Time domain Neal-Smith ( TDNS ) criterion is originated from frequency domain Neal-Smith ( FDNS ) criterion and step target tracking criterion which has been widely used in the research on prediction of longitudinal PIO. In the closed loop system of this criterion, quasi-linear pilot model is extensively used because it has simple structure and can reflect the basic characteristics of pilot’s behavior. But in reality, the driver behavior is usually highly nonlinear, in order to describe the nonlinear characteristics more accurately, this paper uses neural network method to establish the pilot model. Taking a plane as an example, flight test data is used to train and test the neural network, and then creates a model of neural network. Based on time domain Neal-Smith ( TDNS ) criterion, the simulation model is established. Through computer simulation, the prediction results of the PIO trends are obtained. Research shows that compared with the traditional pilot model, neural network model can match with the real driver better. Therefore, putting neural network model into TDNS assessment criterion has actual significance.