An improved retrieval-augmented long-term grouting power prediction method: Rejecting low-similarity retrievals

Abstract

Grouting power long-term prediction is beneficial to regulating power output. Traditional long-term prediction methods require iterative updates with newly accumulated data during construction, which is time-consuming. Retrieval-augmented methods not only achieve higher prediction accuracy but also enable more efficient performance upgrades through database updates, avoiding the need to retrain models. However, conventional retrieval augmented frameworks unconditionally incorporate retrieved sequences into the prediction process, even when their similarity to the query is low. This design choice can introduce noisy or irrelevant historical patterns, misleading the fusion mechanism and degrading overall performance. To address this issue, this study proposes a retrieval-augmented method for long-term grouting power prediction with a rejection-substitution mechanism. Compared with the naive retrieval augmented prediction method, this mechanism enables selective fusion of retrievals by evaluating the similarity of each retrieved sequence before integration. If the similarity falls below a predefined threshold, the corresponding result is substituted with a prediction from the TimeXer model. Otherwise, the retrieved result is retained. The processed results are then fused by a Gate Recurrent Unit network to generate the final prediction. To validate the effectiveness of the proposed method, experiments were conducted on both a grouting power dataset and a publicly accessible dataset. The results indicate that incorporating a rejection-substitution mechanism enhances the prediction accuracy compared to the traditional retrieval-augmented prediction approach.