RESUMO
Enhancing combustion efficiency and optimizing the thrust-to-weight ratio are critical technical challenges encountered in the development, application, and growth of micro turbojet engines. The high-centrifugal (high-g) combustion chamber, as an innovative combustion chamber system, has the capability to replace the primary combustion chamber of the traditional turbojet engine, reducing the length of the combustion chamber while maintaining engine performance. Previous studies on the structure of the high-g combustor (HGC) have shown problems such as uneven temperature distribution of the turbojet rotor. To improve the feasibility of HGC integration into micro turbojet engines, this study conducts relevant experiments on a 120 N thrust engine. Subsequently, the results of these experiments were used to analyze the structural design of HGC through a simulation approach. Including six main configurations, the first four structural designs focused on establishing a suitable highly centrifugal environment to stabilize and improve the combustion performance, which was successfully achieved by designing the outer ring gear-shaped inlet with four different angles. Subsequent structural designs were based around improving the uniformity of the temperature distribution at the combustion chamber outlet. The final design of the HGC combustion efficiency is not much different from the original combustion chamber, and it can shorten the axial length of the combustion chamber by nearly 30%. The design of the air inlet holes and the baffle plate effectively improves the temperature uniformity at the outlet of the combustion chamber. Moreover, without changing the combustion chamber material, the corresponding engine weight can be reduced by about 10.7%, and the engine thrust-to-weight ratio can be improved by up to 12% with the same thrust, which provides design ideas for further lightweight applications.
RESUMO
With the development of computer application technologies, intelligent algorithm has been widely used in various fields. In this study, a coupled Gaussian process regression and feedback neural network (GPR-FNN) algorithm is proposed, and it is used to predict the performance and emission characteristics of a six-cylinder heavy-duty diesel/natural gas (NG) dual-fuel engine. Using the engine speed, torque, NG substitution rate, diesel injection pressure, and injection timing as inputs, an GPR-FNN model is established to predict the crank angle corresponding to 50% heat release, brake-specific fuel consumption, brake thermal efficiency, and carbon monoxide, carbon dioxide, total unburned hydrocarbon, nitrogen oxides, and soot emissions. Subsequently, its performance is evaluated using experimental results. The results show that the regression correlation coefficients of all output parameters are greater than 0.99, and the mean absolute percentage error is less than 5.9%. In addition, a contour plot is used to compare the experimental results with the GPR-FNN prediction data in detail, and the results show that the prediction model has high accuracy. The results of this study can provide new ideas for the research on diesel/natural gas dual-fuel engines.