Predictive Maintenance for Industrial  Machinery

Achanta Mukesh Mourya; G Kanaka Rao; VBM Krishna; KandulaRohith; S Janakiramayya

Predictive Maintenance for Industrial Machinery

Author(s)	Achanta Mukesh Mourya, G Kanaka Rao, VBM Krishna, KandulaRohith, S Janakiramayya
Country	India
Abstract	Predictive maintenance is essential for ensuring the reliable and safe operation of complex industrial systems like turbofan engines. Accurate Remaining Useful Life (RUL) estimation allows for timely maintenance interventions, minimizing operational downtime and preventing catastrophic failures. Traditional deep learning models like LSTMs often struggle to capture long-range dependencies in complex time-series data. To address these challenges, this paper proposes a novel hybrid deep learning framework for accurately predicting the remaining useful life (RUL) of mechanical components Deep-RUL, which integrates Convolutional Neural Networks (CNN) with Transformer Encoder layers. This hybrid approach leverages a 1D Convolutional layer (Conv1D) to refine local spatial-temporal features, followed by three stacked Transformer blocks employing multi-head self-attention (8 heads) and a Position-wise Feed-Forward network (128 units, Swish activation) to dynamically capture complex sequential dependencies. A key contribution of this work is the development of a hybrid deep learning framework that accurately predicts the remaining useful life (RUL) of mechanical components while quantifying predictive uncertainty the deployment of a Probabilistic Output Head, which utilizes dual dense layers to predict not only the Mean () RUL as a point estimate but also the Log-Variance () to provide a measure of Uncertainty Estimation, critical for risk-aware industrial applications. Evaluated on the NASA C-MAPSS FD001 dataset with a look-back window of 60 cycles and piecewise linear RUL clipping (max=125), The proposed ensemble model demonstrates superior predictive performance, achieving a Root Mean Square Error (RMSE) of 11.24, thereby indicating precise and reliable remaining useful life (RUL) estimation a Mean Absolute Error (MAE) of 7.59, and an score of 0.93. Furthermore, the model is integrated into a full-stack real-time Flask web dashboard that categorizes engine health states into three actionable levels: HEALTHY (RUL > 50), INSPECT (25 < RUL 50), or CRITICAL (RUL 25), thereby bridging the gap between theoretical model performance and practical industrial deployment.
Keywords	Remaining Useful Life (RUL), Transformer Networks, Convolutional Neural Networks (CNN), Uncertainty Estimation, NASA C-MAPSS, Deep Learning.
Field	Engineering
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-10

View / Download PDF File

E-ISSN 3048-7641

doi

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1 Cover Page Vol 6 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Predictive Maintenance for Industrial Machinery

Share this