Research on manufacturing systems is further enriched and becomes stronger looking at the papers which had been proposed for 48th North American Manufacturing Research Conference (NAMRC 48). NAMRC 48 scheduled for June 2020 was collocated with MSEC2020/LEM&P, and coordinated by the Conference Coordinating Committee (CCC) involving the host, NAMRI, ASME and JSME. The final recommendation made by CCC was to cancel NAMRC 48 and the collocated conferences after careful assessment of the occurring situation. Discussions started in late February and March 2020 on the impact of the COVID-19 pandemic on attendance at NAMRC 48. Concern for the safety of attendees as well as the impact on attendance prompted discussions to the cancellation of the conference. Carefully considering the situation NAMRI Board and NAMRI Scientific Committee assessed that the reported scientific outputs of authors deserved timely dissemination to be on the cutting edge, maximizing the impact of their research despite this difficult time.
Advancing manufacturing systems is playing a fundamental and strategic role within the framework of Industry 4.0 environment. The effective management of information and data generated at the single machine level through sensors can lead to relevant improvement in the production as quality and robustness are regarded. In this way, manufacturing has to be looked at in synergy with further disciplines as applied statistics, data analytics, computer systems and so on.
Moreover, the introduction in the production shop floor of the most recent manufacturing technologies definitively requires specific innovative solutions at the production system level in order to maximize performances in quality and effectiveness of products, agility in production, short response time to market evolutions, and profitable margins. This special issue titled “New Trends in Manufacturing Systems Research 2020” brings to readers the state-of-the-art and the latest achievements highlighted at NAMRC 48. Five quality papers are selected from NAMRC 48 for inclusion in this special issue and their synopses are provided below.
In the first paper titled “Efficiently registering scan point clouds of 3D printed parts for shape accuracy assessment and modeling” potential pitfalls that can be encountered when applying Iterative Closest Point (ICP) algorithm for assessment of dimensional accuracy of AM parts are evaluated. These challenges are then illustrated using simulated data. Each of these registration errors was shown to be significant enough to noticeably affect the measured deviations. An efficient and practical method to address several of these errors based on engineering informed assumptions is then presented. Both the proposed method and traditional unconstrained ICP are used to produce alignments of real and simulated measurement data. A real designed experiment was conducted to compare the results obtained by the two registration methods using a linear mixed effects modeling approach.
The second paper titled “Using augmented reality to build digital twin for reconfigurable additive manufacturing system” describes a methodology of using augmented reality (AR) technique to conveniently communicate the layout information between a reconfigurable AM system made of robotic arms and its corresponding digital twin for toolpath planning and simulation. A prototype system made of two desktop AM robotic arms is developed, and transformation matrices are derived to determine the spatial relation between different items in the system, including camera, markers, robotic arms and part substrate. Case studies are conducted to demonstrate the capability of this methodology in automatically retrieving layout information and assisting users to deploy pre-determined layout.
The third paper titled “Transferable two-stream convolutional neural network for human action recognition” presents an integrated method based on optical flow and convolutional neural network (CNN)-based transfer learning to, from one side, effectively leverage the temporal information of human motion to improve the performance of action recognition and to obtain large volume of training data. In the proposed approach optical flow images, which encode the temporal information of human motion, are extracted and serve as the input to a two-stream CNN structure for simultaneous parsing of spatial-temporal information of human motion. Then, transfer learning is investigated to transfer the feature extraction capability of a pretrained CNN to manufacturing scenarios.
The fourth paper titled “Image-based flight control of unmanned aerial vehicles (UAVs) for material handling in custom manufacturing” introduces an approach for and the challenges in employing unmanned aerial vehicles (UAVs) for material handling in the emerging industrial custom manufacturing environments. A pose estimation method that employs just a single camera onboard with a UAV, together with multiple ArUco markers positioned strategically over the shop-floor, is implemented to track the real-time location of a UAV. A Kalman filter is applied to mitigate noise effects for pose estimation.
The fifth paper titled “On-line model identification for the machining process based on multirate process data” proposes to improve the identification of the model parameters of the machining process based on on-line process data by using both in-process and postprocess data and by analyzing the identifiability of model parameters. The identification of the model parameters based on multi-rate output is formulated using the maximum-likelihood estimation and the Fisher information matrix for a multi-rate-sampled system is derived to study the identifiability of model parameters. A strategy is developed to improve accuracy and robustness of the model identification considering the identifiability.
Finally, we wish to take this opportunity to thank all the authors for their scientific contributions to this special issue, and for complying with referees’ comments in revising their manuscripts. Through this special issue, we would like to share some insight on the latest advancements in manufacturing systems research along with some of the accompanying challenges, and hope to open doors for new research ideas and achievements in the years to come.