View source for Anomaly Detection in Force/Torque Time Series From Delta Robot

<strong>Collection of Jupyter notebooks and Python code implementations for anomaly detection in time series data, particularly in the context of robotic assembly. </strong> [[File:Anomaly detection force torque data.png|thumb|right|<div style="font-size:88%;line-height: 1.5em">Image 1: Anomaly detection in Force/Torque Time Series</div>]]

== Asset Description ==
<p style="line-height: 1.5em">
This Python package contains a collection of Jupyter notebooks and Python code implementations for anomaly detection in multivariate time series, specifically focusing on force and torque data collected during robotic assembly processes using a delta robot. The methods include traditional statistical approaches as well as advanced deep learning models like LSTM networks.
</p>

== Asset Details ==
=== Asset Content ===
<p style="line-height: 1.5em">
The package offers multiple methods for anomaly detection, including <strong>Dynamic Time Warping (DTW)</strong>, <strong>feature-based classification</strong>, <strong>LSTM neural networks</strong>, and <strong>AR models</strong>. Each method is provided in its own directory with corresponding Python scripts. The repository also includes pre-trained models, evaluation scripts, and example Jupyter notebooks that demonstrate the application of these methods on the publicly available dataset.
</p>

== Usage ==
<p style="line-height: 1.5em">
The repository is ideal for researchers and developers working on anomaly detection in time series data, particularly in the context of robotic assembly.<br>

To use this repository, install the package:
 
<div align="center" >

{| class="wikitable" style="margin:auto; width:300px; line-height: 1.5em"
|-
| '''pip install ctuFaultDetector'''
|-
|}

</div>

Detailed instructions and example code are provided in the Jupyter notebooks (presentation_LSTM, presentation_feature, presentation_nsigma). These notebooks demonstrate how to load the dataset, preprocess the data, train the models, and evaluate their performance. 

</p>

=== Maturity===
<p style="line-height: 1.5em">
First version finished, but new versions are being developed, a more comprehensive documentation will be added in future
</p>

=== Licence===
Open source - [https://opensource.org/license/MIT MIT License]

== Resources ==
<ul>
<li>Python package available [https://pypi.org/project/ctuFaultDetector/ here]</li>
<li>Provided by [https://www.cvut.cz/en Czech Technical University in Prague - CTU]</li>
</ul>

==== Acknowledgement====
<p style="font-size:90%;line-height: 1.5em">
''This work was co-funded partly by AI REDGIO 5.0 and partly by the European Union under the project [https://roboprox.eu/ ROBOPROX](reg. no. CZ.02.01.01/00/22_008/0004590). In the AI REDGIO 5.0 project it will be used in the Didactic Factory Pilot DFXI: AI-driven Monitoring of Robotic Assembly Process''
</p>

== Relevant Categories==
[[Category:Jupyter Notebook]][[Category:Python]][[Category:Model]][[Category:Machine Learning]][[Category:Deep Learning]][[Category:Anomaly Detection]][[Category:Quality Control]][[Category:Process Optimisation]][[Category:Predictive Maintenance]][[Category:Fault Detection]][[Category:Edge]]