ML-Based RF Calibration of Military T/R Modules
DOI:
https://doi.org/10.65834/jdsi.12.52Keywords:
machine learning, artificial intelligence, RF calibration, regression, XGBoost, LightGBM, TabNetAbstract
In this work, Machine Learning (ML) techniques are incorporated into the Radio Frequency (RF) calibration workflow with the objective of reducing associated costs and enhancing operational efficiency for the military grade Transmitter/Receiver (T/R) modules. RF calibration entails a series of measurements that verify the module’s performance at certain temperatures, power levels and frequencies; when performed with conventional procedures, it is both time‑consuming and expensive. In this study for a single unit, the traditional RF calibration process requires approximately 17 h and involves ten dedicated test and calibration stations as well as seven operators. Ensuring RF calibration, seven distinct Received‑Signal‑Strength‑Indicator (RSSI) values are recorded; in this study focuses on one of these parameters, denoted RSSI F, which is essential for the correct functioning of the target module. In validation, the ML predicted RSSI F values are directly benchmarked against measured references under a ±12 mV error envelope; the comparison yielded a 66.80% success rate.
References
Arik, S. O., & Pfister, T. (2019). TabNet: Attentive interpretable tabular learning. arXiv preprint arXiv:1908.07442.
Armstrong, J. S., & Collopy, F. (1992). Error measures for generalizing about forecasting methods: Empirical comparisons. International Journal of Forecasting, 8(1), 69–80.
Cai, J., King, J. B., Yu, C., Pan, B., Sun, L., & Liu, J. (2020). Dynamic behavioural modelling of RF power amplifiers based on decomposed piecewise machine learning technique. International Journal of Microwave and Wireless Technologies, 1‑7. https://doi.org/10.1017/S1759078720001208
Chang, Y., Wen, Y., Hong, Z., Padmanabhan, B., Franzon, P. D., & Floyd, B. A. (2025). A 27–30 GHz T/R module with reflection‑type phase shifting and machine‑learned calibration. IEEE Transactions on Circuits and Systems I: Regular Papers, 72(9), 4649‑4660. https://doi.org/10.1109/TCSI.2024.3524280
Chai, T., & Draxler, R. R. (2014). Root Mean Square Error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48.
Dikmese, S., Anttila, L., Campo, P. P., Valkama, M., & Renfors, M. (2019). Behavioral modeling of power amplifiers with modern machine learning techniques. In 2019 IEEE MTT-S International Microwave Conference on Hardware and Systems for 5G and Beyond (IMC-5G) (pp. 1-3). IEEE. https://doi.org/10.1109/IMC-5G47857.2019.9160381
Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Ortega-González, F. J., García, J. A., Patiño-Gómez, M., & Madueño-Pulido, D. (2025). High-Efficiency Transmitters Operating at HF, VHF, and UHF Frequencies. IEEE Microwave Magazine. https://doi.org/10.1109/MMM.2025.3592159
Sriram, A., & Tuffy, N. (2025). Accelerating RF power amplifier design via intelligent sampling and ML‑based parameter tuning. arXiv. https://arxiv.org/abs/2507.11928
Tong, Y., Wang, J., Fu, T., Su, J., & Liu, J. (2024). Measurement-Driven Automated Design of High-Efficiency Power Amplifiers. In 2024 9th International Conference on Integrated Circuits and Microsystems (ICICM) (pp. 129-133). IEEE. https://doi.org/10.1109/ICICM63644.2024.10814353
Uğur, A. B. (2023). Derin öğrenme tabanlı güç yükseltici modülü kalibrasyonu (Master's thesis, Gazi University).
U.S. Department of Defense. (2019). MIL-STD-810H: Environmental engineering considerations and laboratory tests. http://everyspec.com/MIL-STD/MIL-STD-0800-0899/MIL-STD-810H_55998/
Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 30(1), 79-82.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Defence and Security Industries: Strategy and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.