System and method for predicting damage to a virtual vehicle

Abstract

The present disclosure provides a system 102 and a method 700 for predicting damage to a virtual vehicle. The method 700 includes receiving 702 one or more terrain parameters from one or more physical terrain clusters and one or more vehicle parameters and transforming 704 the one or more terrain parameters into a smoothed particle hydrodynamics (SPH) model. The method 700 further includes determining 706 one or more SPH particles based on the transformation and generating 708 one or more digital terrain clusters in a digital environment using the one or more SPH particles.The method 700 further includes generating 710 the virtual vehicle based on the one or more vehicle parameters and performing 712 a collision between the one or more digital terrain clusters and the virtual vehicle to predict 714 damage to the virtual vehicle based on the collision via an artificial intelligence (AI) model.

Description

TECHNICAL FIELDThe present disclosure relates to the field of automotive engineering. In particular, the present disclosure provides a system and method for predicting damage to a virtual vehicle by simulating a collision between digital terrain clusters and the virtual vehicle within a digital environment.BACKGROUNDIn winter, in certain countries, heavy snowfalls frequently occur, which lead to an accumulation of snow on the roads. This accumulated snow is then pushed aside and forms clusters on the roadside. This situation presents a challenge in practice, since vehicles may inadvertently collide with these snow clusters. Such collisions on parking spaces or roads in winter can result in damage to the bumper and underbody of the vehicles, which results in unnecessary repair costs and the need for damage prevention.Many techniques have been developed to avoid the above problems. Thus, US2009228246A1 describes a system and method for computer-assisted technical analysis using a hybrid approach combining finite element method (FEM) and adaptive smoothed particle hydrodynamics (SPH). In one aspect, computer-aided engineering analysis is performed to simulate an impact event between structures. To illustrate the structures, a FEM mesh model is created which contains numerous volume elements which characterize the geometry and the material properties. In the case of contact between two structures, which leads to a material or structure failure, the volume elements which represent the failed section of the structure are eliminated according to the predefined material constitution equation. Each failed volume element is then replaced with multiple particles for analysis with SPH. The particles which assume all the states and characteristics of the failing element such as location, mass, velocity, acceleration, etc. are replaced according to the principles of mass, momentum and energy conservation.Only a few other documents from the non-patent literature describe the simulation of snowfall movements, the snow accumulation on roads and the behavior of snowfall in environmental test rooms, and a vehicle machine for snowfall on roads.The non-patent literature document entitled "Modeling and prediction of tire-snow interaction using finite element analysis-smooth particle hydrodynamics" (modeling and prediction of the interaction between tire and snow by means of finite element analysis and smoothed particle hydrodynamics) is concerned with, for example, modeling and prediction of the interaction between a truck tire and snow for calculation of the motion resistance coefficient of the tire. The tire of the off-road vehicle is modeled with the aid of the finite element analysis and validated with respect to static and dynamic reactions on the basis of published measurement data. The snow is modeled using the smoothed particle hydrodynamic technique using a hydrodynamically elastic-plastic material that is calibrated using physical measurements from published terramechanics data. The contact algorithm implemented is node symmetric node-segment contact with edge handling. The rolling resistance coefficient, which is equivalent to the movement resistance coefficient in the interaction between truck tire and snow, is calculated for various operating conditions, including vertical load, air pressure, tire longitudinal speed and snow height. In the paper, the influence of these operating conditions on the motion resistance coefficient of truck tires is studied and discussed.Conventional methods and systems lack integration of snow heap modelling and vehicle deformation simulation, which makes it difficult to predict potential damage to the bumpers and underbody portions of vehicles during snow heap impact tests. Moreover, these conventional systems and methods do not adequately address the simulation methodology for snowshock impact tests.Therefore, there is a need to overcome at least the above disadvantages and all other deficiencies or at least provide a valuable alternative to existing simulation methods and systems.OBJECT OF THE PRESENT DISCLOSUREA general object of the present disclosure is to provide an efficient and reliable system and method that efficiently eliminates the above-mentioned limitations of existing systems and methods.An object of the present disclosure is to provide a system and method for predicting damage to a virtual vehicle in a digital environment.Another object of the present disclosure is to provide a system and method that uses a smoothed particle hydrodynamic (SPH) model to determine one or more SPH particles to produce digital terrain clusters.Another object of the present disclosure is to provide a system and method for simulating a collision between digital terrain clusters and a virtual vehicle, wherein the simulation is performed to evaluate charging operations and predict possible complications at early stages of vehicle development.SUMMARYAspects of the present disclosure relate to the field of automotive engineering. In particular, the present disclosure provides a system and method for predicting damage to a virtual vehicle by simulating a collision between digital terrain clusters and the virtual vehicle within a digital environment.An aspect of the present disclosure relates to a method for predicting damage to a virtual vehicle. The method includes receiving, by one or more processors connected to a system, one or more terrain parameters from one or more physical terrain clusters and one or more vehicle parameters, and transforming the one or more terrain parameters into a smoothed particle hydrodynamic model (SPH), by the one or more processors. Further, the method includes determining, by the one or more processors, one or more SPH particles based on the transformation and generating, by the one or more processors, one or more digital terrain clusters in a digital environment using the one or more SPH particles. Further, the method includes generating, by the one or more processors, the virtual vehicle in the digital environment based on the one or more vehicle parameters and performing, by the one or more processors, a collision between the one or more digital terrain clusters and the virtual vehicle to predict damage to the virtual vehicle based on the collision by the one or more processors via an artificial intelligence (AI) model.In one embodiment, the one or more vehicle parameters may include at least one of mass, geometric information, material characteristics, occupants, and functional specifications of propulsion components.In an embodiment, the one or more terrain parameters may comprise at least one of physical features of the one or more physical terrain clusters and structural features of the one or more physical terrain clusters.In one embodiment, the method of generating the one or more digital terrain clusters using the one or more SPH particles may include, by the one or more processors, determining an outer surface of the one or more digital terrain clusters based on the transformation and assigning physical attributes to each SPH particle of the one or more digital terrain clusters by the one or more processors. Further, the method may include simulating, by the one or more processors, the one or more digital terrain clusters based on the physical attributes of each SPH particle and determining, by the one or more processors, one or more physical properties and one or more structural properties of the one or more digital terrain clusters based on the simulation.In one embodiment, the physical attributes may include at least one of the following properties: a material property and geometric information.In one embodiment, one or more SPH particles of the one or more digital terrain clusters represent at least one of the following layers: outermost layers, hardest layers, elastic layers, soft layers, medium density layers, and dense layers.In one embodiment, the method of performing the collision between the one or more digital terrain clusters and the virtual vehicle by the one or more processors may include determining an impact value of a surface of the virtual vehicle during the collision and providing the impact value to a user via a user interface based on the determination. Further, the method may include receiving, by the one or more processors, an input from the user to fine-tune at least one of the one or more virtual vehicle vehicle vehicle parameters, the one or more terrain parameters, and a force of the collision based on the impact value.In one embodiment, the method may include adjusting the one or more virtual vehicle vehicle vehicle parameters, the one or more terrain parameters, and the collision force based on the received input by the one or more processors.Another aspect of the present disclosure relates to a system for predicting damage to a virtual vehicle. The system includes one or more processors; and a memory operatively coupled to the one or more processors, the memory including one or more instructions that, when executed, cause the one or more processors to receive one or more terrain parameters of one or more physical terrain clusters and one or more vehicle parameters and transform the one or more terrain parameters into a smoothed particle hydrodynamic model (SPH). Further, the one or more processors are to determine one or more SPH particles based on the transformation and generate one or more digital terrain clusters in a digital environment using the one or more SPH particles. Further, the one or more processors are to generate the virtual vehicle in the digital environment based on the one or more vehicle parameters and perform a collision between the one or more digital terrain clusters and the virtual vehicle to predict damage to the virtual vehicle based on the collision via an artificial intelligence (AI) model.In an embodiment, the one or more processors may adjust at least one of the one or more virtual vehicle vehicle parameters, the one or more terrain parameters, and a force of the collision based on an impact value of a surface of the virtual vehicle during the collision.Various objects, features, aspects and advantages of the invention will become more apparent from the following detailed description of preferred embodiments taken in conjunction with the accompanying drawings, in which like numerals represent components.BRIEF DESCRIPTION OF THE DRAWINGSThe accompanying drawings serve to further understand the present disclosure and form part of this description. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. FIG. 1 is a block diagram of an example system for predicting damage to a virtual vehicle according to an embodiment of the present disclosure. FIG. 2 shows a flowchart of an example method for simulating a collision between digital terrain clusters and the virtual vehicle according to an embodiment of the present disclosure. FIGS. 3A-3B show an example representation of the digital terrain clusters in accordance with an embodiment of the present disclosure. FIG. 4 shows an example illustration of loading simulation inputs for the digital terrain clusters and the virtual vehicle in a digital environment, in accordance with an embodiment of the present disclosure. FIG. 5 illustrates an example of predicting damage to the virtual vehicle during the collision, according to an embodiment of the present disclosure. FIG. 6 shows an example illustration of the interaction framework for the digital terrain heap model in accordance with an embodiment of the present disclosure. FIG. 7 is a flowchart of an example method for predicting damage to the virtual vehicle according to an embodiment of the present disclosure.DETAILED DESCRIPTIONThe following is a detailed description of the embodiments of the disclosure illustrated in the accompanying drawings. The embodiments are so detailed as to clearly convey the disclosure. However, it is not intended to limit the predictable variations of embodiments with the particularity provided; on the contrary, it is intended to cover all modifications, equivalents and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.The embodiments discussed herein relate to automotive technology. More particularly, the present disclosure relates to a system and method for predicting damage to a virtual vehicle by simulating a collision between digital terrain clusters and the virtual vehicle in a digital environment. Various embodiments of the present disclosure will be explained in detail with reference to the FIGURES. 1-7.FIG. 1 shows a block diagram 100 of an example system 102 for predicting damage to a virtual vehicle according to an embodiment of the present disclosure.As shown in FIG. 1, the system 102 may include one or more processors 104, a memory 106, and one or more interfaces 108. The one or more processors 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that process data based on operating instructions. Among other capabilities, the one or more processor(s) 104 may be configured to fetch and execute computer readable instructions stored in the memory 106 of the system 102. The memory 106 may store one or more computer readable instructions or routines that may be fetched and executed to predict damage to a virtual vehicle. The memory 106 may include any nonvolatile memory device, for example, volatile memory such as random access memory (RAM), or nonvolatile memory such as erasable programmable read-only memory (EPROM), flash memory, and the like.The interface(s) 108 may include a variety of interfaces, e.g., interfaces for data input and output devices referred to as I / O devices, storage devices, and the like. The interface(s) 108 may / may facilitate communication of the system 102 with various devices connected thereto. The interface(s) 108 may also provide a communication path for one or more components of the system 102. Examples of such components include processing engine(s) 110 and database 112. Database 112 may include data that is either stored or generated as a result of functionalities implemented by one of the components of processing engine(s) 110.In one embodiment, the processing machine(s) 110 may be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing machine(s) 110. In the examples described herein, such combinations of hardware and programming may be implemented in various ways. For example, the programming for the processing machine(s) 110 may consist of processor-executable instructions stored on a non-transitory machine-readable storage medium, and the hardware for the one or more processor(s) 104 may include a processing resource (e.g., one or more processors) to execute such instructions. In the present examples, the machine readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 110. In such examples, the system 102 may include the machine readable storage medium storing the instructions and the processing resource for executing the instructions, or the machine readable storage medium may be separate but accessible to the system 102 and the processing resource. In other examples, the processing engine(s) 110 may be implemented by an electronic circuit. The processing module(s) 110 may include a Smoothed Particle Hydrodynamics (SPH) module 114, a digital terrain module 116, a vehicle virtualization module 118, a simulation module 120, a prediction module 122, and another module(s) 124. The other(s) module(s) 124 may implement functions that supplement the applications / functions performed by the processing engine(s) 110.The one or more processors 104 may receive terrain parameters from physical