A fused motor direct-drive operating mechanism state evaluation method

Motor direct-drive operating mechanism (MDDOM), as an important protection device in the power system, is directly related to the overall operational safety of the power system. However, as a new type of operating mechanism, there is a lack of targeted condition evaluation methods. In order to improve the level of digital operation and maintenance of power equipment, this paper proposes a condition assessment method for MDDOM, firstly, establish the health assessment system of the MDDOM and verify it by using the data correlation coefficient method. Secondly, an expert group assessment method (EGAM) is used for condition assessment. To alleviate the influence of subjective factors on the assessment results in the EGAM, a hybrid deep learning model of convolutional neural network (CNN) and gated recurrent unit (GRU) is introduced, and the self-attention mechanism is added at the same time to further improve the performance of the model. Then, a game theory (GT) approach is used to integrate and optimize the weights of the evaluation indicators obtained by using the EGAM and the CNN-GRU hybrid deep learning model based on the self-attention mechanism (CNN-GRU-Attention). In order to prevent the constant weights in the GT method from effectively reflecting the real state of the object to be evaluated when some of the evaluation indicators deviate, the GT weight calculation method is optimized. Finally, the experiment verifies the effectiveness of the method proposed in this paper, and the experimental results show that in the case of moderate jamming of the MDDOM, the method proposed in this paper has an accuracy improvement of 5.71% compared with the EGAM.