Fault coverage

About: Fault coverage is a research topic. Over the lifetime, 10153 publications have been published within this topic receiving 161933 citations. The topic is also known as: test coverage.

Compactor independent direct diagnosis

Abstract: In scan test environment, designs with embedded compression techniques can achieve dramatic reduction in test data volume and test application time. However, performing fault diagnosis with the reduced test data becomes a challenge. In this paper, we provide a general methodology based on circuit transformation technique that can be applied for performing fault diagnosis in the context of any compression technique. The proposed methodology enables seamless reuse of the existing standard ATPG based diagnosis infrastructure with compressed test data. Experimental results indicate that the diagnostic resolution of devices with embedded compression is comparable with that of devices without embedded compression.

Nuclear Power Plant Thermocouple Sensor-Fault Detection and Classification Using Deep Learning and Generalized Likelihood Ratio Test

Abstract: In this paper, an online fault detection and classification method is proposed for thermocouples used in nuclear power plants. In the proposed method, the fault data are detected by the classification method, which classifies the fault data from the normal data. Deep belief network (DBN), a technique for deep learning, is applied to classify the fault data. The DBN has a multilayer feature extraction scheme, which is highly sensitive to a small variation of data. Since the classification method is unable to detect the faulty sensor; therefore, a technique is proposed to identify the faulty sensor from the fault data. Finally, the composite statistical hypothesis test, namely generalized likelihood ratio test, is applied to compute the fault pattern of the faulty sensor signal based on the magnitude of the fault. The performance of the proposed method is validated by field data obtained from thermocouple sensors of the fast breeder test reactor.

Expert system framework for fault detection and fault tolerance in robotics

Abstract: Fault tolerance is of increasing importance for modern robots. The ability to detect and tolerate failures enables robots to effectively cope with internal failures and continue performing assigned tasks without the need for immediate human intervention. To monitor fault tolerance actions performed by lower level routines and to provide higher level information about a robot;s recovery capabilities, we present an expert system and critic which together form a novel and intelligent fault tolerance framework integrating fault detection and tolerance routines with dynamic fault tree analysis. A higher level, operating system inspired critic layer provides a buffer between robot fault tolerant operations and the user. The expert system gives the framework the modularity and flexibility to quickly convert between a variety of robot structures and tasks. It also provides a standard interface to the fault detection and tolerance software and a more intelligent means of monitoring the progress of failure and recovery throughout the robot system. The expert system further allows for prioritization of tasks so that recovery can take precedence over less pressing goals. Fault trees are used as a standard database to reveal the components essential to fault detection and tolerance within a system and detail the interconnection between failures in the system. The trees are also used quantitatively to provide a dynamic estimate of the probability of failure of the entire system or various subsystems.

High Performance Graph ConvolutionaI Networks with Applications in Testability Analysis

Abstract: Applications of deep learning to electronic design automation (EDA) have recently begun to emerge, although they have mainly been limited to processing of regular structured data such as images. However, many EDA problems require processing irregular structures, and it can be non-trivial to manually extract important features in such cases. In this paper, a high performance graph convolutional network (GCN) model is proposed for the purpose of processing irregular graph representations of logic circuits. A GCN classifier is firstly trained to predict observation point candidates in a netlist. The GCN classifier is then used as part of an iterative process to propose observation point insertion based on the classification results. Experimental results show the proposed GCN model has superior accuracy to classical machine learning models on difficult-to-observation nodes prediction. Compared with commercial testability analysis tools, the proposed observation point insertion flow achieves similar fault coverage with an 11% reduction in observation points and a 6% reduction in test pattern count.