Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation

• URL: http://arxiv.org/abs/2606.11990v2
• Date: Tue, 16 Jun 2026 08:38:32 GMT
• Title: Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation
• Abstract summary: We use Chronos-2 as a frozen backbone to extract context window features and train a lightweight regression neural network for RUL prediction.<n>Experiments on real-world industrial sensor data show that Chronos-2 features consistently improve over recurrent, convolutional, Transformer-based, and gradient-boosting baselines.
• Score: 8.955835015831468
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or large labeled datasets to train task-specific sequence models. In this work, we introduce a lightweight learning approach, in which we leverage a frozen pretrained time-series foundation model (TSFM) and combine it with a small regression head for RUL estimation from multivariate sensor streams. More specifically, we use Chronos-2 as a frozen backbone to extract context window features and train a lightweight regression neural network for RUL prediction. Experiments on real-world industrial sensor data from two device types show that Chronos-2 features consistently improve over recurrent, convolutional, Transformer-based, and gradient-boosting baselines under the same preprocessing and evaluation protocol. We further analyze the impact of context length and find that performance improves significantly with longer histories, indicating that TSFM representation offer a practical and data-efficient alternative for RUL estimation in industrial settings.

Related papers

• PEFT-MuTS: A Multivariate Parameter-Efficient Fine-Tuning Framework for Remaining Useful Life Prediction based on Cross-domain Time Series Representation Model [11.1448655248427]
  The application of data-driven remaining useful life (RUL) prediction has long been constrained by the availability of large amount of degradation data.<n>This study investigates PEFT-MuTS, a.<n>Efficient Fine-Tuning framework for few-shot RUL prediction, built on cross-domain pre-trained time-series representation models.
  arXiv  Detail & Related papers  (2026-01-30T06:46:57Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• End-to-End Framework for Predicting the Remaining Useful Life of Lithium-Ion Batteries [0.04660328753262073]
  This paper proposes a RUL prediction approach that leverages data from recent charge-discharge cycles to estimate the number of remaining usable cycles.<n>The approach introduces both a novel signal processing pipeline and a deep learning prediction model.<n> Experimental results on two publicly available large-scale datasets demonstrate that the proposed method outperforms a baseline deep learning approach and machine learning techniques.
  arXiv  Detail & Related papers  (2025-05-22T13:28:18Z)
• CNN-LSTM Hybrid Deep Learning Model for Remaining Useful Life Estimation [0.0]
  We propose a hybrid approach combining Convolutional Neural Networks with Long Short-Term Memory (LSTM) networks for RUL estimation.<n>Our results demonstrate that the hybrid CNN-LSTM model achieves the highest accuracy, offering a superior score compared to the other methods.
  arXiv  Detail & Related papers  (2024-12-20T15:48:57Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• Multi-Dimensional Self Attention based Approach for Remaining Useful Life Estimation [0.17205106391379021]
  Remaining Useful Life (RUL) estimation plays a critical role in Prognostics and Health Management (PHM) This paper carries out research into the remaining useful life prediction model for multi-sensor devices in the IIoT scenario. A data-driven approach for RUL estimation is proposed in this paper.
  arXiv  Detail & Related papers  (2022-12-12T08:50:27Z)
• Accurate Remaining Useful Life Prediction with Uncertainty Quantification: a Deep Learning and Nonstationary Gaussian Process Approach [0.0]
  Remaining useful life (RUL) refers to the expected remaining lifespan of a component or system. We devise a highly accurate RUL prediction model with uncertainty quantification, which integrates and leverages the advantages of deep learning and nonstationary Gaussian process regression (DL-NSGPR) Our computational experiments show that the DL-NSGPR predictions are highly accurate with root mean square error 1.7 to 6.2 times smaller than those of competing RUL models.
  arXiv  Detail & Related papers  (2021-09-23T18:19:58Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)
• Learning representations with end-to-end models for improved remaining useful life prognostics [64.80885001058572]
  The remaining Useful Life (RUL) of equipment is defined as the duration between the current time and its failure. We propose an end-to-end deep learning model based on multi-layer perceptron and long short-term memory layers (LSTM) to predict the RUL. We will discuss how the proposed end-to-end model is able to achieve such good results and compare it to other deep learning and state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-11T16:45:18Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.