Machine Learning Based Detection Method for Wafer Test Induced Defects
Abstract : ? Wafer test is carried out after integrated circuits (IC) fabrication to screen out bad dies.
? In addition, the results can be used to identify problems in the fabrication process and improve manufacturing yield.
? However, the wafer test itself may induce defects to otherwise good dies.
? Test-induced defects not only hurt overall manufacturing yield but also create problems for yield learning, so the source problems in testing should be identified quickly.
? In the wafer acceptance test process, dies are probed in a predetermined order, so test-induced defects, also known as site-dependent faults, exhibit specific patterns that can be effectively captured in test paths.
? In this paper, we analyze characteristics of test-induced defect patterns and define features that can be used by machine learning algorithms for the automatic detection of test-induced defects.
? Therefore, defective dies caused by the wafer test can be retested for yield improvement.
? Test data from six real products are used to validate the proposed method. Several machine learning algorithms have been applied, and experimental results show that our method is effective to distinguish between test-induced and fabrication-induced defects.
? On average, the prediction accuracy is higher than 97%.
? If necessary, the wafer images are first separated into their chips. Afterwards, a localization of the separated chips takes place according to their position inside the wafer, i.e. the system separates the chips into inside and outside the wafer situated ones, including chips on the wafer border and beyond.
? In order to be able to counteract possible lower occurrences of individual error classes, we balanced all occurring classes.
? Afterwards, the chips are classified into inside and outside situated chips, as they are depending on the wafer border.
? This step is realized via convolutional neural network
? To impose sparsity on the matrix, its rank is always used as a minimization objective function.
? An intuitive analogy of rank is the Lo norm for a vector, which is the number of non-zero entries in a vector.
? Automatic defect detection is a fundamental and vital topic in the research field of industrial intelligence.
? In this work, the authors develop a more flexible deep learning method for the industrial defect detection.
? The performance of the proposed method is demonstrated by detecting faults in plasma etch.
? This method is further improved by combining with principle component analysis in to handle large-scale data. A semi-supervised one-class SVM is used in to detect faults in reactive ion etching (RIE) systems.
|