---

Reorganizations of cyclic variations, depending on fuel type, equivalence ratio, engine load and speed, and engine geometry, are the major purposes and may cause fluctuations of output power and unburned hydro-carbon. During this study, the effects of gasoline and natural gas (NG) as fuel on cyclic variations were investigated utilizing the recorded cylinder pressure of a research SI engine over more than 400 successive cycles. This work was performed at full load, 1800rpm and compression ratio of 8 with 0.94 equivalence ratio using gasoline-air and NG-air mixtures. ُStatistical analysis of the obtained results showed that at the above conditions the coefficient of variations (COV) of indicated mean effective pressure (imep), peak pressure (Pmax) and the crank angle position of the peak pressure for gasoline-air mixture were 2.4, 1.29 and 1.04 times of those for NG-air mixture, respectively; at the optimum ignition timing, imep of gasoline-air mixture is increasing with rising Pmax and decreasing with enhancing , however, imep of NG-air mixture seems to be independent to Pmax and .

---

Fuel metering system and controlling fuel-air mixture of spark ignition engines have been the major goals for the researcher. Management in mixture quality and fuel economy have resulted in changing carburetor systems to injection systems. Start of fuel injection position and injection duration play important role in engine performance. In the current work a single cylinder research engine with capability of adjusting spark timing and controlling gasoline injection start position and duration was utilized. Compression ratio, engine speed and injection start position were adjusted to 8, 1800 rpm and breathing top dead center (BTDC), respectively. Injection duration and spark timing were controlled so that to achieve maximum output torque at equivalence ratio of 0.90. Fixing them, the start of injection was only changed in the range of -180 to 180°CA relative to BTDC with a 30°CA increment. For each case, cylinder pressure of 500 successive cycles were recorded and stored. The obtained results showed that the dispersion of indicated mean effective pressure (imep) data of the cases with injection position start after BTDC were higher than those of the cases with injection position start before BTDC. Also, the average values of imep and peak pressure and their coefficient of variation changed with varying fuel injection start position; and for the cases of high dispersion in imep data, the average values of imep and isfc appeared to be high and low respectively.

---

The prerequisite in the majority of control processes is modeling. The model used to design a controller must be both accurate and real-time. Utilizing prevalent approaches of modeling, namely modeling based on (numerically) solving the equations governing the fluid in the combustion chamber, is too time-consuming and not suitable for a control purpose. This paper is to model combustion in an SI engine by means of neural networks and present an accurate and fast-response model for combustion. Obviously, any training procedure of neural networks does involve empirical data acquisition. On the other hand, engine testing is highly expensive, and testing data tables available (in industry) are not sufficient to train neural networks. In this paper, first with the aid of a CFD software, a one-dimensional model of an engine is constructed, and then calibrated using factual experimental data at hand. Afterwards, acquiring data required is performed via the validated CFD model. As a matter of fact, because of not having access to necessary experimental coefficients, calibration is an extremely complicated and time-consuming process. It will be attempted to accomplish and spell out the calibration of the engine model in the GT-Power software, in a scientific practice. After a brief survey on the methods employed in designing the neural networks, modeling of the combustion chamber will be stated. Eventually, the response of the constructed NN model will be compared to the results gained from the GT-Power software, and the great accuracy of the NN model will be indicated.