ADAPTIVE PROCESS PARAMETER CONTROL USING MACHINE LEARNING IN ADDITIVE MANUFACTURING

Abstract

Additive manufacturing has emerged as a revolutionary production technology for fabricating complex components with reduced material waste, enhanced design flexibility, and accelerated manufacturing cycles. However, achieving consistent product quality remains challenging due to complex relationships between process parameters, material behavior, thermal conditions, and manufacturing defects. This paper proposes an adaptive process parameter control framework using machine learning for additive manufacturing by integrating Industrial Internet of Things (IIoT), Digital Twin technology, multi-sensor data fusion, predictive analytics, cloud computing, and intelligent optimization techniques. The proposed methodology continuously analyzes manufacturing data, predicts process deviations, dynamically adjusts critical parameters, and improves production quality through closed-loop control. Experimental evaluation demonstrates improvements in defect reduction, parameter optimization accuracy, surface quality, production stability, energy efficiency, and operational reliability. The proposed framework provides a scalable and intelligent solution for autonomous additive manufacturing systems, supporting Industry 4.0 transformation and sustainable smart factory implementation. Keywords— Adaptive Process Control, Additive Manufacturing, Machine Learning, Parameter Optimization, Digital Twin, IIoT, Smart Manufacturing, Industry 4.0.