ChatGPT-like large-scale foundation models for prognostics and health management: A survey and roadmaps*

PHM technology is vital in industrial production and maintenance, identifying and predicting potential equipment failures and damages. This enables proactive maintenance measures to be implemented, improving equipment reliability and reducing production costs. Recently, artificial intelligence (AI)-based PHM methods have made remarkable achievements, 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 AI due to its brilliant natural language understanding ability. However, the PHM field lacks a consensus on responding to this significant change, and systematic reviews and roadmaps are required to elucidate future development directions. Therefore, this paper expounds on the key components and latest developments of LSF-Models. Then, we systematically answered how to build LSF-Models applicable to PHM tasks and outlined the challenges and future development roadmaps for this research paradigm.