More Like this

1. Learning Enhanced Diagnosis of Logic Circuit Failures

   Mittal, Soumya; Blanton, Ronald D. (May 2019, Proceedings - European Test Workshop)

   Software-based diagnosis analyzes the observed response of a failing circuit to pinpoint potential defect locations and deduce their respective behaviors. It plays a crucial role in finding the root cause of failure, and subsequently facilitates yield analysis, learning and optimization. A two-phase, physically-aware diagnosis methodology called LearnX is developed to improve the quality of diagnosis, and in turn the quality of design, test and manufacturing. In the first phase, a set of deterministic rules are created to identify defects that manifests as well-established fault behaviors. The second phase uses machine learning to build a model that learns the characteristics of defect candidates to distinguish correct candidates from incorrect ones. Results from 30,000 fault injection experiments indicate that LearnX achieves a resolution of one for 75.6% of the injected faults, showing an improvement of 39.0% over state-of-the-art commercial diagnosis. Additionally, the average ideal accuracy of LearnX is 95.7%, which is 27.2% higher than commercial diagnosis. More importantly, LearnX returns an ideal diagnosis result (i.e., a single candidate correctly representing the injected fault) for 73.2% of faulty circuits, which is 86.6% higher than commercial diagnosis. Silicon experiments further demonstrate the value of LearnX. 

   more » « less
2. DeepFL: integrating multiple fault diagnosis dimensions for deep fault localization

   https://doi.org/10.1145/3293882.3330574  

   Li, Xia; Li, Wei; Zhang, Yuqun; Zhang, Lingming (January 2019, ACM SIGSOFT International Symposium on Software Testing and Analysis)

   Learning-based fault localization has been intensively studied recently. Prior studies have shown that traditional Learning-to-Rank techniques can help precisely diagnose fault locations using various dimensions of fault-diagnosis features, such as suspiciousness values computed by various off-the-shelf fault localization techniques. However, with the increasing dimensions of features considered by advanced fault localization techniques, it can be quite challenging for the traditional Learning-to-Rank algorithms to automatically identify effective existing/latent features. In this work, we propose DeepFL, a deep learning approach to automatically learn the most effective existing/latent features for precise fault localization. Although the approach is general, in this work, we collect various suspiciousness-value-based, fault-proneness-based and textual-similarity-based features from the fault localization, defect prediction and information retrieval areas, respectively. DeepFL has been studied on 395 real bugs from the widely used Defects4J benchmark. The experimental results show DeepFL can significantly outperform state-of-the-art TraPT/FLUCCS (e.g., localizing 50+ more faults within Top-1). We also investigate the impacts of deep model configurations (e.g., loss functions and epoch settings) and features. Furthermore, DeepFL is also surprisingly effective for cross-project prediction. 

   more » « less
3. A hierarchical deep learning framework for combined rolling bearing fault localization and identification with data fusion

   https://doi.org/10.1177/10775463221091601  

   Liang, Mingxuan; Zhou, Kai (April 2022, Journal of Vibration and Control)

   Fault diagnosis of rolling bearings becomes an important research subject, where the data-driven deep learning-based techniques have been extensively exploited. While the state-of-the-art research has shown the substantial progresses in bearing fault diagnosis, they mostly were implemented upon the hypothesis that the location of bearing prone to failure already is known. Nevertheless, in actual practice many rolling bearings are installed in a complex machinery system, any of which is likely subject to fault. As such, fault diagnosis essentially is a process to achieve both fault localization and identification, which results in many fault scenarios to be handled. This will significantly degrade the fault diagnosis performance using conventional deep learning analysis. In this research, we aim to develop a new deep learning framework to address abovementioned challenge. We particularly design a hierarchical deep learning framework consisting of multiple sequentially deployed deep learning models built upon the transfer learning. This can improve the learning adequacy for a high-dimensional problem with many fault scenarios involved even under limited dataset, thereby enhancing the fault diagnosis performance. Without the prior knowledge regarding the fault location, this methodology is greatly favored by the sensor/data fusion which takes full advantage of the enriched pivot fault-related features in the measurements acquired from different accelerometers. Systematic case studies using the publicly accessible experimental rolling bearing dataset are carried out to validate this new methodology. 

   more » « less
4. Diagnostic Test Generation that Addresses Diagnostic Holes

   Pomeranz, I (January 2018, IEEE transactions on computer-aided design of integrated circuits and systems)

   A diagnostic test generation procedure targets fault pairs in a set of target faults with the goal of distinguishing all the fault pairs. When a fault pair cannot be distinguished, it prevents the diagnostic test set from providing information about the faults, and consequently, about defects whose diagnosis would have benefited from a diagnostic test for the indistinguishable fault pair. This is referred to in this paper as a diagnostic hole. The paper observes that it is possible to address diagnostic holes by targeting different but related fault pairs, possibly from a different fault model. As an example, the paper considers the case where diagnostic test generation is carried out for single stuck-at faults, and related bridging faults are used for addressing diagnostic holes. Considering fault detection, an undetectable single stuck-at fault implies that certain related bridging faults are undetectable. The paper observes that, even if a pair of single stuck-at faults is indistinguishable, a related pair of bridging faults may be distinguishable. Based on this observation, diagnostic tests for pairs of bridging faults are added to a diagnostic test set when the related single stuck-at faults are indistinguishable. Experimental results of defect diagnosis for defects that do not involve bridging faults demonstrate the importance of eliminating diagnostic holes. 

   more » « less
5. A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection

   https://doi.org/10.1109/ICPHM.2019.8819385  

   Jin, Baihong; Chen, Yuxin; Li, Dan; Poolla, Kameshwar; Sangiovanni-Vincentelli, Alberto (June 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM))

   Early detection of incipient faults is of vital im- portance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types. 

   more » « less