terrain clusters and vehicle parameters from a physical vehicle, where the physical vehicle may include, but is not limited to, two-wheels, three-wheels, four-wheels, buses, trucks, cars, trains, ships, vans, aircraft, and the like. In one embodiment, the physical terrain pieces may be, but are not limited to, snow, earth, sand, and the like. In some embodiments, the terrain parameters may include physical characteristics of the physical terrain clusters, structural information of the physical terrain clusters, and the like, among others. Similarly, the virtual vehicle vehicle vehicle parameters may include, but are not limited to, mass, geometric information, material characteristics, occupants, and functional specifications of propulsion components.The SPH module 114 may transform the terrain parameters into a Smooth Particle Hydrodynamics (SPH) model and determine SPH particles based on the transformation. By utilizing the capabilities of SPH modeling, a sophisticated simulation technique may be used to evaluate the structural effects of vehicle impacts on the terrain clusters within a digital environment. Once the SPH module 114 has determined the SPH particles, the digital terrain generation module 116 may generate digital terrain clusters using the SPH particles. To generate the digital terrain clusters, the SPH module 114 may determine an exterior surface of the digital terrain clusters based on the transformation and assign physical attributes to the SPH particles of the digital terrain clusters. Further, the SPH module 114 may simulate the digital terrain clusters based on the physical attributes of the SPH particles to determine a behavior, i.e., the physical properties and the structural properties, of the digital terrain clusters. In one embodiment, the physical attributes may include, but are not limited to, material properties and geometric information. In some embodiments, the SPH particles may represent the outermost layers of the digital terrain clusters, the hardest layers of the digital terrain clusters, the elastic layers of the digital terrain clusters, the soft layers of the digital terrain clusters, the medium density layers of the digital terrain clusters, the dense layers of the digital terrain clusters, and the like.At the same time, the vehicle virtualization module 118 may generate the virtual vehicle using the vehicle parameters. Once the digital terrain clusters and the virtual vehicle are generated, the simulation module 120 may simulate a collision between the digital terrain clusters and the virtual vehicle. During the simulation, the simulation module 120 may determine an impact value of a surface of the virtual vehicle and provide the impact value to a user via a user interface, where the user interface may be, but is not limited to, a display and the like. For example, the simulation module 120 may perform the collision between the virtual vehicle and the digital terrain clusters at different speeds and angles to determine the impact value, wherein the impact value may represent an impact level occurring in the virtual vehicle during the collision. The user may provide input to the system 102 to fine tune the virtual vehicle's vehicle parameters, the terrain parameters, and a force of the collision based on the impact value provided by the system 102. The system 102 may adjust the virtual vehicle vehicle vehicle parameters, the terrain parameters, and the force of the impact based on the input received from the user. The prediction module 122 may predict damage to the virtual vehicle in the digital environment based on the simulation, where the simulation technique relies on the principles of SPH. The prediction module 122 may be tailored to predict damage that may occur to the bumpers and the underbody of the vehicle upon impact with a hill of the ground in a real scenario. The one or more processors 104 may provide output that may represent a result of the simulation process. The output may include, but is not limited to, videos, images, texts, files, audio files, and the like.FIG. 2 shows a flow diagram of an example method 200 for simulating a collision between digital terrain clusters and a virtual vehicle according to an embodiment of the present disclosure.At blocks 202A- 202D, the method may include scanning physical terrain clusters to generate terrain parameters and transforming the terrain parameters to a Smooth Particle Hydrodynamics (SPH) model to determine SPH particles for building the digital terrain cluster, wherein the digital terrain clusters may be built based on the received physical attributes of the SPH particles. In one embodiment, a virtual test environment reproduces all macroscopic irregularities and surface variations present under real conditions and enables correlation activities through the representation of road inputs. Using scan data from the physical terrain clusters, a finite element method (FEM) model is created by SPH particles. The simulation model presents a great challenge and authentically maps the terrain properties. At block 204A, the method may include determining vehicle parameters of a physical vehicle using a computer aided design (CAD) model. At block 204B, the method may include analyzing a representation or simulation of the dynamics and behavior of the virtual vehicle during a collision or accident to predict the impact forces, deformation, and other factors associated with vehicle collisions. At block 204C, the method may include determining information and parameters