A Deep Learning Approach for Gain-Scheduled PID Control Design via Advanced Supervisory Controllers


ATAM E., ZEYBEK A., ÖZATEŞ Ş. B., Guzelkaya N.

IEEE Transactions on Emerging Topics in Computational Intelligence, cilt.10, sa.3, ss.2610-2623, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 10 Sayı: 3
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1109/tetci.2026.3669780
  • Dergi Adı: IEEE Transactions on Emerging Topics in Computational Intelligence
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2610-2623
  • Anahtar Kelimeler: PD control, PI control, Control systems, Control design, Deep learning, System dynamics, Industries, Adaptive control, Quadrotors, Hardware, Gain-scheduled PID control, supervisory control, deep learning, linear parameter-varying control, reinforcement learning, controller approximation, inverted pendulum
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Proportional-integral-derivative (PID) control is by far the most widely used control type in industry. However, for some systems even the optimally tuned PID control system can be unsatisfactory, especially when the underlying system is nonlinear, includes parameter-varying components and time delays or when system dynamics change with time. Due to the long-standing development and readiness of the infrastructure of PID controllers in the industry, along with cost factors, it is essential to improve the system performance without replacing the established structure. Gain-scheduled PID control is a strong solution for such situations. In this paper, we present a new approach for the gain-scheduled PID control design using deep learning to learn from advanced controllers such as linear parameter-varying controller and reinforcement learning agent. For each gain of PID, a deep artificial neural network is developed as a function of the scheduling signals. To validate the proposed approach, we tested it on two challenging case studies and compared its performance against optimally tuned conventional PID controllers with fixed parameters, as well as advanced state-of-the-art controllers that the gain-scheduled PID controllers aim to emulate. The proposed gain-scheduled method provided up to 71.6% performance improvement relative to the optimally tuned PID controller with fixed gains.