Active Vibration Isolation Control Using Positional Deviation Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vibration isolation systems struggle to determine optimal control parameters without complex adjustments, leading to suboptimal performance in active vibration isolation for industrial machines.

Innovation Solution

A machine learning apparatus that acquires positional deviations between command and actual positions of movable parts and updates a learning model to output suitable control parameters for active vibration isolation systems, enabling automatic determination of control parameters without requiring intricate setup processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If control parameters are manually adjusted based on state determination, then the vibration isolation apparatus can adapt to different conditions, but the process becomes complicated and time-consuming

Engineering Contradiction:

Improveadaptability of control parametersVSAvoidcomplexity of parameter adjustment process

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system automatically determines optimal control parameters by itself using machine learning algorithms. The learning model processes sensor data from the industrial machine and autonomously outputs appropriate control parameters for the vibration isolation apparatus, eliminating the need for manual adjustment and complex setup procedures

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical adjustment processes with an automated information processing system. A machine learning model processes sensor data and automatically generates control parameters, substituting the complex manual tuning process with an automated computational approach that simplifies operation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If simple control parameter changes are implemented based on state determination, then the operation becomes easier, but the control parameter optimization is insufficient

Engineering Contradiction:

Improveease of control parameter settingVSAvoidoptimization of control parameter

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system continuously monitors the actual position of movable parts in the industrial machine and uses this feedback information to update control parameters. The machine learning model learns from the differences between command positions and actual positions, automatically optimizing control parameters based on real-time performance data while maintaining ease of operation

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The vibration isolation apparatus automatically optimizes its own control parameters through the machine learning model without requiring manual intervention. The system self-adjusts by processing sensor data and generating optimized parameters, achieving both ease of operation and reliable optimization simultaneously

Inventive Principle:

Principle #25Self-service

3Measurement precision

If machine learning model is updated using positional deviation data, then the control parameter determination becomes more accurate, but the data processing complexity increases

Engineering Contradiction:

Improveaccuracy of control parameter determinationVSAvoidcomplexity of learning model processing

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces a machine learning model as an intermediary between sensor data and control parameter output. This model automatically processes the complex relationships between industrial machine state data and optimal vibration isolation parameters, achieving high accuracy while keeping the overall system interface simple and easy to operate

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11748659B2Machine learning apparatus, machine learning method, and industrial machine

Publication Date: 2023.09.05 FANUC LTD

AI summary

A machine learning apparatus determines a control parameter of an active vibration isolation apparatus on which an industrial machine is mounted. The industrial machine includes a movable part, a drive source that drives the movable part, and a drive source control section that controls the drive source to position the movable part at a command position. The machine learning apparatus includes: an acquiring section that acquires, as teacher data, a positional deviation, which is a difference between the command position and an actual position of the movable part; a storage section that stores a learning model that outputs the control parameter corresponding to a state quantity concerning the industrial machine; and a learning section that updates the learning model using the teacher data.