Robot Abnormality Detection Using Disturbance Torque Trends
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality detection systems for robots struggle to accurately detect abnormalities due to varying ranges of disturbance torque, often overlooking small changes or incorrectly identifying normal operation as abnormal, due to fixed threshold values.
Innovation Solution
An abnormality detection device and method that analyze time-series data by calculating differences and integrating numerical values to detect continuous changes in disturbance torque, regardless of the range of fluctuation, using defined numerical values to indicate increases or decreases and determine abnormalities based on moving averages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed threshold value is used for abnormality detection, then the detection method is simple, but abnormalities may be overlooked when the disturbance torque variation range is narrow or false positives occur when the threshold is set low
Solution Approach 1:
The patent applies dynamics by transforming the static threshold comparison into a dynamic trend analysis. Instead of using a fixed threshold value, the system calculates the rate of change of disturbance torque over time and detects abnormalities based on whether this rate exceeds a threshold. This dynamic approach adapts to varying disturbance torque ranges while maintaining detection sensitivity, resolving the contradiction between detection accuracy and method simplicity.
2Reliability
If the threshold is set to a low value to avoid overlooking abnormalities, then detection sensitivity increases, but normally operating robots are erroneously determined to be abnormal
Solution Approach 1:
The patent applies preliminary action by calculating the rate of change of disturbance torque before making an abnormality determination. This preliminary calculation of the derivative (rate of change) serves as a preprocessing step that filters out normal variations in disturbance torque. By detecting abnormalities based on the rate of change rather than absolute values, the system maintains high detection sensitivity while reducing false positives from normal operational variations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An abnormality detection device detects an abnormality of a device (101) based on time-series data (RD) acquired from a device (101) having a movable part. The abnormality determination device determines whether time-series data (RDt) at a specific time have increased or decreased with respect to time-series data (RDt-k) from a certain time prior to the specific time as the specific time is shifted, indicates an increase or decrease of the time-series data (RD) by defined numerical values, and detects an abnormality of the device (101) based on integrated values (FD1-FD3) obtained by integrating the defined numerical values.