Deterioration trend prediction of hydropower units helps to detect abnormal conditions of hydropower units and can prevent early failures. The reliability and accuracy of the prediction results are crucial to ensure the safe operation of the units and promote the stable operation of the power system. In this paper, the long short-term neural network (LSTM) is introduced, a comprehensive deterioration index (CDI) trend prediction model based on the time–frequency domain is proposed, and the prediction accuracy of the situation trend of hydropower units is improved. Firstly, the time–domain health model (THM) is constructed with back-propagation neural network (BPNN) and condition parameters of active power, guide vane opening and blade opening and the time–domain indicators. Subsequently, a frequency-domain health model (FHM) is established based on ensemble empirical mode decomposition (EEMD), approximate entropy (ApEn), and k-means clustering algorithm. Later, the time–domain degradation index (TDI) is developed according to THM, the frequency-domain degradation index (FDI) is constructed according to FHM, and the CDI is calculated as a weighted sum by TDI and FDI. Finally, the prediction model of LSTM is proposed based on the CDI to achieve degradation trend prediction. In order to validate the effectiveness of the CDI and the accuracy of the prediction model, the vibration waveform dataset of a hydropower plant in China is taken as a case study and compared with four different prediction models. The results demonstrate that the proposed model outperforms other comparison models in terms of predicting accuracy and stability.

Fault diagnosis plays an essential role in maintaining the safe and stable operation of hydroelectric units. In this paper, an intelligent fault diagnosis method based on radar maps and improved GoogleNet by depthwise separate convolution (DSC) is proposed to address the problems of low recognition accuracy and weak computing speed of fault diagnosis models in the field of hydroelectric unit fault diagnosis at present. Firstly, a one-dimensional signal sequence is obtained and denoised. Secondly, five time-domain features are extracted and radar maps are plotted. Then, an improved GoogleNet intelligent fault diagnosis model based on DSC (DSC-GoogLeNet) is constructed for training and validation. To assess the effectiveness of the proposed model, two case studies are conducted using the simulated dataset of the rotor experimental bench and the actual measured dataset of a domestic hydroelectric power plant. The results demonstrate that the average recognition accuracy of the fault diagnosis method proposed in this paper is as high as 99.04% on the simulated dataset, and even though the recognition accuracy decreases on the actually measurement dataset, it still has a recognition rate of 98.79%. The fault diagnosis performance is better than the other types of comparison models. The results demonstrate that the proposed fault diagnosis method holds significant engineering applicability in the domain of safe operation of hydroelectric units. It effectively addresses the existing challenges in fault diagnosis within this field with accuracy, stability, and efficiency.

Nonlinear modeling of the hydroturbine is one of the current research hot spots. The existing nonlinear hydroturbine model lacks “memory capability,” which means that the output of the model is not related to the historical input and output; that is, the model is a description of the static characteristics of the hydroturbine. To address this issue, based on actual operation data, this paper proposes long short‐term memory artificial neural network (LSTMNN) with output feedback to realize real‐time dynamic modeling of hydroturbine. Firstly, the torque characteristic sample data are calculated from the actual operation data, and the operation data of the hydropower unit are converted into the discharge characteristic sample data through hydroturbine test data. Then, by training LSTM neural networks with different feedback orders, the optimal order is got, and at the same time, the superiority of replacing time lag with the output feedback is verified. On this basis, a feedback‐based hydroturbine LSTMNN model is obtained. Finally, the proposed modeling method is compared with standard back‐propagation neural network with output feedback (F‐BPNN), through which the effectiveness and applicability are verified. The results show that: (a) By introducing output feedback, the accuracy of nonlinear hydroturbine model can be increased and the proposed modeling method is better than F‐BPNN; (b) the hydroturbine LSTMNN model can not only describe the static characteristics, but also reflect the real‐time dynamic characteristics; (c) taking the actual operation data of hydroturbine as the sample data source, the proposed modeling method can replace the traditional modeling method and effectively improve the numerical simulation accuracy.