The raw signals produced by internal gear pumps are susceptible to noises brought on by mechanical vibrations and the surrounding environment, and the sample count collected during the various operating periods is not distributed evenly. Accurately diagnosing faults in internal gear pumps is significantly complicated by these factors. In light of these issues, accelerated life testing was performed in order to collect signals from an internal gear pump during various operating periods. Based on the architecture of a convolutional auto-encoder network, preprocessing of the signals in the various operating periods was performed to suppress noise and enhance operating period-representing features. Thereafter, variational mode decomposition was utilized to decompose the preprocessed signal into multiple intrinsic mode functions, and the multi-scale permutation entropy value was extracted for each intrinsic mode function to form a feature set. The feature set was subsequently divided into a training set and a test set, with the training set being trained to utilize a particle swarm optimization–least squares support vector machine network. For pattern recognition, the test set samples were fed into the trained model. The results demonstrated a 99.2% diagnostic accuracy. Compared to other methods of fault diagnosis, the proposed method is more effective and accurate.

Mechanical equipment failure may cause massive economic and even life loss. Therefore, the diagnosis of the failures of machine parts in time is crucial. The rolling bearings are one of the most valuable parts, which have attracted the focus of fault diagnosis. Many successful rolling bearing fault diagnoses have been made based on machine learning and deep learning. However, most diagnosis methods still rely on complex signal processing and artificial features, bringing many costs to the deployment and migration of diagnostic models. This paper proposes an end-to-end continuous/discontinuous feature fusion method for rolling bearing fault diagnosis (C/D-FUSA). This method comprises long short-term memory (LSTM), convolutional neural networks (CNN) and attention mechanism, which automatically extracts the continuous and discontinuous features from vibration signals for fault diagnosis. We also propose a contextual-dependent attention module for the LSTM layers. We compare the method with the other simpler deep learning methods and state-of-the-art methods in rolling bearing fault data sets with different sample rates. The results show that our method is more accurate than the other methods with real-time inference. It is also easy to be deployed and trained in a new environment.

Compared with involute internal gear pumps and gerotor pumps, lower flow ripple is the main advantage of Truninger pumps. Understanding the flow ripple mechanism and characteristics is of great significance to guide the design and manufacture of this type of pump. In this paper, the theoretical flow ripple and flow ripple rate expressions of the pump are derived based on the vector ray method, and the effects of variations of the design parameters of the pump on the theoretical flow ripple characteristics are studied. A three-dimensional numerical simulation model was established in Simerics-MP+ that accounted for the fluid properties and cavitation. All the geometric features, including unloading grooves, the oil distribution areas, the shapes of the suction and delivery passageways, and the axial and radial leakage gaps, were considered to achieve the highest accuracy in the prediction of flow ripple. Finally, a flow ripple test platform was built based on the secondary source method. The validity and accuracy of the model were verified by test results. The flow ripple characteristics under different working conditions were compared and analyzed. The following conclusions were obtained: (1) The smaller module, the larger addendum coefficient and the half angle of the tooth profile in the design process, the lower the pump speed during operation is beneficial to reduce the vibration and noise of this pump; (2) Flow ripple is the comprehensive result of the oil characteristics, internal leakage, and geometric characteristics through the comparisons of theoretical, simulation and experimental results; (3) The flow ripple amplitude and the ripple rate increased with the increase in the outlet pressure and the influence of the pump speed variations on the flow ripple characteristics is less than that of outlet pressure variations. The conclusions obtained in this paper will help designers understand the flow ripple mechanism, achieve low-noise pump designs, and optimize Truninger pumps.

