We analyze a time series of the combustion pressure in the idle state, measured from a spark ignition engine of a motorcycle. It is clarified that the engine system can be described by a lowdimensional deterministic dynamics perturbed by some stochastic process.We also propose a method to stabilize the chaotic behaviour of engine’s data by adopting the Pyragas’ method. We actually use this method in a computer experiment for the control of combustion pressure data to demonstrate the efficiency of the proposed method. As a result of the experiment, we eliminate the fluctuations in the combustion pressure data and obtain a periodic orbit.