Interpretable Predictive Maintenance for Hard Drives
This work addresses the need for interpretable predictive maintenance for data center operators, offering a solution that is not just incremental but enhances trust and usability in real-world scenarios.
The paper tackled the problem of predicting hard drive failure in data centers by applying interpretable machine learning methods, achieving high predictive performance while providing meaningful insights into drive health, even with limited historical data.
Existing machine learning approaches for data-driven predictive maintenance are usually black boxes that claim high predictive power yet cannot be understood by humans. This limits the ability of humans to use these models to derive insights and understanding of the underlying failure mechanisms, and also limits the degree of confidence that can be placed in such a system to perform well on future data. We consider the task of predicting hard drive failure in a data center using recent algorithms for interpretable machine learning. We demonstrate that these methods provide meaningful insights about short- and long-term drive health, while also maintaining high predictive performance. We also show that these analyses still deliver useful insights even when limited historical data is available, enabling their use in situations where data collection has only recently begun.