Hybrid adaptive network-based fuzzy inference system Model for Biodiesel Production in Renewable System

¹ Department of Automobile Engineering, Dr. Mahalingam College of Engineering and Technology, Pollachi, Tamilnadu.
² Department of Mechanical Engineering, Sri Ramakrishna Engineering College, Coimbatore, Tamilnadu
³ Department of Mechanical Engineering, CVR College of Engineering, Hyderabad, Telangana.
⁴ Department of Mechatronics Engineering, Sona College of Technology, Salem, Tamilnadu
⁵ Department of Mechanical Engineering, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, Telangana
⁶ Department of Chemistry, Annamacharya University, Rajampeta - 516 126, Andhra Pradesh, India. Email: othuru.akbar@gmail.com

^* Corresponding Author: ram1289@grietcollege.com

Abstract

Biodiesel is used which positively impact the environment or reducing the dependence on fossil fuels while providing a viable alternative. This paper presents the use of machine learning approach, namely adaptive neuro-fuzzy inference system (ANFIS) to optimize and model the biodiesel production from combination of soya oil and waste cooking oil. The effect of the process parameters catalyst value (5-7 wt. %), Methnol/soya +waste cooking oil ratio (10-20) , and react time (20–40 min) were studied. after optimizing the reaction parameters, bio diesel production (BDP) of 95.8 % was achieved while maintaining catalyst value (CA ) of 7wt%, Methnol/soya +waste cooking oil ratio (SW )of 20:1, and a react time (RT) of 20min. ANFIS models were implemented to improve and optimize these reaction parameters for the purpose of obtaining the maximum biodiesel output. Consequently, remarkably higher yields of 97.9% is achieved by ANFIS model by these parameters of CA of 7wt%,, SW of 10:1 , RT of 30min.