Teaching Device Shock Prediction via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing teaching pendants lack the ability to predict and prevent shocks, making it difficult to safeguard against strong shocks in various operational environments.

Innovation Solution

A machine learning device that observes the inclination and position of a teaching device, obtains labels based on shocks received, and generates a learning model to predict and prevent shocks by advising operators through alarms and warnings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a teaching pendant is used in various environments by various operators, then the teaching device can be widely applied and operated, but the risk of receiving strong shocks increases and cannot be predicted or prevented

Engineering Contradiction:

Improveapplicability to various operators and environmentsVSAvoidprediction and prevention capability against shocks

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by observing the teaching device's state (inclination, position, acceleration) before a shock occurs, using machine learning to predict potential shock events in advance and issue warnings to operators, thereby preventing damage before it happens

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring the teaching device's state through sensors (acceleration sensors, inclination sensors, position sensors) and using machine learning to analyze the data, providing real-time predictions and warnings to operators about potential shock risks

Inventive Principle:

Principle #23Feedback

2Device complexity

If no shock prediction system is implemented, then the device structure remains simple, but the teaching device cannot predict or prevent shocks resulting in potential malfunction

Engineering Contradiction:

Improvestructure simplicityVSAvoidshock damage risk

Core Design Contradiction:

Device complexityVSObject-affected harmful factors

Solution Approach 1:

The system introduces an intermediary machine learning model that processes sensor data and predicts shock events, acting as a mediator between the physical teaching device and the operator, enabling shock prediction without requiring complex structural modifications to the teaching device itself

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces potential mechanical protection structures with an information-based machine learning prediction system, using software intelligence rather than physical barriers to prevent shock damage, thereby maintaining structural simplicity while enhancing protection capability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10430726B2Machine learning device that learns shocks to teaching device, shock prevention system of teaching device, and machine learning method

Publication Date: 2019.10.01 FANUC LTD

AI summary

A machine learning device, which learns shocks to a teaching device, includes a state observation unit which observes data based on an inclination of the teaching device or a present position of the teaching device; a label obtaining unit which obtains a label based on a shock received by the teaching device; and a learning unit which generates a learning model based on an output of the state observation unit and an output of the label obtaining unit.