Protection safety test method and device for automobile decorating part

Abstract

The invention discloses a protection safety test method and device for an automobile decorating part, and relates to the technical field of data processing, and the method comprises the steps: collecting the image information of the automobile decorating part; identifying the image information to obtain automobile structure environment features and decorative part image identification features; performing correlation analysis by taking the protection safety as a target to obtain a protection safety test target; constructing a digital twinborn simulation space; performing a simulation test to obtain a multi-scene test data set; performing safety protection risk identification to obtain risk test values of all scenes; and obtaining a protection safety test result. The technical problem that the accuracy and the reliability of the protection safety test are poor due to the fact that various complex environment conditions in use are difficult to accurately simulate in the existing automobile decoration test is solved. The technical effect of improving the accuracy and reliability of the protection safety test of the automobile decorative part is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to data processing, and in particular to a protective safety testing method and device for automobile decorative parts. Background Art

[0002] In today's automobile market, consumers' requirements for vehicles are not limited to basic driving functions, but they pay more attention to the appearance, interior and personalized customization services of the vehicle. With the rapid development of the automobile industry, automobile decoration parts, as an important element to enhance the beauty, comfort and personalization of vehicles, continue to grow in market demand. Automobile decoration parts, such as body stickers, wheel covers, seat covers, steering wheel covers, etc., have become the first choice for car owners to show their personality and improve the grade of their vehicles due to their diversity and easy replacement. However, while these decoration parts enhance the appearance and user experience of the car, they also face various potential safety risks. It is particularly important to conduct strict protection safety tests on automobile decoration parts. However, the protection safety tests of traditional automobile decoration parts cannot fully reflect the safety performance of automobile decoration parts in actual use, and the test environment is difficult to fully simulate the complex and changeable environmental conditions faced by automobile decoration parts in actual use, such as high temperature, strong wind, heavy fog, etc., resulting in deviations between the safety test results and the actual situation, affecting the overall quality and safety of automobile decoration parts.

[0003] Therefore, in the current technologies related to protective safety testing of automotive decorative parts, it is difficult to accurately simulate the various complex environmental conditions encountered during use, which causes deviations between the safety test results and the actual situation, leading to technical problems such as poor accuracy and reliability of protective safety testing. Summary of the invention

[0004] The present application provides a protective safety testing method and device for automobile decorative parts, and adopts technical means such as image recognition and construction of digital twin simulation space to solve the technical problem that it is difficult to accurately simulate the various complex environmental conditions encountered in the existing automobile decorative parts testing, which causes the safety test results to deviate from the actual situation, thereby leading to poor accuracy and reliability of the protective safety test, thereby achieving the technical effect of improving the accuracy and reliability of the protective safety test of automobile decorative parts.

[0005] The present application provides a protection safety test method for automobile decorative parts, the method comprising: collecting image information of automobile decorative parts, the image information comprising automobile setting environment information and automobile decorative parts information; identifying the image information to obtain automobile structural environment characteristics and decorative parts image recognition characteristics, and marking the positional relationship between the decorative parts image recognition characteristics and the automobile structural environment characteristics; taking protection safety as the goal, performing correlation analysis on the decorative parts image recognition characteristics and the positional relationship between the decorative parts image recognition characteristics and the automobile structural environment characteristics to obtain a protection safety test target; constructing a digital twin simulation space, the digital twin simulation space comprising a built-in scene simulation module and a test condition simulation module; connecting the digital twin simulation space according to the protection safety test target for simulation testing, switching scenes and test conditions through the built-in scene simulation module and the test condition simulation module to obtain a multi-scenario test data set; performing safety protection risk identification according to the multi-scenario test data set to obtain a risk test value for each scene; and comprehensively calculating all scene risk test values ​​to obtain a protection safety test result.

[0006] In a possible implementation, the image information is identified to obtain the structural environment characteristics of the automobile and the image recognition characteristics of the decorative parts, and the following processing is also performed: the image information is preprocessed, including denoising and contrast enhancement, and the image information includes a full-angle acquisition image of the decorative parts; the preprocessed image information is segmented into background and foreground using a convolution model, and feature recognition is performed on the segmentation result, including identifying the structural environment characteristics of the automobile in the background, and identifying the shape, texture, edge, and color of the decorative parts in the foreground, to obtain the image recognition characteristics of the decorative parts, and the image recognition characteristics of the decorative parts have an acquisition angle identifier, wherein the convolution model is a convolutional neural network model with background segmentation and image feature recognition functions obtained by training and convergence of historical sample data; the physical structure information of the automobile is obtained, three-dimensional coordinates are constructed, and the coordinate position of the image recognition characteristics of the decorative parts is determined based on the structural environment characteristics of the automobile, and the decorative parts and their image recognition characteristics of the decorative parts are spliced ​​according to the acquisition angle identifier to restore the structural characteristics of the decorative parts, and are fitted into the three-dimensional coordinates, and the positional relationship between the image recognition characteristics of the decorative parts and the structural environment characteristics of the automobile is determined and identified.

[0007] In a possible implementation, the digital twin simulation space is constructed and the following processing is performed: based on the three-dimensional coordinates, the digital twin simulation space is constructed to simulate the physical structure information, decorative parts and decorative parts image recognition features of the automobile; according to the automobile operation scenario and operation environment condition parameters, the scene parameters and test condition parameters are respectively configured to construct the scene simulation module and the test condition simulation module; the scene simulation module and the test condition simulation module are fitted into the digital twin simulation space.

