Extraction of electrical test parameters by artificial neural network

In semiconductor industry, cycle time of the wafer fabrication is very crucial and one of the contributing factors comes from wafer testing. This paper presents the application of back propagation Artificial Neural Network (ANN) model designed to infer electrical test parameters from the given list of parameters with the intention of reducing test time, to enhance throughput, and to improve cycle time. It also investigates if the ANN based inference system can be established as a robust method for parameter extraction to provide an accurate electrical value to minimize false measurement. It is shown that the ANN model does quite an excellent job and the predicted values are in good agreement with the measured values. Significance: Test time and measurement accuracy are extremely crucial. The ANN model proposed herein serves to reduce test time and improve data integrity to ensure cost efficiency and product quality.