EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PGA-LLM: A Probability-Guided Alignment Large Language Model Framework for Fault Diagnosis

Tao Wang, Yanqiang Di, Shaochong Feng, Qiongyao Liu, Haohao Cui, Qing Liu

Technologies · 06.08.2026 · 14 (8) · 494

DOI: 10.3390/technologies14080494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 06.08.2026. Verfasst von Tao Wang und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault diagnosis for complex industrial equipment plays a crucial role in safeguarding production safety and advancing the capabilities of intelligent operation and maintenance. Current deep learning approaches have demonstrated promising accuracy in fault classification tasks; however, their signal representations alone cannot provide a transparent interface for embedded large language models. To tackle the aforementioned challenges, we propose PGA-LLM, a novel fault diagnosis framework for industrial equipment that leverages large language models via probability-guided alignment. First, a variational autoencoder (VAE)-based signal encoder embedded with reconstruction constraints is established. Joint reconstruction and classification objectives balance discriminative representation learning and signal reconstruction. Second, the probability-guided alignment (PGA) module combines fault-class probability guidance with a residual feature path; a learned gate fuses both paths before continuous soft-prompt projection. Furthermore, a progressive three-stage training scheme is adopted, encompassing encoder pre-training, interface optimization, and low-rank adaptation (LoRA) of Qwen2.5-1.5B. Extensive experiments are carried out on four standard datasets, CWRU, Gear, Mixed, and MBHM, and the Stage 2 signal-side output achieves classification accuracies of 97.1%, 99.0%, 93.4%, and 96.3%, respectively. The report-generation branch provides a schema-constrained signal-to-language interface for maintenance-oriented reporting.

Zitieren

APA

Wang, T., Di, Y., Feng, S., Liu, Q., Cui, H., & Liu, Q. (2026). PGA-LLM: A Probability-Guided Alignment Large Language Model Framework for Fault Diagnosis. Technologies, 14(8), 494. https://doi.org/10.3390/technologies14080494

Vancouver

Wang T, Di Y, Feng S, Liu Q, Cui H, Liu Q. PGA-LLM: A Probability-Guided Alignment Large Language Model Framework for Fault Diagnosis. Technologies. 2026;14(8):494. doi:10.3390/technologies14080494

BibTeX
@article{Wang2026,
  author = {Wang, Tao and Di, Yanqiang and Feng, Shaochong and Liu, Qiongyao and Cui, Haohao and Liu, Qing},
  title = {PGA-LLM: A Probability-Guided Alignment Large Language Model Framework for Fault Diagnosis},
  journal = {Technologies},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {494},
  doi = {10.3390/technologies14080494}
}
Kostenlos starten →