Realtime Predictive Maintenance with Lambda Architecture

TL;DR

This paper presents a lambda architecture-based platform for real-time predictive maintenance using IoT, enabling anomaly detection, rule extraction, and automated cloud-based maintenance, while continuously improving accuracy through batch data analysis.

Contribution

It introduces a novel maintenance platform combining edge and cloud processing for real-time analysis and automatic maintenance decision-making.

Findings

Real-time anomaly detection achieved on edge nodes.

Automated maintenance orders issued by cloud system.

Model updates improve detection accuracy over time.

Abstract

Recently, IoT technologies have been progressed and applications of maintenance area are expected. However, IoT maintenance applications are not spread in Japan yet because of insufficient analysis of real time situation, high cost to collect sensing data and to configure failure detection rules. In this paper, using lambda architecture concept, we propose a maintenance platform in which edge nodes analyze sensing data, detect anomaly, extract a new detection rule in real time and a cloud orders maintenance automatically, also analyzes whole data collected by batch process in detail, updates learning model of edge nodes to improve analysis accuracy.