Vehicle corrosion resistance performance evaluation method, device and equipment based on deep learning

Abstract

The application discloses a whole vehicle corrosion resistance performance evaluation method, device and equipment based on deep learning, comprising: obtaining three-dimensional structure data, vehicle body image data, material electrochemical characteristic data and environmental load data of a target vehicle; inputting the three-dimensional structure data, vehicle body image data, material electrochemical characteristic data and environmental load data into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risks of each region of the target vehicle; and determining the whole vehicle corrosion resistance score of the target vehicle according to the predicted corrosion risks. The application improves the accuracy and comprehensiveness of the whole vehicle corrosion resistance performance evaluation and can be applied to the field of artificial intelligence technology.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus and equipment for evaluating the corrosion resistance performance of a vehicle based on deep learning. Background Technology

[0002] The corrosion resistance of a vehicle involves a combination of factors across multiple dimensions, including materials, structure, coating, and environment. Traditional methods cannot achieve unified modeling and in-depth analysis of multi-source data, resulting in insufficient assessment accuracy. Existing technologies rely on manual experience and offline testing, making it impossible to identify high-risk corrosion areas in advance during the design phase. This leads to high remediation costs and long development cycles, hindering the automatic classification, quantitative assessment, and lifespan prediction of corrosion defects across the entire vehicle and its entire lifecycle, and thus failing to support precise control over vehicle reliability. Furthermore, the early identification of hidden defects such as crevice corrosion and galvanic corrosion is challenging, and traditional methods are prone to missing these defects, posing a risk of corrosion failure after the vehicle enters service. Summary of the Invention

[0003] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0004] Therefore, one objective of this invention is to provide a deep learning-based method for evaluating the corrosion resistance of a vehicle. This method predicts the corrosion risk of various regions of the vehicle based on its three-dimensional structural data, body image data, material electrochemical property data, and environmental load data. Based on the predicted corrosion risk, the method determines the vehicle's overall corrosion resistance score, thereby improving the accuracy and comprehensiveness of the vehicle's corrosion resistance evaluation.

[0005] Another objective of this invention is to provide a vehicle corrosion resistance evaluation device based on deep learning.

[0006] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for evaluating the corrosion resistance performance of a vehicle based on deep learning, comprising the following steps: Acquire the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data; The three-dimensional structural data, the vehicle body image data, the material electrochemical property data, and the environmental load data are input into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. The overall corrosion resistance score of the target vehicle is determined based on the predicted corrosion risk.

[0007] Furthermore, in one embodiment of the present invention, the acquisition of the target vehicle's three-dimensional structural data, vehicle body image data, material electrochemical property data, and environmental load data specifically includes: The target vehicle is subjected to a three-dimensional laser scan to obtain the three-dimensional structural data. Images of various parts of the target vehicle are acquired using a camera device to obtain vehicle body image data; The polarization curves and galvanic couple sequences of various parts of the target vehicle body are determined to obtain the electrochemical property data of the material; The environmental load data is obtained by determining the meteorological and road environment data of the target vehicle's operating environment.

[0008] Furthermore, in one embodiment of the present invention, the corrosion risk prediction model is trained through the following steps: The three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle were obtained, and the corrosion risk labels of each area of ​​the sample vehicle were determined by manual annotation. The three-dimensional structure sample, the vehicle body image sample, the material electrochemical property sample, and the environmental load sample are input into a pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction value of each region of the sample vehicle. The loss value is determined based on the predicted corrosion risk value and the corrosion risk label; The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to obtain the trained corrosion risk prediction model.

[0009] Further, in one embodiment of the present invention, the CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. The step of inputting the three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples into the pre-constructed CNN-LSTM hybrid neural network to obtain corrosion risk prediction values ​​for various regions of the sample vehicle specifically includes: The three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples are respectively input into the 3D CNN branch, the 2D CNN branch, the LSTM branch, and the CNN branch for feature extraction to obtain three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. The feature fusion layer performs feature fusion on the three-dimensional structural features, the vehicle body image features, the material electrochemical features, and the environmental load features to obtain a fused feature vector; The fully connected layer maps the fused feature vector to the corrosion risk prediction values ​​for each region of the sample vehicle.

