本文關(guān)鍵詞： 二叉樹SVM 隨機(jī)森林 飛行狀態(tài)識(shí)別 線性相關(guān)性 小樣本　出處：《南昌航空大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：直升機(jī)飛行在不同狀態(tài)時(shí),有壽件和動(dòng)部件的損傷程度不同。因此,正確識(shí)別飛行狀態(tài)對(duì)直升機(jī)關(guān)鍵部件的壽命預(yù)測(cè)及故障診斷,具有重要的意義。在實(shí)際中,用于直升機(jī)飛行狀態(tài)訓(xùn)練的樣本一般為小樣本,而傳統(tǒng)神經(jīng)網(wǎng)絡(luò)方法,在訓(xùn)練樣本較少時(shí),識(shí)別率欠佳。針對(duì)這個(gè)問題,本文采用二叉樹SVM和隨機(jī)森林方法,研究了直升機(jī)飛行狀態(tài)識(shí)別技術(shù),旨在提高識(shí)別率和識(shí)別速度,可為我國直升機(jī)健康和使用監(jiān)測(cè)系統(tǒng)(HUMS)研制提供核心的技術(shù)。本文主要研究工作和成果如下:(1)研究并實(shí)現(xiàn)直升機(jī)飛行狀態(tài)識(shí)別預(yù)處理。主要包括數(shù)據(jù)預(yù)處理、敏感參數(shù)提取和狀態(tài)預(yù)分類。數(shù)據(jù)預(yù)處理首先采用去野點(diǎn)、限幅及中值濾波對(duì)飛行數(shù)據(jù)進(jìn)行去噪;然后,利用最小二乘法,擬合得到飛行參數(shù)的變化率,作為新的飛行參數(shù);去噪實(shí)驗(yàn)驗(yàn)證了本文方法的有效性。敏感參數(shù)提取是根據(jù)直升機(jī)操縱特性和飛行參數(shù)線性相關(guān)性進(jìn)行的,并通過真實(shí)飛行參數(shù)數(shù)據(jù)進(jìn)行了驗(yàn)證。狀態(tài)預(yù)分類是利用選擇的敏感參數(shù),將35種某型直升機(jī)飛行狀態(tài)預(yù)分為10小類,通過真實(shí)飛行參數(shù)數(shù)據(jù)驗(yàn)證了預(yù)分類方法的有效性。(2)提出并實(shí)現(xiàn)基于二叉樹SVM的直升機(jī)飛行狀態(tài)識(shí)別。在狀態(tài)識(shí)別預(yù)處理的基礎(chǔ)上,首先,對(duì)每個(gè)小類進(jìn)行二叉樹SVM分類器的設(shè)計(jì);然后,利用粒子群算法和遺傳算法對(duì)二叉樹SVM進(jìn)行參數(shù)尋優(yōu),從而提高了識(shí)別率;最后,分別對(duì)每一個(gè)二叉樹SVM分類器進(jìn)行樣本訓(xùn)練,并將已訓(xùn)練好的網(wǎng)絡(luò)模型,用于直升機(jī)飛行狀態(tài)識(shí)別。以某型直升機(jī)真實(shí)飛行數(shù)據(jù)作為實(shí)驗(yàn)數(shù)據(jù),并將本方法與SVM方法和RBF神經(jīng)網(wǎng)絡(luò)方法進(jìn)行了對(duì)比實(shí)驗(yàn),結(jié)果表明,在小樣本訓(xùn)練情況下,二叉樹SVM對(duì)直升機(jī)飛行狀態(tài)識(shí)別率有明顯的提高。但是,該方法的識(shí)別速度不快,針對(duì)此問題,利用隨機(jī)森林具有小樣本情況下泛化能力較強(qiáng)和訓(xùn)練收斂速度快的特征,進(jìn)一步開展了飛行狀態(tài)識(shí)別方法研究。(3)提出并實(shí)現(xiàn)基于隨機(jī)森林的直升機(jī)飛行狀態(tài)識(shí)別。在狀態(tài)識(shí)別預(yù)處理的基礎(chǔ)上,首先,設(shè)計(jì)每個(gè)小類的隨機(jī)森林分類器;然后,利用分類回歸樹,構(gòu)建隨機(jī)森林,并對(duì)每一個(gè)隨機(jī)森林分類器進(jìn)行樣本訓(xùn)練;最后,將已訓(xùn)練好的網(wǎng)絡(luò)模型,用于識(shí)別直升機(jī)飛行狀態(tài)。以直升機(jī)真實(shí)飛行數(shù)據(jù)作為實(shí)驗(yàn)數(shù)據(jù),并將隨機(jī)森林方法與二叉樹SVM方法和RBF神經(jīng)網(wǎng)絡(luò)方法進(jìn)行對(duì)比實(shí)驗(yàn),結(jié)果表明,在小樣本訓(xùn)練情況下,隨機(jī)森林的識(shí)別速度明顯優(yōu)于二叉樹SVM和RBF神經(jīng)網(wǎng)絡(luò),同時(shí)該方法的識(shí)別率與二叉樹SVM方法相近,明顯高于RBF神經(jīng)網(wǎng)絡(luò)方法。
[Abstract]:When the helicopter is flying in different states, the damage degree of the parts with longevity and moving parts is different. Therefore, it is of great significance to correctly identify the flight state for the life prediction and fault diagnosis of the key parts of the helicopter. The samples used for helicopter flight state training are usually small samples, but the traditional neural network method has poor recognition rate when the training samples are small. In this paper, binary tree SVM and stochastic forest method are used to study the helicopter flight status recognition technology, which aims to improve the recognition rate and speed. It can provide the core technology for the development of Chinese helicopter health and use monitoring system (HUMS). The main work and results of this paper are as follows: 1). Research and implementation of helicopter flight status recognition preprocessing, including data preprocessing. First, the de-field point, amplitude limit and median filter are used for de-noising flight data. Then, by using the least square method, the change rate of flight parameters is obtained as a new flight parameter. The effectiveness of the proposed method is verified by denoising experiments. The sensitive parameters are extracted according to the linear correlation between helicopter control characteristics and flight parameters. It is verified by the real flight parameter data. The state pre-classification is to pre-classify 35 kinds of helicopter flight state into 10 subcategories by using the selected sensitive parameters. The validity of the pre-classification method is verified by the real flight parameter data. (2) the helicopter flight state recognition based on binary tree SVM is proposed and realized. First of all, based on the pre-processing of state recognition. A binary tree SVM classifier is designed for each subclass. Then, the particle swarm optimization algorithm and genetic algorithm are used to optimize the parameters of binary tree SVM, which improves the recognition rate. Finally, each binary tree SVM classifier is trained and the trained network model is used for helicopter flight status recognition. The actual flight data of a certain helicopter is used as experimental data. The method is compared with the SVM method and the RBF neural network method. The results show that in the case of small sample training. Binary tree SVM can improve the recognition rate of helicopter flight state obviously. However, the speed of this method is not fast. The random forest has the characteristics of strong generalization ability and fast training convergence rate in the case of small samples. Further research on the flight state recognition method is carried out. (3) the helicopter flight state recognition based on random forest is proposed and realized. First of all, on the basis of the pre-processing of state recognition. Design a random forest classifier for each subclass; Then, the random forest is constructed by using the classification and regression tree, and each random forest classifier is trained by sample. Finally, the trained network model is used to identify the flight state of the helicopter, and the real flight data of the helicopter is taken as the experimental data. Compared with the binary tree SVM method and the RBF neural network method, the random forest method is compared. The results show that in the case of small sample training. The recognition speed of random forest is obviously better than that of binary tree SVM and RBF neural network, and the recognition rate of this method is similar to that of binary tree SVM method, and is obviously higher than that of RBF neural network method.
【學(xué)位授予單位】：南昌航空大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：V275.1;V267;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李軍亮;胡國才;韓維;柳文林;;基于Elman網(wǎng)絡(luò)的某型直升機(jī)飛行狀態(tài)識(shí)別[J];火力與指揮控制;2015年12期

