Industry 4.0 is strongly intertwined with big data streaming flows from intelligent sensors and machinery installed in industrial facilities. Failures can disrupt production and lead the supply chain ecosystem to malfunction. Maintenance strategies are necessary to safeguard the continuous operation of production lines, minimize supply chain disruptions, and improve sustainability indicators. Within the context of smart manufacturing, predictive maintenance (PdM) approaches could decrease downtimes, reduce operational costs, and increase productivity, improving system performance and decision-making. The overarching aim of this research is to systematically review state-of-the-art predictive maintenance applications across diverse manufacturing sectors to provide customized insights from academic and operational perspectives, summarized into a comparative decision support map. The study classifies predictive maintenance solutions based on prevailing methodologies, input features, predicted variables, applied algorithms, evaluation metrics, and state-of-the-art software tools per industry sector. The outcomes highlight that data-driven predictive maintenance constitutes a cutting-edge solution with a growing interest in modern manufacturing. Moreover, this research provides insights into the technology readiness of each industrial sector, covering modern areas for PdM implementation, while raising the extant challenges. The proposed multi-sector framework is expected to act as a guiding light for researchers and practitioners towards the development of PdM driven applications in data driven industries.

中文翻译：

---

工业 4.0 中的预测性维护：系统化的多部门映射

工业 4.0 与工业设施中安装的智能传感器和机械的大数据流密切相关。故障可能会扰乱生产并导致供应链生态系统出现故障。维护策略对于保障生产线的持续运行、最大限度地减少供应链中断并提高可持续性指标是必要的。在智能制造的背景下，预测维护 (PdM) 方法可以减少停机时间、降低运营成本、提高生产率、改善系统性能和决策。这项研究的总体目标是系统地回顾不同制造领域最先进的预测性维护应用，从学术和运营角度提供定制的见解，并总结为比较决策支持图。该研究根据每个行业的流行方法、输入特征、预测变量、应用算法、评估指标和最先进的软件工具对预测维护解决方案进行分类。结果表明，数据驱动的预测性维护构成了一种尖端解决方案，人们对现代制造业的兴趣与日俱增。此外，这项研究还深入了解了每个工业部门的技术准备情况，涵盖了 PdM 实施的现代领域，同时提出了现有的挑战。拟议的多部门框架预计将为研究人员和从业人员在数据驱动行业中开发 PdM 驱动的应用程序提供指导。