[0010] Furthermore, in one embodiment of the present invention, determining the overall corrosion resistance score of the target vehicle based on the predicted corrosion risk specifically includes: The regional weight of each region is determined based on the vehicle type of the target vehicle. The predicted corrosion risk of each region is weighted and summed according to the region weight to obtain the overall vehicle corrosion risk. The vehicle corrosion resistance score is determined based on the overall vehicle corrosion risk.

[0011] On the other hand, embodiments of the present invention provide a vehicle corrosion resistance evaluation device based on deep learning, comprising: The data acquisition module is used to acquire the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data; The corrosion risk prediction module is used to input the three-dimensional structural data, the vehicle body image data, the material electrochemical property data, and the environmental load data into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. The corrosion resistance rating module is used to determine the overall corrosion resistance rating of the target vehicle based on the predicted corrosion risk.

[0012] Furthermore, in one embodiment of the present invention, the corrosion risk prediction model is trained through the following steps: The three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle were obtained, and the corrosion risk labels of each area of ​​the sample vehicle were determined by manual annotation. The three-dimensional structure sample, the vehicle body image sample, the material electrochemical property sample, and the environmental load sample are input into a pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction value of each region of the sample vehicle. The loss value is determined based on the predicted corrosion risk value and the corrosion risk label; The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to obtain the trained corrosion risk prediction model.

[0013] Further, in one embodiment of the present invention, the CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. The step of inputting the three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples into the pre-constructed CNN-LSTM hybrid neural network to obtain corrosion risk prediction values ​​for various regions of the sample vehicle specifically includes: The three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples are respectively input into the 3D CNN branch, the 2D CNN branch, the LSTM branch, and the CNN branch for feature extraction to obtain three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. The feature fusion layer performs feature fusion on the three-dimensional structural features, the vehicle body image features, the material electrochemical features, and the environmental load features to obtain a fused feature vector; The fully connected layer maps the fused feature vector to the corrosion risk prediction values ​​for each region of the sample vehicle.

[0014] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described deep learning-based method for evaluating the corrosion resistance of a vehicle.

[0015] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the aforementioned deep learning-based method for evaluating the corrosion resistance of a vehicle.

[0016] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the aforementioned deep learning-based method for evaluating the corrosion resistance of a vehicle.

[0017] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention acquires three-dimensional structural data, vehicle body image data, material electrochemical property data, and environmental load data of a target vehicle. These data are then input into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk for each region of the target vehicle. Based on the predicted corrosion risk, the overall vehicle corrosion resistance score is determined. This invention improves the accuracy and comprehensiveness of overall vehicle corrosion resistance performance evaluation by predicting the corrosion risk of each region of the vehicle based on its three-dimensional structural data, vehicle body image data, material electrochemical property data, and environmental load data. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating the steps of a deep learning-based method for evaluating the corrosion resistance of a vehicle, as provided in an embodiment of the present invention. Figure 2 A structural block diagram of a vehicle corrosion resistance evaluation device based on deep learning provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0022] The deep learning-based vehicle corrosion resistance evaluation method provided in this invention can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the deep learning-based vehicle corrosion resistance evaluation method, but is not limited to the above forms.

[0023] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0024] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user parking space location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0025] Reference Figure 1 This invention provides a method for evaluating the corrosion resistance of a vehicle based on deep learning, specifically including the following steps: S101. Acquire the target vehicle's three-dimensional structural data, vehicle body image data, material electrochemical property data, and environmental load data; S102. Input the three-dimensional structural data, vehicle body image data, material electrochemical property data and environmental load data into the pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. S103. Determine the overall corrosion resistance score of the target vehicle based on the predicted corrosion risk.

