A hybrid ANN-Fuzzy approach for optimization of engine operating parameters of a CI engine fueled with diesel-palm biodiesel-ethanol blend Suman Dey, Narath Moni Reang, Arindam Majumder, Madhujit Deb * , Pankaj Kumar Das Mechanical Engineering Department, NIT Agartala, Tripura, 799046, India article info Article history: Received 5 September 2019 Received in revised form 6 April 2020 Accepted 5 May 2020 Available online 8 May 2020 Keywords: Diesel-palm biodiesel-ethanol Performance-emissions ANN prediction Fuzzy system optimization abstract This paper investigates use of artificial neural network (ANN) model in prediction of brake specific en- ergy consumption (BSEC), nitrogen oxides (NO x ), unburnt hydrocarbon (UHC), and carbon dioxide (CO 2 ) emissions of a single cylinder diesel engine operates with diesel-palm biodiesel-ethanol blends. The engine is run at different load form 20e100% and 1500 rpm constant speed. The fuel used in this present study are diesel and six different diesel-palm biodiesel-ethanol blends. The Levenberg-Marquardt back propagation training algorithm with logistic-sigmoid activation function results best prediction of per- formance and emission characteristics with accurate overall correlation coefficient (R) (0.99329 e0.99875) and minimum mean square error (MSE) (0.000179082e0.000465809). The mean absolute percentage errors (MAPE) are observed to be in range of 2.32e4.54% with the acceptable margin of mean square relative error (MSRE). Furthermore, experimental and ANN predicted data are compared in fuzzy interface system (FIS) to find optimum engine operating parameters. Compared to other blends, at 20% load, D85BD10E5 blend exhibits the highest MPCI (multi performance characteristics index) values of 0.718 and 0.705 for experimental and ANN predicted data respectively. Robustness and reliability of the proposed techniques clearly explain the application of ANN and fuzzy logic system in the prediction and optimization of engine parameters. © 2020 Elsevier Ltd. All rights reserved. 1. Introduction Diesel engine, a source of mechanical power tremendously dominating since many decades by imparting its valuable and useful effect in different sectors like agriculture, industries, and automobiles etc. The well-known fact of rapid depletion of the petroleum reservoir makes alternative fuel a fastest growing fuel substitute in the present scenario [1]. Threatening human health related issues like, contamination of air, acid rain, increase in greenhouse gas, and lopsided heat balance of the earth due to diesel combustion makes alternative fuel a promising future energy fuel for the industries or transportation sectors. In view to this above conflicts, it is very much essential to reduce the emissions by curbing petroleum fuel consumption. Thus, the use of environ- mental friendly, non-toxic, biodegradable alternative fuel effec- tively reduce greenhouse gas emissions and petroleum consumption [2]. In this quest, a fractional replacement of diesel with the alcohol or biodiesel in CI engine could be a successful blend with similar properties like base diesel [3]. However the technique of mixing alcohol into diesel is always complex and challenging task that requires dedicated solution. The major laxness in such diesel-alcohol blend is there poor stability. Ac- cording to Shahir et al. [4] stability could be improved by knowing chemical composition of diesel, actual working temperature, ethanol concentration and the quality of ethanol (hydrous or anhydrous). Lei et al. [5] experimentally developed a diesel-ethanol emulsion using CLZ emulsifier. CLZ, a novel mixture of biofuels, castor oil and other single emulsifier can keep physical stability of diesel-ethanol blend up to ethanol substitution of 25% by volume. The major challenges in diesel-biodiesel-ethanol blends related to their mixing strength, miscibility and stability has been investi- gated by Pradelle et al. [6]. Temperature is one of the important deciding factor for the miscibility where they observed that with increasing temperature miscibility of ethanol (hydrous) in diesel- biodiesel-ethanol mixture increased. From the results it is also indicated that methyl esters are better than ethyl ester biodiesel in * Corresponding author. E-mail address: madhujit_deb@rediffmail.com (M. Deb). Contents lists available at ScienceDirect Energy journal homepage: www.elsevier.com/locate/energy https://doi.org/10.1016/j.energy.2020.117813 0360-5442/© 2020 Elsevier Ltd. All rights reserved. Energy 202 (2020) 117813