Enhancing Fault Detection in Digital Circuits Using Machine Learning and LFSR-Based Test Pattern Generation
DOI:
https://doi.org/10.22399/ijcesen.3231Keywords:
Fault detection, LFSR-linear feedback shift Register, Test pattern Generation, Random Forest classifierAbstract
For digital circuits, such as half adders, full adders, and other combinational logic gates, to be reliable, fault detection and test pattern creation are essential. This work introduces a novel method for effectively detecting faults in logic gates by combining machine learning (ML) with test pattern creation based on Linear Feedback Shift Registers (LFSR). Traditional methods for generating deterministic test patterns can be laborious and might not translate well to intricate circuits. In order to solve this, we use fault-injected datasets to apply a Random Forest Classifier (RFC) to categorize faults like Stuck-at-0 (SA0) and Stuck-at-1 (SA1). Comprehensive fault analysis is made possible by the LFSR-generated test patterns, which are inputs to circuits such as half adders and full adders. With a loss function of less than 1% and an R2 score of 99%, the trained ML model detects defects with accuracy. For complicated digital circuits, the combination of ML and LFSR-based test generation improves fault coverage, lowers computational overhead, and offers an effective Design-for-Test (DFT) method.
References
[1] J. Shi, W. Chen and H. Zhou, "Research on Design for Testability and Evaluation System
Based on Systems Modeling Language," 2024 Global Reliability and Prognostics and Health Management Conference (PHM-Beijing), Beijing, China, 2024, pp. 01-08, doi: 10.1109/PHM-Beijing63284.2024.10874508.
[2] H. Fujiwara and T. Shimono, "On the Acceleration of Test Generation Algorithm," IEEE Transactions on Computers, vol. C-32,
no. 12, pp. 1137–1144, Dec. 1983, doi:
10.1109/TC.1983.1676269.
[3] A. K. Goel and S. Dey, "Machine LearningBased Test Pattern Generation for Logic Fault
Detection," IEEE Transactions on ComputerAided Design of Integrated Circuits and Systems, vol. 39, no. 12, pp. 4621–4633, Dec. 2020, doi: 10.1109/TCAD.2020.2999148.
[4] Y. Lei, F. Jia, J. Lin, S. Xing, and S. X. Ding, "An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data," IEEE Transactions on
Industrial Electronics, vol. 63, no. 5, pp. 3137–
3147, May 2016, doi:
10.1109/TIE.2016.2522863.
[5] M. Chen, Y. Liu, and K. Zhang, "Fault Detection in Industrial Processes Using Random Forests," IEEE Transactions on Industrial Informatics, vol. 14, no. 4, pp. 1583–1591, Apr. 2018, doi:
10.1109/TII.2017.2759502.
[6] J. R. Arora and M. Sharma, "Random ForestBased Fault Classification for LFSR-Generated Test Patterns," IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 29, no. 8, pp. 1507–1518, Aug. 2021, doi:
10.1109/TVLSI.2021.3071158.
[7] M. Sridharan and H. Patel, "Built-In Self-Test
Using LFSR and Machine Learning-Based Classifiers," IEEE Transactions on
Instrumentation and Measurement, vol. 70, pp.
1–10, 2021, Art no. 9507112, doi: 10.1109/TIM.2021.3051345.
[8] J. V. Carreira, D. Costa, and S. J. G., "Fault Injection Spot-Checks Computer System Dependability," IEEE Spectrum, vol. 36, no. 6, pp. 50–55, Jun. 1999.
[9] Y. Lee and C. Wang, "Classification and
Diagnosis of Logic Gate Faults Using Ensemble Learning," IEEE Transactions on Reliability, vol. 70, no. 3, pp. 987–998, Sept. 2021, doi: 10.1109/TR.2020.3034937.
[10] Y. Zorian, S. Dey, and C. Secord, “Test program generation for LFSR‐based BIST,” in Proc. IEEE VLSI Test Symposium (VTS), Napa, CA, USA, 1994, pp. 203–208, doi: 10.1109/VTS.1994.311483.
[11] Qianyu Huang and Tongfang Zhao, "Data Collection and Labeling Techniques for Machine Learning," arXiv preprint arXiv:2407.12793, Jun. 2024.
[12] T. Ubertini, A. Toma, and E. Macii, “DeviceLevel Fault Simulation and Classification in VLSI Circuits Using Random Forests,” IEEE Transactions on Computer‐Aided Design of Integrated Circuits and Systems, vol. 37, no. 4, pp. 765–777, Apr. 2018, doi:
10.1109/TCAD.2017.2789045.
[13] Y. Zhang, J. D. M. E. S. "A Comparative Study on Machine Learning Algorithms in Python using Scikit-learn," International Journal of Computer Applications, vol. 178, no.
18, pp. 17–23, May 2021, doi:
10.5120/ijca2021921423.
[14] N. Choudhary, S. Bhatnagar, and A. Arora, "Implementation of Machine Learning
Techniques in Python: A Case Study on Scikitlearn," Proceedings of the International Conference on Computing, Communication, and Intelligent Systems, pp. 232–241, 2018, doi: 10.1109/CCIS.2018.00060.
[15] P. Girard and S. Pravossoudovitch, “Polynomial-Based Test Vector Mapping for LFSR-Generated Patterns,” IEEE Transactions on Very Large Scale Integration (VLSI)
Systems, vol. 12, no. 6, pp. 628–638, Jun. 2004, doi: 10.1109/TVLSI.2004.829236.
[16] Y. Zhang, L. Wang, and X. Li, "Fault Diagnosis of Rotating Machinery Using Random Forest Algorithm," IEEE Transactions on Industrial Electronics, vol. 65, no. 5, pp.
4290–4298, May 2018, doi:
10.1109/TIE.2017.2764842.
[17] S. S. S. J. Y. S. "F1-Score: A Robust Performance Metric for Text Classification," IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 6, pp. 1865–1877, Jun. 2021, doi: 10.1109/TKDE.2020.3033151.
[18] V. R. B. A. H. M. C. A. S. M. "Analyzing Classification Performance with Confusion
Matrix," IEEE Transactions on Artificial Intelligence, vol. 6, no. 3, pp. 251–261, Mar. 2021, doi: 10.1109/TAI.2020.3032341.
[19] S. Bregni, M. Carbonelli, D. De Seta, and D. Perucchini, ‘‘Impact of slave clock internal noise on Allan variance and root mean square time interval error measurements,’’ in Proc. IEEE Instrum. Meas. Technol. Conf. (IMTC),
May 1994, pp. 1411–1414, doi:
10.1109/IMTC.1994.352160.
[20] A. C. Cameron and F. A. Windmeijer, ‘‘An R-squared measure of goodness of fit for some common nonlinear regression models,’’ J. Econ., vol. 77, no. 2, pp. 329–342, 1997, doi:
10.1016/S0304-4076(96)01818-0.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