[0026] The embodiments of the present invention predict the corrosion risk of each region of a vehicle based on its three-dimensional structural data, body image data, material electrochemical property data, and environmental load data. Based on the predicted corrosion risk, the corrosion resistance score of the whole vehicle is determined, thereby improving the accuracy and comprehensiveness of the overall vehicle corrosion resistance performance assessment.

[0027] As a further optional implementation, the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data are acquired, specifically including: S1011. Perform a three-dimensional laser scan on the target vehicle to obtain three-dimensional structural data; S1012. Obtain images of various parts of the target vehicle body through a camera device to obtain vehicle body image data; S1013. Determine the polarization curves and galvanic couple sequences of various parts of the target vehicle body to obtain material electrochemical property data. S1014. Determine the meteorological and road environment data of the target vehicle's operating environment to obtain environmental load data.

[0028] Specifically, the three-dimensional structural data of the whole vehicle (body / chassis / welds / gaps, etc.), the electrochemical properties of materials (polarization curves, galvanic couples, coating performance), environmental load data (salt spray, temperature and humidity, pH, road spectrum) and vehicle image data are integrated as inputs for subsequent models.

[0029] For acquiring 3D structural data, an industrial-grade 3D laser scanner (such as the FARO Focus series) or a high-precision photogrammetry system is used to perform a full-angle scan of the vehicle. The scan must cover all structural areas, including the exterior surface of the vehicle body, chassis, frame, and interior frame, ensuring that easily corroded details such as welds, rivets, and dents are captured. The obtained point cloud data is then imported into software such as Geomagic Design X for denoising, stitching, and surface reconstruction to generate a 3D CAD model containing precise dimensional parameters, while also marking the connection methods and stress concentration areas of different structures.

[0030] For acquiring vehicle body image data, a high-resolution industrial camera, paired with a ring light, was used to photograph various parts of the vehicle under uniform lighting conditions. The shooting angles needed to cover the front, sides, back, bottom, and gaps and corners of each component, with an overlap of at least 30% between any two adjacent shooting positions to ensure complete image stitching. For areas showing slight rust, paint peeling, or coating cracking, a macro lens was used to capture close-up shots, recording the texture, area, and location information of the initial corrosion state.

[0031] To acquire data on the electrochemical properties of the materials, samples were extracted from different parts of the vehicle (such as body panels, chassis steel beams, aluminum alloy wheels, and plastic trim parts) and tested using an electrochemical workstation. Tests included open-circuit potential, polarization curves, and AC impedance spectroscopy to obtain core parameters such as self-corrosion potential, corrosion current density, and polarization resistance, reflecting the material's corrosion resistance under different environments. Some samples were placed in salt spray and damp heat chambers to simulate different climatic environments, and changes in their electrochemical properties were periodically tested to obtain data on the change in material corrosion rate over time.

[0032] To acquire environmental load data, environmental sensors, including temperature and humidity sensors, salinity sensors, and pH sensors, are installed on the target vehicle to monitor the climate parameters of the vehicle's operating environment over a long period. Simultaneously, stress and strain sensors are installed to record load changes at different locations during vehicle operation. Combined with meteorological data (such as annual precipitation, number of salt fog days, and temperature range) and road environment data (such as road salinity and road surface smoothness) from the vehicle's operating area, a complete environmental load dataset is constructed to clarify the intensity of corrosion induction factors in different regions.

[0033] As an optional implementation, the corrosion risk prediction model is trained through the following steps: S201. Obtain the three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle, and determine the corrosion risk labels of each area of ​​the sample vehicle through manual annotation. S202. Input the three-dimensional structure samples, vehicle body image samples, material electrochemical property samples, and environmental load samples into a pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction values ​​for each region of the sample vehicle. S203. Determine the loss value based on the predicted corrosion risk value and the corrosion risk label; S204. Update the parameters of the CNN-LSTM hybrid neural network based on the loss value to obtain the trained corrosion risk prediction model.

