Predictive FCEV Energy Management for Fuel Cell-Battery Power Blending
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional supervisory energy management techniques for fuel cell electric vehicles (FCEVs) are limited by short-term prediction horizons, lack of dynamic tuning of terminal conditions, and failure to account for external factors like charging station availability and road topology, leading to sub-optimal fuel cell and battery system control.
Innovation Solution
A predictive supervisory energy management system that utilizes real-time and historical data to optimize fuel cell and high voltage battery system control through a cost function with dynamically tuned weighting factors, considering driver inputs, vehicle states, and external inputs to achieve near-optimal performance across various scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional rule-based reactive techniques are used for fuel cell system control, then the system is easier to operate, but the fuel cell system experiences more transients which reduces efficiency and life
Solution Approach 1:
The control system performs preliminary actions by predicting future energy consumption and determining optimal power distribution before transients occur. The supervisor predicts energy consumption over a future horizon and proactively adjusts fuel cell and battery power output to prevent transients, rather than reacting to them after they occur.
Solution Approach 2:
The control system implements feedback by continuously monitoring actual energy consumption and comparing it with predicted values. The supervisor uses real-time vehicle states, driver inputs, and external inputs to update predictions and adjust control strategies, creating a closed-loop system that maintains optimal performance while minimizing transients.
2Reliability
If optimization-based techniques are used for fuel cell system control, then the fuel cell system efficiency is improved, but the system lacks adaptability to different usage scenarios
Solution Approach 1:
The control system implements dynamics by making the weighting factors and boundary conditions adaptive rather than fixed. The supervisor dynamically adjusts these parameters based on predicted energy consumption, vehicle states, and usage scenarios. This allows the system to maintain optimal efficiency while adapting to different driving conditions, vehicle loads, and external factors such as charging station availability.
Solution Approach 2:
The control system changes parameters by adjusting weighting factors in the cost function and modifying boundary conditions based on predicted future states. The supervisor varies these parameters in real-time to optimize performance for different usage scenarios, such as extending range, maximizing regenerative braking, or preparing for upcoming high-power demands.
3Speed
If short-term prediction horizon is used in energy management, then the control response is faster, but the optimization performance is sub-optimal
Solution Approach 1:
The control system performs preliminary optimization over an extended prediction horizon while maintaining fast response through hierarchical control. The supervisor predicts energy consumption further ahead and prepares optimal power distribution strategies in advance, allowing both long-term optimization and rapid adaptation when actual conditions diverge from predictions.
Solution Approach 2:
The control system maintains continuity of useful action by continuously updating predictions and re-optimizing power distribution over the prediction horizon. The supervisor continuously monitors vehicle states and external inputs, updating energy consumption predictions and adjusting control strategies in real-time, ensuring both long-term optimization and responsive adaptation to changing conditions.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances FCEV performance by optimizing range, drive performance, and component health through advanced prediction and blending of fuel cell and battery power, addressing limitations of conventional methods.
Implementation Method 1
a fuel cell system that is configured to perform a chemical conversion of a fuel (e.g., hydrogen) to generate electrical energy
Implementation Method 2
a high voltage battery system for powering one or more electric traction motors of the FCEV for propulsion
Data Source
AI summary
A predictive supervisory energy management technique for a fuel cell electric vehicle (FCEV) involves monitoring driver inputs to the FCEV, states of the FCEV, and external inputs affecting the FCEV along a defined route, predicting energy consumption by a high voltage system of the FCEV across a future prediction horizon based on the driver inputs, the states of the FCEV, and the external inputs affecting the determining weighting factors and boundary conditions for a cost function for the energy consumption by the high voltage system of the FCEV, evaluating the cost function based on the determined weighting factors, boundary conditions, and the predicted energy consumption by the high voltage system across the future prediction horizon, and optimally controlling a fuel cell system and a high voltage battery system of the high voltage system of the FCEV based on the evaluation of the cost function.