基于目前对飞行品质的评价没有一套完整、准确的自动评价系统,本文提出了基于支持向量机的飞行品质评价方法,用支持向量机模型来构建一套自动评价系统。模型把飞行员的生理信号数据和飞行数据结合起来,以心率、呼吸频率、下降率、偏航角、速度变化率、着陆速度、襟翼度数作为模型的输入,飞行品质作为输出,对飞行员飞行品质做出了评价。本文通过该模型和传统神经网络模型作比较,结果表明:对于飞行员飞行品质评价问题,支持向量机方法较传统神经网络方法精度更高,实际应用中也更易于实现;并且它也很好的弥补了专家打分主观性强的不足。可用作评价飞行品质的模型。 Based on the current evaluation of flight quality, there is not a complete and accurate automatic evaluation system. This paper presents a flight quality evaluation method based on support vector machine, and builds an automatic evaluation system by using support vector machine model. The model combines the pilot’s physiological signal data with the flight data and takes the input of heart rate, respiration rate, descent rate, yaw rate, rate of change of speed, landing speed and flap degree as the input and the flight quality as the output, Made a comment. This paper compares the model with the traditional neural network model. The results show that the support vector machine method is more accurate than the traditional neural network for pilot flight quality evaluation, and is also easier to implement in practical applications; and it is also a good remedy Experts lack the subjectivity of the deficiencies. Can be used as a model to evaluate flight quality.