Mechanical vibration defect is the key factor leading to sudden failure of gas-insulated switchgear (GIS) equipment. It is important to realise effective prediction of the mechanical vibration state development trend of GIS equipment in order to improve its active safety protection level. This paper carried out research on the accurate prediction method and experimental validation of the mechanical vibration state and its defect severity development trend for the GIS equipment. Firstly

the deep and shallow vibration feature parameters for different mechanical defect signals were jointly extracted by time-domain features and deep belief network methods. Secondly

a new prediction model

incorporating the attention mechanism and the bidirectional gated recurrent unit (BiGRU)

was constructed with the deep and shallow vibration feature parameters as inputs. Finally

the prediction trend effectiveness was verified based on the real-type GIS mechanical simulation platform and the field operation GIS equipment. Results show that the deep and shallow vibration feature extraction method proposed in this paper can characterise the mechanical defect information more comprehensively. The new prediction method of the vibration state trend based on the attention-BiGRU model shows ideal accuracy

and the predicted vibration state development trend is highly consistent with the actual

with an average absolute error of 0.063. The root mean square error (ERMSE) value of the prediction method is <5%

which reduces the relative error value at least 37% compared with the traditional prediction models. This paper provides a valuable reference for the proactive defence of GIS mechanical failure.