Dataset for anomalies detection in 3D printing

TL;DR

This paper introduces a dataset collected from a 3D printer, including sensor data during malfunctions, to facilitate research on anomaly detection in industrial IoT applications.

Contribution

It provides a novel dataset with sensor streams from 3D printing malfunctions, enabling advancements in anomaly detection methods for Industry 4.0.

Findings

Dataset includes accelerometer, power, and temperature data during malfunctions

Data can be used to develop and evaluate anomaly detection algorithms

Supports research in IoT-based industrial monitoring

Abstract

Nowadays, Internet of Things plays a significant role in many domains. Especially, Industry 4.0 is making a great usage of concepts like smart sensors and big data analysis. IoT devices are commonly used to monitor industry machines and detect anomalies in their work. In this paper we present and describe a set of data streams coming from working 3D printer. Among others, it contains accelerometer data of printer head, intrusion power and temperatures of the printer elements. In order to gain data we lead to several printing malfunctions applied to the 3D model. Resulting dataset can therefore be used for anomalies detection research.