An improved aircraft landing distance prediction model based on particle swarm optimization — Extreme learning machine method
Silin Qian, Shenghan Zhou, Wenbing Chang, Fajie Wei · 2017
Aiming at the problem that aircraft landing runway overrun, this paper proposed a landing distance prediction model based on improved extreme learning machine (ELM) with flight data. Particle swarm optimization (PSO) was used to optimize the input layer weights and the hidden element bias of a single hidden layer feedforward network. And then the optimal input weights and the implicit bias were applied to the ELM prediction model. Firstly, flight data is preprocessed with data slicing method based on flight height, and determine model input variables. Secondly, select the appropriate activation function. Subsequently, establish the PSO-ELM model of landing distance prediction. In the end, compare with traditional BP neural network and ELM under different evaluation indexes. The results show that the prediction of landing distance conforms to the actual measured data. The maximum absolute error is 45 meters, and the maximum relative error is 6%.