Article
Computer Science, Artificial Intelligence
Antonino Ferraro, Antonio Galli, Vincenzo Moscato, Giancarlo Sperli
Summary: In recent years, the optimization of maintenance operations has been a major challenge in Industry 4.0. Various predictive maintenance frameworks have been developed to reduce maintenance costs and downtime intervals. However, these frameworks often rely on complex deep learning models, making it difficult for humans to understand their predictions. This paper focuses on using explainable artificial intelligence (XAI) methodologies to explain the predictions made by a recurrent neural network model for estimating the remaining useful life (RUL) of hard disk drives (HDDs). The results show that the SHapley Additive exPlanations (SHAP) method outperforms the local interpretable model-agnostic explanations (LIME) method, providing a suitable and effective solution for HDD predictive maintenance applications.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Automation & Control Systems
Jishan Ahmed, Robert C. Green II
Summary: This study proposes the use of long short term memory networks and a modified focal loss function to address the class imbalance issue in failure prediction. Comparing with traditional machine learning algorithms, the results demonstrate that this approach achieves better performance while maintaining a higher failure detection rate.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Chemistry, Physical
Tomasz Skrzekut, Maciej Wedrychowicz, Andrzej Piotrowicz
Summary: The paper presents a comparison study on two methods of recycling aluminum from HDD platters – the melting method and the method of plastic consolidation. The study involved examining the composition and properties of HDD memory components, specifically the data carriers (platters), through various tests and analysis. The results provide insights into the performance characteristics of the materials under different recycling methods.
Article
Materials Science, Multidisciplinary
Akihiko Aoyagi, Barry Stipe, Roger Wood, Steven Campbell, Xiaodong Che
Summary: This paper describes the history and advantages of helium-sealed HDDs, and discusses the future prospects of sealed-drive technology.
JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS
(2022)
Article
Engineering, Environmental
Kali Frost, Ines Sousa, Joanne Larson, Hongyue Jin, Inez Hua
Summary: This study evaluated a pilot-scale R&R process for RE magnet assemblies and compared the environmental impacts using life cycle assessment (LCA). The results showed an 86% reduction in global warming potential and highlighted the benefits of collocated R&R process with data centers.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Engineering, Environmental
Julien Walzberg, Robin Burton, Fu Zhao, Kali Frost, Stephanie Muller, Alberta Carpenter, Garvin Heath
Summary: By 2025, the installed data storage capacity in the US is projected to reach 2.2 Zettabytes, resulting in around 50 million units of end-of-life hard-disk drives (HDDs) annually. Currently, most EOL HDDs are shredded due to data security concerns, causing economic loss. Additionally, the extraction of raw materials for storage production has environmental impacts. A circular economy (CE) approach, involving reuse and recycling, can maximize value retention and minimize environmental impacts. However, the lack of trust in non-physical data removal methods hinders HDD reuse. This study proposes an agent-based modeling (ABM) approach to analyze the factors influencing end-users' decisions to adopt alternative EOL management practices. The results highlight the potential of green procurement and robust standards in building trust in data wiping technologies, demonstrating the environmental and economic benefits of HDD reuse compared to shredding and material recovery.
RESOURCES CONSERVATION AND RECYCLING
(2022)
Article
Engineering, Multidisciplinary
Takenori Atsumi, Shota Yabui
Summary: The future of cloud services relies on the growth of hard disk drive (HDD) capacity to meet the increasing demands for data storage. To address this, a proposed control system design method for future HDD technology called the quadruple-stage actuator system is introduced, using a robust controller design approach with visualized guidelines. Validation results demonstrate that the proposed control system exhibits strong robustness against significant disturbances for HDDs.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Sladjana M. Djurasevic, Uros M. Pesovic, Borislav S. Djordjevic
Summary: The electromechanical design of HDD makes it prone to failures, which can result in permanent data loss. The SMART system warns users of potential failures by monitoring HDD parameters. This paper introduces a machine learning-based anomaly detection model for accurate failure prediction and timely data backup.
