Compressors are important components in various power systems in the field of energy and power. In practical applications, compressors often operate under non-design conditions. Therefore, accurate calculation on performance under various operating conditions is of great significance for the development and application of certain power systems equipped with compressors. To calculate and predict the performance of a compressor under all operating conditions through limited data, the interpolation method was combined with a support vector machine (SVM). Based on the known data points of compressor design conditions, the interpolation method was adopted to obtain training samples of the SVM. In the calculation process, preliminary screening was conducted on the kernel functions of the SVM. Two interpolation methods, including linear interpolation and cubic spline interpolation, were used to obtain sample data. In the subsequent training process of the SVM, the genetic algorithm (GA) was used to optimize its parameters. After training, the available data were compared with the predicted data of the SVM. The results show that the SVM uses the Gaussian kernel function to achieve the highest prediction accuracy. The prediction accuracy of the SVM trained with the data obtained from linear interpolation was higher than that of cubic spline interpolation. Compared with the back propagation neural network optimized by the genetic algorithm (GA-BPNN), the genetic algorithm optimization of extreme learning machine neural network (GA-ELMNN), and the genetic algorithm optimization of generalized regression neural network (GA-GRNN), the support vector machine optimized by the genetic algorithm (GA-SVM) has a better generalization, and GA-SVM is more accurate in predicting boundary data than the GA-BPNN. In addition, reducing the number of original data points still enables the GA-SVM to maintain a high level of predictive accuracy.

The application of direct injection (DI) technology can effectively improve the atomization effect of heavy fuel to reduce the fuel loss of heavy fuel engines (HFE). The fuel spray characteristics directly affect the combustion performance of the engine. To investigate the atomization process and evaporation characteristics of heavy fuel in-cylinder for an air-assisted direct injection (AADI) engine, a simulation calculation model of AADI HFE was established with the use of a computational fluid dynamics tool. The air-assisted injector model and the one-dimensional performance calculation model were verified by test data. The influences of injection timing and injection pressure on the spray characteristics and mixture formation in the engine cylinder were discussed. The results show that the mixture concentration distribution is uniform after the injection timing is advanced, and the mass fraction of the fuel evaporation increases. The earlier injection timing can provide the fuel with sufficient time to evaporate, while the later injection timing will result in increasing the Sauter mean diameter (SMD) of the fuel droplets, and the unevaporated heavy fuel in the combustion chamber tends to become concentrated. With the increase in air injection pressure, the distribution of the mixed gas in the cylinder becomes uniform, and the SMD of the fuel droplets in the cylinder decreases. When the injection pressure is 0.65 MPa and 0.75 MPa, the difference between the SMD of the fuel droplets in-cylinder decreases, and a favorable fuel atomization effect can be maintained.

As a miniaturized direct injection (DI) solution, the pump injector is of great significance for small aviation piston engines, such as two-stroke heavy-fuel engines. The accurate control of the timing and amount of injections is an important application prerequisite. In this paper, the flow characteristics of a pump injector with different driving circuits and parameters are investigated. The effects of the power supply and freewheeling circuits on the opening and closing delays are theoretically studied. A schematic of a self-designed logic control circuit is proposed, and it achieves peak and hold current control without software intervention. Simulations and experiments are carried out, and the drive current and flow characteristics in different states are measured. The results show that when driving a solenoid with a high internal resistance of 2.70 Ω, a single power supply is more suitable, and the variable-freewheeling circuit exhibits excellent performance in terms of control accuracy and energy recovery. Notably, the invariable-freewheeling circuit results in nonlinear flow characteristics, and the nonlinear segment corresponds to the drive current transitioning from the peak value to the hold value. In contrast, the variable-freewheeling circuit overcomes this problem. To comprehensively consider solenoid opening and closing delays, energy consumption and the linearity of the flow characteristics during injection, a peak current of 10 A and a hold current of 8 A are adopted.