System and method for vehicle modeling
By generating vehicle-specific models and combining physics-based and machine learning methods, the problem that existing vehicle models are difficult to reflect the dynamic behavior and static performance of vehicles on remote computing devices is solved, enabling accurate simulation of fault identification and predictive maintenance, as well as driver assistance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-06
- Publication Date
- 2026-04-03
AI Technical Summary
Existing technologies struggle to effectively utilize integrated vehicle models to provide functions such as accident reconstruction, driver assessment, preventative maintenance, safety-critical control, and driver tactile assistance, especially in reflecting and predicting the dynamic behavior and static performance of vehicle systems on remote computing devices.
By generating vehicle-specific models, combined with physics-based and machine learning-based models, and utilizing remote computing systems for vehicle modeling, the system receives design specifications and line-end characteristics, generates a master model and initial parameters, updates the model to reflect vehicle operating data, identifies potential faults, and provides predictive maintenance and auxiliary functions.
It enables accurate simulation of the dynamic behavior and static performance of vehicle systems on remote computing devices, providing fault identification, predictive maintenance, and driver assistance, and improving the accuracy of accident reconstruction and safety-critical controls.
Smart Images
Figure CN121786982A_ABST
Abstract
Description
[0001] This application is a divisional application of the application filed on May 6, 2021, with application number 202110491878X and invention title "System and Method for Vehicle Modeling". Technical Field
[0002] This disclosure relates to vehicle modeling, and more particularly to generating and maintaining digital vehicle models on cloud-based computing systems. Background Technology
[0003] Vehicles such as cars, trucks, sport utility vehicles, crossovers, minivans, or other suitable vehicles include a variety of components, systems, and features that assist in the operation of the vehicle. For example, such vehicles typically include power steering features such as electric power steering (EPS) systems.
[0004] EPS systems are typically configured to provide steering assistance to the operator and / or autonomous controller of the corresponding vehicle. For example, an EPS system may be configured to apply auxiliary torque to an electric motor connected to the steering mechanism. When the operator interacts with the hand-held steering wheel or steering wheel associated with the steering mechanism, the amount of force or torque applied by the operator to the hand-held steering wheel or steering wheel will be assisted by the electric motor (e.g., reducing the amount of force or torque required for the operator to perform the corresponding steering maneuvers).
[0005] In addition to power steering, such vehicles may include additional features such as autonomous driving features and infotainment features. Typically, these features rely on various sensors, controllers, and / or assistive devices in the operation of the vehicle. These sensors, controllers, and / or other components can generate data corresponding to the various functions and operations of the vehicle. Summary of the Invention
[0006] This disclosure generally pertains to vehicle modeling.
[0007] One aspect of the disclosed embodiments includes a method for vehicle modeling. The method includes receiving one or more design specification features corresponding to a vehicle steering system design, and receiving one or more line-end features of the vehicle steering system including the vehicle steering system design. The method further includes generating a master model of the vehicle steering system design using the one or more design specification features corresponding to the vehicle steering system design, and generating at least one initial parameter using the one or more line-end features of the vehicle steering system. The method further includes generating a vehicle-specific model based on the master model and the at least one initial parameter, and receiving operational data corresponding to the vehicle steering system. The method further includes generating at least one subsequent parameter using the operational data, and updating the vehicle-specific model using the at least one subsequent parameter.
[0008] Another aspect of the disclosed embodiments includes a system for vehicle modeling. The system includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to: receive one or more design specification features corresponding to a vehicle steering system design; receive one or more line-end features of the vehicle steering system including the vehicle steering system design; generate a master model of the vehicle steering system design using the one or more design specification features corresponding to the vehicle steering system design; generate at least one initial parameter using the one or more line-end features of the vehicle steering system; generate a vehicle-specific model based on the master model and the at least one initial parameter; receive operational data corresponding to the vehicle steering system; generate at least one subsequent parameter using the operational data; and update the vehicle-specific model using the at least one subsequent parameter.
[0009] Another aspect of the disclosed embodiments includes a vehicle modeling system. The system includes a processor and a memory, the memory including instructions that, when executed by the processor, cause the processor to: receive a master model including a digital representation of a vehicle category corresponding to a vehicle design; receive one or more line-end characteristics of the vehicle including the vehicle design; generate an initial parameter set using the one or more line-end characteristics of the vehicle; generate a vehicle-specific physics-based model using the master model and the initial parameter set; generate a vehicle-specific machine learning-based model using at least one of the vehicle-specific physics-based model, the master model, and the initial parameter set; update at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning-based model in response to receiving operational data corresponding to the vehicle; and selectively determine the operational behavior of at least one component of the vehicle using at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning model.
[0010] These and other aspects of this disclosure are disclosed in the following detailed description of the embodiments, the appended claims and the accompanying drawings. Attached Figure Description
[0011] This disclosure is best understood by reading in conjunction with the accompanying drawings and through the following detailed description. It should be emphasized that, by convention, the various features in the drawings are not drawn to scale. Instead, for clarity, the dimensions of the various features have been arbitrarily enlarged or reduced.
[0012] Figure 1 A vehicle based on the principles of this disclosure is shown in general.
[0013] Figure 2A and Figure 2B A block diagram of a vehicle modeling system based on the principles of this disclosure is shown in general.
[0014] Figure 3A block diagram of a specific vehicle model based on the principles of this disclosure is shown in general.
[0015] Figure 4 The physics-based portion of a specific vehicle model, based on the principles of this disclosure, is shown in general.
[0016] Figure 5 A flowchart is provided to generally illustrate a vehicle modeling method based on the principles of this disclosure. Detailed Implementation
[0017] The following discussion pertains to various embodiments of this disclosure. While one or more of these embodiments may be preferred, the disclosed embodiments should not be construed as or otherwise used to limit the scope of this disclosure, including the claims. Furthermore, those skilled in the art will understand that the following description has broad application, and the discussion of any embodiment is intended only as an illustrative discussion of that embodiment and not to imply that the scope of this disclosure, including the claims, is limited to that embodiment.
