Electric Power Steering Motor Control With Neural PID Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric power steering systems face suboptimal performance over time due to fixed PID controller gain terms that fail to adapt to changes in vehicle operating conditions, leading to reduced motor control accuracy and stability.
Innovation Solution
Incorporating a neural network that adjusts PID controller gain terms (P, I, D) in real-time or offline, using additional environmental variables to enhance motor tracking control and stability robustness, by calculating and updating gain values periodically or storing them in a lookup table for real-time use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If fixed PID controller gain terms are used during design phase, then device complexity is reduced and ease of manufacture is improved, but motor control accuracy deteriorates over time as the system changes internally
Solution Approach 1:
The patent implements dynamic adjustment of PID controller gain terms by introducing a neural network that continuously adapts the gain values (Kp, Ki, Kd) based on real-time operating conditions. This transforms the static, fixed gain structure into a dynamic system that automatically recalibrates itself, maintaining optimal motor control accuracy without requiring manual retuning or increasing overall device complexity
Solution Approach 2:
The patent changes the parameters of the PID controller by using a neural network to dynamically modify the gain terms (Kp, Ki, Kd) based on operating conditions such as vehicle speed and steering angle. This parameter adaptation allows the controller to maintain high manufacturing precision across varying operational states without fixing the gains at design-phase values
2Adaptability or versatility
If fixed gain terms are set during design phase, then ease of operation is improved, but adaptability deteriorates as vehicle operating conditions change
Solution Approach 1:
The patent implements self-service by enabling the PID controller to automatically adjust its own gain terms through an integrated neural network. The system monitors its own performance and operating conditions, then autonomously retunes the control parameters without external intervention, maintaining both high adaptability and ease of operation
Solution Approach 2:
The patent incorporates feedback mechanisms where the neural network continuously monitors operating conditions (vehicle speed, steering angle, motor current) and performance metrics, then uses this feedback to dynamically adjust the PID gain terms. This closed-loop adaptation ensures the controller remains optimized across varying vehicle conditions while maintaining simple operation
3Reliability
If neural network is added to dynamically adjust PID gain terms, then motor control accuracy is improved, but device complexity increases
Solution Approach 1:
The patent merges the neural network with the existing PID controller structure, integrating the adaptive intelligence directly into the control pathway. By combining these two components into a unified hybrid controller, the system achieves enhanced reliability through dynamic adaptation while minimizing the increase in device complexity that would result from separate, independent systems
Solution Approach 2:
The patent creates a universal controller that performs both traditional PID control and neural network-based adaptation functions through a single integrated system. This multi-functional approach allows the controller to handle both routine control tasks and adaptive retuning operations, improving reliability across diverse operating conditions without proportionally increasing device complexity
Data Source
AI summary
An electric power assisted steering system for a vehicle is disclosed. The electric power assisted steering system can include an electric motor configured to apply an assistance torque to a part of a steering assembly so as to assist a driver of a vehicle in turning the steering wheel, a drive circuit for the motor which selectively connects the motor phases to an electrical supply to cause current to flow in the motor phases. The amount of assistance torque applied by the motor can be a function of the current flowing in the phases of the motor. The electric power assisted steering system can include a control circuit which generates a control signal that is applied to the motor drive stage.