考虑设备劣化的加工工时预测方法

In response to the issue of the fixed standard results for process time at different stages of service life, a variable process time prediction method considering equipment degradation is proposed. For one single condition, a process time prediction method based on the BiGCU-MHResAtt model is constructed, with local features extracted in conjunction with BiGCU. Multiple head residual self-attention networks capture the influence relationships between different features, and a fully connected layer optimizes the Remaining Useful Life (RUL) while implementing machining time rate prediction through the Weibull probability distribution function. For multiple working conditions, a large dataset and feature transfer model are designed in combination with the single working condition model. Clustering and curve fitting are employed to generate a machining time prediction spectrum. Finally, the effectiveness of the proposed method is validated through model training and prediction by using the C-MAPSS dataset.