A Deep Learning framework for simulation and defect prediction applied in microelectronics

Abstract

The prediction of upcoming events in industrial processes has been a longstanding research goal since it enables optimization of manufacturing parameters, planning of equipment maintenance and more importantly prediction and eventually prevention of defects. While existing approaches have accomplished substantial progress, they are mostly limited to processing of one dimensional signals or require parameter tuning to model environmental parameters. In this paper, we propose an alternative approach based on deep neural networks that simulates changes in the 3D structure of a monitored object in a batch based on previous 3D measurements. In particular, we propose an architecture based on 3D Convolutional Neural Networks (3DCNN) in order to model the geometric variations in manufacturing parameters and predict upcoming events related to sub-optimal performance. We validate our framework on a microelectronics use-case using the recently published "PCB scans" dataset where we simulate changes on the shape and volume of glue deposited on an Liquid Crystal Polymer (LCP) substrate before the attachment of integrated circuits (IC). Experimental evaluation examines the impact of different choices in the cost function during training and shows that the proposed method can be efficiently used for defect prediction.

Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns

“…We formulate the problem of finding the best augmentation policy as a discrete search problem. The operations we searched were rotation (5,10,15,20,25,30,35,40,45), flipping (horizontal and vertical), shifting (width and height), shearing range (horizontal and vertical), and zooming (1%-20%). In total, we have 46 operations in the search space.…”

“…As the fabrication process becomes more challenging and complicated, the number of defects increase. The processed wafer was tested using the fabrication process, detailed later on, and subsequently assisted in identifying several defects [10][11][12]. As semiconductor manufacturing becomes complicated, and the difficulty of the refined process techniques increases, a new type of wafer defect map appears.…”

Cost-Sensitive Siamese Network for PCB Defect Classification

“…In addition, Zhang et al [17] proposed a modified ResNet model with an adjustment layer attached to the end. Dimitriou et al [18] proposed an algorithm based on 3D convolutional neural networks (3DCNN) in order to predict upcoming events related to suboptimal performance in a manufacturing process. However, it focuses more on the prediction of upcoming events than scanning and filtering the existing defected boards.…”

A comparison of 2DCNN network architectures and boosting techniques for regression-based textile whiteness estimation

“…On the other hand, in recent years deep learning and convolutional networks have gained a lot of traction in quality control for Industry 4.0 [12] with several methods proposed for micro-electronics [13,14], metal parts manufacturing [15], visual inspection process in the printing [16], visual quality control automation on the assembly line [17], spectrophotometric color correction [18] and geometric deep lean learning to support sustainable organizational growth [19] among others.…”