An intelligent wind turbine with yaw mechanism using machine learning to reduce high-cost sensors quantity

Sep 17, 2026

Uploaded by Ezra

An intelligent wind turbine design uses a machine learning model to reduce reliance on high-cost sensors while improving wind-direction prediction for better energy capture. The proposed system combines a squirrel cage induction generator with six rotor blades and a yaw mechanism actuated by two stepper motors. Random forest regression is trained on sensor data and deployed on a Raspberry Pi to store inputs and generate wind-degree estimates. Results indicate the model can potentially replace selected expensive sensors, lowering overall cost for similar weather conditions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Article Info

Abstract

Introduction

Background Study

An intelligent wind turbine with yaw mechanism using machine learning to reduce high-cost sensors quantity Subrotho Bhandari Abhi1, Plabon Kumar Saha2, A. Z. M. Tahmidul Kabir1, Al Mamun Mizan1, Mohammad Minhazur Rahman1, Afrina Talukder Mimi2, Md. Mainul Ahsan3, Arpita Hoque1, Humyra Nusrat1 1Department of Electrical and Electronic Engineering, American International University-Bangladesh, Dhaka, Bangladesh 2Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, Bangladesh 3Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh | Article history:
Received Jul 9, 2022 Revised Feb 18, 2023 Accepted Feb 21, 2023 | In this paper, with the assistance of some tools and a machine learning model, a smart wind turbine was formed that eliminates some expensive sensors and reduces sensor complexity. Squirrel cage induction generator (SCIG) and six rotor blades make up the proposed design, and depending on the wind's direction, the turbine itself can rotate the rotor hub to produce energy more effectively. Additionally, two stepper motors are coupled to the yaw mechanism with the aid of the rotor hub, and the entire controlling procedure will depend on the direction of the wind. The rotor hub must continuously revolve in the same direction as the wind to maximize wind energy utilization. Additionally, to correctly predict wind degrees, a machine learning model was deployed. Random forest regression was used to train and predict the wind direction. The model is deployed in Raspberry Pi, where the incoming sensor values are being stored. Using the generated data, machine learning model was trained and it can be concluded that the model can potentially replace some of the expensive sensors to reduce cost. The model can be used for similar weather conditions only based on machine learning model and fewer sensors.
This is an open access article under the CC BY-SA license.
| | --- | --- | | Keywords:
Machine learning Raspberry Pi Wind direction
Wind turbine Yaw mechanism | | Corresponding Author: A. Z. M. Tahmidul Kabir Department of Electrical and Electronic Engineering, American International University-Bangladesh Dhaka-1229, Bangladesh Email: [tahmidulkabir@gmail.com](tahmidulkabir@gmail.com) Article Info ABSTRACT 1. INTRODUCTION A power generator generates electricity by converting mechanical energy to electrical energy. This technology produces power using renewable resources. The power generation capacity of a wind turbine is determined by several elements, such as the size of the power generator and the shape of the turbine blades [1] . Typically, wind turbines start producing electricity at wind speeds of approximately 4 m/s, achieve their maximum rated power output at around 13 m/s, and cease power generation at 25 m/s [1]. Due to the variability of the wind resource, the wind turbine operates at dynamic power levels that frequently fluctuate. Due to this fluctuation, the rotary engine at smart wind energy facilities operates at about one-third of its maximum practicable capacity on average over a year. The quantity of electricity generated by a turbine depends on two factors: wind speed and turbine availability. The power output provided by the wind is proportional to the cube of its speed, which means that if the wind speed doubles, its energy output can increase eightfold. Turbine availableness can be the aptitude to control once the wind is processing. But alternative factors like environmental issues and grid association necessities typically take precedence over the optimum wind capture layout [1], [2] . Although the system is very neatly designed, there are various sensors involved. Sensors are prone to error, meaning they generate null values, or even the sensors themselves can sometimes get damaged. So, using machine learning, the wind speed can be outputted with accuracy. After get

FAQs

How does the proposed wind turbine improve energy generation?

It uses a yaw mechanism that rotates the rotor hub toward the wind direction, supported by stepper motors, enabling more effective wind energy utilization.

Which machine learning method is used for wind direction prediction?

Random forest regression is used to train and predict wind direction from collected sensor values.

How does the system reduce the need for expensive sensors?

The machine learning model is trained using sensor data and then the approach uses feature selection to identify and reduce the set of sensors needed to predict wind direction without lowering performance.

Sep 17, 2026

Uploaded by Ezra