relating to the operating aspects and performance of the virtual vehicle and including a broad spectrum of data points that provide information about how various systems and components within a vehicle function and cooperate. At block 204D, the method may include determining an axle configuration of the vehicle. At block 204E, the method may include integrating mass, connections, and function specifications of powertrain components from a real-world model to generate the virtual vehicle using an automatic net generation for structural analysis (ANSA) preprocessor.At block 206, the method may include combining the digital terrain clusters and the virtual vehicle using a Livermore software for Nonlinear Dynamic Analysis (LS-DYNA) solver, wherein the LS-DYNA solver may simulate a collision between the digital terrain clusters and the virtual vehicle. At block 208, the method may include determining quantitative and qualitative damage predictions using an Animator postprocessor. For example, after post-processing the simulation, a system, i.e., 102, may generate an output in the form of a visual representation using the animator pre-processor to display the output to a user via a user interface of the system, i.e., 102.FIGS. 3A-3B show example representations 300A, 300B of digital terrain clusters, in accordance with an embodiment of the present disclosure.As shown in FIG. 3A, an external device, such as a scanner (not shown in the figures), may be used to scan physical terrain clusters and create a scan model 300A for determining terrain parameters. In FIG. 3B, the construction of a finite element method (FEM) model using smooth particle hydrodynamics (SPH) particles is facilitated by the inclusion of scan data from the terrain heap scanner model 300A.For example, in one embodiment, digital modeling may simulate the effects of a virtual vehicle on digital terrain clusters 300B to detect detailed dynamics. It can begin with real terrain clusters where a detailed scanning process generates a digital representation in various formats such as the.stl format. This digital representation may include the physical properties and structure of the terrain. After the stl data is transferred to the Automatic Net Generation for Structural Analysis (ANSA) preprocessor, the data is converted to a shell representation that accurately captures the outer surface profile of the digital terrain clusters 300B and forms the basis for a precise digital simulation.Within this volume enclosed by a shell, the dynamic behavior of the terrain is acribically captured. By utilizing the versatile possibilities of ANSA, SPH particles can be introduced, each of which embodies different layers of snow behavior. The digital terrain heap 300B reflects the composition of the terrain in the real world and has three distinct layers: an outer layer characterized as the hardest and most resistant layer, a soft layer underneath it to absorb shocks, and a medium density layer further down. An additional dense layer serves as a protective shell enclosing this layered structure. In some embodiments, the interactions between the terrain layers and the external elements are controlled by the assignment of terrain material properties and contact methods within ANSA. This comprehensive approach ensures a consistent representation of the terrain dynamics in the digital simulation.FIG. 4 shows an example illustration 400 of loading simulation inputs for digital terrain clusters 300B and a virtual vehicle 402 in a digital environment, according to an embodiment of the present disclosure.Referring to FIG. 4, the virtual vehicle 402 may undergo a series of movements, e.g., 90-degree and 45-degree rectilinear impacts on the left and right portions of the virtual vehicle 402 with the digital terrain clusters 300B.In one embodiment, an Automatic Net Generation for Structural Analysis (ANSA) preprocessor is centered as a dynamic digital canvas. The versatility of the method is apparent in that it can accommodate a range of variants of a virtual vehicle 402 and provides a flexible basis for the analysis. This comprehensive digital model is provided with important data such as mass and geometry of the vehicle up to its complicated functional elements including the behavior of springs and dampers. A digital terrain heap 300B is simulated using Smooth Particle Hydrodynamics (SPH) particles. This process culminates in a true-to-original representation of the digital terrain heap 300B, a key component in simulating terrain impacts.Livermore software for Nonlinear Dynamic Analysis (LS-DYNA) is a sophisticated solver that serves as a data center. Geometry information, material specifications, and complicated function data transition seamlessly from the ANSA preprocessor to LS dyna. It systematically performs a series of detailed calculations and coordinates a thorough analysis of forces, shocks and interactions.Simply stated, the LS Dyna solver is a tool that performs complicated calculations to simulate how a vehicle behaves in various situations. Rather than only providing numerical results, it creates a virtual reality. This illustration clearly shows how the vehicle is moving and responding in a digital environment, with each impact, displacement, and response being detailed as if they were occurring in the real world.The LS dyna may generate detailed results of the virtual vehicle 402. Rather than presenting raw data only, the output represents complete information about the virtual vehicle 402. For example, the