Cavitation detection for water hydraulic axial piston pump based on physics-informed CNN data augmentation and XGBoost

Robust backstepping sliding mode control with time-driven disturbance observer and command filtering for electro-hydraulic energy recovery systems.

A cloud-based intelligent reconstruction method for low-sampling-rate signals in remote condition monitoring of hydraulic pumps

Abstract There is a current trend towards the electrification of mobile machines that have traditionally been dominated by diesel engine-driven hydraulics, necessitating hydraulic pumps that are driven by electric motors. The benefits to power density are possibly by integrating an electric motor and hydraulic pump inside a single casing. In comparison to coupling a separate electric motor and pump, the integrated machine eliminates a set of bearings and a shaft seal. Additionally, the leakage from the hydraulic pump can be used as a coolant for the electrical machine, improving power density. In this paper, a hydrostatic radial piston pump is proposed to integrate with an axial flux PM machine. This pump uses spherical head pistons that can tilt while reciprocating inside the cylinders, eliminating the need for joints at the slippers. To reduce the frictional loss between the slipper pad and the cam at high speeds, the cam freely rotates. In the earlier work, a detailed model of the pump was developed, including the losses, and the pump performance was predicted for an integrated machine. This work focuses on the standalone pump prototype test, which required a separate driver and shaft sealing unlike the integrated machine. The pump mathematical model was therefore modified to account for the shaft seal losses and experimental churning losses. With these modifications, the standalone pump performance was predicted from the mathematical model and then compared with experimental results for an actual pump prototype.

As a core component of hydraulic systems, hydraulic pumps generate vibration signals that contain abundant key features reflecting the operational state of internal machinery. However, most existing fault diagnosis methods rely solely on single-channel vibration data, neglecting the correlations and complementarities among multi-channel signals, which results in unstable and less accurate diagnostic outcomes. To address this limitation, this study proposes an intelligent fault diagnosis approach for hydraulic pumps based on multi-source signal fusion and a dual attention mechanism. First, vibration, pressure, and acoustic signals are transformed into time-frequency feature images, and an RGB image fusion strategy is applied to map the time-frequency representations of different signals into the individual channels of a color image. Subsequently, a convolutional neural network incorporating enhanced channel and spatial attention mechanisms is constructed to extract features from the fused images and perform classification. Experimental results demonstrate that the proposed method significantly improves fault diagnosis performance and outperforms other deep learning-based approaches, offering a novel strategy for intelligent hydraulic pump diagnostics with promising engineering applications.

Many cardiac surgical procedures use cardiopulmonary bypass (CPB), which in neonates requires the heart-lung machine (HLM) to be positioned close to the patient due to their small circulating blood volume. The absence of an MR-compatible blood pump to be used in CPB remains a key challenge for studying perioperative brain injury mechanisms in this high-risk group. This study aims to take the first step toward MR-conditional HLMs by developing hardware, verifying pump hydraulics, and ensuring MR compatibility. This study presents three MR-conditional blood pump prototypes: a roller pump, a non-occlusive roller pump, and a centrifugal pump. MR compatibility was assessed by monitoring for imaging interference during scanning. Hydraulic performance was evaluated with pressure-flow diagrams using a mock circulation test bench. None of the prototypes interfered with MR imaging, and although SNR was reduced by -8.43% ± 7.96%, image quality remained sufficient for reliable assessment of relevant brain regions. Roller and non-occlusive pumps maintained stable flow across pressure heads, with reductions of -4.46 ± 8.02 and -119.33 ± 18.22 mL/min, respectively. The centrifugal pump exhibited pressure-dependent performance (slope -2.21 ± 0.45 mmHg/[L/min]). All pumps generated non-pulsatile flow (SHE < 1000 erg/cm3). All three pumps meet basic MR-conditionality and flow requirements, supporting their potential for use in MRI-guided studies during neonatal cardiac surgery.

The electrification of non-road mobile machinery is advancing to enhance sustainability and reduce emissions. This study investigates how to maximize the efficiency of the retrofitting of a material handler from an internal combustion engine to a battery-powered electric motor, while keeping the hydraulic system unchanged. Using a previously validated model, this study proposes three control strategies for the electric motor and hydraulic pump to enhance efficiency and performance. The first control strategy optimizes hydraulic pump performance within its most efficient displacement range. The second strategy maximizes powertrain efficiency by considering both efficiencies of the electric motor and hydraulic pump. The third strategy uses a servo-actuated valve to adjust the load-sensing margin and exhibits energy savings up to 14.2% and an 11.5% increase in efficiency. The proposed strategies avoid complex optimization algorithms, ensuring practical applicability for small- and medium-sized enterprises, which often face cost constraints and limited scalability.

