Multiscale modeling and neural network model based control of a plasma etch process

Xiao, Tianqi; Ni, Dong

doi:10.1016/j.cherd.2020.09.013

Cited by 10 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ANN is considered a reliable tool for handling problems that involve prediction, control, or nonlinear process identification [37,38]. The principal advantage of an ANN is in its ability to learn from the observed data and approximate a function [39]. Mostly, this technique is used as a black box approach to model the linear as well as complex non-linear systems [40][41][42].…”

Section: Development Of Ann Modelsmentioning

confidence: 99%

Intelligent Control of an Industrial Debutanizer Column

et al. 2022

View full text Add to dashboard Cite

A debutanizer column located at a refinery in Malaysia produces LPG as its top product and light naphtha as its bottom product. Control of the product compositions of the column is very important to maintain the desired purities. The current control design of the debutanizer column is based on the classical proportional integral derivative approach, which has been found to be less effective in controlling the variations in the column as the process is characterized by strong nonlinear and uncertain dynamics. Here, intelligent control based on an adaptive neurofuzzy inference system (ANFIS) is investigated and compared against an artificial neural network, for the special case of limited training data of the industrial debutanizer column. The ANFIS-based controller outperforms the other control configurations for both set point tracking and disturbance rejection cases and has better generalization performance even when trained with limited data samples.

show abstract

Section: Development Of Ann Modelsmentioning

confidence: 99%

Intelligent Control of an Industrial Debutanizer Column

et al. 2022

View full text Add to dashboard Cite

show abstract

“…46−49 Specific and detailed illustrations on the plasma chemistry can be found in our previous work. 11 The control variables of the plasma chamber are set as the power of the top coils (P rf ), the bottom electrode bias (V B ), Ar/Cl 2 ratio of the input gases at edge inlet (R 1 ), and Ar/Cl 2 ratio of the input gases at center inlet (R 2 ).…”

Section: Preliminariesmentioning

confidence: 99%

“…In an earlier work by our group, we have presented a 3D multiscale model for the silicon etch process using Cl 2 /Ar inductive coupled plasma (ICP) analysis. 11 Plasma models are complex in that they are derived from conservation laws and are described by highly dissipative systems. Traditional methods to solve PDEs involve temporal and spatial discretization by using a finite-difference or finiteelement method, 12,13 the main drawback of which is that they require significant computational resources.…”

Section: Introductionmentioning

confidence: 99%

Recurrent Neural-Network-Based Model Predictive Control of a Plasma Etch Process

Xiao

Christofides

et al. 2021

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

In this article, we propose the development of a recurrent neural network (RNN)-based model predictive controller (MPC) for a plasma etch process on a three-dimensional substrate using inductive coupled plasma (ICP) analysis. Specifically, the plasma etch process is simulated by a multiscale model: (1) A macroscopic fluid model is applied to simulate the gas flows and chemical reactions of plasma. (2) A kinetic Monte Carlo (kMC) model is applied to simulate the etching process on the substrate. Subsequently, proper orthogonal decomposition (POD) is used to derive the empirical eigenfunctions of the plasma model. Then the empirical eigenfunctions are utilized as basis functions within a Galerkin’s model reduction framework to compute a low-order system capturing dominant dynamics of the plasma model. Additionally, RNN is introduced to approximate dynamics of both the reduced-order plasma system and the microscopic etch process. The training data for the RNN models are generated from discrete sampling of open-loop simulations. A probability distribution function is also involved to present the stochastic characteristic of the kMC model. The trained RNN models are then implemented as the prediction model in the development of MPC to achieve desired control objectives. Closed-loop simulation results are presented to compare the performance of the model predictive controller and a proportional-integral (PI) controller, which show that the proposed MPC framework is effective and exhibits better performance than does a PI controller.

show abstract

“…In particular, for processes using plasma, such as etching and deposition, the plasma conditions may change according to the amount of injected gas, chamber pressure, applied radio frequency (RF) power, chamber leakage, etc. [3,4]. Semiconductor process equipment are often operated at their set parameter values, but unnoticed deviations from these set values affect the plasma conditions, which eventually produce unacceptable process results.…”

Section: Introductionmentioning

confidence: 99%

Use of Optical Emission Spectroscopy Data for Fault Detection of Mass Flow Controller in Plasma Etch Equipment

Kwon

Hong

2022

Electronics

View full text Add to dashboard Cite

To minimize wafer yield losses by misprocessing during semiconductor manufacturing, faster and more accurate fault detection during the plasma process are desired to increase production yields. Process faults can be caused by abnormal equipment conditions, and the performance drifts of the parts or components of complicated semiconductor fabrication equipment are some of the most unnoticed factors that eventually change the plasma conditions. In this work, we propose improved stability and accuracy of process fault detection using optical emission spectroscopy (OES) data. Under a controlled experimental setup of arbitrarily induced fault scenarios, the extended isolation forest (EIF) approach was used to detect anomalies in OES data compared with the conventional isolation forest method in terms of accuracy and speed. We also used the OES data to generate features related to electron temperature and found that using the electron temperature features together with equipment status variable identification data (SVID) and OES data improved the prediction accuracy of process/equipment fault detection by a maximum of 0.84%.

show abstract

Multiscale modeling and neural network model based control of a plasma etch process

Cited by 10 publications

References 42 publications

Intelligent Control of an Industrial Debutanizer Column

Intelligent Control of an Industrial Debutanizer Column

Recurrent Neural-Network-Based Model Predictive Control of a Plasma Etch Process

Use of Optical Emission Spectroscopy Data for Fault Detection of Mass Flow Controller in Plasma Etch Equipment

Contact Info

Product

Resources

About