STTR Phase II: Development of Autocalibration Techniques to Enable Commercial Scale-up of Software-based Vibration Compensation for 3D Printers

The broader/commercial impact of this Small Business Technology Transfer (STTR) Phase II project is to increase the productivity of manufacturing machines at low cost through software improvements, without sacrificing quality. The project is specifically motivated by 3D printing, an $11 billion and rapidly growing industry within advanced manufacturing that is critical to national security, supply chain resiliency, and economic prosperity. The adoption of 3D printing for mainstream manufacturing is often hindered by the low speed of 3D printers. A major hindrance to high-speed 3D printing is vibration, which causes loss of quality at high-speed operation. This project seeks to develop a low-cost, software-based approach for mitigating the vibration of 3D printers. A major impediment to the effectiveness of the proposed software solution is the need for accurate calibration of the changing vibration behavior of 3D printers under varying operating conditions. This project will develop a set of automatic calibration techniques to address this impediment. The software algorithms developed through this project will not only benefit 3D printing but would also apply to a wide range of advanced manufacturing machines, like machine tools and robots, whose speed and accuracy are often limited by vibration. This Small Business Technology Transfer Phase II project seeks to develop a suite of automatic calibration techniques to enable a proprietary vibration compensation algorithm to adapt to frequent changes in vibration behavior of 3D printers that occur in the field. To achieve this goal, three technical objectives will be pursued. The first technical objective will involve the development of a sensor-less auto calibration technique that continuously updates the calibration of 3D printers whose moving mass and vibration behavior changes as material is being deposited on the print bed. The second technical objective will focus on the development of a sensor-based, autocalibration technique that uses shallow machine learning to continuously fine-tune the calibration maps of 3D printers with onboard accelerometers. The third technical objective will involve the development of a sensor-based autocalibration-as-a-service technique primarily for 3D printers that do not have onboard accelerometers. To achieve these objectives, research is needed to overcome technical hurdles that hinder the accuracy and computational efficiency of the proposed auto-calibration approaches. The intellectual merit of this project is in developing science-based approaches that overcome the technical hurdles and their associated risks. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.