Shaft misalignment is among the most common faults in rotating machinery, and although many diagnostic methods have been proposed, reliably detecting it under varying load conditions remains a major challenge for vibration-based techniques. To address this issue, this study proposes a new vibration-based misalignment detection framework that leverages cointegration analysis. The approach examines both the stationarity of vibration signals and the residuals derived from the cointegration process. Specifically, it combines the Augmented Dickey–Fuller (ADF) test with cointegration analysis in three stages: (1) applying the ADF test to raw vibration data before cointegration, (2) performing cointegration on the vibration time series, and (3) reapplying the ADF test to the post-cointegrated data. The method was validated using experimental measurements collected from a laboratory-scale test rig comprising a motor, gearbox, and hydraulic gear pump, tested under both healthy and misaligned states with varying degrees of severity. Vibration signals were recorded across multiple load conditions. The results demonstrate that the proposed method can successfully detect misalignment despite load variations, while also providing insights into fault severity. In addition, the residuals from the cointegration process proved to be highly sensitive to damage, highlighting their value as features for vibration-based condition monitoring.

Variable displacement hydraulic pumps are applied to a wide range of fields for energy saving, but the displacement control is easily influenced by changes in dynamic characteristics depending on the operating point, and the control valve and pump displacement have constraints. Therefore, high control performance cannot be obtained without considering these nonlinearities. In a previous study, we designed a pump displacement control system based on a model predictive control (MPC) method that can consider various constraints at the design step. However, the previously presented control system requires the pre-designed reference trajectory of the pump displacement at the design step. Furthermore, the pump displacement cannot track to other reference trajectories. In this study, an extended MPC proposed in a previous study is combined with an adaptive model matching-based MPC with an inverse optimization method, proposed as a control system by the authors. This compensates for modeling errors and optimizes the weights of the evaluation function to achieve tracking to arbitrary time-varying reference trajectories using a virtual reference signal. To improve tracking performance, variable control input constraints, which are also proposed in our previous study, are introduced. The tracking performance of this control system for arbitrary time-varying reference trajectories have been verified by experiments. The experimental results have shown that the proposed control system achieves high tracking accuracy for an arbitrary time-varying reference trajectory and significantly reduces the man-hours for the parameter design of the control system.

Numerical Investigation on Hydraulic Gear Pump Behaviour under Thermal and Pressure-Induced Stressors

Semi-supervised multi-adversarial domain-adaptive fault diagnosis for hydraulic pumps from pressure simulation data to experimental data

Deep transferable model with multi-head attention for small sample fault diagnosis of hydraulic pumps

This article focuses on the problem of building a real-world predictive maintenance system for hydraulic piston pumps. Particular attention is given to the issue of limited data availability regarding the failure state of systems with a damaged valve plate. The main objective of this work was to analyze the impact of imbalanced data on the quality of the failure prediction system. Several data balancing techniques, including oversampling, undersampling, and combined methods, were evaluated to overcome the limitations. The dataset used for evaluation includes recordings from eleven sensors, such as pressure, flow, and temperature, registered at various points in the hydraulic system. It also includes data from three additional vibration sensors. The experiments were conducted with imbalance ratios ranging from 0.5% to a fully balanced dataset. The results indicate that two methods, Borderline SMOTE and SMOTE+Tomek Links, dominate. These methods allowed the system to achieve the highest performance on a completely new dataset with different levels of damaged valve plates, for the balance rate larger than three percent. Furthermore, for balance rates below one percent, the use of data balancing methods may adversely affect the model. Finally, our results indicate the limitations of the use of cross-validation procedures when assessing data balancing methods.

The difficulty in precisely extracting single-fault signatures from hydraulic pump composite faults, which stems from structural complexity and coupled multi-source vibrations, is tackled herein via a new diagnostic technique based on underdetermined blind source separation (UBSS). Utilizing sparse component analysis (SCA), the proposed method achieves blind source separation without relying on prior knowledge or multiple sensors. However, conventional SCA-based approaches are limited by their reliance on a predefined number of sources and their high sensitivity to noise. To overcome these limitations, an adaptive source number estimation strategy is proposed by integrating information–theoretic criteria into density peak clustering (DPC), enabling automatic source number determination with negligible additional computation. To facilitate this process, the short-time Fourier transform (STFT) is first employed to convert the vibration signals into the frequency domain. The resulting time–frequency points are then clustered using the integrated DPC–Bayesian Information Criterion (BIC) scheme, which jointly estimates both the number of sources and the mixing matrix. Finally, the original source signals are reconstructed through the minimum L1-norm optimization method. Simulation and experimental studies, including hydraulic pump composite fault experiments, verify that the proposed method can accurately separate mixed vibration signals and identify distinct fault components even under low signal-to-noise ratio (SNR) conditions. The results demonstrate the method’s superior separation accuracy, noise robustness, and adaptability compared with existing algorithms.

