Application of Fuzzy Regression Analysis in Predicting the Performance of the Anaerobic Reactor Co-digesting Spent Tea W
- PDF / 2,702,180 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 120 Views
ORIGINAL PAPER
Application of Fuzzy Regression Analysis in Predicting the Performance of the Anaerobic Reactor Co‑digesting Spent Tea Waste with Cow Manure Naseem Khayum1 · Amruta Rout2 · B. B. V. L. Deepak2 · S. Anbarasu1 · S. Murugan1 Received: 25 April 2019 / Accepted: 29 October 2019 © Springer Nature B.V. 2019
Abstract Modelling and optimization of production of different renewable energy sources are receiving great interest by researchers; as they are used to provide gross information on the possibilities of harnessing energy from variety of resources. Spent tea waste (STW) is one of the potential organic wastes remarkably available in India. In this research work, possibility of producing biogas by co-digesting STW with cow manure (CM) was predicted through a novel fuzzy regression approach. Triangular membership functions with five levels were considered for the fuzzy subsets and a Mamdani-type of fuzzy approach was used to implement a total of 125 rules in the IF–THEN format. The digestion time, carbon to nitrogen (C/N) ratio and pH were considered as input parameters, while the biogas yield was considered as an output. Experimental data obtained from the lab scale reactors were used to predict the biogas yield using fuzzy logic methodology. The obtained results were validated with the experimental results by carrying out a regression analysis. The results indicated that a good agreement found between experimental and predicted data with a coefficient of determination R2 = 0.994. Graphic Abstract
Keywords Spent tea waste · Cow manure · Fuzzy logic · Biogas · Mamdani approach · Regression analysis * Naseem Khayum [email protected] 1
Department of Mechanical Engineering, National Institute of Technology Rourkela, Rourkela, India
Department of Industrial Design, National Institute of Technology Rourkela, Rourkela, India
2
Abbreviations Ai Actual values AARE Absolute average relative error ANFIS Adaptive neuro-fuzzy inference system ANN Artificial neural network AR Anaerobic reactor
13
Vol.:(0123456789)
ARE Average relative error CM Cow manure C/N Carbon to nitrogen ratio FA Firely algorithm FIS Fuzzy inference system GA Genetic algorithm kg Kilogram ml Millilitre MSE Mean squared normalised error NH3 Ammonia Pi Predicted values RF Random forest RMSE Root mean squared error RPM Revolutions per minute RSM Response surface methodology SD Standard deviation STW Spent tea waste TS Total solid
Statement of Novelty This research work predicts the potential of deriving biogas from spent tea waste; which is a municipal solid organic waste, significantly available in refreshment stalls, hostels, hotels and almost all the houses release this waste. A novel fuzzy regression technique was used for predicting the biogas production. As per authors knowledge, this article is the first of its kind, which proposes a novel fuzzy regression technique for predicting the biogas production using spent tea waste. A good agreement has been found with a correlation coefficient of
Data Loading...
