本文關(guān)鍵詞： BP神經(jīng)網(wǎng)絡(luò) L-M算法 學(xué)習(xí)率自適應(yīng) 傳感器辨識(shí) 故障診斷　出處：《杭州電子科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：能源問題一直受到人們的廣泛關(guān)注,以光伏發(fā)電為代表的新能源技術(shù)得到了重視,光伏監(jiān)控是利用好太陽能的重要手段。但是光伏監(jiān)控中存在著復(fù)雜非線性問題,如何利用人工智能技術(shù)將光伏監(jiān)控中存在的難題朝著智能化方向發(fā)展是本文的主要研究動(dòng)機(jī)。本文基于神經(jīng)網(wǎng)絡(luò)方法從光角度傳感器模型辨識(shí)以及組件故障診斷方面做了應(yīng)用研究,具體內(nèi)容如下:第一部分:主要介紹神經(jīng)網(wǎng)絡(luò)的理論基礎(chǔ)。首先,從生物神經(jīng)元描述出發(fā),對(duì)其抽象出的人工神經(jīng)元原理以及工作特點(diǎn)進(jìn)行了介紹。然后,基于環(huán)境提供信息的多少對(duì)神經(jīng)網(wǎng)絡(luò)的三種學(xué)習(xí)方式進(jìn)行了總結(jié)與描述。最后,對(duì)于神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)過程中所采用的三種常用算法原理以及典型網(wǎng)絡(luò)結(jié)構(gòu)進(jìn)行了總結(jié)與歸納。第二部分:選擇了BP神經(jīng)網(wǎng)絡(luò)模型作為本文主要研究對(duì)象。首先,對(duì)于BP神經(jīng)網(wǎng)絡(luò)模型的算法原理進(jìn)行了簡單概述,對(duì)于該模型工作過程中的信號(hào)前饋計(jì)算和誤差反向傳播分別進(jìn)行了理論推導(dǎo),獲取到最終的誤差迭代公式。然后,在網(wǎng)絡(luò)結(jié)構(gòu)設(shè)計(jì)方面進(jìn)行了研究,關(guān)于輸入輸出樣本的選擇和處理做了深入討論。最后,主要對(duì)于網(wǎng)絡(luò)訓(xùn)練中的參數(shù)選擇進(jìn)行了研究與分析。第三部分:針對(duì)光伏監(jiān)控中使用的一種特殊光角度傳感器存在模型難以辨識(shí)的問題,提出了L-M算法優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)系統(tǒng)辨識(shí)模型。首先,針對(duì)光角度傳感器中存在的制造或安裝誤差而無法準(zhǔn)確測量角度的非線性問題,建立了用于模型辨識(shí)的BP神經(jīng)網(wǎng)絡(luò)模型。然后,研制了一套基于光角度傳感器的實(shí)驗(yàn)數(shù)據(jù)采集系統(tǒng),獲取到訓(xùn)練神經(jīng)網(wǎng)絡(luò)的輸入輸出實(shí)驗(yàn)數(shù)據(jù)。最后,對(duì)于訓(xùn)練完成且達(dá)到目標(biāo)設(shè)定值的神經(jīng)網(wǎng)絡(luò),可以有效地根據(jù)光角度傳感器測得的電流數(shù)據(jù)預(yù)測出輸出角度值,該方法可以有效地應(yīng)用于機(jī)理建模中存在參數(shù)未知甚至難以建模的數(shù)學(xué)問題。第四部分:針對(duì)光伏組件存在運(yùn)行狀態(tài)與運(yùn)行參數(shù)之間的復(fù)雜非線性問題,提出了學(xué)習(xí)率自適應(yīng)的BP神經(jīng)網(wǎng)絡(luò)故障診斷模型。首先,采用數(shù)學(xué)語言分析了運(yùn)行參數(shù)與環(huán)境條件之間的復(fù)雜非線性問題,建立了學(xué)習(xí)率自適應(yīng)的BP神經(jīng)網(wǎng)絡(luò)故障診斷模型。然后,為了驗(yàn)證模型的有效性,采用的是光伏組件本構(gòu)方程進(jìn)行實(shí)驗(yàn)數(shù)據(jù)采集,獲取到用于訓(xùn)練網(wǎng)絡(luò)的輸入輸出數(shù)據(jù)。最后,對(duì)于訓(xùn)練完成且達(dá)到目標(biāo)設(shè)定值的神經(jīng)網(wǎng)絡(luò),采用一組新的運(yùn)行數(shù)據(jù)用來驗(yàn)證神經(jīng)網(wǎng)絡(luò),結(jié)果表明該網(wǎng)絡(luò)可以有效地對(duì)組件運(yùn)行狀態(tài)進(jìn)行識(shí)別與分類,驗(yàn)證了方法的有效性。
[Abstract]:The energy problem has been paid more and more attention, and the new energy technology, represented by photovoltaic power generation, has been paid attention to. Photovoltaic monitoring is an important means to make good use of solar energy. However, there are complex nonlinear problems in photovoltaic monitoring. How to make use of artificial intelligence technology to develop the problem of photovoltaic monitoring towards the direction of intelligence is the main motivation of this paper. This paper based on the neural network method from the perspective of light sensor model identification and component fault diagnosis. Has done the applied research in the aspect, The main contents are as follows: the first part mainly introduces the theoretical basis of neural network. Firstly, from the description of biological neurons, the abstract principle and working characteristics of artificial neurons are introduced. The three learning methods of neural network are summarized and described based on the amount of information provided by the environment. Finally, Three common algorithms and typical network structure used in the learning process of neural network are summarized and summarized. The second part: the BP neural network model is selected as the main research object of this paper. The algorithm principle of BP neural network model is briefly summarized. The signal feedforward calculation and error back propagation in the working process of the model are derived theoretically, and the final error iterative formula is obtained. In the aspect of network structure design, the selection and processing of input and output samples are discussed. Finally, This paper mainly studies and analyzes the parameter selection in network training. Part three: aiming at the problem that a special optical angle sensor used in photovoltaic monitoring is difficult to identify. The identification model of BP neural network system optimized by L-M algorithm is proposed. Firstly, aiming at the nonlinear problem of manufacturing or installing errors in optical angle sensor, it can not accurately measure the angle. A BP neural network model for model identification is established. Then, a set of experimental data acquisition system based on optical angle sensor is developed to obtain the input and output experimental data of the training neural network. Finally, For the neural network which has completed the training and reached the target set value, it can effectively predict the output angle value based on the current data measured by the optical angle sensor. This method can be effectively applied to the mathematical problems where the parameters are unknown or even difficult to model in the mechanism modeling. Part 4th: aiming at the complex nonlinear problem between the running state and the operating parameters of the photovoltaic module, A BP neural network fault diagnosis model with adaptive learning rate is proposed. Firstly, the complex nonlinear problems between operating parameters and environmental conditions are analyzed by mathematical language. A BP neural network fault diagnosis model with adaptive learning rate is established. Then, in order to verify the validity of the model, the photovoltaic component constitutive equation is used to collect the experimental data, and the input and output data for the training network are obtained. A new set of running data is used to verify the neural network for the neural network which has completed the training and reached the target set value. The results show that the neural network can effectively identify and classify the running states of the components and verify the effectiveness of the method.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP183;TM615