Vibration reduction in axial piston pumps remains challenging due to the difficulty in identifying dominant transfer paths without extensive experimental data. This study proposes a novel power-based transfer path contribution methodology to achieve significant vibration mitigation within the pump system. Firstly, an experimentally validated dynamic model with 4 lumped mass points and 19 degrees of freedom is developed to systematically investigate vibration transmission mechanisms. Based on this theoretical model, we introduce a power-based ranking algorithm to quantitatively evaluate the contributions of dynamic movements and transfer paths to the overall vibration response. Results reveal that the end-cover is the primary radiating component, with rotational motion around the X EC axis being the dominant contributor to total vibration power. Theoretical transfer path analyses further identify PEC1 (cylinder force) and PEC3 (housing force) as the dominant vibration power transmission paths to the end-cover, while PEC2 (shaft force) also contributes significantly at specific frequencies. Based on these insights, a transfer path analysis (TPA)-guided optimization strategy combined with the single-objective genetic algorithm (GA) is implemented to minimize total vibration power by tuning the structural configuration and stiffness parameters of key connection components. The proposed method achieves substantial vibration reduction in the end-cover across multiple frequency bands and yields notable system-level improvements, including reduced housing vibration around the X H axis. These findings validate the theoretical foundation and demonstrate the practical value of the proposed approach for vibration control in hydraulic pumps.

Ever-increasing demands to improve fuel burn efficiency of aero gas turbines lead to rises in fuel system pressures and temperatures, posing challenges for the structural integrity of the pump housing and creating internal deflections that can adversely affect volumetric efficiency. Non-invasive strain and vibration measurements could allow transient effects to be quantified and considered during the design process, leading to more robust fuel pumps. Fuel pumps used on a high bypass turbofan engine were instrumented with optical fibre Bragg grating (FBG) sensors, strain gauges and thermocouples. A hydraulic hand pump was used to facilitate measurements under static conditions, while dynamic measurements were performed on a dedicated fuel pump test rig. The experimental data were compared with the outputs from a finite element (FE) model and, in general, good agreement was observed. Where differences were observed, it was concluded that they arose from the sensitivity of the model to the selection of nodes that best matched the sensor location. Strain and vibration measurements were performed over the frequency range of 0 to 2.5 kHz and demonstrated the ability of surface-mounted FBGs to characterise vibrations originating within the internal sub-components of the pump, offering potential for condition monitoring.

Degradation data plays a crucial role in the reliability assessment and condition monitoring of engineering systems. The stage-wise changes in degradation rates often signal turning points in system performance or potential fault risks. To address the issue of structural changes during the degradation process, this paper constructs a degradation modeling framework based on a two-stage Inverse Gaussian (IG) process and proposes a change-point detection method based on an adjusted CUSUM (cumulative sum) statistic to identify potential stage changes in the degradation path. This method does not rely on complex prior information and constructs statistics by accumulating deviations, utilizing a binary search approach to achieve accurate change-point localization. In simulation experiments, the proposed method demonstrated superior detection performance compared to the classical likelihood ratio method and modified information criterion, verified through a combination of experiments with different change-point positions and degradation rates. Finally, the method was applied to real degradation data of a hydraulic piston pump, successfully identifying two structural change points during the degradation process. Based on these change points, the degradation stages were delineated, thereby enhancing the model’s ability to characterize the true degradation path of the equipment.

Accurately delineating the groundwater source recharge area is of great importance for assessing environmental risks and ensuring the supply of drinking water. In this study, taking the Chengxi Wellfield of Suzhou City, Anhui Province, as an example, the typical groundwater source recharge area with high extraction intensity was studied. Innovatively combining the MODFLOW–MODPATH particle tracking method, a three-dimensional transient groundwater flow model was established for the delineation of the dynamic recharge area. Model calibration showed strong agreement between simulated and observed hydraulic heads, reliably capturing groundwater level dynamics. The simulated results revealed significant head decline at the wellfield center and the formation of an expanding cone. The particle trajectories progressively extended outward, and the boundary of the capture zone was delineated after 12 050 days. Sensitivity analysis identified hydraulic conductivity, specific storage, and pumping rate as the main factors controlling recharge extent and flow dynamics. In addition, the nonlinear response model quantitatively characterized the gradual expansion of the recharge area over time and with pumping intensity. The study confirms the reliability of particle tracking methods for dynamic recharge delineation in complex aquifer systems and provides practical insights for adaptive and sustainable groundwater management under intensified extraction.

Hydraulic pump fault diagnosis by modified slime mold algorithm optimized support vector machine

MLIFT: Multi-scale linear interaction fusion transformer for fault diagnosis of hydraulic pumps