Application of multi-machine power system supervised machine-learning in error correction of electromechanical sensors. (July 2022)

• Record Type: Journal Article
• Authors: Yu, Linlin; Su, Li; Qin, Fang; Wang, Lijuan
• Is Part Of: Energy reports. Volume 8(2022)Supplement 4
• Page Start: 1381
• Page End: 1391
• Publication Date: 2022-07
• Subjects: Power system -- Electromechanical sensor -- Vibration error -- Machine learning -- Rotation rate correction; Power resources -- Periodicals; Energy industries -- Periodicals; Power resources; Periodicals; Electronic journals; 621.04205
• DOI: 10.1016/j.egyr.2022.02.002
• Languages: English
• ISSNs: 2352-4847

Abstract

Abstract: The shortage of electric energy in the supply process and supply interruption will not only directly affect the production level of all walks of life, but also affect the normal life order, and cause adverse effects on the development of the whole society. In order to ensure the stable operation of the system under the premise of ensuring safety, the actual control system is often affected by constraints. In this paper, the intelligent control strategy based on supervised machine learning is used to restrict the output of the system. The back stepping method and Lyapunov method are used to design the control, and then the supervised machine learning sensor of multi-machine power system under the constraint condition is optimized and improved. By introducing the k-class function adjusted according to the error, the system gain is automatically corrected. The simulation results show that the designed controllers can ensure that the output of the speed difference of the system is in the constrained range. Through comparison, it is concluded that the constrained fuzzy adaptive controller can further improve the rotation speed of the speed difference, reduce the vibration amplitude of the speed difference, and achieve better results.