[0018] As described above, vehicles such as automobiles, trucks, sport utility vehicles, crossovers, minivans, or other suitable vehicles include a variety of components, systems, and features that assist in the operation of the vehicle. For example, such vehicles typically include power steering features such as electric power steering (EPS) systems.
[0019] EPS systems are typically configured to provide steering assistance to the operator and / or autonomous controller of the corresponding vehicle. For example, an EPS system may be configured to apply auxiliary torque to an electric motor connected to the steering mechanism. When the operator interacts with the hand-held steering wheel or steering wheel associated with the steering mechanism, the amount of force or torque applied by the operator to the hand-held steering wheel or steering wheel will be assisted by the electric motor (e.g., reducing the amount of force or torque required for the operator to perform the corresponding steering maneuvers).
[0020] In addition to power steering, such vehicles may include additional features such as autonomous driving features and infotainment features. Typically, these features rely on various sensors, controllers, and / or assistive devices in the operation of the vehicle. These sensors, controllers, and / or other components can generate data corresponding to the various functions and operations of the vehicle.
[0021] The need to analyze this data is increasing for accident reconstruction, driver assessment, preventative maintenance, redundancy handling of safety-critical controls, driver tactile assistance, other data-driven functions, or combinations thereof. Therefore, systems and methods such as those described herein may be desired, configured to use an integrated vehicle model to provide accident reconstruction, driver assessment, preventative maintenance information, redundancy handling of safety-critical controls, driver tactile or other assistance, other data-driven functions, or combinations thereof, whereby the integrated vehicle model is configured to provide driver and vehicle behavior prediction information, system and / or driver response information, other data-driven information, or combinations thereof.
[0022] In some embodiments, the systems and methods described herein may be configured to provide a vehicle model (e.g., which may be referred to as a digital twin of the vehicle) stored on and processed on a remote computing device (e.g., a cloud server or other suitable remote computing device). The vehicle model may reflect the static performance and / or dynamic behavior of the vehicle and its subsystems.
[0023] In some embodiments, the systems and methods described herein may be configured to receive inputs from a vehicle driver (e.g., steering torque and / or other suitable inputs) from vehicle systems (e.g., steering system, chassis system, other vehicle systems, etc.) and / or from sensors configured to sense the vehicle's environment (e.g., road surface information or other suitable inputs indicating environmental characteristics). The systems and methods described herein may be configured to receive outputs from vehicle systems (e.g., yaw values, acceleration values, other suitable outputs, or combinations thereof) as well as engineering data, production data, warranty data, and usage data (e.g., during vehicle operation or other post-production use). The systems and methods described herein may be configured to use inputs and / or outputs to provide predictions of: system failures, maintenance requirements, driver competence information and driver assistance recommendations, accident reconstruction information (e.g., after an accident), vehicle and / or system responses to inputs (e.g., estimated or predicted yaw values, acceleration values, other suitable estimated or predicted outputs, or combinations thereof), other suitable information, or combinations thereof.
[0024] In some embodiments, the systems and methods described herein may be configured to provide predictions of system failures, maintenance requirements, driver capability information and driver assistance recommendations, accident reconstruction information (e.g., after an accident), vehicle and / or system responses to inputs (e.g., estimated or predicted yaw values, acceleration values, other suitable estimated or predicted outputs, or combinations thereof), other suitable information, or combinations thereof, by predicting system behavior and / or by comparing expected system behavior with actual system behavior. The systems and methods described herein may also be configured to provide operator state detection (e.g., sleeping or inattentive), prediction of potential failures or malfunctions, maintenance recommendations, navigation directions, object avoidance, etc.
[0025] In some embodiments, the systems and methods described herein can be configured to generate a master vehicle model corresponding to a vehicle category associated with the vehicle (e.g., vehicle type, vehicle production model, etc.) and / or a category corresponding to one or more subsystems of the vehicle (e.g., vehicle steering system, vehicle autonomous control system, etc.). The systems and methods described herein can receive data from engineering and design systems (e.g., engineering specifications corresponding to the vehicle and / or its subsystems) and / or end-of-line data (e.g., data from systems during the manufacturing of the vehicle and / or its subsystems). The systems and methods described herein can be configured to generate a master vehicle model representing the vehicle category and / or the category of one or more vehicle subsystems.
[0026] In some embodiments, the systems and methods described herein can be configured to identify a set of parameters (e.g., which may be referred to as a signature) for a particular vehicle. The parameter set can represent each system and / or subsystem in the vehicle. For example, the systems and methods described herein can receive data from various sensors of the vehicle and can generate a set of parameters indicative of various measurements, component details, vehicle usage, other suitable information, or combinations thereof. The systems and methods described herein can be configured to generate a vehicle-specific model using a master vehicle model and a parameter set corresponding to the vehicle. The systems and methods described herein can be configured to generate multiple parameter sets corresponding to a specific vehicle. The systems and methods described herein can be configured to generate a vehicle-specific model for each specific vehicle using a master model and some of the corresponding parameter sets.
[0027] In some embodiments, the systems and methods described herein can be configured to generate vehicle-specific models comprising one or more constituent models. For example, the vehicle-specific model may include physics-based models and / or machine learning models to improve the predictive accuracy of the vehicle-specific model. In some embodiments, the systems and methods described herein may be triggered by driver input and / or loads on the vehicle. The systems and methods described herein can be configured to measure the vehicle response and compare the measured vehicle response with the expected vehicle response via computation on a remote computing device. The systems and methods described herein can be configured to use the difference between the predicted vehicle response and the measured vehicle response to identify specific failure models (e.g., tire wear, friction in the steering gear, etc.).
