Vehicle Component Load Profiles Using Predictive Usage Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating vehicle component load profiles are complex, impractical, and often consider only short driving phases, failing to account for individual customer usage patterns, leading to inadequate component design and development.
Innovation Solution
A method utilizing modern model-based approaches, including autoencoding and autoregressive neural networks, to create representative load profiles by compressing and predicting vehicle data, enabling detailed simulation and design improvements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If representative sampling (e.g., WLTC) and Markov chain approaches are used to combine components into an overall profile, then the complexity of simulations is reduced, but the ability to account for individual usage patterns is lost
Solution Approach 1:
The patent segments individual vehicle usage patterns into distinct profiles (e.g., urban driving, highway driving, mixed driving) based on multiple parameters including velocity, acceleration, and driving duration. This segmentation allows the system to maintain simulation simplicity while preserving individual usage pattern characteristics through profile-based representation rather than treating all usage uniformly.
Solution Approach 2:
The patent changes the parameter set used for profile generation from simple single-parameter approaches to multi-parameter combinations (velocity ranges, acceleration patterns, driving duration thresholds). This parameter expansion enables the system to distinguish between different usage patterns while maintaining manageable simulation complexity through structured parameter classification.
2Loss of time
If only short driving phases are considered during component development, then the measurement and simulation time is reduced, but the accuracy of component design is compromised
Solution Approach 1:
The patent performs preliminary classification of usage patterns during data collection by pre-defining threshold values for driving phases (e.g., urban: velocity < 50 km/h, duration > 10 minutes). This preliminary action enables the system to process and categorize long-term usage data efficiently, maintaining design accuracy without requiring excessive measurement time for each individual phase.
Solution Approach 2:
The patent employs periodic sampling and classification of driving phases to represent long-term usage patterns through repeated measurement cycles. By systematically collecting data across multiple driving phases and categorizing them according to predefined criteria, the system achieves comprehensive usage representation without requiring continuous measurement of every single phase.
3Device complexity
If only two measurement signals (velocity, acceleration) are recorded, then the data collection complexity is reduced, but the comprehensiveness of usage pattern analysis is limited
Solution Approach 1:
The patent segments the usage pattern analysis into distinct functional categories (driving phase identification, usage pattern classification, profile generation) that can be processed using a core set of measurement signals. By organizing the analysis process this way, the system maximizes the utilization of available data (velocity, acceleration, duration) while maintaining comprehensive coverage of usage patterns without requiring additional sensor complexity.
Solution Approach 2:
The patent adds the dimension of temporal duration and phase classification to the analysis of velocity and acceleration data. By introducing time-based parameters (driving phase duration, frequency of phase transitions) and categorical classifications (urban vs. highway vs. mixed driving), the system enriches the information content from basic measurement signals without adding physical sensors.
Data Source
Figure 1~2
Figure 3~4
AI summary
The invention relates to a method for providing representative load profiles for a component (101) of a vehicle (100) in order to improve the design of the component (101) during development, comprising: - providing a second model (B) which is used to create, based on vehicle data (FD) or representations (z) of vehicle data (FD) for a past period (tr), - a prediction (FD*, z*) of vehicle data (FD) or representations (z) of vehicle data (FD) for a future period (tz) and/or - a reproduction (FD', z`) of vehicle data (FD) or representations (z) of vehicle data (FD) for a past period (tr), - using the prediction (FD*, z*) and/or reproduction (FD', z`) for the design of the component (101).