On Guidance Parameter Calculation of Flight Vehicle Using Relevance Vector Machine and Particle Swarm Optimization
| Autor: | Yun Tan, Yao Zhao, Ying Zou, Hai-tao Tian |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science Particle swarm optimization Regression analysis 02 engineering and technology Relevance vector machine Statistics::Machine Learning symbols.namesake 020901 industrial engineering & automation Function approximation Control theory 0202 electrical engineering electronic engineering information engineering Gaussian function symbols 020201 artificial intelligence & image processing Algorithm Interpolation |
| Zdroj: | 2020 39th Chinese Control Conference (CCC). |
| DOI: | 10.23919/ccc50068.2020.9188772 |
| Popis: | To deal with the problem that guidance parameter calculation of flight vehicle requires a lot of computer memory space to store interpolation data tables, a novel guidance parameter calculation method based on relevance vector machine (RVM) and particle swarm optimization (PSO) is presented. By utilizing non-linear mapping property of RVM, parameter regression model for calculating guidance parameter is constructed. The model is trained based on the samples which are generated from the interpolation data tables of flight control trajectories. During training, the Gaussian kernel parameter of RVM is automatically selected by the use of PSO. Simulations on non-linear function approximation and flight vehicle data show that PSO-RVM model achieves high regression accuracy and the structure of model is much sparser. The guidance parameter can be calculated by storing less parameter in the controller of flight vehicle, and the presented method has some engineering application value. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|