[0028] In some embodiments, the systems and methods described herein may be configured to use a vehicle controller (e.g., such as an electronic control unit) to modify the trigger points of a vehicle-specific model to simulate frequency scanning, thereby generating a fingerprint of a specific fault model (e.g., for high friction in gears).
[0029] In some embodiments, the systems and methods described herein can be configured to enable over-the-air system maintenance (e.g., without hardware replacement) using a vehicle-specific model via parameter updates. For example, the systems and methods described herein can be configured to correct faults (e.g., increased friction in steering gears or other suitable faults) using an over-the-air updated set of parameters. The systems and methods described herein can be configured to generate an update to the signature of the faulty system on a remote computing device. In some embodiments, the systems and methods described herein can be configured to generate a vehicle-specific model that includes at least a power steering model and a lateral vehicle dynamics model.
[0030] In some embodiments, the systems and methods described herein may be configured to receive one or more design specification characteristics corresponding to a vehicle steering system design. The systems and methods described herein may be configured to receive one or more line-end characteristics of a vehicle steering system including the vehicle steering system design. The systems and methods described herein may be configured to generate a master model of the vehicle steering system design using one or more design specification characteristics corresponding to the vehicle steering system design. In some embodiments, the master model includes a digital representation of a vehicle steering system category corresponding to the vehicle steering system design.
[0031] In some embodiments, the systems and methods described herein can be configured to generate at least one initial parameter using one or more line-end characteristics of the vehicle steering system. The systems and methods described herein can be configured to generate a vehicle-specific model based on a master model and at least one initial parameter. In some embodiments, the vehicle-specific model includes at least a digital representation of the vehicle steering system. In some embodiments, the vehicle-specific model includes a first constituent model and a second constituent model. The first constituent model may include a physics-based representation of the vehicle steering system. The second constituent model may include a machine learning-based representation of the vehicle steering system. In some embodiments, the master model and the vehicle-specific model are stored on a computing device located remotely from the vehicle steering system.
[0032] In some embodiments, the systems and methods described herein may be configured to receive operational data corresponding to a vehicle steering system. In some embodiments, the operational data includes at least vehicle sensor data indicating one or more measurements of the vehicle steering system during operation of the vehicle corresponding to the vehicle steering system. The systems and methods described herein may be configured to generate at least one subsequent parameter using the operational data. The systems and methods described herein may be configured to update a vehicle-specific model using at least one subsequent parameter.
[0033] In some embodiments, the systems and methods described herein may be configured to use a vehicle-specific model to identify potential faults in a vehicle steering system. In some embodiments, the systems and methods described herein may be configured to use a vehicle-specific model to identify at least one characteristic of a maneuver previously performed by the vehicle steering system. In some embodiments, the systems and methods described herein may be configured to receive steering system input and use a vehicle-specific model to determine the future response of the vehicle steering system to the steering system input.
[0034] In some embodiments, the systems and methods described herein may be configured to receive a master model, which includes a digital representation of a vehicle category corresponding to a vehicle design. The systems and methods described herein may be configured to receive one or more line-end characteristics of a vehicle, including the vehicle design. The systems and methods described herein may be configured to generate an initial parameter set using one or more line-end characteristics of the vehicle. The systems and methods described herein may be configured to generate a vehicle-specific physics-based model using the master model and the initial parameter set. The systems and methods described herein may be configured to generate a vehicle-specific machine learning-based model using at least one of the vehicle-specific physics-based model, the master model, and the initial parameter set. The systems and methods described herein may be configured to update at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning-based model in response to receiving operational data corresponding to the vehicle. The systems and methods described herein may be configured to selectively determine the operational behavior of at least one component of the vehicle using at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning model.
[0035] Figure 1 Vehicle 10, generally illustrated according to the principles of this disclosure, is shown. Vehicle 10 may include any suitable vehicle, such as a car, truck, SUV, minivan, crossover, any other passenger vehicle, any suitable commercial vehicle, or any other suitable vehicle. Although vehicle 10 is illustrated as a passenger vehicle with wheels and used on a road, the principles of this disclosure can be applied to other means of transportation, such as airplanes, ships, trains, drones, or other suitable vehicles.
[0036] Vehicle 10 includes a body 12 and an engine hood 14. A passenger compartment 18 is defined at least partially by the body 12. Another portion of the body 12 defines an engine compartment 20. The engine hood 14 is movably attached to a portion of the body 12 such that when the engine hood 14 is in a first position or an open position, the engine hood 14 provides access to the engine compartment 20, and when the engine hood 14 is in a second position or a closed position, the engine hood 14 covers the engine compartment 20. In some embodiments, the engine compartment 20 may be located at the rear of vehicle 10 (as opposed to what is typically shown).
[0037] The passenger compartment 18 may be located behind the engine compartment 20, but in embodiments where the engine compartment 20 is located in the rear portion of the vehicle 10, the passenger compartment 18 may be located in front of the engine compartment 20. The vehicle 10 may include any suitable propulsion system, including an internal combustion engine, one or more electric motors (e.g., an electric vehicle), one or more fuel cells, a hybrid propulsion system including a combination of an internal combustion engine and one or more electric motors (e.g., a hybrid vehicle), and / or any other suitable propulsion system.
[0038] In some embodiments, vehicle 10 may include a gasoline engine or a gasoline-fueled engine, such as a spark-ignition engine. In some embodiments, vehicle 10 may include a diesel-fueled engine, such as a compression-ignition engine. Engine compartment 20 houses and / or surrounds at least some components of the propulsion system of vehicle 10. Additionally or optionally, propulsion control devices (e.g., accelerator actuators, brake actuators, steering wheel, and other such components) are disposed in passenger compartment 18 of vehicle 10. The propulsion control devices may be actuated or controlled by the driver of vehicle 10 and may be directly connected to corresponding components of the propulsion system, such as throttle, brakes, axles, vehicle transmission, etc. In some embodiments, the propulsion control devices may transmit signals to a vehicle computer (e.g., drive-by-wire), which in turn may control the corresponding propulsion components of the propulsion system. Thus, in some embodiments, vehicle 10 may be an autonomous vehicle.
