PHM-GPT: A Large Language Model for Prognostics and Health Management

Jiaxin Ren; Xue Liu; Tianlei Wang; Zhibin Zhao; Xuefeng Chen; Weihua Li; Ruqiang Yan

doi:10.1016/j.eng.2025.11.001

Engineering ›› :202511001 DOI: 10.1016/j.eng.2025.11.001

Research

research-article

PHM-GPT: A Large Language Model for Prognostics and Health Management

Jiaxin Ren ^a^,^b
, Xue Liu ^a^,^b
, Tianlei Wang ^a^,^b
, Zhibin Zhao ^a^,^b
, Xuefeng Chen ^a^,^b
, Weihua Li ^c
, Ruqiang Yan ^a^,^b^,^*

Author information +

History +

PDF (3770KB)

Abstract

In the digital transformation era of the fourth industrial revolution, prognostics and health management (PHM) is playing increasingly important roles in various engineering fields. As the complexity of industrial systems continues to increase, model-based or data-driven PHM technologies face growing challenges related to interpretability, generalization, and applicability, which limit the widespread deployment of PHM technologies. To address these challenges, this PHM-GPT, a large language model (LLM) specifically designed for PHM, is proposed in this paper. By leveraging LLMs, the PHM-GPT unifies anomaly detection, fault diagnosis, and maintenance decision-making tasks, enabling robust generalization across diverse datasets. In detail, a signal-to-text (S2T) pipeline is presented to develop the InsPHM-456k dataset, focusing on representative components such as bearings and gears. Furthermore, a novel framework for adapting general-purpose LLMs into PHM-specific LLMs is proposed through knowledge injection-based pretraining, PHM-specific instruction tuning, and downstream application fine-tuning during PHM. Additionally, an efficient architecture is introduced to incorporate low-rank adaptation adapters into the group attention module and the feedforward neural network. To validate the effectiveness of the PHM-GPT, extensive simulation studies are conducted, demonstrating its strong generalization across diverse datasets and its broad applicability to machinery components such as bearings and gears. Beyond automatically providing anomalies, diagnoses, and maintenance results, the PHM-GPT exhibits emergent abilities that have never been observed before, such as attribution reasoning, threshold setting, and knowledge discovery, which contribute to enhanced qualitative interpretability and deeper insight into system behaviors. Finally, this paper provides new insights into the PHM field and explores the future of LLMs in terms of advancing PHM technology deployment, accelerating the digital transformation process during the fourth industrial revolution.

Keywords

Prognostics and Health Management / Large Language Model / Fault Diagnosis

Cite this article

Download citation ▾

Jiaxin Ren, Xue Liu, Tianlei Wang, Zhibin Zhao, Xuefeng Chen, Weihua Li, Ruqiang Yan. PHM-GPT: A Large Language Model for Prognostics and Health Management. Engineering 202511001 DOI:10.1016/j.eng.2025.11.001

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Vogl GW, Weiss BA, Helu M. A review of diagnostic and prognostic capabilities and best practices for manufacturing. J Intell Manuf 2019; 30(1):79-95.

[2]	Ranasinghe K, Sabatini R, Gardi A, Bijjahalli S, Kapoor R, Fahey T, et al. Advances in integrated system health management for mission-essential and safety-critical aerospace applications. Prog Aerosp Sci 2022;128:100758.

[3]	Dirkes S, Leidig J, Fisch P, Pischinger S. Prescriptive lifetime management for PEM fuel cell systems in transportation applications, part I: state of the art and conceptual design. Energ Conver Manage 2023;277:116598.

[4]	Jiang G, He H, Yan J, Xie P. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Trans Ind Electron 2019; 66(4):3196-207.

[5]	Huang Y, Tao J, Sun G, Wu T, Yu L, Zhao X. A novel digital twin approach based on deep multimodal information fusion for aero-engine fault diagnosis. Energy 2023;270:126894.

[6]	Zio E. Prognostics and Health Management (PHM): where are we and where do we (need to) go in theory and practice. Reliab Eng Syst Saf 2022;218:108119.

[7]	Bao Y, Chen Z, Wei S, Xu Y, Tang Z, Li H. The state of the art of data science and engineering in structural health monitoring. Engineering 2019; 5(2):234-42.

[8]	Li Y, Wang Q, Pan X, Zuo J, Xu J, Han Y. Digital twins for engineering asset management: synthesis, analytical framework, and future directions. Engineering 2024;41:261-75.

[9]	Liao SH. Expert system methodologies and applications—a decade review from 1995 to 2004. Expert Syst Appl 2005; 28(1):93-103.

[10]	Widodo A, Yang BS. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Sig Process 2007; 21(6):2560-74.

[11]	Breiman L. Random forests. Mach Learn 2001; 45(1):5-32.

[12]	Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans Inf Theory 1967; 13(1):21-7.

[13]	Lei Y, Yang B, Jiang X, Jia F, Li N, Nandi AK. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Sig Process 2020;138:106587.

