A first attempt is made to use recently developed, non-conventional Artificial Neural Network (ANN) models with Multilayer Perceptron (MLP), Radial Basis Function (RBF) and Adaptive Neuro-Fuzzy Interference System (ANFIS) architectures to predict the fuel flow rate of a commercial aircraft using real data obtained from Flight Data Records (FDRs) of the cruise, climb and descent phases. The training of the architectures with a single hidden layer is performed by utilising the Delta-Bar-Delta (DBD), Conjugate Gradient (CG) and Quickprop (QP) algorithms. The optimum network topologies are sought by varying the number of processing elements in the hidden layer of the networks using a trial-and-error method. An evaluation of the approximate fuel intake values against the ideal fuel intake data from the FDRs indicates a good fit for all three ANN models. Thus, more accurate fuel intake estimations can be obtained by applying the RBF-ANN model during the climb and descent flight stages, whereas the MLP-ANN model is more effective for the cruise phase. The best accuracy obtained in terms of the linear correlation coefficient is 0.99988, 0.91946 and 0.95252 for the climb, cruise and descent phase, respectively.
Exergy efficiency can be used as an objective function in order to improve systems efficiency. Thus, the most efficient regions for the operation parameters can be searched easily. Exergy efficiency data of a turboprop engine’s components that have been calculated using basic engine parameters in the previous studies are modeled using cubic spline curve fitting methodology. Spline curves are on the two dimensional plane, where x axis is the input parameter and y axis is the exergy efficiency of the component. A spline curve is defined by the points subject to arbitrary selection of number and position. Initially positions of the points are located with two different methods and then in order to obtain better accuracy point positions are improved by ‘Ant colony’ and ‘Goldsection’ optimisation methods. Sum of Squares of the errors between the fitted value and data value was used as the fitness function. Least square error of 5 × 10−9is assumed as acceptable accuracy which yields to a minimum R = 0.9998 linear correlation coefficient. In the optimisation step, independent engine variable versus calculated engine performance parameters were checked against spline fitted values. Improvement of the fitness function is observed as the number of fitting points is increased. Ant colony optimisation in engine exergy efficiency parametric modeling is a new approach in authors’ point of view.