[0039] In some embodiments, vehicle 10 includes a transmission that communicates with the crankshaft via a flywheel, clutch, or hydraulic coupling. In some embodiments, the transmission includes a manual transmission. In some embodiments, the transmission includes an automatic transmission. In the case of an internal combustion engine or hybrid vehicle, vehicle 10 may include one or more pistons that cooperate with the crankshaft to generate force, which is transmitted through the transmission to one or more shafts, causing wheels 22 to rotate. When vehicle 10 includes one or more electric motors, a vehicle battery and / or fuel cell provides energy to the electric motors to rotate the wheels 22.
[0040] Vehicle 10 may include an automated vehicle propulsion system, such as cruise control, adaptive cruise control, automatic braking control, other automated vehicle propulsion systems, or combinations thereof. Vehicle 10 may be an automated or semi-automated vehicle, or other suitable type of vehicle. Vehicle 10 may include additional or fewer features compared to those generally shown and / or disclosed herein.
[0041] In some embodiments, vehicle 10 may include an Ethernet component 24, a controller area network (CAN) bus 26, a media-oriented system transport component (MOST) 28, a FlexRay component 30 (e.g., a brake-by-wire system), and a local interconnect component (LIN) 32. Vehicle 10 may use the CAN bus 26, MOST 28, FlexRay component 30, LIN 32, other suitable network or communication systems, or combinations thereof, to transmit various information from, for example, sensors inside or outside the vehicle, to, for example, various processors or controllers inside or outside the vehicle. Vehicle 10 may include additional or fewer features compared to those generally shown and / or disclosed herein.
[0042] Figure 2A and Figure 2B A block diagram of a vehicle modeling system 100 according to the principles of this disclosure is generally shown. System 100 may include a computing device 102 and a remote computing system 110. In some embodiments, system 100 may include two or more computing devices and may communicate with two or more remote computing systems. Remote computing system 110 may include any suitable remote computing system, such as a cloud computing system comprising one or more servers located in a respective data center or any suitable remote computing system.
[0043] The computing device 102 may include any suitable computing device, including a desktop computer, laptop computer, mobile computing device, or any suitable computing device. In some embodiments, the computing device 102 may communicate with a remote computing system. For example, the computing device 102 may be located remotely from the remote computing system 110 and may at least store one or more vehicle models configured to represent one or more corresponding vehicles. Additionally or alternatively, the computing device 102 may be located adjacent to or within the remote computing system 110.
[0044] The computing device 102 may include a processor 104 and a memory 106, generally as follows: Figure 2B As shown. Processor 104 may include any suitable processor, such as those described herein. Additionally or alternatively, computing device 102 may include any suitable number of processors in addition to or excluding processor 104. Memory 106 may include a single disk or multiple disks (e.g., hard disk drives) and includes a storage management module that manages one or more partitions within memory 106. In some embodiments, memory 106 may include flash memory, semiconductor (solid-state) memory, etc. Memory 106 may include random access memory (RAM), read-only memory (ROM), or a combination thereof. Memory 106 may include instructions that, when executed by processor 104, cause processor 104 to perform at least the functions associated with the systems and methods described herein.
[0045] In some embodiments, computing device 102 may be configured to provide predictions of: system failures, maintenance requirements, driver capability information and driver assistance recommendations, accident reconstruction information (e.g., after an accident), vehicle and / or system responses to inputs (e.g., estimated or predicted yaw values, acceleration values, other suitable estimated or predicted outputs or combinations thereof), other suitable information or combinations thereof.
[0046] The computing device 102 may receive one or more design specification characteristics corresponding to the vehicle steering system design and / or other systems of the vehicle category subsystem corresponding to vehicle 10. For example, the computing device 102 may receive input indicating engineering and / or design information corresponding to the engineering and / or design specifications of the vehicle category corresponding to vehicle 10 and / or other vehicles 10-1 to 10-N. Vehicles 10-1 to 10-N may include features similar to or different from vehicle 10. The engineering and / or design information may include engineering tolerances of the vehicle steering system design and / or other systems or subsystems of vehicle 10, component model or specifications, component dimensions (e.g., weight, length, width, depth, etc.), component characteristics (e.g., functions that various components are capable of performing), sensor locations, controller types, any other suitable engineering and design specifications or combinations thereof. Additionally or alternatively, one or more design specification characteristics may include warranty information, sales information, safety feature information, recall information, other suitable information, or combinations thereof corresponding to the vehicle steering system and / or system or subsystem category of the vehicle category. It should be understood that vehicle 10 and vehicles 10-1 to 10-N may belong to the same or different vehicle categories or be associated with the same or different vehicle categories, and may include the same or different vehicle steering system categories.
[0047] In some embodiments, computing device 102 may receive one or more line-end characteristics of the vehicle steering system and / or other subsystems or systems of vehicle 10, including the vehicle steering system design. Line-end characteristics may include actual manufactured components used during the production of the vehicle steering system, the category of the vehicle steering system, vehicle 10, and / or the vehicle category corresponding to vehicle 10. Additionally or alternatively, line-end characteristics may include production measurements of the vehicle steering system, the category of the vehicle steering system, vehicle 10, and / or the vehicle category corresponding to vehicle 10, production tolerances, other suitable production information, or combinations thereof.
[0048] In some embodiments, computing device 102 may use one or more design specification features to generate a main vehicle model of the vehicle steering system design, the vehicle category associated with vehicle 10, and / or the vehicle categories corresponding to vehicles 10-1 to 10-N. Additionally or alternatively, computing device 102 may use one or more design specification features and one or more line-end features to generate a main vehicle model of the vehicle steering system design, the vehicle category associated with vehicle 10, and / or the vehicle categories corresponding to vehicles 10-1 to 10-N. For example, computing device 102 may generate a main vehicle model 120 corresponding to the vehicle steering system design (e.g., the vehicle steering system category corresponding to the vehicle steering systems of vehicles 10 and / or vehicles 10-1 to 10-N). In some embodiments, computing device 102 may retrieve or receive the main vehicle model from another computing device, vehicle 10 and / or vehicles 10-1 to 10-N, any other suitable location, or a combination thereof.
