基于SSA-GRNN的铜CMP抛光液抛光速率预测
Prediction of Copper CMP Polishing Rate Based on SSA-GRNN
栾晓东 1张拓 2穆成银2
作者信息
- 1. 江苏海洋大学 电子工程学院,江苏 连云港 222005;江苏省海洋资源开发研究院,江苏 连云港 222005
- 2. 江苏海洋大学 电子工程学院,江苏 连云港 222005
- 折叠
摘要
铜化学机械抛光(CMP)是集成电路制造的关键步骤之一,其中铜抛光速率是衡量抛光液性能的关键指标.在CMP过程中,由于铜抛光液中各组分与铜之间的化学反应复杂,需要大量的数据实验来实现可调的抛光速率.为提高铜 CMP 抛光速率预测的准确性,利用麻雀搜索算法对广义回归神经网络的平滑因子进行优化,提出了一种基于麻雀搜索算法的广义回归神经网络(SSA-GRNN)铜CMP抛光液抛光速率预测模型.首先,在MATLAB 中建立 SSA-GRNN网络模型,然后输入抛光液各组分数据,预测在不同组分下抛光液的抛光速率,最后将SSA-GRNN模型的预测结果与BP神经网络模型(BP-NCABC)的预测结果对比.结果表明,SSA-GRNN模型在训练集上的平均绝对百分比误差(MAPE)比BP-NCABC模型降低 4.82 百分点,在测试集上的MAPE 比BP-NCABC模型降低 1.78 百分点;SSA-GRNN模型在训练集上的最优预测精度比 BP-NCABC 模型提高 0.09 百分点,在测试集上的最优预测精度比BP-NCABC模型提高 0.32 百分点.上述研究结果表明,在CMP抛光速率的预测上SSA-GRNN模型比BP-NCABC模型的准确性更高,这为指导CMP实验、提升实验效率、降低研发成本和优化抛光液组分提供了一种可选的模型.
Abstract
Copper chemical mechanical polishing(CMP)is one of the key steps in the manufacture of integrated circuits,and the copper polishing rate is the key index to measure the performance of the polishing slurry.It requires vast amounts of experimental data to achieve adjustable polis-hing rates due to the complex chemical reactions between various components of the copper polis-hing slurry and copper during the CMP process.To enhance the accuracy of copper CMP polis-hing rate prediction,sparrow search algorithm is used to optimize the smoothing operator of gen-eralized regression neural network,and a prediction model of copper CMP polishing rate based on SSA-GRNN is proposed.Firstly,an SSA-GRNN network model is established in MATLAB.Subsequently,the component data of the polishing slurry is inputted to predict the polishing rate of the slurry under different compositions.Finally,a comparison is made between the prediction results of the SSA-GRNN model and the BP-NCABC model.The comparative results indicate that the SSA-GRNN model exhibited a 4.82 percentage point reduction in mean absolute percent-age error(MAPE)on the training set and a 1.78 percentage point reduction in MAPE on the tes-ting set.The SSA-GRNN model demonstrated a 0.09 percentage point improvement in optimal prediction accuracy on the training set and a 0.32 percentage point improvement on the testing set compared to the BP-NCABC model.These findings indicate the SSA-GRNN model exhibits high-er accuracy than the BP-NCABC model in predicting CMP polishing rates,which provides an al-ternative model for guiding CMP experiments to enhance experimental efficiency and reduce re-search and development costs and optimizing the components of the polishing slurry.
关键词
化学机械抛光/抛光液/广义回归神经网络/麻雀搜索算法Key words
chemical mechanical planarization(CMP)/polishing slurry/general regression neural network(GRNN)/sparrow search algorithm(SSA)引用本文复制引用
基金项目
国家中长期科技发展规划科技重大专项资助项目(2016ZX02301003)
国家自然科学基金资助项目(62104087)
江苏省自然科学青年基金项目(BK20191005)
江苏省高等学校自然科学研究面上项目(19KJB430011)
出版年
2024
NETL
NSTL
万方数据