Wafer Fault Research Articles

Identification of key features using topological data analysis for accurate prediction of manufacturing system outputs

Topological data analysis (TDA) has emerged as one of the most promising approaches to extract insights from high-dimensional data of varying types such as images, point clouds, and meshes, in an unsupervised manner. To the best of our knowledge, here, we provide the first successful application of TDA in the manufacturing systems domain. We apply a widely used TDA method, known as the Mapper algorithm, on two benchmark data sets for chemical process yield prediction and semiconductor wafer fault detection, respectively. The algorithm yields topological networks that capture the intrinsic clusters and connections among the clusters present in the data sets, which are difficult to detect using traditional methods. We select key process variables or features that impact the system outcomes by analyzing the network shapes. We then use predictive models to evaluate the impact of the selected features. Results show that the models achieve at least the same level of high prediction accuracy as with all the process variables, thereby, providing a way to carry out process monitoring and control in a more cost-effective manner.

Wafer fault detection and key step identification for semiconductor manufacturing using principal component analysis, AdaBoost and decision tree

In this paper, a data mining approach is presented to identify the key parameters and the key steps in the manufacture process. For key parameters, a principal component analysis (PCA) algorithm is first used to filter data before classification models of fault detection are established by using SVM and AdaBoost algorithms. A decision tree is then used to locate the key step for root cause identification. In the preliminary study in terms of a set of real wafer fabrication profile data in semiconductor manufacturing, the AdaBoost classifier with PCA has been shown the most effective in identifying key parameters in fault detection. Subsequently, these key parameters along with associated reading values at different timings were used to build a decision tree for the set of empirical rules to best identify problematic timing. It has been further verified that the critical timing among this set of empirical rules had occurred in the same manufacturing phase.

Probabilistic diagnosis of clustered faults for shared structures

The probabilistic diagnosis model is useful in many fields such as distributed network, digital system level testing and wafer fault testing. Some topologies and continuous defect units distributions are studied in our previous work. In this paper, we extend the model to arbitrary topology structure with share nodes and to the discrete defect distributions, such as Poission distribution and Binomial distribution. The results show high identification percentage of the nodes.

Decomposition in data mining: an industrial case study

Data mining offers tools for discovery of relationships, patterns, and knowledge in large databases. The knowledge extraction process is computationally complex and therefore a subset of all data Is normally considered for mining. In this paper, numerous methods for decomposition of data sets are discussed. Decomposition enhances the quality of knowledge extracted from large databases by simplification of the data mining task. The ideas presented are illustrated with examples and an industrial case study. In the case study reported in this paper, a data mining approach is applied to extract knowledge from a data set. The extracted knowledge is used for the prediction and prevention of manufacturing faults in wafers.

Wafer fault measurement by coherent optical processor

A microscope coherent optical processor based on the VanderLugt optical correlator is applied to the measurement of registration error in multilayer integrated-circuit wafers. A treatment of the effects of wafer faults on the correlation signal is given. Threshold criteria and fault-induced peak splitting of the correlation signal from reject production samples are exploited to demonstrate the easy and rapid detection of faults in partially processed integrated-circuit wafers.

SC-net: A hybrid connectionist, symbolic system

This paper describes the SC-net system that has been developed to provide expert systems capability augmented with learning in a hybrid connectionist/symbolic approach. A distributed connectionist representation of cells connected by links is used to represent symbolic knowledge. Rules may be directly encoded in the connectionist network or learned from examples. The learning method is a form of instance-based learning in which some of the individual instances in the training set are encoded by adding structure to the network and others cause modifications to biases in the network. Both continuous and nominal attributes are directly represented in the network structure. A limited form of variables in the form of attribute value bindings on the right-hand side of rules is supported. Relational comparators in the form of cell groups are also supported. Relational comparators and attribute value structures are represented by groups of connected cells in the network. The learning algorithm is presented and methods for providing generalization in an instance-based connectionist environment are presented. Empirical results are presented, which include learning in domains (fevers and gems) that contain uncertainty and the well-known iris, and soybean data sets together with a real world domain for semiconductor wafer fault diagnosis. The generalization ability of the learned network is shown to be good in several domains including iris. The system is shown to compare favorably with a nonneural instance-based learning algorithm IBL.