Generative pre-trained transformer NEOX large language model driven predictive maintenance system in industrial IoT with hybrid deep learning

Predictive maintenance is a crucial approach in the industrial sector, and the utilization of Industrial Internet of Things (IIoT) sensors is becoming popular to detect faults and monitor the equipment’s condition. Still, the gathering, processing, and transmission of a large volume of data in predictive maintenance is highly challenging. To tackle such issues, this paper develops the Recurrent Radial Basis Long Short-Term Memory (RRBLSTM)-based predictive maintenance system using IIoT. The IIoT simulation is the primary process for a predictive maintenance system. The input time series data is subjected to the Box-Cox transformation for data transformation. The interval features, Discrete Fourier Transform (DFT), and Discrete Wavelet Transform (DWT) features are extracted. The RRBLSTM is developed to label the issue. Using the predictive labels, the prompt is generated. The prompt is converted into a sentence by the utilization of the Generative Pre-trained Transformer NEOX Large Language Model (GPT-NEOX LLM) model. In addition, metrics like Mean Absolute Percentage Error (MAPE), R-Square, Mean Square Error (MSE), and Root MSE (RMSE) are used to estimate the efficacy of the model, and the corresponding outcome of 0.325, 0.901, 0.098, and 0.313.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-19
DOI
https://doi.org/10.1038/s41598-026-77543-0
Primary Topic
Machine Fault Diagnosis Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Generative pre-trained transformer NEOX large language model driven predictive maintenance system in industrial IoT with hybrid deep learning

Sufola Das Chagas Silva Araujo, Deepika Patil, Daneshwari I. Hatti, Arvind Kamble
Scientific Reports
Machine Fault Diagnosis Techniques
article

Generative pre-trained transformer NEOX large language model driven predictive maintenance system in industrial IoT with hybrid deep learning

Sufola Das Chagas Silva Araujo, Deepika Patil, Daneshwari I. Hatti, Arvind Kamble
article en

Abstract

Predictive maintenance is a crucial approach in the industrial sector, and the utilization of Industrial Internet of Things (IIoT) sensors is becoming popular to detect faults and monitor the equipment’s condition. Still, the gathering, processing, and transmission of a large volume of data in predictive maintenance is highly challenging. To tackle such issues, this paper develops the Recurrent Radial Basis Long Short-Term Memory (RRBLSTM)-based predictive maintenance system using IIoT. The IIoT simulation is the primary process for a predictive maintenance system. The input time series data is subjected to the Box-Cox transformation for data transformation. The interval features, Discrete Fourier Transform (DFT), and Discrete Wavelet Transform (DWT) features are extracted. The RRBLSTM is developed to label the issue. Using the predictive labels, the prompt is generated. The prompt is converted into a sentence by the utilization of the Generative Pre-trained Transformer NEOX Large Language Model (GPT-NEOX LLM) model. In addition, metrics like Mean Absolute Percentage Error (MAPE), R-Square, Mean Square Error (MSE), and Root MSE (RMSE) are used to estimate the efficacy of the model, and the corresponding outcome of 0.325, 0.901, 0.098, and 0.313.

Scientific Reports
Sanjay Ghodawat University (IN), Visvesvaraya Technological University (IN)
Machine Fault Diagnosis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon