A Machine Learning based Frame Work for Predicting Overall Equipment Effectiveness with Environmental Factors in Additive Manufacturing
In advanced manufacturing technologies, Additive Manufacturing (AM) stands out for its potential to revolutionize production processes. However, assessing the efficiency and productivity of AM machines remains a significant challenge. This research work presents a novel framework for generating a dataset to calculate the Overall Equipment Effectiveness (OEE) of additive manufacturing machines. The proposed OEE-3D printing framework systematically captures Key Performance Indicators (KPIs) including availability, performance, and quality metrics specific to AM processes. By integrating data acquisition techniques with real time monitoring systems, the proposed framework ensures the accurate collection of relevant operational data. This work outlines the methodology, data collection procedures, validation techniques, k-nearest neighbours, support vector machine and Naive Bayes machine learning algorithms utilized for predicting the OEE values, both inclusive and exclusive of environmental parameters, pertaining to the AM machine. The findings demonstrate the capability of this methodology to yield practical insights and drive continuous improvement in the additive manufacturing sector. Correlation analysis within the study revealed strong positive relationships between availability and performance (0.99), as well as between OEE and both availability (0.91) and performance (0.89). Major Findings: This study reveals that environmental factors significantly impact the Overall Equipment Effectiveness (OEE) in 3D printing. Specifically, fluctuations in room temperature, bed temperature, nozzle temperature, and humidity adversely affect print quality, machine performance, and downtime. By integrating sensors to monitor these conditions, we observed enhanced process stability and efficiency. Additionally, incorporating environmental factors into OEE calculations resulted in a noticeable shift from “Good” to “Moderate” performance categories, underscoring their critical role