Vibration Actuator Control Using ML Feedback for Position Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vibration motor control systems face challenges in accurately controlling non-linear motor characteristics, which are affected by driving conditions and temperature changes, leading to complex adjustments and reduced controllability.
Innovation Solution
A vibration actuator control apparatus utilizing a trained machine learning model to output control amounts for moving a contact body relative to a vibrator, incorporating automatic gain control to adjust phase difference and frequency based on target speed and position deviations, thereby compensating for changes in motor characteristics and environmental conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional PID control is used to control vibration motor speed and position, then basic control functionality is achieved, but controllability deteriorates under varying driving conditions and temperature environments due to non-linear motor characteristics
Solution Approach 1:
The patent implements dynamic control parameter adjustment by continuously adapting the control amounts (phase difference and frequency) based on real-time detection of actual speed and position, comparing them with target values, and modifying control parameters accordingly. This dynamic adaptation enables the system to maintain high controllability across varying driving conditions and temperature environments, resolving the contradiction between reliability and adaptability.
Solution Approach 2:
The patent employs feedback control mechanisms where the actual speed and position of the vibration motor are continuously detected and fed back to the control unit. The control unit calculates position deviation and speed deviation, then adjusts control parameters (phase difference and frequency) based on these deviations. This feedback loop ensures reliable control performance while adapting to changing conditions, addressing the contradiction between controllability and environmental adaptability.
2Measurement precision
If multiple control parameters (frequency, phase difference, voltage) are adjusted to improve control precision, then positioning accuracy is enhanced, but system complexity increases
Solution Approach 1:
The patent extracts and focuses on two critical control parameters (phase difference and frequency) that have the most significant impact on vibration motor performance. By concentrating control efforts on these key parameters rather than adjusting all possible parameters (including voltage), the system achieves high positioning accuracy while keeping the control system manageable and avoiding excessive complexity.
Solution Approach 2:
The patent utilizes parameter changes in phase difference and frequency to achieve precise control of the vibration motor's speed and position. The control unit dynamically adjusts these parameters based on feedback from position and speed sensors, enabling accurate positioning without requiring complex multi-parameter adjustment mechanisms. This approach maintains simplicity while achieving high measurement precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances controllability and accuracy by automatically correcting control amounts, reducing position deviations and improving robustness across varying driving conditions and temperatures, ensuring stable and precise motor performance.
Implementation Method 1
a piezoelectric element 204 that is an electro-mechanical energy conversion element connected to an elastic body 202
Data Source
AI summary
A vibration actuator control apparatus includes a control amount output unit. The control amount output unit includes a trained model trained by machine learning configured to output a control amount, if the target speed and a value based on the target position are input to the trained model, to move the contact body relative to the vibrator. The value based on the target position is a value based on a product of first and second values. The first value is a value based on a difference between the target position and a detection position detected from the vibration actuator moved based on the control amount. The second value is a value based on a ratio between the control amount output from the control amount output unit and a value output from the trained model if the target speed and a predetermined value are input to the trained model.