UCAV situation assessment method based on C-LSHADE-means and SAE-LVQ

The unmanned combat aerial vehicle (UCAV) is a research hot issue in the world, and situation assessment an important part of it. To overcome shortcomings existing methods, such as low accuracy strong dependence on prior knowledge, data-driven method proposed. clustering classification are combined, former used to mine situational latter realize rapid assessment. Angle evaluation factor distance proposed transform multi-dimensional air information into two-dimensional features. A convolution success-history based adaptive differential evolution with linear population size reduction-means (C-LSHADE-Means) algorithm convolutional pooling layer compress data preserve distribution characteristics. LSHADE initialize center mean clustering, which overcomes defect initialization sensitivity. Comparing experiment seven algorithms done UCI set, through four indexes, it proves that this paper has better performance. model stacked autoencoder learning vector quantization (SAE-LVQ) network constructed, uses SAE reconstruct features, self-competition LVQ achieve efficient classification. Compared five kinds assessments models, SAE-LVQ highest accuracy. Finally, three confrontation processes from maneuvering instrumentation (ACMI) selected, for results line actual situation.