Adaptive Driver Advisory Control for Hybrid Vehicle Fuel Economy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hybrid electric vehicle powertrains do not effectively optimize fuel economy based on driver style and behavior, leading to potential improvements in fuel efficiency that are not fully realized due to lack of adaptive feedback systems.
Innovation Solution
A real-time driver advisory system using a fuzzy logic-based adaptive algorithm that learns driver preferences and provides visual and haptic feedback to optimize accelerator pedal inputs, balancing fuel economy and drivability without being intrusive.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If a non-adaptive real-time fuel economy advisory system is used, then fuel economy can be improved through visual and haptic feedback, but the system is intrusive to the driver and does not account for individual driving preferences
Solution Approach 1:
The system implements a closed-loop feedback mechanism where the advisory system monitors driver responses to its recommendations and uses this information to adapt future advice. The feedback loop includes detecting driver accelerator pedal inputs, comparing them to recommended inputs, and adjusting the advisory strategy based on whether the driver accepts or rejects recommendations, thereby reducing intrusiveness while maintaining fuel economy benefits
Solution Approach 2:
The system dynamically adapts its characteristics based on learned driver preferences. The advisory thresholds, feedback intensity, and recommendation strategies are not fixed but change over time as the system learns from driver behavior patterns. This dynamic adaptation allows the system to become less intrusive for each individual driver while continuing to provide fuel economy improvements
2Loss of energy
If the advisory system provides frequent feedback to improve fuel economy, then fuel efficiency increases, but the driver experience deteriorates due to excessive intrusiveness
Solution Approach 1:
The system changes key parameters of the advisory feedback based on learned driver preferences. These parameters include the frequency of feedback, the aggressiveness of recommendations, the types of situations in which advice is given, and the intensity of haptic versus visual feedback. By dynamically adjusting these parameters, the system optimizes the balance between fuel efficiency improvement and driver experience preservation
3Ease of operation
If the system adapts to driver preferences to reduce intrusiveness, then driver acceptability improves, but the complexity of the control system increases
Solution Approach 1:
The system performs self-adjustment by automatically learning driver preferences from observed behavior without requiring manual calibration or complex configuration. The learning algorithm autonomously processes driver responses and updates advisory strategies internally, eliminating the need for complex user setup procedures while achieving high driver acceptability
Solution Approach 2:
The patent replaces complex mechanical or manual adaptation mechanisms with software-based learning algorithms. Instead of requiring physical adjustments or complex control hardware, the system uses computational algorithms to learn and adapt to driver preferences, reducing overall system complexity while maintaining adaptability
Data Source
AI summary
A vehicle powertrain controller includes a fuzzy logic-based adaptive algorithm with a learning capability that estimates a driver's long term driving preferences. An adaptive algorithm arbitrates competing requirements for good fuel economy, avoidance of intrusiveness and vehicle drivability. A driver's acceptance or rejection of advisory information may be used to adapt subsequent advisory information to the driving style. Vehicle performance is maintained in accordance with a driver's driving style.