[0008] In a possible implementation, the protective safety is taken as the goal, and a correlation analysis is performed on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the automobile structural environment features. Before obtaining the protective safety test target, the following processing is performed: protective safety accident cases of automobile decorative parts are collected; top-level events are determined based on the accident types of the protective safety accident cases; the top-level events are used as the starting point of the accident tree, and the top-level events are decomposed according to the protective safety accident cases to determine intermediate events, which are the direct causes of the top-level events; based on the intermediate events, the decomposition is continued until the basic events are decomposed to obtain accident factors, which are the minimum accident impact parameters; risk probability assessments are performed on accident factors and intermediate events according to the protective safety accident cases to determine the risk function relationship; based on the risk function relationship, the minimum cut set is identified, and the minimum cut set is a combination of a group of accident factors. When the minimum cut set occurs, it will cause the occurrence of the top event. The minimum cut set and its risk function relationship are used as output to obtain a reverse parsing accident tree.

[0009] In a possible implementation, with protection safety as the goal, a correlation analysis is performed on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features to obtain a protection safety test target, and the following processing is also performed: the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features are identified through the reverse parsing accident tree to determine the accident factors in the decorative part image recognition features and their positional relationship; the decorative part image recognition features corresponding to the accident factors and their positional relationship with the vehicle structural environment features are used as the protection safety test targets.

[0010] In a possible implementation, the scenes and test conditions are switched through the built-in scene simulation module and the test condition simulation module to obtain a multi-scenario test data set, and the following processing is also performed: the simulation parameters are switched through the built-in scene simulation module and the test condition simulation module, including the scene parameters and the test condition parameters, wherein the scene parameters include driving, parking, braking, turning, and bumping, and the test condition parameters include temperature, altitude, humidity, and chemical resistance; based on different combinations of the scene parameters and test condition parameters, multiple scenes are constructed, and the simulation dynamic data of each scene is obtained respectively to obtain the multi-scenario test data set.

[0011] In a possible implementation, security protection risk identification is performed based on the multi-scenario test data set to obtain risk test values ​​for each scenario, and the following processing is also performed: when there is a security anomaly in the multi-scenario test data set, the scenario risk test value is obtained based on the risk level of the security anomaly; when the security anomaly does not exist in the multi-scenario test data set, a time series change analysis is performed based on the multi-scenario test data set, and a change prediction is performed based on the correspondence between the scenario parameters, test condition parameters and the time series change; the scenario risk test value is obtained based on the change prediction result and the corresponding predicted risk level of the security anomaly.

[0012] The present application also provides a protective safety testing device for automotive decorative parts, comprising:

[0013] An image information acquisition module, the image information acquisition module is used to acquire image information of automobile decoration parts, the image information includes automobile setting environment information and automobile decoration part information;

[0014] An image information recognition module, the image information recognition module is used to recognize the image information, obtain the vehicle structure environment characteristics, the decorative parts image recognition characteristics, and identify the positional relationship between the decorative parts image recognition characteristics and the vehicle structure environment characteristics;

[0015] A protection safety test target acquisition module, wherein the protection safety test target acquisition module takes protection safety as a target, performs a correlation analysis on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features, and obtains a protection safety test target;

[0016] A digital twin simulation space construction module, wherein the digital twin simulation space construction module is used to construct a digital twin simulation space, wherein the digital twin simulation space includes a built-in scene simulation module and a test condition simulation module;

[0017] A simulation test module, wherein the simulation test module is used to connect the digital twin simulation space to perform simulation testing according to the protection safety test target, switch scenes and test conditions through the built-in scene simulation module and the test condition simulation module, and obtain a multi-scene test data set;

[0018] A risk test value acquisition module, the risk test value acquisition module is used to identify security protection risks according to the multi-scenario test data set and obtain a risk test value for each scenario;

[0019] The protection safety test result acquisition module is used to comprehensively calculate all scenario risk test values ​​to obtain the protection safety test results.

[0020] Through the protection safety test method and device for automobile decorative parts proposed in this application, it is planned to collect image information of automobile decorative parts; identify the image information to obtain the structural environmental characteristics of the automobile and the image recognition characteristics of the decorative parts; conduct correlation analysis with protection safety as the goal to obtain the protection safety test target; build a digital twin simulation space; conduct simulation tests to obtain a multi-scenario test data set; conduct safety protection risk identification to obtain the risk test value of each scenario; and obtain the protection safety test results. This solves the technical problem that it is difficult to accurately simulate the various complex environmental conditions faced in the use of existing automobile decorative parts tests, which makes the safety test results deviate from the actual situation, and then leads to poor accuracy and reliability of the protection safety test, and achieves the technical effect of improving the accuracy and reliability of the protection safety test of automobile decorative parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0022] Figure 1 A schematic flow chart of a protective safety testing method for automotive decorative parts provided in an embodiment of the present application;

[0023] Figure 2 A schematic structural diagram of a protective safety testing device for automotive decorative parts provided in an embodiment of the present application.