LS dyna may show how well the virtual vehicle 402 avoids challenges (durability) and where it could have problems (vulnerabilities). This output also documents the status of the virtual vehicle 402 after these simulated encounters to show any damage to the underbody and bumper.An Animator postprocessor takes control of a special controller which converts complicated data into comprehensible image material. It converts raw data into dynamic animations and visualizations, thus facilitating the analysis and understanding of those skilled in the art. In this way, the experts can identify important points of interest, evaluate changes, and understand the possible effects of these changes in a particular situation.FIG. 5 shows an example diagram 500 of predicting damage to a virtual vehicle 402 during a collision in a digital environment, according to an embodiment of the present disclosure.Referring to FIG. 5, in some embodiments, including SPH (Smooth Particle Hydrodynamics) model terrain particles in a simulation framework includes assigning a Morhr-Coulomb material map. This imparts certain properties to the terrain, including modulus of elasticity, Poisson's ratio, angle of friction and cohesion. These parameters form the basis for the behavior of the terrain and allow a realistic response of the terrain in a digital environment.At the beginning of the simulation, the virtual vehicle 402 may be assigned an initial speed, which gives the Livermore software for Nonlinear Dynamic Analysis (LS-DYNA) the impulse on detailed measurements. In a computational symphony, LS-Dyna explores the dynamic fineness of the behavior of a vehicle. This decrypts the complicated interaction of the forces during the impact, which subsequently triggers a cascade of effects that ultimately determine the resulting damage.The heart of this force calculation is a contact method integrated into LS Dyna. This method may include a conceptual spring, a virtual elastic tether that is activated to prevent excessive intrusion of the vehicle surface into the terrain. By creating a compressive force, this contact method maintains a dynamic balance reasonably and defeats any unauthorized intrusion into the digital terrain clusters 300B. The result of these complicated computations manifests itself in the creation of a tangible output, which is rendered by LS Dyna as a graphical file, e.g., d3plot. This output represents a fundus of findings that captures the entire chorea of the vehicle's interaction with the digital terrain clusters 300B. In one embodiment, the damage prediction report may connect visualization of geometric representations with overall dynamic responses calculated by a numerical integrator LS-Dyna. A method of contact detection incorporated into the numerical solver identifies and visually displays proximate contact points based on geometric inputs, which facilitates the accurate identification of potential contact points and resulting damage by engineers. The role then transitions to that of the animator which can convert data to convincing visual counts.An animator postprocessor converts the d3plot output to a motion picture and displays videos showing the collision of the virtual vehicle 402 with the digital terrain clusters 300B. These visual findings are not only visually appealing, but also convey technical findings. This includes a detailed analysis of the damage caused by the impact, which serves the designers as an unpredictable resource.Equipped with captive videos and a thorough understanding of the damage being observed, engineers begin a diligently research into vehicle design refinement. The findings obtained from these simulations enable engineers to fine-tune design decisions, optimize components, and determine a heading to improve vehicle robustness and performance. This iterative cycle of simulation, visualization, and analysis becomes a director, which presents the path to more robust, safer, and better designed vehicles.FIG. 6 shows an example illustration 600 of the interaction framework for the impact model of the digital terrain clusters 300B, according to an embodiment of the present disclosure.As shown in FIG. 6, the method at block 602A may include acquiring a terrain profile by scanning physical terrain clusters based on specific methods. This scanned data is then converted to a Smooth Particle Hydrodynamics (SPH) model to accurately represent the properties of the terrain. At block 604A, the method may include determining vehicle parameters of a physical vehicle using a computer aided design (CAD) model. Subsequently, at block 602B, the method may include generating terrain clusters by SPH particles defined with ear coulomb properties to mimic the behavior of real snow. At block 604B, the method may include creating a model using an automatic net generation for structural analysis (ANSA) preprocessor in which a detailed digital representation of a vehicle, including variants, is created. The vehicle is provided with an initial speed in the digital environment, thereby creating the requirements for dynamic interactions.At block 606, the method may include performing complicated measurements using LS Dyna Solver methods. This approach takes the rears into the hand, simulates the dynamic behavior of the vehicle upon impact, calculates the forces generated, and predicts the damage resulting therefrom. Moreover, the method may include simulating a virtual spring that prevents excessive intrusion of the vehicle into the snowshaft by generating