Best Practices In Moving Towards Large-scale Production Planning In 3D Printing

Planning and scheduling for additive manufacturing (AM) at a factory scale opens up an incredible array of possibilities, but also corresponding challenges. At the top of those challenges is the fact additive manufacturing - or colloquially 3D printing - tends to get hung up on a single, time-consuming step.

The positive side of this bottleneck is that there is an opportunity to fit multiple components onto the same build plate, so they can be produced in parallel while incurring only marginal additional time costs. This paper is about finding ways to optimize the process and incorporate the best aspects of 3D printing and traditional manufacturing together to create a better future for everyone.

The focus of this article has been to capture the fundamental difficulty involved in the newly emerging intersection between AM, operations research, and AI. This model was presented at the 2018 International Conference on Automated Planning and Scheduling. We believe this new model we explored could ultimately be extended into an end-to-end optimization model that captures all the discrete decision-making challenges in AM.

Download this paper from Oqton to learn more about some of the challenges in AM.

Download today

Latest News

Massivit 3000 Large-Format 3D Printer Launches
The new printer enables high-speed production of 3D window displays, 2D/3D combined point-of-purchase displays, interactive event props, and molds...

Indy Autonomous Challenge to Returns to Indianapolis Speedway
Race set to feature a head-to-head race of possibly the fastest autonomous racecars piloted by artificial intelligence driver software, organizers...

Desktop Metal Releases Binder Jet 3D Printing Upgrade
The Production System P-1 metal binder jet 3D printer will be offered with a Reactive Safety Kit for high-speed production...

MathWorks Advances Software-Defined Workflows with NVIDIA’s Help
Developers can use their existing MATLAB Algorithm Codebase to develop and deploy AI-enabled applications via the NVIDIA Holoscan platform.

AI in Design: In Need of New Hardware
New hardware options are emerging to support artificial intelligence use cases.

Can AI Eat Itself?
Looks like synthetic training data is here to stay—it's something engineering organizations should keep a close eye on.

All posts