Fizik tabanlı eğitim verisi kullanılarak dijital hidrolik valf sistemleri için vekil modelleme yaklaşımı

Abstract

Dijital hidrolik sistemlerde akış kontrolü, birden fazla birbirinden bağımsız aç/kapa valfin konumlarının uygun şekilde birleştirilmesiyle sağlanmaktadır. Bununla birlikte, yüksek boyutlu dijital akış kontrol üniteleri (DFCU) için dinamik simülasyonların yürütülmesi ciddi düzeyde hesaplama gerektirmektedir ve zaman almaktadır. Örneğin, 16x4 valf devresinde bir DFCU toplamda 65.536 olası valf durumuna sahiptir ve her bir durum ayrı bir dinamik çözümleme gerektirmektedir. Bu çalışmada, basınç ve hız izleme hatalarını temsil eden maliyet fonksiyonu J’yi tahmin etmek üzere ileri beslemeli bir yapay sinir ağı (YSA) kullanan veri odaklı vekil model olan ValveNet uygulanmıştır. Önerilen ağ, 2.048.000 fizik tabanlı örnekten oluşan geniş bir veri seti (4000 rastgele çalışma durumu x durum başına 512 valf eylemi) ile eğitilmiş ve sadeleştirilmiş model tabanlı bir referanstan elde edilen 65.536 valf kombinasyonu üzerinde doğrulanmıştır. Kompakt YSA mimarisi ([16–8], SCG eğitimi), doğrulama aşamasında R²=0.998 düzeyinde yüksek başarı göstermiş; fiziksel modele ilişkin karşılaştırmalarda ise R²=0.78–0.99 aralığında güçlü bir uyum sağlamış ve yaklaşık 5.7 kat daha yüksek hesaplama hızı elde edilmiştir. Elde edilen sonuçlar, ValveNet’in karmaşık DFCU konfigürasyonlarını hızlı biçimde değerlendirebildiğini; ayrıca gerçek zamanlı valf optimizasyonu ve dijital hidrolik kontrolünde etkili bir vekil model olarak kullanılabileceğini göstermektedir.

Keywords

• Dijital Hidrolik
• Yapay Sinir Ağları
• Dijital Akış Kontrol Ünitesi (DFCU)
• Hidrolik Valf Optimizasyonu
• Vekil Modelleme

A surrogate modeling approach for digital hydraulic valve systems using physics-based training data

Abstract

In digital hydraulic systems, flow regulation is achieved by combining the discrete openings of multiple on/off valves. However, performing dynamic simulations for large digital flow control units (DFCU) is computationally intensive. A 16x4 DFCU, for instance, involves 65,536 possible valve states, each requiring separate dynamic evaluation. This work presents ValveNet, a data-based model that uses a feedforward artificial neural network (ANN)to estimate the cost value J, which reflects the pressure and velocity tracking errors. The network was trained on 2,048,000 physics-based samples (4000 random operating combination x 512 valve actions per state) and validated against a benchmark grid of 65,536 valve combinations derived from a simplified model-based type. The compact ANN architecture ([16–8], SCG training) achieved R2=0.998 on validation data and maintained strong correlation with the physical model (R2=0.78–0.99) while showing a 5.7x computational speed-up. ValveNet enables rapid evaluation of complex DFCU configurations. Also, it achieves real-time valve optimization and digital hydraulic control properly.

Keywords

• Digital Hydraulics
• Artificial Neural Networks
• Digital Flow Control Unit (DFCU)
• Hydraulic Valve Optimization
• Surrogate Modeling

References

1. [1] J. Huang, J. Dai, L. Quan, and Y. Lan, “Performance of Proportional Flow Valve With Pilot Pressure Drop—Spool Opening Compensation,” Journal of Dynamic Systems, Measurement, and Control, vol. 139, no. 1, Art. no. 1, Oct. 2016.
2. [2] H. Wang, X. Wang, J. Huang, and L. Quan, “Flow Control for a Two-Stage Proportional Valve with Hydraulic Position Feedback,” Chin. J. Mech. Eng., vol. 33, no. 1, Dec. 2020.
3. [3] M. Linjama, M. Paloniitty, L. Tiainen, and K. Huhtala, “Mechatronic Design of Digital Hydraulic Micro Valve Package,” Procedia Engineering, vol. 106, pp. 97–107, 2015.
4. [4] P. Tamburrano, A. R. Plummer, E. Distaso, and R. Amirante, “A Review of Direct Drive Proportional Electrohydraulic Spool Valves: Industrial State-of-the-Art and Research Advancements,” Journal of Dynamic Systems, Measurement, and Control, vol. 141, no. 2, Art. no. 2, Oct. 2018.
5. [5] H. Y. Pan, S. N. Liu, Y. M. Yao, and Y. L. Jiang, “Fault Diagnostic of Electro-Hydraulic Servo Valve,” AMR, vol. 619, pp. 259–263, Dec. 2012.
6. [6] C. X. Bao, “Development of the Jet Flow Testing System and the Influence of the Hydraulic Oil on the Jet Flow Quality,” KEM, vol. 667, pp. 439–443, Oct. 2015.
7. [7] M. Pascal, A. Abou El-Azm, and R. Taher, “EXPERIMENTAL STUDY OF LEAKAGE COMPENSATION ON DYNAMIC CHARACTERISTICS OF HYDRAULIC POWER SYSTEMS,” The International Conference on Applied Mechanics and Mechanical Engineering, vol. 16, no. 16, pp. 1–17, May 2014.
8. [8] J. Y. Li, J. P. Shao, X. J. Wang, B. Qin, and Y. J. Qiao, “Research on Flow Press Servo-Valve Controlling Electro-Hydraulic Force Control System and Nonlinear Performance Analysis,” AMM, vol. 121–126, pp. 4606–4612, Oct. 2011.

