A dataset on in-situ electromagnetic wave integrity control of selective laser fusion printed parts using Machine Learning

DeepSLM Dataset

This dataset contains signals from metal parts printed in 3D using SLM (Selective laser melting) technology, produced as part of the DeepSLM project: In-situ monitoring of Selective-Laser-Melted Ti6Al4V Parts Using Eddy Current Testing and Machine Learning.

Sensor and data collection

An impedance-based non-destructive testing device is installed on the LPBF coating device. It is in the form of sensors with the following characteristics:

Spectrum of analysis of the sensors

Minimal length: 3-5 mm

Minimal width acquisition: 2-3 mm (Without borders effects)

Minimal number of layers: 50 layers

Signal minimal penetration depth (TiAl6V4/875kHz) = 1.5 mm

The sensors record the signal during printing, while simultaneously sending it to a computer via Bluetooth. The signals are first stored in the database. Next, a dataset is constructed from the extracted signals related to each part, and from the  added semi-automatic annotations which describe the porosity of the part and layers.

Annotations

In the annotation process, there are 2 different types of labels and a metadata summary for these prints:

1. Archimedean porosity measurement for the whole part2. Layer porosity obtained after image processing applied on the resulting metallography images3. Print-related metadata such as print parameters, part dimensions, layer thickness, etc

Size: 66 partsSet of printing parameters: 250

 --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Dataset organization

The dataset is composed of 7 different printings and is organized as follows:- signals: contains collected signals- metallography: contains porosity extracted by metallography- archimedean: contains porosity extracted by archimedean weighing- metallography-images: contains metallography process images- metadata.csv: contains print metadata (print parameter, part name, strategy, etc.)

Each printed part has a unique ID ranging from 0 to 65. Each sub-part has an ID which is the ID of the base part suffixed with the sub-part position: 14_1 is the first sub-part of part 14. This nomenclature is uniform throughout the dataset.

The README.md file in the dataset provides more detailed information on the structure of the dataset and the format of each of the files making up the dataset.

Relative article

https://doi.org/10.1007/978-3-031-47784-3_18

Sallem, H., Ghorbel, H., Goffinet, E., Cinna, A., Pralong, J., Wicht, J., & Revaz, B. (2023, May). In-Situ Monitoring of Selective Laser Melted Ti–6Al–4V Parts Using Eddy Current Testing and Machine Learning. In Advances In Additive Manufacturing Conference (pp. 139-148). Cham: Springer Nature Switzerland.