Predictive Hydrogen Pressure Control for Fuel Cell Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing control methods for vehicle-mounted hydrogen systems cannot meet the real-time hydrogen requirements of fuel cell systems, leading to fluctuations in pressure and flow that affect the operation of fuel cell vehicles, especially during conditions like climbing and rapid acceleration.
Innovation Solution
A control method and apparatus that uses a pressure prediction model to anticipate and adjust the hydrogen pressure output, comparing prediction errors with actual errors to ensure the hydrogen system meets the fuel cell's demands, utilizing a grey prediction model for accurate pre-adjustment of hydrogen flow and pressure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a mechanical pressure regulator is used to control hydrogen flow and pressure, then the system structure is simple, but the dynamic response time is slow (seconds) compared to the chemical reaction speed (milliseconds)
Solution Approach 1:
The patent applies preliminary action by using a prediction model to forecast future hydrogen pressure values before they actually occur. The controller predicts the pressure at the next moment based on historical pressure data, and uses this predicted value to proactively adjust the pressure regulator, rather than reacting after the pressure deviation occurs. This transforms the passive reactive control into active predictive control, achieving millisecond-level response that matches the chemical reaction speed.
Solution Approach 2:
The patent replaces the purely mechanical pressure regulator control with an intelligent control system that uses prediction algorithms (such as grey prediction model or neural network). The mechanical pressure regulator remains the same, but its control signal is generated by an intelligent algorithm that predicts future pressure trends, effectively substituting mechanical reactive control with intelligent predictive control to achieve faster response.
2Reliability
If passive adjustment of hydrogen pressure is used after pressure deviation occurs, then the control logic is simple, but the hydrogen supply cannot meet real-time requirements during rapid power changes
Solution Approach 1:
The patent uses preliminary action by predicting future pressure values before the actual pressure deviation occurs. The prediction model analyzes historical pressure data to forecast the next moment's pressure, and the controller proactively adjusts the pressure regulator based on this prediction. This eliminates the time delay associated with waiting for pressure deviation to occur and then reacting, ensuring hydrogen supply reliability during rapid power changes.
Solution Approach 2:
The patent implements feedback by continuously monitoring the actual hydrogen pressure, comparing it with the predicted pressure value, and using the error between them to adjust the control strategy. The system calculates the difference between predicted and actual pressure, and when the prediction error is within an acceptable range, it trusts the prediction model; otherwise, it adjusts based on actual measurements. This closed-loop feedback ensures reliable hydrogen supply.
3Productivity
If the pressure regulator adjusts hydrogen pressure in real-time, then the hydrogen supply meets fuel cell requirements, but the control system becomes complex with multiple sensors and controllers
Solution Approach 1:
The patent replaces complex multi-sensor control systems with an intelligent prediction-based control approach. Instead of using multiple pressure sensors and complex control algorithms to continuously monitor and adjust pressure, the system uses a prediction model (such as grey prediction or neural network) that processes historical pressure data to forecast future pressure values. This simplifies the control apparatus while maintaining high hydrogen supply efficiency.
Solution Approach 2:
The patent applies self-service by enabling the pressure control system to predict and adjust its own operation based on historical data patterns. The prediction model learns from past pressure variations and automatically generates control signals without requiring complex external control logic or multiple sensors. The system serves itself by using its own historical operational data to make intelligent control decisions.
Data Source
Figure 1
Figure 2~3
AI summary
The present invention relates to a control method and apparatus for a vehicle-mounted hydrogen system and a vehicle-mounted hydrogen system, belonging to the field of fuel cell vehicles. The method comprises: building a pressure prediction model for a gas output by the vehicle-mounted hydrogen system, and determining, according to the pressure prediction model, a predicted pressure value for controlling the vehicle-mounted hydrogen system to output the gas; calculating a difference between the predicted pressure value and a set target pressure value to obtain a prediction error; obtaining an actual pressure value of the gas output by the vehicle-mounted hydrogen system, and calculating a difference between the actual pressure value and the target pressure value to obtain an actual error; comparing the prediction error with the actual error, and when the prediction error is less than the actual error, outputting a predicted pressure value at the next time point by using the pressure prediction model, as a target pressure at the next time point, to control the vehicle-mounted hydrogen system to output the gas. According to the present invention, a change trend of the output pressure of the vehicle-mounted hydrogen system is determined in advance, and the pressure of the gas output by the vehicle-mounted hydrogen system is adjusted in advance, so that hydrogen supplied can meet the requirements of a fuel cell system.