Parameter Optimization | Dr. Ankit Goel

November 2021 — January 2025

Background: Dr. Ankit Goel is an assistant professor at UMBC. He runs the Estimation, Control, and Learning Laboratory (ECLL) in the Mechanical Engineering department.

Comparing novel Extended Kalman Filter supported neural network at tracking the Lorenz system, against clasical extended kalman filter and open loop neural network.

I implement and test various optimization techniques to solve classical non-linear problems and train neural networks (NNs). In particular, I have,

Used conventional machine learning techniques to train NNs using both Keras, Pytorch, and custom gradient descent,
Illustrated the ability of gradient free methods, such as the Newtonian method and random search method, to surpass conventional gradient descent in training NNs,
Tested the effect on inertial measurement units due to properties of accelerometers, gyroscopes, and magnetometers,
Implemented a novel finite time algorithm in discreet problems such as NNs, shown in the image below,
Combined extended Kalman filter with NNs to improve long term convergence, shown in the video above.
And developed a simultaneous localization and mapping platform for future research and coursework.

Additionally, I had the opportunity to present on my research:

URCAD, 2023
Presented poster on neural networks and gradient-free training on UMBC's undergraduate research day. Link to abstracts
2023. Time accelerated algorithms. This was cancelled due to thresholding.
URCAD, 2024
Modelling dynamical systems using neural networks.

Plot of convergence of various optimizers, in which FTE outranks Adam, and Adam outranks SGD.

Comparing training algorithm performance on MNIST dataset; the finite time method was shown to outperform conventional adaptive momentum and stochastic gradient descent methods in this case

Magnesium Extraction Methods from Seawater | Dr. Michael Wagner

Summer 2024 (REU)

Backgroud: Dr. Michael Wagner is a Mechanical Engineering professor at University of Wisconsin, Madison. He runs the Energy Systems Optimization Lab (ESOL) with a focus on applied research on developing simulation models and software, and methodologies of improving usage of sustainable energy sources or methods.

Two figures showing the effect of pH on magnesium extraction. In the top figure, as the pH increases (by adding sodium hydroxide), the amount of magnesium precipitate increases between pH of about 7 and 12.5. Then calcium begins precipitating out. Both are linear. The second figure is the effect of adding calcium hydroxide to increase the pH. Magnesium begins precipitating up to a point, after which any calcium hydroxide added will remain precipitated.

Effect of pH on magnesium hydroxide and calcium hydroxide precipitate using sodium hydroxide or calcium hydroxide as the base, as calculated using PHREEQC.

A seawater mining with zero-liquid discharge powered by nuclear energy was proposed by ESOL. Seawater would undergo pretreatment, all ions will be extracted, and finally reverse osmosis would provide fresh drinking water, all while being powered by sustainable nuclear energy.

My role over the summer was researching the extraction of bivalent ions, primarily magnesium ions, from seawater. I determined and analyzed the energy and cost requirements for all the methods related with magnesium salt extraction and conversion to pure magnesium metal. Figure below showcases the utilization one of the methodologies that I had to test to determine its effectiveness, and figure above showcases a method by Sano et al. 2018. I went beyond and researched pre-treatment of seawater, extraction of calcium, and concentration of seawater and its inaccuracies.

Two deliverables were produced during this research experience:

Research poster, presented at University of Wisconsin, Madison.
Detailed documentation on extracting magnesium.

Figure illustrating electrodialysis method for extracting magnesium from seawater. One chamber has brine flowing through cathode and yields brine, magnesium hydroxide, and hydrogen gas. The other chamber has sodium chloride solution flowing through anode and yields oxygen gas and hydrochloric acid. Sodium passes through the exchange membrane from the anode to the cathode.

Visual illustration of magnesium hydroxide

Design of a Lab-Scale Ocean Wave-Powered Desalination System | Dr. James Van de Ven

Summer 2023 (REU)

Background: Dr. James Van de Ven is a Mechanical Engineering professor at University of Minnesota. He runs the Mechanical Energy & Power Systems Laboratory (MEPS) with a focus on fluid power.

Illustration of a wave energy based desalination system. The kinetic energy of a large flap, hinged at the sea bed, is used to drive a hydraulic system. The hydraulic system uses seawater to transfer power, generate electricity, and produce freshwater.

Illustration of the core processes and elements in the desalination system.

A self-powered and decentralized wave energy converter and desalination system was proposed in prior work by the MEPS lab. The wave energy is harvested using a large oscillating flap hinged at the sea bed, whose kinetic energy is then transferred into hydraulics; the pressurized seawater is used to generate electricity and freshwater. Figure above showcases these primary traits.

My role over the summer was to help scale this full-scale system to a lab-scale hardware-in-the-loop test system. With the help of my graduate mentor, Jeremy Simmons, I:

Used fluid equations, efficiency computations, and dimension constraints to size the system.
Identified parts required to construct the system and generated a bill of materials.
Designed custom parts and fittings, and a draft assembly model.

I had to compare the maximum required pressure differential to the achievable pressure differential based on the energy losses through a specific servo valve; the maximum required flow rate is compared against the achievable flow of the pump. Performance evaluations such as this helped determine whether the combination of the chosen parts would be capable of simulating the motion of the wave energy converter.

Three deliverables were produced during this research experience:

Research poster, presented at SURE at University of Minnesota. Link to abstracts.
Extended abstract, which can be read here
Project hand-off memo, consisting of all research files and deliverables.