[0034] Specifically, the process involves acquiring 3D structural samples, vehicle body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle, and manually labeling each region of the sample vehicle to determine corrosion risk tags. These samples are then input into a pre-built CNN-LSTM hybrid neural network to obtain predicted corrosion risk values ​​for each region of the sample vehicle. A loss value is determined based on the predicted corrosion risk value and the corrosion risk tag. The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to complete one iteration of training. Training stops when the number of iterations reaches a preset threshold or the loss value falls below the preset threshold, resulting in a well-trained corrosion risk prediction model.

[0035] As a further optional implementation, the CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. Three-dimensional structural samples, vehicle body image samples, material electrochemical property samples, and environmental load samples are input into the pre-constructed CNN-LSTM hybrid neural network to obtain corrosion risk prediction values ​​for various regions of the sample vehicle. Specifically, this includes: S2021. Input the three-dimensional structure samples, vehicle body image samples, material electrochemical property samples, and environmental load samples into the 3D CNN branch, 2D CNN branch, LSTM branch, and CNN branch respectively for feature extraction to obtain three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. S2022. The feature fusion layer is used to fuse the three-dimensional structural features, vehicle body image features, material electrochemical features and environmental load features to obtain a fused feature vector. S2023. The fused feature vector is mapped to the corrosion risk prediction value of each area of ​​the sample vehicle through a fully connected layer.

[0036] Specifically, the CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. Specifically: the 3D CNN branch extracts the three-dimensional structural features of the entire vehicle, accurately identifying high-risk areas such as gaps, overlaps, and dissimilar metal connections; the 2D CNN branch extracts corrosion morphology image features, automatically classifying defect types such as uniform corrosion, galvanic corrosion, crevice corrosion, and pitting corrosion, and quantifying the degree of rust; the CNN branch extracts environmental load features; the LSTM temporal branch learns the temporal laws of corrosion evolution, fits long-term aging trends, and achieves corrosion protection life prediction; the feature fusion layer fuses the three-dimensional structural features, vehicle body image features, material electrochemical features, and environmental load features to obtain a fused feature vector; and the fully connected layer maps the fused feature vector to the corrosion risk prediction values ​​for various areas of the sample vehicle, finely dividing areas such as the body, chassis, engine compartment, sill, welds, and bolt connections, and outputting a corrosion risk heatmap and defect level for each area.

[0037] As a further optional implementation, the overall corrosion resistance score of the target vehicle is determined based on the predicted corrosion risk, specifically including: S1031. Determine the regional weight of each region based on the vehicle type of the target vehicle; S1032. The predicted corrosion risk of each region is weighted and summed according to the region weight to obtain the overall vehicle corrosion risk; S1033. Determine the vehicle corrosion resistance score based on the overall vehicle corrosion risk.

[0038] Specifically, weights are assigned to different areas of the vehicle based on their importance, maintenance costs, and the severity of corrosion consequences. For example, the weight of load-bearing structures such as the frame and chassis is set at 0.3, the weight of the exterior surface of the vehicle body is set at 0.2, the weight of the interior structure is set at 0.1, and the remaining weights for other components are allocated according to their actual impact.

[0039] In some optional embodiments, the weights are adjusted according to the vehicle's usage scenario (such as commercial vehicle, private vehicle, off-road vehicle). The weight of the chassis of commercial vehicles can be appropriately increased, and the weight of the body exterior surface of private vehicles can be appropriately increased.

[0040] The predicted corrosion risks of each region are weighted and summed according to the region weights to obtain the overall vehicle corrosion risk. The overall vehicle corrosion resistance score is determined based on the overall vehicle corrosion risk. The higher the overall vehicle corrosion risk, the lower the overall vehicle corrosion resistance score.

[0041] The system outputs the final corrosion resistance score for the entire vehicle and generates a visual report that marks the location of high-risk areas, the causes of corrosion, and recommended protective measures, providing data support for vehicle maintenance and improvement.

[0042] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention predict the corrosion risk of various regions of a vehicle based on its three-dimensional structural data, body image data, material electrochemical property data, and environmental load data, and determine the overall vehicle corrosion resistance score based on the predicted corrosion risk, thereby improving the accuracy and comprehensiveness of the overall vehicle corrosion resistance performance assessment.

[0043] Reference Figure 2 This invention provides a deep learning-based vehicle corrosion resistance evaluation device, comprising: The data acquisition module is used to acquire the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data; The corrosion risk prediction module is used to input three-dimensional structural data, vehicle body image data, material electrochemical property data, and environmental load data into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. The corrosion resistance rating module is used to determine the overall corrosion resistance rating of a target vehicle based on the predicted corrosion risk.

[0044] As an optional implementation, the corrosion risk prediction model is trained through the following steps: We obtained three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicles, and determined the corrosion risk labels of each area of ​​the sample vehicles through manual annotation. The three-dimensional structure samples, vehicle body image samples, material electrochemical property samples, and environmental load samples are input into a pre-built CNN-LSTM hybrid neural network to obtain the corrosion risk prediction values ​​for each region of the sample vehicle. The loss value is determined based on the predicted corrosion risk value and the corrosion risk label; The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to obtain a trained corrosion risk prediction model.

[0045] As a further optional implementation, the CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. Three-dimensional structural samples, vehicle body image samples, material electrochemical property samples, and environmental load samples are input into the pre-constructed CNN-LSTM hybrid neural network to obtain corrosion risk prediction values ​​for various regions of the sample vehicle. Specifically, this includes: The three-dimensional structure samples, vehicle body image samples, material electrochemical property samples, and environmental load samples are respectively input into the 3D CNN branch, 2D CNN branch, LSTM branch, and CNN branch for feature extraction, resulting in three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. The feature fusion layer fuses 3D structural features, vehicle body image features, material electrochemical features, and environmental load features to obtain a fused feature vector. The fused feature vectors are mapped to corrosion risk predictions for various regions of the sample vehicle through a fully connected layer.

[0046] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0047] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned deep learning-based method for evaluating the corrosion resistance performance of a vehicle.

[0048] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0049] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the aforementioned deep learning-based method for evaluating the corrosion resistance of a vehicle.

[0050] This invention provides a computer-readable storage medium that can execute a deep learning-based method for evaluating the corrosion resistance of a vehicle, as provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and possesses the corresponding functions and beneficial effects of the method.

[0051] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned deep learning-based method for evaluating the corrosion resistance of a vehicle.

[0052] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0053] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0055] The terms "first," "second," "third," "fourth," etc. (if present) in the specification 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 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 a 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.

[0056] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0057] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0058] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several 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 methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0060] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0061] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0062] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0063] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0064] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for evaluating the corrosion resistance performance of a vehicle based on deep learning, characterized in that, Includes the following steps: Acquire the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data; The three-dimensional structural data, the vehicle body image data, the material electrochemical property data, and the environmental load data are input into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. The overall corrosion resistance score of the target vehicle is determined based on the predicted corrosion risk.

2. The method for evaluating the corrosion resistance of a vehicle based on deep learning according to claim 1, characterized in that, The acquisition of the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data specifically includes: The target vehicle is subjected to a three-dimensional laser scan to obtain the three-dimensional structural data. Images of various parts of the target vehicle are acquired using a camera device to obtain vehicle body image data; The polarization curves and galvanic couple sequences of various parts of the target vehicle body are determined to obtain the electrochemical property data of the material; The environmental load data is obtained by determining the meteorological and road environment data of the target vehicle's operating environment.

