A real-time t-s fuzzy modeling method for heavy-duty gas turbines in combined cycle units

Abstract

The invention discloses a real-time T-S fuzzy modeling method for a heavy-duty gas turbine of a combined cycle unit. Firstly, the model structure of the gas turbine to be identified is established according to actual requirements, and field operation data of the heavy-duty gas turbine of the combined cycle unit are collected as training data for model identification; Then, the initial training data is preprocessed to eliminate the adverse effects of abnormal data; secondly, the data space is classified by the improved entropy clustering method, and the number of clusters and their corresponding cluster centers are automatically obtained; on this basis , introduce an improved whale optimization algorithm to modify the initial cluster center and calculate the corresponding cluster radius; next, obtain the parameters of each sub-model in the subsequent identification through the least square algorithm with forgetting factor and carry out fuzzy weighting The global output is obtained; finally, the identified model is verified.

Description

technical field [0001] The present invention generally relates to the technical field of modeling and optimization, and more specifically relates to a real-time T-S fuzzy modeling method for a heavy-duty gas turbine of a combined cycle unit. Background technique [0002] As the national development strategy pays more and more attention to energy and environmental issues, the power generation process based on clean energy has gradually become a trend in the development of the power industry. Among them, natural gas has become one of the preferred energy sources because of its easy acquisition, cleanness and environmental protection. The gas-steam combined cycle unit is currently the main device that uses natural gas to generate electricity in China. It generates the electricity required by users through the organic cooperation of the gas turbine system and the steam turbine system. As one of the most critical components of combined cycle units, heavy-duty gas turbines play a...

AI Technical Summary

Problems solved by technology

With the continuous expansion of the installed capacity of combined cycle power plants in recent years, the complexity of the gas turbine system and the strictness of the control requirements have also increased. The traditional T-S fuzzy modeling has been difficult to meet the requirements of the accuracy and real-time modeling process. , the present invention provides a method based on the real-time T-S fuzzy modeling of the heavy gas turbine of the combined cycle unit, to at least partly solve the above-mentioned problems

Images