摘要
针对传统成品率预测模型中需要大量缺陷信息且极少考虑范围预测的情况,借鉴多智能体思想,研究了一种模糊聚合与支持向量回归相融合的方法,对成品率进行预测。在逐步缩减预测范围的同时,多智能体协同调整学习速率等参数,根据确定好的参数构建多个模糊成品率学习模型;利用模糊规则对多个学习模型的预测结果进行聚合,以提高预测准确性;利用支持向量回归将聚合结果去模糊化,得到最终的成品率预测值。仿真实验表明,该方法预测过程较简便,预测范围更精确,具有可行性。
Aiming at problem that the existing methods needed to consider a lot of defect data and rarely estimate pre- diction range in traditional yield prediction model, based on Multi-Agent System （MAS）, an approach which com- bined fuzzy rules intersection method and Support Vector Regression （SVR） was proposed to predict the semicon- ductor yield. Through reducing the prediction rang gradually and adjusting parameters such as learning rate coordi- nately by agents, multiple fuzzy yield learning models were constructed. The fuzzy forecasts of multiple fuzzy learn- ing models was aggregated with fuzzy rules, and the predicted accuracy was improved. SVR was adopted to defuzzi- fy the fuzzy yield prediction. Theoretic analysis and experiments showed that the proposed method was available, the forecasting process was relatively simple as well as the prediction range was more accurate than the existing methods.
作者
赵婷婷
曹政才
邱明辉
ZHAO Tingting CAO Zhengcai QIU Minghui(College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029 China)
出处
《计算机集成制造系统》
EI
CSCD
北大核心
2017年第4期852-859,共8页
Computer Integrated Manufacturing Systems
基金
国家自然科学基金资助项目(51375038)
北京市自然科学基金资助项目(4162046)
高等学校博士学科点专项科研基金博导类资助项目(20130010110009)~~
关键词
半导体生产线
成品率预测
多智能体
模糊聚合
支持向量回归
semiconductor wafer fabrication
yield prediction
multi-agent
fuzzy intersection
support vector regres-sion