[0049] The main vehicle model 120 may include a vehicle steering system design, a vehicle category associated with vehicle 10, and / or a digital representation of the vehicle categories corresponding to vehicles 10-1 to 10-N. The computing device 102 may store the main vehicle model 120 on a remote computing system 110. Additionally or alternatively, the computing device 102 may store the main vehicle model 120 in the memory of the corresponding vehicle 10 or vehicles 10-1 to 10-N.
[0050] In some embodiments, computing device 102 may use one or more line-end characteristics of the vehicle steering system, vehicle 10, and / or vehicles 10-1 to 10-N to generate at least one initial parameter or parameter set (e.g., a signature). For example, computing device 102 may generate a parameter set 122 corresponding to the vehicle steering system of vehicle 10. Computing device 102 may generate one or more parameter sets 122-1 to 122-N respectively corresponding to vehicles 10-1 to 10-N. Parameter set 122 may include values such as numeric strings or other suitable values. Parameter set 122 may represent system or component information specific to the vehicle steering system of vehicle 10. It should be understood that computing device 102 may generate parameter sets corresponding to vehicle 10 and / or other components, systems, or subsystems of vehicle 10.
[0051] In some embodiments, computing device 102 may receive operational data corresponding to the vehicle steering system, vehicle 10, and / or vehicles 10-1 to 10-N. The operational data may include vehicle sensor data indicating one or more measurements of the vehicle steering system, vehicle 10, and / or vehicles 10-1 to 10-N during operation. For example, the operational data may include sensor data indicating hand-grip steering wheel friction, wheel angles corresponding to applied hand-grip steering wheel torque, other suitable measurements of the vehicle steering system, or combinations thereof. It should be understood that computing device 102 may receive any suitable operational data corresponding to any system or subsystem of vehicle 10 and / or vehicles 10-1 to 10-N.
[0052] In some embodiments, computing device 102 may generate at least one subsequent parameter based on operating data. For example, computing device 102 may generate parameters or parameter sets that indicate measurement results and / or other information corresponding to the operating data. Computing device 102 may use at least one subsequent parameter or parameter set to update parameter set 122. In some embodiments, computing device 102 may continuously or periodically receive operating data and may continuously or periodically update parameter set 122 based on the operating data. It should be understood that computing device 102 may update parameter sets 122-1 to 122-N based on the received corresponding operating data.
[0053] In some embodiments, the computing device 102 can generate a vehicle-specific model based on the main vehicle model 120 and the parameter set 122, for example... Figure 3 The vehicle-specific model 200 is generally shown in the diagram. The vehicle-specific model 200 may include nominal design data (e.g., computer-aided design data) 202, as-built data (e.g., digital tracking data) 204, and data in use 206. The nominal design data 202 may correspond to one or more design specification characteristics. The as-built data may correspond to one or more line-end characteristics. The data in use 206 may correspond to operational data. In some embodiments, the computing device 102 may retrieve or receive the vehicle-specific model from another computing device, vehicle 10 and / or vehicles 10-1 to 10-N, any other suitable location, or a combination thereof.
[0054] The vehicle-specific model may include a first constituent model 208. The first constituent model 208 may include a physics-based model, such as... Figure 4As generally shown. The first configuration model 208 can receive nominal design data 202, as-built data 204, in-use data 206, any other suitable data, or combinations thereof. The computing device 102 can use the nominal design data 202, as-built data 204, in-use data 206, any other suitable data, or combinations thereof to generate the first configuration model 208. The first configuration model 208 can represent physical aspects of the vehicle steering system (e.g., and / or vehicle 10 and vehicles 10-1 to 10-N). For example, the first configuration model 208 can represent wheel angles, tire lateral slip, vehicle heading angle, vehicle yaw rate, other suitable physical aspects of the vehicle steering system (e.g., and / or vehicle 10 and vehicles 10-1 to 10-N), or combinations thereof.
[0055] In some embodiments, the vehicle-specific model 200 includes a second constituent model 210. It should be understood that the vehicle-specific model 200 may include only the first constituent model 208, only the second constituent model 210, both the first and second constituent models 208 and 210, additional constituent models, or any combination of the first constituent model 208, the second constituent model 210, and any additional suitable constituent models. The second constituent model 210 may include a machine learning-based model. The second constituent model 210 may be trained using any suitable data corresponding to the vehicle steering system design, vehicle categories corresponding to vehicles 10, 10-1, and 10-N, the vehicle steering system, vehicle 10, vehicles 10-1 to 10-N, any other suitable data, or combinations thereof. The second constituent model 210 may receive data 206 in use and / or any other suitable data.
[0056] In some embodiments, the first configuration model 208 and / or the second configuration model 210 receive inputs (e.g., steering torque and / or other suitable inputs) corresponding to the vehicle steering system and / or any suitable system or subsystem (e.g., steering system, chassis system, other vehicle systems, etc.) of the vehicle 10. The inputs may be generated by the driver of the vehicle 10 and / or by sensors configured to sense the environment of the vehicle 10 (e.g., road surface information or other suitable inputs indicating environmental characteristics).
[0057] In some embodiments, the first configuration model 208 and / or the second configuration model 210 receive outputs from sensors of the vehicle 10 (e.g., yaw values, acceleration values, other suitable outputs, or combinations thereof). The first configuration model 208 may determine one or more intermediate outputs (e.g., rack force or other suitable outputs). The first configuration model 208 may communicate one or more intermediate outputs to the second configuration model 210. The second configuration model 210 may analyze one or more intermediate outputs and / or the data 206 in use, and may generate one or more predicted parameters (e.g., the current tire radius) or the response of the vehicle steering system (e.g., or the response of the vehicle 10 and / or the vehicle 10-1 to 10-N). The second configuration model 210 may update the parameter set 122 based on the predicted parameters or response. The second configuration model 210 may communicate the updated parameter set 122 to the first configuration model 208.
