Steer-by-Wire Control with Neural PID Gain Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The performance of existing steer by wire (SBW) systems, particularly in automotive vehicles, becomes suboptimal over time due to changes in system features and operating conditions, as the gain terms of PID controllers used in these systems are fixed during the design phase and fail to adapt to dynamic changes.
Innovation Solution
Incorporating a neural network into the control circuit of the SBW system to dynamically determine the P, I, and D gain terms of the PID controller, using additional discrete environmental variables such as vehicle speed and steering torque, allowing for real-time adaptation and improved control accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If fixed gain terms are used in PID controller during design phase, then device complexity is reduced and ease of manufacture is improved, but control precision deteriorates over time as system changes
Solution Approach 1:
The patent implements dynamic gain adjustment by replacing fixed PID gain terms with neural network-based adaptive gains. The neural network continuously processes sensor inputs (vehicle speed, steering angle, road gradient) to dynamically determine optimal gain values, allowing the controller to adapt to changing system conditions and maintain high control precision throughout the vehicle's operational lifecycle.
Solution Approach 2:
The patent changes the parameters of the PID controller from fixed values to dynamically adjustable values based on environmental conditions. The neural network modifies the gain terms (Kp, Ki, Kd) in real-time based on inputs such as vehicle speed, steering angle, and road gradient, enabling the controller to optimize performance across different operating scenarios without increasing manufacturing complexity.
2Adaptability or versatility
If fixed gain terms are used in PID controller, then ease of operation is improved during design phase, but adaptability deteriorates when operating conditions change
Solution Approach 1:
The patent implements self-service through the neural network component that automatically adjusts PID gain terms without requiring manual intervention. The system autonomously processes sensor data (vehicle speed, steering angle, road gradient) and dynamically determines optimal gain values, enabling the controller to adapt to changing operating conditions while maintaining ease of operation during actual vehicle use.
Solution Approach 2:
The patent incorporates feedback mechanisms where the neural network continuously receives real-time sensor inputs (vehicle speed, steering angle, road gradient) and uses this information to adjust the PID controller gains. This closed-loop feedback system ensures the controller adapts to changing conditions while maintaining simple operation for the driver.
3Manufacturing precision
If neural network is added to dynamically determine gain terms, then control precision is improved through real-time adaptation, but device complexity increases
Solution Approach 1:
The patent achieves universality by designing a control system where the neural network serves multiple functions: it processes various sensor inputs (vehicle speed, steering angle, road gradient), dynamically determines optimal PID gains for different operating conditions, and adapts to changing system characteristics over time. This multi-functional approach maintains control precision while managing complexity through a unified adaptive framework.
Data Source
AI summary
A steer by wire system for a vehicle includes a hand wheel, a steering gear that is attached to at least one steered road wheel, and at least one actuator that is connected to the hand wheel or the steering gear for the vehicle to apply to torque to the hand wheel or steering gear. The steer by wire system can include a control circuit comprising a first PID Controller which receives at an input a set point signal and provides as an output a control signal that is used to control the motor, the controller being arranged in a closed loop with the motor and configured to minimise an error value indicative of the difference between the demanded behaviour of the motor as indicated by the set point signal and the actual behaviour of the motor.