[0024] Explanation of the accompanying drawings: image information acquisition module 10, image information recognition module 20, protection and safety test target acquisition module 30, digital twin simulation space construction module 40, simulation test module 50, risk test value acquisition module 60, protection and safety test result acquisition module 70. DETAILED DESCRIPTION

[0025] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0026] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0027] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0028] The present application embodiment provides a protective safety test method for automotive decorative parts, such as Figure 1 As shown, the method includes:

[0029] Step S100, collecting image information of automobile decorations, the image information including automobile setting environment information and automobile decoration information. Use a high-definition camera to collect image information of automobile decorations, the image information of automobile decorations includes automobile setting environment information and automobile decoration information. Specifically, the automobile setting environment information may include background information of the automobile (such as indoor parking lots, outdoor roads, garages, etc.), lighting conditions (such as light intensity, direction, uniformity, etc. in the image), surrounding objects (such as other vehicles, buildings, trees, etc. around the car), shooting angle and distance (angle and distance between the camera and the car, different angles and distances will affect the size and clarity of the decoration in the image), other environmental factors, such as weather conditions (sunny, rainy, snowy, etc.), time (day, night), etc.; automobile decoration information may include the type of decoration (such as body stickers, wheel decorations, car logos, headlight decorations, etc.), the appearance of the decoration (color, shape, texture, size, etc.), the position of the decoration (such as the car logo at the front of the car, the taillight decoration at the rear of the car, etc.), and the state of the decoration (whether it is intact, damaged, or stained).

[0030] Step S200, the image information is identified to obtain the structural environment characteristics of the automobile and the image recognition characteristics of the decorative parts, and the positional relationship between the image recognition characteristics of the decorative parts and the structural environment characteristics of the automobile is identified. The collected images of the automobile and its decorative parts are identified and analyzed in detail through image processing technology to obtain the structural environment characteristics of the automobile and the image recognition characteristics of the decorative parts, and the positional relationship between the image recognition characteristics of the decorative parts and the structural environment characteristics of the automobile is identified. Specifically, the structural environment characteristics of the automobile refer to the structural characteristics of the automobile such as the type, model, color, body lines, etc., and the environmental characteristics of the automobile, such as the road type, weather conditions, background objects, etc., which are identified through image analysis; the image recognition characteristics of the decorative parts refer to the characteristics of the type, color, shape, texture, etc., which are identified. After obtaining the structural environment characteristics of the automobile and the image recognition characteristics of the decorative parts, the position of each decorative part on the automobile and the relative positional relationship between them and the structural characteristics of the automobile can be accurately located through image processing technology, including the installation position of the decorative part on the automobile, the fit with the body structure, the relative position with other components, etc.

[0031] In a possible implementation, step S200 further includes step S210, preprocessing the image information, including denoising and contrast enhancement, and the image information includes a full-angle captured image of the decorative part. Due to the influence of equipment, environment, etc., the captured image may have noise (such as spots, uneven colors, etc.), which can be denoised by median filtering, Gaussian filtering, etc. to effectively remove the noise in the image. Contrast is the degree of difference between bright and dark areas in the image. Contrast enhancement by histogram equalization, contrast stretching, etc. can improve the clarity and recognizability of the image. Full-angle captured images refer to views of various angles of automobile decorative parts captured using a rotating stage, camera array or multi-view shooting technology, that is, the appearance and details of automobile decorative parts in various directions. The method further includes step S210, using a convolution model to perform background and foreground segmentation on the preprocessed image information, and performing feature recognition on the segmentation results, including recognition of the structural environmental features of the car in the background, and recognition of the shape, texture, edge, and color of the decorative parts in the foreground, to obtain the decorative parts image recognition features, wherein the decorative parts image recognition features have a collection angle identifier, wherein the convolution model is a convolutional neural network model with background segmentation and image feature recognition functions obtained through historical sample data training convergence. Based on the convolutional neural network, a convolutional neural network model (CNN), i.e., a convolutional model, is obtained through historical sample data training convergence, and is used to perform background segmentation and image feature recognition on the preprocessed image, wherein background and foreground segmentation refers to recognition of the structural environmental features of the car in the background and the car decorative parts in the foreground, such as shape, texture, edge, and color, which constitute the image recognition features of the car decorative parts. The method further includes step S230, obtaining the physical structure information of the automobile, constructing three-dimensional coordinates, determining the coordinate position of the image recognition feature of the decorative part based on the structural environment characteristics of the automobile, splicing the decorative part and its image recognition feature according to the acquisition angle mark to restore the structural feature of the decorative part, and fitting it into the three-dimensional coordinates, determining the positional relationship between the image recognition feature of the decorative part and the structural environment characteristics of the automobile for identification. Scan and measure the automobile to obtain the physical structure information of the automobile, including the precise size and shape information of each part of the automobile, construct three-dimensional coordinates, accurately represent the spatial position of each part of the automobile, determine the coordinate position of the image recognition feature of the decorative part based on the structural environment characteristics of the automobile, that is, the position of the automobile decorative part in the three-dimensional coordinate system, because the decorative part is photographed from multiple angles, it is necessary to splice the image recognition features of different angles to restore the complete three-dimensional structural features of the decorative part, fit it into the constructed three-dimensional coordinates, ensure that the three-dimensional model of the decorative part closely matches the structural environment characteristics of the automobile, determine the accurate positional relationship between the decorative part and each part of the automobile and identify it, for example, using labels, annotations or directly marking on the three-dimensional model.

