Machine Learning Correction Parameter Adjustment for Motor Drive Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing motor drive systems with multiple correction functions require extensive time and effort to adjust correction parameters, as existing algorithms can only adjust parameters for a single correction function, necessitating individual algorithm creation for each function.

Innovation Solution

A machine learning apparatus that observes state variables from drive data and correction functions to learn correction parameters for each correction function, using a training dataset to adjust command values effectively across multiple correction functions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If an algorithm is created to adjust correction parameters for multiple correction functions, then the adjustment capability is improved, but the development time and effort increase enormously

Engineering Contradiction:

Improveadjustment capabilityVSAvoiddevelopment time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent creates a single universal algorithm that can adjust correction parameters for multiple different correction functions (friction compensation, rigid body compensation, elastic body compensation, thermal expansion compensation). This universal algorithm eliminates the need to develop separate algorithms for each correction function, thereby improving adjustment capability while reducing development time and effort.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If an operator manually adjusts correction conditions for each motor drive system, then the adjustment accuracy is improved, but the time and effort required increase significantly

Engineering Contradiction:

Improveadjustment accuracyVSAvoidadjustment time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements automatic correction parameter adjustment where the system adjusts its own correction parameters without requiring manual operator intervention. The universal algorithm automatically determines optimal correction conditions for each motor drive system, maintaining adjustment accuracy while eliminating the time and effort previously required for manual adjustment.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback mechanisms to automatically adjust correction parameters based on the actual performance and error characteristics of each motor drive system. This allows the system to self-optimize correction conditions, achieving high adjustment accuracy without manual intervention and significantly reducing adjustment time.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11562048B2Machine learning correction parameter adjustment apparatus and method for use with a motor drive control system

Publication Date: 2023.01.24 MITSUBISHI ELECTRIC CORP

AI summary

A machine learning apparatus for learning a correction parameter used in correction of a command value that controls a motor in a motor drive system including a plurality of kinds of correction functions includes: a state observation unit that observes, as a state variable, each of a feature calculated on the basis of drive data and the kind of any of the correction functions of the motor drive system and the correction parameter; and a learning unit that learns the correction parameter for each of the correction functions according to a training data set created on the basis of the state variable.