An official website of the United States government
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. This paper describes a twophase, physically-aware diagnosis methodology called LearnX to improve the quality of diagnosis, and in turn the quality of design, test and manufacturing. The first phase attempts to diagnose a defect that manifests as a well-established fault behavior (e.g., stuck or bridge fault models). The second phase uses machine learning to build a model (separate for each defect type) that learns the characteristics of defect candidates to distinguish correct candidates from incorrect ones. Results from 30,000 fault injection experiments indicate that 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 state-of-the-art commercial diagnosis. Silicon experiments further demonstrate the value of LearnX.
more »
« less
Adaptive Test Pattern Reordering for Diagnosis using k-Nearest Neighbors
Logic diagnosis is a software-based methodology to identify the behavior and location of defects in failing integrated circuits, which is an essential step in yield learning. However, accurate diagnosis requires a sufficient amount of failing data, which is in contradiction to the requirement of reducing test time and cost. In this work, a dynamic test pattern reordering method is proposed to “recommend” which test patterns should be applied for a given failing chip, with the goal of maximizing failing data while minimizing test time. Unlike prior work that uses population statistics from already tested chips, this method uses a machine learning technique, namely k-Nearest Neighbors. Experiments using three industrial chips demonstrate the efficacy of the proposed methodology; specifically, the recommended test pattern order led to a 35% reduction, on average, while maximizing the amount of failure data collected.
more »
« less
- Award ID(s):
- 1816512
- PAR ID:
- 10249437
- Date Published:
- Journal Name:
- 2020 IEEE International Test Conference in Asia (ITC-Asia)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
Abstract The connectivity of modern vehicles allows for the monitoring and analysis of a large amount of sensor data from vehicles during their normal operations. In recent years, there has been a growing interest in utilizing this data for the purposes of predictive maintenance. In this paper, a multi-label transfer learning approach is proposed using 14 different pretrained convolutional neural networks retrained with engine simulation data to predict the failure conditions of a selected set of engine components. The retrained classifier networks are designed such that concurrent failure modes of an exhaust gas recirculation, compressor, intercooler, and fuel injectors of a four-cylinder diesel engine can be identified. Time-series simulation data of various failure conditions, which include performance degradation, are generated to retrain the classifier networks to predict which components are failing at any given time. The test results of the retrained classifier networks show that the overall classification performance is good, with the normalized value of mean average precision varying from 0.6 to 0.65 for most of the retrained networks. To the best of the authors’ knowledge, this work represents the first attempt to characterize such time-series data utilizing a multi-label deep learning approach.more » « less
-
Reliability of modern multicore and many-core chips is tightly coupled with the reliability of their on-chip networks. Communication channels in current Network-on-Chips (NoCs) are extremely susceptible to crosstalk faults. In this work, we propose a set of rules for generating classes of crosstalk free coding systems to protect communication channels in NoCs against crosstalk faults. Codewords generated through these rules are free of '101' and '010' bit patterns, which are the main sources of crosstalk faults in NoC communication channels. The proposed rules determine: (1) the weights of different bit positions in a coding system to reach crosstalk free codings, and (2) how the coding might be utilized in an NoC to prevent crosstalk generating bit patterns in NoC channels. Using the proposed set of rules, designers can obtain coding systems which are crosstalk free for any widths of communication channels. Compared to conventional Forbidden Pattern Free (FPF) systems, the proposed methodology is able to provide unique representation to any input values at the lower bound of the codeword lengths. Analyses show that the proposed rules, along with the proposed encoding/decoding mechanisms, are effective in preventing forbidden pattern coding systems for network-on-chips of any arbitrary channel width.more » « less
-
This paper presents a cost-effective, non-intrusive, and easy-to-deploy traffic count data collection method using two-dimensional light-detection and ranging (LiDAR) technology. The proposed method integrates a LiDAR sensor, continuous wavelet transform (CWT), and support vector machine (SVM) into a single framework for traffic count. LiDAR is adopted since the technology is economical and easily accessible. Moreover, its 360° visibility and accurate distance information make it more reliable compared with radar, which uses electromagnetic waves instead of light rays. The obtained distance data are converted into the signals. CWT is employed to detect any deviation in distance profile, because of its efficiency in detecting modest changes over a period of time. SVM is one of the supervised machine learning tools for data classification and regression. In the methodology, the SVM is applied to classify the distance data points obtained from the sensor into detection and non-detection cases, which are highly complex. Proof-of-concept (POC) test is conducted in three different places in Newark, New Jersey, to examine the performance of the proposed method. The POC test results demonstrate that the proposed method achieves acceptable performances in vehicle count collection, resulting in 83–94% accuracy. It is discovered that the accuracy of the proposed method is affected by the color of the exterior surface of a vehicle.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ITC-Asia51099.2020.00022
