Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 10, 2026Open Access

LSTM-CNN Hybrid Deep Learning Architecture for Predictive Maintenance and Remaining Useful Life Estimation in Rotating Industrial Machinery

View Full Paper
Ask AI
Bookmark
Share

Authors

KMKatharina Steiner Thomas Müller

Discussion

Loading...

Member takes

Overview

This work demonstrates a hybrid LSTM-CNN model that predicts faults and estimates remaining useful life in industrial machinery, indicating improved maintenance strategies.

Key Points

  • The aim is to develop an effective hybrid deep learning model for predicting machine faults and estimating Remaining Useful Life (RUL).
  • Developed a hybrid model combining LSTM and CNN for time-series analysis.
  • Trained on the CWRU Bearing Dataset and custom data from IIT Bombay.
  • Employed one-dimensional convolutional layers for feature extraction and bidirectional LSTM for temporal modeling.
  • Achieved classification accuracy of 97.8% using macro-F1.
  • Reported an AUC of 0.991 for fault classification.
  • Demonstrated an RUL prediction RMSE of 38.4 cycles, outperforming traditional baseline methods.

Cite This Study

Katharina Steiner Thomas Müller (2026) studied this question.

synapsesocial.com/papers/69d895206c1944d70ce06286https://doi.org/10.5281/zenodo.19453066
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Deep Learning-Based Predictive Maintenance Framework Using CNN-LSTM Architecture for Industrial Rotating Machinery Fault Detection2025
  2. 2Machine Learning-Based Predictive Fault Detection in Industrial Rotating Machinery Using Hybrid CNN-LSTM Architecture2026
  3. 3Machine Learning-Based Predictive Maintenance Framework for Rotating Equipment in Process Industries2026
  4. 4Machine Learning-Based Predictive Maintenance Framework for Rotating Equipment in Process Industries2026
  5. 5A Novel prediction of remaining useful life time of rolling bearings using Convolutional Neural network with Bidirectional Long Short Term Memory2024 · 22 citations