Vehicle Fuel System Predictive Control Under Limited Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Model predictive control systems are computationally intensive, making them difficult to implement in mobile settings such as vehicles, where resources and processing power are limited.
Innovation Solution
A processing circuit with one or more memory devices and processors is used to receive information about the observed state of a vehicle system, determine a predictive state, and execute a control problem to determine control inputs for the fuel system, optimizing operations such as fuel injection, rail pressure, and engine management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If model predictive control is implemented in vehicle systems, then control accuracy and system performance are improved, but computational requirements increase making implementation difficult in mobile settings
Solution Approach 1:
The control problem is segmented into multiple discrete steps including receiving observed state information, determining predictive state, determining constraints, executing control problem, and determining control inputs. This segmentation allows the complex model predictive control to be broken down into manageable computational tasks that can be executed sequentially on vehicle processors.
Solution Approach 2:
The system performs preliminary actions by determining the predictive state of the vehicle system over a prediction horizon before final control decisions are made. This advance prediction allows the control system to prepare optimal control inputs in advance, reducing real-time computational burden while maintaining high control accuracy.
2Productivity
If model predictive control is used to optimize fuel system operations, then fuel efficiency and emissions control are improved, but processing power requirements make implementation challenging in vehicles
Solution Approach 1:
The system changes parameters by optimizing multiple fuel system parameters simultaneously including start of injection timing, fuel flow rate, and rail pressure. By coordinating changes across these parameters based on predictive modeling, the system achieves improved fuel efficiency without requiring exponential processing power increases.
Solution Approach 2:
The system implements feedback by receiving observed state information from vehicle sensors and using this actual state data to update and refine the predictive control model. This feedback mechanism allows the system to learn from actual vehicle operation and improve fuel efficiency over time while keeping computational requirements manageable through iterative refinement rather than exhaustive calculation.
Data Source
AI summary
Systems and methods for using machine learning to improve control, management, and operation of vehicle systems are disclosed. A system includes a processing circuit configured to: receive information indicative of an observed state of a vehicle system from a sensor of the vehicle, the vehicle system including a fuel system; determine a predictive state of the vehicle system over a prediction horizon; determine one or more constraints for the vehicle system; execute a control problem to determine a predictive state of the vehicle system based on the one or more constraints; determine a plurality of control inputs for the vehicle system based on the executed control problem; and command the fuel system of the vehicle based on at least one of the determined plurality of control inputs.