[0032] Step S300, with the protection safety as the goal, the image recognition features of the decorative parts and the positional relationship between the image recognition features of the decorative parts and the vehicle structural environment features are analyzed for correlation, and the protection safety test target is obtained. With the protection safety as the goal, the image recognition features of the decorative parts and the positional relationship between the decorative parts and the vehicle structural environment features are analyzed for correlation, including analyzing whether the size and shape of the decorative parts match the vehicle structure, whether there is a potential risk of collision or interference, analyzing whether the color and material of the decorative parts meet the safety requirements, such as whether it affects the driving line of sight or reflective performance, analyzing whether the installation position of the decorative parts is stable and reliable, and whether it may fall off or shift due to vibration or collision. Through correlation analysis, key factors and potential risk points that may affect protection safety can be identified. Based on these analysis results, targeted protection safety test targets are formulated, such as testing the fixing stability, impact resistance, and wind resistance of decorative parts.

[0033] In a possible implementation, step S300 further includes step S310, collecting protective safety accident cases of automobile decorative parts. Cases of safety accidents or potential dangerous situations related to automobile decorative parts are collected, including accident cases that cause injury or loss to vehicles or passengers during the design, manufacture, installation or use of the decorative parts themselves. It also includes step S320, determining the top event based on the accident type of the protective safety accident case. Identify and analyze the most general and representative top events from these cases, which can fully reflect a series of similar safety accidents. It also includes step S330, taking the top event as the starting point of the accident tree, decomposing the top event according to the protective safety accident case, and determining the intermediate event, which is the direct cause of the top event. Taking the top event as the starting point of the accident tree, and decomposing the top event based on the protective safety accident case, an accident tree is constructed to clearly show all possible paths and logical relationships from the top event to the bottom event (basic cause), and the intermediate event is the direct cause of the safety accident of the automobile decorative parts. It also includes step S340, based on the intermediate event, continue to decompose until the basic event is decomposed to obtain the accident factor, which is the minimum accident impact parameter. Starting from the top event, after the decomposition of the intermediate event, until the most basic event that cannot be further decomposed is reached, that is, the basic event or the accident factor, wherein the accident factor is the smallest unit constituting the accident tree and is also the minimum accident impact parameter that causes the accident. It also includes step S350, based on the protection safety accident case, the risk probability of the accident factor and the intermediate event is evaluated to determine the risk function relationship. Based on the collected protection safety accident cases, the probability of each accident factor and intermediate event is quantitatively evaluated, and then the mathematical relationship between them, that is, the risk function relationship, is determined to describe the relationship between the probability of the intermediate event of the automobile decoration safety accident and the accident factor. It also includes step S360, based on the risk function relationship, identifying the minimum cut set, the minimum cut set is a combination of a group of accident factors, when the minimum cut set occurs, it will cause the occurrence of the top event, the minimum cut set and its risk function relationship are used as output to obtain the reverse parsing accident tree. The minimum cut set refers to the combination of accident factors. When and only when this set of basic events occurs at the same time, the top event (automotive decorative parts safety accident) will occur. The reverse analysis of the accident tree starts from the top event and traces down to the basic events (accident factors) through the minimum cut set and their risk function relationship. The minimum cut set and its risk function relationship are used as output to show which combinations of basic events are most likely to lead to the occurrence of the top event of the accident tree.

[0034] In a possible implementation, step S300 further includes step S370, identifying the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environmental features through the reverse parsing accident tree, and determining the accident factors in the decorative part image recognition features and their positional relationship. By reverse parsing the accident tree, combined with the decorative part image recognition features and their positional relationship with the vehicle structural environmental features, factors that may cause accidents are identified, that is, the accident factors in the decorative part image recognition features and their positional relationship, such as design defects, improper installation, positional offset, etc. of the decorative parts, or performance degradation or failure of the decorative parts due to environmental factors (such as temperature, humidity, vibration, etc.). It also includes step S380, using the decorative part image recognition features corresponding to the accident factors and their positional relationship with the vehicle structural environmental features as the protection safety test targets. When conducting safety tests on automobile decorative parts, factors that may cause safety accidents (i.e., accident factors) and the related decorative parts image recognition features and their positional relationship in the automobile structure will be used as protection safety test targets. Specifically, during the protection safety test, focus is placed on whether the decorative parts image recognition features and their positional relationship with the environmental characteristics of the automobile structure can lead to the occurrence of safety accidents.

[0035] Step S400, construct a digital twin simulation space, which includes a built-in scene simulation module and a test condition simulation module. Based on all the collected data related to automobile decoration parts, use modeling tools, simulation tools, visualization tools, etc. to establish a digital twin model, integrate and deploy the built-in scene simulation module and the test condition simulation module to form a complete digital twin simulation space, ensure that the data interaction and collaborative work between the modules can proceed smoothly to support various testing and simulation needs. Specifically, the built-in scene simulation module is mainly responsible for simulating and replicating various scenes in the actual environment, such as the road environment where the car is driving, the production line of the factory, the interior or exterior of the building, etc. Through precise three-dimensional modeling and rendering technology, the built-in scene simulation module can create a highly realistic virtual environment, and can be customized and expanded according to needs. For example, according to the specific application scenario, specific elements can be added or deleted, and adjustments can be made. The lighting, weather and other parameters of the entire scene can more accurately simulate the actual environment. The built-in scene simulation module also supports a variety of interactive methods, such as navigation and operation in a virtual environment through virtual reality (VR) devices or augmented reality (AR) devices; the test condition simulation module is mainly used to simulate and simulate various conditions in the actual test process, including environmental parameters such as temperature, humidity, pressure, and wind speed. Through the test condition simulation module, various tests can be performed on automotive decorative parts in a virtual environment to evaluate their performance and reliability under different conditions. The test condition simulation module also supports a variety of test methods, such as stress testing, durability testing, fault simulation, etc. According to specific test requirements, the corresponding test methods and parameter settings can be selected to simulate various situations in the actual test of automotive decorative parts. Through the constructed digital twin simulation space, various tests and simulation experiments can be performed on automotive decorative parts to evaluate the performance and reliability of automotive decorative parts.

