High-entropy alloys possessing mechanical, chemical, and electrical properties that far exceed those of conventional alloys have the potential to make a significant impact on many areas of engineering. Identifying element combinations and configurations to form these alloys, however, is a difficult, time-consuming, computationally intensive task. Machine learning has revolutionized many different fields due to its ability to generalize well to different problems and produce computationally efficient, accurate predictions regarding the system of interest. In this thesis, we demonstrate the effectiveness of machine learning models applied to toy cases representative of simplified physics that are relevant to high-entropy alloy simulation. We show these models are effective at learning nonlinear dynamics for single and multi-particle cases and that more work is needed to accurately represent complex cases in which the system dynamics are chaotic. This thesis serves as a demonstration of the potential benefits of machine learning applied to high-entropy alloy simulations to generate fast, accurate predictions of nonlinear dynamics.

Pelvic Circumferential Compression Devices (PCCDs), an important medical device when caring for patients with pelvic fractures, play a crucial role in the stabilization and reduction of the fracture. During pelvic fracture cases, control of internal bleeding through access to the femoral artery is of utmost importance. Current designs of PCCDs do not allow vital access to this artery and in attempts to gain access, medical professionals and emergency care providers choose to cut into the PCCDs or place them in suboptimal positions with unknown downstream effects. We researched the effects on surface pressure and the overall pressure distribution created by the PCCDs when they are modified or placed incorrectly on the patient. In addition, we investigated the effects of those misuses on pelvic fracture reduction, a key parameter in stabilizing the patient during critical care. We hypothesized that incorrectly placing or modifying the PCCD will result in increased surface pressure and decreased fracture reduction. Our mannequin studies show that for SAM Sling and T-POD, surface pressure increases if a PCCD is incorrectly placed or modified, in support of our hypothesis. However, opposite results occurred for the Pelvic Binder, where the correctly placed PCCD had higher surface pressure when compared to the incorrectly placed or modified PCCD. Additionally, pressure distribution was significantly affected by the modification of the PCCDs. The cadaver lab measurements show that modifying or incorrectly placing the PCCDs significantly limits their ability to reduce the pelvic fracture. These results suggest that while modifying or incorrectly placing PCCDs allows access to the femoral artery, there are potentially dangerous effects to the patient including increased surface pressures and limited fracture reduction.