Within the next decades the Electric Vehicle (EV) will dominate the cars market, may be before 2040, where all countries will cope with the zero emissions policy of international institutions to reduce the destructive influence of the climate change. The EVs are simpler in construction and control compared with the Internal Combustion Engine (ICE) vehicles. EV’s speed is the most important factors to be controlled and optimized. Throughout this research article the Fractional Order PID (FOPID) controller has been used to regulate the speed of the EV while meta-heuristic techniques (AEFA, AEO, SMA, GOA, AND WCA) are used to optimize the performance of the EV using Brush Less Direct Motor (BLDC).

Industry 4.0 technologies need to plan reactive maintenance and Preventive Maintenance (PM) strategies for their production machines. However, preventive maintenance cannot predict the future faults or conditions of the machine components in advance to prevent halting the production cycle. This study aims to use a Predictive Maintenance (PdM) technology with communication technologies to counter these problems. Sensors Information Modeling (SIM) and the Internet of Things (IoT) have the potential to improve the efficiency of industrial production machines maintenance management. They can provide a better maintenance strategy utilizing a data-driven predictive maintenance planning framework based on our proposed SIM and IoT technologies. Data is collected and integrated with the proposed (SIM) models and the IoT network. The proposed system consists of the data entry form that contains all the measurements, notes of events that are difficult to electronically monitor, and the credibility of data measured by sensors. The status and performance of the machine are continuously being monitored as they consciously vary according to the operating conditions. Data collection from the SIM models, and IoT network are integrated in a software framework that consists of, (1) condition and performance monitoring and faults module, (2) machine condition evaluation module, (3) failure prediction module, (4) maintenance decision module. Machine learning algorithms and artificial neural networks are used to detect the healthy or faulty operating conditions and predict probability of failures, evaluate the conditions of the machine components and estimate the remaining lifetime. To verify the feasibility of our approach, our proposed framework is applied to a corrugated board production factory real industrial environment. The results show that, updated data obtained from the information layer with machine learning algorithms in the application the layer can effectively predict the future state of the machine components to make appropriate maintenance decisions.