a counteracting compressive force using the LS-Dyna contact method. Further, the method may include generating a d3plot output to encapsulate an entire simulated scenario including forces and damage. At block 608, the method may include converting the d3plot output to captive videos using an Animator postprocessor method. These videos show the impact of the vehicle on the terrain fill and the damage that has occurred. At block 610, the method may include creating a report based on the simulation analysis. Additionally, the method may include improving vehicle design through the use of videos and damage visualizations. The visualized information may improve the design, contributing to optimization of the components and increasing the general durability of the virtual vehicle. The method may also include fine tuning and improving vehicle designs for improved performance, safety, and durability using an iterative cycle of simulation, visualization, and analysis. Blocks 602A- 608 may perform tests in the digital environment prior to manufacturing a real-world vehicle to avoid costs. This cost-saving approach results in improved efficiency and resource allocation.FIG. 7 shows a flow diagram of an example method 700 for predicting damage to a virtual vehicle according to an embodiment of the present disclosure.Referring to FIG. 7, at block 702, the method 700 may include receiving one or more terrain parameters of one or more physical terrain clusters and one or more vehicle parameters. In one embodiment, the one or more vehicle parameters may include a mass, geometric information, material characteristics, occupants, and functional specifications of propulsion components. In some embodiments, the one or more terrain parameters include at least one of the physical properties of the one or more physical terrain clusters and structural information of the one or more physical terrain clusters. At block 704, the method 700 may include converting the one or more terrain parameters to a smoothed particle hydrodynamic model (SPH). At block 706, the method 700 may include determining one or more SPH particles based on the transformation. At block 708, the method 700 may include generating one or more digital terrain clusters in a digital environment using the one or more SPH particles. Further, the method 700 may include determining an outer surface of the one or more digital terrain clusters based on the transformation and assigning physical attributes to each SPH particle of the one or more digital terrain clusters. Further, the method 700 may include simulating the one or more digital terrain clusters based on the physical attributes of each SPH particle and determining a behavior of the one or more digital terrain clusters based on the simulation. At block 710, the method may include generating the virtual vehicle in the digital environment based on the one or more vehicle parameters. At block 712, the method may include performing a collision between the one or more digital terrain clusters and the virtual vehicle. Further, the method 700 may include determining an impact of the surface of a virtual vehicle during the impact and adjusting at least one force of the impact, the one or more terrain parameters, and the one or more vehicle parameters. At block 714, the method may include predicting virtual vehicle damage based on the collision by an artificial intelligence (AI) model.While the foregoing describes various embodiments of the disclosure, other and further embodiments of the invention may be devised without departing from the basic scope of the disclosure. The scope of the disclosure is defined by the following claims. The disclosure is not limited to the described embodiments, versions, or examples included to enable a person of ordinary skill in the art to make and use the disclosure when combined with information and knowledge available to the person of ordinary skill in the art.ADVANTAGES OF THE PRESENT DISCLOSUREThe present disclosure provides a simulation methodology that is unestimately valuable at the early stages of vehicle development because it allows identification of potential problems prior to construction of physical prototypes, thereby reducing the need for extensive hardware testing.The present disclosure provides an early prediction for automotive engineers with a critical time window to make design changes and take countermeasures that aim to mitigate the risks associated with possible damage.The present disclosure enables early detection of hazardous areas, resulting in cost savings since later adaptations of manufacturing methods for parts that could be damaged during real snow impacts are avoided.The present disclosure reduces costs associated with post-changes and minimizes possible damage to bumpers and underbody components, thereby improving the overall quality of the vehicles being delivered.The present publication emphasizes the increasing attractiveness of simulation scenarios promoted by the improved feasibility and accuracy of numerical solution methods.The present disclosure provides a comprehensive and consistent representation of terrain and impact behavior, which allows early damage prediction and increases vehicle development efficiency and quality.The present disclosure provides a system and method that uses complex fusion of particle modelling, smooth particle hydrodynamics (SPH) techniques and thorough analysis that contribute to early detection of damage and potential problems and thereby enable proactive measures for damage prevention.The present disclosure prevents false parts from being manufactured using machine tools in the prototype phase of vehicle hardware and rationalizes the overall development process.References included in the specificationThis list of documents cited by the applicant has been produced in an automated manner and is only included for the better information of the reader. The list is not part of the German patent application or utility model application. The DPMA does not take any adhesion for any faults or omissions.Patent Literature citedUS 2009228246A1

