AI Models for Supporting SI Analysis on PCB Net Structures: Comparing Linear and Non-Linear Data Sources
Julian Withöft
CORRESPONDING AUTHOR
TU Dortmund/Information Processing Lab, Otto-Hahn-Straße 4, 44227 Dortmund, Germany
Werner John
Pyramide 2525, Doerener Weg 4B, 33100 Paderborn, Germany
Emre Ecik
TU Dortmund/Information Processing Lab, Otto-Hahn-Straße 4, 44227 Dortmund, Germany
Ralf Brüning
EMC Technology Center/Zuken GmbH, Am Hoppenhof 30, 33104 Paderborn, Germany
Jürgen Götze
TU Dortmund/Information Processing Lab, Otto-Hahn-Straße 4, 44227 Dortmund, Germany
Related authors
Emre Ecik, Werner John, Julian Withöft, and Jürgen Götze
Adv. Radio Sci., 21, 37–48, https://doi.org/10.5194/ars-21-37-2023, https://doi.org/10.5194/ars-21-37-2023, 2023
Short summary
Short summary
The implementation of an anomaly detection with a decision tree was investigated with respect to the evaluation of selected SI effects in PCB design. The tree based approach allows the designer to understand the proposals more easily (explainable AI). High prediction accuracies for two simple networks were achieved with the proposed method. The use of anomaly detection with a decision tree will be further developed in future work for various more complex SI applications in circuit design.
Emre Ecik, Werner John, Julian Withöft, and Jürgen Götze
Adv. Radio Sci., 21, 37–48, https://doi.org/10.5194/ars-21-37-2023, https://doi.org/10.5194/ars-21-37-2023, 2023
Short summary
Short summary
The implementation of an anomaly detection with a decision tree was investigated with respect to the evaluation of selected SI effects in PCB design. The tree based approach allows the designer to understand the proposals more easily (explainable AI). High prediction accuracies for two simple networks were achieved with the proposed method. The use of anomaly detection with a decision tree will be further developed in future work for various more complex SI applications in circuit design.
Nima Ghafarian Shoaee, Zouhair Nezhi, Werner John, Ralf Brüning, and Jürgen Götze
Adv. Radio Sci., 21, 49–55, https://doi.org/10.5194/ars-21-49-2023, https://doi.org/10.5194/ars-21-49-2023, 2023
Short summary
Short summary
The effects of parameters (decaps, power plane and stackup) affecting the input impedance of a power delivery network are investigated. An artificial neural network is trained using the generated data utilizing a process to generate suitable input for training a machine learning module, which is able to predict the impedance profile of the PDN. In order to obtain a more accurate prediction, Bayesian optimization is implemented and the results are compared to commercial power integrity software.
Patrick Jansen, Michael Vollnhals, Daniel Renner, David Vergossen, Werner John, and Jürgen Götze
Adv. Radio Sci., 14, 55–62, https://doi.org/10.5194/ars-14-55-2016, https://doi.org/10.5194/ars-14-55-2016, 2016
Short summary
Short summary
Further improvements on the novel method for state of charge (SOC) determination of lithium iron phosphate (LFP) cells based on the impedance spectra classification are presented.
Daniel Renner, Patrick Jansen, David Vergossen, Werner John, and Stephan Frei
Adv. Radio Sci., 14, 77–83, https://doi.org/10.5194/ars-14-77-2016, https://doi.org/10.5194/ars-14-77-2016, 2016
Short summary
Short summary
Continuously increasing requirements for onboard
system performances lead to new topologies for the
energy distribution in vehicles. One promising concept is the
usage of a dual-battery system instead of the conventional
lead-acid battery. The conventional performance estimation
method for standalone lead-acid batteries can no
longer be applied to this system. Therefore, a new algorithm
for the voltage drop calculation of the dual-battery system
is proposed.
David Krause, Werner John, and Robert Weigel
Adv. Radio Sci., 13, 269–278, https://doi.org/10.5194/ars-13-269-2016, https://doi.org/10.5194/ars-13-269-2016, 2016
Short summary
Short summary
The implementation of electrical drive trains in modern vehicles is a new challenge for EMC development. One crucial issue is the appearance of magnetic fields, which need to be limited due to legal regulations. This contribution therefore depicts a variety of investigations on magnetic field coupling of automotive high-voltage systems. Within the scope of a comprehensive analysis decisive influence quantities are stated and design rules with regard to minimized magnetic fields are discussed.
P. Jansen, D. Vergossen, D. Renner, W. John, and J. Götze
Adv. Radio Sci., 13, 127–132, https://doi.org/10.5194/ars-13-127-2015, https://doi.org/10.5194/ars-13-127-2015, 2015
Short summary
Short summary
New method for determining the state of charge on lithium iron phosphate cells using frequency domain data.