2 石瑞敏;楊兆建;;基于復(fù)雜網(wǎng)絡(luò)優(yōu)化的DAG-SVM在滾動(dòng)軸承故障診斷中的應(yīng)用[J];振動(dòng)與沖擊;2015年12期

3 趙燕偉;任設(shè)東;陳尉剛;樓炯炯;冷龍龍;;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的可拓分類器構(gòu)建[J];計(jì)算機(jī)集成制造系統(tǒng);2015年10期

4 肖先勇;崔燦;汪洋;劉陽;;電壓暫降分類特征可比性、相關(guān)性及馬氏距離分類法[J];中國電機(jī)工程學(xué)報(bào);2015年06期

5 Wu Wei;;Identification method for helicopter flight dynamics modeling with rotor degrees of freedom[J];Chinese Journal of Aeronautics;2014年06期

6 姚明煌;駱炎民;;改進(jìn)的隨機(jī)森林及其在遙感圖像中的應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2016年04期

7 趙海森;杜中蘭;劉曉芳;王慶;;基于遞推最小二乘法與模型參考自適應(yīng)法的鼠籠式異步電機(jī)轉(zhuǎn)子電阻在線辨識(shí)方法[J];中國電機(jī)工程學(xué)報(bào);2014年30期

8 姜高霞;王文劍;;時(shí)序數(shù)據(jù)曲線排齊的相關(guān)性分析方法[J];軟件學(xué)報(bào);2014年09期

9 張世輝;劉建新;孔令富;;基于深度圖像利用隨機(jī)森林實(shí)現(xiàn)遮擋檢測(cè)[J];光學(xué)學(xué)報(bào);2014年09期

10 劉敏;郎榮玲;曹永斌;;隨機(jī)森林中樹的數(shù)量[J];計(jì)算機(jī)工程與應(yīng)用;2015年05期

相關(guān)碩士學(xué)位論文 前1條

1 劉雨;基于SVM的直升機(jī)飛行狀態(tài)識(shí)別方法及其應(yīng)用研究[D];南昌航空大學(xué);2016年

，

本文編號(hào)：1443941