[0058] In some embodiments, computing device 102 may use inputs from and / or outputs from the first constituent model 208 and / or the second constituent model 210 to provide output 212. Output 212 may include predictions of: system faults, maintenance requirements, driver capability information, driver assistance recommendations, accident reconstruction information (e.g., after an accident), vehicle and / or system responses to inputs (e.g., estimated or predicted yaw values, acceleration values, other suitable estimated or predicted outputs, or combinations thereof), vehicle and environmental estimates (e.g., mu from the first constituent model 208), vehicle and environmental estimates from the second constituent model 210, diagnostics or fault detection, other suitable information, or combinations thereof. Vehicle-specific model 200 may include data fusion module 214. Data fusion module 214 may be configured to perform data fusion on vehicle and environmental estimates from the first constituent model 208 and vehicle and environmental estimates from the second constituent model 210. The data fusion module 214 can be configured to perform data fusion on any other suitable output of the first constituent model 208 and the second constituent model 210.
[0059] In some embodiments, the computing device 102 may use inputs to and / or outputs from the first configuration model 208 and / or the second configuration model 210 to identify potential faults in the vehicle steering system. In some embodiments, the computing device 102 may use inputs to and / or outputs from the first configuration model 208 and / or the second configuration model 210 to identify at least one characteristic of a maneuver previously performed by the vehicle steering system. In some embodiments, the computing device 102 may receive steering system inputs and use the inputs to and / or outputs from the first configuration model 208 and / or the second configuration model 210 to determine the future response of the vehicle steering system to the steering system inputs. It should be understood that the computing device 102 may generate any suitable outputs, including any suitable predictions, estimates, accident reconstruction information, driving state or response information, any other suitable outputs or information, or combinations thereof.
[0060] In some embodiments, system 100 and / or computing device 102 may perform the methods described herein. However, the methods performed by system 100 and / or computing device 102 as described herein are not intended to be limiting, and therefore any type of software executing on a controller can perform the methods described herein without departing from the scope of this disclosure. For example, a controller (e.g., a processor executing software within a computing device) may perform the methods described herein.
[0061] Figure 5 This is a flowchart generally illustrating a vehicle modeling method 300 according to the principles of this disclosure. At 302, method 300 receives one or more design specification characteristics corresponding to a vehicle steering system design. For example, computing device 102 receives one or more design specification characteristics corresponding to a vehicle steering system design.
[0062] At 304, method 300 receives one or more line-end characteristics of a vehicle steering system, including the vehicle steering system design. For example, computing device 102 receives one or more line-end characteristics of a vehicle steering system corresponding to the vehicle steering system design.
[0063] At 306, method 300 uses one or more design specification features to generate a master model of the vehicle steering system design. For example, computing device 102 uses one or more design specification features and / or one or more line-end features to generate a master vehicle model 120 of the vehicle steering system design.
[0064] At 308, method 300 uses one or more line-end characteristics to generate at least one initial parameter. For example, computing device 102 uses one or more line-end characteristics to generate at least one initial parameter. Computing device 102 can use at least one initial parameter to generate parameter set 122.
[0065] At 310, method 300 generates a vehicle-specific model based on the master model and at least one initial parameter. For example, computing device 102 generates a vehicle-specific model 200 based on master vehicle model 120 and parameter set 122.
[0066] At 312, method 300 receives operating data corresponding to the vehicle steering system. For example, computing device 102 receives operating data corresponding to the vehicle steering system (e.g., data 206 in use).
[0067] At 314, method 300 uses runtime data to generate at least one subsequent parameter. For example, computing device 102 uses runtime data (e.g., data 206 in use) to generate at least one subsequent parameter. Computing device 102 can use at least one subsequent parameter to update parameter set 122.
[0068] At 316, method 300 updates the vehicle-specific model using at least one subsequent parameter. For example, computing device 102 updates vehicle-specific model 200 using the updated parameter set 122.
[0069] At 318, method 300 selectively predicts vehicle characteristics based on a vehicle-specific model. For example, computing device 102 may use vehicle-specific model 200 to selectively predict system failures, maintenance requirements, driver competence information and driver assistance recommendations, accident reconstruction information (e.g., after an accident), vehicle and / or system responses (e.g., estimated or predicted yaw values, acceleration values, other suitable estimates or predictions, or combinations thereof), other suitable vehicle characteristic predictions, or combinations thereof.
[0070] In some embodiments, a method for vehicle modeling includes: receiving one or more design specification features corresponding to a vehicle steering system design, and receiving one or more line-end features of the vehicle steering system including the vehicle steering system design. The method further includes: generating a master model of the vehicle steering system design using the one or more design specification features corresponding to the vehicle steering system design, and generating at least one initial parameter using the one or more line-end features of the vehicle steering system. The method further includes: generating a vehicle-specific model based on the master model and the at least one initial parameter, and receiving operational data corresponding to the vehicle steering system. The method further includes: generating at least one subsequent parameter using the operational data, and updating the vehicle-specific model using the at least one subsequent parameter.
[0071] In some embodiments, operational data includes at least vehicle sensor data indicating one or more measurements of the vehicle steering system during vehicle operation corresponding to the vehicle steering system. In some embodiments, the master model includes a digital representation of a vehicle steering system category corresponding to the vehicle steering system design. In some embodiments, the vehicle-specific model includes at least a digital representation of the vehicle steering system. In some embodiments, the vehicle-specific model includes a first constituent model and a second constituent model, wherein the first constituent model includes a physics-based representation of the vehicle steering system, and wherein the second constituent model includes a machine learning-based representation of the vehicle steering system.
