An artificial neural network approach for screening test escapes

Lin, Fan; Cheng, Kwang-Ting

doi:10.1109/aspdac.2017.7858358

Cited by 9 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms are indeed able to detect complex correlations between variables, by, for instance, mapping measurements to circuit performances and identifying previously hidden faults when processing the results from (extra) measurements, as presented in this paper. There exist numerous works proving the efficiency of machine learning and deep learning algorithms to different test applications, such as fault detection [6,11,21,28,29,31,32,32,36,37], fault diagnosis and yield learning [15], test escape detection [19,27], or alternate testing and calibration [1-3, 20, 24]. The term alternate test refers to a cost-effective methodology where the complete test process is replaced by low-cost measurements, correlated to the actual performances of the circuit with machine learning algorithms [35].…”

Section: Machine Learning Techniques For Fault Detectionmentioning

confidence: 99%

“…Features can also be extracted using deep learning techniques. Encoders based on neural networks are popular among them, and have recently been used in the context of test escape detection [19,27]. Their principle is similar to PCA but enables to extract non-linear features.…”

Section: Classify Circuit Instances With Machine Learning Algorithmsmentioning

confidence: 99%

“…Instead of using PCA analysis to extract features, an encoder can be used. Combined with a neural network decoding the data, we obtain a complete autoencoder, which has been used recently in the context of testing [19,27]. We also applied the autoencoder to our case study, in order to evaluate if better features could be extracted to improve the performance of the algorithm.…”

Section: Comparison Of Feature Extractions and Machine Learning Algormentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning-based Defect Coverage Boosting of Analog Circuits under Measurement Variations

Xama

Andraud

Gomez

et al. 2020

ACM Trans. Des. Autom. Electron. Syst.

View full text Add to dashboard Cite

Safety-critical and mission-critical systems, such as airplanes or (semi-)autonomous cars, are relying on an ever-increasing number of embedded integrated circuits. Consequently, there is a need for complete defect coverage during the testing of these circuits, in order to guarantee their functionality in the field. In this context, reducing the escape rate of defects during production testing is crucial, and significant progress has been made to this end. However, production testing using automatic test equipment is subject to various measurement parasitic variations, which may have a negative impact on the testing procedure and therefore limit the final defect coverage. To tackle this issue, this paper proposes an improved test flow targeting increased analog defect coverage, both at system-and block-level, by analyzing and improving the coverage of typical functional and structural tests under these measurement variations. To illustrate the flow, the technique of inserting a pseudo-random signal at available circuit nodes and applying machine learning techniques to its response is presented. A DC-DC converter, derived from an industrial product, is used as a case study to validate the flow. In short, results show that system-level tests for the converter suffer strongly from the measurement variations and are limited to just under 80% coverage, even when applying the proposed test flow. Block-level testing, on the other hand, can achieve only 70% fault coverage without improvements, but is able to consistently achieve 98% of fault coverage at a cost of at most 2% yield loss with the proposed machine-learning based boosting technique. CCS Concepts: • Computing methodologies → Neural networks; • Hardware → Design for testability; Integrated circuits; Methodologies for EDA.

show abstract

Section: Machine Learning Techniques For Fault Detectionmentioning

confidence: 99%

Section: Classify Circuit Instances With Machine Learning Algorithmsmentioning

confidence: 99%

Section: Comparison Of Feature Extractions and Machine Learning Algormentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-based Defect Coverage Boosting of Analog Circuits under Measurement Variations

Xama

Andraud

Gomez

et al. 2020

ACM Trans. Des. Autom. Electron. Syst.

View full text Add to dashboard Cite

show abstract

A Convolutional Autoencoder Approach for Feature Extraction in Virtual Metrology

Maggipinto

Masiero

Beghi

et al. 2018

Procedia Manufacturing

View full text Add to dashboard Cite

End-to-end deep learning framework for printed circuit board manufacturing defect classification

Bhattacharya

Cloutier

2022

Sci Rep

View full text Add to dashboard Cite

We report a complete deep-learning framework using a single-step object detection model in order to quickly and accurately detect and classify the types of manufacturing defects present on Printed Circuit Board (PCBs). We describe the complete model architecture and compare with the current state-of-the-art using the same PCB defect dataset. These benchmark methods include the Faster Region Based Convolutional Neural Network (FRCNN) with ResNet50, RetinaNet, and You-Only-Look-Once (YOLO) for defect detection and identification. Results show that our method achieves a 98.1% mean average precision(mAP[IoU = 0.5]) on the test samples using low-resolution images. This is 3.2% better than the state-of-the-art using low-resolution images (YOLO V5m) and 1.4% better than the state-of-the-art using high-resolution images (FRCNN-ResNet FPN). While achieving better accuracies, our model also requires roughly 3× fewer model parameters (7.02M) compared with the state-of-the-art FRCNN-ResNet FPN (23.59M) and YOLO V5m (20.08M). In most cases, the major bottleneck of the PCB manufacturing chain is quality control, reliability testing and manual rework of defective PCBs. Based on the initial results, we firmly believe that implementing this model on a PCB manufacturing line could significantly increase the production yield and throughput, while dramatically reducing manufacturing costs.

show abstract

An artificial neural network approach for screening test escapes

Cited by 9 publications

References 20 publications

Machine Learning-based Defect Coverage Boosting of Analog Circuits under Measurement Variations

Machine Learning-based Defect Coverage Boosting of Analog Circuits under Measurement Variations

A Convolutional Autoencoder Approach for Feature Extraction in Virtual Metrology

End-to-end deep learning framework for printed circuit board manufacturing defect classification

Contact Info

Product

Resources

About