• Home
  • Search
  • Integrating Few-Shot Learning and Pre-trained Models into Similarity-Based PHM using Small Data in Complex Engineering Systems
  • https://doi.org/10.36001/phmconf.2025.v17i1.4594Copy DOI Icon

Integrating Few-Shot Learning and Pre-trained Models into Similarity-Based PHM using Small Data in Complex Engineering Systems

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Prognostics and Health Management (PHM) is vital for complex engineering systems, yet its data-driven solutions are often hampered by the "small data problem"—a scarcity of labeled fault data in industrial settings. This limitation restricts the training and generalization of machine learning models and is compounded by varying operational conditions that reduce the relevance of historical data and pre-trained models. This research introduces a research framework to tackle these small data challenges in PHM. The primary objective is to develop a robust and adaptable PHM methodology by enhancing and synergistically integrating similarity-based Few-Shot Learning (FSL) with large-scale pre-trained time-series models. The research will focus on two main thrusts. First, it aims to improve the generalization capabilities of FSL frameworks by addressing limitations such as noise robustness, domain shift adaptability, and generalization to novel faults across diverse PHM domains. This involves developing noise-robust feature extraction, integrating domain adaptation techniques, and exploring expressive similarity metrics. Second, the study will investigate the effective adaptation of state-of-the-art pre-trained time-series models (e.g., TimesNet) for PHM tasks under data scarcity, focusing on efficient fine-tuning and synergistic integration with the enhanced FSL approaches. The author's prior success in a PHM data challenge using a similarity-based method for spacecraft systems provides preliminary validation. This research is expected to deliver an enhanced PHM framework for high-accuracy diagnostics with limited data, contributing generalized FSL models, systematic methods for leveraging pre-trained models in PHM, and advancing the practical deployment of intelligent PHM solutions.

Similar Papers
  • Research Article

LLMs as Pre-trained Models for Time-Series Applications in PHM

  • Oct 26, 2025
  • Annual Conference of the PHM Society
  • Takanobu Minami +2
  • Conference Article
  • Citations1

Remaining Useful Life prediction with a Deep Self-Supervised Learning Approach

  • Jan 01, 2022
  • A Akrim +3
  • Research Article

PHM-Vibench

  • Jan 13, 2026
  • PHM Society Asia-Pacific Conference
  • Qi Li +8
  • Conference Article

Study on Non-linear Regression Algorithm for Prognostic and Health Management of Aero-engine

  • Sep 28, 2017
  • Yingqi Liu +3
  • Research Article

Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management

  • Jan 01, 2026
  • IEEE Transactions on Industrial Informatics
  • Chaewon Yoon +2
  • Research Article
  • Citations2

Implementing PHM for legacy flight control actuators through operational aircraft data: Approach and lessons learned

  • Dec 01, 2025
  • Results in Engineering
  • Leonardo Baldo +4
  • PDF
  • Research Article
  • Citations1

Designing for Human-Centred Decision Support Systems in PHM

  • Jul 08, 2014
  • PHM Society European Conference
  • Darren McDonnell +3
  • Research Article
  • Citations57

Modernizing risk assessment: A systematic integration of PRA and PHM techniques

  • Aug 15, 2020
  • Reliability Engineering & System Safety
  • Ramin Moradi +1
  • PDF
  • Research Article
  • Citations122

Small data challenges for intelligent prognostics and health management: a review

  • Jul 23, 2024
  • Artificial Intelligence Review
  • Chuanjiang Li +5
  • Research Article
  • Citations11

Fault Detection of Cyber-Physical Systems Using a Transfer Learning Method Based on Pre-Trained Transformers

  • Jul 04, 2025
  • Sensors (Basel, Switzerland)
  • Pooya Sajjadi +2
  • Research Article
  • Citations16

A fine-grained self-adapting prompt learning approach for few-shot learning with pre-trained language models

  • Jun 01, 2024
  • Knowledge-Based Systems
  • Xiaojun Chen +5
  • Research Article
  • Citations21

Metrics for evaluating the performance of complex engineering system health monitoring models

  • Mar 25, 2022
  • Reliability Engineering & System Safety
  • Austin D Lewis +1
  • Research Article
  • Citations1

OSPtk: Cost-aware Optimal Sensor Placement Toolkit Enabling Design-for-PHM in Critical Industrial Systems

  • Oct 26, 2023
  • Annual Conference of the PHM Society
  • Liang Tang +4
  • Research Article
  • Citations28

Opportunities and data requirements for data-driven prognostics and health management in liquid hydrogen storage systems

  • May 01, 2022
  • International Journal of Hydrogen Energy
  • Camila Correa-Jullian +1
  • Research Article

Mission Profile Clustering for Usage-Based Health Modeling of Flight Control Actuators Applied to a Fleet of Advanced Jet Trainers

  • Oct 26, 2025
  • Annual Conference of the PHM Society
  • Leonardo Baldo +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.