[0072] In some embodiments, the method further includes: identifying potential faults in the vehicle steering system using at least one of a first compositional model and a second compositional model. In some embodiments, the method further includes: generating accident reconstruction information using at least the first compositional model. In some embodiments, the method further includes: receiving steering system input and predicting the future response of the vehicle steering system to the steering system input using at least the second compositional model.
[0073] In some embodiments, the method further includes: identifying potential faults in the vehicle steering system using a vehicle-specific model. In some embodiments, the method further includes: identifying at least one characteristic of a maneuver previously performed by the vehicle steering system using a vehicle-specific model. In some embodiments, the master model and the vehicle-specific model are stored on a computing device located remotely from the vehicle steering system. In some embodiments, the method further includes: receiving steering system input and determining the future response of the vehicle steering system to the steering system input using the vehicle-specific model.
[0074] In some embodiments, a system for vehicle modeling includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to: receive one or more design specification features corresponding to a vehicle steering system design; receive one or more line-end features of the vehicle steering system including the vehicle steering system design; generate a master model of the vehicle steering system design using the one or more design specification features corresponding to the vehicle steering system design; generate at least one initial parameter using the one or more line-end features of the vehicle steering system; generate a vehicle-specific model based on the master model and the at least one initial parameter; receive operational data corresponding to the vehicle steering system; generate at least one subsequent parameter using the operational data; and update the vehicle-specific model using the at least one subsequent parameter.
[0075] In some embodiments, the operational data includes at least vehicle sensor data indicating one or more measurements of the vehicle steering system during vehicle operation corresponding to the vehicle steering system. In some embodiments, the master model includes a digital representation of a vehicle steering system category corresponding to the vehicle steering system design. In some embodiments, the vehicle-specific model includes at least a digital representation of the vehicle steering system. In some embodiments, the vehicle-specific model includes a first constituent model and a second constituent model, wherein the first constituent model includes a physics-based representation of the vehicle steering system, and wherein the second constituent model includes a machine learning-based representation of the vehicle steering system. In some embodiments, the instructions further instruct the processor to: identify potential faults in the vehicle steering system using the vehicle-specific model. In some embodiments, the instructions further instruct the processor to: identify at least one characteristic of a maneuver previously performed by the vehicle steering system using the vehicle-specific model. In some embodiments, the master model and the vehicle-specific model are stored on a computing device located remotely from the vehicle steering system. In some embodiments, the instructions further instruct the processor to: receive steering system inputs and determine the future response of the vehicle steering system to the steering system inputs using the vehicle-specific model.
[0076] In some embodiments, a vehicle modeling system includes a processor and a memory, the memory including instructions that, when executed by the processor, cause the processor to: receive a master model including a digital representation of a vehicle category corresponding to a vehicle design; receive one or more line-end characteristics of the vehicle including the vehicle design; generate an initial parameter set using the one or more line-end characteristics of the vehicle; generate a vehicle-specific physics-based model using the master model and the initial parameter set; generate a vehicle-specific machine learning-based model using at least one of the vehicle-specific physics-based model, the master model, and the initial parameter set; update at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning-based model in response to receiving operational data corresponding to the vehicle; and selectively determine the operational behavior of at least one component of the vehicle using at least one of the vehicle-specific physics-based model and the vehicle-specific machine learning model.
[0077] In some embodiments, at least one component of the vehicle includes a vehicle steering system.
[0078] The foregoing discussion is intended to illustrate the principles and various embodiments of the invention. Once the foregoing disclosure is fully understood, many variations and modifications will become apparent to those skilled in the art. The following claims are intended to be construed as encompassing all such variations and modifications.
[0079] The word “example” is used herein to mean used as an example, illustration, or description. Any aspect or design described herein as an “example” is not necessarily to be construed as being more preferred or advantageous than other aspects or designs. Rather, the use of the word “example” is intended to present a concept in a specific manner. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise stated or clearly apparent from the context, “X comprises A or B” is intended to mean any natural inclusion. That is, if X comprises A; X comprises B; or X comprises both A and B, then “X comprises A or B” is satisfied in any of the foregoing cases. Additionally, the article “a / an” used in this application and the appended claims should generally be interpreted as meaning “one or more” unless otherwise stated or clearly apparent from the context to the singular form. Furthermore, unless so described, the use of the terms “implementation” or “an embodiment” throughout the document is not intended to refer to the same embodiment or implementation.
[0080] The systems, algorithms, methods, and instructions described herein can be implemented in hardware, software, or any combination thereof. Hardware may include, for example, a computer, intellectual property (IP) core, application-specific integrated circuit (ASIC), programmable logic array, optical processor, programmable logic controller, microcode, microcontroller, server, microprocessor, digital signal processor, or any other suitable circuit. In the claims, the term "processor" should be understood to include any of the foregoing hardware, individually or in combination. The terms "signal" and "data" are used interchangeably.
[0081] As used herein, the term "module" can include a packaged functional hardware unit designed for use with other components, a set of instructions executable by a controller (e.g., a processor executing software or firmware), processing circuitry configured to perform a specific function, and self-contained hardware or software components that interface with a larger system. For example, a module can include an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), circuitry, digital logic circuitry, analog circuitry, a combination of discrete circuitry, gate circuits, and other types of hardware or combinations thereof. In other embodiments, the system may include a memory storing instructions executable by the controller to implement the features of the module.
[0082] Furthermore, in one respect, for example, the system described herein can be implemented using a general-purpose computer or general-purpose processor with a computer program that, when executed, performs any of the corresponding methods, algorithms, and / or instructions described herein. Additionally or alternatively, for example, a special-purpose computer / processor may be utilized, which may contain additional hardware for performing any of the methods, algorithms, or instructions described herein.
