This paper is concerned with the design and implementation of an adaptive predictive controller for oxides of nitrogen (NOx) emissions from gas turbine combustors. Predictive control techniques with both fixed and adaptive parameters are introduced. An online parameter estimation algorithm is used to model the nonlinear characteristics of the combustor NOx process. The predictive control strategies are implemented using the MATLAB/dSPACE, controller development environment. Their performance is evaluated on an atmospheric test rig fitted with a commercial combustor and also compared with a PID controller.