Electric Vehicle Damage Modeling With Combustion-Engine Baselines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately predict and measure the damage potential and risk of electrically powered vehicles due to the lack of sufficient data and different driving characteristics compared to combustion engine vehicles, leading to increased uncertainty and inefficiency in insurance and risk assessment.
Innovation Solution
An automated system and method that utilizes a forward-looking modeling structure to combine measurable parameters from combustion engine vehicles with electric vehicle-specific factors, applying modification factors to predict damage potential and risk based on historical data and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional damage prediction systems are used for electric vehicles, then the system structure remains simple, but the measurement precision and reliability of damage prediction deteriorate due to lack of sufficient EV-specific data
Solution Approach 1:
The system segments the damage prediction task into two distinct modules: a base model trained on combustion engine vehicle data and an EV-specific adjustment module that applies modification factors to adapt the base predictions to electric vehicle characteristics. This segmentation allows the system to leverage existing robust data while incorporating EV-specific adjustments, thereby improving measurement precision without requiring a complete redesign of the entire prediction system.
Solution Approach 2:
The patent introduces modification factors as an intermediary element that bridges the gap between combustion engine vehicle data and electric vehicle damage characteristics. These modification factors serve as adjustable parameters that translate base model predictions into EV-specific predictions, enabling accurate damage assessment for electric vehicles without needing extensive EV crash data from scratch.
2Reliability
If EV-specific damage data is collected and used, then the reliability of damage prediction improves, but the loss of time and resources for data collection and processing increases
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing modification factors for various electric vehicle types and configurations before actual damage prediction is needed. These modification factors are derived from available EV characteristics and crash test data in advance, so that when a real-world EV damage case needs assessment, the system can immediately apply the pre-prepared adjustment factors without needing to conduct new data collection or analysis at the time of prediction.
3Adaptability or versatility
If modification factors are applied to adapt combustion engine vehicle data to electric vehicles, then the adaptability of the system improves, but the device complexity increases due to additional calculation layers
Solution Approach 1:
The system applies parameter changes by modifying key prediction parameters through multiplication or adjustment by modification factors. Instead of fundamentally changing the prediction algorithm, the system adjusts specific output parameters (such as expected damage costs, repair time, or component failure probability) by applying EV-specific modification factors to the base model predictions. This approach maintains the core calculation structure while adapting the results to electric vehicle characteristics.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Proposed is an automated system and method for measuring and/or allocating risk measures of loss for a replacement cost of an electric vehicle and/or parts of the electric vehicle. The system based on a forward looking model structure for electric vehicles (FLM-EV) returns rating modification factors for MTPL and MOD for electric vehicles. The input consists of either car make, model year or rating parameters like model year, maximum power etc. The output are modification factors that are applied on MOD or MTPL frequency, severity or expected loss for non-electric cars.