本文關(guān)鍵詞： 半導(dǎo)體生產(chǎn)線 成品率預(yù)測(cè) 多智能體 模糊聚合 支持向量回歸　出處：《計(jì)算機(jī)集成制造系統(tǒng)》2017年04期 　論文類型：期刊論文

【摘要】：針對(duì)傳統(tǒng)成品率預(yù)測(cè)模型中需要大量缺陷信息且極少考慮范圍預(yù)測(cè)的情況,借鑒多智能體思想,研究了一種模糊聚合與支持向量回歸相融合的方法,對(duì)成品率進(jìn)行預(yù)測(cè)。在逐步縮減預(yù)測(cè)范圍的同時(shí),多智能體協(xié)同調(diào)整學(xué)習(xí)速率等參數(shù),根據(jù)確定好的參數(shù)構(gòu)建多個(gè)模糊成品率學(xué)習(xí)模型;利用模糊規(guī)則對(duì)多個(gè)學(xué)習(xí)模型的預(yù)測(cè)結(jié)果進(jìn)行聚合,以提高預(yù)測(cè)準(zhǔn)確性;利用支持向量回歸將聚合結(jié)果去模糊化,得到最終的成品率預(yù)測(cè)值。仿真實(shí)驗(yàn)表明,該方法預(yù)測(cè)過(guò)程較簡(jiǎn)便,預(yù)測(cè)范圍更精確,具有可行性。
[Abstract]:In view of the fact that a lot of defect information is needed in the traditional product rate prediction model and the range prediction is seldom considered, a method of fusion of fuzzy aggregation and support vector regression is studied based on the idea of multi-agent. At the same time, the multi-agent adjusts the learning rate and other parameters, and constructs several fuzzy yield learning models according to the determined parameters. The prediction results of multiple learning models are aggregated by fuzzy rules to improve the prediction accuracy, and the final yield prediction value is obtained by using support vector regression to deblur the aggregate results, and the simulation results show that, The method is simple, accurate and feasible.
【作者單位】： 北京化工大學(xué)信息科學(xué)與技術(shù)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(51375038) 北京市自然科學(xué)基金資助項(xiàng)目(4162046) 高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金博導(dǎo)類資助項(xiàng)目(20130010110009)~~
【分類號(hào)】：TN305;TP18
，

本文編號(hào)：1535329