Litcius/Paper detail

Adaptive Neural Control of Superheated Steam System in Ultra-Supercritical Units With Output Constraints Based on Disturbance Observer

Zhongrui Zhou, Juan Zhang, Yingchun Wang, Dongsheng Yang, Zeyi Liu

2025IEEE Transactions on Circuits and Systems I Regular Papers22 citationsDOI

Abstract

For the superheated steam temperature control system, an optimized disturbance observer and output-constrained control algorithm have been designed. Initially, the original system with output constraints is transformed into a system without any state constraints, suitable for backstepping design, through state transformation. Then, based on the concept of negative gradient optimization, a gain iterative disturbance observer is constructed, which dynamically improves the control accuracy of the system compared to a constant gain disturbance observer. Finally, an adaptive neural control scheme based on the gain iterative disturbance observer is proposed, proving that all output states are constrained within predefined bounds, and all closed-loop signals are semi-globally uniformly bounded. The effectiveness of the proposed scheme is demonstrated through a simulation example of the superheated steam temperature system.

Topics & Concepts

Control theory (sociology)Supercritical fluidDisturbance (geology)Superheated steamControl systemSuperheatingControl engineeringObserver (physics)Computer scienceEngineeringControl (management)Boiler (water heating)PhysicsElectrical engineeringArtificial intelligenceWaste managementPaleontologyCondensed matter physicsThermodynamicsBiologyQuantum mechanicsAdvanced Control Systems OptimizationFault Detection and Control SystemsIterative Learning Control Systems
Adaptive Neural Control of Superheated Steam System in Ultra-Supercritical Units With Output Constraints Based on Disturbance Observer | Litcius