本文選題：相關(guān)向量機(jī) + 小樣本��； 參考：《西安工程大學(xué)》2016年碩士論文

【摘要】：目前常用的一些基本的故障診斷、故障預(yù)測(cè)方法都將大樣本數(shù)據(jù)作為基礎(chǔ),但在實(shí)際問(wèn)題中常常能得到的故障數(shù)據(jù)都屬于小樣本類型.傳統(tǒng)的故障診斷、故障預(yù)測(cè)方法已不適于用來(lái)解決小樣本類型的故障問(wèn)題.相關(guān)向量機(jī)(Relevance Vector Machine,簡(jiǎn)稱RVM)是新提出的以支持向量機(jī)(Support Vector Machine,簡(jiǎn)稱SVM)為基礎(chǔ)的模型,該模型更適應(yīng)于解決小樣本問(wèn)題.已經(jīng)被應(yīng)用于語(yǔ)音及圖像處理、醫(yī)學(xué)診斷、模式分類等很多領(lǐng)域.本文針對(duì)RVM在小樣本故障診斷、故障預(yù)測(cè)中的應(yīng)用問(wèn)題展開(kāi)研究,主要包含以下方面:(1)分析故障診斷、故障預(yù)測(cè)的研究現(xiàn)狀;(2)RVM理論基礎(chǔ)及其在故障診斷、故障預(yù)測(cè)中的可行性;(3)針對(duì)RVM中核函數(shù)選擇的盲目性及核函數(shù)中相關(guān)參數(shù)對(duì)RVM性能的影響,通過(guò)組合高斯核函數(shù)和柯西核函數(shù)構(gòu)造混合核函數(shù),利用布谷鳥搜索算法(Cuckoo Search Algorithm,簡(jiǎn)稱CS)對(duì)混合核函數(shù)的參數(shù)進(jìn)行優(yōu)化選擇,建立基于布谷鳥算法的混合核函數(shù)相關(guān)向量機(jī)模型(CS-RVM),并通過(guò)仿真測(cè)試驗(yàn)證模型的有效性;(4)將CS-RVM應(yīng)用到航空發(fā)動(dòng)機(jī)的氣路診斷和柴油機(jī)的油路診斷中,通過(guò)與RVM和基于差分進(jìn)化(Differential Evolution,簡(jiǎn)稱DE)的混合核函數(shù)相關(guān)向量機(jī)模型(DE-RVM)比較,充分說(shuō)明該方法在小樣本故障診斷、故障預(yù)測(cè)中的可行性.
[Abstract]:At present, some basic fault diagnosis methods are based on large sample data, but the fault data often obtained in practical problems belong to small sample types. Traditional fault diagnosis and fault prediction methods are not suitable to solve the problem of small sample types of faults. Correlation vector machine (RVM) is a new model based on support vector machine support Vector Machine (SVM), which is more suitable for solving small sample problem. It has been used in many fields, such as speech and image processing, medical diagnosis, pattern classification and so on. In this paper, the application of RVM in small sample fault diagnosis and fault prediction is studied, which mainly includes the following aspects: 1) Analysis of fault diagnosis, present situation of research on fault prediction and its theoretical basis and its application in fault diagnosis. According to the blindness of kernel function selection in RVM and the influence of relevant parameters in kernel function on the performance of RVM, the hybrid kernel function is constructed by combining Gao Si kernel function and Cauchy kernel function. Cuckoo search algorithm (CSA) is used to optimize the selection of parameters of hybrid kernel function. A hybrid kernel function correlation vector machine model based on cuckoo algorithm is established, and the validity of the model is verified by simulation tests. The CS-RVM is applied to the gas path diagnosis of aero-engine and the oil path diagnosis of diesel engine. Compared with RVM and DE-RVM-based hybrid kernel function correlation vector machine model based on differential evolution (DEV), the feasibility of this method in small sample fault diagnosis and fault prediction is fully demonstrated.
【學(xué)位授予單位】：西安工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：V263.6;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王波;劉樹林;蔣超;張宏利;;基于量子遺傳算法優(yōu)化RVM的滾動(dòng)軸承智能故障診斷[J];振動(dòng)與沖擊;2015年17期

2 丁騰飛;曹云俠;;基于改進(jìn)PSO優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的變壓器故障診斷[J];制造業(yè)自動(dòng)化;2015年10期

3 諶璐;賀興時(shí);;改進(jìn)的支持向量機(jī)算法在人臉識(shí)別上的應(yīng)用[J];紡織高�；A(chǔ)科學(xué)學(xué)報(bào);2015年01期

4 陳星;嚴(yán)華;;二叉樹SVM算法在小樣本故障診斷中的優(yōu)化[J];計(jì)算機(jī)測(cè)量與控制;2015年03期

5 王波;劉樹林;張宏利;蔣超;;相關(guān)向量機(jī)及其在機(jī)械故障診斷中的應(yīng)用研究進(jìn)展[J];振動(dòng)與沖擊;2015年05期

6 李練兵;張秀云;王志華;王志強(qiáng);;故障樹和BAM神經(jīng)網(wǎng)絡(luò)在光伏并網(wǎng)故障診斷中的應(yīng)用[J];電工技術(shù)學(xué)報(bào);2015年02期

7 陳芬;;基于多分類相關(guān)向量機(jī)的變壓器故障診斷方法[J];控制工程;2014年06期

8 劉然;傅攀;;基于SVM和BP神經(jīng)網(wǎng)絡(luò)的滾動(dòng)軸承故障診斷[J];機(jī)械工程與自動(dòng)化;2014年06期

9 鄭巧燕;莫愿斌;劉付永;馬彥追;;一種小規(guī)模多種群布谷鳥算法[J];計(jì)算機(jī)應(yīng)用與軟件;2014年10期

10 孫玉紅;;柴油機(jī)漏油、滲氣和油路堵塞的故障診斷與防治[J];湖北農(nóng)機(jī)化;2014年04期

相關(guān)碩士學(xué)位論文 前1條

1 楊升;基于分形技術(shù)與概率神經(jīng)網(wǎng)絡(luò)的柴油機(jī)故障診斷[D];中北大學(xué);2014年

，

本文編號(hào)：2000454