Shah, Rohan | Engineering Papers

DOE OSTI2024

Reactive extrusion of frontally polymerizing continuous carbon fiber reinforced polymer composites

The manufacturing of carbon fiber-reinforced polymer (CFRP) composites demands rapid and energy-efficient strategies. Frontal polymerization (FP) enables the manufacturing of CFRP using dicyclopentadiene (DCPD) thermoset polymer which meets these requirements. In this work, we introduce reactive extrusion of CFRP (RE-CFRP), where two rollers provide localized heat and pressure to sustain the curing reaction and the consolidation of a continuous carbon fiber tow pre-impregnated with DCPD. We study the effect of the extrusion speed, temperature, and compaction force on the properties of the produced CFRP. Mechanical testing confirms that the resulting fiber volume fraction and the elastic modulus are similar to bulk cured tows. A homogenized thermo-chemical model is developed to study the effect of the process parameters on the polymerization reaction. The process produces hollow woven composite tubes directly via extrusion and in situ curing. Overall, this process offers advantages in curing, tooling, speed, and energy.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Correlated Trajectory Uncertainty for Adaptive Sequential Decision Making

One of the great challenges with decision making tasks on real world systems is the fact that data is sparse and acquiring additional data is expensive. In these cases, it is often crucial to make a model of the environment to assist in making decisions. At the same time, limited data means that learned models are erroneous, making it just as important to equip the model with good predictive uncertainties. In the context of learning sequential decision making policies, these uncertainties can prove useful for informing which data to collect for the greatest improvement in policy performance \citep{mehta2021experimental, mehta2022exploration} or informing the policy about unsure regions of state and action space to avoid during test time \citep{yu2020mopo}. Additionally, assuming that realistic samples of the environment can be drawn, an adaptable policy can be trained that attempts to make optimal decisions for any given possible instance of the environment \citep{ghosh2022offline, chen2021offline}. In this work, we examine the so-called ``probabilistic neural network'' (PNN) model that is ubiquitous in model-based reinforcement learning (MBRL) works. We argue that while PNN models may have good marginal uncertainties, they form a distribution of non-smooth transition functions. Not only are these samples unrealistic and may hamper adaptability, but we also assert that this leads to poor uncertainty estimates when predicting multiple step trajectory estimates. To address this issue, we propose a simple sampling method that can be implemented on top of pre-existing models.We evaluate our sampling technique on a number of environments, including a realistic nuclear fusion task, and find that, not only do smooth transition function samples produce more calibrated uncertainties, but they also lead to better downstream performance for an adaptive policy.

Offline Reinforcement Learning↗