The researches on Wankel engines are very rare and considered new in modellingand prediction. Therefore this study deals with the artificial neural network(ANN) modelling of a Wankel engine to predict the power, volumetric efficiencyand emissions, including nitrogen oxide, carbon dioxide, carbon monoxide andoxygen by using the change of mean effective pressure, intake manifold pressure,start of ignition angle and injection duration as inputs. The experiment results aretaken from a research which is performed on a single-rotor, four stroke and portfuel injection 13B Wankel engine. The number of data which are taken fromexperimental results are scarce and varied in six different data set (for example;mean effective pressure, from 1 to 6 bar) at 3000 rpm engine speed. The standardback-propagation (BPNN) Levenberg-Marquardt neural network algorithm isapplied to evaluate the performance of middle speed range Wankel engine. Themodel performance is validated by comparing the prediction data sets with themeasured experimental data. Results approved that the artificial neural network(ANN) model provided good agreement with the experimental data with goodaccuracy while the correlation coefficient R varies between 0.79 and 0.97.