Adilkhan Salkimbayev

Symbolic Kolmogorov-Arnold Networks as a Constant-Time Alternative to Linear Time-Varying Model Predictive Control for Embedded Control of Non-Minimum Phase Systems

Fri, 24 Apr 2026 00:00:00 +0000

Model Predictive Control (MPC) is the gold standard for constrained multi-variable control, yet its computational burden often precludes deployment on low-cost embedded hardware. As a primary contribution to artificial intelligence, this work proposes distilling complex control policies into a symbolic Kolmogorov-Arnold network (KAN), creating a computationally efficient, explicit neural controller.

Robust Adaptive Kolmogorov-Arnold Neural Control

Thu, 16 Apr 2026 00:00:00 +0000

Designed an adaptive control architecture achieving a significant speedup and reduction of upwards of 1.5x in actuator Total Variation compared to Linear Time-Varying Model Predictive Control. Features rigorous experimental validation and proof of Lyapunov stability by ISS/GUUB and LaSalle-Yoshizawa Theorem.

CV

Mon, 01 Jan 0001 00:00:00 +0000

Download PDF — my CV (Curriculum vitae).

Education

Kazakh-British Technical University — Automation and Control, 2027

Completed Theory of Linear/Non-Linear Control Systems, Foundations of Electrical Engineering I/II, PLC Programming;
GPA 3.58

Research experience

Self-directed, KBTU — Architect · (Nov 2025 - ongoing)

Produced two papers (one under review at Engineering Applications of Artificial Intelligence, one completed for further submission)
Utilized Kolmogorov-Arnold Networks for control-theoretic applications
Designed Model Predictive Control for K. H. Johansson’s Quadruple-Tank Process
Implemented the embedded C code for the NUCLEO-H753ZI motherboard
Gained experience with Hardware-in-the-Loop methodology
Produced empirical and theoretical validation for the control architectures
Gained hands-on experience with Machine Learning and training methodologies
Familiarized myself with relevant literature and theoretical knowledge
Gained experience of research iteration under Dr. Khawaja S. Haider
Currently transitioning to Functional Analysis and Partial Differential Equations

Publications

Manuscripts in progress — preprints are linked under Projects.