Aiming at the limitation that traditional methods for combat intention recognition of aerial targets are difficult to effectively capture the essential characteristics of intelligence information, we design a novel deep learning method, Panoramic Convolutional Long Short-Term Memory networks (PCLSTM), to improve the recognition ability. First, based on the characteristics of aerial target intelligence information, a panoramic convolutional layer is designed to extract the loosely coupled characteristics of intelligence information, and a time series pooling layer is designed to reduce the scale of neural network parameters on a large scale. Then, the temporal feature extraction capability of the LSTM layer and the depth feature mining capability of the traditional deep learning layer are combined to construct the PCLSTM neural network. Subsequently, the recognition performance of PCLSTM is analyzed by simulation experiments compared with standard deep net, convolutional neural network and LSTM network as benchmark models. Finally, PCLSTM was used to carry out simulation tests on different truncated data sets of original intelligence information, to analyze the optimal length of truncated data for different combat intention recognition. And then a reasonable aerial target combat intention recognition method is designed. The simulation results show that the method presented in this paper has theoretical significance and reference value for command decision-making. INDEX TERMS Aerial targets, combat intension recognition, deep learning, panoramic convolutional long short-term memory neural network.
To achieve efficient and accurate remaining life prediction and effectively express the uncertainty of prediction results, this paper proposes a remaining life prediction method based on fuzzy evaluation-Gaussian process regression (FE-GPR). First, the prediction of the remaining useful life (RUL) is affected by unknown variables, such as the environment, and it is difficult to achieve accurate predictions. It is necessary to effectively express the uncertainty of such prediction results. In this paper, we have put forward a RUL prediction method based on GPR, which can realize the RUL prediction with a confidence interval. Second, combined with the characteristics of the GPR method, an observation data preprocessing method based on fuzzy evaluation is proposed. The initial fuzzy evaluation method is established based on expert knowledge. Then, the classification nodes are optimized by the gravitational search algorithm (GSA) and historical data. This method, which uses fuzzy logic combined with expert knowledge, can avoid over-fitting in the case of limited data, and effectively improves the prediction accuracy of the GPR model. Finally, we use NASA PCoE. lithium battery data for a case study. The results show that the FE-GPR method achieves a more accurate RUL prediction and effectively reflects the uncertainty of the prediction results.
Proportional-Integral-Derivative (PID) controller is one of the most widely used controllers for its property of simplicity and practicability. In order to design high-quality performances PID controllers, an Advanced Fireworks (AFW) algorithm based on self-adaption principle and bimodal Gaussian function is proposed, which is built to optimize the PID controller by parameters tuning. Firstly, a compound index of optimization performance is formulated, and then the extremal optimization method of PID control system is proposed. Secondly, a PID parameters tuning model combined with AFW is built. At last, 5 typical transfer functions are simulated to obtain optimal parameters by AFW and contrast tuning method, such as Ziegler-Nichols method, Enhanced Fireworks (EFW) algorithm, and Particle Swarm Optimization (PSO). Simulation results show that AFW are effective and are easily implemented methods to solve PID control problems of different transfer functions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.