Performance degradation in an advanced power system by analyzing process dynamics

Power plants are increasingly required to cycle to meet dispatch demand. Performance degradation in a recuperative gas turbine power system designed for hybridization was studied using start-up transients over a six-year period. The advanced power system consisted of a gas turbine, compressor, exhaust gas recuperator, hybrid system plenum, natural gas combustor, generator, and electric load bank. A Python script was used to align, filter, organize, transform, and summarize process data from facility start-up sequences. Data analytics including principal component and discriminant analyses were applied to identify potential sources of performance degradation for hybrid power systems in this hybrid configuration. Over 177 start-up tests from 103 datasets were considered in the analysis. The fuel flow increased with timestamp for the same start-up sequence, indicating a loss in efficiency. The decrease in efficiency could be detected in similar variations in pressures and temperatures around the turbine, but the changes in these indicators were unaffected by replacing the turbine. It was inferred from the results that a leak in the compressed gas system was responsible for the degradation. This multivariable methodology can be readily adapted to investigate the effects of system component wear and tear resulting in a decrease in system performance.