Stage Motion Control With Dual ML Compensation for Vibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems, including those using machine learning, struggle to effectively reduce vibrations in high-frequency ranges when a stage is mounted on a main structure, often leading to excitation of vibrations in the main structure and inadequate reduction of stage equipment vibrations.
Innovation Solution
A control device with a combination of a PID controller and a neural network (NN) controller that measures and compensates for motion differences between a stage and a main structure, using machine learning to adjust parameters for operation amounts, thereby reducing vibrations by controlling the stage and main structure movements independently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a control system using machine learning is applied to reduce stage vibrations, then low-frequency vibrations can be compensated, but high-frequency vibrations (100 Hz or higher) in the main structure are excited and stage equipment vibrations cannot be adequately reduced
Solution Approach 1:
The control system is segmented into two independent machine learning controllers: a first machine learning controller for the stage and a second machine learning controller for the main structure. Each controller operates independently with its own parameter optimization, allowing separate tuning of frequency responses. This segmentation enables the stage controller to reduce vibrations while the main structure controller prevents high-frequency excitation, resolving the contradiction between low-frequency compensation and high-frequency vibration prevention.
2Manufacturing precision
If machine learning is used to compensate for stage vibration, then control deviation can be decreased, but vibration transfer from pipes and ducts to the stage occurs
Solution Approach 1:
The second machine learning controller acts as an intermediary by actively controlling the main structure to counteract vibrations transferred from pipes and ducts. This intermediary controller prevents vibration transfer to the stage by optimizing main structure parameters, thereby maintaining manufacturing precision while blocking the harmful vibration transfer path.
3Device complexity
If a single control system is used for both stage and main structure, then device complexity is reduced, but vibration suppression stability is insufficient
Solution Approach 1:
The control system is divided into two independent machine learning controllers, each dedicated to a specific component (stage and main structure). This segmentation allows each controller to be optimized independently for its specific vibration characteristics, improving overall vibration suppression stability. The first controller optimizes stage parameters while the second optimizes main structure parameters, ensuring stable vibration suppression across different frequency ranges despite increased system complexity.
Data Source
AI summary
In order to control motions of a first movable part and a second movable part in which the first movable part is mounted, the control device includes: a first measuring unit configured to measure the motion of the first movable part; a first compensation unit configured to generate a first amount of operation based on an output of the first measuring unit to control the motion of the first movable part; a second compensation unit configured to generate a second amount of operation based on the output of the first measuring unit to control the motion of the first movable part; a first computing unit configured to generate an amount of operation for driving the first movable part based on an output of the first compensation unit and an output of the second compensation unit; a second measuring unit configured to measure the motion of the second movable part; a third compensation unit configured to generate a third amount of operation based on an output of the second measuring unit to control the motion of the second movable part; and a control unit configured to determine parameter values for generating the second and third amounts of operation in the second and third compensation units using machine learning by starting the machine learning at different timings.