Audio Visual in-situ Monitoring Dataset for Laser Directed Energy Deposition (LDED) of Maraging Steel C300

This dataset presents a set of acoustic signals and coaxial CCD images captured during a single-bead wall experiment in robotic Laser Directed Energy Deposition (LDED) using Maraging Steel C300. The acoustic data was recorded using a high-fidelity Prepolarized microphone sensor (Xiris WeldMIC), capturing the intricate sound profiles associated with the LDED process at a sampling rate of 44,100 Hz. The coaxial CCD melt pool images are captured at 30 Hz.

Laser Directed Energy Deposition:

This dataset was generated with a robotic LDED process that consists of a six-axis industrial robot (KUKA KR90) coupled with a two-axis positioner, a laser head, and a coaxial powder-feeding nozzle.

File Naming Convention:

Audio files within the audio_files folder are named following the pattern sample_ExperimentID_SampleID.wav. Given that there's only one experiment and one sample provided in this demo dataset, the naming will be consistent, for example, sample_1_1.wav for the first file.

Coaxial melt pool image files within the images folder are named following the pattern sample_ExperimentID_SampleID.jpg. 

Annotation Details:

The annotations_1.csv file contains detailed labels for each audio file and image file, correlating to the conditions observed during the experiment, aiding in quick identification and analysis.

Handcrafted features for ML modelling:

The audio_features.h5 file contains various physics-informed acousitc feature extracted through Python, which can be used for baseline ML modelling purpose.

Experimental Parameters: The dataset reflects a controlled experiment setup with the following specifications:

Geometry: Single bead wall structure

Dimensions: 90 mm * 42.5 mm

Number of layers: 50

Laser beam diameter: 2 mm

Layer thickness: 0.85 mm

Stand-off distance: 12 mm

Laser profile: Gaussian

Laser wavelength: 1064 nm

Process Parameters:

Laser power: 2.3 kW

Speed: 25 mm/s

Dwell time: 0 s

Powder flow rate: 12 g/min

This dataset aims to facilitate the development and testing of acoustic-based, or multi-sensor fusion-based defect detection models for real-time quality monitoring in LDED processes. It can also serve as a reference point for further research on sensor fusion, machine learning, and real-time monitoring of manufacturing processes.