Narrow Results

The modernization that is currently taking over across the world is resulting in numerous advancements in a variety of industries, and the most notable and apparent development is the rising use of solar energy, which has become more prevalent every day. Most companies, residences, schools, and other organizations rely mostly on solar energy as the main source of electricity. It was discovered that anti-reflective coating (ARC) had been applied to solar cells with the goal of increasing power conversion efficiency, decreasing reflection loss, and improving absorption. Although a single layer of ARC is sufficient, applying an additional layer might improve the solar cell application’s effectiveness. Hence, the modeling and analysis of double layers of anti-reflection coating (ARC) with different types of materials have been investigated and evaluated using personal computer one-dimensional (PC1D) simulation software. In this study, the double-layer anti-reflection coating on the solar cell was modeled using PC1D, where this software allowed for one-dimensional simulation of the parameters required for the operation of semiconductor-based solar energy systems. The PC1D simulation reveals that SiO₂/TiO₂ has the highest efficiency (22.82%) and lowest reflection compared to Si₃N₄/TiO₂ and ZnO/TiO₂. Also, SiO₂/TiO₂ generates the highest external quantum efficiency (EQE) among ARC double layers, making it ideal for silicon solar cell applications in order to boost the solar cell’s efficiency. The results for the effects of current, voltage, reflection, and EQE of the different double layers of ARC have also been studied in this paper.

To reduce the aerodynamic load of super high-speed elevators, in this paper, the coefficient of drag $C_d$ and the coefficient of yawing moment $C_{ym}$ of the elevator are selected as optimization objectives for the optimization of the air rectification cover (ARC) shape. The elliptic curve method was used to build the parametric model of the ARCs, six design variables were selected, and the design space of the ARC was determined. With the optimal Latin hypercube design method, the training points were selected, and the computational fluid dynamics numerical simulation was conducted to calculate the corresponding responses. Then, the relationship between the design variables and the responses was analyzed. The radial basis function (RBF) surrogate model of the relationship between the design variables and responses was constructed. Finally, the non-dominated sorting genetic algorithm-II (NSGA-II) was employed to optimize the shape of the ARC. The results show that the $C_d$ and $C_{ym}$ decrease by 16.51% and 60.92%, respectively, compared with the unoptimized ARC, indicating that the ARC designed in this paper is optimized and can effectively reduce the aerodynamic load. Furthermore, among all the design variables, the bluntness of the ARC in the $X$-direction has the most significant effect on the aerodynamic load, and the height of the ARC ($h_1$ and $h_2$) has the second most significant effect on the aerodynamic load of elevators.

Although the most important feature of a classifier is its generalization capability, the effectiveness of a training procedure is strictly related to its automation degree. A low automation degree can be a serious drawback for a classification system, since it can prevent an unskilled user from successfully generating an acceptable model. From this point of view, a learning procedure should not depend on any critical parameter. Among fuzzy classifiers, Min-Max networks have the advantage to be trained in a constructive way, with a simple learning procedure. The use of the hyperbox as a frame on which different membership functions can be modeled, makes the Min-Max network a flexible tool. The present chapter focuses on Fuzzy Min-Max networks and on improved versions recently developed in order to overcome some inconveniences. By relying on a basic principle of Learning Theory, a simple technique to improve generalization capability will be described. The application of this technique to the Min-Max fuzzy classifier yields the Optimized Min-Max training algorithm (OMM), which is able to choose automatically a critical parameter that affects the original Simpson's learning procedure. However, OMM still exhibits the same inconveniences that characterize Min-Max learning; in particular there is an excessive dependence on the presentation order of the training set and the coverage resolution is constrained to be the same in the overall input space.

The Adaptive Resolution Classifier (ARC) is a batch training algorithm for Min-Max Fuzzy networks able to overcome these drawbacks. ARC is characterized by a high automation degree and allows obtaining networks with a remarkable generalization capability. In order to further improve the reconstruction capability of the decision region, it is necessary to consider a new type of fuzzy neural network. By adopting the Generalized Min-Max model (GMM) it is possible to arrange the hyperbox orientation along any direction of the data space. A suitable training algorithm (GPARC) can be used for the automatic determination of the optimal GMM model. The performances of ARC, PARC and GPARC training algorithms will be discussed through a set of bidimensional toy problems and real data benchmarks.