This study proposes a hybrid predictive maintenance framework that integrates the Kolmogorov-Arnold Network (KAN) with Short-Time Fourier Transform (STFT) for intelligent fault diagnosis in industrial rotating machinery. The method is designed to address challenges posed by non-linear and non-stationary vibration signals under varying operational conditions. Experimental validation using the FALEX multispecimen test bench demonstrated a high classification accuracy of 97.5%, outperforming traditional models such as SVM, Random Forest, and XGBoost. The approach maintained robust performance across dynamic load scenarios and noisy environments, with precision and recall exceeding 95%. Key contributions include a hardware-accelerated K

CIGS nanoink has synthesized from molecular precursors of CuCl, InCl3, GaCl3 and Se metal heat up 240 °C for a half hour in N2-atmosphere to form CIGS nanoink, and then deposited onto substrates of soda-lime glass (SLG). This work focused on CIGS nanocrystals, indicates their synthesis and applications in photovoltaic devices (PVs) as an active light absorber layers. in this work, using spin-coating to deposit CIGS layers (75 mg/ml and 500 nm thickness), without selenization at high temperatures, were obtained up to 1.398 % power conversion efficiency (PCE) at AM 1.5 solar illumination. Structural formations of CIGS chalcopyrite structure were studied by using x ray diffraction XRD. The morphology and composition of CIGS were studied using

ABSTRACT:

              Interest rates are one of the important aspects that affect the banking business directly, which is characterized by unstable dynamic dynamics, which must be viewed on a daily and continuous basis through the macroeconomic view, which directly affects the bank’s income realized from loans as interest received or interest paid on its deposits as an expense. Hence the earnings per share. The relationship between interest rates and between net income and earnings per share was measured and a correlation was found between them, and then the effect between them was measured using regression equations and they were applied and th

The purpose of this study is to evaluate the hydraulic performance and efficiency of using direction diverting blocks, DDBs, fixed on the surface on an Ogee spillway in reducing the acceleration and dissipating the energy of the incoming supercritical flow. Fifteen types of DDB models were made from wood with a triangulate shape and different sizes were used. Investigation tests on pressure distribution at the DDBs boundaries were curried out to insure there is no negative pressures is developed that cause cavitation. In these tests, thirty six test runs were accomplished by using six types of blocks with the same size but differ in apex angle. Results of these test showed no negative pressures developed at the boundarie

Various theories have been proposed since in last century to predict the first sighting of a new crescent moon. None of them uses the concept of machine and deep learning to process, interpret and simulate patterns hidden in databases. Many of these theories use interpolation and extrapolation techniques to identify sighting regions through such data. In this study, a pattern recognizer artificial neural network was trained to distinguish between visibility regions. Essential parameters of crescent moon sighting were collected from moon sight datasets and used to build an intelligent system of pattern recognition to predict the crescent sight conditions. The proposed ANN learned the datasets with an accuracy of more than 72% in comp

A fast laser texturing technique has been utilized to produce micro/nano surface textures in Silicon by means of UV femtosecond laser. We have prepared good absorber surface for photovoltaic cells. The textured Silicon surface absorbs the incident light greater than the non-textured surface. The results show a photovoltaic current increase about 21.3% for photovoltaic cell with two-dimensional pattern as compared to the same cell without texturing.

The paper proposes a methodology for predicting packet flow at the data plane in smart SDN based on the intelligent controller of spike neural networks(SNN). This methodology is applied to predict the subsequent step of the packet flow, consequently reducing the overcrowding that might happen. The centralized controller acts as a reactive controller for managing the clustering head process in the Software Defined Network data layer in the proposed model. The simulation results show the capability of Spike Neural Network controller in SDN control layer to improve the (QoS) in the whole network in terms of minimizing the packet loss ratio and increased the buffer utilization ratio.

The aim of this study was to making an analytical study in some kinematics variables in (200) meter breaststroke swimming to first ranking in championship 2003 – Spanish. The swimming in our country still suffering from several obstruction with retarded it’s development for the better since the investigators observe the insufficiency of swimming in our country to any analytical study for the international champions, this led to no specific and scientific discovering to these advanced levels as the estimation of the value of performance from the Iraqi coaches dependent on personality observation dependent on their opinion without referring to the specific and scientific diction. The investigators dependent on several kinematics variables