Short‐term forecast of the gas dissolved in power transformer using the hybrid grey model

Abstract

Purpose

The purpose of this paper is to define new method (grey model (GM)) for predicting the value of gases in oil‐immersed power equipment, as well as change the traditional GM which requires equal interval data.

Design/methodology/approach

Trend forecasting is an important aspect in fault diagnosis and work state supervision, however, in practice, it is not practical that a number of data is necessary to build the forecast model. In transformer, the concentration of the gases dissolved in transformer oil is associated with gas type, oil quality, oil temperature, transformer load, etc. which some are known, others are unknown. So it can consider that transformer is grey system and the theory of grey system is chosen as a mathematical framework to solve the problem of forecasting the change of gases.

Findings

If possible, the results should be accompanied by significance.

Research limitations/implications

Accessibility and availability of data are the main limitations which model will be applied.

Practical implications

A very useful advice for power transformer fault diagnosis method based on dissolved gas analysis data.

Originality/value

The paper presents a new approach of forecasting the value of gases in oil‐immersed power equipment and is aimed at unequal interval gases data which is used to GM.

Citation

Song, B. and Zheng‐hong, P. (2009), "Short‐term forecast of the gas dissolved in power transformer using the hybrid grey model", Kybernetes, Vol. 38 No. 3/4, pp. 489-496. https://doi.org/10.1108/03684920910944209