基于BP神經(jīng)網(wǎng)絡(luò)的衛(wèi)星激光測(cè)距望遠(yuǎn)鏡指向誤差的建模研究
發(fā)布時(shí)間：2018-07-29 17:24
【摘要】：隨著光、機(jī)、電技術(shù)的迅速發(fā)展，衛(wèi)星激光測(cè)距（SLR）技術(shù)已日漸成熟。在數(shù)據(jù)精度方面，無論國內(nèi)外的固定站，還是流動(dòng)站都已步入亞厘米級(jí)時(shí)代。近年來，隨著高重復(fù)率激光技術(shù)的廣泛應(yīng)用，國內(nèi)各SLR站在數(shù)據(jù)量和精度方面都進(jìn)入了新階段。但是，隨著國內(nèi)各SLR站在白天測(cè)距、盲目跟蹤、無人值守觀測(cè)和月球激光測(cè)距領(lǐng)域的探索和研究，，進(jìn)而對(duì)衛(wèi)星激光測(cè)距指向精度也提出更高的要求。 在衛(wèi)星激光測(cè)距觀測(cè)中，提高望遠(yuǎn)鏡的指向精度對(duì)提高跟蹤目標(biāo)的捕獲能力具有重要意義，尤其在盲目跟蹤或白天測(cè)距中，是保證觀測(cè)數(shù)據(jù)獲取的重要指標(biāo)之一。常用的指向誤差的建模方法有球諧函數(shù)模型、基本參數(shù)模型和轉(zhuǎn)臺(tái)模型。球諧函數(shù)模型表達(dá)式的各項(xiàng)沒有物理意義，模型不穩(wěn)定；基本參數(shù)模型的模型參數(shù)有實(shí)際的物理意義，模型比較穩(wěn)定；轉(zhuǎn)臺(tái)模型是對(duì)基本參數(shù)模型的擴(kuò)展，精度更高，但沒有基本參數(shù)模型穩(wěn)定。 針對(duì)衛(wèi)星激光測(cè)距望遠(yuǎn)鏡指向誤差問題，文本提出一種基于BP（Back Propagation）神經(jīng)網(wǎng)絡(luò)的建模方法。BP神經(jīng)網(wǎng)絡(luò)是一種按誤差逆?zhèn)鞑ニ惴ㄓ?xùn)練的多層前饋網(wǎng)絡(luò)，是目前應(yīng)用最廣泛的神經(jīng)網(wǎng)絡(luò)模型之一。將BP神經(jīng)網(wǎng)絡(luò)算法應(yīng)用到流動(dòng)衛(wèi)星激光測(cè)距儀的指向誤差建模中，不僅拓展了神經(jīng)網(wǎng)絡(luò)算法的應(yīng)用領(lǐng)域，同時(shí)對(duì)提高衛(wèi)星激光測(cè)距系統(tǒng)的跟蹤精度具有重要意義。 通過獲取武漢流動(dòng)衛(wèi)星激光測(cè)距站的三組實(shí)測(cè)恒星觀測(cè)數(shù)據(jù)，將其分為訓(xùn)練集和檢驗(yàn)集。利用訓(xùn)練集分別建立BP神經(jīng)網(wǎng)絡(luò)模型、轉(zhuǎn)臺(tái)模型、球諧函數(shù)模型和基本參數(shù)模型，再利用檢驗(yàn)集對(duì)建立的模型進(jìn)行測(cè)試，最后計(jì)算并對(duì)比四種模型輸出的中誤差。研究表明BP神經(jīng)網(wǎng)絡(luò)模型可以提高衛(wèi)星激光測(cè)距望遠(yuǎn)鏡的指向精度，且優(yōu)于另外三種模型。 另外，利用武漢流動(dòng)衛(wèi)星激光測(cè)距站的實(shí)測(cè)數(shù)據(jù)，并輔以長春SLR站和上海天文臺(tái)SLR站的5組觀測(cè)數(shù)據(jù)，進(jìn)一步研究了指向誤差的分布特性。首先采用遺傳算法將武漢流動(dòng)SLR站的觀測(cè)數(shù)據(jù)分為訓(xùn)練集和檢驗(yàn)集，利用轉(zhuǎn)臺(tái)模型建模。然后分析檢驗(yàn)集樣本殘差的分布特性和指向精度。實(shí)驗(yàn)結(jié)果表明，轉(zhuǎn)臺(tái)模型輸出的高度誤差和方位誤差的殘差不一定符合正態(tài)分布，并且可通過遺傳算法優(yōu)化模型，提高望遠(yuǎn)鏡的指向精度。 最后，考慮到指向誤差模型的實(shí)用性，并進(jìn)一步完善指向誤差模型，文章介紹了基于MATLAB開發(fā)環(huán)境，將各種模型建模方法的界面化過程。
[Abstract]:With the rapid development of light, machine and electric technology, the (SLR) technology of satellite laser ranging has matured day by day. In terms of data accuracy, both domestic and foreign fixed stations or mobile stations have stepped into the sub-centimeter era. In recent years, with the wide application of high repetition rate laser technology, all SLR stations in China have entered a new stage in terms of data volume and accuracy. However, with the exploration and research of SLR stations in the field of daytime ranging, blind tracking, unmanned observation and lunar laser ranging, the pointing accuracy of satellite laser ranging is also required. In satellite laser ranging observation, it is very important to improve the target acquisition ability by improving the pointing accuracy of the telescope. Especially in blind tracking or daytime ranging, it is one of the important indicators to