This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Shweta Zambare,
Shivani Shendage,
Pratiksha Surve,
Nilophar Shaikh,
Vaibhav Godase,
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- Assistant Professor, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
Abstract
The rapid development of fifth generation (5G) and emerging sixth generation (6G) wireless communication systems require compact, low-loss, highly selective and frequency-stable radio- frequency front-end components. Microwave bandpass filters play an important role in selecting desired communication channels while suppressing out-of-band interference. However, conventional filter design generally requires repeated electromagnetic simulation and manual optimization of geometrical parameters, resulting in considerable computational time. This paper presents an artificial intelligence (AI)-assisted methodology for the design and optimization of a compact microstrip bandpass microwave filter for 5G/6G applications. A compact three- resonator microstrip topology with modified resonating slots and controlled coupling sections is proposed. Electromagnetic design parameters including resonator length, resonator width, coupling gap, feed-line width, substrate thickness and slot dimensions are considered as input variables. The corresponding center frequency, bandwidth, insertion loss, return loss and quality factor are used as output parameters. A simulation-based dataset containing 1200 design configurations is considered for training and evaluation of Random Forest (RF), Support Vector Regression (SVR), Artificial Neural Network (ANN), and Extreme Gradient Boosting (XGBoost) models. The AI models are subsequently used to predict filter responses and identify an optimized geometry. The illustrative simulation results indicate that XGBoost provides the lowest prediction error, with an value of 0.96 for center-frequency prediction and 0.94 for bandwidth prediction. The optimized filter is designed around a 3.5 GHz center frequency, corresponding to a representative sub-6-GHz 5G application, with an illustrative bandwidth of approximately 350 MHz. The proposed AI-assisted design methodology reduces the number of full-wave simulations required during optimization and provides a systematic route toward compact microwave filter design. The approach can be extended to mmWave and future 6G frequency bands.
Keywords: Artificial intelligence, machine learning, microwave filter, bandpass filter, 5G, 6G, microstrip, XGBoost, CST, RF optimization
References
1. Pozar DM. Microwave engineering. Fourth Editions, University of Massachusetts at Amherst, John Wiley & Sons, Inc. 2012:26-30.
2. Hong JS, Lancaster MJ. Microstrip filters for RF/microwave applications. New York: wiley; 2011 Jan 6.
3. Matthaei G, Young L, Jones EM. Microwave Filters, Impedance-Matching. Networks, and Coupling Structure” Artech House. 1980:200-320.
4. Cameron RJ, Kudsia CM, Mansour RR. Microwave filters for communication systems: fundamentals, design, and applications. John Wiley & Sons; 2018 Apr 17.
5. Zhang Y, Yao Y, Hu J, He S. A compact and narrow-band bandpass filter based on substrate integrated waveguide and spoof surface plasmon polaritons for millimeter-wave applications. AEU-International Journal of Electronics and Communications. 2024 May 1;178:155250.
6. Wang F, Lu Y, Yin X, Liu J, Yu N, Yang Y. Miniaturized silicon-based substrate integrated waveguide filter for 6G applications. Microelectronics Journal. 2023 Aug 1;138:105837.
7. Wang F, Kou J, Yin X, Liu J, Jing K, Yu N, Yang Y, Li Q. A compact fifth-order SIW BPF based on TSV technology with high selectivity. Microelectronics Journal. 2024 Feb 1;144:106067.
8. Le Y, Dong H, Su G, Zhan J, Quan X, Liu J. A miniaturized and low-loss Q-band SIW bandpass filter based on evanescent-mode in wafer-level packaging process. Microelectronics Journal. 2024 Jul 1;149:106209.
9. Akkader S, Bouyghf H, Baghdad A, Belbachir AK, El Bakkali M. Fabrication of compact substrate integrated waveguide dual band bandpass filter using complementary split-ring resonators for C and X band applications. e-Prime-Advances in Electrical Engineering, Electronics and Energy. 2024 Sep 1;9:100739.
10. Yahya SI, Zubir F, Nouri L, Jizat NM. An ultra-compact microstrip bandpass filtering coupler with suppressed harmonics and low group delay: a novel structure for 5G applications. Results in Engineering. 2024 Dec 1;24:103003.
11. Chinda FE, Hanif M, Soeung S, Yahya MS, Al-Gburi AJ, Bashir F, Zahoor F, Sovuthy C. Design of sub-6 GHz BPF using chained even and odd mode admittance polynomials for 5G C-band applications. Results in Engineering. 2025 Mar 1;25:103614.
12. Máximo-Gutiérrez C, Hinojosa J, Alvarez-Melcon A. A technique for the passband and stopband control of wideband band-pass substrate integrated waveguide (SIW) filters designed with elliptic stepped impedances. AEU-International Journal of Electronics and Communications. 2024 Apr 1;177:155172.
13. Mishra GK, Pandey HK, Pathak NP. A novel SIW bandpass filter design by diagonal coupling approach on single and multilayer model. AEU-International Journal of Electronics and Communications. 2025 Oct 1;200:155916.
14. Ismaeel Z, Yousif T. A Comprehensive Survey on Microwave Photonic Filter: Design Techniques and Implementations. International Journal of Mechatronics, Robotics, and Artificial Intelligence. 2026 Jun 1;2(1):35-50.
15. Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016 Nov 18.
16. Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5-32.
17. Vapnik VN. The nature of statistical learning theory. Springer science & business media; 2013 Apr 17.
18. Chen T, Guestrin C. Xgboost: A scalable tree boosting system. InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 785-794).
19. Godase V. Cross-domain comparative analysis of microwave imaging systems for medical diagnostics and industrial testing. Journal of Microwave Engineering & Technologies. 2025 Aug;12(2):39-48.
20. Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A Review on Real-time Substation Feeder Power Line Monitoring and Auditing Systems,”. International Journal of Emerging IoT Technologies in Smart Electronics and Communication. 2025 Sep;1(2):1-6.
21. Godase VV. VLSI-Integrated Energy Harvesting Architectures for Battery-Free IoT Edge Systems. Journal of Electronics Design and Technology. 2025 Sep;2(3):1-2.
22. Godase V, Pawar P, Nagane S, Kumbhar S. Automatic railway horn system using node MCU. Journal of Control & Instrumentation. 2024 Jan;15(1).
Journal of Microwave Engineering and Technologies
| Volume | 13 | |
| 02 | ||
| Received | 20/09/2026 | |
| Accepted | 22/09/2026 | |
| Published | 26/10/2026 | |
| Publication Time | 36 Days |