Servo Control Filter Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing servo control devices face challenges in setting optimal parameters for notch filters to effectively suppress resonance, leading to potential phase delays and deteriorated servo control performance.
Innovation Solution
A machine learning device that optimizes filter coefficients based on measurement information of input/output gain and phase delay using reinforcement learning, adjusting parameters such as central frequency and bandwidth to minimize vibration and phase delay.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If filter parameters (central frequency and bandwidth) are manually adjusted to suppress resonance, then resonance suppression performance is improved, but device complexity and adjustment difficulty increase
Solution Approach 1:
The system performs self-diagnosis and self-adjustment of filter parameters by automatically detecting resonance frequencies and optimizing bandwidth values through trial-and-error learning, eliminating the need for manual parameter tuning while maintaining optimal resonance suppression performance
Solution Approach 2:
The system continuously monitors servo control performance and resonance characteristics, using this feedback to iteratively adjust filter parameters through reinforcement learning, thereby automatically optimizing resonance suppression without increasing operational complexity
2Reliability
If filter bandwidth is increased to suppress multiple resonance frequencies, then resonance suppression performance is improved, but phase delay increases and servo control performance deteriorates
Solution Approach 1:
The filter bandwidth is transformed from a fixed parameter to a dynamically adjustable parameter that is automatically optimized based on actual resonance characteristics and servo control performance requirements, allowing the system to adaptively balance resonance suppression and phase delay
Solution Approach 2:
The system automatically optimizes filter parameters including central frequency and bandwidth by changing these parameters based on detected resonance characteristics and performance feedback, thereby achieving optimal balance between resonance suppression and servo control performance without manual intervention
3Manufacturing precision
If multiple filter parameters are manually optimized to achieve optimal resonance suppression, then servo control performance is improved, but adjustment time and operational complexity increase
Solution Approach 1:
The system performs preliminary automatic optimization of filter parameters during initial setup or maintenance periods, storing optimized parameter values that can be automatically applied in future operations, thereby eliminating repeated manual adjustment time while maintaining optimal servo control performance
Solution Approach 2:
The system automatically detects resonance characteristics and optimizes filter parameters through self-learning processes, eliminating the need for operator intervention and manual parameter tuning time while achieving optimal servo control performance automatically
Data Source
AI summary
Setting of parameters that determine filter characteristics is facilitated. A machine learning device performs machine learning of optimizing coefficients of at least one filter provided in a servo control device that controls rotation of a motor. The filter is a filter for attenuating a specific frequency component. The coefficients of the filter are optimized on the basis of measurement information of a measurement device that measures at least one of an input/output gain and an input/output phase delay of the servo control device on the basis of an input signal of which the frequency changes and an output signal of the servo control device.