Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey
FZI Research Center for Information Technology（FZI信息技术研究中心）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Siemens（西门子）；NXP Semiconductors Germany GmbH（恩智浦半导体德国有限公司）
Alexandru Vasilache, Sven Nitzsche, Daniel Floegel, Tobias Schuermann, Stefan von Dosky, Thomas Bierweiler, Marvin Mußler, Florian Kälber, Soeren Hohmann, Juergen Becker
备注：
The final version will be published at the ECML-PKDD 2024 joint post-workshop proceeding in Springer Communications in Computer and Information Science
The advancements in smart sensors for Industry 4.0 offer ample opportunities for low-powered predictive maintenance and condition monitoring. However, traditional approaches in this field rely on processing in the cloud, which incurs high costs in energy and storage. This paper investigates the potential of neural networks for low-power on-device computation of vibration sensor data for predictive maintenance. We review the literature on Spiking Neural Networks (SNNs) and Artificial Neuronal Networks (ANNs) for vibration-based predictive maintenance by analyzing datasets, data preprocessing, network architectures, and hardware implementations. Our findings suggest that no satisfactory standard benchmark dataset exists for evaluating neural networks in predictive maintenance tasks. Furthermore frequency domain transformations are commonly employed for preprocessing. SNNs mainly use shallow feed forward architectures, whereas ANNs explore a wider range of models and deeper networks. Finally, we highlight the need for future research on hardware implementations of neural networks for low-power predictive maintenance applications and the development of a standardized benchmark dataset.
A Survey on Predictive Maintenance for Industry 4.0
University of Würzburg（维尔茨堡大学）；University of Mannheim（曼海姆大学）；Syntax Systems GmbH；MOZYS Engineering GmbH；Chair of Information Systems II（信息系统II研究所）；Software Engineering Group（软件工程组）
Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance
FZI Research Center for Information Technology（弗劳恩霍夫信息技术研究中心）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；NETZSCH Pumpen und Systeme GmbH（NETZSCH泵与系统有限公司）；Infineon Technologies（英飞凌科技）
Research on Milling Machine Predictive Maintenance Based on Machine Learning and SHAP Analysis in Intelligent Manufacturing Environment
School of Advanced Manufacturing Engineering（先进制造工程学院）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；School of Computing and Information Systems（计算与信息学院）；The University of Melbourne（墨尔本大学）；School of Science, Computing and Engineering Technologies（科学、计算与工程技术学院）；Swinburne University of Technology（斯威本科技大学）；Gezhi Future Research Institute（智未来研究院）
Online Detection of Vibration Anomalies Using Balanced Spiking Neural Networks
Institute of Neuroinformatics, University of Zurich and ETH Zurich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）；KTH Royal Institute of Technology（瑞典皇家理工学院）；University of Hertfordshire（赫特福德大学）；Western Sydney University（西悉尼大学）
Vibe2Spike: Batteryless Wireless Tags for Vibration Sensing with Event Cameras and Spiking Networks
Department of EECS, The University of Tennessee, Knoxville（电子工程与计算机科学系，田纳西大学）；Department of ECE, Oklahoma State University（电气与计算机工程系，俄克拉荷马州立大学）；Accenture Labs, Accenture（Accenture实验室，Accenture）
Vibe2Spike 提出一种无电池无线振动感知框架，利用压电片、齐纳二极管和 LED 组成的超低成本标签采集振动能量并发射可见光脉冲，结合事件相机与演化优化的脉冲神经网络实现活动识别，在五类设备上达到 94.9% 的平均分类适应度。