9. [9] W. Liu, J. Wei, J. Fang, and S. Li, “Hydraulic-feedback proportional valve design for construction machinery,” Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 229, no. 17, pp. 3162–3178, Feb. 2015.
10. [10] F. Sciatti, P. Tamburrano, E. Distaso, and R. Amirante, “Digital Hydraulic Technology: Applications, Challenges, and Future Direction,” J. Phys.: Conf. Ser., vol. 2648, no. 1, p. 012053, Dec. 2023.
11. [11] B. Xu, J. Shen, S. Liu, Q. Su, and J. Zhang, “Research and Development of Electro-hydraulic Control Valves Oriented to Industry 4.0: A Review,” Chin. J. Mech. Eng., vol. 33, no. 1, Art. no. 1, Apr. 2020.
12. [12] S. Peng, “An Zero-Flowrate-Switching (ZFS) Control Method Applied in a Digital Hydraulic System,” presented at the The 15:th Scandinavian International Conference on Fluid Power, 15th Scandinavian International Conference on Fluid Power, Fluid Power in the Digital Age, SICFP’17, June 7-9 2017 - Linköping, Sweden, Dec. 2017, pp. 172–177.
13. [13] M. Linjama and M. Vilenius, “Improved Digital Hydraulic Tracking Control of Water Hydraulic Cylinder Drive,” International Journal of Fluid Power, vol. 6, no. 1, Art. no. 1, Jan. 2005.
14. [14] M. B. Rannow, H. C. Tu, P. Y. Li, and T. R. Chase, “Software Enabled Variable Displacement Pumps: Experimental Studies,” Fluid Power Systems and Technology, pp. 67–76, Jan. 2006.
15. [15] D. Oliveira e Silva, M. P. Nostrani, R. S. Lopes Junior, and V. J. De Negri, “Digital Hydraulic Actuators: An Alternative for Aircraft Control Surfaces,” Linköping Electronic Conference Proceedings, vol. 196, pp. 8–13, Mar. 2023.
16. [16] C. Yuan, V. L. Mao Lung, A. Plummer, and M. Pan, “Theoretical and Experimental Studies of a Digital Flow Booster Operating at High Pressures and Flow Rates,” Processes, vol. 8, no. 2, p. 211, Feb. 2020.
17. [17] C. Yuan, M. Pan, and A. Plummer, “A Review of Switched Inertance Hydraulic Converter Technology1,” Journal of Dynamic Systems, Measurement, and Control, vol. 142, no. 5, Mar. 2020.
18. [18] S. Peng, D. T. Branson, E. Guglielmino, T. Boaventura, and D. G. Caldwell, “Performance Assessment of Digital Hydraulics in a Quadruped Robot Leg,” Volume 3: Advanced Composite Materials and Processing; Robotics; Information Management and PLM; Design Engineering, pp. 227–234, Jul. 2012.
19. [19] J. Zhang, M. Yang, and B. Xu, “Design and Experimental Research of a Miniature Digital Hydraulic Valve,” Micromachines, vol. 9, no. 6, Art. no. 6, Jun. 2018.
20. [20] C. Noergaard, D. B. Roemer, M. M. Bech, and T. O. Andersen, “Experimental Validation of Mathematical Framework for Fast Switching Valves Used in Digital Hydraulic Machines,” in ASME/BATH 2015 Symposium on Fluid Power and Motion Control, Chicago, Illinois, USA: American Society of Mechanical Engineers, Oct. 2015, p. V001T01A062.
21. [21] K. Pate, I. Azzam, F. Breidi, J. R. Marschand, and J. H. Lumkes, “Digitalization of Radial Piston Pumps through Internal Mechanically Actuated Designs,” Actuators, vol. 12, no. 11, p. 425, Nov. 2023.
22. [22] A. F. Özalp, “DİJİTAL HİDROLİK VALF KONTROL SİSTEMİ KULLANILARAK BİR HİDROLİK SİLİNDİRİN KONUM VE HIZ KONTROLÜ,” Karabük Üniversitesi, Karabük, 2022.
23. [23] A. F. Ozalp, R. Polat, C. Cetinkaya, and M. H. Cetin, “Investigation of a Digital Hydraulic Valve Operated by Servo Motors,” Eng. Technol. Appl. Sci. Res., vol. 11, no. 6, Art. no. 6, Dec. 2021.
