Oil level prediction of power transformer based on BP neural network

Transformer oil plays the role of heat dissipation and insulation in the operation of transformer, and any excessive high (low) transformer oil level will affect the safe and stable operation of the transformer; the transformer oil level will change with the change of ambient temperature and load rate, so it is necessary to predict the oil level of the transformer, and then it can be governed in advance. First, according to the shape of the transformer oil storage cabinet, oil surface characteristics and the working principle of the oil level meter, the relationship between the oil volume in the transformer oil storage cabinet and the oil level indication is established; second, according to the transformer operating parameters, the BP neural network oil level prediction model is constructed, and the model is trained and tested to determine the optimal number of training times; finally, by comparing the predicted curve of the transformer oil level with the actual operating curve, the model is verified for its accuracy of the model.