Thermal power generating unit primary frequency modulation analysis and optimization method based on BP neural network algorithm

Abstract

The invention discloses a thermal power generating unit primary frequency modulation analysis and optimization method based on a BP neural network algorithm. The method comprises the following steps:obtaining primary frequency modulation performance index assessment data, operation data uploaded by a thermal power generating unit PMU subsystem, and unit related operation data corresponding to a thermal power generating unit DCS system and a DEH system; performing correlation calculation on indexes in primary frequency modulation performance index assessment and factors possibly influencing primary frequency modulation assessment performance, and extracting derivative variables influencing the factors according to calculation results; constructing a primary frequency modulation analysis and diagnosis system by using a BP neural network algorithm, performing pattern recognition on a primary frequency modulation assessment performance index result, and training system parameters; mutating derivative variables in the constraint range, and substituting the derivative variables into a trained BP neural network model for iterative computation; and according to the variation direction anddegree of the derivative variable meeting the requirement that the model output becomes qualified, performing reverse analysis on the reason that the primary frequency modulation performance assessment index is unqualified to obtain an optimization scheme.

Description

technical field [0001] The invention relates to the field of generating sets, in particular to a method for analyzing and optimizing the primary frequency regulation of a thermal power set based on a BP neural network algorithm. Background technique [0002] The prior art is not pertinent and practical for comprehensively improving the primary frequency regulation performance of thermal power units. First of all, the different parameters of thermal power units, different operating equipment states, and even differences in unit-related configuration logic determine that each unit has different reasons for the failure of a frequency regulation action assessment result. There is a single factor but more of a combination of multiple factors. Therefore, it is necessary to carry out comprehensive analysis and optimization from multiple aspects. Therefore, it is particularly necessary to conduct targeted analysis and diagnosis of the primary frequency regulation action of each uni...

AI Technical Summary

Problems solved by technology

Existing technologies can only predict the current primary frequency modulation capability, or only find the reason why primary frequency modulation is evaluated from a single factor, or find out the reasons that affect primary frequency modulation performance evaluation indicators, but cannot further propose qualitative and quantitative improvement methods or Opinion

Images