MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection

@inproceedings{Purohit2019MIMIIDS,
  title={MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection},
  author={Harsh Purohit and Ryo Tanabe and Kenji Ichige and Takashi Endo and Yuki Nikaido and Kaori Suefusa and Yohei Kawaguchi},
  booktitle={DCASE},
  year={2019}
}
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… 

Figures and Tables from this paper

MIMII Due: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts Due to Changes in Operational and Environmental Conditions
TLDR
Experimental results showed significant performance differences between the source and target domains, indicating that the dataset contains the domain shifts, demonstrating that the datasets created will be helpful for checking the robustness against domain shifts.
A Supervised Approach for Corrective Maintenance Using Spectral Features from Industrial Sounds
TLDR
This paper addresses corrective maintenance based on fault recognition relying on sounds produced by machine components with promising results based on the f1-score and improves the AUC (Area Under the Curve) metric by up to 39.5% compared with the baseline approach.
ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions
TLDR
A large number of operating sounds of miniature machines (toys) under normal and anomaly conditions by deliberately damaging them but extended with providing controlled depth of damages in anomaly samples to propose a new large-scale dataset for anomaly detection in machine operating sounds (ADMOS).
ToyADMOS2 dataset: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions
TLDR
The ToyADMOS2 dataset is designed for evaluating systems under typical application scenarios of ADMOS often require robust performance under domain-shift conditions, and consists of two sub-datasets for machine-condition inspection: fault diagnosis of machines with geometrically fixed tasks and fault diagnosisof machines with moving tasks.
Acoustic Anomaly Detection of Mechanical Failures in Noisy Real-Life Factory Environments
TLDR
A noise-tolerant deep learning-based methodology for real-life sound-data-based anomaly detection within real-world industrial machinery sound data and the main element of the proposed methodology is a generative adversarial network (GAN) used for the reconstruction of sound signal reconstruction and the detection of anomalies.
Health Monitoring of Industrial machines using Scene-Aware Threshold Selection
TLDR
This paper presents an autoencoder based unsupervised approach to identify anomaly in an industrial machine using sounds produced by the machine using log-melspectrogram representations of the sound signal and proposes a scene classification framework, which can classify the underlying surrounding.
Canonical polyadic decomposition and deep learning for machine fault detection
TLDR
This work proposes a powerful data-driven and quasi non-parametric denoising strategy for spectral data based on a tensor decomposition: the Non-negative Canonical Polyadic (CP) decomposition.
FEATURE BASED FUSION SYSTEM FOR ANOMALOUS SOUNDS MONITORING Technical Report
TLDR
This paper introduces the system for Task2 of Dcase 2020 challenges (Unsupervised Detection of Anomalous Sounds for Machine Condition Monitoring), and shows that for different machine type, different features may improve the detection results respectively, and DAE is more likely to preform much better than machine learning techniques.
IAEO3-COMBINING OPENL3 EMBEDDINGS AND INTERPOLATION AUTOENCODER FOR ANOMALOUS SOUND DETECTION Technical Report
TLDR
This proposed method combines pre-trained OpenL3 embeddings with the reconstruction error of an interpolation autoencoder using a gaussian mixture model as the final predictor and outperformed the published baseline by 14.9% AUC and 17.2% pAUC.
Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net
TLDR
The Mixed Feature is created, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture, which outperformed the baseline system in terms of the AUC and pAUC evaluation metrics.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection
TLDR
This paper introduces a new dataset called "ToyADMOS" designed for anomaly detection in machine operating sounds ( ADMOS), which consists of three sub-datasets for machine-condition inspection, fault diagnosis of machines with geometrically fixed tasks, and fault diagnosisof machines with moving tasks.
Residual Error Based Anomaly Detection Using Auto-Encoder in SMD Machine Sound
TLDR
This paper proposes to detect abnormal operation sounds or outliers in a very complex machine along with reducing the data-driven annotation cost by using an auto-encoder, and uses the residual error, which stands for its reconstruction quality, to identify the anomaly.
Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge
TLDR
The emergence of deep learning as the most popular classification method is observed, replacing the traditional approaches based on Gaussian mixture models and support vector machines.
Diagnosis of tidal turbine vibration data through deep neural networks
TLDR
This paper investigates the use of deep learning approaches for fault detection within a tidal turbine's generator from vibration data, and evaluates a deep learning approach through a stacked autoencoder network in comparison to feature-based classification methods.
The SINS Database for Detection of Daily Activities in a Home Environment Using an Acoustic Sensor Network
TLDR
A database recorded in one living home, over a period of one week, containing activities being performed in a spontaneous manner, which make use of an acoustic sensor network, and are recorded as a continuous stream is introduced.
Unsupervised Detection of Anomalous Sound Based on Deep Learning and the Neyman–Pearson Lemma
TLDR
This paper proposes a novel optimization principle and its implementation for unsupervised anomaly detection in sound (ADS) using an autoencoder (AE) and defines an objective function based on the Neyman–Pearson lemma by considering the ADS as a statistical hypothesis test.
Anomaly Detection Based on an Ensemble of Dereverberation and Anomalous Sound Extraction
TLDR
Experimental results indicate that the proposed method for detecting anomalous sounds based on a front-end ensemble consisting of a blind-dereverberation algorithm and multiple anomalous-sound-extraction algorithms improves detection performance significantly.
Structured Denoising Autoencoder for Fault Detection and Analysis
TLDR
A new fault detection and analysis approach which can leverage incomplete prior information is proposed, called the structured denoising autoencoder (StrDA), which does not require specic information and can perform well without overtting.
How can we detect anomalies from subsampled audio signals?
  • Y. Kawaguchi, Takashi Endo
  • Computer Science
    2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2017
TLDR
Experimental results indicate that the proposed method for reducing the sampling rate and applying a long short-term memory-(LSTM)-based autoencoder network for detecting anomalies is suitable for anomaly detection from the subsampled signal.
A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks
TLDR
This paper presents a novel unsupervised approach based on a denoising autoencoder which significantly outperforms existing methods by achieving up to 93.4% F-Measure.
...
...