APPLIED ARTIFICIAL INTELLIGENCE
(2021)
Article
Chemistry, Analytical
Tek Raj Chhetri, Anelia Kurteva, Jubril Gbolahan Adigun, Anna Fensel
Summary: Hard drive failure can lead to system crashes and data loss. Current studies on hard drive failure prediction mostly rely on machine learning, lacking context-awareness. Semantic technology provides context-awareness through knowledge graphs, but lacks the learning patterns and prediction capabilities of machine learning. This paper presents a method that combines the advantages of both machine learning and semantic technology, achieving higher accuracy in hard drive failure prediction.
Article
Engineering, Electrical & Electronic
Wei Jiang, Gang Zhu, Ying Zheng
Summary: By combining ILC with LESO for AGV drive motor control, the precision of control can be enhanced and the positional accuracy of AGV workflow can be improved, especially in dealing with estimation and compensation of non-repetitive load disturbances.
Article
Chemistry, Multidisciplinary
Mingyu Zhang, Wenqiang Ge, Ruichun Tang, Peishun Liu
Summary: This paper proposes a novel failure prediction method that combines machine learning algorithms and neural networks. Through experiments on the publicly available BackBlaze hard disk datasets, it demonstrates the superiority of this method in hard disk failure prediction and solves the problem of low robustness and generalization in traditional machine learning methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Physical
Botao Li, Yoshihiko Nishikawa, Philipp Hollmer, Louis Carillo, A. C. Maggs, Werner Krauth
Summary: This paper discusses pressure computations for the hard-disk model since 1953 and compares them with the results obtained from advanced Monte Carlo and Metropolis algorithms. The difficulty of estimating pressure in the hard-disk phase-transition scenario has not been fully recognized in the long-standing controversy. The authors present the physics of the hard-disk model, the definition of pressure, unbiased estimators, and different sampling algorithms and criteria for bounding mixing times.
JOURNAL OF CHEMICAL PHYSICS
(2022)
Article
Engineering, Electrical & Electronic
Pierre-Olivier Jubert, Yuri Obukhov, Cristian Papusoi, Paul Dorsey
Summary: The magnetic properties and recording capability of sputtered tape media were evaluated using HDD components. The addition of a magnetic cap significantly improved the performance of the sputtered tape, including recording performance. The results demonstrate the potential of achieving high areal density and further improvements in the tape medium.
IEEE TRANSACTIONS ON MAGNETICS
(2022)
Article
Physics, Applied
Hirofumi Suto, Masayuki Takagishi, Naoyuki Narita, Hitoshi Iwasaki, Tazumi Nagasawa, Gaku Koizumi, Akihiko Takeo, Tomoyuki Maeda
Summary: The paper investigates the application of microwave-assisted magnetic recording technology using the flux control effect in hard disk drives, confirming its effectiveness through experiments and validating the magnetization dynamics in actual devices through simulation models.
JOURNAL OF APPLIED PHYSICS
(2021)
Article
Physics, Multidisciplinary
Carl P. Dettmann, Orestis Georgiou
Summary: The random geometric graph is formed by a random point set with links between points within a fixed threshold. In this case, the same geometric connection rule is used for a deterministic point set called the sunflower spiral. The properties of the graph depend on a combination of the central region and the perturbed distant lattices.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Automation & Control Systems
Ran Jiao, Wenjie Liu, Ramy Rashad, Jianfeng Li, Mingjie Dong, Stefano Stramigioli
Summary: A novel end-effector bilateral rehabilitation robotic system (EBReRS) is developed for upper limb rehabilitation of patients with hemiplegia, providing simulations of multiple bimanual coordinated training modes, showing potential for application in home rehabilitation.
Article
Automation & Control Systems
Qiaosheng Pan, Yifang Zhang, Xiaozhu Chen, Quan Wang, Qiangxian Huang
Summary: A resonant piezoelectric rotary motor using parallel moving gears mechanism has been proposed and tested, showing high power output and efficiency.