| Peer-Reviewed

Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits

Received: 12 August 2021     Accepted: 21 August 2021     Published: 31 August 2021
Views:       Downloads:
Abstract

With heritage in nonlinear adaptive control (as proposed by Slotine) and physics-based control (as proposed by Lorenz), recently proposed methods referred to as deterministic artificial intelligence (D.A.I.) claim slight performance improvement over the parent methods. This brief communication firstly validates claims of slight improvement, but furthermore highlights a key feature: indications that improvements in observer implementations are the proper path for subsequent development in the field. The manuscript validates the recently published 97% performance improvement over classical methods using nonlinear adaptive methods, with an addition 0.23% performance improvement using D.A.I. compared to nonlinear adaptive control. Furthermore, the work also identifies strong correlation between system performance and observer performance, which is significant since D.A.I. eliminates controller tuning. Thus, observer improvement is recommended for future developments. The recently published 2-norm optimal learning scheme (of Smeresky) is recommended as the next step in the lineage of research in the discipline assuming augmentation with nonlinear state observers.

Published in Control Science and Engineering (Volume 5, Issue 1)
DOI 10.11648/j.cse.20210501.12
Page(s) 13-19
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2021. Published by Science Publishing Group

Keywords

Deterministic Artificial Intelligence, D.A.I., Van Der Pol, Adaptive Control, Physics-Based Controls, State Observers, Luenberger Observers

