning as provided in all the inventive embodiments of the present application is implemented.

[0117] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0118] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0119] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0120] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] Embodiment 5

[0122] In an exemplary embodiment, an application product is also provided, including one or more instructions, which can be executed by the processor 301 of the above-mentioned device to complete the above-mentioned deep learning-based automatic identification and classification method of stamping ribs.

[0123] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and implementation mode. It can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily realized. Therefore, without departing from the general concept defined by the claims and equivalent scope, the present invention is not limited to the specific details and the illustrations shown and described here.

Claims

1. A method for automatic identification and classification of stamping ribs based on deep learning, characterized in that: include: Data preparation; Label making; Model selection and training; Model evaluation and optimization; Algorithm integration; Continuous monitoring and updating.

2. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific method of data preparation is as follows: Use simulation software to take screenshots of the stamping ribs in the automobile data, save them, and create a data set. Then, divide the data set into a training set and a test set in a ratio of 8:

2.

3. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific method of making the label is as follows: Label and classify the data set according to requirements.

4. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific method of model selection and training is as follows: Select a suitable deep learning model and use the training set to train the model. During the training process, continuously adjust the parameters and structure of the model to achieve optimal performance.

5. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific methods of model evaluation and optimization are as follows: Determine the importance of model prediction accuracy and reliability based on specific application scenarios and business needs; Find a balance between prediction accuracy and model complexity; If the model's prediction accuracy and reliability do not meet the standards, the model needs to be retrained through data quality checks, feature engineering, model selection and optimization until it meets the standards.

6. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific method of algorithm integration is as follows: Integrate the trained model into the simulation software. When the simulation software loads new geometric data, use the trained model to automatically identify and classify stamping ribs, including: a) Open the geometry data; b) Obtain all stamping ribs and put them into the first variable; c) Determine whether the first variable is empty; if the first variable is not empty, proceed to the next step; if the first variable is empty, end. d) Assign the first element of the first variable to the second variable. e) Display data processing functions separately, take screenshots and save them; f) Use the trained model parameters to identify and classify the punching rib screenshots; g) Delete the first element in the first variable.

7. The method for automatic identification and classification of stamping ribs based on deep learning according to claim 1 is characterized in that: The specific method of continuous monitoring and updating is as follows: Update deep learning models regularly at a custom time, monitor the performance of the models in actual applications, and make necessary adjustments or optimizations based on feedback.

8. A device for automatic identification and classification of stamping ribs based on deep learning, characterized in that: include: Preparation module, used for data preparation; Production module, used for label production; Training module, used for model selection and training; Optimization module, used for model evaluation and optimization; Integration module, used for algorithm integration; Update module, used for continuous monitoring and updating.

9. A terminal, characterized in that: include: one or more processors; a memory for storing the one or more processor-executable instructions; Wherein, the one or more processors are configured to: Execute a method for automatic identification and classification of stamping ribs based on deep learning as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute the method for automatic identification and classification of stamping ribs based on deep learning as described in any one of claims 1 to 7.