Claim Missing Document
Check
Articles

Found 7 Documents
Search

Dual axis solar tracking system for agriculture applications using machine learning Somasundaram, Deepa; Dhandapani, Lakshmi; Kathirvel, Jayashree; Sagayaraj, Marlin; Jagadeesan, Vijay Anand
International Journal of Power Electronics and Drive Systems (IJPEDS) Vol 15, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijpeds.v15.i1.pp631-638

Abstract

The three most basic amenities required for human survival are food, shelter and clothing. In today's tech-savvy generation, these have experienced a great deal of scientific advancement. Unfortunately, agriculture is still more man power-oriented. So they have to rely on the hit and trial method to learn from experience which leads to waste of time. In proposed work includes an automated system using dual axis solar tracking system and gives crop recommendation for different types of soil to yield maximum. The suggested system is a dual-axis solar tracker based on machine learning that is intended to considerably increase the effectiveness of energy harvesting. The approach makes use of the logistic regression algorithm (LR) to do this. This novel strategy tries to maximize the solar panel's ability to produce energy, leading to increased energy yields. The quality of soil is predicted by using suitable sensors for crop recommendation. The data’s are temperature, humidity, pH of soil, nitrogen, phosphorous & potassium in soil and rainfall in soil are considered. For crop recommendation six algorithms- SVM, KNN, Native Bays, Logistic Regression, Decision Tree classifier, Random Forest Classifier are applied and tested. It is found that random forest classifier gave us excellent results.
Optimal fuzzy controller for speed control of DC drive using salp swarm algorithm Somasundaram, Deepa; Arumugham, Sasikala; Ramalingam, Puviarasi; Dhandapani, Kirubakaran; Ramaiyan, Kalaivani
International Journal of Power Electronics and Drive Systems (IJPEDS) Vol 15, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijpeds.v15.i3.pp1951-1958

Abstract

The inherent non-linearity of the system being investigated highlights the limitations of traditional proportional integral or PI tuning approaches. Consequently, the primary objective of this study is to construct and refine the PI controller by leveraging the salp swarm algorithm, aiming to enhance the performance of the DC drive output. Through the application of the salp swarm algorithm, the fuzzy PI controller undergoes dynamic online modifications, leading to optimal results. The controller's superior performance is achieved by employing an optimization approach to identify the optimal set of solutions for the Fuzzy PI parameters. Rigorous simulations are conducted to comprehensively evaluate the proposed salp swarm algorithm technique, assessing its viability and efficacy in real-world. Thorough simulations assess the viability of the salp swarm algorithm, evaluating its effectiveness in real-world applications. The study demonstrates the methodology's reliability through comparative analyses of DC/DC converters against alternative methods. In non-linear systems like the DC drive, innovative optimization strategies are shown to significantly boost PI controller performance. The findings offer valuable insights for advanced control system design.
Machine learning applications for predicting system production in renewable energy Somasundaram, Deepa; Muthukumar, R.; Rajavinu, N.; Ramaiyan, Kalaivani; Kavitha, P.
International Journal of Power Electronics and Drive Systems (IJPEDS) Vol 15, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijpeds.v15.i3.pp1925-1933

Abstract

Renewable energy systems play pivotal role in addressing the global challenge of sustainable energy production. Efficiently harnessing energy from renewable sources requires accurate prediction models to optimize system production. This paper delves into the realm of predictive modeling, focusing on the utilization of machine learning techniques to forecast system production in renewable energy systems. The investigation incorporates a range of factors such as wind speed, sunshine, air pressure, radiation, air temperature, and relative air humidity, alongside temporal data ('Date-Hour (NMT)'). These factors undergo rigorous curation and preprocessing to ensure the reliability and quality of the predictive model. Various machine learning algorithms, including linear regression, decision tree, random forest, and support vector machine (SVM), are employed to examine the relationships between these factors and system production. The findings are assessed using metrics such as mean squared error, mean absolute error, and R-squared. Through comparative analysis, the study illuminates the strengths and limitations of each algorithm, providing valuable insights into their suitability for renewable energy forecasting. This paper adds to renewable energy research by examining how machine learning predicts system production. The insights are valuable for researchers, practitioners, and policymakers in sustainable energy development.
Smart solar maintenance: IoT-enabled automated cleaning for enhanced photovoltaic efficiency Ramalingam, Puviarasi; Kathirvel, Jayashree; Adaikalam, Arul Doss; Somasundaram, Deepa; Sreenivasan, Pushpa
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 1: July 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i1.pp14-19