3. The method for evaluating the corrosion resistance of a vehicle based on deep learning according to claim 1, characterized in that, The corrosion risk prediction model is trained through the following steps: The three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle were obtained, and the corrosion risk labels of each area of ​​the sample vehicle were determined by manual annotation. The three-dimensional structure sample, the vehicle body image sample, the material electrochemical property sample, and the environmental load sample are input into a pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction value of each region of the sample vehicle. The loss value is determined based on the predicted corrosion risk value and the corrosion risk label; The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to obtain the trained corrosion risk prediction model.

4. The method for evaluating the corrosion resistance of a vehicle based on deep learning according to claim 1, characterized in that, The CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. The process involves inputting the three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples into the pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction values ​​for each region of the sample vehicle. Specifically, this includes: The three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples are respectively input into the 3D CNN branch, the 2D CNN branch, the LSTM branch, and the CNN branch for feature extraction to obtain three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. The feature fusion layer performs feature fusion on the three-dimensional structural features, the vehicle body image features, the material electrochemical features, and the environmental load features to obtain a fused feature vector; The fully connected layer maps the fused feature vector to the corrosion risk prediction values ​​for each region of the sample vehicle.

5. The method for evaluating the corrosion resistance of a vehicle based on deep learning according to claim 1, characterized in that, The determination of the overall corrosion resistance score of the target vehicle based on the predicted corrosion risk specifically includes: The regional weight of each region is determined based on the vehicle type of the target vehicle. The predicted corrosion risk of each region is weighted and summed according to the region weight to obtain the overall vehicle corrosion risk. The vehicle corrosion resistance score is determined based on the overall vehicle corrosion risk.

6. A deep learning-based vehicle corrosion resistance evaluation device, characterized in that, include: The data acquisition module is used to acquire the target vehicle's three-dimensional structural data, body image data, material electrochemical property data, and environmental load data; The corrosion risk prediction module is used to input the three-dimensional structural data, the vehicle body image data, the material electrochemical property data, and the environmental load data into a pre-trained corrosion risk prediction model to obtain the predicted corrosion risk of each area of ​​the target vehicle. The corrosion resistance rating module is used to determine the overall corrosion resistance rating of the target vehicle based on the predicted corrosion risk.

7. The vehicle corrosion resistance evaluation device based on deep learning according to claim 6, characterized in that, The corrosion risk prediction model is trained through the following steps: The three-dimensional structural samples, body image samples, material electrochemical property samples, and environmental load samples of the sample vehicle were obtained, and the corrosion risk labels of each area of ​​the sample vehicle were determined by manual annotation. The three-dimensional structure sample, the vehicle body image sample, the material electrochemical property sample, and the environmental load sample are input into a pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction value of each region of the sample vehicle. The loss value is determined based on the predicted corrosion risk value and the corrosion risk label; The parameters of the CNN-LSTM hybrid neural network are updated based on the loss value to obtain the trained corrosion risk prediction model.

8. The vehicle corrosion resistance evaluation device based on deep learning according to claim 7, characterized in that, The CNN-LSTM hybrid neural network includes a 3D CNN branch, a 2D CNN branch, a CNN branch, an LSTM branch, a feature fusion layer, and a fully connected layer. The process involves inputting the three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples into the pre-constructed CNN-LSTM hybrid neural network to obtain the corrosion risk prediction values ​​for each region of the sample vehicle. Specifically, this includes: The three-dimensional structure samples, the vehicle body image samples, the material electrochemical property samples, and the environmental load samples are respectively input into the 3D CNN branch, the 2D CNN branch, the LSTM branch, and the CNN branch for feature extraction to obtain three-dimensional structure features, vehicle body image features, material electrochemical features, and environmental load features. The feature fusion layer performs feature fusion on the three-dimensional structural features, the vehicle body image features, the material electrochemical features, and the environmental load features to obtain a fused feature vector; The fully connected layer maps the fused feature vector to the corrosion risk prediction values ​​for each region of the sample vehicle.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a deep learning-based method for evaluating the corrosion resistance of a vehicle as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a deep learning-based method for evaluating the corrosion resistance of a vehicle as described in any one of claims 1 to 5.

Images