Unsupervised electric motor fault detection by using deep autoencoders

TLDR: An unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders, and the results showed that all the autoencoder-based approaches outperform the OC-SVM algorithm.

Abstract: Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literature for detecting faults automatically. Deep neural networks have been successfully employed for this task, but, up to the authors &#x02BC knowledge, they have never been used in an unsupervised scenario. This paper proposes an unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders. In the proposed method, vibration signals are acquired by using accelerometers and processed to extract Log-Mel coefficients as features. Autoencoders are trained by using normal data only, i.e., data that do not contain faults. Three different autoencoders architectures have been evaluated: the multi-layer perceptron &#x0028 MLP &#x0029 autoencoder, the convolutional neural network autoencoder, and the recurrent autoencoder composed of long short-term memory &#x0028 LSTM &#x0029 units. The experiments have been conducted by using a dataset created by the authors, and the proposed approaches have been compared to the one-class support vector machine &#x0028 OC-SVM &#x0029 algorithm. The performance has been evaluated in terms area under curve &#x0028 AUC &#x0029 of the receiver operating characteristic curve, and the results showed that all the autoencoder-based approaches outperform the OC-SVM algorithm. Moreover, the MLP autoencoder is the most performing architecture, achieving an AUC equal to 99.11 &#x0025.