Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Using Classification-Based Methods

The task of unsupervised anomalous sound detection (ASD) is challenging for detecting anomalous sounds from a large audio database without any annotated anomalous training data. Many unsupervised methods were proposed, but previous works have confirmed that the classification-based models far exceeds the unsupervised models in ASD. In this paper, we adopt two classification-based anomaly detection models: (1) Outlier classifier is to distinguish anomalous sounds or outliers from the normal; (2) ID classifier identifies anomalies using both the confidence of classification and the similarity of hidden embeddings. We conduct experiments in task 2 of DCASE 2020 challenge, and our ensemble method achieves an averaged area under the curve (AUC) of 95.82% and averaged partial AUC (pAUC) of 92.32%, which outperforms the state-of-the-art models.

Unsupervised Detection of Anomalous Sound for Machine Condition Monitoring using Fully Connected U-Net

Anomaly detection in the sound from machines is an important task in machine monitoring. An autoencoder architecture based on the reconstruction error using a log-Mel spectrogram feature is a conventional approach for this domain. However, because of the non-stationary nature of some sounds from the target machine, such a conventional approach does not perform well in those circumstances. In this paper, we propose a novel approach regarding the choice of used features and a new auto-encoder architecture. We created the Mixed Feature, which is a mixture of different sound representations, and a new deep learning method called Fully-Connected U-Net, a form of autoencoder architecture. With experiments on the same dataset as the baseline system, using the same architecture for all types of machines, the experimental results showed that our methods outperformed the baseline system in terms of the AUC and pAUC evaluation metrics. The optimized model achieved 83.38% AUC and 64.51% pAUC on average overall machine types on the developed dataset and outperformed the published baseline by 13.43% AUC and 8.13% pAUC.

Predictive Maintenance of Compressor Using ThingSpeak IoT Platform

Any instrument or machine that needs to be monitored and inspected on a regular basis to ensure its long life and proper maintenance. Machine condition monitoring in the time and frequency domain is unquestionably required to ensure reliability. Condition monitoring is a method of observing a machine's condition parameter (vibration, temperature and etc.), with the explicit objective of detecting a substantial change that could indicate the onset of a malfunction It's an important part of compressor predictive maintenance and lowering compressor downtime. In today's world, the Internet of Things (IoT) is the most effective approach and technology for continuously monitoring the state of any machine. We've employed MEMS sensors to detect misalignment, non-linearity, and other anomalies., Through the Wi-Fi module ESP8266, vibrations and temperature in compressors, as well as changes in signals, will be communicated to the cloud. These signals are in order in the temporal domain. The Fast Fourier transform is used to examine and convert the time domain sequence into the frequency domain.