[0083] Furthermore, all or part of the embodiments of this disclosure may take the form of a computer program product accessible from, for example, a computer-usable or computer-readable medium. A computer-usable or computer-readable medium may be, for example, any means that can tangibly contain, store, communicate, or transmit a program for use by or in connection with any processor. The medium may be, for example, an electrical, magnetic, optical, electromagnetic, or semiconductor device. Other suitable media may also be used.
[0084] The embodiments, implementations, and aspects described above are intended to allow for an easy understanding of the invention and do not limit this disclosure. Rather, the invention is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which should be given the broadest interpretation to cover all such modifications and equivalent structures permitted by law.
Claims
1. A method for vehicle modeling, the method comprising: Receive one or more design specification characteristics corresponding to the vehicle steering system design; Receive one or more line-end characteristics of a vehicle steering system including the design of the vehicle steering system, wherein the one or more line-end characteristics include one or more design characteristics of at least one actual manufactured component used in the manufacturing process associated with the vehicle steering system, and wherein the vehicle steering system includes an electric power steering system. The master model of the vehicle steering system design is generated using one or more design specification characteristics corresponding to the vehicle steering system design. At least one initial parameter is generated using one or more line-end characteristics of the vehicle steering system; A vehicle-specific model is generated based on the master model and the at least one initial parameter, wherein the vehicle-specific model includes a first constituent model and a second constituent model; Receive operational data corresponding to the vehicle steering system, wherein the operational data includes at least steering system input data and vehicle sensor data, the vehicle sensor data indicating one or more measurements of the vehicle steering system in response to the steering system input data during the operation of the vehicle after the vehicle associated with the vehicle steering system has exited the manufacturing process, wherein the vehicle sensor data corresponds to the actual response of the vehicle steering system to the steering system input data; The vehicle-specific model is updated using at least one subsequent parameter, which is generated using the operational data, wherein the vehicle-specific model includes nominal design data corresponding to one or more design specification characteristics corresponding to the vehicle steering system design, completion data corresponding to one or more line end characteristics, and data in use corresponding to the operational data; Using the first constitutive model, intermediate data is generated based on the steering system input data and the vehicle sensor data, wherein the intermediate data indicates the predicted response of the vehicle steering system to the steering system input data; and Using the second constitutive model, a potential fault in the vehicle steering system is predicted, based at least on a comparison of vehicle sensor data corresponding to the actual response of the vehicle steering system to the steering system input data and intermediate data indicating the predicted response of the vehicle steering system to the steering system input data, wherein the potential fault is associated with the future condition of the vehicle steering system.
2. The method according to claim 1, wherein, The master model includes a digital representation of the vehicle steering system category corresponding to the vehicle steering system design.
3. The method according to claim 1, wherein, The vehicle-specific model includes at least a digital representation of the vehicle steering system.
4. The method according to claim 1, wherein, The first constitutive model includes a physics-based representation of the vehicle steering system, and the second constitutive model includes a machine learning-based representation of the vehicle steering system.
5. The method according to claim 4, further comprising: The potential fault in the vehicle steering system is identified using at least one of the first and second configuration models.
6. The method according to claim 4, further comprising: Accident reconstruction information is generated using at least the first constituent model.
7. The method according to claim 1, wherein, The master model and the vehicle-specific model are stored on a computing device located away from the vehicle steering system.
8. A system for vehicle modeling, the system comprising: processor; as well as The memory includes instructions that, when executed by the processor, cause the processor to: Receive one or more design specification characteristics corresponding to the vehicle steering system design; Receive one or more line-end characteristics of a vehicle steering system including the design of the vehicle steering system, wherein the one or more line-end characteristics include one or more design characteristics of at least one actual manufactured component used in the manufacturing process associated with the vehicle steering system, and wherein the vehicle steering system includes an electric power steering system. The master model of the vehicle steering system design is generated using one or more design specification characteristics corresponding to the vehicle steering system design. At least one initial parameter is generated using one or more line-end characteristics of the vehicle steering system; A vehicle-specific model is generated based on the master model and the at least one initial parameter, wherein the vehicle-specific model includes a first constituent model and a second constituent model; Receive operational data corresponding to the vehicle steering system, wherein the operational data includes at least steering system input data and vehicle sensor data, the vehicle sensor data indicating one or more measurements of the vehicle steering system in response to the steering system input data during the operation of the vehicle after the vehicle associated with the vehicle steering system has exited the manufacturing process, wherein the vehicle sensor data corresponds to the actual response of the vehicle steering system to the steering system input data; The vehicle-specific model is updated using at least one subsequent parameter, which is generated using the operational data, wherein the vehicle-specific model includes nominal design data corresponding to one or more design specification characteristics corresponding to the vehicle steering system design, completion data corresponding to one or more line end characteristics, and data in use corresponding to the operational data; Using the first constitutive model, intermediate data is generated based on the steering system input data and the vehicle sensor data, wherein the intermediate data indicates the predicted response of the vehicle steering system to the steering system input data; and Using the second constitutive model, a potential fault in the vehicle steering system is predicted, based at least on a comparison of vehicle sensor data corresponding to the actual response of the vehicle steering system to the steering system input data and intermediate data indicating the predicted response of the vehicle steering system to the steering system input data, wherein the potential fault is associated with the future condition of the vehicle steering system.
9. The system according to claim 8, wherein, The master model includes a digital representation of the vehicle steering system category corresponding to the vehicle steering system design.
10. The system according to claim 8, wherein, The vehicle-specific model includes at least a digital representation of the vehicle steering system.
11. The system according to claim 8, wherein, The first constitutive model includes a physics-based representation of the vehicle steering system, and the second constitutive model includes a machine learning-based representation of the vehicle steering system.
12. The system according to claim 8, wherein, The instructions also instruct the processor to use at least one of the first configuration model and the second configuration model to identify the potential fault in the vehicle steering system.
13. The system according to claim 8, wherein, The master model and the vehicle-specific model are stored on a computing device located away from the vehicle steering system.