Training spectrum generation for machine learning system for spectrographic monitoring
A technology of spectrum and spectral value, which is applied in the field of optical monitoring, can solve the problems of determining the polishing end point, etc., and achieve the effect of reducing thickness unevenness and improving reliability
Pending Publication Date: 2020-08-25
APPLIED MATERIALS INC
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, it may not be possible to determine the polishing endpoint only as a function of polishing time or to achieve the desired profile simply by applying a constant pressure
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
[0023] One monitoring technique is to measure the spectrum of light reflected from the substrate being polished. Various techniques have been proposed to determine characteristic values, such as the thickness of the layer being polished, from the measured spectra. One possible technique is to train the neural network based on training spectra from sample device substrates and measured characteristic values for those sample substrates. After training, during normal operation, the measured spectra from the device substrate can be input to the neural network, and the neural network can output characteristic values, such as the calculated thickness of the top layer of the substrate. The motivation for using a neural network is the possibility to remove the influence of the thickness of the underlying membrane on the calculated thickness of the top layer.
[0024] A problem with training a neural network in this context is that impractically large data sets may be required to ad...
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
A method of generating training spectra for training of a neural network includes measuring a first plurality of training spectra from one or more sample substrates, measuring a characterizing value for each training spectra of the plurality of training spectra to generate a plurality of characterizing values with each training spectrum having an associated characterizing value, measuring a plurality of dummy spectra during processing of one or more dummy substrates, and generating a second plurality of training spectra by combining the first plurality of training spectra and the plurality ofdummy spectra, there being a greater number of spectra in the second plurality of training spectra than in the first plurality of training spectra. Each training spectrum of the second plurality of training spectra having an associated characterizing value.
Description
technical field [0001] The present disclosure pertains to optical monitoring of substrates, eg, during processing such as chemical mechanical polishing. Background technique [0002] Integrated circuits are typically formed on a substrate by sequentially depositing conductive, semiconductive or insulating layers on a silicon wafer. One fabrication step involves depositing a filler layer on the non-planar surface and planarizing the filler layer. For some applications, the filler layer is planarized until the top surface of the patterned layer is exposed. For example, a conductive filler layer can be deposited on the patterned insulating layer to fill trenches or holes in the insulating layer. After planarization, the portions of the conductive layer remaining between the raised patterns of the insulating layer form vias, plugs and lines that provide conductive paths between the thin film circuits on the substrate. For other applications, the filler layer is planarized unt...
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 Applications(China)
IPC IPC(8): H01L21/67H01L21/66H01L21/304G01B11/06
CPCG05B13/027G06N3/08G06N3/045G06N3/047G06N3/048H01L21/67242H01L22/12H01L22/24H01L22/30H01L21/67092H01L21/304G01B11/0616G05B2219/45199G05B2219/32335G05B2219/45031G05B19/4063G05B19/4155G05B2219/40066G05B2219/41054
Inventor B·切里安N·威斯韦尔J·钱T·H·奥斯特海德
Owner APPLIED MATERIALS INC