This project focuses on the clustering analysis of the UR3 CobotOps dataset. The dataset includes multidimensional time-series data from the UR3 cobot, offering insights into operational parameters and faults for machine learning in robotics and automation.
To reproduce the analysis, follow these steps:
-
Clone the repository:
git clone https://github.com/yourusername/ur3-cobotops-clustering.git cd UR3-Cobotops-Clustering
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the Jupyter notebook:
jupyter notebook UR3 CobotOps Clustering.ipynb
The UR3 CobotOps dataset is a comprehensive collection of data including:
- Electrical currents
- Temperatures
- Speeds across joints (J0-J5)
- Gripper current
- Operation cycle count
- Protective stops
- Grip losses
Dataset Characteristics:
- Type: Multivariate, Time-Series
- Instances: 7409
- Features: 20
- Tasks: Classification, Regression, Clustering
Dataset
: The dataset used for the analysis.UR3 CobotOps - UCI Machine Learning Repository.pdf
: Documentation explaining the dataset and its variables.Fuzzy Cognitive Maps.pdf
: Scientific paper providing theoretical background on Fuzzy Cognitive Maps (FCMs) used in the analysis.UR3 CobotOps Clustering.ipynb
: Jupyter notebook with code and visualizations for clustering analysis.
The project employs clustering techniques to analyze the UR3 CobotOps dataset. The primary methodology involves:
- Data Pre-processing: Handling missing values, normalizing data, and encoding categorical variables.
- Clustering: Applying various clustering algorithms to identify patterns and anomalies.
- Visualization: Creating visualizations to interpret the clustering results.
Here are some of the key visualizations from the analysis:
Description: This visualization shows the clustering results of the UR3 CobotOps dataset using K-Means algorithm.
Description: This plot depicts the importance of different features in determining the clusters.
- UR3 CobotOps Dataset - UCI Machine Learning Repository
- Tyrovolas, M., Liang, X. S., & Stylios, C. (2023). Information flow-based fuzzy cognitive maps with enhanced interpretability. Granular Computing, 8, 2021-2038. DOI: 10.1007/s41066-023-00417-7
This work was supported by the Department of Informatics and Telecommunications, University of Ioannina, and the Industrial Systems Institute, Athena Research Center.