Optimization of diesel engine dual-variable geometry turbocharger regulated two-stage turbocharging system based on radial basis function neural network-quantum genetic algorithm

Abstract

ABSTRACT Aiming at the problem of power and economy reduction in high-altitude operation of diesel engines, a radial basis function neural network-quantum genetic algorithm (RBFNN-QGA) optimization method is proposed to optimize diesel engine dual-variable geometry turbocharger (VGT) regulated two-stage turbocharging (RTST) system. Firstly, the GT-power simulation model of dual-VGT RTST diesel engine was established, and then calibrated with test data. The latin hypercube sampling (LHS) algorithm was selected for the experimental design, and the back propagation neural network (BPNN), RBFNN, and extreme learning machine (ELM) were used to establish three diesel engine high-altitude performance prediction models based on the sample data, to compare the ability of the three neural networks in predicting the performance of diesel engines. Finally, RBFNN is coupled with QGA to establish the optimization model of dual-VGT RTST system at different altitudes with torque, fuel consumption rate as the optimization target, and vortex front row temperature and in-cylinder combustion pressure as the constraints. The study results show that three kinds of neural networks have achieved satisfactory prediction results, BPNN and RBFNN are better than ELM in prediction accuracy, and ELM training is faster than BPNN and RBFNN; QGA converges faster and has higher optimization efficiency than GA, and the maximum torque of the optimized dual-VGT diesel engine is restored to more than 85% of the plain level, compared with the single-turbocharged diesel engine and the single-VGT two-stage turbocharged diesel engine, the low-speed torque of the dual-VGT RTST diesel engine is increased by 384% and 100%. This optimization model has better optimization effect and efficiency.