Route-Learning Hybrid Powertrain Control for Driver Preference Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hybrid powertrains lack the ability to adapt to a driver's preferences for vehicle operation on specific routes, leading to a less responsive driving experience due to their fuel-conscious programming.
Innovation Solution
A route-learning powertrain control system that utilizes feedback from acceleration and brake sensors, steering wheel angle, and navigation data to optimize powertrain operations such as transmission shifting, regenerative braking, and start/stop functionality based on learned driver preferences, allowing customization of the driving experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If hybrid powertrain operates in fuel-conscious manner, then fuel economy is improved, but driver's perception of vehicle control and responsiveness deteriorates
Solution Approach 1:
The powertrain control system dynamically adjusts its operation mode based on learned driver preferences and route characteristics. The system transitions between fuel-conscious and driver-responsive modes by learning from sensor feedback about driver behavior patterns, allowing the vehicle to adapt its control characteristics over time rather than maintaining a fixed operational mode.
Solution Approach 2:
The system incorporates feedback from acceleration and brake sensors, steering wheel angle sensors, and other driver input devices to learn driver preferences. This feedback loop enables the control system to understand and adapt to individual driver behaviors, adjusting powertrain response to match driver expectations while maintaining fuel efficiency.
2Ease of operation
If powertrain is programmed to be driver-responsive, then driving experience is improved, but fuel consumption increases
Solution Approach 1:
The system performs preliminary learning of driver preferences and route characteristics before actual driving occurs. By pre-learning from sensor data collected during previous trips on the same route, the system can anticipate driver intentions and pre-optimize powertrain parameters, enabling responsive driving experience without real-time fuel penalties.
3Device complexity
If powertrain lacks route-specific adaptation, then system complexity is reduced, but adaptability to driver preferences deteriorates
Solution Approach 1:
The powertrain control system performs self-learning by automatically collecting and analyzing sensor data from driver operations without requiring external programming or complex configuration. The system serves itself by autonomously adapting to driver preferences through machine learning algorithms that process feedback from acceleration, braking, and steering sensors, eliminating the need for manual system reconfiguration.
4Device complexity
If powertrain uses limited integrated learning capacity confined to shift timing, then device complexity is reduced, but adaptability to driver and route preferences deteriorates
Solution Approach 1:
The learning system is expanded from单一的shift timing adaptation to a multi-functional learning capability that encompasses multiple powertrain parameters including transmission shifting, start/stop functionality, regenerative braking control, battery conditioning, and cylinder deactivation. This universal learning approach allows a single adaptive system to optimize diverse powertrain operations based on comprehensive driver and route preference analysis.
Data Source
AI summary
The technology described herein provides a powertrain system with a route-learning feature. Particularly, learned information is used to optimize powertrain operation along any learned route. The learned information comprises, generally, feedback from the vehicle's acceleration and brake sensors and information from an on-board trip computer. At the least, the powertrain is able to optimize its operation to a driver's preference based on the feedback recorded along a particular route that the driver has specified. The route-learning powertrain control described herein is particularly useful with a hybrid powertrain, and can be used to optimize start/stop and regenerative braking control. The system described herein can also be integrated with a navigation system and GPS receiver, to provide more accurate route-learning and/or automated operation.