Multi-feature-parameter-based comprehensive fault diagnosis method of transformer

Abstract

The invention provides a multi-feature-parameter-based comprehensive fault diagnosis method of a transformer. The method comprises: partial discharging of a transformer is classified into different partial discharge classes; a partial discharge signal is obtained by a partial discharge analyzer; feature extraction is carried out on the signal; a specific partial discharge type is identified by using a Fisher classification method; a vibration signal of the transformer is monitored and analyzed to determine the state of the transformer; if a partial discharge signal is monitored, a diagnosis iscarried out based on partial discharge signal diagnosis and DGA diagnosis knowledge rules; and if a partial discharge signal and a vibration signal are monitored simultaneously, a diagnosis is carried out based on the vibration signal, the partial discharge signal, and the DGA diagnosis knowledge rules and comprehensive diagnosis is carried out according to a collaborative diagnosis rule. The diagnosis method has high openness; and when a new monitoring quantity is added, the diagnostic processes of other monitoring data do not need to be changed.

Description

technical field [0001] The invention belongs to the field of power systems, and in particular relates to a comprehensive fault diagnosis method for transformers based on multiple characteristic parameters. Background technique [0002] Transformer is an important equipment in the power system, and its operating status directly affects the safety level of the power system. However, since the transformer is a closed whole that integrates multi-disciplinary technologies such as machinery, electricity, chemistry, and thermodynamics, the causes of its faults are intricate, and fault diagnosis requires various data and knowledge. The conclusion will inevitably lead to misjudgment or missed judgment. For example, oil chromatographic monitoring of DGA data is currently the most convenient and effective means for early fault diagnosis of oil-immersed transformers, but the dissolved gas in the oil itself does not carry sufficient fault location information, and fault diagnosis only r...

AI Technical Summary

Problems solved by technology

However, since the transformer is a closed whole that integrates multi-disciplinary technologies such as machinery, electricity, chemistry, and thermodynamics, the causes of its faults are intricate and complex, and fault diagnosis requires various data and knowledge. The conclusion will inevitably lead to misjudgment or omission

For example, oil chromatographic monitoring of DGA data is currently the most convenient and effective means for early fault diagnosis of oil-immersed transformers. However, the dissolved gas in the oil itself does not carry enough fault location information, and fault diagnosis only relies on the information provided by the gas in the oil. certain limitations

Images