Abstract: Classical PID speed control method provides no guarantees for closed-loop system stability or performances for the full operating range of a piston engine. Complex engine control strategy, including generalized predictive control (GPC) and forward-feed compensation control rule, is proposed for an unmanned helicopter engine speed regulation based on controlled auto-regressive integrated moving-average (CARIMA). According to several typical conditions in practice, off-line simulations are carried out and compared with PID. The simulations and tethered test show that the proposed controller can meet the performance requirements for the unmanned helicopter engine use, namely tracking performance, disturbance rejection and robustness.