SFFDD: Deep Neural Network with Enriched Features for Failure Prediction with Its Application to Computer Disk Driver
This work addresses failure prediction for computer disk drives to improve storage system availability and prevent data loss, but it appears incremental as it builds on existing methods with feature enhancements.
The authors tackled the problem of predicting system failures using multivariate time series sensor data by proposing a classification technique with a novel feature derivation method, treating the data as images and applying transformations to characterize failure patterns, which resulted in a large improvement in classification accuracy.
A classification technique incorporating a novel feature derivation method is proposed for predicting failure of a system or device with multivariate time series sensor data. We treat the multivariate time series sensor data as images for both visualization and computation. Failure follows various patterns which are closely related to the root causes. Different predefined transformations are applied on the original sensors data to better characterize the failure patterns. In addition to feature derivation, ensemble method is used to further improve the performance. In addition, a general algorithm architecture of deep neural network is proposed to handle multiple types of data with less manual feature engineering. We apply the proposed method on the early predict failure of computer disk drive in order to improve storage systems availability and avoid data loss. The classification accuracy is largely improved with the enriched features, named smart features.