References
[1] Smeresky, B.; Rizzo, A.; Sands, T. Optimal Learning and Self-awareness versus PDI. Algorithms 2020, 13 (1), 23.
[2] Lobo, K.; Lang, J.; Starks, A.; Sands, T. Analysis of Deterministic Artificial Intelligence for Inertia Modifications and Orbital Disturbance. Int. J. Control Sci. Eng. 2018, 8, 53.
[3] Sands, T. Development of deterministic artificial intelligence for unmanned underwater vehicles (UUV). J. Mar. Sci. Eng. 2020, 8 (8), 578.
[4] Sands, T.; Bollino, K.; Kaminer, I.; Healey, A. Autonomous Minimum Safe Distance Maintenance from Submersed Obstacles in Ocean Currents. J. Mar. Sci. Eng. 2018, 6 (3), 98.
[5] Cooper, M.; Heidlauf, P.; Sands, T. Controlling Chaos—Forced van der Pol Equation. Mathematics 2017, 5 (4), 70.
[6] Slotine, J., Weiping Li. Applied Nonlinear Control. Prentice Hall: Englewood Cliffs, U.S.A, 1991; pp. 422-433.
[7] Sands, T.; Lorenz, R. Physics-Based Automated Control of Spacecraft. In Proceedings of the AIAA Space Conference & Exposition, Pasadena, CA, USA, 14–17 September 2009.
[8] Kang, Ye Gu & Reigosa, David & Lorenz, Robert. (2020). SPMSMs HFI Based Self-Sensing Using Intentional Magnetic Saturation. IEEE Access. PP. 1-1. 10.1109/ACCESS.2020.3045275.
[9] Kang, Ye Gu & Reigosa, David & Sarlioglu, Bulent & Lorenz, Robert. (2020). D and Q-axes Inductance Estimation and Self-Sensing Condition Monitoring using 45 Angle High-Frequency Injection. IEEE Transactions on Industry Applications. PP. 1-1. 10.1109/TIA.2020.3029993.
[10] Alvi, Muhammad & Sheng, Minhao & Lorenz, Robert & Jahns, Thomas. (2020). Power Module Design for Integrated Three-Phase Current Sensing Using a Single 3-D Point Field Detector. 3328-3335. 10.1109/ECCE44975.2020.9235335.
[11] Alvi, Muhammad & Sheng, Minhao & Lorenz, Robert & Jahns, Thomas. (2020). SiC Power Module Design for High Bandwidth Integrated Current Sensing using a Magnetoresistive Point Field Detector. 1506-1512. 10.1109/APEC39645.2020.9124383.
[12] Polom, Timothy & Lorenz, Robert. (2020). Expediting Transient Thermal Frequency Response Characterization and Sensitivity Analysis. 10.1109/ECCE44975.2020.9235671.
[13] Polom, Timothy & Lorenz, Robert. (2020). Spatial Thermal Frequency Response Measurement of Power Semiconductor Equipment.
[14] Polom, Timothy & Van der Broeck, Christoph & Doncker, Rik & Lorenz, Robert. (2020). Designing Power Module Health Monitoring Systems Based on Converter Load Profile. IEEE Transactions on Industry Applications. PP. 1-1. 10.1109/TIA.2020.3023070.
[15] Sheng, Minhao & Alvi, Muhammad & Lorenz, Robert. (2020). GMR-based Integrated Current Sensing in SiC Power Modules with Phase Shift Error Reduction. IEEE Journal of Emerging and Selected Topics in Power Electronics. PP. 1-1. 10.1109/JESTPE.2020.3028275.
[16] Van der Broeck, Christoph & Polom, Timothy & Lorenz, Robert & Doncker, Rik. (2020). Real-Time Monitoring of Thermal Response and Life-Time Varying Parameters in Power Modules. IEEE Transactions on Industry Applications. PP. 1-1. 10.1109/TIA.2020.3001524.
[17] Zhu, Guangqi & Lorenz, Robert & Wan, Cheng. (2020). Optimization of “I” Type Shielding for Low Air-Gap Magnetic and Electric Fields Inductive Wireless Power Transfer. 1208-1213. 10.1109/ITEC48692.2020.9161730.
[18] Zhu, Guangqi & Lorenz, Robert & Diao, Fei & Zhao, Yue. (2020). Low Loss Online Capacitor Tuning Method for Reactive Power Reduction of Inductive Wireless Power Transfer System Under Misalignment. 961-965. 10.1109/ITEC48692.2020.9161382.
[19] Imamura, Ryoko & Lorenz, Robert. (2020). Stator Winding MMF Analysis for Variable Flux and Variable Magnetization Pattern-PMSMs. IEEE Transactions on Industry Applications. PP. 1-1. 10.1109/TIA.2020.2981605.
[20] Xu, Yang & Morito, Chikara & Lorenz, Robert. (2020). Accurate Discrete-Time Modeling for Improved Torque Control Accuracy for Induction Machine Drives at Very Low Sampling-to-Fundamental Frequency Ratios. IEEE Transactions on Transportation Electrification. PP. 1-1. 10.1109/TTE.2020.2977204.
[21] Flieh, Huthaifa & Slininger, Timothy & Lorenz, Robert & Totoki, Eigo. (2020). Self-Sensing via Flux Injection With Rapid Servo Dynamics Including a Smooth Transition to Back-EMF Tracking Self-Sensing. IEEE Transactions on Industry Applications. PP. 1-1. 10.1109/TIA.2020.2970150.
[22] Petit, Marc & Lorenz, Robert & Gagas, Brent & Secrest, Caleb & Sarlioglu, Bulent. (2019). Spatial Deadbeat Torque Control for Six-Step Operation. 10.1109/ECCE.2019.8912507.
[23] Petit, Marc & Sarlioglu, Bulent & Lorenz, Robert & Gagas, Brent & Secrest, Caleb. (2019). Using Flux and Current for Robust Wide-Speed Operation of IPMSMs. 10.23919/EPE.2019.8915510.
[24] Petit, Marc & Sarlioglu, Bulent & Lorenz, Robert & Van der Broeck, Christoph. (2019). Carrier Separation Techniques for Improved Disturbance Rejection of Injection-Based Self-Sensing Control. 10.1109/SLED.2019.8896264.
[25] Slininger, Timothy & Petit, Marc & Flieh, Huthaifa & Chien, Shao-Chuan & Ku, Li-Hsing & Lorenz, R.. (2019). Full Order Discrete-Time Modeling for Accurate and Speed-Independent Pulsating Voltage Injection Self-Sensing. 1-6. 10.1109/SLED.2019.8896346.
[26] Polom, T.; van der Broeck, C.; De Doncker, R.; Lorenz, R. "Designing Power Module Health Monitoring Systems Based on Converter Load Profile," in IEEE Transactions on Industry Applications, vol. 56, no. 6, pp. 6711-6721, Nov.-Dec. 2020, doi: 10.1109/TIA.2020.3023070.
[27] Polom, T.; Andresen, M.; Liserre, M.; Lorenz, R. "Experimentally Extracting Multiple Spatial Thermal Models that Accurately Capture Slow and Fast Properties of Assembled Power Semiconductor Converter Systems," 2018 IEEE Energy Conversion Congress and Exposition (ECCE), Portland, OR, USA, 2018, pp. 7391-7398, doi: 10.1109/ECCE.2018.8557855.
[28] Boffi, N.; Slotine, J. Implicit regularization and momentum algorithms in nonlinear adaptive control and prediction. arXiv: 1912.13154v6 [math. OC], available online (accessed 29 March 2021): https://arxiv.org/abs/1912.13154.
[29] Fossen, T. Comments on Hamiltonian adaptive control of spacecraft by J. J. E. Slotine and M. D. Di Benedetto. IEEE Trans. Auto. Con. 1993, 38 (4) 671.
[30] Sands, T.; Kim, J. J.; Agrawal, B. N. Improved Hamiltonian adaptive control of spacecraft. In Proceedings of the IEEE Aerospace, Big Sky, MT, USA, 7–14 March 2009; IEEE Publishing: Piscataway, NJ, USA, 2009; pp. 1–10.
[31] Baker, K.; Cooper, M.; Heidlauf, P.; Sands, T. Autonomous trajectory generation for deterministic artificial intelligence. Electr. Electron. Eng. 2018, 8 (3), 59.
[32] Sands, T. (Ed.). Deterministic Artificial Intelligence. IntechOpen: London, 2020. ISBN: 978-1-78984-111-4.
[33] Cooper M., Heidlauf, P. Nonlinear Feed Forward Control of a Perturbed Satellite using Extended Least Squares Adaptation and a Luenberger Observer. J Aeronaut Aerospace Eng 2018, 7 (1), 205. doi: 10.4172/2168-9792.1000205.
Cite This Article
  • APA Style