[14]	Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX. Deep learning and its applications to machine health monitoring. Mech Syst Sig Process 2019;115:213-37.

[15]	Wen J, Ren J, Zhao Z, Zhai Z, Chen X. Residual-based adversarial feature decoupling for remaining useful life prediction of aero-engines under variable operating conditions. Expert Syst Appl 2024;255:124538.

[16]	Yu W, Kim IY, Mechefske C. An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme. Reliab Eng Syst Saf 2020;199:106926.

[17]	Chen Z, Chen D, Zhang X, Yuan Z, Cheng X. Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things J 2022; 9(12):9179-89.

[18]

Ren J, Hu C, Shang Z, Li Y, Zhao Z, Yan R. WavFormer:an interpretable wavelet-constrained transformer for industrial acoustics diagnosis. In: Proceedings of the IEEE International Instrumentation and Measurement Technology Conference (I2MTC); 2024 May 20-23; Glasgow, UK. New York City: IEEE; 2024. p. 1-6.

[19]	Zhuo Y, Shardt YA, Ge Z. One-variable attack on the industrial fault classification system and its defense. Engineering 2022;19:240-51.

[20]	Liang YC, Wang S, Li WD, Lu X. Data-driven anomaly diagnosis for machining processes. Engineering 2019; 5(4):646-52.

[21]	Jiang D, He C, Chen Z, Zhao J. Are novel deep learning methods effective for fault diagnosis? IEEE Trans Reliab 2024;74:1-15.

[22]	Li T, Sun C, Fink O, Yang Y, Chen X, Yan R. Filter-informed spectral graph wavelet networks for multiscale feature extraction and intelligent fault diagnosis. IEEE Trans Cybern 2024; 54(1):506-18.

[23]	Li W, Lan H, Chen J, Feng K, Huang R. WavCapsNet: an interpretable intelligent compound fault diagnosis method by backward tracking. IEEE Trans Instrum Meas 2023;72:1-11.

[24]	Ren J, Wen J, Zhao Z, Yan R, Chen X, Nandi AK. Uncertainty-aware deep learning: a promising tool for trustworthy fault diagnosis. IEEE/CAA J Autom Sin 2024; 11(6):1317-30.

[25]	Chen X, Yang R, Xue Y, Huang M, Ferrero R, Wang Z. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Meas 2023;72:1-21.

[26]	Li W, Huang R, Li J, Liao Y, Chen Z, He G, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Sig Process 2022;167:108487.

[27]	Jiao J, Liang K, Ding C, Lin J. Towards prediction constraints: a novel domain adaptation method for machine fault diagnosis. IEEE Trans Industr Inform 2022; 18(10):7198-207.

[28]	Qian Q, Luo J, Qin Y. Adaptive intermediate class-wise distribution alignment: a universal domain adaptation and generalization method for machine fault diagnosis. IEEE Trans Neural Netw Learn Syst 2024; 36(3):4296-310.

[29]	Fink O, Wang Q, Svensen M, Dersin P, Lee WJ, Ducoffe M. Potential, challenges and future directions for deep learning in prognostics and health management applications. Eng Appl Artif Intel 2020;92:103678.

[30]	Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, et al. GPT-4 technical report. arXiv:230308774.

[31]	Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A, Letman A, et al. The LLAMA 3 herd of models. arXiv:240721783.

[32]	Zhang B, Haddow B, Birch A. Prompting large language model for machine translation:a case study. In: Proceedings of the International Conference on Machine Learning; 2023 Jul 23-29; Honolulu, HI, USA. Cambridge: JMLRorg; 2023. p. 41092-110.

[33]

Jiang J, Zhou K, Dong Z, Ye K, Zhao WX, Wen JR. StructGPT:a general framework for large language model to reason over structured data. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing; 2023 Dec 6-10; Singapore City, Singapore. Kerrville: The Association for Computational Linguistics (ACL); 2023. p. 9237-51.

[34]

Zhang W, Deng Y, Liu B, Pan SJ, Bing L. Sentiment analysis in the era of large language models:a reality check. In: Findings of the Association for Computational Linguistics: NAACL 2024; 2024 Jun 16-21; Mexico City, Mexico. Kerrville: The Association for Computational Linguistics (ACL); 2024. p. 3881-906.

[35]	Romera-Paredes B, Barekatain M, Novikov A, Balog M, Kumar MP, Dupont E, et al. Mathematical discoveries from program search with large language models. Nature 2024; 625(7995):468-75.

[36]	Gilbert S, Harvey H, Melvin T, Vollebregt E, Wicks P. Large language model AI chatbots require approval as medical devices. Nat Med 2023; 29(10):2396-8.

[37]	Nijkamp E, Pang B, Hayashi H, Tu L, Wang H, Zhou Y, et al. CodeGen: an open large language model for code with multi-turn program synthesis. In: Proceedings of the 11th International Conference on Learning Representations; 2023 May 1-5; Kigali, Rwanda. Ithaca: OpenReviewnet; 2022.

