Articulated Robot Failure Prediction Using Vibration And Motor Current

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies struggle to accurately predict failures in articulated robots, particularly for each individual part, especially when motion information is not pre-stored by the user, and there is a lack of methods for predicting failures based on motor current values.

Innovation Solution

Measuring individual vibration and current values for each part of an articulated robot, analyzing correlations between unit position pattern information, vibration value data, and current value data, and using a data set to predict failures through a correlation analysis and learning process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If motion information is pre-stored by the user to predict failure, then prediction accuracy is improved, but ease of operation deteriorates because users who are not manufacturers find it difficult to program and pre-store motion information

Engineering Contradiction:

Improvefailure prediction accuracyVSAvoidease of motion information storage

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically collects motion information through external sensors without requiring user programming or manual input. The robot performs self-diagnosis by autonomously gathering and analyzing its own operational data, eliminating the need for users to pre-store motion information while maintaining high prediction accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual programming and information storage mechanisms with automated sensor-based data collection. External sensors automatically capture motion information, substituting the need for user-friendly interfaces or manual data entry systems

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Difficulty of detecting and measuring

If vibration components are extracted to determine reducer abnormality, then detection capability is improved, but device complexity increases due to specialized vibration analysis requirements

Engineering Contradiction:

Improveabnormality detection capabilityVSAvoidvibration analysis system complexity

Core Design Contradiction:

Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The system uses a unified data collection framework that gathers vibration, current, and motion information through the same external sensor infrastructure. This multi-functional approach allows vibration analysis to be performed alongside other diagnostic measurements without requiring separate specialized systems, reducing overall device complexity while maintaining detection capability

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Productivity

If failure prediction is performed without part-specific analysis, then productivity is improved by faster assessment, but reliability deteriorates because part-specific failure possibilities cannot be identified for targeted repair

Engineering Contradiction:

Improveprediction speedVSAvoidpart-specific prediction accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system segments the robot into multiple parts (reducer, motor, etc.) and analyzes vibration and current data separately for each component. By dividing the diagnostic process into part-specific analyses, the system maintains high prediction speed while identifying which specific parts are likely to fail, enabling targeted repairs and improving overall reliability

Inventive Principle:

Principle #1Segmentation

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

Enables accurate and rapid prediction of failures in articulated robots, facilitating easy repair by identifying abnormal data exceeding predetermined thresholds.

Implementation Method 1

a plurality of vibration measurement circuits that individually measure individual vibration values for each part of the articulated robot

Methodology Applied

Scientific EffectVibration measurement: Vibration

Implementation Method 2

individual current values output by each of a plurality of motors that drive the plurality of joints, respectively

Methodology Applied

Scientific EffectCurrent measurement: Electrical Resistance

Data Source

PatentUS20250332727A1System and method for predicting failure of articulated robot

Publication Date: 2025.10.30 YUILROBOTICS CO LTD

AI summary

According to one embodiment of the proposed invention, individual vibration values for each part of an articulated robot are measured, individual current values of respective motors are measured, a correlation between a plurality of pieces of unit position pattern information, vibration value data, and current value data is analyzed, and a failure or possibility of failure for each part of an articulated robot is predicted.