This project investigates novel methodologies for modelling, simulation and control of gas turbines using artificial neural networks. Simulated and operational data sets are employed to demonstrate the capability of Artificial Neural Network (ANN) in capturing complex nonlinear dynamics of gas turbines. Both static (multi-layer perceptron, MLP) and dynamic (nonlinear autoregressive with exogenous inputs, NARX) networks are explored in ANN-based modelling. Simulink and NARX models are set up to explore both steady-state and transient behaviours. The results demonstrate that both Simulink and NARX models successfully capture dynamics of the system, but MARX models gas turbine behaviour with higher accuracy compared to Simulink. Furthermore a neural network based controller consisting of ANN-based model predictive control (MPC) and feedback linearization NARMA-L2 has been developed. It proves to perform better than conventional PID controllers. The resulted models can be used off line for design and manufacturing purposes; or on line and on site for condition monitoring, fault detection and trouble shooting of gas turbines.