CNN-BiGRU-Attention Based Equipment Assurance Demand Forecasting

CNN-BiGRU-Attention Based Equipment Assurance Demand Forecasting

연구 분야: Verification

학회: CAICE '25: Proceedings of the 4th International Conference on Computer, Artificial Intelligence and Control Engineering

Aiming at the problems of many influencing factors, high requirement standards and low accuracy of traditional single prediction model, combining the different advantages of Convolutional Neural Network (CNN), Bi-directional Gated Recurrent Units (BiGRU) and Attention mechanism in prediction, we propose a CNN-BiGRU-Attention based equipment security demand prediction model. The experimental results show that the mean square error (MSE), mean absolute error (MAE), mean relative error (MAPE), and coefficient of determination of the model are 0.12, 0.28, 1.52%, and 99.0%, respectively, which are significantly better than those of the models such as BiGRU and CNN-BiGRU, and have higher prediction accuracies, which verifies the advantages of the model in the forecasting of equipment safeguard demand, and is useful for the It is of great significance to proactively grasp the development and change of the future demand of equipment guarantee and provide scientific decision-making basis for equipment guarantee.