24. [24] Q. Gao, M. Linjama, M. Paloniitty, and Y. Zhu, “Investigation on positioning control strategy and switching optimization of an equal coded digital valve system,” Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 234, no. 8, Art. no. 8, Nov. 2019.
25. [25] H. Wang, Z. Chen, J. Huang, L. Quan, and B. Zhao, “Development of High-Speed On–Off Valves and Their Applications,” Chin. J. Mech. Eng., vol. 35, no. 1, p. 67, Jun. 2022.
26. [26] P. Tamburrano, P. De Palma, A. R. Plummer, E. Distaso, F. Sciatti, and R. Amirante, “Simulation of a high frequency on/off valve actuated by a piezo-ring stack for digital hydraulics,” E3S Web Conf., vol. 312, p. 05008, 2021.
27. [27] P. Tamburrano, F. Sciatti, E. Distaso, and R. Amirante, “Comprehensive Numerical Analysis of a Four-Way Two-Position (4/2) High-Frequency Switching Digital Hydraulic Valve Driven by a Ring Stack Actuator,” Energies, vol. 16, no. 21, p. 7355, Oct. 2023.
28. [28] I. Azzam, K. Pate, J. Garcia-Bravo, and F. Breidi, “Energy Savings in Hydraulic Hybrid Transmissions through Digital Hydraulics Technology,” Energies, vol. 15, no. 4, p. 1348, Feb. 2022.
29. [29] J. Liu et al., “Sensor Technologies for Hydraulic Valve and System Performance Monitoring: Challenges and Perspectives,” Advanced Sensor Research, vol. 3, no. 7, Mar. 2024.
30. [30] O. Vermesan et al., “Automotive Intelligence Embedded in Electric Connected Autonomous and Shared Vehicles Technology for Sustainable Green Mobility,” Front. Future Transp., vol. 2, Aug. 2021.
31. [31] H. Ding, Y. Liu, and Y. Zhao, “A new hydraulic synchronous scheme in open-loop control: Load-sensing synchronous control,” Measurement and Control, vol. 53, no. 1–2, pp. 119–125, Jan. 2020.
32. [32] P. Woś and A. Liniowego, “Sensorless step positioning of hydraulic linear actuator,” CT, vol. 11, 2018.
33. [33] C. Sun and R. Yuan, “Adaptive robust cross-coupling position synchronization control of a hydraulic press slider-leveling,” Science Progress, vol. 104, no. 1, Jan. 2021.
34. [34] S. J. Xu, J. F. Xing, and L. K. Peng, “Nonlinear Position Control of Digital Hydraulic Cylinder Despite Disturbance,” AMR, vol. 998–999, pp. 638–641, Jul. 2014.
35. [35] M. Linjama, “DIGITAL FLUID POWER – STATE OF THE ART,” presented at the The Twelfth Scandinavian International Conference on Fluid Power, May 2011, p. 23.
36. [36] J. Ersfolk et al., “Online Fault Identification of Digital Hydraulic Valves Using a Combined Model-Based and Data-Driven Approach,” Mar. 15, 2018, arXiv: arXiv:1803.05644.
37. [37] E. Xu, Q. Zhong, M. Pan, X. Yan, Y. Miao, and H. Yang, “Novel adaptive sliding-mode control of digital hydraulic systems with nonlinear flow prediction and friction identification,” Measurement, vol. 257, p. 118841, Jan. 2026.
38. [38] M. Linjama, M. Huova, and K. Huhtala, “Model-based force and position tracking control of an asymmetric cylinder with a digital hydraulic valve,” International Journal of Fluid Power, vol. 17, no. 3, Art. no. 3, May 2016.
39. [39] M. LINJAMA and M. VILENIUS, “ENERGY-EFFICIENT MOTION CONTROL OF A DIGITAL HYDRAULIC JOINT ACTUATOR,” Proceedings of the JFPS International Symposium on Fluid Power, vol. 2005, no. 6, Art. no. 6, 2005.