Tadros, M., Ventura, M., Guedes Soares, C. and Lampreia, S. (2020), “Predicting the performance of a sequentially turbocharged marine diesel engine using ANFIS”, Sustainable Development and Innovations in Marine Technologies, Georgiev, P. & Guedes Soares C. (Eds.), Taylor and Francis Group, London, pp. 300-305

A large number of parameters must be optimized to simulate the performance of a sequentially turbocharged marine diesel engine. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is applied to predict the performance of the mentioned engine. This method is able to solve nonlinear problems without developing any explicit mathematical model or conducting optimization procedures. Experimental test results are collected from the manufacturer and are divided randomly into training and testing data. Gaussian curve membership function and 100 training iterations are used for the training process. The model maps the relationship between the two inputs; engine speed and brake power; and the brake specific fuel consumption as an output. The results show that ANFIS is able to predict the performance of the four-stroke diesel engine operated at different engine speeds with a high level of accuracy. This model can be used to investigate the effect of different parameters on engine performance in future research.

If you did not manage to obtain a copy of this paper: Request a copy of this article

For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications