Traditional retrieval methods for hydropower engineering codes typically suffer from low efficiency, inaccurate clause localization, and limited answer reliability. To address these issues, a structure-aware multi-agent framework for hydropower engineering code retrieval and question answering is proposed. In the framework, a structured knowledge model is developed to preserve the hierarchical relationships of engineering codes and employ multiple agents to perform code routing, hierarchical retrieval, trustworthy reasoning, and answer generation; a traceable response mechanism is introduced to provide supporting code sources and clause references. Experimental results show that the proposed method achieves higher code localization accuracy, answer accuracy, and traceability than existing retrieval and retrieval-augmented generation (RAG)-based methods. The proposed framework provides an effective solution for intelligent engineering code services.

Solid gravity energy storage (SGES) is a method of energy storage technology that combines the prospects of operation safety, cost-effectiveness, and adaptive application. There are different systems within the SGES technology, which are grouped into three categories: mountain gravity energy storage (MGES), underground cavern energy storage (UCES), and structural building energy storage (SBES). However, there is a lack of studies comparing the round-trip efficiency of these SGES systems. To address this issue, this study first conducted academic review on differing SGES technologies, and simplified physical models were established to derive corresponding theoretical equations for determining the round-trip energy storage efficiency. Then, primary factors of influence on energy storage efficiency along with technical benefits and drawbacks of each system were then analyzed, revealing a variety of possible effects on efficiency and how to best utilize each SGES system, based on theoretical data.

Concrete temperature control during dam construction (e.g., concrete placement and curing) is important for cracking prevention. In this study, a short-term temperature forecast model for mass concrete cooling control is developed using artificial neural networks (ANN). The development workflow for the forecast model consists of data integration, data preprocessing, model construction, and model application. More than 80 000 monitoring samples are collected by the developed intelligent cooling control system in the Baihetan Arch Dam, which is the largest hydropower project in the world under construction. Machine learning algorithms, including ANN, support vector machines, long short-term memory networks, and decision tree structures, are compared in temperature prediction, and the ANN is determined to be the best for the forecast model. Furthermore, an ANN framework with two hidden layers is determined to forecast concrete temperature at intervals of one day. The root mean square error of the forecast precision is 0.15 ${}^{\mathrm{\circ }}$C on average. The application on concrete blocks verifies that the developed ANN-based forecast model can be used for intelligent cooling control during mass concrete construction.