Intelligent Geothermal Energy Storage: Integration of Nano-Enhanced Phase Change Materials, Sub-Surface Diagnostics, and Edge-Native Deep Learning for Real-Time Structural Health Monitoring
Intelligent Geothermal Energy Storage: Integration of Nano-Enhanced Phase Change Materials, Sub-Surface Diagnostics, and Edge-Native Deep Learning for Real-Time Structural Health Monitoring
Amirhossein Ghadamyari1 Ali Azizi2 Ali Asghar Shojaat3 Masoud Mirzaei4
1) Department of Metallurgy, Ma.C., Islamic Azad University, Mashhad, Iran,
2) Department of Extractive Metallurgy, School of Metallurgy and Materials Engineering, Iran University of Science and Technology, Tehran, Iran
3) Department of Advanced Materials and Nanotechnology, Imam Hossein University, Tehran, Iran,
4) Department of Metallurgy, Ma.C., Islamic Azad University, Mashhad, Iran,
IOI Code
:
AAHD-ABKEAZ
Publication :
National Conference on Information Technology, Nanotechnology, Artificial Intelligence and Technological Futures Studies(itnaf.ir)
Abstract :
The global transition toward grid-scale thermal energy storage (TES) necessitates advanced media capable of overcoming volumetric constraints inherent in sensible heat reservoirs. This report evaluates a comprehensive materials and computational framework for latent heat thermal energy storage (LHTES), utilizing engineered porous sedimentary and micro-fractured igneous rock matrices infiltrated with nanocomposite phase change materials (Nano-PCMs). While Nano-PCMs substantially elevate volumetric energy density via isothermal phase transitions, their integration into subterranean formations introduces critical vulnerabilities, including thermomechanical fatigue, micro-cracking, and accelerated chemical leaching during high-temperature cycling. This study details the synthesis of carbon- and metal-oxide-doped Nano-PCMs, rigorously defining dispersion parameters to maximize phonon transport while suppressing agglomeration. A specific procedure for geological matrix infiltration via vacuum impregnation is established, combined with an in-situ supramolecular lock shell encapsulation and silica-nanofluid wettability alteration to mitigate primary silicate dissolution. To continuously monitor reservoir integrity, a hybrid diagnostic architecture is formulated, multiplexing Fiber Bragg Grating (FBG) optical sensors with Electrochemical Impedance Spectroscopy (EIS). These disparate data streams are ingested by a decentralized Edge AI platform utilizing NVIDIA Jetson Nano architectures. A Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) topology processes the multivariate time-series data to predict incipient structural failure. To rectify acute class imbalance in failure data, Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) are deployed. The framework yields a enhancement in base thermal conductivity, near-zero leakage, and predictive anomaly detection achieving an Area Under the Curve (AUC) of 0.97, establishing a resilient architecture for next-generation geothermal energy storage.
Keywords : geothermal energy energystorage nano pcms edge ai structural health monitoring cnn lstm