本文關(guān)鍵詞： 航空發(fā)動(dòng)機(jī) 動(dòng)態(tài)模型 非線性系統(tǒng)辨識(shí) NARX網(wǎng)絡(luò)　出處：《計(jì)算機(jī)工程與應(yīng)用》2017年12期 　論文類型：期刊論文

【摘要】：針對(duì)航空發(fā)動(dòng)機(jī)參數(shù)非線性動(dòng)態(tài)特性,提出一種基于外部輸入非線性自回歸(NARX)神經(jīng)網(wǎng)絡(luò)的發(fā)動(dòng)機(jī)參數(shù)動(dòng)態(tài)辨識(shí)模型。主要思路是根據(jù)NARX網(wǎng)絡(luò)的非線性時(shí)序預(yù)測(cè)特性,結(jié)合發(fā)動(dòng)機(jī)參數(shù)的穩(wěn)態(tài)和動(dòng)態(tài)參數(shù),提出一種基于偏穩(wěn)態(tài)差值預(yù)測(cè)的NARX參數(shù)動(dòng)態(tài)模型結(jié)構(gòu)。設(shè)計(jì)了SP-P辨識(shí)結(jié)構(gòu),整定了模型內(nèi)部結(jié)構(gòu)參數(shù)并建立N1(低壓轉(zhuǎn)子轉(zhuǎn)速)、N2(高壓轉(zhuǎn)子轉(zhuǎn)速)、EGT(渦輪后排氣溫度)參數(shù)非線性差分預(yù)測(cè)模型。最后依據(jù)某發(fā)動(dòng)機(jī)試車樣本,對(duì)推桿加減速時(shí)N1、N2、EGT動(dòng)態(tài)辨模型進(jìn)行仿真。仿真結(jié)果表明,N2相對(duì)誤差小于0.2%,N1相對(duì)誤差小于0.3%,EGT相對(duì)誤差小于1℃,滿足發(fā)動(dòng)機(jī)試車仿真需要。最后,將所建模型應(yīng)用于某A320機(jī)務(wù)維修訓(xùn)練器的發(fā)動(dòng)機(jī)仿真系統(tǒng)。
[Abstract]:Aiming at the nonlinear dynamic characteristics of aero-engine parameters. A dynamic identification model of engine parameters based on external input nonlinear autoregressive neural network is proposed. The main idea is based on the nonlinear prediction characteristics of NARX neural network. Combining the steady and dynamic parameters of engine parameters, a dynamic model structure of NARX parameters based on partial steady-state difference prediction is proposed, and the SP-P identification structure is designed. The internal structural parameters of the model were set up and the N1 (low pressure rotor speed) was established. EGT (turbine exhaust temperature) parameter nonlinear differential prediction model. Finally, according to a test sample of an engine, the dynamic identification model of N _ (1) N _ (2) EGT during acceleration and deceleration of push rod is simulated. The simulation results show that. The relative error of N2 is less than 0.2 and N1 is less than 0.3 and EGT relative error is less than 1 鈩，

本文編號(hào)：1491061