EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-learning adaptive neuro-fuzzy approximation of robust control behavior in electric power steering systems

Tuan Anh Nguyen iD, Tran Minh Ngoc Do, Thi Thu Huong Tran, The Truc Nguyen, Quang Vinh Tran

PLOS One · 2025

DOI: 10.1371/journal.pone.0334539 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Tuan Anh Nguyen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical Engineering, Thuyloi University, Hanoi, Vietnam. Hauptthemen laut MEDLINE: Fuzzy Logic, Neural Networks, Computer, Electric Power Supplies. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Quỹ Đổi mới sáng tạo Vingroup.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data training algorithms based on Artificial Intelligence (AI) often encounter overfitting, underfitting, or bias issues. This article presents the design of a hybrid self-learning algorithm to address the above challenges. The proposed approach is developed by integrating fuzzy logic and neural network structures into an Adaptive Network-Based Fuzzy Inference System (ANFIS), which leverages the strengths of both components. This integration is considered a key contribution of the study. Compared to conventional training algorithms, the proposed ANFIS demonstrates high training accuracy while maintaining strong interpolation and prediction capabilities, even under varying conditions. The model is designed with three inputs and one output, trained using data derived from a high-performance robust controller for Electric Power Steering (EPS) systems. Simulation results show that the training error of the proposed ANFIS remains below 1.7% in well-trained cases and under 6.1% in interpolation scenarios. Moreover, the algorithm maintains a prediction error of less than 9.3% when applied to scenarios outside the training domain. The issue of overfitting is significantly resolved, unlike in the case of the Backpropagation Neural Network (BPNN), which is used as a benchmark for comparison. Overall, the proposed algorithm significantly improves data training accuracy and generalization performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Fuzzy LogicNeural Networks, ComputerElectric Power SuppliesAlgorithmsArtificial IntelligenceComputer SimulationHumans

Autor:innen und Institutionen

  • Faculty of Mechanical Engineering, Thuyloi University, Hanoi, Vietnam.
  • School of Mechanical Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam.
  • University of Wisconsin-Whitewater, Whitewater, Wisconsin, Unites State of America.
  • Phenikaa school of Engineering, Phenikaa University, Hanoi, Vietnam.

ORCID-Profile: Tuan Anh Nguyen

Förderung

  • Quỹ Đổi mới sáng tạo Vingroup

Zitieren

APA

Nguyen, T. A., Do, T. M. N., Tran, T. T. H., Nguyen, T. T., & Tran, Q. V. (2025). Self-learning adaptive neuro-fuzzy approximation of robust control behavior in electric power steering systems. PLOS One. https://doi.org/10.1371/journal.pone.0334539

Vancouver

Nguyen TA, Do TMN, Tran TTH, Nguyen TT, Tran QV. Self-learning adaptive neuro-fuzzy approximation of robust control behavior in electric power steering systems. PLOS One. 2025. doi:10.1371/journal.pone.0334539

BibTeX
@article{Nguyen2025,
  author = {Nguyen, Tuan Anh and Do, Tran Minh Ngoc and Tran, Thi Thu Huong and Nguyen, The Truc and Tran, Quang Vinh},
  title = {Self-learning adaptive neuro-fuzzy approximation of robust control behavior in electric power steering systems},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0334539}
}
Kostenlos starten →