Based on the principle of symmetry, we propose a variable step-size FxLMS algorithm with double nonlinear functions cooperative coupling (DNVSS-FxLMS), aiming to optimize the contradiction between convergence rate and steady-state error in the active pressure pulsation control system of hydraulic systems. The algorithm innovatively couples two types of nonlinear mechanisms (rational-fractional and exponential-function-based), constructing a refined error-step mapping relationship to achieve a balance between rapid convergence and low steady-state error. Simulation experiments were conducted considering the complex time-varying operating environment of a simulation-based hydraulic system. The results demonstrate that, when the system undergoes unstable random changes, the DNVSS-FxLMS algorithm converges at least twice as fast as traditional and existing variable step size algorithms, while reducing steady-state error by 2–5 dB. The proposed DNVSS-FxLMS algorithm exhibits significant advantages in convergence rate, steady-state error reduction, and tracking capability, providing a highly efficient and robust solution for real-time active control of hydraulic system pressure pulsation under complex operating conditions.

The fluid–structure interaction effect should not be disregarded when examining the vibration characteristics of hydraulic pipeline systems. The transfer matrix method (TMM) is an efficacious method for analyzing the vibration characteristics of hydraulic pipelines in the frequency domain, offering advantages such as simplicity and efficiency. However, the TMM suffers the problem of high frequency instability when dealing with long-span hydraulic pipelines, which restricts its practical application. Currently, several modified transfer matrix methods face challenges such as low computational efficiency and difficulties in handling complex boundaries. In response to these issues, this paper proposes a novel modified transfer matrix method known as the mixed variable transfer matrix method. This innovative method possesses clear physical significance and effectively prevents the transfer matrix from becoming singular without necessitating the subdivision of the pipeline length. Consequently, it addresses high-frequency instability while maintaining high computational efficiency. Moreover, this method is capable of addressing complex boundary problems by integrating boundary matrices, thereby demonstrating enhanced applicability compared to existing methods. The performance of the proposed method was validated through the utilization of classic Dubee pipeline impact test data, and the result shows maximum errors of 3.03% relative to the public data. Subsequently, an experiment was conducted on a section of hydraulic piping within a ship’s steering system. A hydraulic fluid noise generator was established to induce fluid pulsation excitation to the pipeline, thereby simulating the actual boundary conditions encountered in a ship’s hydraulic pipeline system so as to corroborate the efficacy of the proposed method in predicting the frequency domain vibration characteristics of a real hydraulic pipeline system. The experimental results indicate that the proposed method offers significant advantages in terms of high precision, efficiency, and stability, shows maximum errors of 4.35% relative to experimental data, and demonstrates promising prospects for engineering applications.

The operational characteristics of Electro-Hydraulic Actuator(EHA) result in the EHA internal pump facing complex conditions of variable speed, pressure and even direction, resulting in poor lubrication state of friction pairs. To study the evolution of lubrication states under varying working conditions, a joint simulation model using Simerics-MP+(Version: 5.2.13, https://www.simerics.com) and MATLAB(Version: R2020a, https://www.mathworks.com/products/matlab.html) was established, focusing on the gear ring/shell friction pair as the subject of study. The model was used to predict the micro-motion trajectory of the gear ring, and the results were validated through experimental measurements of dynamic changes. Results indicate that the simulation model can accurately predict oil film variations, with a calculation error of less than 7.6% for oil film thickness. The reduction in speed and the increase in load pressure will deteriorate the lubrication characteristics of the oil film in the friction pair. Under pump operating conditions, when the direction reversing rate increases from 20,000 rpm/s to 40,000 rpm/s, the average oil film thickness increases by 23.64%, while the fluctuation rate decrease by 2.57%. Similarly, when the direction reversing pressure decreases from 10 MPa to 5 MPa, the average oil film thickness increases by 22.39%, and the fluctuation rate decreases by 8.17%. During pump-motor working condition switching, an increase in the switching rate from 10,000 rpm/s to 40,000 rpm/s results in a 10.33% increase in average oil film thickness and a 20.9% decrease in fluctuation rate. This study significantly contributes to enhancing our comprehension of the evolutionary patterns of friction pairs in EHA internal pumps under varying operational conditions.