[0036] In a possible implementation, step S400 further includes step S410, constructing the digital twin simulation space based on the three-dimensional coordinates, simulating the physical structure information of the car, the decorative parts and their decorative parts image recognition features. According to the three-dimensional coordinates, a virtual simulation space is constructed using digital twin technology, which is a digital replica of the car and the car decorative parts, and various situations can be simulated and tested. Specifically, in the digital twin simulation space, according to the three-dimensional coordinate information of the car, the physical structure of each part of the car is accurately simulated, and the decorative parts and their image recognition features (such as shape, texture, color, etc.) are mapped to the simulation space according to the actual size and position. In the constructed digital twin simulation space, various interactions and tests can be performed. For example, the driving conditions of the car under different road conditions can be simulated to check the performance or appearance changes of the decorative parts under specific conditions. It also includes step S420, according to the car operation scene and the operation environment condition parameters, the scene parameters and the test condition parameters are respectively configured to construct the scene simulation module and the test condition simulation module. Among them, the car operation scene may include urban roads, highways, rural roads, mountain roads, etc., and the operating environment condition parameters may include weather (such as sunny days, rainy days, snowy days, foggy days, etc.), temperature, wind speed, etc., according to the car operation scene, the corresponding scene parameters are configured. For example, for the urban road scene, the road width, number of lanes, traffic lights and other parameters are set to build the scene simulation module; according to the operating environment condition parameters, the test condition parameters are configured. For example, for rainy day tests, the raindrop size, raindrop density and other parameters are set to build the test condition simulation module. It also includes step S430, fitting the scene simulation module and the test condition simulation module into the digital twin simulation space. The scene simulation module and the test condition simulation module are integrated into the constructed digital twin simulation environment to simulate various situations and conditions that the car may encounter in the actual operating environment, and to conduct more comprehensive and accurate simulation tests on automobile decorative parts.

[0037] Step S500, connect the digital twin simulation space according to the protection safety test target for simulation testing, switch scenes and test conditions through the built-in scene simulation module and test condition simulation module, and obtain a multi-scenario test data set. Connect the digital twin simulation space according to the protection safety test target for simulation testing, mainly through the built-in scene simulation module and the test condition simulation module to simulate and switch different scenes and test conditions, and obtain a multi-scenario test data set. Specifically, connecting the protection safety test target with the digital twin simulation space refers to importing the relevant data of the protection safety test target of the automobile decoration into the digital twin simulation space, so as to test in the simulation environment, switch different scenes and test conditions through the built-in scene simulation module and the test condition simulation module, and obtain a multi-scenario test data set, including the real-time response data, performance parameters, safety indicators, etc. of the target automobile decoration in various scenarios, which are used to analyze the performance and safety of automobile decorations under different scenarios and environmental conditions.

[0038] In a possible implementation, step S500 further includes step S510, which switches simulation parameters through the built-in scenario simulation module and the test condition simulation module, including the scenario parameters and the test condition parameters, wherein the scenario parameters include driving, parking, braking, turning, and bumping, and the test condition parameters include temperature, altitude, humidity, and chemical resistance. Specifically, the simulation includes driving (such as acceleration, deceleration, overtaking, following, etc.), parking (such as parking at different positions such as flat ground and ramps), braking (such as braking conditions under different road surfaces and speeds), turning (such as turning behavior of vehicles at intersections, bends or curved roads), bumps (such as potholes, ups and downs, bumps, etc.), temperature (such as high temperature, low temperature, temperature changes), altitude, humidity (such as rainy days, wet land, deserts, etc.), chemical resistance including weather resistance and aging resistance, weather resistance refers to the ability of automobile decorative parts to maintain stable physical and chemical properties under long-term exposure to natural factors such as sunlight, rain, temperature changes, humidity, pollutants, etc., and aging resistance refers to the ability of automobile decorative parts to resist performance degradation and appearance changes caused by factors such as oxidation and ultraviolet radiation during long-term use. It also includes step S520, based on different combinations of the scene parameters and test condition parameters, construct multiple scenes, obtain simulation dynamic data of each scene respectively, and obtain the multi-scene test data set. Combine scenario parameters and test condition parameters in different ways to construct multiple scenarios. For example, construct a scenario of high-speed driving and high-temperature environment, or a scenario of bumpy road surface and high altitude, etc., to cover various actual use environment conditions that the vehicle may encounter. Simulate the digital twin simulation space to obtain the corresponding simulation dynamic data, integrate the simulation dynamic data collected in different scenarios, and form a multi-scenario test data set, which includes the performance data of vehicle decorative parts under different environmental conditions.

