Most modern diesel engines are equipped with common fuel rail system. The common fuel rail pressure and start of injection are two important fuel path control variables which are needed to be carefully calibrated over all engine operation range. They both have big effects on engine emissions, fuel consumptions and combustion noise performance. Though there are mature techniques such as design of experiment, model based calibration together with optimization method for engine calibration task, the engine test points are still many and the calibration costs are still high. Besides, the outputs of the calibration are look up tables or maps which are used in engine open loop control strategy in engine control system. Open loop control system has no adaptive and disturbance rejection ability. So the initially optimally calibrated look up control tables will gradually become less and less optimal when the engine is aging. Furthermore, if the fuel property or the fuel injection system performance changes, those calibrated look up tables may not fit and may need to be recalibrated.A reliable and simple combustion process parameters based two-input-two-output feedback control structure was proposed in this paper to replace the lookup table based start of injection and fuel rail pressure control system. The controlled combustion parameters are combustion phasing and a variable consists of combined information of ignition delay and combustion width. The control strategy is a decentralized control which also can be named as two single loop control system. The references for these two combustion parameters were calculated from two linear algebra equations involved with only two engine variables: speed and load. The constants in the reference algorithm were obtained by a solution to a neural network engine model based optimization problem subjected to a specific engine transient test type. The results of engine speed and torque transient test show that this combustion parameters feedback based start of injection and fuel rail pressure online adjustment system works not only smoothly but reliably and makes engine has improved fuel consumption and exhaust gas emissions performance compared to lookup table control system. By applying this control strategy, enormous calibration work could be reduced and combustion process is closed loop controlled.