本文選題：質(zhì)量監(jiān)控 + SPC控制圖模式��； 參考：《沈陽理工大學(xué)》2017年碩士論文

【摘要】：在2015年由國(guó)務(wù)院印發(fā)的《中國(guó)制造2025》行動(dòng)綱領(lǐng)中,“質(zhì)量為先”是其五大基本方針之一,表明產(chǎn)品質(zhì)量已經(jīng)成為國(guó)家的重點(diǎn)關(guān)注對(duì)象,也是目前制造企業(yè)生產(chǎn)過程的主要目標(biāo)。因此,如何有效地對(duì)產(chǎn)品的生產(chǎn)過程進(jìn)行質(zhì)量監(jiān)控以保證產(chǎn)品質(zhì)量,是目前制造企業(yè)的重要研究問題。統(tǒng)計(jì)過程控制(Statistical Process Control,SPC)技術(shù)是目前生產(chǎn)制造領(lǐng)域?qū)Ξa(chǎn)品質(zhì)量進(jìn)行監(jiān)控的主要技術(shù)。根據(jù)SPC控制圖的圖像特征可以判斷生產(chǎn)過程是否出現(xiàn)異常,通過對(duì)SPC控制圖模式的識(shí)別可以推斷生產(chǎn)過程發(fā)生異常的原因。近年來研究人員采用多種智能算法用于對(duì)SPC控制圖模式的識(shí)別研究,由于目前生產(chǎn)過程控制圖模式的樣本較少,而支持向量機(jī)(Support Vector Machines,SVM)可以有效解決小樣本條件下的模式識(shí)別問題,因此本文將支持向量機(jī)作為控制圖模式識(shí)別的主要研究工具。本文主要做了以下研究:1)對(duì)SPC控制圖模式數(shù)據(jù)進(jìn)行仿真,并通過統(tǒng)計(jì)特征和形狀特征對(duì)其進(jìn)行特征提取,通過研究、分析支持向量機(jī)原理及其多分類方式的特點(diǎn),選擇“有向無環(huán)圖”(Directed Acyclic Graph,DAG)型支持向量機(jī)作為多分類器,并采用粒子群算法(Particle Swarm Optimization,PSO)對(duì)其參數(shù)進(jìn)行優(yōu)化,然后通過相應(yīng)的仿真實(shí)驗(yàn)進(jìn)行對(duì)比分析;2)為了進(jìn)一步提高控制圖模式的識(shí)別效率及準(zhǔn)確率,提出兩種改進(jìn)方式:首先通過特征融合將原始數(shù)據(jù)和特征數(shù)據(jù)的識(shí)別優(yōu)勢(shì)相結(jié)合,然后通過主成分分析(Principal Component Analysis,PCA)算法對(duì)融合特征進(jìn)行進(jìn)一步的維數(shù)約簡(jiǎn),提取出對(duì)分類影響較大的數(shù)據(jù)特征,從而提高了分類準(zhǔn)確率和識(shí)別效率;對(duì)粒子群算法進(jìn)行改進(jìn),通過增強(qiáng)粒子的主動(dòng)搜索能力,解決其易陷入“局部最優(yōu)”的缺陷,從而提高了分類器識(shí)別的準(zhǔn)確率。仿真實(shí)驗(yàn)結(jié)果表明,通過對(duì)識(shí)別及優(yōu)化算法的改進(jìn),分類器對(duì)控制圖模式的識(shí)別效率和準(zhǔn)確率方面都有了相應(yīng)的提高,識(shí)別率能夠達(dá)到95%以上,能夠滿足基本的生產(chǎn)需求,有效預(yù)防生產(chǎn)異�，F(xiàn)象的出現(xiàn)。
[Abstract]:Therefore, how to effectively monitor the quality of the production process to ensure the quality of products is an important research issue in manufacturing enterprises at present.Statistical Process Control (SPC) technology is the main technology to monitor the product quality in the field of production and manufacturing.According to the image features of SPC control chart, the abnormal production process can be judged, and the reason of abnormal production process can be inferred by recognizing the pattern of SPC control chart.In recent years, researchers have used a variety of intelligent algorithms to study the pattern recognition of SPC control charts.Support vector machine (SVM) can effectively solve the problem of pattern recognition under the condition of small sample, so support vector machine is regarded as the main research tool of control chart pattern recognition in this paper.In this paper, we do the following research: 1) simulate the pattern data of SPC control chart, and extract the feature by statistical feature and shape feature. Through the research, we analyze the principle of support vector machine and the characteristics of multi-classification.The support vector machine "directed Acyclic directed Acyclic Graph DAG" is selected as multi-classifier, and its parameters are optimized by particle swarm optimization algorithm (PSO).In order to further improve the recognition efficiency and accuracy of the control chart, two improved methods are proposed: firstly, the recognition advantages of the original data and the feature data are combined through feature fusion.Then, the principal component analysis (PCA) algorithm is used to reduce the dimension of the fusion features, which has a great influence on the classification, which improves the classification accuracy and recognition efficiency, and improves the particle swarm optimization algorithm.By enhancing the active searching ability of particles, the defect of local optimum is solved, and the accuracy of classifier recognition is improved.The simulation results show that by improving the recognition and optimization algorithm, the classifier can improve the recognition efficiency and accuracy of the control chart pattern, and the recognition rate can reach more than 95%, which can meet the basic production requirements.Effective prevention of abnormal production phenomenon.
【學(xué)位授予單位】：沈陽理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TB114.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 吳德利;;《中國(guó)制造2025》指引中國(guó)工業(yè)“向質(zhì)量進(jìn)軍”[J];上海質(zhì)量;2015年09期

2 蘇衛(wèi)星;朱云龍;胡琨元;劉芳;;基于模型的過程工業(yè)時(shí)間序列異常值檢測(cè)方法[J];儀器儀表學(xué)報(bào);2012年09期

3 丁世飛;齊丙娟;譚紅艷;;支持向量機(jī)理論與算法研究綜述[J];電子科技大學(xué)學(xué)報(bào);2011年01期

4 卓德保;徐濟(jì)超;;質(zhì)量診斷技術(shù)及其應(yīng)用綜述[J];系統(tǒng)工程學(xué)報(bào);2008年03期

相關(guān)博士學(xué)位論文 前6條

1 朱波;基于支持向量機(jī)的自動(dòng)加工過程質(zhì)量控制方法研究[D];重慶大學(xué);2013年

2 楊文安;制造過程質(zhì)量智能控制與診斷中若干問題的研究[D];南京航空航天大學(xué);2012年

3 李英偉;基于增量改進(jìn)BP神經(jīng)網(wǎng)絡(luò)微波深度干燥模型及應(yīng)用研究[D];昆明理工大學(xué);2011年

4 劉建華;粒子群算法的基本理論及其改進(jìn)研究[D];中南大學(xué);2009年

5 李鋼;基于SPC的計(jì)算機(jī)集成質(zhì)量控制系統(tǒng)研究[D];合肥工業(yè)大學(xué);2007年

6 李榮雨;基于PCA的統(tǒng)計(jì)過程監(jiān)控研究[D];浙江大學(xué);2007年

相關(guān)碩士學(xué)位論文 前1條

1 徐玉杰;粒子群算法的改進(jìn)及應(yīng)用[D];南京師范大學(xué);2013年

，

本文編號(hào)：1739052