基于神经网络的罗茨增压器性能预测研究

Performance Prediction of Roots Supercharger Based on BP Artificial Neural Network

运用人工神经网络原理建立了罗茨增压器性能预测的BP神经网络模型,并利用该模型对罗茨增压器不同压比条件下的温升、转速与流量的特性关系进行了预测分析,取得了良好的预测效果。网络预测和实测结果的对比表明,BP神经网络的预测误差较小,适用于此类流体机械的性能预测。

The BP neural network model of Roots Supercharger is established based on ANN theory. It is used to analyse the relationshiops between temperature rise, rotational speed and flow rate under different pressure ratios, and satisfied prediction results are obtained. The contrast of network prediction and experimental results shows that the BP neural network prediction has relatively small error, is suitable for the performance prediction on this kind of fluid machine.