Predictive model using artificial neural network to design phase change material-based ocean thermal energy harvesting systems for powering uncrewed underwater vehicles

Journal Article

Title: Predictive model using artificial neural network to design phase change material-based ocean thermal energy harvesting systems for powering uncrewed underwater vehicles

Author:

Ouro-Koura, H.; Jung, H.; Li, J.; Borca-Tasciuc, D-A.; Copping, A.; Deng, Z.

Publication Date:

August 15, 2024

Journal:

Energy

Volume:

301

Pages:

131660

Publisher:

Elsevier

Affiliation:

Pacific Northwest National Laboratory (PNNL), Rensselaer Polytechnic Institute, ASM America, University of Michigan

Technology:

OTEC

Collection Method:

Lab Data, Modeling

Engineering:

Performance

Document Access

Website:

External Link

Citation

Ouro-Koura, H.; Jung, H.; Li, J.; Borca-Tasciuc, D-A.; Copping, A.; Deng, Z. (2024). Predictive model using artificial neural network to design phase change material-based ocean thermal energy harvesting systems for powering uncrewed underwater vehicles. Energy, 301, 131660. https://doi.org/10.1016/j.energy.2024.131660

Abstract

Uncrewed underwater vehicles (UUVs) significantly benefit from phase change material (PCM)-based ocean thermal energy harvesting for long mission duration. However, this technology relies on different parameters that are critical to its efficiency. Sea trials indicated that a design using this technology has lower performance than its initial specifications. This underperformance results from different factors—mainly, the UUV's trajectory, travel time, temperature fluctuations, and biofouling on the heat exchanger due to long-term underwater operations. Therefore, there exists a need to continuously monitor the ambient energy harvesting system and predict system performance for mission planning. Two major parameters that influence the energy harvesting system include the pressure inside the hydraulic accumulator and the electrical load. This work focuses on the hydraulic-to-electric energy conversion system. A combination of numerical simulation and experimental tests is used to develop a predictive model using artificial neural network (ANN) in MATLAB. 1000 data samples from a numerical model are used to train the ANN. Compared to experimental results, the ANN model predicts the designed benchtop system's total efficiency with a maximum efficiency of 51 % and an overall relative error of less than 15 %. This work will enable energy-efficient mission planning for UUVs using PCM-based ocean thermal energy harvesting.