Aiming at addressing the problem that the faults in axial piston pumps are complex and difficult to effectively diagnose, an axial piston pump fault diagnosis method that is based on the combination of Mel-frequency cepstrum coefficients (MFCC) and the extreme learning machine (ELM) is proposed. Firstly, a sound sensor is used to realize contactless sound signal acquisition of the axial piston pump. The wavelet packet default threshold denoises the original acquired sound signals. Afterwards, windowing and framing are added to the de-noised sound signals. The MFCC voiceprint characteristics of the processed sound signals are extracted. The voiceprint characteristics are divided into a training sample set and test sample set. ELM models with different numbers of neurons in the hidden layers are established for training and testing. The relationship between the number of neurons in the hidden layer and the recognition accuracy rate is obtained. The ELM model with the optimal number of hidden layer neurons is established and trained with the training sample set. The trained ELM model is applied to the test sample set for fault diagnosis. The fault diagnosis results are obtained. The fault diagnosis results of the ELM model are compared with those of the back propagation (BP) neural network and the support vector machine. The results show that the fault diagnosis method that is proposed in this paper has a higher recognition accuracy rate, shorter training and diagnosis times, and better application prospect.

This paper addresses the difficulty of evaluating operating status in widely used gear pumps. A method for constructing hydraulic pump health indicators and evaluating health status is proposed based on LSTM–VAE. In this study, the vibration signal data source of gear pumps was assessed in the accelerated life test. Firstly, the normalized feature vectors of the whole-life operation data of gear pumps were extracted by wavelet packet decomposition and amplitude feature extraction. Combining an LSTM algorithm with a VAE algorithm, a method for constructing hydraulic pump health indicators based on LSTM–VAE is proposed. By learning the feature vectors of gear pumps in varying health conditions, a one-dimensional HI curve of the gear pumps was obtained. Then, LSTM was used to predict the HI curve of gear pumps. According to the volume efficiency of the gear pumps, the health status of gear pumps is divided into four states: health, sub-health, deterioration, and failure. The health status of the hydraulic pump is accurately evaluated by the health indicator. Finally, the proposed method is compared with the traditional method based on feature selection and PCA dimensionality reduction. The health indicator constructed by the method proposed in this paper is superior to the traditional method in terms of tendency, robustness, and monotonicity, which proves the effectiveness of the method proposed in this paper.

The rolling mill with hydraulic system is widely used in the production of strip steel. For the problem of vertical vibration of the rolling mill, the effects of different equivalent damping coefficient, leakage coefficient, and proportional coefficient of the controller on the hydraulic screw down system of the rolling mill are studied, respectively. First, a vertical vibration model of a hydraulic screw down system was established, considering the nonlinear friction and parameter uncertainty of the press cylinder. Second, the correlation between different equivalent damping coefficient, internal leakage coefficient, proportional coefficient, vertical vibration was analyzed. The simulation results show that, in the closed-loop state, when Proportional-Integral-Derivative (PID) controller parameters are fixed, due to the change of the equivalent damping coefficient and internal leakage coefficient, the system will have parameter uncertainty, which may lead to the failure of the PID controller and the vertical vibration of the system. This study has theoretical and practical significance for analyzing the mechanism of vertical vibration of the rolling mill.

To improve the identification accuracy of leakage layer location in an open-hole well with a distributed fiber optic temperature system, a transient temperature field heat transfer numerical calculation model for bare hole wellbore leakage process was established based on process of the distributed fiber optic open-hole well temperature measurement technology, considering factors such as drilling fluid frictional pressure drop, casing section and bare hole section boundary conditions. The distributed fiber optic test data was compared with the calculation model, and the wellbore calculated temperature distribution was consistent with the test temperature curve, and the temperature characteristics of the leakage layer location were obvious, with a maximum error of less than 5.5%. The calculation results show that when using distributed fiber optic open-hole well leak detection, by extending the continuous injection time of drilling fluid to 30 min and increasing the injection flow rate of drilling fluid by 30 L/s, the temperature at the wellbore leak location reaches 2.7 °C and 6.6 °C, respectively, which can reduce the difficulty of identifying the leak location and improve the accuracy of leak location identification. However, after changing the type of drilling fluid, the calculated wellbore temperature distribution showed a difference of no more than 0.01 °C. When detecting the location of the leakage layer in open-hole wells with high temperature gradients, the temperature difference at the leakage layer is more pronounced, which can reduce the difficulty of leak location via distributed fiber optic system.