engleski

CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis

Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. Traditional data-driven techniques for fault diagnosis require signal processing for feature extraction, as they are unable to work with raw signal data, consequently leading to need for both expert knowledge and human work. This paper presents authors research in deep learning-based data-driven fault diagnosis of rotating subsystems. Different combinations of hyperparameters are prepared for training and testing. Then, convolutional artificial neural network is used for training a model that can predict class identifying the state of the rotary machinery based on the collected data. Accuracy on test data is used as a metric for hyperparameters combination effectiveness.

condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks

nije evidentirano