Dual-Channel and Bidirectional Neural Network for Hypersonic Glide Vehicle Trajectory Prediction

Abstract

Different from traditional aircraft, hypersonic glide vehicles (HGVs) possess stronger maneuverability and a higher flight speed (generally higher than 5 Mach), making trajectory prediction very complicated. Several works have been conducted in this field, which usually analyze the motion characteristics of the HGV first and then use a Kalman filter to track and predict the trajectory. In this way, the accuracy of prediction depends on how to model the control parameters of the target vehicle. The core idea of this paper mainly concerns treating the HGV trajectory prediction as a multivariate time series forecasting problem since HGV trajectories are special multivariate time series with nonperiodic temporal patterns. Moreover, capturing the hidden dependencies between time steps and different time series ensures the accuracy and robustness of predictions. Recently, recurrent neural networks have been widely used in predicting data with temporal patterns between several time steps; however, they fail in capturing nonperiodic temporal patterns. Therefore, we propose a brand-new model named the dual-channel and bidirectional neural network (DCBNN) to intelligently predict the trajectory of hypersonic vehicles in undetectable areas, especially for those with complex maneuver models. DCBNN is constructed with a nonlinear component and a linear component to collect both nonlinear and linear features from input data to improve robustness. Moreover, a dual-branch architecture is utilized in the nonlinear component to capture the complex and mixed dependencies between long-term and short-term patterns. Experiments reveal that the proposed method is effective and intelligent.

Detecting and tracking hypersonic glide vehicles: A cybersecurity-engineering analysis of academic literature

“…• Trajectory prediction is divided into two parts: linear and nonlinear. For example, Xie et al (2021) applied a recurrent neural network with bidirectional gated recurrent units to the nonlinear part, and a single-layer perceptron to the linear part. applied the seq2seq architecture to the nonlinear part and also a single-layer perceptron to the linear part.…”

An Intelligent Trajectory Prediction Algorithm for Hypersonic Glide Targets Based on Maneuver Mode Identification

“…where S mili S mlli represent the position of the i − th predicted start point and last point in a batch, S oili S olli represent the position of the i − th observed start point and last point in a batch, and N represents the number of batches in Equation ( 31); ξ mi is the i − th modified maneuver parameter sequence in a batch, and ξ fi is the i − th filtering maneuver parameter sequence in a batch in Equation ( 32); ξ pi is the i − th modified maneuver parameter sequence in a batch, and ξ di is the i − th generated maneuver parameter sequence in a batch in Equation (33). l cls , p cls , respectively, represent the one-hot value of label classification and prediction classification in Equation (34).…”

“…Yang et al [32] modified the trajectory prediction error based on the generalized regression neural network (GRNN), by which the accurately predicted trajectory could be obtained. Li et al [33] combined the neural network and Kalman filter, based on the filtering result obtained the predicted trajectory. Cai et al [34] established trajectory data sets of different maneuver modes for hypersonic targets and realized the classification and prediction of hypersonic glide target trajectory by using LSTM.…”

An adaptive multivariate Student's t‐process recursive method for hypersonic glide vehicle trajectory prediction

“…Neural network prediction [17,18] and regression analysis theory [19,20] are two typical types of data-based prediction methods. To solve the trajectory prediction problem of HGV under complex manoeuvring patterns, reference [21] proposed a method to capture the hybrid dependence between short-term and long-term manoeuvring patterns using a dual-channel bidirectional neural network to intelligently predict the trajectory of HGV in undetectable regions. In the reference [22], a model for predicting target acceleration information using regression integrated sliding average was proposed to solve the trajectory prediction problem for variable manoeuvre HGV targets.…”