Variable-speed pumped storage power control method based on BP algorithm

By adopting a variable-speed pumped storage power control method based on BP neural network, the problems of fast response, high precision and smoothness of traditional PI controllers in variable-speed pumped storage systems are solved. It achieves fast response while reducing overshoot and steady-state error, thereby improving the overall performance of the controller.

CN122456677APending Publication Date: 2026-07-24NANJING INST OF TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202610325846.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-17
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Traditional PI controllers are difficult to meet the requirements of rapid response, high precision, multi-condition adaptability and smoothness of variable speed pumped storage systems, especially when there are large power changes, they have overshoot problems.

Method used

A variable-speed pumped storage power control method based on BP neural network is adopted. By modeling a doubly fed variable-speed pumped storage system, a three-layer feedforward neural network is designed. The BP neural network is used for training and control to realize the mapping of the input layer, hidden layer and output layer. The hyperbolic tangent function is used for activation, and online control is achieved by real-time adaptive weight update.

Benefits of technology

While achieving rapid response, the power overshoot is close to zero, the steady-state error is small, the response is smooth and oscillation-free, and the control accuracy and steady-state performance are significantly improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention belongs to the field of pumped storage, and relates to a BP algorithm-based variable-speed pumped storage power control method. The invention provides a variable-speed pumped storage power control method based on a BP (Back Propagation) algorithm aiming at the problems of nonlinearity, time-varying property and the like in power control of a variable-speed pumped storage unit. A mathematical model of a variable-speed pumped storage system is established, a 3-5-1 feedforward neural network controller with online learning capability is designed, and the controller adopts an error back propagation algorithm to adjust network weight in real time. A Matlab / Simulink simulation result shows that compared with a traditional PI controller, the BP neural network controller has the advantages that the power overshoot is close to zero, the steady-state error is small, and the response is smooth without oscillation in the step response.
Need to check novelty before this filing date? Find Prior Art