    Eric Miller, Timothy Sands. (2021). Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits. Control Science and Engineering, 5(1), 13-19. https://doi.org/10.11648/j.cse.20210501.12

    Copy | Download

    ACS Style

    Eric Miller; Timothy Sands. Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits. Control Sci. Eng. 2021, 5(1), 13-19. doi: 10.11648/j.cse.20210501.12

    Copy | Download

    AMA Style

    Eric Miller, Timothy Sands. Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits. Control Sci Eng. 2021;5(1):13-19. doi: 10.11648/j.cse.20210501.12

    Copy | Download

  • @article{10.11648/j.cse.20210501.12,
      author = {Eric Miller and Timothy Sands},
      title = {Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits},
      journal = {Control Science and Engineering},
      volume = {5},
      number = {1},
      pages = {13-19},
      doi = {10.11648/j.cse.20210501.12},
      url = {https://doi.org/10.11648/j.cse.20210501.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.cse.20210501.12},
      abstract = {With heritage in nonlinear adaptive control (as proposed by Slotine) and physics-based control (as proposed by Lorenz), recently proposed methods referred to as deterministic artificial intelligence (D.A.I.) claim slight performance improvement over the parent methods. This brief communication firstly validates claims of slight improvement, but furthermore highlights a key feature: indications that improvements in observer implementations are the proper path for subsequent development in the field. The manuscript validates the recently published 97% performance improvement over classical methods using nonlinear adaptive methods, with an addition 0.23% performance improvement using D.A.I. compared to nonlinear adaptive control. Furthermore, the work also identifies strong correlation between system performance and observer performance, which is significant since D.A.I. eliminates controller tuning. Thus, observer improvement is recommended for future developments. The recently published 2-norm optimal learning scheme (of Smeresky) is recommended as the next step in the lineage of research in the discipline assuming augmentation with nonlinear state observers.},
     year = {2021}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Critical Commentary on Deterministic Artificial Intelligence Applied to Oscillatory Circuits
    AU  - Eric Miller
    AU  - Timothy Sands
    Y1  - 2021/08/31
    PY  - 2021
    N1  - https://doi.org/10.11648/j.cse.20210501.12
    DO  - 10.11648/j.cse.20210501.12
    T2  - Control Science and Engineering
    JF  - Control Science and Engineering
    JO  - Control Science and Engineering
    SP  - 13
    EP  - 19
    PB  - Science Publishing Group
    SN  - 2994-7421
    UR  - https://doi.org/10.11648/j.cse.20210501.12
    AB  - With heritage in nonlinear adaptive control (as proposed by Slotine) and physics-based control (as proposed by Lorenz), recently proposed methods referred to as deterministic artificial intelligence (D.A.I.) claim slight performance improvement over the parent methods. This brief communication firstly validates claims of slight improvement, but furthermore highlights a key feature: indications that improvements in observer implementations are the proper path for subsequent development in the field. The manuscript validates the recently published 97% performance improvement over classical methods using nonlinear adaptive methods, with an addition 0.23% performance improvement using D.A.I. compared to nonlinear adaptive control. Furthermore, the work also identifies strong correlation between system performance and observer performance, which is significant since D.A.I. eliminates controller tuning. Thus, observer improvement is recommended for future developments. The recently published 2-norm optimal learning scheme (of Smeresky) is recommended as the next step in the lineage of research in the discipline assuming augmentation with nonlinear state observers.
    VL  - 5
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Systems Engineering Program, Cornell University, Ithaca, USA

  • Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, USA

  • Sections