Due to the increase in demand of energy, there is a steep rise in petroleum product, which led to the depletion of conventional energy. This gave rise to the need of biodiesel as an alternate for diesel fuel. This paper deals with the study of biodiesel blend's performance and different emission behaviour using the Taguchi and fuzzy logic method. Experimental investigations on a single cylinder constant speed direct injection diesel engine were carried out under two parameters: blend proportion and percentage load for six and five levels, respectively. As per this method, an L30 orthogonal array was used to collect data for 30 trials, which were experimented at different engine load and blend proportion. The optimisations are done on brake thermal efficiency, carbon monoxide (CO), carbon dioxide (CO2), hydrocarbon (HC), oxides of nitrogen (NOx), smoke, exhaust gas temperature, ignition delay, combustion delay and maximum rate of pressure rise. The signal-to-noise ratio was used for data analysis and the result is verified by the Fuzzy control system model with multi input multi output (MIMO) to predict the performance of engine. The developed model produced idealised results with the correlation coefficients of 0.897–0.998 and root mean square error and found to be useful for predicting the engine performance characteristics with limited number of available data. © 2015 Informa UK Limited, trading as Taylor & Francis Group.