Prognostics and health management (PHM) technology plays a critical role in industrial production and equipment maintenance by identifying and predicting possible equipment failures and damages, thereby allowing necessary maintenance measures to be taken to enhance equipment service life and reliability while reducing production costs and downtime. In recent years, PHM technology based on artificial intelligence (AI) has made remarkable achievements in the context of the industrial IoT and big data, and it is widely used in various industries, such as railway, energy, and aviation, for condition monitoring, fault prediction, and health management. The emergence of large-scale foundation models (LSF-Models) such as ChatGPT and DALLE-E marks the entry of AI into a new era of AI-2.0 from AI-1.0, where deep models have rapidly evolved from a research paradigm of single-modal, single-task, and limited-data to a multi-modal, multi-task, massive data, and super-large model paradigm. ChatGPT represents a landmark achievement in this research paradigm, offering hope for general artificial intelligence due to its highly intelligent natural language understanding ability. However, the PHM field lacks a consensus on how to respond to this significant change in the AI field, and a systematic review and roadmap is required to elucidate future development directions. To fill this gap, this paper systematically expounds on the key components and latest developments of LSF-Models. Then, we systematically answered how to build the LSF-Model applicable to PHM tasks and outlined the challenges and future development roadmaps for this research paradigm.

翻译：预测与健康管理（PHM）技术在工业生产和设备维护中发挥着关键作用，通过识别和预测可能的设备故障与损伤，以便采取必要的维护措施，提高设备使用寿命和可靠性，同时降低生产成本和停机时间。近年来，基于人工智能（AI）的PHM技术在工业物联网和大数据背景下取得了显著成就，广泛应用于铁路、能源、航空等行业的状态监测、故障预测和健康管理。ChatGPT和DALL-E等大规模基础模型（LSF-Models）的出现标志着AI从AI-1.0进入AI-2.0新时代，深度模型已从单模态、单任务、有限数据的研究范式快速演变为多模态、多任务、海量数据和超大规模模型范式。ChatGPT是该研究范式的一个里程碑式成果，凭借其高度智能的自然语言理解能力，为通用人工智能带来了希望。然而，PHM领域尚未就如何应对AI领域的这一重大变革达成共识，需要系统的综述和路线图来阐明未来发展方向。为填补这一空白，本文系统阐述了LSF-Models的关键组成部分和最新进展，然后系统回答了如何构建适用于PHM任务的LSF-Model，并概述了该研究范式面临的挑战及未来发展路线图。