基于ANFIS的进近阶段飞行员操纵模型设计
|
摘要
自适应神经模糊系统(ANFIS)中的模糊推理部分能有效地模拟飞行员在操纵时的感知、决策、执行过程,人工神经网络部分能对复杂的非线性系统进行自适应学习,因此利用ANFIS对飞行员的操纵行为进行建模是非常合适的。本文基于CESSNA 172模拟器设计了飞行员在环的人机实验,通过实验采集了进近阶段飞行员的操纵数据和飞机实时响应数据,将数据处理后作为ANFIS的输入输出训练得到飞行员在进近时的操纵模型,并对模型预测效果进行了验证。ANFIS训练得到的操纵模型既可以作为进一步研究飞行员操纵行为的工具,也可以作为评判飞行员进近时操纵表现的标准。
The fuzzy reasoning part of the ANFIS can effectively simulate the process of pilot's perception, decision-making and execution during operation, and the artificial neural network part can carry out adaptive learning for the complex nonlinear system. Therefore, it is very appropriate to use ANFIS to model pilot's control behavior. This paper designs the pilot's man-machine experiment in the loop based on CESSNA 172 simulator.Through the experiment, the pilot's control data and aircraft real-time response data are collected. The data are processed as input and output of ANFIS.Then, the pilot's control model is trained and the predictive effect of the model is verified. The control model trained by ANFIS can be used not only as a tool to further study pilot's control behavior, but also as a criterion to evaluate pilot's maneuvering performance when approaching.
The fuzzy reasoning part of the ANFIS can effectively simulate the process of pilot's perception, decision-making and execution during operation, and the artificial neural network part can carry out adaptive learning for the complex nonlinear system. Therefore, it is very appropriate to use ANFIS to model pilot's control behavior. This paper designs the pilot's man-machine experiment in the loop based on CESSNA 172 simulator.Through the experiment, the pilot's control data and aircraft real-time response data are collected. The data are processed as input and output of ANFIS.Then, the pilot's control model is trained and the predictive effect of the model is verified. The control model trained by ANFIS can be used not only as a tool to further study pilot's control behavior, but also as a criterion to evaluate pilot's maneuvering performance when approaching.
引文
[1]中国民用航空总局人为因素课题组.民用航空人的因素培训手册[M].北京:中国民航出版社,2003.
[2] Tustin, A., An Investigation of the Operator’s Response in Manual Control of a Power Driven Gun[C]. C. S. Memorandum Number 169, Metropolitan Vickers Electric Company, Ltd, Sheffield,England,1944.
[3] McRuer, D. T.,&Jex, H. R. A review of quasi-linear pilot models[J]. IEEE Transactions on Human Factors in Electronics,HFE, 1967,8(3):231-249.
[4] Hess, R. A. Structural model of the adaptive human pilot[J].Journal of Guidance, Control, and Dynamics,1979,3(5),416-423.
[5] Hosman, R. Pilot’s perception and control of aircraft motions[C]. Delft University Press,1996.
[6] Takagi, T. and Sugeno, M., Fuzzy Identification of Systems and Its Application to Modeling and Control[J]. IEEE Trans. On Systems, Man&Cybernetics,1985,(15):116-132.
[7] Sugeno, M., Industrial Applications of Fuzzy Control[J].Elsevier Science Pub. Co.,1985.
[8] Chiu, S., Fuzzy Model Identification Based on Cluster Estimation[J]. Journal of Intelligent&Fuzzy Systems, 1994,Vol. 2, No. 3.
[2] Tustin, A., An Investigation of the Operator’s Response in Manual Control of a Power Driven Gun[C]. C. S. Memorandum Number 169, Metropolitan Vickers Electric Company, Ltd, Sheffield,England,1944.
[3] McRuer, D. T.,&Jex, H. R. A review of quasi-linear pilot models[J]. IEEE Transactions on Human Factors in Electronics,HFE, 1967,8(3):231-249.
[4] Hess, R. A. Structural model of the adaptive human pilot[J].Journal of Guidance, Control, and Dynamics,1979,3(5),416-423.
[5] Hosman, R. Pilot’s perception and control of aircraft motions[C]. Delft University Press,1996.
[6] Takagi, T. and Sugeno, M., Fuzzy Identification of Systems and Its Application to Modeling and Control[J]. IEEE Trans. On Systems, Man&Cybernetics,1985,(15):116-132.
[7] Sugeno, M., Industrial Applications of Fuzzy Control[J].Elsevier Science Pub. Co.,1985.
[8] Chiu, S., Fuzzy Model Identification Based on Cluster Estimation[J]. Journal of Intelligent&Fuzzy Systems, 1994,Vol. 2, No. 3.