• Home
  • Search
  • DLformer: A Dynamic Length Transformer-Based Network for Efficient Feature Representation in Remaining Useful Life Prediction.
  • Cite Icon57
  • https://doi.org/10.1109/tnnls.2023.3257038Copy DOI Icon

DLformer: A Dynamic Length Transformer-Based Network for Efficient Feature Representation in Remaining Useful Life Prediction.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Representation learning-based remaining useful life (RUL) prediction plays a crucial role in improving the security and reducing the maintenance cost of complex systems. Despite the superior performance, the high computational cost of deep networks hinders deploying the models on low-compute platforms. A significant reason for the high cost is the computation of representing long sequences. In contrast to most RUL prediction methods that learn features of the same sequence length, we consider that each time series has its characteristics and the sequence length should be adjusted adaptively. Our motivation is that an "easy" sample with representative characteristics can be correctly predicted even when short feature representation is provided, while "hard" samples need complete feature representation. Therefore, we focus on sequence length and propose a dynamic length transformer (DLformer) that can adaptively learn sequence representation of different lengths. Then, a feature reuse mechanism is developed to utilize previously learned features to reduce redundant computation. Finally, in order to achieve dynamic feature representation, a particular confidence strategy is designed to calculate the confidence level for the prediction results. Regarding interpretability, the dynamic architecture can help human understand which part of the model is activated. Experiments on multiple datasets show that DLformer can increase up to 90% inference speed, with less than 5% degradation in model accuracy.

Similar Papers
  • PDF
  • Research Article
  • Citations5

Remaining useful life prediction towards cycling stability of organic electrochemical transistors

  • Jan 01, 2024
  • Materials Research Express
  • Jie Xu +7
  • Research Article
  • Citations36

Probabilistic remaining useful life prediction without lifetime labels: A Bayesian deep learning and stochastic process fusion method

  • Jun 24, 2024
  • Reliability Engineering and System Safety
  • Junlin Pan +6
  • Research Article
  • Citations71

A Neural Network-Based Joint Prognostic Model for Data Fusion and Remaining Useful Life Prediction.

  • Jan 01, 2021
  • IEEE Transactions on Neural Networks and Learning Systems
  • Yuanyuan Gao +2
  • Research Article
  • Citations10

A Hybrid Deep Learning Prediction Method of Remaining Useful Life for Rolling Bearings Using Multiscale Stacking Deep Residual Shrinkage Network

  • Jan 01, 2023
  • International Journal of Intelligent Systems
  • Xudong Song +6
  • Research Article
  • Citations43

Remaining useful life prediction for multi-sensor systems using a novel end-to-end deep-learning method

  • Jun 15, 2021
  • Measurement
  • Yuyu Zhao +1
  • PDF
  • Research Article
  • Citations18

Residual Remaining Useful Life Prediction Method for Lithium-Ion Batteries in Satellite With Incomplete Healthy Historical Data

  • Jan 01, 2019
  • IEEE Access
  • Jian Peng +4
  • Research Article
  • Citations26

Multi-sensor data fusion and bidirectional-temporal attention convolutional network for remaining useful life prediction of rolling bearing

  • Jul 24, 2023
  • Measurement Science and Technology
  • Haopeng Liang +2
  • Research Article
  • Citations9

Remaining useful life prediction of aero-engines based on random-coefficient regression model considering random failure threshold

  • Apr 01, 2023
  • Journal of Systems Engineering and Electronics
  • Fengfei Wang +5
  • Research Article
  • Citations13

PSTFormer: A novel parallel spatial-temporal transformer for remaining useful life prediction of aeroengine

  • Mar 01, 2025
  • Expert Systems With Applications
  • Song Fu +6
  • PDF
  • Research Article
  • Citations14

Research on Remaining Useful Life Prediction Method of Rolling Bearing Based on Health Indicator Extraction and Trajectory Enhanced Particle Filter

  • Apr 02, 2022
  • Journal of Dynamics, Monitoring and Diagnostics
  • Peng Luo +4
  • Research Article
  • Citations2

A knowledge-driven method for IGBT remaining useful life prediction using bidirectional learning and physics-enhanced pathformer networks

  • Aug 11, 2025
  • Journal of Computational Design and Engineering
  • Zhaohua Zhang +1
  • Conference Article
  • Citations4

Lithium-ion Battery Remaining Useful Life Prediction Based on Hybrid Model

  • Apr 15, 2022
  • Gang Zou +2
  • Conference Article
  • Citations2

Cuckoo Search Based Relevance Vector Machine with Hybrid Kernel for Battery Remaining Useful Life Prediction

  • Oct 01, 2019
  • Yiting Chen +5
  • Conference Article

Remaining Useful Life Prediction of Parts and Components based on BiLSTM Autoencoder with Attention Mechanism and Skip Connection

  • Oct 15, 2021
  • 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)
  • Mengqi He +3
  • Conference Article
  • Citations2

Towards Uncertainty-aware Remaining Useful Life Prediction via Domain Adaptation

  • Oct 19, 2022
  • Hyun Yong Lee +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.