MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection
This dataset addresses the problem of machine failure monitoring for industrial companies, but it is incremental as it fills a gap in existing public datasets without introducing new methods.
The authors tackled the lack of public datasets for industrial machine sound monitoring by creating the MIMII dataset, which includes normal and anomalous sounds from valves, pumps, fans, and slide rails in real factory environments to support automated maintenance development.
Factory machinery is prone to failure or breakdown, resulting in significant expenses for companies. Hence, there is a rising interest in machine monitoring using different sensors including microphones. In the scientific community, the emergence of public datasets has led to advancements in acoustic detection and classification of scenes and events, but there are no public datasets that focus on the sound of industrial machines under normal and anomalous operating conditions in real factory environments. In this paper, we present a new dataset of industrial machine sounds that we call a sound dataset for malfunctioning industrial machine investigation and inspection (MIMII dataset). Normal sounds were recorded for different types of industrial machines (i.e., valves, pumps, fans, and slide rails), and to resemble a real-life scenario, various anomalous sounds were recorded (e.g., contamination, leakage, rotating unbalance, and rail damage). The purpose of releasing the MIMII dataset is to assist the machine-learning and signal-processing community with their development of automated facility maintenance. The MIMII dataset is freely available for download at: https://zenodo.org/record/3384388