ensure the acquisition of observation data. The commonly used modeling methods of pointing error include spherical harmonic function model, basic parameter model and turntable model. The expressions of spherical harmonic function model have no physical meaning and the model is unstable; the model parameters of the basic parameter model have practical physical significance and the model is relatively stable; the turntable model extends the basic parameter model and has higher precision. But no basic parameter model is stable. Aiming at the problem of pointing error of satellite laser ranging telescope, this paper presents a modeling method based on BP (Back Propagation) neural network. BP neural network is a multi-layer feedforward network trained by error back-propagation algorithm. It is one of the most widely used neural network models. The application of BP neural network algorithm to the modeling of pointing error of mobile satellite laser rangefinder not only expands the application field of neural network algorithm, but also plays an important role in improving the tracking accuracy of satellite laser ranging system. Three groups of observed star data from Wuhan mobile satellite laser ranging station were obtained and divided into training set and test set. The BP neural network model, the turntable model, the spherical harmonic function model and the basic parameter model are established by using the training set, and the test set is used to test the established model. Finally, the middle errors of the four models are calculated and compared. The results show that the BP neural network model can improve the pointing accuracy of the satellite laser ranging telescope and is superior to the other three models. In addition, using the measured data of Wuhan mobile satellite laser ranging station and five sets of observation data from Changchun SLR station and Shanghai Observatory SLR station, the distribution characteristics of pointing error are further studied. First, the observation data of Wuhan mobile SLR station are divided into training set and test set by genetic algorithm, and the turret model is used to model the data. Then, the distribution characteristics and pointing accuracy of the sample residuals in the test set are analyzed. The experimental results show that the height error and azimuth error of the turntable model are not always in accordance with the normal distribution, and the pointing accuracy of the telescope can be improved by optimizing the model by genetic algorithm. Finally, considering the practicability of the pointing error model and further improving the pointing error model, this paper introduces the interfacing process of various modeling methods based on MATLAB development environment.
