Additive manufacturing processes are capable of printing parts with any shape and complexity. The parts fabricated with additive manufacturing processes requires minimum human intervention. Process planning decisions play an important role in making sure the fabricated parts meets the desired specification, including the build time and cost. A quick and unified approach to quantify the manufacturing build time, accuracy, and cost in real time is lacking. In the present research, a generic and near real-time framework for unified additive manufacturing process planning is presented. We have developed computational geometric solutions to estimate tight upper bound of manufacturing process planning decisions that can be analyzed in almost real time. Results of developed computational approach are compared against the optimized process plans to ensure its applicability. Case studies comprising of numerous parts with varying shape, and application area is also outlined.
A Real-Time Iterative Machine Learning Approach for Temperature Profile Prediction in Additive Manufacturing Processes