[0039] Step S600, identify security protection risks according to the multi-scenario test data set, and obtain the risk test value of each scenario. Using the data set collected during the multi-scenario simulation test, evaluate the security protection capabilities of the target system or device in different scenarios, and quantify the risks it faces. Specifically, analyze the data in the multi-scenario test data set, identify possible security threats or risks based on the results of the data analysis, and quantitatively evaluate the identified security risks, that is, assign a specific test value to each risk to indicate the potential impact of the risk on the target automotive decorative parts, and finally obtain the risk test value of each scenario.

[0040] In a possible implementation, step S600 further includes step S610, when there is a security anomaly event in the multi-scenario test data set, obtaining the scenario risk test value according to the risk level of the security anomaly event. Identify the security anomaly events in the multi-scenario test data set, evaluate the risk level of each security anomaly event based on factors such as the severity of the event, the frequency of occurrence, and the possible consequences, and determine a scenario risk test value for each scenario based on the risk level of the security anomaly event, indicating the potential risk level in the scenario. It also includes step S620, when the security anomaly event does not exist in the multi-scenario test data set, perform a time series variation analysis based on the multi-scenario test data set, and perform a variation prediction based on the correspondence between the scenario parameters, the test condition parameters and the time series variation. There are no abnormal safety events in the multi-scenario test data set, indicating that there are no safety protection issues in the current test, but there may be potential safety hazards. The analysis of the time series variation is to make predictions based on the current test status, and to conduct test evaluations on the probability of possible safety accidents of automobile decorative parts in combination with the risk level, and to predict the future changes of various performance parameters in the multi-scenario test data set, where the time series variation may represent the displacement, vibration frequency, inclination or surface cracks of automobile decorative parts. It also includes step S630, obtaining the scenario risk test value according to the variation prediction result and the corresponding risk level of the predicted safety abnormal event. Possible safety abnormal events can be further predicted based on the variation prediction result, and the scenario risk test value can be determined in combination with the corresponding risk level of the predicted safety event, indicating the risk level faced by automobile decorative parts in a given scenario.

[0041] Step S700, comprehensively calculate the risk test values ​​of all scenarios to obtain the protection safety test results. The risk test values ​​collected in different scenarios are integrated and analyzed to obtain a comprehensive test result that reflects the overall safety protection performance of the target system or equipment. Specifically, the risk test values ​​obtained in each scenario are summarized, and different weights are assigned to different scenarios according to the importance of each scenario and the reliability of the risk test values. Based on the weight allocation, the risk test values ​​of all scenarios are weighted averaged to obtain the protection safety test results, which are used to represent the overall protection safety performance of the target automotive decorative parts.

[0042] In the above, refer to Figure 1 The protective safety test method for automobile decoration parts according to an embodiment of the present invention is described in detail. Figure 2 A protection safety testing device for automobile decorative parts according to an embodiment of the present invention is described.

[0043] The protection safety test device for automobile decorative parts according to the embodiment of the present invention is used to solve the technical problem that it is difficult to accurately simulate various complex environmental conditions faced in the existing automobile decorative parts test, which makes the safety test results deviate from the actual situation, and then leads to poor accuracy and reliability of the protection safety test, thereby achieving the technical effect of improving the accuracy and reliability of the protection safety test of automobile decorative parts. The protection safety test device for automobile decorative parts includes: an image information acquisition module 10, an image information recognition module 20, a protection safety test target acquisition module 30, a digital twin simulation space construction module 40, a simulation test module 50, a risk test value acquisition module 60, and a protection safety test result acquisition module 70.

[0044] An image information acquisition module 10, the image information acquisition module 10 is used to acquire image information of automobile decoration parts, the image information includes automobile setting environment information and automobile decoration part information;

[0045] An image information recognition module 20, the image information recognition module 20 is used to recognize the image information, obtain the vehicle structure environment characteristics, the decorative parts image recognition characteristics, and identify the positional relationship between the decorative parts image recognition characteristics and the vehicle structure environment characteristics;

[0046] A protection safety test target acquisition module 30, wherein the protection safety test target acquisition module 30 takes protection safety as a target, performs a correlation analysis on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features, and obtains a protection safety test target;

[0047] A digital twin simulation space construction module 40, wherein the digital twin simulation space construction module 40 is used to construct a digital twin simulation space, wherein the digital twin simulation space includes a built-in scene simulation module and a test condition simulation module;

[0048] A simulation test module 50, which is used to connect the digital twin simulation space to perform simulation testing according to the protection safety test target, switch scenes and test conditions through the built-in scene simulation module and test condition simulation module, and obtain a multi-scene test data set;

[0049] A risk test value obtaining module 60, wherein the risk test value obtaining module 60 is used to identify security protection risks according to the multi-scenario test data set and obtain a risk test value for each scenario;

[0050] The protection safety test result obtaining module 70 is used to comprehensively calculate all scenario risk test values ​​to obtain the protection safety test result.

