This study focuses on the fault diagnosis of a hydroelectric generation system with hydraulic‐mechanical‐electric structures. To achieve this analysis, a methodology combining Bayesian network approach and fault diagnosis expert system is presented, which enables the time‐based maintenance to transform to the condition‐based maintenance. First, fault types and the associated fault characteristics of the generation system are extensively analyzed to establish a precise Bayesian network. Then, the Noisy‐Or modeling approach is used to implement the fault diagnosis expert system, which not only reduces node computations without severe information loss but also eliminates the data dependency. Some typical applications are proposed to fully show the methodology capability of the fault diagnosis of the hydroelectric generation system.

Water is the source of all things, so it can be said that without the sustainable development of water resources, there can be no sustainable development of human beings. In recent years, sudden water pollution accidents have occurred frequently. Emergency response plan optimization is the key to handling accidents. Nevertheless, the non-linear relationship between various indicators and emergency plans has greatly prevented researchers from making reasonable assessments. Thus, an integrated assessment method is proposed by incorporating an improved technique for order preference by similarity to ideal solution, Shannon entropy and a Coordinated development degree model to evaluate emergency plans. The Shannon entropy method was used to analyze different types of index values. TOPSIS is used to calculate the relative closeness to the ideal solution. The coordinated development degree model is applied to express the relationship between the relative closeness and inhomogeneity of the emergency plan. This method is tested in the decision support system of the Middle Route Construction and Administration Bureau, China. By considering the different nature of the indicators, the integrated assessment method is eventually proven as a highly realistic method for assessing emergency plans. The advantages of this method are more prominent when there are more indicators of the evaluation object and the nature of each indicator is quite different. In summary, this integrated assessment method can provide a targeted reference or guidance for emergency control decision makers.

The changes in cracks on the surface of rock mass reflect the development of geological disasters, so cracks on the surface of rock mass are early signs of geological disasters such as landslides, collapses, and debris flows. To research geological disasters, it is crucial to swiftly and precisely gather crack information on the surface of rock masses. Drone videography surveys can effectively avoid the limitations of the terrain. This has become an essential method in disaster investigation. This manuscript proposes rock crack recognition technology based on deep learning. First, images of cracks on the surface of a rock mass obtained by a drone were cut into small pictures of 640 × 640. Next, a VOC dataset was produced for crack object detection by enhancing the data with data augmentation techniques, labeling the image using Labelimg. Then, we divided the data into test sets and training sets in a ratio of 2:8. Then, the YOLOv7 model was improved by combining different attention mechanisms. This study is the first to combine YOLOv7 and an attention mechanism for rock crack detection. Finally, the rock crack recognition technology was obtained through comparative analysis. The results show that the precision of the improved model using the SimAM attention mechanism can reach 100%, the recall rate can achieve 75%, the AP can reach 96.89%, and the processing time per 100 images is 10 s, which is the optimal model compared with the other five models. The improvement is relative to the original model, in which the precision was improved by 1.67%, the recall by 1.25%, and the AP by 1.45%, with no decrease in running speed. This proves that rock crack recognition technology based on deep learning can achieve rapid and precise results. It provides a new research direction for identifying early signs of geological hazards.

The Long Short-Term Memory (LSTM) neural network model is an effective deep learning approach for predicting streamflow, and the investigation of the interpretability of deep learning models in streamflow prediction is of great significance for model transfer and improvement. In this study, four key hydrological stations in the Xijiang River Basin (XJB) in South China are taken as examples, and the performance of the LSTM model and its variant models in runoff prediction were evaluated under the same foresight period, and the impacts of different foresight periods on the prediction results were investigated based on the SHapley Additive exPlanations (SHAP) method to explore the interpretability of the LSTM model in runoff prediction. The results showed that (1) LSTM was the optimal model among the four models in the XJB; (2) the predicted results of the LSTM model decreased with the increase in foresight period, with the Nash–Sutcliffe efficiency coefficient (NSE) decreasing by 4.7% when the foresight period increased from one month to two months, and decreasing by 3.9% when the foresight period increased from two months to three months; (3) historical runoff had the greatest impact on streamflow prediction, followed by precipitation, evaporation, and the North Pacific Index (NPI); except evaporation, all the others were positively correlated. The results can provide a reference for monthly runoff prediction in the XJB.

In this study, a Bayesian network (BN)-based inhibition model is developed for the rainstorm–landslide–debris flow (R-L-D) disaster chain in the mountainous area of the Greater Bay Area (GBA), China, using the historical disaster data. Twelve nodes are selected for the inhibition model, which are classified into four types, including Hazardous Factor, Response Operation, Disaster Evolution, and Disaster Result. By combining the proposed inhibition with the scenario analysis method, the probabilities of the BN nodes under different rainfall scenarios are analyzed, and then the inhibitory effects of the environmental geological conditions and rescue speed on the R-L-D disaster chain under the most unfavorable rainfall scenario are investigated. On this basis, an inhibition framework consisting of the early warning, inhibition, and measures layers is proposed for the R-L-D disaster chain. The results reveal that under the most unfavorable rainfall scenarios, where the rainfall intensity is greater than 100 mm/d and the rainfall duration is greater than 24 h, the probability of landslides and debris flow is 0.930 and 0.665, respectively. Improving the environmental geological conditions such as slope, lithology and geological structure can greatly inhibit the occurrence of the R-L-D disaster chain. Moreover, the improvement of geological structure conditions is the most significant, and reduces the probability of landslides and debris flow by 0.684 and 0.430, respectively, as well as reducing the probability of death and direct economic loss by 0.411 and 0.619, respectively. Similarly, increasing the rescue speed leads to a reduction in the probability of death and direct economic loss by 0.201 and 0.355, respectively. This study can provide theoretical and practical insights into the prevention and inhibition of the R-L-D disaster chain.