Fault diagnosis plays an important role in maintaining the safe and stable operation of hydropower units. This paper presents an intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits. Firstl the vibration signals in the X and Y directions that constitute the axis orbit of the unit shaft are processed by the denoising method based on modal decomposition and permutation entropy. Second, the relative position and distribution of the axis orbits for different samples in the image window are unified. Third, the trained convolution neural network is chosen as the classifier to recognize the axis orbit image for fault-type recognition. Through the analysis of the measured data of a hydropower station, the influence of the sample number of the training set and the size of the axis orbit image on the performance of the proposed method and the necessity of denoising operation are studied. Compared with the existing methods, the proposed method has higher fault recognition accuracy and better generalization performance for different training sample sets. The results indicate that the proposed method is an effective alternative for the fault diagnosis of hydropower units.

Axis-orbit recognition is an essential means for the fault diagnosis of hydropower units. An axis-orbit recognition method based on feature combination and feature selection is proposed, aiming to solve the problems of the low recognition accuracy, poor robustness, and low efficiency of existing axis-orbit recognition methods. First, various contour, moment, and geometric features of axis orbit samples are extracted from the original data and combined into a multidimensional feature set; then, Random Forest (RF)-Fisher feature selection is applied to realize feature dimensionality reduction; and finally, the selected features are set as the input of the support vector machine (SVM), which is optimized by the gravitational search algorithm (GSA) for axis-orbit recognition. The analytical results show that the proposed method has high recognition efficiency and good robustness while maintaining high accuracy for axis-orbit recognition.

Hydraulic impedance, as an efficient frequency-domain analysis alternative, has been widely utilized in hydraulic transient analysis for decades. Since the mathematical expressions of hydraulic systems with complicated pipe networks are usually rather complex, it is difficult for the traditional continuous impedance method to obtain the analytical solutions to the system’s frequency responses directly. Therefore, an equivalent circuit modeling-based discrete impedance method is proposed to mathematically express the hydraulic systems of a pumped storage plant system with complicated pipe networks. Through drawing an analogy between various hydraulic facilities and different types of electrical circuits, the equivalent circuit topology of any hydraulic system can be obtained according to the circuit theory in electrical engineering. The oscillation analysis of the pumped-storage power plant is conducted, and influences of the pump-turbine impedance on the system’s oscillation characteristics have been discussed.