【學(xué)位授予單位】：中國地震局地震研究所
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP183;P228
本文編號(hào)：2153442
[Abstract]:With the rapid development of light, machine and electric technology, the (SLR) technology of satellite laser ranging has matured day by day. In terms of data accuracy, both domestic and foreign fixed stations or mobile stations have stepped into the sub-centimeter era. In recent years, with the wide application of high repetition rate laser technology, all SLR stations in China have entered a new stage in terms of data volume and accuracy. However, with the exploration and research of SLR stations in the field of daytime ranging, blind tracking, unmanned observation and lunar laser ranging, the pointing accuracy of satellite laser ranging is also required. In satellite laser ranging observation, it is very important to improve the target acquisition ability by improving the pointing accuracy of the telescope. Especially in blind tracking or daytime ranging, it is one of the important indicators to ensure the acquisition of observation data. The commonly used modeling methods of pointing error include spherical harmonic function model, basic parameter model and turntable model. The expressions of spherical harmonic function model have no physical meaning and the model is unstable; the model parameters of the basic parameter model have practical physical significance and the model is relatively stable; the turntable model extends the basic parameter model and has higher precision. But no basic parameter model is stable. Aiming at the problem of pointing error of satellite laser ranging telescope, this paper presents a modeling method based on BP (Back Propagation) neural network. BP neural network is a multi-layer feedforward network trained by error back-propagation algorithm. It is one of the most widely used neural network models. The application of BP neural network algorithm to the modeling of pointing error of mobile satellite laser rangefinder not only expands the application field of neural network algorithm, but also plays an important role in improving the tracking accuracy of satellite laser ranging system. Three groups of observed star data from Wuhan mobile satellite laser ranging station were obtained and divided into training set and test set. The BP neural network model, the turntable model, the spherical harmonic function model and the basic parameter model are established by using the training set, and the test set is used to test the established model. Finally, the middle errors of the four models are calculated and compared. The results show that the BP neural network model can improve the pointing accuracy of the satellite laser ranging telescope and is superior to the other three models. In addition, using the measured data of Wuhan mobile satellite laser ranging station and five sets of observation data from Changchun SLR station and Shanghai Observatory SLR station, the distribution characteristics of pointing error are further studied. First, the observation data of Wuhan mobile SLR station are divided into training set and test set by genetic algorithm, and the turret model is used to model the data. Then, the distribution characteristics and pointing accuracy of the sample residuals in the test set are analyzed. The experimental results show that the height error and azimuth error of the turntable model are not always in accordance with the normal distribution, and the pointing accuracy of the telescope can be improved by optimizing the model by genetic algorithm. Finally, considering the practicability of the pointing error model and further improving the pointing error model, this paper introduces the interfacing process of various modeling methods based on MATLAB development environment.
【學(xué)位授予單位】：中國地震局地震研究所
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP183;P228
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 劉基余;激光在天空對(duì)地觀測(cè)中的應(yīng)用[J];測(cè)繪工程;2001年02期
2 瞿鋒,衛(wèi)志斌,程伯輝,項(xiàng)清革,王譚強(qiáng),劉乃苓;恒星跟蹤與人衛(wèi)激光測(cè)距儀望遠(yuǎn)鏡指向修正[J];測(cè)繪科學(xué);2004年02期
3 瞿鋒;趙春梅;衛(wèi)志斌;;人衛(wèi)激光測(cè)距望遠(yuǎn)鏡系統(tǒng)的指向修正[J];測(cè)繪科學(xué);2006年04期
4 夏治中,葉文蔚,蔡慶福,郭唐永,夏炯煜;DZR—Ⅲ型厘米級(jí)衛(wèi)星激光測(cè)距儀[J];地殼形變與地震;1993年04期
5 孫建中,王培源,譚業(yè)春,李欣,嚴(yán)奉軒,杜瑞林;毫米級(jí)高數(shù)據(jù)密度流動(dòng)衛(wèi)星激光測(cè)距儀的研究[J];大地測(cè)量與地球動(dòng)力學(xué);2005年02期
6 張德賢;前向神經(jīng)網(wǎng)絡(luò)合理隱含層結(jié)點(diǎn)個(gè)數(shù)估計(jì)[J];計(jì)算機(jī)工程與應(yīng)用;2003年05期
7 葉斌,雷燕;關(guān)于BP網(wǎng)中隱含層層數(shù)及其節(jié)點(diǎn)數(shù)選取方法淺析[J];商丘職業(yè)技術(shù)學(xué)院學(xué)報(bào);2004年06期
8 沈花玉;王兆霞;高成耀;秦娟;姚福彬;徐巍;;BP神經(jīng)網(wǎng)絡(luò)隱含層單元數(shù)的確定[J];天津理工大學(xué)學(xué)報(bào);2008年05期
9 張曉祥,吳連大;望遠(yuǎn)鏡靜態(tài)指向模型的基本參數(shù)[J];天文學(xué)報(bào);2001年02期
10 鄭向明,王武,張?jiān)瞥?馮和生;1.2米地平式望遠(yuǎn)鏡指向模型的研究(1.全天指向模型的建立)[J];天文學(xué)報(bào);2003年03期
本文編號(hào)：2153442
本文鏈接：http://sikaile.net/kejilunwen/dizhicehuilunwen/2153442.html
最近更新
教材專著
