Average material removal rate prediction method, apparatus, electronic device and storage medium
A prediction method and removal rate technology, applied in the field of virtual measurement, can solve problems such as inaccurate prediction of average material removal rate, and achieve the effect of assisting users in decision-making and ensuring prediction accuracy
Active Publication Date: 2022-06-24
深圳市信润富联数字科技有限公司
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the technical problem of inaccurate prediction of the average material removal rate in the existing chemical mechanical polishing process, an embodiment of the present invention provides a method, device, electronic device and storage medium for predicting the average material removal rate
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.
[0050] Before introducing the solutions of the embodiments of the present invention, the following related contents are introduced first:
[0051] In the semiconductor and integrated circuit manufacturing process, chemical mechanical polishing (Chemical Mechanical Planarization, CMP) is a key process to achieve wafer surface planarization. Different from the traditional pure mechanical or pure chemical polishing methods, the CMP process realizes the removal of micron and even nano-scale materials on the wafer surface through the combination of surface chemistry and mechanical grinding technology, so as to achieve nano-scale flattening of the wafer surface. This enables the subsequent photolithography process to proceed. Therefore, in order to improve production efficiency and product quality, Advanced Process Control (APC) is widely used in sem...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an average material removal rate prediction method, device, electronic equipment and storage medium. Wherein, the method includes obtaining a model training set; performing normalization processing on the model training set; performing feature extraction on each sample in the training set after normalization processing; performing Gaussian process regression according to the extracted features Modeling: using the model after modeling to predict the test sample, and obtain the predicted value of the average material removal rate of the test sample. Adopting the solution provided by the present invention does not need to extract corresponding statistical features from process variables for modeling, which can ensure the prediction accuracy of the model. The invention uses the Gaussian process regression to model, and can also provide the confidence interval of the prediction result, which can assist users in decision-making.
Description
technical field [0001] The invention relates to the technical field of virtual measurement, and in particular, to a method, device, electronic device and storage medium for predicting an average material removal rate. Background technique [0002] In the semiconductor and integrated circuit manufacturing process, chemical mechanical polishing (Chemical Mechanical Planarization, CMP) is a key process to achieve wafer surface planarization. In this process, the average material removal rate (MRR) is one of the key indicators used to evaluate the performance of the CMP process and product quality. Since it is difficult to measure by sensors or other metrology methods, the method of virtual metrology (VM) is widely used in the prediction of MRR. [0003] In the prior art, to predict the MRR index in the CMP process, it is necessary to extract features from process variables for modeling. Therefore, equipment degradation will affect the prediction results, resulting in low accur...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27G06Q10/04G06K9/62
Inventor 冯建设成建洪刘小双
Owner 深圳市信润富联数字科技有限公司