Dataset for "Filament Type Recognition for Additive Manufacturing Using a Spectroscopy Sensor and Machine Learning"

The file contains data collected from three sensors: AS72651, AS72652, and AS72653. Each of these sensor-specific files includes three folders representing different measurement distances: 12mm, 16mm, and 20mm. These folders contain data collected from 12 different filaments. Additionally, there is data recorded without a filament, labeled as "no_object." The following example of organizational structure is consistent across all filament data.

Folder : AS72651 ->12mm->first measurement: abs_carbonfiber1.csv
->second measurement: abs_carbonfiber2.csv
->third measurement: abs_carbonfiber3.csv
->three measurements together: abs_carbonfiber.csv

Each collected dataset is stored in CSV format. The data can be utilized for filament recognition using machine learning models, enabling the identification of different filament types based on sensor measurements.

Keywords:
filament recognition, machine learning, autonomous additive manufacturing, spectroscopy sensor
Subjects:
Information and communication technologies

Cite this dataset as:
Al, G., 2025. Dataset for "Filament Type Recognition for Additive Manufacturing Using a Spectroscopy Sensor and Machine Learning". Bath: University of Bath Research Data Archive. Available from: https://doi.org/10.15125/BATH-01501.

Export

Data

Spectroscopy … Filament_Dataset.zip
application/zip (304kB)
Creative Commons: Attribution 4.0

The folder contains three subfolders, each named after a sensor: AS72651, AS72652, and AS72653. Inside each of these subfolders, there are three additional folders corresponding to different measurement distances: 12mm, 16mm, and 20mm. The collected data for each filament is stored within these distance-specific folders.

Creators

Gorkem Anil Al
University of Bath

Contributors

University of Bath
Rights Holder

Documentation

Data collection method:

The methodology is described in the associated paper.

Funders

Engineering and Physical Sciences Research Council
https://doi.org/10.13039/501100000266

Manufacturing in Hospital: BioMed 4.0
EP/V051083/1

Publication details

Publication date: 3 March 2025
by: University of Bath

Version: 1

DOI: https://doi.org/10.15125/BATH-01501

URL for this record: https://researchdata.bath.ac.uk/1501

Related papers and books

Al, G. A., and Martinez-Hernandez, U., 2025. Filament Type Recognition for Additive Manufacturing Using a Spectroscopy Sensor and Machine Learning. Sensors, 25(5), 1543. Available from: https://doi.org/10.3390/s25051543.

Contact information

Please contact the Research Data Service in the first instance for all matters concerning this item.

Contact person: Gorkem Anil Al

Departments:

Faculty of Engineering & Design
Electronic & Electrical Engineering

Research Centres & Institutes
Centre for Digital, Manufacturing & Design (dMaDe)