Abstract Context: As Industrial Cyber–Physical Systems (ICPS) become more connected and widely-distributed, often operating in safety-critical environments, we require innovative approaches to detect and diagnose the faults that occur in them. Objective: We profile fault identification and diagnosis techniques employed in the aerospace, automotive, and industrial control domains. Each of these sectors has adopted particular methods to meet their differing diagnostic needs. By examining both theoretical presentations as well as case studies from production environments, we present a profile of the current approaches being employed and identify gaps. Methodology: A scoping study was used to identify and compare fault detection and diagnosis methodologies that are presented in the current literature. We created categories for the different diagnostic approaches via a pilot study and present an analysis of the trends that emerged. We then compared the maturity of these approaches by adapting and using the NASA Technology Readiness Level (TRL) scale. Results: Fault identification and analysis studies from 127 papers published from 2004 to 2019 reveal a wide diversity of promising techniques, both emerging and in-use. These range from traditional Physics-based Models to Data-Driven Artificial Intelligence (AI) and Knowledge-Based approaches. Hybrid techniques that blend aspects of these three broad categories were also encountered. Predictive diagnostics or prognostics featured prominently across all sectors, along with discussions of techniques including Fault trees, Petri nets and Markov approaches. We also profile some of the techniques that have reached the highest Technology Readiness Levels, showing how those methods are being applied in real-world environments beyond the laboratory. Conclusions: Our results suggest that the continuing wide use of both Model-Based and Data-Driven AI techniques across all domains, especially when they are used together in hybrid configuration, reflects the complexity of the current ICPS application space. While creating sufficiently-complete models is labor intensive, Model-free AI techniques were evidenced as a viable way of addressing aspects of this challenge, demonstrating the increasing sophistication of current machine learning systems. Connecting ICPS together to share sufficient telemetry to diagnose and manage faults is difficult when the physical environment places demands on ICPS. Despite these challenges, the most mature papers present robust fault diagnosis and analysis techniques which have moved beyond the laboratory and are proving valuable in real-world environments.

中文翻译：

---

查找故障：工业信息物理系统故障诊断的范围研究

摘要背景：随着工业网络物理系统 (ICPS) 变得更加连接和广泛分布，通常在安全关键环境中运行，我们需要创新的方法来检测和诊断其中发生的故障。目标：我们概述了航空航天、汽车和工业控制领域中采用的故障识别和诊断技术。这些部门中的每一个都采用了特定的方法来满足其不同的诊断需求。通过检查理论演示以及生产环境中的案例研究，我们展示了当前采用的方法的概况并找出差距。方法：范围界定研究用于识别和比较当前文献中提出的故障检测和诊断方法。我们通过试点研究为不同的诊断方法创建了类别，并对出现的趋势进行了分析。然后，我们通过调整和使用 NASA 技术准备水平 (TRL) 量表来比较这些方法的成熟度。结果：对 2004 年至 2019 年发表的 127 篇论文的故障识别和分析研究揭示了新兴和正在使用的各种有前途的技术。这些范围从传统的基于物理的模型到数据驱动的人工智能 (AI) 和基于知识的方法。还遇到了融合这三大类方面的混合技术。预测诊断或预测在所有领域都占有突出地位，同时还讨论了包括故障树、Petri 网和马尔可夫方法在内的技术。我们还介绍了一些达到最高技术就绪水平的技术，展示了这些方法如何应用于实验室以外的现实环境中。结论：我们的结果表明，基于模型和数据驱动的 AI 技术在所有领域的持续广泛使用，尤其是当它们在混合配置中一起使用时，反映了当前 ICPS 应用程序空间的复杂性。虽然创建足够完整的模型是劳动密集型的，但无模型 AI 技术被证明是解决这一挑战的可行方法，证明了当前机器学习系统的日益复杂。当物理环境对 ICPS 提出要求时，将 ICPS 连接在一起以共享足够的遥测数据来诊断和管理故障是很困难的。