[0051] The specific configuration of the image information recognition module 20 will be described in detail below. The image information recognition module 20 may further include: preprocessing the image information, including denoising and contrast enhancement, wherein the image information includes a full-angle acquisition image of the decorative part; using a convolution model to segment the background and foreground of the preprocessed image information, and performing feature recognition on the segmentation result, including recognizing the structural environmental features of the car in the background, recognizing the shape, texture, edge, and color of the decorative part in the foreground, and obtaining the decorative part image recognition feature, wherein the decorative part image recognition feature has an acquisition angle identifier, wherein the convolution model is a convolutional neural network model with background segmentation and image feature recognition functions obtained by training and converging with historical sample data; obtaining the physical structure information of the car, constructing three-dimensional coordinates, determining the coordinate position of the decorative part image recognition feature based on the structural environmental features of the car, splicing the decorative part and its decorative part image recognition feature according to the acquisition angle identifier to restore the decorative part structural feature, and fitting them to the three-dimensional coordinates, determining the positional relationship between the decorative part image recognition feature and the structural environmental feature of the car for identification.

[0052] The specific configuration of the digital twin simulation space construction module 40 will be described in detail below. The digital twin simulation space construction module 40 further includes: constructing the digital twin simulation space based on the three-dimensional coordinates, simulating the physical structure information of the car, the decorative parts and their decorative parts image recognition features; configuring the scene parameters and the test condition parameters according to the car operation scene and the operation environment condition parameters, respectively, and constructing the scene simulation module and the test condition simulation module; fitting the scene simulation module and the test condition simulation module into the digital twin simulation space.

[0053] The specific configuration of the protection safety test target acquisition module 30 will be described in detail below. The protection safety test target acquisition module 30 may further include: collecting protection safety accident cases of automobile decorative parts; determining the top event based on the accident type of the protection safety accident case; taking the top event as the starting point of the accident tree, decomposing the top event according to the protection safety accident case, and determining the intermediate event, which is the direct cause of the top event; continuing to decompose based on the intermediate event until it is decomposed to the basic event, and obtaining the accident factor, which is the minimum accident impact parameter; evaluating the risk probability of the accident factor and the intermediate event according to the protection safety accident case, and determining the risk function relationship; based on the risk function relationship, identifying the minimum cut set, the minimum cut set is a combination of a group of accident factors, and when the minimum cut set occurs, it will cause the occurrence of the top event, and the minimum cut set and its risk function relationship are used as output to obtain the reverse parsing accident tree.

[0054] The specific configuration of the protection safety test target acquisition module 30 will be described in detail below. The protection safety test target acquisition module 30 may further include: identifying the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features through the reverse parsing accident tree, determining the accident factors in the decorative part image recognition features and their positional relationship; using the decorative part image recognition features corresponding to the accident factors and their positional relationship with the vehicle structural environment features as the protection safety test targets.

[0055] The specific configuration of the simulation test module 50 will be described in detail below. The simulation test module 50 further includes: switching simulation parameters through the built-in scene simulation module and the test condition simulation module, including the scene parameters and the test condition parameters, wherein the scene parameters include driving, parking, braking, turning, and bumping, and the test condition parameters include temperature, altitude, humidity, and chemical resistance; based on different combinations of the scene parameters and the test condition parameters, constructing multiple scenes, respectively acquiring the simulation dynamic data of each scene, and obtaining the multi-scene test data set.

[0056] The specific configuration of the risk test value acquisition module 60 will be described in detail below. The risk test value acquisition module 60 further includes: when there is a safety abnormal event in the multi-scenario test data set, the scenario risk test value is obtained according to the risk level of the safety abnormal event; when there is no safety abnormal event in the multi-scenario test data set, a time series variation analysis is performed according to the multi-scenario test data set, and a variation prediction is performed based on the corresponding relationship between the scenario parameters, the test condition parameters and the time series variation; the scenario risk test value is obtained according to the variation prediction result and the corresponding predicted safety abnormal event risk level.

[0057] The protection safety testing device for automobile decorative parts provided in the embodiment of the present invention can execute the protection safety testing method for automobile decorative parts provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0058] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0059] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, 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 application should be included in the protection scope of this application.

Claims

1. A protective safety test method for automotive decorative parts, characterized in that: The method comprises: Collecting image information of automobile decoration parts, wherein the image information includes automobile setting environment information and automobile decoration part information; Identify the image information to obtain the vehicle structure environment characteristics and the decorative part image recognition characteristics, and identify the positional relationship between the decorative part image recognition characteristics and the vehicle structure environment characteristics; Taking protection safety as the goal, a correlation analysis is performed on the image recognition features of the decorative parts and the positional relationship between the image recognition features of the decorative parts and the structural environment features of the automobile to obtain a protection safety test target; Constructing a digital twin simulation space, wherein the digital twin simulation space includes a built-in scenario simulation module and a test condition simulation module; Connecting the digital twin simulation space to perform simulation testing according to the protection safety test target, switching scenes and test conditions through the built-in scene simulation module and test condition simulation module, and obtaining a multi-scene test data set; Perform security protection risk identification based on the multi-scenario test data set to obtain a risk test value for each scenario; All scenario risk test values ​​are calculated comprehensively to obtain the protection safety test results.