Abstract

This innovative project aims to increase the effectiveness and user experience of solar panel systems by introducing a state-of-the-art dust and speck removal system. Leveraging cutting-edge technology, the system demonstrates a remarkable 32% increase in power output compared to dirty solar panels. The approach is characterized by its reliance on the universe as the system controller, reducing the need for manual intervention and minimizing the workforce required for panel cleaning. The proposed timed system utilizes water and wipers, facilitated by internet of things (IoT) technology, microcontrollers, and sensor modules for efficient and automated operation. An Android application provides user control and notifications about ongoing processes. The system’s adaptability for various settings is emphasized, offering a portable solution. The smart IoT based automatic solar panel cleaning ensures reliable performance, underscoring the project’s commitment to improve scalability, cost-efficiency, performance, integrity, and consistency.
Enhanced vegetation encroachment detection along power transmission corridors using random forest algorithm Somasundaram, Deepa; Sivaraj, Nivetha; Shalinirajan, Shalinirajan; Karuppiah, Santhi; Rajendran, Sudha
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 2: May 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i2.pp1376-1382

Abstract

Vegetation encroachment along power transmission corridors poses significant risks to infrastructure safety and reliability, necessitating effective monitoring and management strategies. This study introduces an innovative methodology for detecting vegetation encroachment using a combination of manual and automatic processes integrated with the random forest algorithm. The issue of vegetation encroachment is critical as it can lead to power interruptions and safety hazards if not addressed promptly. The objective of this research is to develop a scalable and cost-effective solution for vegetation management in power infrastructure maintenance. The methodology involves manual patch extraction and labeling to ensure the accuracy of the training dataset, combined with automatic feature extraction techniques to capture relevant information from satellite imagery. Leveraging the random forest algorithm, the model constructs an ensemble of decision trees based on the extracted features, achieving robust classification accuracy. Findings from this study demonstrate that the proposed approach enables consistent and timely identification of vegetation encroachment in new satellite imagery. Stored model parameters facilitate efficient testing, enhancing the system's ability to provide proactive interventions. This scalable solution significantly reduces reliance on manual labor and offers a cost-effective method for continuous monitoring, ultimately contributing to the resilience and safety of power transmission infrastructure.
Wind turbine defect detection using deep learning Somasundaram, Deepa; Vanitha, M.; Kumar, T. Sathish; Adaikalam, I. Arul Doss; Kavitha, P.; Kalaivani, R.
International Journal of Power Electronics and Drive Systems (IJPEDS) Vol 16, No 2: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijpeds.v16.i2.pp1348-1355

Abstract

Wind turbines play a critical role in the generation of renewable energy, but their maintenance and inspection, especially in large-scale wind farms, present significant challenges. Traditionally, wind turbines have been inspected manually, a process that is not only time-consuming but also costly and risky. Unmanned aerial vehicles (UAVs) have emerged as an efficient alternative, offering a safer and more economical means of gathering inspection data. However, the challenge lies in the manual analysis of the collected data, which demands expertise and considerable time. This paper proposes using object detection algorithms, specifically YOLOv8, to automate the detection of wind turbines and their defects, streamlining the inspection process. The model is trained on wind turbine images to identify potential faults such as cracks and corrosion. This approach aims to increase the accuracy and efficiency of wind turbine maintenance, ensuring prompt defect detection and reducing both operational costs and downtime.
Automated defect detection in submersible pump impellers using image classification Somasundaram, Deepa; Pramila, V.; Ezhilarasi, G.; Lakshmi, D.; Kavitha, P.; Kalaivani, R.
Indonesian Journal of Electrical Engineering and Computer Science Vol 40, No 2: November 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v40.i2.pp1158-1166

Abstract

Casting is a crucial manufacturing process used to produce complex metal parts, but it is often plagued by defects such as cracks, porosity, shrinkage, and cold shuts, which can compromise quality and lead to financial losses. Traditional visual inspection methods for detecting these defects are slow and prone to human error, making them inefficient for large-scale production. This project proposes automating the defect detection process using advanced AI-powered non-destructive testing (NDT) techniques. Specifically, convolutional neural networks (CNNs), a deep learning model, are employed for real-time visual inspection of castings. CNNs, trained on high-resolution images, can accurately identify surface defects such as cracks, scratches, and dimensional irregularities, significantly improving inspection speed and accuracy. The performance metrics of the system include defect detection accuracy, false positive and false negative rates, processing time, and scalability for high-volume production environments. By minimizing human intervention, this automated system reduces error rates, enhances product quality, and lowers production costs. Furthermore, the real-time capabilities of CNNs allow for rapid feedback, preventing defective parts from advancing through the production line. Overall, the integration of AI-based vision systems boosts efficiency, sustainability, and profitability in manufacturing, ensuring castings meet customer specifications with minimal errors.