摘要:針對低速旋轉(zhuǎn)的滑翔增程制導(dǎo)炮彈存在的俯仰和偏航通道控制耦合性問題,本文闡述了利用基于PID神經(jīng)網(wǎng)絡(luò)進(jìn)行雙通道解耦控制設(shè)計。為此,首先描述了滑翔增程炮彈動力學(xué)模型,基于對該模型的分析基礎(chǔ)上提出了PID神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)和計算方法,并采用增加動量項的權(quán)值修正和自適應(yīng)可變學(xué)習(xí)率對其進(jìn)行改進(jìn)。在此基礎(chǔ)上,通過粒子群優(yōu)化算法對網(wǎng)絡(luò)的初始權(quán)值進(jìn)行優(yōu)化。通過matlab仿真并對其結(jié)果進(jìn)行分析可以得到,該設(shè)計方法較好地滿足了系統(tǒng)的解耦控制要求,且能迅速接近控制目標(biāo),同時可以很好地克服彈體處于不同馬赫時氣動參數(shù)變化對控制系統(tǒng)造成的影響,能實現(xiàn)較為理想的控制效果。
關(guān)鍵詞:PID神經(jīng)網(wǎng)絡(luò),解耦控制,粒子群優(yōu)化,動量項,自適應(yīng)學(xué)習(xí)速率
Design of Decoupling Control System for Glide Extended Range Guided Munition Based on PID Neural Network
Abstract: For the existing control coupling between pitch and yaw channels in low-speed rotation of the glide extended range guided munition, this paper describes the dual-channel decoupling control design using PID neural network. To this end, the paper first describes the dynamic model of glide extended range guided munition, based on the analysis of the model a structure and calculation method of PID neural network,is proposed , and it is improved by modified weight which uses increasing momentum term and adaptive variable learning rate. On this basis, through particle swarm optimization algorithm the initial weights of the network is optimized. By simulation through Matlab and analysis of the results ,it can be obtained that the method designed satisfies the requirements of decoupling control system, and can rapidly approaching the control target, at the same time it can well overcome the impact of the control system caused by the changes of missile aerodynamic parameters in different Maches,so a better control results can be achieved through this design.
Keywords: PID neural network, decoupling control, particle swarm optimization, momentum, adaptive learning rate
1 引言(Introduction)
滑翔增程制導(dǎo)炮彈是一種增程效率高,實現(xiàn)遠(yuǎn)程精確打擊的一種新型制導(dǎo)彈藥。它的前部有舵翼,彈尾部有尾翼。該炮彈以一定的初速發(fā)射,出炮口后尾翼張開保持穩(wěn)定飛行, 出炮口幾秒后彈上的小型火箭助推發(fā)動機(jī)工作, 給彈丸以推力幫助彈丸(爬高) 增程,發(fā)動機(jī)工作結(jié)束后炮彈像普通尾翼彈一樣繼續(xù)在升弧段上飛行,彈載彈道參數(shù)探測系統(tǒng)開始工作,在彈道升弧段某位置上舵翼張開,開始滑翔和制導(dǎo)控制, 不斷調(diào)整炮彈的位置和姿態(tài),向前滑翔至給定目標(biāo)。該彈采用方案制導(dǎo)方式,通過設(shè)計合適的尾翼斜切角, 使得彈體在滑翔控制段保持一定的低速轉(zhuǎn)速。采用兩對電動舵機(jī)并基于旋轉(zhuǎn)實現(xiàn)俯仰和偏航雙通道控制原理達(dá)到相應(yīng)的控制要求。然而由于彈體始終保持一定的轉(zhuǎn)速在旋轉(zhuǎn),這必然造成俯仰和偏航兩通道產(chǎn)生耦合問題;同時彈體飛行過程中氣動參數(shù)主要隨速度的變化而變化,使得模型也隨之發(fā)生變化,因此,采用經(jīng)典控制理論可能將無法達(dá)到滿意的控制效果。本文基于對滑翔增程彈飛行過程中的多變量耦合行問題進(jìn)行分析,采用了一種簡單有效且易于實現(xiàn)的PID神經(jīng)網(wǎng)絡(luò)對彈體的飛行過程進(jìn)行控制。
注:本文中所涉及到的圖表、注解、公式等內(nèi)容請以PDF格式閱讀原文