[38]	Jiang P, Sonne C, Li W, You F, You S. Preventing the immense increase in the life-cycle energy and carbon footprints of LLM-powered intelligent chatbots. Engineering 2024;40:202-10.

[39]	Wang Y, Yu Y, Sun K, Lei P, Zhang Y, Zio E, et al. RmGPT: rotating machinery generative pretrained model. arXiv:240917604.

[40]	Lai Z, Yang C, Lan S, Wang L, Shen W, Zhu L. Towards a foundation model for bearing fault diagnosis by domain knowledge and contrastive learning. Int J Prod Econ 2024;275:109319.

[41]	Yang A, Yang B, Zhang B, Hui B, Zheng B, Yu B, et al. Qwen2 5 technical report. arXiv:241215115.

[42]	Jiang J, Zhou K, Dong Z, Ye K, Zhao WX, Wen JR. StructGPT: a general framework for large language model to reason over structured data. arXiv:230509645.

[43]	Nijkamp E, Pang B, Hayashi H, Tu L, Wang H, Zhou Y, et al. CodeGen: an open large language model for code with multi-turn program synthesis. arXiv:220313474.

[44]	Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, et al. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Brief Bioinform 2022; 23(6):bbac409.

[45]	Cui J, Li Z, Yan Y, Chen B, Yuan L. ChatLaw: open-source legal large language model with integrated external knowledge bases. arXiv:230616092.

[46]	Xia Y, Chen Y, Zhao Y, Kuang L, Liu X, Hu J, et al. FCLLM-DT: enpowering federated continual learning with large language models for digital twin-based industrial IoT. IEEE Internet Things J 2024; 12(6):6070-81.

[47]	Qaid HA, Zhang B, Li D, Ng SK, Li WFDLLM. Large language model for fault diagnosis of machines. arXiv:241201218.

[48]	Tao L, Liu H, Ning G, Cao W, Huang B, Lu C. LLM-based framework for bearing fault diagnosis. Mech Syst Sig Process 2025;224:112127.

[49]	Pang Z, Luan Y, Chen J, Li T. ParInfoGPT: an LLM-based two-stage framework for reliability assessment of rotating machine under partial information. Reliab Eng Syst Saf 2024;250:110312.

[50]	Khan A, Nahar R, Chen H, Flores GE, Li C. FaultExplainer: leveraging large language models for interpretable fault detection and diagnosis. arXiv:241214492.

[51]	Li Q, Huang J, He H, Zhang X, Zhang F, Qin Z, et al. VSLLaVA: a pipeline of large multimodal foundation model for industrial vibration signal analysis. arXiv:240907482.

[52]	Tao L, Huang Q, Wu X, Zhang W, Wu Y, Li B, et al. LLM-R: a framework for domain-adaptive maintenance scheme generation combining hierarchical agents and RAG. arXiv:241104476.

[53]	Peng H, Liu J, Du J, Gao J, Wang W. BearLLM: a prior knowledge-enhanced bearing health management framework with unified vibration signal representation. arXiv:240811281.

[54]	Randall R, Antoni J. Rolling element bearing diagnostics—a tutorial. Mech Syst Sig Process 2011; 25(2):485-520.

[55]	Samuel P, Pines D. A review of vibration-based techniques for helicopter transmission diagnostics. J Sound Vibrat 2005; 282(1-2):475-508.

[56]	Zhang T, Zhang Y, Cao W, Bian J, Yi X, Zheng S, et al. Less is more: fast multivariate time series forecasting with light sampling-oriented MLP structures. arXiv:220701186.

[57]	Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017 Dec 4-9; Long Beach, CA, USA. Red Hook: Curran Associates Inc; 2017. p. 6000-10.

[58]	Kitaev N, Kaiser Ł, Levskaya A. Reformer: the efficient transformer. arXiv:200104451.

[59]	Wu H, Xu J, Wang J, Long M. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst 2021;34:22419-30.

[60]	Zhang Y, Yan J. Crossformer:transformer utilizing cross-dimension dependency for multivariate time series forecasting. In: Proceedings of the 11th International Conference on Learning Representations; 2023 May 1-5, Kigali, Rwanda. Ithaca: OpenReviewnet; 2023.

[61]

Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H, et al. Informer:beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2021 Feb 2-9; held virtually. Washington, DC: The Association for the Advancement of Artificial Intelligence (AAAI); 2021. p. 11106-15.

[62]	Zhou T, Ma Z, Wen Q, Wang X, Sun L, Jin R. FEDformer: frequency enhanced decomposed transformer for long-term series forecasting. PMLR 2022;162:27268-86.

[63]	Nie Y, Nguyen NH, Sinthong P, Kalagnanam J. A time series is worth 64 words: long-term forecasting with transformers. arXiv:221114730.

[64]	Wang H, Peng J, Huang F, Wang J, Chen J, Xiao Y. MICN:multi-scale local and global context modeling for long-term series forecasting. In: Proceedings of the 11th International Conference on Learning Representations; 2023 May 1-5; Kigali, Rwanda. Ithaca: OpenReviewnet; 2023.