AI Vehicle Range Estimation Using Route-Aware Energy Rules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately predict the mileage range of vehicles, particularly electric vehicles, due to neglecting real-world driving conditions and various factors affecting energy consumption, leading to inaccurate travel estimates and potential vehicle stranding.
Innovation Solution
A knowledge-based artificial intelligence system (KBAIS) that utilizes a rules-based approach to predict mileage range by considering vehicle and route characteristics, such as terrain, driver behavior, and other factors, using a hybrid model combining data-driven and physics-based methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a simple energy consumption model is used to predict mileage range, then the computational complexity is low and the system is easy to operate, but the prediction accuracy is insufficient and fails to account for real-world driving conditions
Solution Approach 1:
The system segments the mileage range prediction into multiple components: base energy consumption calculation, route characteristic analysis (elevation changes, traffic patterns, road grade), vehicle-specific factors (aerodynamics, rolling resistance, drivetrain efficiency), and environmental conditions. Each segment is calculated separately and aggregated to produce the final prediction, improving accuracy while keeping each component manageable in complexity
Solution Approach 2:
The system dynamically adjusts prediction parameters based on real-time and historical data. It uses machine learning models that continuously learn from actual driving patterns, route characteristics, and energy consumption data to refine predictions. The system adapts to changing conditions such as weather, traffic patterns, and driver behavior, maintaining high accuracy without requiring complete system redesign
2Reliability
If a comprehensive model considering multiple factors is used to predict mileage range, then the prediction accuracy improves, but the computational resources required and system complexity increase
Solution Approach 1:
The system performs preliminary calculations of route characteristics (elevation profiles, distance, traffic patterns) and vehicle parameters (aerodynamic coefficients, rolling resistance) before the actual trip. Historical data and pre-computed models are cached and reused when applicable, reducing real-time computational energy requirements while maintaining comprehensive prediction accuracy
Solution Approach 2:
The system dynamically changes computational parameters based on available resources and prediction needs. It adjusts the level of detail in calculations, uses approximations when appropriate, and prioritizes which factors to include based on their impact on prediction accuracy. This allows the system to maintain reliability while optimizing energy consumption based on operational context
3Productivity
If best-case scenario assumptions are used for mileage range prediction, then the calculation is simple and fast, but the predictions are inaccurate and do not reflect actual driving conditions
Solution Approach 1:
The system uses actual vehicle data from sensors (energy consumption, driving patterns, route characteristics) to automatically refine its own predictions. It continuously learns from real-world performance and adjusts its models accordingly, enabling fast predictions that are continuously improving in accuracy without requiring manual calibration or extensive external data
Solution Approach 2:
The system implements feedback loops where actual mileage achieved is compared with predicted mileage, and discrepancies are used to refine future predictions. Historical data on actual energy consumption under various conditions is fed back into the models to improve accuracy. This allows the system to maintain high prediction speed while progressively improving precision through learned patterns from actual driving behavior
Data Source
AI summary
Apparatuses, systems, and methods relate to technology to identify travel data associated with a vehicle. The technology further identifies a travel route associated with the vehicle based on the travel data, identifies a selected rule from a plurality of rules based on one or more of a first characteristic of the travel route or a second characteristic of the vehicle, and determines a depletion mileage amount for the vehicle based on the selected rule.