الفهرس | Only 14 pages are availabe for public view |
Abstract Energy deficiency has become a critical issue. It has influenced the development of new fuel sources. Compared with classical computing methods, artificial intelligence including deep learning provides accurate and rapid automated learning and analysis due to a variety of advantageous circumstances. In this study, we introduce a new rapid and facial strategy using deep learning (DL) regression models to predict the relationship between capacitance and various variables. Typically, we use a one-dimensional convolutional neural network (CNN Conv 1d 1), and stacked ensemble models. According to experimental results, the performance of the different DL models is ranked as follows: stacked ensemble-based CNN Conv 1d > CNN Conv 1d1> CNN Conv 1d 2. Among these models, the stacked ensemble of two CNN Conv 1d 1 models shows the best performance, i.e., RMSE of approximately 66.013, and can generate the relative contribution of all variables to the capacitance in carbon-based supercapacitors, demonstrating the accurate prediction of the stacked ensemble-based CNN Conv 1d model because of its simple structure. Overall, the proposed DL-based stacked ensemble method is an accurate, rapid, and effective approach for capacitance prediction of energy storage devices due to using various regression techniques. This study deals with the Zinc oxide (ZnO) nanocomposite as a supercapacitor and the modeling of its cyclic voltammetry behavior using an Artificial Neural Network (ANN) and Random Forest Algorithm (RFA). A good agreement was found between experimental results and the predicted values generated by using ANN and RFA. Simulation results confirmed the accuracy of the models compared to measurements from supercapacitor module power-cycling. A comparison of best performance between ANN and RFA models shows that the ANN models performed better (value of MAE = 0.18) than the RFA models for all datasets used in this study. The results of the ANN and RFA models could be useful in designing unique nanocomposites for supercapacitors and other strategies related to energy and the environment. Keywords: Supercapacitors, Carbon nanomaterials, Zinc oxide nanomaterials, Artificial intelligence, Machine learning, Deep learning, Stack ensemble model, cyclic voltammetry. |