2. The protective safety testing method for automobile decorative parts according to claim 1, characterized in that: Identify the image information to obtain the vehicle structure environment features and the decorative parts image recognition features, including: Preprocessing the image information, including denoising and contrast enhancement, wherein the image information includes a full-angle captured image of the decorative part; The convolution model is used to segment the background and foreground of the preprocessed image information, and the segmentation results are subjected to feature recognition, including recognition of the structural environment features of the automobile in the background, and recognition of the shape, texture, edge, and color of the decorative parts in the foreground, to obtain the decorative parts image recognition features, wherein the decorative parts image recognition features have a collection angle identifier, wherein the convolution model is a convolutional neural network model with background segmentation and image feature recognition functions obtained through historical sample data training convergence; The physical structure information of the automobile is obtained, and three-dimensional coordinates are constructed. Based on the structural environment characteristics of the automobile, the coordinate position of the decorative part image recognition feature is determined, and the decorative part and its decorative part image recognition feature are spliced ​​according to the acquisition angle mark to restore the decorative part structural feature, and fitted into the three-dimensional coordinates, and the positional relationship between the decorative part image recognition feature and the structural environment characteristics of the automobile is determined and marked.

3. The protective safety testing method for automobile decorative parts according to claim 2, characterized in that: The construction of the digital twin simulation space includes: Based on the three-dimensional coordinates, construct the digital twin simulation space to simulate the physical structure information of the automobile, the decorative parts and the decorative parts image recognition features; According to the vehicle operation scenario and the operating environment condition parameters, respectively configure the scenario parameters and the test condition parameters, and construct the scenario simulation module and the test condition simulation module; The scenario simulation module and the test condition simulation module are fitted into the digital twin simulation space.

4. The protective safety testing method for automobile decorative parts according to claim 1, characterized in that: The method further comprises: taking protection safety as the goal, performing correlation analysis on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features, before obtaining the protection safety test goal. Collect cases of safety accidents involving the protection of automobile decoration parts; Determining top events based on the incident type of the protection safety incident case; Taking the top event as the starting point of the accident tree, the top event is decomposed according to the protection safety accident case to determine the intermediate event, and the intermediate event is the direct cause of the top event; Continue to decompose based on the intermediate event until it is decomposed to the basic event, and obtain the accident factor, which is the minimum accident impact parameter; Conduct risk probability assessment of accident factors and intermediate events based on the protection safety accident cases, and determine the risk function relationship; Based on the risk function relationship, the minimum cut set is identified. The minimum cut set is a combination of accident factors. When the minimum cut set occurs, it will lead to the occurrence of the top event. The minimum cut set and its risk function relationship are used as output to obtain a reverse parsing accident tree.

5. The protective safety testing method for automobile decorative parts according to claim 4, characterized in that: The protection safety is taken as the goal, and the correlation analysis is performed on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structure environment features to obtain the protection safety test target, including: Identify the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features through the reverse parsing accident tree, and determine the accident factors in the decorative part image recognition features and their positional relationship; The decorative part image recognition features corresponding to the accident factors and their positional relationship with the vehicle structural environment features are used as the protection safety test targets.

6. The protective safety testing method for automobile decorative parts according to claim 3, characterized in that: The built-in scene simulation module and the test condition simulation module are used to switch scenes and test conditions to obtain a multi-scene test data set, including: Switching simulation parameters through the built-in scenario simulation module and the test condition simulation module respectively, including the scenario parameters and the test condition parameters, wherein the scenario parameters include driving, parking, braking, turning, and bumping, and the test condition parameters include temperature, altitude, humidity, and chemical resistance; Based on different combinations of the scenario parameters and test condition parameters, multiple scenarios are constructed, and simulation dynamic data of each scenario is obtained respectively to obtain the multi-scenario test data set.

7. The protective safety testing method for automobile decorative parts according to claim 6, characterized in that: Security protection risk identification is performed according to the multi-scenario test data set to obtain the risk test value of each scenario, including: When there is a security anomaly event in the multi-scenario test data set, obtaining the scenario risk test value according to the risk level of the security anomaly event; When the safety abnormal event does not exist in the multi-scenario test data set, performing time series variation analysis according to the multi-scenario test data set, and performing variation prediction based on the corresponding relationship between the scenario parameters, the test condition parameters and the time series variation; The scenario risk test value is obtained based on the change prediction result and the corresponding predicted risk level of the safety abnormal event.

8. A protective safety test device for automobile decorative parts, characterized in that: The device is used to implement the protective safety testing method for automobile decorative parts according to any one of claims 1 to 7, and the device comprises: An image information acquisition module, the image information acquisition module is used to acquire image information of automobile decoration parts, according to which the image information includes automobile setting environment information and automobile decoration part information; An image information recognition module, the image information recognition module is used to recognize the image information, obtain the vehicle structure environment characteristics, the decorative parts image recognition characteristics, and identify the positional relationship between the decorative parts image recognition characteristics and the vehicle structure environment characteristics; A protection safety test target acquisition module, wherein the protection safety test target acquisition module takes protection safety as a target, performs a correlation analysis on the decorative part image recognition features and the positional relationship between the decorative part image recognition features and the vehicle structural environment features, and obtains a protection safety test target; A digital twin simulation space construction module, wherein the digital twin simulation space construction module is used to construct a digital twin simulation space, wherein the digital twin simulation space includes a built-in scene simulation module and a test condition simulation module; A simulation test module, wherein the simulation test module is used to connect the digital twin simulation space to perform simulation testing according to the protection safety test target, switch scenes and test conditions through the built-in scene simulation module and the test condition simulation module, and obtain a multi-scene test data set; A risk test value acquisition module, the risk test value acquisition module is used to identify security protection risks according to the multi-scenario test data set and obtain a risk test value for each scenario; The protection safety test result acquisition module is used to comprehensively calculate all scenario risk test values ​​to obtain the protection safety test results.

Images