Power generator set subsynchronous risk evaluating method based on wave recording big data abnormal detection

Abstract

The invention provides a power generator set subsynchronous risk evaluating method based on wave recording big data abnormal detection. The method comprises the following contents of collecting all torsional vibration wave recording files of the same machine unit in a period of time; performing Fourier transformation on the machine end three-phase current signals; extracting industrial frequency components, subsynchronous and supersynchronous harmonic component coefficients; constructing an original feature data set Feature; performing decorrelation and data cleaning on the original feature data set by a main component analysis method; obtaining a dimension reduction feature data set Feature_scomp; building the mahalanobis distance distribution between each sample and the statistics features on the basis of the obtained dimension reduction feature data set; using the value of the mahalanobis distance for measuring the subsynchronous risk; performing the system warning when the risk value reaches 90 percent or higher than 90 percent. The power generator set subsynchronous risk evaluating method has the advantages that the SSO (single sign-on) risk safe evaluation is fast realized, and an auxiliary decision measure is provided for the SSO defense and inhibition in electric network operation.

Description

technical field [0001] The invention belongs to the technical field of power system stability and control, and specifically relates to a generator set sub-synchronization risk assessment method based on wave recording big data anomaly detection, which provides auxiliary decision-making and safety early warning for power system stability and safe operation. technical background [0002] Under the background of long-distance large-capacity transmission demand, due to the extensive use of series compensation transmission, AC-DC hybrid transmission and FACTS equipment, the resulting Subsynchronous Oscillation (SSO) seriously threatens the safe and stable operation of the power grid and generating units. At present, the research on SSO focuses on the unit torsional vibration protection and oscillation control, and there is a lack of oscillation defense means for power grid operation monitoring. Therefore, it is of great significance to deeply study the subsynchronous risk assessm...

AI Technical Summary

Problems solved by technology

[0003] At present, the torsional vibration monitoring / control / protection device of the unit shaft system has produced a large number of wave recording files, which record the shaft speed signal of the unit and the voltage / current signal of the machine terminal during the power grid operation in real time. However, the processing method of the wave recording files is often Manual, manual, and targeted analysis after failures. Therefore, a large number of historical recording files accumulated over the years have not formed knowledge that can help operators understand the operating status of the power grid except for historical filing.

In addition, the analysis of SSO mainly starts from the high-sensitivity shaft speed signal, which is processed with the help of some cumbersome algorithms and techniques (such as filtering and damping calculation), while the electrical quantity signal is only used for auxiliary analysis, and its utilization rate is very small

Images