Volume 14 | Issue 7 | July-2026

 Abstract

Accidents involving electric vehicle fires have increased as the number of electric vehicles has grown recently. The issue of charging safety is a key barrier to the growth of the electric vehicle sector because these accidents have resulted in large financial losses for car owners and charging facility operators. The approach for resolving the issue of electric car charging safety through an electric vehicle charging safety warning system is suggested in this research. The suggested solution uses an adaptive optimization of long short-term memory neural network (A-LSTM) to forecast voltage changes throughout the whole charging process by using the vehicle's daily historical charging data. The warning threshold adjustment method is established by the difference between the predicted voltage data and the actual voltage data, which is dynamically adjusted as the charging process progresses. Finally, a real-time warning model for vehicle charging alert is developed. The daily charging data of electric vehicles is used in the paper to verify the precision of data prediction and the accuracy and timeliness of the model. The study's findings demonstrate that the early warning model suggested in this paper can quickly send out early warning signals to safeguard the safety of car charging and can identify aberrant charging data.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Electric Vehicle Charging, Safety Warning System, Long Short-Term Memory (LSTM), Attention Mechanism, Adaptive Threshold, Thermal Runaway.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

T Lithium-ion batteries remain foundational to electric vehicle propulsion and stationary energy storage, yet the persistent tension between fast charging throughput and long-term electrochemical health continues to constrain their practical deployment. Conventional constant-current constant-voltage protocols, while computationally inexpensive, impose rigid current and voltage boundaries that fail to adapt to progressive cell degradation, accelerating solid-electrolyte interphase growth and lithium plating over repeated charge cycles. Advanced control paradigms - spanning model predictive control, side-reaction overpotential regulation, and increasingly, deep reinforcement learning - have emerged as promising alternatives capable of balancing charging speed against battery longevity. Among these, lifelong or continual reinforcement learning frameworks represent the most ambitious frontier, enabling charging agents that continuously adapt their policies as cells age without discarding prior learning.. A structured literature synthesis table is presented to facilitate direct cross-study comparison across topology, method, key contribution, and identified limitation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Battery degradation, deep reinforcement learning, electric vehicle, fast charging, lifelong learning, lithium-ion battery, model predictive control, single particle model, state of charge, state of health.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a comparative analysis of photovoltaic (PV) systems operating with and without maximum power point tracking (MPPT). The MPPT techniques considered are the Perturb and Observe (P&O) and Incremental Conductance (IC) algorithms. The objective is to evaluate and identify the algorithm that achieves higher efficiency in extracting maximum power from PV cells. A boost converter is employed to ensure impedance matching between the PV array and the load, thereby improving energy transfer. The systems - without MPPT, with P&O are modeled and simulated in MATLAB/Simulink, and their performance is analyzed under varying operating conditions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Photovoltaic system; maximum power point tracking (MPPT); Perturb and Observe; boost converter; MATLAB/Simulink.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Battery energy storage systems (BESS) have emerged as a cornerstone technology for enabling large- scale renewable energy integration and providing essential grid ancillary services. This review synthesises recent advances in BESS electrochemical technologies--including lithium-ion (NMC, LFP), vanadium redox flow batteries, and emerging chemistries--alongside power conversion architectures, control strategies (droop, virtual synchronous generator, model predictive control), and energy management systems. Applications spanning frequency regulation, peak shaving, voltage support, renewable firming, and black-start capability are critically examined. Sizing and optimisation methodologies including MILP, particle swarm optimisation, and genetic algorithms are reviewed in the context of techno-economic performance. Degradation mechanisms, state-of-health estimation, and thermal management strategies are analysed, followed by a discussion of prevailing challenges in safety, supply chain, recycling, and grid-code compliance. Global installed BESS capacity grew from approximately 9 GWh in 2018 to 95 GWh by 2024, underscoring the technology's accelerating deployment trajectory.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Battery energy storage systems, frequency regulation, grid integration, lithium iron phosphate, model predictive control, renewable energy