[0003]

Claims

A method (700) of predicting damage to a virtual vehicle, comprising: receiving (702), from one or more processors (104) connected to a system (102), one or more terrain parameters of one or more physical terrain clusters and one or more vehicle parameters; converting (704), by the one or more processors (104), the one or more terrain parameters to a Smooth Particle Hydrodynamics (SPH) model; determining (706), by the one or more processors (104), one or more SPH particles based on the transformation; generating (708), by the one or more processors (104), one or more digital terrain clusters in a digital environment using the one or more SPH particles; Generating (710), by the one or more processors (104), the virtual vehicle in the digital environment based on the one or more vehicle parameters; executing (712), by the one or more processors (104), a collision between the one or more digital terrain clusters and the virtual vehicle; and predicting (714), by the one or more processors (104), damage to the virtual vehicle based on the collision via an artificial intelligence (AI) model.The method (700) of claim 1, wherein the one or more vehicle parameters comprise at least one of mass, geometric information, material properties, occupants, and functional specifications of propulsion components.The method (700) of claim 1, wherein the one or more terrain parameters comprise at least one of physical properties of the one or more physical terrain clusters and structural properties of the one or more physical terrain clusters.The method (700) of claim 1, wherein generating (708), by the one or more processors (104), the one or more digital terrain clusters using the one or more SPH particles comprises: determining, by the one or more processors (104), an outer surface of the one or more digital terrain clusters based on the transformation; assigning physical attributes to each SPH particle of the one or more digital terrain clusters by the one or more processors (104); simulating, by the one or more processors (104), the one or more digital terrain clusters based on the physical attributes of each SPH particle; and determining, by the one or more processors (104), one or more physical properties and one or more structural properties of the one or more digital terrain clusters based on the simulation.The method (700) of claim 4, wherein the physical attributes comprise at least one of the following properties: a material property and geometric information.The method (700) of claim 4, wherein the one or more SPH particles of the one or more digital terrain clusters are at least one of the following: outermost layers, hardest layers, elastic layers, soft layers, medium density layers, and dense layers.The method (700) of claim 1, wherein performing (712) the collision between the one or more digital terrain clusters and the virtual vehicle by the one or more processors (104) comprises: determining, by the one or more processors (104), an impact value of a surface of the virtual vehicle during the collision; providing, by the one or more processors (104), the impact value to a user via a user interface based on the determination; and receiving, by the one or more processors (104), an input from the user to fine tune at least one of: the one or more vehicle parameters of the virtual vehicle, the one or more terrain parameters, and a force of the collision based on the impact value.The method (700) of claim 7, comprising: adjusting, by the one or more processors (104), the one or more virtual vehicle vehicle vehicle parameters, the one or more terrain parameters, and the force of the collision based on the received input.A system (102) for predicting damage to a virtual vehicle, comprising: one or more processors (104); and a memory (106) operatively coupled to the one or more processors (104), the memory (106) comprising one or more instructions that, when executed, cause the one or more processors (104) to: receive one or more terrain parameters of one or more physical terrain clusters and one or more vehicle parameters; convert the one or more terrain parameters to a Smooth Particle Hydrodynamics (SPH) model; determine one or more SPH particles based on the transformation; generate one or more digital terrain clusters in a digital environment using the one or more SPH particles; generating the virtual vehicle in the digital environment based on one or more vehicle parameters; performing a collision between the one or more digital terrain clusters and the virtual vehicle; and predicting damage to the virtual vehicle due to the collision using an artificial intelligence (AI) model.The system (102) of claim 9, wherein the one or more processors (104) set at least one of the one or more virtual vehicle vehicle parameters, the one or more terrain parameters, and a force of the collision based on an impact value of a surface of the virtual vehicle during the collision.

Images