Industrial Robot Data Clustering for Operating-Condition Anomalies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot data analysis methods struggle to distinguish between varying operating conditions, leading to false alarms and erroneous conclusions about robot degradation due to the mixing of data from different job tasks and duty cycles.
Innovation Solution
A method using K-means clustering to separate robot joint parameter data into clusters, determining the optimal number of clusters through a scoring technique, allowing for accurate separation of data points by operating condition and identification of anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing robot data analysis methods are used to monitor joint parameters, then robot degradation can be detected, but false alarms occur due to mixing of data from different job tasks and duty cycles
Solution Approach 1:
The patent segments the robot operational data into distinct clusters based on operating conditions (job types, duty cycles) using K-means clustering. This segmentation allows the system to analyze each cluster separately, preventing false alarms caused by mixing different operating conditions while maintaining the ability to detect genuine degradation patterns within each condition.
2Reliability
If manual separation of data by job types is performed, then accurate anomaly detection is achieved, but operational complexity and time requirements increase
Solution Approach 1:
The patent implements self-service by using the K-means clustering algorithm to automatically separate and organize robot operational data into clusters based on operating conditions. The system performs this separation autonomously without requiring manual intervention from operators, thereby maintaining high anomaly detection accuracy while reducing operational complexity and time requirements.
3Measurement precision
If K-means clustering with multiple K values is performed, then optimal cluster separation is achieved, but computational requirements increase
Solution Approach 1:
The patent applies parameter changes by systematically varying the K value in the K-means clustering algorithm to determine the optimal number of clusters. By evaluating different K values and selecting the one that provides the best cluster separation accuracy, the system achieves precise anomaly detection while managing computational resources through a structured search approach.
Data Source
AI summary
A method and system for analyzing robot data to identify anomalies. Data from robot production operations are provided to a processor running a K-means clustering algorithm which separates the data into a number (K) of clusters. The K-means clustering algorithm is executed two or more times on the data, each time using a different value of K within a predefined range. A scoring technique is used to determine an optimal value for the number of clusters K, where the score is calculated in a computation which rewards small distances between points within a cluster and large distances between points in different clusters. The K-means clustering results for the optimal value of K are used to separate the data by cluster, whereupon the separated data is analyzed to identify trends in the parameter data. One of the clusters may contain outlier data points, some of which may indicate an anomaly condition.