Publication Date

Spring 2023

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

Navrati Saxena

Third Advisor

William Andreopoulos

Keywords

Neural Networks, Deep Learning, Long Short Term Memory, Recurrent Neural Networks, Simulation, Wafer Heating, Keras

Abstract

Neural Networks are now emerging in every industry. All the industries are trying their best to exploit the benefits of neural networks and deep learning to make predictions or simulate their ongoing process with the use of their generated data. The purpose of this report is to study the heating pattern of a silicon wafer and make predictions using various machine learning techniques. The heating of the silicon wafer involves various factors ranging from number of lamps, wafer properties and points taken in consideration to capture the heating temperature. This process involves dynamic inputs which facilitates the heating of the silicon wafer to make an IC chip. In this research, LSTMs (Long Short Term Memory) and RNNs (Recurrent Neural Network) have been used with the time series. This problem comes under the Multivariate time series analysis where time factor is taken into account as the heating goes on. This study includes the wafer heating pattern recognition, implementing LSTM and findings which leads to advancement of the silicon wafer heating so that manufacturing firms can identify heating anomalies and adjust inout parameters in their heating recipes to get the best yield. Also, these findings help to simulate the wafer heating by inputting the input parameters to get the surface temperature of the silicon wafer so that process engineers can build a fair idea of the recipe adjustments beforehand to get the best yield. The technical implementation done in this comprises use of Keras and sklearn libraries to use the machine learning capability via Python.

Download
COinS