AviChain: A Permissioned Blockchain Architecture for Tamper-Evident Aviation Maintenance Records with Integrated GRU-Based Remaining Useful Life Prediction

AviChain is a full-stack system combining a Hyperledger Fabric permissioned blockchain with a GRU recurrent neural network for predictive aviation maintenance. Every maintenance event is anchored as a tamper-evident, multi-organisation ledger entry; a two-layer GRU trained on the NASA C-MAPSS FD001 turbofan degradation dataset predicts Remaining Useful Life before each transaction is submitted. On the standard 100-engine FD001 test protocol, the GRU achieves MAE = 11.4 cycles, RMSE = 15.0 cycles, and R² = 0.86 — a 44% reduction in MAE over an ARIMA baseline. Uncertainty is quantified via Monte-Carlo dropout (30 forward passes). The smart contract is deployed in Chaincode-as-a-Service mode across a two-organisation Fabric network with Raft ordering. Source code and trained model weights are included.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-15
DOI
https://doi.org/10.5281/zenodo.22771552
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
article

AviChain: A Permissioned Blockchain Architecture for Tamper-Evident Aviation Maintenance Records with Integrated GRU-Based Remaining Useful Life Prediction

Gurtej Singh Lamba
Zenodo (CERN European Organization for Nuclear Research)
Machine Fault Diagnosis Techniques
article

AviChain: A Permissioned Blockchain Architecture for Tamper-Evident Aviation Maintenance Records with Integrated GRU-Based Remaining Useful Life Prediction

Gurtej Singh Lamba
article en

Abstract

AviChain is a full-stack system combining a Hyperledger Fabric permissioned blockchain with a GRU recurrent neural network for predictive aviation maintenance. Every maintenance event is anchored as a tamper-evident, multi-organisation ledger entry; a two-layer GRU trained on the NASA C-MAPSS FD001 turbofan degradation dataset predicts Remaining Useful Life before each transaction is submitted. On the standard 100-engine FD001 test protocol, the GRU achieves MAE = 11.4 cycles, RMSE = 15.0 cycles, and R² = 0.86 — a 44% reduction in MAE over an ARIMA baseline. Uncertainty is quantified via Monte-Carlo dropout (30 forward passes). The smart contract is deployed in Chaincode-as-a-Service mode across a two-organisation Fabric network with Raft ordering. Source code and trained model weights are included.

Zenodo (CERN European Organization for Nuclear Research)
Responsible consumption and production
Openalex Percentile: Top 14%
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.