10.14489/td.2021.10.pp.036-043

2021, 10 October

DOI: 10.14489/td.2021.10.pp.036-043

Demidova L. A., Filatov A. V.
MONITORING AND CLASSIFYING THE STATE OF HARD DISKS USING RECURRENT NEURAL NETWORKS
(pp. 36-43)

Abstract. The article considers an approach to solving the problem of monitoring and classifying the states of hard disks, which is solved on a regular basis, within the framework of the concept of non-destructive testing. It is proposed to solve this problem by developing a classification model using machine learning algorithms, in particular, using recurrent neural networks with Simple RNN, LSTM and GRU architectures. To develop a classification model, a data set based on the values of SMART sensors installed on hard disks it used. It represents a group of multidimensional time series. At the same time, the structure of the classification model contains two layers of a neural network with one of the recurrent architectures, as well as a Dropout layer and a Dense layer. The results of experimental studies confirming the advantages of LSTM and GRU architectures as part of hard disk state classification models are presented.

Keywords: hard drives, nondestructive control, recurrent neural network, SIMPLE RNN, LSTM, GRU, SMART, binary classification, dataset.

+ - About the Authors Click to collapse

L. A. Demidova, A. V. Filatov (MIREA – Russian Technological University, Moscow, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - (References Click to collapse

1. Demidova L. A., Ivkina M. S., Marchev D. V. (2019). Application of the Machine Learning Tools in the Problem of Classifying Failures in the Work of the Complex Technical Systems. 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA), pp. 540 – 545. Lipetsk. DOI 10.1109/SUMMA48161. 2019.8947561.
2. Demidova L. A., Marchev D. V. (2019). Application of recurrent neural networks in the problem of classification of failures of complex technical systems in the framework of proactive maintenance. Vestnik Ryazanskogo gosudarstvennogo radio-tekhnicheskogo universiteta, 69, pp. 135 – 148. [in Russian language]
3. Li Q., Li H., Zhang K. (2019). A survey of SSD Lifecycle Prediction. IEEE 10th International Conference on Software Engineering and Service Science (ICSESS). Beijing.
4. Pereira F. L. F., Teixeira D. N., Gomes J. P. P., Machado J. C. (2019). Evaluating One-Class Classifiers for Fault Detection in Hard Disk Drives. 8th Brazilian Conference of Intelligent Systems (BRACIS). IEEE. Salvador
5. Quieroz L. P., Rodrigues F. C. M., Gomes J. P. P. et al. (2016). A fault detection metod for hard disk drives based on mixture of Gaussian and non-parametric statistics. IEEE Transaction of Industrial Informatics.
6. Ragmania A., Elomria A., Abghoura N. et al. (2020). Adaptive Faulttolerant Model for Improving Cloud Computing Performance Using Artificial Neural Network. The 10th International Symposium on Frontiers in Ambient and Mobile Systems (FAMS 2020). Procedia Computer Science, Vol. 170, pp. 929 – 934. Warsaw.
7. Tatbul N., Lee T. J., Zdonik S., Alam M., Gottschlich J. (2018). Precision and Recall for Time Series. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). Montreal.
8. Hochreiter S., Schmidhuber J. (1997). Long shortterm memory. Neural Computation journal, Vol. 9, (8), pp. 1735 – 1780.
9. Chung J., Gulcehre C., Cho K. H., Bengio Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, arΧiv:1412.3555. Available at: [1412.3555] Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling (arxiv.org).
10. Understanding LSTM Networks. Available at: http://colah.github.io/posts/2015-08-Understanding-LSTMs
11. Athira P., Geetha R., Vinayakumar K. P. S. (2018). DeepAirNet: Applying Recurrent Networks for Air Quality Prediction. Procedia Computer Science, Vol. 132, pp. 1394 – 1403.
12. Kingma D. P., Ba J. L. (2015). Adam: A Method for Stochastic Optimization. 3rd International Conference for Learning Representations. San Diego. (Preprint/arXiv.org; № 1412.6980)

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

The cost of a single article is 450 rubles. (including VAT 20%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/td.2021.10.pp.036-043

and fill out the form