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 KAN architecture, adaptive feature selection, and integration of explainable AI for interpretability. This framework enables real-time, transparent diagnostics in energy-critical, resource-constrained environments, supporting improved asset lifecycle management and reduced downtime. The study advances AI-based condition monitoring, bridging theoretical innovation with practical reliability in the context of sustainable industrial energy systems.
At the temperature 298.15 K, some physical properties such as: refractive indices (nD), viscosities (η) and densities (ρ) were studied in four liquid-liquid mixtures: carboxylic acids (HCOOH, CH3COOH, CH3CH2COOH and CH3CH2CH2COOH) with tetrahydrofurfuryl alcohol (THFA) with the identified configuration set. These empirical data were utilized to estimate the excess molar volumes (Vm E), refractive index perversions (ΔR), viscosity deviations (ηE) and excess molar Gibbs free energy (ΔG*E). Values of Vm E, ηE , ΔG*E and ΔR were plotted versus mole fraction of tetrahydrofurfuryl alcohol. In all cases, the values of Vm E, ηE , ΔG*E and ΔR that obtained in this study were found to be negative at 298.15 K. The excess parameters
... Show MoreSurface electromyography (sEMG) and accelerometer (Acc) signals play crucial roles in controlling prosthetic and upper limb orthotic devices, as well as in assessing electrical muscle activity for various biomedical engineering and rehabilitation applications. In this study, an advanced discrimination system is proposed for the identification of seven distinct shoulder girdle motions, aimed at improving prosthesis control. Feature extraction from Time-Dependent Power Spectrum Descriptors (TDPSD) is employed to enhance motion recognition. Subsequently, the Spectral Regression (SR) method is utilized to reduce the dimensionality of the extracted features. A comparative analysis is conducted between the Linear Discriminant Analysis (LDA) class
... Show MoreThe measurement data of the raw water quality of Tigris River were statistically analyzed to measure the salinity value in relation to the selected raw water quality parameters. The analyzed data were collected from five water treatment plants (WTPs) assembled alongside of the Tigris River in Baghdad: Al-Karkh, Al-Karama, Al-Qadisiya, Al-Dora, and Al-Wihda for the period from 2015 to 2021. The selected parameters are total dissolved solid (TDS), electrical conductivity (EC), pH and temperature. The main objective of this research is to predicate a mathematical model using SPSS software to calculate the value of salinity along the river, in addition, the effect of electrical conductivi
Artificial Neural networks (ANN) are powerful and effective tools in time-series applications. The first aim of this paper is to diagnose better and more efficient ANN models (Back Propagation, Radial Basis Function Neural networks (RBF), and Recurrent neural networks) in solving the linear and nonlinear time-series behavior. The second aim is dealing with finding accurate estimators as the convergence sometimes is stack in the local minima. It is one of the problems that can bias the test of the robustness of the ANN in time series forecasting. To determine the best or the optimal ANN models, forecast Skill (SS) employed to measure the efficiency of the performance of ANN models. The mean square error and
... Show MoreThis work proposes a new video buffer framework (VBF) to acquire a favorable quality of experience (QoE) for video streaming in cellular networks. The proposed framework consists of three main parts: client selection algorithm, categorization method, and distribution mechanism. The client selection algorithm was named independent client selection algorithm (ICSA), which is proposed to select the best clients who have less interfering effects on video quality and recognize the clients’ urgency based on buffer occupancy level. In the categorization method, each frame in the video buffer is given a specific number for better estimation of the playout outage probability, so it can efficiently handle so many frames from different video
... Show MoreThe purpose of this paper is to develop a hybrid conceptual model for building information modelling (BIM) adoption in facilities management (FM) through the integration of the technology task fit (TTF) and the unified theory of acceptance and use of technology (UTAUT) theories. The study also aims to identify the influence factors of BIM adoption and usage in FM and identify gaps in the existing literature and to provide a holistic picture of recent research in technology acceptance and adoption in the construction industry and FM sector.
In this work, a test room was built in Baghdad city, with (2*1.5*1.5) m3 in dimensions, while the solar chimneys (SC) were designed with aspect ratio (ar) bigger than 12. Test room was supplied by many solar collectors; vertical single side of air pass with ar equals 25, and tilted 45o double side of air passes with ar equals 50 for each pass, both collectors consist of flat thermal energy storage box collector (TESB) that covered by transparent clear acrylic sheet, third type of collector is array of evacuated tubular collectors with thermosyphon in 45o instelled in the bottom of TESB of vertical SC. The TESB was
... Show More