HEV Engine Activation Planning Using Learned Driving Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hybrid electric vehicles face inefficiencies in engine activation policies that lead to wasted energy, reduced battery life, and increased noise levels due to sub-optimal engine activation, which is often disconnected from driving conditions and route planning.
Innovation Solution
An engine activation planner that analyzes historical driving data to identify patterns, predicts future scenarios, and generates an optimized engine activation policy to minimize energy consumption and noise, using a Markov decision process and multi-objective stochastic shortest path model to dynamically adjust engine activation based on real-time conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If traditional engine activation policy is used, then engine control is simple, but energy efficiency deteriorates and battery life is reduced
Solution Approach 1:
The system performs preliminary analysis of historical driving data to identify recurring scenarios and patterns before actual driving occurs. This pre-computed knowledge is stored and used to guide real-time engine activation decisions, eliminating the need for complex real-time optimization while improving energy efficiency through anticipatory control strategies.
Solution Approach 2:
The system uses the vehicle's own historical driving data to train and update its predictive models continuously. By leveraging its own operational history, the system improves its energy management capabilities without requiring external intervention or complex infrastructure, achieving adaptive optimization through self-learning.
2Reliability
If frequent engine activation occurs, then battery charging is improved, but noise levels increase and battery life is reduced
Solution Approach 1:
The system predicts future driving scenarios based on historical patterns before they occur. By anticipating upcoming driving conditions, the system can proactively charge the battery during optimal times (such as during regenerative braking opportunities) rather than reactively activating the engine, thereby reducing noise while ensuring battery reliability.
Solution Approach 2:
The system continuously monitors actual driving conditions and compares them with predicted scenarios, using this feedback to refine its predictions and adjust engine activation timing. This closed-loop control ensures battery charging reliability while minimizing unnecessary engine activations that会产生 noise.
3Speed
If real-time engine control is implemented, then responsiveness is improved, but computational complexity increases
Solution Approach 1:
The system pre-computes driving patterns and scenarios from historical data offline, storing the results for rapid retrieval during real-time operation. This separates the computationally intensive analysis from real-time control, maintaining responsiveness while avoiding excessive computational complexity during actual driving.
Solution Approach 2:
The system introduces a layer of pre-processed knowledge (driving patterns and predictions) that mediates between raw historical data and real-time control decisions. This intermediary layer enables fast, intuitive control responses without requiring complex real-time computation, as the system simply applies pre-determined strategies to current conditions.
Data Source
AI summary
Engine activation planning in a hybrid electric vehicle (HEV) is disclosed. Historical driving data of the HEV are analyzed to identify recurring driving scenarios and patterns specific to a driver of the HEV. Future driving scenarios are predicted based on the historical driving data. An engine activation policy is generated for the HEV. The engine activation policy optimizes battery charging and usage in response to the future driving scenarios. The engine activation policy is used to control activation of a gasoline engine in the HEV where a control decision is dynamically adjusted based on a comparison of real-time driving conditions with the future driving scenarios.