基于GA-BP模型的国产民机落地剩油预测研究

Research on Prediction of Domestic Civil Aircraft Landing Residual Fuel Based on GA-BP Model

针对全球碳排放量和航油价格的增加,需提升国产民机的竞争力。研究提出基于GA-BP神经网络的ARJ21飞机落地剩油预测,先进行相关性分析,筛选出与落地剩油关联较大的6个参数,再分别采用BP神经网络模型和GA-BP神经网络模型对落地剩余油量进行预测,对比两个模型的预测结果和准确度,进行误差分析。结果表明,GA-BP神经网络模型比BP神经网络模型的预测精度提高了2.7%,且GA-BP神经网络模型预测精度均在97%以上,预测效果更优。研究可为航空公司油量监控和国产民机节油策略等方面的研究提供算法支持。

Aiming at the increased carbon emissions and jet fuel prices in global,it is necessary to enhance the competitiveness of domestic civil aircraft.The study proposes a prediction of ARJ21 aircraft landing residual fuel based on GA-BP neural network.Firstly,correlation analysis was conducted to screen out 6 parameters that are significantly related to landing residual fuel.Then,BP neural network model and GA-BP neural network model were used to predict the landing residual fuel,and the prediction results and accuracy of the two models were compared for error analysis.The results show that the prediction accuracy of the GA-BP neural network model is 2.7%higher than the BP neural network model;The prediction accuracy of the GA-BP neural network model is above 97%,and the prediction effect of the GA-BP neural network model is better.The research can provide the algorithm support for fuel monitoring of airlines and the research of domestic civil aircraft fuel saving strategy.