Nanostructured Materials for Energy Storage and Conversion

Unlocking the Power of Artificial Intelligence: Accurate Zeta Potential Prediction Using Machine Learning

Nanoparticles have gained significance in modern science due to their unique characteristics and diverse applications in various fields. Zeta potential is critical in assessing the stability of nanofluids and colloidal systems but measuring it can be time-consuming and challenging. The current research proposes the use of cutting-edge machine learning techniques, including multiple regression analyses (MRAs), support vector machines (SVM), and artificial neural networks (ANNs), to simulate the zeta potential of silica nanofluids and colloidal systems, while accounting for affecting parameters such as nanoparticle size, concentration, pH, temperature, brine salinity, monovalent ion type, and the presence of sand, limestone, or nano-sized fine particles. Zeta potential data from different literature sources were used to develop and train the models using machine learning techniques. Performance indicators were employed to evaluate the models' predictive capabilities. The correlation coefficient (r) for the ANN, SVM, and MRA models was found to be 0.982, 0.997, and 0.68, respectively. The mean absolute percentage error for the ANN model was 5%, whereas, for the MRA and SVM models, it was greater than 25%. ANN models were more accurate than SVM and MRA models at predicting zeta potential, and the trained ANN model achieved an accuracy of over 97% in zeta potential predictions. ANN models are more accurate and faster at predicting zeta potential than conventional methods. The model developed in this research is the first ever to predict the zeta potential of silica nanofluids, dispersed kaolinite, sand-brine system, and coal dispersions considering several influencing parameters. This approach eliminates the need for time-consuming experimentation and provides a highly accurate and rapid prediction method with broad applications across different fields.

Geometric Optimization of Perovskite Solar Cells with Metal Oxide Charge Transport Layers

Perovskite solar cells (PSCs) are a promising area of research among different new generations of photovoltaic technologies. Their manufacturing costs make them appealing in the PV industry compared to their alternatives. Although PSCs offer high efficiency in thin layers, they are still in the development phase. Hence, optimizing the thickness of each of their layers is a challenging research area. In this paper, we investigate the effect of the thickness of each layer on the photoelectric parameters of n-ZnO/p-CH₃NH₃PbI₃/p-NiO_x solar cell through various simulations. Using the Sol-Gel method, PSC structure can be formed in different thicknesses. Our aim is to identify a functional connection between those thicknesses and the optimum open-circuit voltage and short-circuit current. Simulation results show that the maximum efficiency is obtained using a perovskite layer thickness of 200 nm, an electronic transport layer (ETL) thickness of 60 nm, and a hole transport layer (HTL) thickness of 20 nm. Furthermore, the output power, fill factor, open-circuit voltage, and short-circuit current of this structure are 18.9 mW/cm², 76.94%, 1.188 V, and 20.677 mA/cm², respectively. The maximum open-circuit voltage achieved by a solar cell with perovskite, ETL and HTL layer thicknesses of (200 nm, 60 nm, and 60 nm) is 1.2 V. On the other hand, solar cells with the following thicknesses, 800 nm, 80 nm, and 40 nm, and 600 nm, 80 nm, and 80 nm, achieved a maximum short-circuit current density of 21.46 mA/cm² and a fill factor of 83.35%. As a result, the maximum value of each of the photoelectric parameters is found in structures of different thicknesses. These encouraging results are another step further in the design and manufacturing journey of PSCs as a promising alternative to silicon PV.