Robert S. Jaffe

Principal Component Analysis of Optical Emission Spectroscopy and Mass Spectrometry: Application to Reactive Ion Etch Process Parameter Estimation Using Neural Networks

We report on a simple technique that characterizes the effect of process parameters (i.e., pressure, RF power, and gas mixture) on the optical emission and mass spectra of CHFJO2 plasma. This technique is sensitive to changes in chamber contamination levels (e.g., formation of Teflon-like thin-film), and appears to be a promising tool for real-time monitoring and control of reactive ion etching. Through principal component analysis, we observe that 99% of the variance in the more than 1100 optical and mass spectra channels are accounted for by the first four principal components of each sensor. Projection of the mass spectrum on its principal components suggests a strong linear relationship with respect to chamber pressure. This representation also shows that the effect of changes in thin-film levels, gas mixture, and RF power on the mass spectrum is complicated, but predictable. To model the nonlinear relationship between these process parameters and the principal component projections, a feedforward, multi-layered neural network is trained and is shown to be able to predict all process parameters from either the mass or the optical spectrum. The projections of the optical emission spectrum on its principal components suggest that optical emission spectroscopy is much more sensitive to changes in RF power than the mass spectrum, as measured by the residual gas analyzer. Model performance can be significantly improved if both the optical and mass spectrum projections are used (so called sensor fusion). Our analysis indicates that accurate estimates of process parameters and chamber conditions can be made with relatively simple neural network models which fuse the principal components of the measured optical emission and mass spectra. In the reactive ion etching (RIE) process, plasma characteristics depend on many parameters; some of these parameter values are set by the tool operator, e.g., chamber pressure, RF power, and gas flow, while others are internal to the condition of the chamber, e.g., thin-film thickness on the chamber walls, or the amount of material etched. Plasma characteristics can be observed using in situ measurements, e.g., via optical emission spectroscopy (OES) or residual gas analysis (RGA). How these measurements can be used to estimate the process parameters is the question

The P300: a system for automatic patterned wafer inspection

This paper describes a machine vision technique and associated system (the P300) for automated inspection of integrated circuit chips on multi-level patterned wafers for pattern defects and particulates. This inspection has been variously referred to as “micro,” “first optical,” and just “defect inspection.” Despite the fact that this inspection is primarily performed manually today, the effectiveness of manual inspection is marginal-especially for products requiring the detection of sub-micron defects. In the future, on smaller groundrule products, manual inspection will clearly become inadequate. The system described here performs this inspection on periodic patterns such as those found in memory and CCD arrays. It has been shown effective for inspecting a broad range of production wafers. A description of the problem and a survey of previous work are presented. Following these, the P300 system and associated image analysis algorithms are described. The image analysis technique consists of a reference comparison combined with certain devices (gated operators and statistical sampling) designed to significantly reduce false alarms with minimal reduction in detection probability. The current version of the system has demonstrated the ability to reliably find 0.5 μm defects and can be extended to smaller defect sizes. The technique is especially significant because of its high detection probability achieved at an extremely low false alarm rate. High throughput and low cost have been achieved due to both the unique algorithm and a custom parallel processor, which executes the inspection algorithm at high (video frame rate) throughput.