Optimization of diesel substitution rate based on piston maximum temperature pattern recognition in dual-fuel engine:

摘要: The diesel and natural gas dual-fuel engine has gained increasing interest in recent years because of its excellent power economy. However, the substitution rate cannot be controlled optimally, owing to lack a feedback indicator reflecting cylinder combustion process, which easily leads serious thermal load problem. This paper presents closed-loop control with from piston maximum temperature (PMT) pattern regulate real time. A v-support vector machine (v-SVM) is proposed train classifiers for online recognition PMT pattern. Nitrogen oxide (NOx) emission levels, excess air coefficient, speed inlet pressure are chosen as feature variables. PMTs, calculated by finite element analysis ANSYS, utilized determine labels data. Moreover, 10-fold cross-validation employed choose optimal kernel function, parameters penalty factor. synthetic minority oversampling techniqu...