Data from: A prediction model of compressor with variable geometry diffuser based on elliptic equation and Partial Least Squares

In order to fulfill more and more extensive intake air flow range of diesel engine, variable geometry compressor (VGC) is introduced into turbocharged diesel engine. However, due to the variable diffuser vanes angle (DVA), the prediction for the performance of VGC becomes more difficult than normal compressor. In the present study, a prediction model comprised of elliptical equation and PLS (Partial Least Squares) model was proposed to predict the performance of VGC. The speed lines of pressure ratio map and efficiency map with elliptical equation were fitted, and the coefficients of elliptical equation was introduced into PLS model to build the polynomial relationship between the coefficients and relative speed, DVA. And further, the maximal order of polynomical was detailed investigated to reduce the number of sub-coefficients and acceptable fit accuracy simultaneously. The prediction model was validated with sample data and in order to present the superiority in compressor performance prediction, the prediction results of this model were compared with those of look-up table and BPNN. The validation and comparison results show that the prediction accuracy of the new developed model is acceptable, and this model is much more suitable than look-up table and BPNN under the same condition in the VGA performance prediction. Moreover, the new developed prediction model provides a novel and effective prediction solution for VGC and can be used to improve the accuracy of the thermodynamic model for turbocharged diesel engines in the future.

为满足柴油机日益宽泛的进气流量需求，可变几何截面压气机（variable geometry compressor, VGC）被应用于涡轮增压柴油机中。然而由于可变扩压器叶片角（variable diffuser vanes angle, DVA）的存在，可变几何截面压气机的性能预测难度相较于常规压气机显著提升。本研究提出了一种结合椭圆方程与偏最小二乘（Partial Least Squares, PLS）模型的可变几何截面压气机性能预测方案：首先通过椭圆方程拟合压比特性图与效率特性图的转速线，并将椭圆方程的系数引入偏最小二乘模型，以建立系数与相对转速、可变扩压器叶片角之间的多项式关联关系；随后，本研究对多项式的最高阶数开展了精细化研究，在保证拟合精度符合要求的前提下，减少了子系数的数量。本研究通过样本数据对所提预测模型进行了验证，并为凸显其在压气机性能预测中的优势，将该模型的预测结果与查表法（look-up table）以及反向传播神经网络（Back Propagation Neural Network, BPNN）的预测结果进行了对比。验证与对比结果表明，所提出的新型模型预测精度可接受，且在相同工况下用于可变几何截面压气机性能预测时，其性能优于查表法与反向传播神经网络。此外，该新型预测模型为可变几何截面压气机性能预测提供了一种新颖且有效的解决方案，未来可用于提升涡轮增压柴油机热力学模型的预测精度。