A Dual-Model Machine Learning Framework for Predictive Maintenance of Industrial Digital Press Components

A Dual-Model Machine Learning Framework for Predictive Maintenance of Industrial Digital Press Components

Accra, Ghana and Virtual

This study presents a novel dual-model predictive maintenance framework designed to improve maintenance scheduling for components in industrial digital presses. The framework integrates two complementary approaches: a Threshold-Based Maintenance Approach (TBMA) for components operating within acceptable usage limits, and an Overdue Severity-Based Maintenance Approach (OSBMA) for those that have exceeded their expected lifespans or show signs of critical degradation. This study uses real-world operational data from a Konica Minolta C6000 press. It applies advanced machine learning models, including Gradient Boosting Machines and Random Forest for classification, and Generalized Additive Models (GAM) for Remaining Useful Life (RUL) prediction. The goal is to support data-driven decision-making. The TBMA model achieved an overall classification accuracy of 99.0% with substantial agreement (κ = 0.987), while the OSBMA model reached 99.1% accuracy (κ = 0.988), underscoring the reliability of the framework. The proposed approach enables proactive monitoring and intelligent prioritization of maintenance tasks, offering a robust, scalable alternative to traditional fixed-schedule or reactive maintenance strategies in digital press environments.