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project is about creating a smart robot that helps parents take care of their babies using a small computer called Raspberry PI . The robot uses sensors and a camera to watch the baby and the room. It can hear when the baby cries and tell the parents right away through a phone app. It also lets parents talk to their baby and can gently rock the baby's cradle to help them sleep. This system helps keep babies safe and makes it easier for parents to care for them, even when they are not close by.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

GPS tracking system,ESP32-CAM.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Poor quality of electric supply is normally caused by power line disturbances such as transients, notches, momentary interruptions, voltage sag and swell, over-voltage, under-voltages and harmonic distortions. Filters are used for improving the power quality. Active and Passive filters eliminate major fluctuating factors. Hybrid filters are the combination of active and passive filters. Conventional Active Filtering using PLL also reduces the harmonics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Harmonics; Hybrid Topology; Nonlinear Load; Power Quality (PQ);

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Power quality issues have become a major concern in modern distribution systems due to the increasing use of voltage-sensitive equipment. Among various power quality disturbances, voltage sag is the most frequent and severe problem, causing malfunction or tripping of sensitive loads and resulting in significant financial losses. A Dynamic Voltage Restorer is recognized as an effective custom power device for mitigating voltage sag by injecting the required compensating voltage in series with the supply.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

HARDWARE IMPLEMENTATION OF DYNAMIC VOLTAGE RESTORER TO REDUCE VOLTAGE SAG

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Solar Energy based rooftop trains are an innovative and eco-friendly transportation system designed to reduce fuel consumption and environmental pollution in railway networks. In this system, solar panels are mounted on the roof of train coaches to capture sunlight and convert it into electrical energy using photovoltaic cells. The generated electricity is used to power lighting systems, fans, charging ports

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

SOLAR BASED ROOF TOP SYSTEM ON TRAINS

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The growing demand for intelligent and automated solutions in daily life has led to the development of smart systems that enhance convenience, safety, and efficiency. One such critical area is infant care, where continuous monitoring and timely response are essential for ensuring the well-being of a baby. In many modern households, caregivers often face difficulty in maintaining constant supervision due to work commitments and other responsibilities. This situation creates a need for a reliable system that can assist in monitoring infants and responding appropriately without continuous human intervention. The proposed work presents the design and development of an AI-based smart cradle system that combines embedded technology, sensor networks, and intelligent decision-making to improve infant care.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Smart Cradle, Infant Monitoring, Internet of Things, Embedded Systems, Automation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Road maintenance, particularly pothole repair, poses significant challenges for transportation authorities worldwide. Traditional methods of pothole detection and repair are often inefficient and costly. This project introduces a semi-automated robotic system for pothole identification and repair cost estimation, aiming to streamline road maintenance processes. The system employs an ultrasonic sensor for pothole detection, a GPS module for location tracking, and a Node MCU controller for data integration. An Arduino ATmega328 controller manages robot movement via servo and DC motors. The robot utilizes the depth measurements from the ultrasonic sensor to estimate repair costs based on the thickness of road layers. Real-time data is displayed on an LCD screen and transmitted wirelessly through Bluetooth and the Blynk IoT platform. Initial tests demonstrate the system's ability to accurately detect potholes, measure their depth, and estimate repair costs. The robot successfully navigates road surfaces, providing precise location data for each identified pothole. Cost estimations show a strong correlation with actual repair expenses, varying based on pothole depth and corresponding road layer thickness. This semi-automated approach offers a promising solution for enhancing road maintenance efficiency. By automating pothole detection and providing accurate cost estimates based on depth and road layer thickness, the system has the potential to optimize resource allocation and improve overall road quality. Future work will focus on expanding the system's capabilities and conducting large-scale field trials.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Pothole detection, Semi-automated robot, IoT, Ultrasonic sensing, GPS mapping, Repair cost estimation, Road maintenance, Infrastructure management.

  License

Creative Commons Attribution 4.0 and The Open Definition