M. Lechtenberg, J. Götze, K. Görner, and C. Rehtanz
Adv. Radio Sci., 12, 43–48, https://doi.org/10.5194/ars-12-43-2014, https://doi.org/10.5194/ars-12-43-2014, 2014
J. Geldmacher and J. Götze
Adv. Radio Sci., 12, 187–195, https://doi.org/10.5194/ars-12-187-2014, https://doi.org/10.5194/ars-12-187-2014, 2014
M. Kühn, W. John, and R. Weigel
Adv. Radio Sci., 12, 83–89, https://doi.org/10.5194/ars-12-83-2014, https://doi.org/10.5194/ars-12-83-2014, 2014
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org/ (last access: 18 October 2023), 2015. a
Analog Devices: LTspice XVII, https://www.analog.com/en/design-center/design-tools-and-calculators/ltspice-simulator.html (last access: 18 October 2023), a
Bäck, T. and Schwefel, H.-P.: An Overview of Evolutionary Algorithms for Parameter Optimization, Evol. Comput., 1, 1–23, https://doi.org/10.1162/evco.1993.1.1.1, 1993. a
Blank, J. and Deb, K.: pymoo: Multi-Objective Optimization in Python, IEEE Access, 8, 89497–89509, https://doi.org/10.1109/ACCESS.2020.2990567, 2020. a
Chen, S., Chen, J., Zhang, T., and Wei, S.: Semi-Supervised Learning Based on Hybrid Neural Network for the Signal Integrity Analysis, IEEE T. Circuits. Syst. II: Express Briefs, 67, 1934–1938, https://doi.org/10.1109/TCSII.2019.2948527, 2020. a
Chollet, F.: Keras [code], https://keras.io (last access: 18 October 2023), 2015. a
Deb, K., Sindhya, K., and Okabe, T.: Self-Adaptive Simulated Binary Crossover for Real-Parameter Optimization, GECCO '07, 1187–1194, Association for Computing Machinery, New York, NY, USA, https://doi.org/10.1145/1276958.1277190, 2007. a
Ecik, E., John, W., Withöft, J., and Götze, J.: Anomaly Detection with Decision Trees for AI Assisted Evaluation of Signal Integrity on PCB Transmission Lines, 20, submitted to Advances in Radio Science, 2023. a
Frazier, P. I.: A Tutorial on Bayesian Optimization, arXiv [preprint], https://doi.org/10.48550/arxiv.1807.02811, 8 July 2018. a
Goldberg, D. E.: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, New York, NY, USA, ISBN: 978-0-201-15767-3, 1989. a
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press, Cambridge, MA, USA, ISBN: 978-0-262-03561-3, 2016. a
John, W., Withöft, J., Ecik, E., Brüning, R., and Götze, J.: A Practical Approach Based on Machine Learning to Support Signal Integrity Design, in: 2022 International Symposium on Electromagnetic Compatibility – EMC Europe, 623–628, https://doi.org/10.1109/EMCEurope51680.2022.9901213, 2022. a, b, c, d, e
Kim, H., Sui, C., Cai, K., Sen, B., and Fan, J.: Fast and Precise High-Speed Channel Modeling and Optimization Technique Based on Machine Learning, IEEE T. Electromagn. C., 60, 2049–2052, https://doi.org/10.1109/TEMC.2017.2782704, 2018. a, b
Lu, T., Sun, J., Wu, K., and Yang, Z.: High-Speed Channel Modeling With Machine Learning Methods for Signal Integrity Analysis, IEEE T. Electromagn. C., 60, 1957–1964, https://doi.org/10.1109/TEMC.2017.2784833, 2018. a, b, c
Ma, H., Li, E.-P., Cangellaris, A. C., and Chen, X.: High-Speed Link Design Optimization Using Machine Learning SVR-AS Method, in: 2020 IEEE 29th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS), 1–3, https://doi.org/10.1109/EPEPS48591.2020.9231368, 2020a. a
Ma, H., Li, E.-P., Cangellaris, A. C., and Chen, X.: Support Vector Regression-Based Active Subspace (SVR-AS) Modeling of High-Speed Links for Fast and Accurate Sensitivity Analysis, IEEE Access, 8, 74339–74348, https://doi.org/10.1109/ACCESS.2020.2988088, 2020b. a
Ma, H., Li, E.-P., Wang, Y., Shi, B., Schutt-Aine, J., Cangellaris, A., and Chen, X.: Channel Inverse Design Using Tandem Neural Network, in: 2022 IEEE 26th Workshop on Signal and Power Integrity (SPI), 1–3, https://doi.org/10.1109/SPI54345.2022.9874935, 2022. a
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E.: Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res., 12, 2825–2830, 2011. a
Roy, K., Dolatsara, M. A., Torun, H. M., Trinchero, R., and Swaminathan, M.: Inverse Design of Transmission Lines with Deep Learning, in: 2019 IEEE 28th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS), 1–3, https://doi.org/10.1109/EPEPS47316.2019.193220, 2019. a, b
Trinchero, R., Dolatsara, M. A., Roy, K., Swaminathan, M., and Canavero, F. G.: Design of High-Speed Links via a Machine Learning Surrogate Model for the Inverse Problem, in: 2019 Electrical Design of Advanced Packaging and Systems (EDAPS), 1–3, https://doi.org/10.1109/EDAPS47854.2019.9011627, 2019. a
Zhang, H. H., Xue, Z. S., Liu, X. Y., Li, P., Jiang, L., and Shi, G. M.: Optimization of High-Speed Channel for Signal Integrity With Deep Genetic Algorithm, IEEE T. Electromagn. C., 64, 1270–1274, https://doi.org/10.1109/TEMC.2022.3161298, 2022. a, b
Zhang, T., Chen, S., Wei, S., and Chen, J.: A Data-Efficient Training Model for Signal Integrity Analysis based on Transfer Learning, in: 2019 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), 186–189, https://doi.org/10.1109/APCCAS47518.2019.8953103, 2019. a
Zuken: CADSTAR Version 2021.0, Zuken [software], https://www.ecadstar.com/en/product/cadstar (last access: 18 October 2023), 2021a. a
Zuken: eCADSTAR Version 2021.1, Zuken [software], https://www.ecadstar.com/en/ (last access: 18 October 2023), 2021b. a
Short summary
In this paper, a two-stage artificial intelligence framework for supporting the signal integrity compliant printed circuit board design process has been developed. This framework was applied to compare linear and non-linear data, which showed that the non-linear data source gains advantages over the linear data in terms of attainable regression accuracy. For the investigated application however, the linear model can be utilized directly or by utilizing transfer learning for adequate results.
In this paper, a two-stage artificial intelligence framework for supporting the signal integrity...