Implementation of Energy-efficient Axial Fans for Air Handling Unit Using AI Model

Year : 2024 | Volume : 11 | Issue : 03 | Page : 28 34
    By

    Dhanush M,

  • Shivashankar Hiremath,

  • Subramanya R. Prabhu B,

  1. Student, Department of Mechatronics, Manipal Institute of Technology, Manipal Academy Higher Education (MAHE), Manipal, Karnataka, India
  2. Professor, Department of Mechatronics, Manipal Institute of Technology, Manipal Academy Higher Education (MAHE), Manipal, Karnataka,
  3. Professor, Department of Mechatronics, Manipal Institute of Technology, Manipal Academy Higher Education (MAHE), Manipal, Karnataka, India

Abstract

This research explores the integration of energy-efficient axial fans in Air Handling Units (AHUs) within a large automotive manufacturing facility to enhance HVAC (heating, ventilation, and air conditioning) performance and reduce energy consumption. Standard AHUs in the facility’s clean rooms and other spaces utilize traditional blower fans, which primarily rely on static pressure, limiting their efficiency. By replacing these with electronically commutated (EC) axial flow fans, which leverage both static and dynamic pressures, the system’s overall efficiency is improved significantly. The new axial fans achieve over 85% efficiency, resulting in reduced energy consumption by 20-50%, lower operating costs, and a decrease in carbon emissions. Additionally, a CFM heat load calculation is employed to match fan ratings to clean room requirements, emphasizing precise temperature and humidity controls essential for quality manufacturing. A machine learning-based classification algorithm, with a focus on the decision tree model, is integrated to optimize airflow regulation by interfacing with edge gateway systems. This approach allows for accurate control of Variable Frequency Drives (VFD) in the AHUs, resulting in energy savings and system responsiveness. In addressing the specific cooling demands of the facility’s clean rooms, this study demonstrates that implementing EC fans and advanced control algorithms can significantly enhance HVAC efficiency, support sustainable energy practices, and contribute to climate change mitigation. These findings underscore the potential for optimized AHU design and control to transform energy-intensive industrial environments.

Keywords: Energy efficiency, classification algorithm, Building management system, Heat ventilation and air conditioning system, electronically commutated fans.

[This article belongs to Journal of Refrigeration, Air conditioning, Heating and ventilation ]

How to cite this article:
Dhanush M, Shivashankar Hiremath, Subramanya R. Prabhu B. Implementation of Energy-efficient Axial Fans for Air Handling Unit Using AI Model. Journal of Refrigeration, Air conditioning, Heating and ventilation. 2024; 11(03):28-34.
How to cite this URL:
Dhanush M, Shivashankar Hiremath, Subramanya R. Prabhu B. Implementation of Energy-efficient Axial Fans for Air Handling Unit Using AI Model. Journal of Refrigeration, Air conditioning, Heating and ventilation. 2024; 11(03):28-34. Available from: https://journals.stmjournals.com/jorachv/article=2024/view=191665


References

  1. Dhanush M, Shivashankar H, Subramanya R Prabhu B. Implementation of energy-efficient axial fans for air handling units using AI model. Manipal Institute of Technology, Manipal Academy of Higher Education; 2024.
  2. ASHRAE Handbook: HVAC Systems and Equipment. American Society of Heating, Refrigerating and Air-Conditioning Engineers; 2023.
  3. The Engineering Mindset. Humidifier used in air handling units [Internet]. Available from: https://theengineeringmindset.com
  4. Molinaroli L, Ivanov I, Rizzi F. Energy-saving and sustainable HVAC systems: A review of design and operational considerations. Renew Sustain Energy Rev. 2021;139:110696.
  5. Koury RN, Machado L, Ismail KAR. Numerical simulation of a variable speed refrigeration system. Appl Therm Eng. 2001;21(3):259–277.
  6. Balaras CA, Gaglia AG, Georgopoulou E, Mirasgedis S, Sarafidis Y, Lalas DP. European residential buildings and empirical assessment of the Hellenic building stock, energy consumption, emissions and potential energy savings. Build Environ. 2007;42(3):1298–1314.
  7. Pout C, MacKenzie F, Bettle R. Carbon dioxide emissions and energy performance of buildings. Build Res Inf. 2002;30(1):21–28.
  8. Patil A, Kumar P, Agrawal S, Joshi M. Machine learning for energy efficiency in HVAC systems: A review of current applications, challenges, and future prospects. Energy Build. 2023;287:113073.
  9. Dhingra R, Kumar B, Rana A, Singh K. Implementation of AI algorithms in energy management systems for HVAC optimization. Int J Comput Appl. 2020;175(30):20–28.
  10. Cui Y, Zhu J, Luck R, Mago PJ. Optimization of building energy efficiency using machine learning and dynamic HVAC control. Autom Constr. 2022;142:104263.
  11. Lee JH, Suh SC, Kim DH, Kim H, Koo J. Intelligent HVAC control with predictive modeling in an IoT-based smart building environment. Sensors (Basel). 2016;16(6):1012.
  12. Wang L, Srinivasan RS. A review of artificial intelligence-based building energy use prediction: Contrasting the capabilities of AI methods for sustainable building operation. Renew Sustain Energy Rev. 2017;82(3):1399–1413.
Regular Issue Subscription Original Research
Volume 11
Issue 03
Received 26/10/2024
Accepted 30/10/2024
Published 31/12/2024
182

Login


My IP

PlumX Metrics