The rise of Industry 4.0 and smart manufacturing has highlighted the importance of utilizing intelligent manufacturing techniques, tools, and methods, including predictive maintenance. This feature allows for the early identification of potential issues with machinery, preventing them from reaching critical stages. This paper proposes an intelligent predictive maintenance system for industrial equipment monitoring. The system integrates Industrial IoT, MQTT messaging and machine learning algorithms. Vibration, current and temperature sensors collect real-time data from electrical motors which is analyzed using five ML models to detect anomalies and predict failures, enabling proactive maintenance. The MQTT protocol is used for efficient communication between the sensors, gateway devices, and the cloud server. The system was tested on an operational motors dataset, five machine learning algorithms, namely k-nearest neighbor (KNN), supported vector machine (SVM), random forest (RF), linear regression (LR), and naive bayes (NB), are used to analyze and process the collected data to predict motor failures and offer maintenance recommendations. Results demonstrate the random forest model achieves the highest accuracy in failure prediction. The solution minimizes downtime and costs through optimized maintenance schedules and decisions. It represents an Industry 4.0 approach to sustainable smart manufacturing.
Abstract. This study presents experimental and numerical investigation on the effectiveness of electrode geometry on flushing and debris removal in Electrical Discharge Drilling (EDD) process. A new electrode geometry, namely side-cut electrode, was designed and manufactured based on circular electrode geometry. Several drilling operations were performed on stainless steel 304 using rotary tubular electrodes with circular and side-cut geometries. Drilling performance was characterized by Material Removal Rate (MRR), Electrode Wear Rate (EWR), and Tool Wear Ratio (TWR). Dimensional features and surface quality of drilled holes were evaluated based on Overcut (OC), Hole Depth (HD), and Surface Roughness (SR). Three-dimensional
... Show MoreSilver/polyvinyl alcohol (Ag/PVA) nanocomposite films were synthesized via solution casting with varying concentrations of Ag nanoparticles (1–5 wt%). A comprehensive investigation was conducted to understand the influence of Ag content on the structural, optical, mechanical, thermal, electrical, and antibacterial properties of the composites. UV-Vis spectroscopy revealed a red shift in absorption peaks and a reduction in the optical band gap, which decreased from 3.78 eV for pure PVA to 3.37 eV for the 5 wt% Ag composite. FTIR and SEM analyses confirmed successful nanoparticle incorporation and morphological changes. The nanocomposites exhibited enhanced tensile strength, elongation at break, Young’s modulus, and hardness due t
... Show MorePolymer blended electrolytes of various concentrations of undoped PAN/PMMA (80/20, 75/25, 70/30, 65/35 and 60/40 wt%) and doped with lithium salts (LiCl, Li2SO4H2O, LiNO3, Li2CO3) at 20% wt have been prepared by the solution casting method using dimethylformamide as a solvent. The electrical conductivity has been carried out using an LCR meter. The results showed that the highest ionic conductivity was 2.80x10-7 (Ω.cm)-1 and 1.05x10-1 (Ω.cm)-1 at 100 kHz frequency at room temperature for undoped (60% PAN + 40% PMMA) and (80% PAN + 20% PMMA) doped with 20%wt Li2CO3 composite blends, respect
... Show MoreChannel estimation (CE) is essential for wireless links but becomes progressively onerous as Fifth Generation (5G) Multi-Input Multi-Output (MIMO) systems and extensive fading expand the search space and increase latency. This study redefines CE support as the process of learning to deduce channel type and signal-tonoise ratio (SNR) directly from per-tone Orthogonal Frequency-Division Multiplexing (OFDM) observations,with blind channel state information (CSI). We trained a dual deep model that combined Convolutional Neural Networks (CNNs) with Bidirectional Recurrent Neural Networks (BRNNs). We used a lookup table (LUT) label for channel type (class indices instead of per-tap values) and ordinal supervision for SNR (0–20 dB,5-dB steps). T
... Show MoreObjective: To identify the effect of the cube model on visual-spatial intelligence and learning the skill of spikinging in volleyball for female students, The researchers used the experimental method by designing two equivalent groups with pre- and post-measurements. Research methodology: The main research sample of (30) female students was selected from the research community represented by second-stage students in the College of Physical Education and Sports Sciences - University of Baghdad for the academic year (2024-2025). The sample was divided equally into two control and experimental groups. The researchers conducted the sample homogenization process and the equivalence process between the two groups in the variables of visua
... Show MoreIn order to advance the education process and raise the educational level of the players, it became necessary to introduce new educational aids, programmed education in the education process, through which the basic skills to be learned are explained and clarified, and immediate feedback is provided that would enhance the information of the learner, and Reaching the goal to be achieved, taking into account the individual differences between the players, and thus it is possible to move away from the educational methods used in learning skills, which requires great effort and time, in addition to that the open playground may not perform the skill accurately and the player looks from one side, while when using the computer you look from severa
... Show More