【摘要】：隨著全球工業(yè)智造的大行其道,人們對(duì)工業(yè)生產(chǎn)系統(tǒng)的穩(wěn)定性、工業(yè)生產(chǎn)運(yùn)行過(guò)程的經(jīng)濟(jì)性及產(chǎn)品質(zhì)量等各個(gè)方面的要求愈加嚴(yán)格。工業(yè)自動(dòng)化市場(chǎng)規(guī)模的急劇擴(kuò)張使得現(xiàn)代工業(yè)系統(tǒng)和設(shè)備愈加復(fù)雜,要保證大型復(fù)雜工業(yè)系統(tǒng)正常運(yùn)行,需要面臨諸多挑戰(zhàn)。因此,為實(shí)現(xiàn)對(duì)工業(yè)過(guò)程實(shí)時(shí)有效地監(jiān)控與檢測(cè),確保生產(chǎn)過(guò)程的安全可靠,利用支持向量機(jī)方法對(duì)對(duì)非線性工業(yè)過(guò)程的大數(shù)據(jù)進(jìn)行故障檢測(cè)與預(yù)測(cè)具有重要的理論價(jià)值和實(shí)際意義。本文分析了支持向量機(jī)的基礎(chǔ)理論,推導(dǎo)了該算法的建模原理和過(guò)程。針對(duì)非線性工業(yè)過(guò)程中大數(shù)據(jù)的故障檢測(cè)和預(yù)測(cè),首先采用交叉驗(yàn)證優(yōu)化方法對(duì)支持向量機(jī)進(jìn)行核參數(shù)優(yōu)化。然后分別利用支持向量機(jī)、主成分分析法和增強(qiáng)偏最小二乘法對(duì)連續(xù)攪拌釜式加熱器過(guò)程進(jìn)行故障檢測(cè),并對(duì)各個(gè)算法的故障檢測(cè)結(jié)果進(jìn)行分析比對(duì),實(shí)驗(yàn)結(jié)果表明,SVM分類(lèi)器在實(shí)際復(fù)雜工業(yè)過(guò)程中具有優(yōu)異的預(yù)測(cè)能力和理想的運(yùn)行時(shí)間。針對(duì)非線性工業(yè)過(guò)程的故障預(yù)測(cè)問(wèn)題,通過(guò)學(xué)習(xí)半監(jiān)督學(xué)習(xí)方法,利用孿生支持向量機(jī)和改進(jìn)算法(S~4VM)對(duì)工業(yè)過(guò)程的故障狀態(tài)進(jìn)行有效地預(yù)測(cè)分析。S~4VM對(duì)初始參數(shù)設(shè)定值不敏感,能同時(shí)考慮多個(gè)候選大邊界低密度分界線,并在最壞情況下優(yōu)化標(biāo)簽分配,在解決非線性工業(yè)過(guò)程大數(shù)據(jù)的故障預(yù)測(cè)的問(wèn)題上表現(xiàn)優(yōu)異。
[Abstract]:With the popularity of global industrial intelligence, the requirements for the stability of industrial production system, the economy of industrial production process and the quality of products are becoming more and more stringent. The rapid expansion of industrial automation market makes modern industrial systems and equipment more complex. To ensure the normal operation of large-scale complex industrial systems, many challenges need to be faced. Therefore, in order to realize the real-time and effective monitoring and detection of the industrial process and ensure the safety and reliability of the production process, The support vector machine (SVM) method is of great theoretical value and practical significance for the fault detection and prediction of big data in nonlinear industrial processes. In this paper, the basic theory of support vector machine is analyzed, and the modeling principle and process of the algorithm are deduced. Aiming at the fault detection and prediction of big data in nonlinear industrial process, the kernel parameters of support vector machine are optimized by cross-validation optimization method. Then, support vector machine, principal component analysis and enhanced partial least square method are used to detect the faults of the continuous stirred tank heater, and the results of each algorithm are analyzed and compared. The experimental results show that the SVM classifier has excellent prediction ability and ideal running time in complex industrial processes. In order to solve the problem of nonlinear industrial process fault prediction, by learning semi-supervised learning method, twinning support vector machine and improved algorithm (S~4VM) are used to effectively predict the fault state of industrial process and analyze that Sch _ 4VM is insensitive to the initial parameter setting value. It can simultaneously consider multiple candidate large boundary low density boundaries and optimize label assignment in the worst case. It is excellent in solving the problem of big data's fault prediction in nonlinear industrial processes.
【學(xué)位授予單位】：渤海大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP277

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 王麗;侍洪波;;采用改進(jìn)核偏最小二乘法的非線性化工過(guò)程故障檢測(cè)(英文)[J];Chinese Journal of Chemical Engineering;2014年06期

2 Naik A;;On the Application of PCA Technique to Fault Diagnosis[J];Tsinghua Science and Technology;2010年02期

3 劉萬(wàn)里;劉三陽(yáng);王金艷;;不平衡支持向量機(jī)的調(diào)整方法[J];計(jì)算機(jī)科學(xué);2009年03期

4 賈銀山,賈傳熒;一種加權(quán)支持向量機(jī)分類(lèi)算法[J];計(jì)算機(jī)工程;2005年12期

5 馬笑瀟,黃席樾,柴毅;基于SVM的二叉樹(shù)多類(lèi)分類(lèi)算法及其在故障診斷中的應(yīng)用[J];控制與決策;2003年03期

6 胡壽松,王源;基于支持向量機(jī)的非線性系統(tǒng)故障診斷[J];控制與決策;2001年05期

7 張學(xué)工;關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)[J];自動(dòng)化學(xué)報(bào);2000年01期

相關(guān)碩士學(xué)位論文 前2條

1 祝向平;針對(duì)關(guān)鍵性能指標(biāo)的故障診斷方法研究[D];渤海大學(xué);2016年

2 張彥周;基于支持向量機(jī)的測(cè)井曲線預(yù)測(cè)儲(chǔ)層參數(shù)方法[D];西安科技大學(xué);2006年

，

本文編號(hào)：2231705