Cfd is also used to get the data of performance parameters of the nozzle at different nozzle pressure ratio , different nozzle area ratio and different geometric defected angle . the theory of function approximation is used to establish the transient model of thrust vectoring with the data calculated 本文通過cfd計(jì)算獲得矢量噴管的性能參數(shù),如流量系數(shù)、推力系數(shù)以及有效推力矢量角等與矢量噴管壓比、面積比以及幾何偏轉(zhuǎn)角之間的關(guān)系數(shù)據(jù),并利用函數(shù)逼近理論建立了矢量噴管的動(dòng)態(tài)數(shù)學(xué)模型。
The kanerva ' s sparse distributed memory ( sdm ) tackles the problem of training large data patterns and extendes the storage mode of existing computer . but it ' s address array produced randomly ca n ' t reveal the distribution of patterns and it has ' t the ability of function approximation for its learning rule Kanerva的稀疏分布存儲(chǔ)( sdm )模型解決了大維數(shù)樣本的訓(xùn)練問題,推廣了現(xiàn)有計(jì)算機(jī)的存儲(chǔ)方式。但其地址矩陣的隨機(jī)預(yù)置方式不能反映樣本的分布,并且sdm的學(xué)習(xí)方式使之不能用于函數(shù)逼近及時(shí)間序列預(yù)測(cè)問題。
The need for function approximations arises in many branches of applied mathematics, and computer science in particular. In general, a function approximation problem asks us to select a function among a well-defined class that closely matches ("approximates") a target function in a task-specific way.