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄭寧來;;2100年全球?qū)⒏鎰e化石能源[J];煉油技術(shù)與工程;2015年10期

2 尹寶才;王文通;王立春;;深度學(xué)習(xí)研究綜述[J];北京工業(yè)大學(xué)學(xué)報(bào);2015年01期

3 戴慶忠;;優(yōu)化電源結(jié)構(gòu) 走電力可持續(xù)發(fā)展道路——“十二五”電力工業(yè)發(fā)展規(guī)劃解析[J];東方電機(jī);2013年02期

4 孟小峰;慈祥;;大數(shù)據(jù)管理:概念、技術(shù)與挑戰(zhàn)[J];計(jì)算機(jī)研究與發(fā)展;2013年01期

5 高金輝;唐靜;賈利鋒;;太陽能電池參數(shù)求解新算法[J];電力系統(tǒng)保護(hù)與控制;2012年09期

6 曹連彬;宋衛(wèi)平;韓如成;;故障樹在光伏并網(wǎng)系統(tǒng)失效研究中的應(yīng)用[J];電氣技術(shù);2012年04期

7 蘭琴麗;章樂多;;BP神經(jīng)網(wǎng)絡(luò)在光伏發(fā)電系統(tǒng)故障診斷中的應(yīng)用[J];通信電源技術(shù);2011年04期

8 王新勇;陳濤;;采用變頻器故障樹為訓(xùn)練樣本的BAM神經(jīng)網(wǎng)絡(luò)故障診斷方法[J];電光與控制;2011年05期

9 項(xiàng)文強(qiáng);張華;王Y，

本文編號(hào)：1527627