Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65599
Volume:
10 |
6 |
Jun 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Engineering
NBNSTIC
Computer Engineering
NBNSTIC
Computer Engineering
NBNSTIC
Computer Engineering
NBNSTIC
Computer Engineering
NBNSTIC
Wind turbines play a vital role in renewable energy generation, but unexpected equipment failures can lead to increased maintenance costs, reduced power output, and unplanned downtime. Traditional maintenance approaches are often reactive or based on fixed schedules, making them inefficient for modern wind farms. This paper presents Wind Sight AI 2.0, an AI-powered real-time monitoring and predictive maintenance system developed using React.js, Flask, MongoDB, and Scikit-learn. The proposed system collects and processes turbine parameters such as temperature, vibration, wind speed, rotor speed (RPM), and power output to predict turbine health using supervised machine learning. The trained model is deployed with Job lib and exposed through Flask REST APIs, enabling real-time predictions that are visualized on an interactive React dashboard. MongoDB is used to store sensor readings, prediction results, and maintenance records for historical analysis. The dashboard provides live monitoring, health status visualization, performance analytics, and maintenance alerts, supporting engineers in making timely maintenance decisions. Experimental evaluation demonstrates that the proposed system achieves reliable prediction performance with low response latency while improving operational efficiency and reducing the likelihood of unexpected turbine failures. The modular architecture is scalable and can be extended to integrate IoT sensors, cloud platforms, and advanced deep learning models for large-scale wind farm deployments.
KEYWORDS
This paper presented WindSight AI 2.0, a full-stack predictive maintenance system for real-time wind turbine monitoring using React.js, Flask, MongoDB, and Scikit-learn. The proposed system analyzes turbine sensor data to predict equipment health and generate maintenance alerts through an interactive dashboard. The integration of machine learning with REST APIs enables accurate and efficient real-time fault prediction. The developed solution improves maintenance planning, reduces operational downtime, and enhances the reliability of wind energy systems. The modular architecture also supports future integration with IoT devices, cloud platforms, and advanced AI models, making it suitable for large-scale renewable energy applications.
[1] P. Sasinthiran, R. Kumar, and S. Balakrishnan, "AI-Based Wind Turbine Health Monitoring: A Review," Renewable Energy, vol. 225, pp. 1201–1218, 2024. [2] M. Valdivia-Bautista, J. Pérez, and L. Hernández, "Artificial Intelligence in Wind Speed Forecasting: A Comprehensive Review," Energies, vol. 16, no. 5, pp. 1–22, 2023. [3] H. Zhu, Y. Wang, and Z. Li, "Predictive Maintenance for Wind Turbines: A Physics-Driven Artificial Intelligence Approach," Engineering Applications of Artificial Intelligence, vol. 132, 2025. [4] S. Chatterjee and N. Dethlefs, "XAI4Wind: Explainable Artificial Intelligence for Wind Turbine Operation and Maintenance," arXiv preprint, arXiv:2009.11234, 2020. [5] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd ed., O'Reilly Media, 2023. [6] M. Grinberg, Flask Web Development: Developing Web Applications with Python, 2nd ed., O'Reilly Media, 2018. [7] MongoDB Inc., "MongoDB Documentation," https://www.mongodb.com/docs/ [8] React Documentation, "React – A JavaScript Library for Building User Interfaces," https://react.dev/ [9] Scikit-learn Developers, "Scikit-learn: Machine Learning in Python," https://scikit-learn.org/ [10] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
Publication Date
6/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...