Pedal Position Prediction for Engine Actuator Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing engine control systems face challenges in predicting driver input and torque requests, leading to suboptimal engine performance and increased fuel consumption, as they often assume constant torque requests rather than accounting for driver behavior and vehicle conditions.

Innovation Solution

A system that includes a pedal position prediction module and an engine actuator control module, using model predictive control (MPC) to predict driver input based on driving style and vehicle conditions, and adjust engine actuators accordingly, thereby improving engine performance and fuel efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing engine control systems assume constant torque requests, then control simplicity is maintained, but engine performance and fuel efficiency deteriorate

Engineering Contradiction:

Improveengine performanceVSAvoidcontrol system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary prediction of driver torque requests using a neural network model that analyzes historical pedal position data and current vehicle conditions. This advance prediction allows the control system to proactively adjust engine actuators rather than reactively responding to actual pedal movements, improving engine performance and fuel efficiency without requiring complex real-time control adjustments

Inventive Principle:

Principle #10Preliminary action

2Loss of energy

If pedal position prediction based on driver behavior is implemented, then fuel efficiency improves, but measurement and prediction difficulty increases

Engineering Contradiction:

Improvefuel consumptionVSAvoiddriver behavior prediction difficulty

Core Design Contradiction:

Loss of energyVSDifficulty of detecting and measuring

Solution Approach 1:

The system creates a virtual model (neural network) that copies and simulates driver behavior patterns by training on historical pedal position data. This digital twin of driver behavior allows the system to predict future pedal positions without directly measuring or interfering with actual driver inputs, reducing the complexity of driver behavior analysis while improving fuel efficiency through accurate predictions

Inventive Principle:

Principle #26Copying

3Speed

If actual pedal position is used for control, then responsiveness to driver input is maintained, but engine performance optimization deteriorates due to lag

Engineering Contradiction:

Improvecontrol responsivenessVSAvoidengine performance optimization

Core Design Contradiction:

SpeedVSProductivity

Solution Approach 1:

The control system uses predicted future pedal positions from the neural network model to adjust engine actuators in advance, eliminating the inherent lag between driver input and engine response. This preliminary action based on predicted driver intent maintains responsiveness while optimizing engine performance by ensuring actuators are already positioned optimally when the driver actually moves the pedal

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9938908B2System and method for predicting a pedal position based on driver behavior and controlling one or more engine actuators based on the predicted pedal position

Publication Date: 2018.04.10 GM GLOBAL TECHNOLOGY OPERATIONS LLC

AI summary

A system according to the principles of the present disclosure includes a pedal position prediction module and an engine actuator control module. The pedal position prediction module predicts a pedal position at a future time based on driver behavior and vehicle driving conditions. The pedal position includes at least one of an accelerator pedal position and a brake pedal position. The engine actuator control module controls an actuator of an engine based on the predicted pedal position.