This paper uses multi - layer feedforward artificial neural networks ( abbr . mlf nns ) to approximate the nonlinear dynamic inversion on the basis of analyzing principle and characteristics of nonlinear dynamic inversion and neural networks . the pseudo - linear system has been synthesized by classic pid control and self - adaptive control separately 將神經(jīng)網(wǎng)絡(luò)與非線性動(dòng)態(tài)逆相結(jié)合,利用神經(jīng)網(wǎng)絡(luò)對(duì)系統(tǒng)的逆模型進(jìn)行建模,對(duì)實(shí)現(xiàn)的偽線性系統(tǒng)分別設(shè)計(jì)pid控制和自適應(yīng)控制兩種方案進(jìn)行綜合。