Search

When performing time-intensive optimization tasks, such as those in Topology Optimization or Shape Optimization, researchers have turned to Machine Learned (ML) Inverse Design methods — i.e., algorithms that predict the optimized geometry from input conditions — to either replace or warm start traditional optimizers. Almost exclusively, such methods are trained and optimized to reduce the Mean Squared Error between a method’s output and a ground truth training dataset of optimized designs, this being the obvious choice for traditional supervised learning. While convenient, we show that this choice may be myopic. Specifically, we compare two methods of optimizing the hyper-parameters of both a random forest (RF) and k-nearest neighbors (KNN) model for predicting the optimal topology in a 2D heat sink example. We show that under both direct Inverse Design as well as when warm starting further Topology Optimization (TO), using typical Mean Squared Error metrics produces less performant models than a proposed metric that directly evaluates the objective function, though both methods produce designs that are almost one order of magnitude better than a control condition that uses a uniform initialization common in TO. We also illustrate how warm starting TO with predicted solutions impacts both the convergence time, the type of solutions obtained during optimization, and the final designs. Sensitivity analyses on various model parameters demonstrate that the results are not dependent on other model hyperparameters. Overall, our initial results portend that researchers may need to revisit common choices for evaluating ID methods that subtly trade-off factors in how an ID method will actually be used. We hope our open-source dataset and evaluation environment will spur additional research in those directions.

This paper a will provide background and research outcomes for a student-led multi-University motion capture design project with the FDA Human Device Interaction Lab. This research project spawned from the FDA’s interest in studying mobile Apps used to collect information about a rehabilitation patient’s function outside of a laboratory setting. This is particularly important from a research perspective as it allows knowledge to be gathered about the reliability, safety, and efficacy of such devices, which can later inform human factors guidelines and regulatory oversight. While there is a wide range of applications for remote monitoring of patient function, this project focuses specifically on wearables used to track rehabilitative progress of individuals suffering from upper or lower limb impairment. These wearables may also be used to assess the efficacy of a new assistive technology intended to restore or augment function. The interdisciplinary student teams applied human-centered design principles to develop and prototype hardware and software components for a rotatable body-worn mobile device holder to remotely track rehabilitation progress. The design process and outcomes are presented along with insights on further development of system components.