Abstract—Identifying the “health state” of the equipment is the domain of condition monitoring. The paper proposes a study of two models: DNN (Deep Neural Network) and CNN (Convolutional Neural Network) over an existent dataset provided by Case Western Reserve University for analyzing vibrations in fault diagnosis. After the model is trained on the windowed dataset using an optimal learning rate, minimizing the cost function, and is tested by computing the loss, accuracy and precision across the results, the weights are saved, and the models can be tested on other real data. The trained model recognizes raw time series data collected by micro electro-mechanical accelerometer sensors and detects anomalies based on former times series entries.
Index Terms—DNN, CNN, anomaly detection, fault diagnosis, vibration analyses condition monitoring, industry 4.0.
The authors are with the University “Politehnica” of Bucharest, Romania (e-mail: george.deac@impromedia.ro, crina.deac@impromedia.ro, radu.parpala@gmail.com, laur.popa79@gmail.com, costelemilcotet@gmail.com).
[PDF]
Cite: Crina Deac, Gicu Călin Deac, Radu Constantin Parpală, Cicerone Laurentiu Popa, and Costel Emil Cotet, "Vibration Anomaly Detection using Deep Neural Network and Convolutional Neural Network," International Journal of Modeling and Optimization vol. 11, no. 1, pp. 19-28, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
(CC BY 4.0).