Search Results (43)

A fault diagnosis method based on meta-learning and an improved multi-channel convolutional neural network (MAML-MCCNN-ISENet) was proposed to solve the problems of insufficient feature extraction and low fault type identification accuracy of vibration signals at small sample sizes. The signal is first preprocessed using adaptive chirp mode decomposition (ACMD) methods. A multi-channel input structure is then employed to process the multidimensional signal information after preprocessing. The improved squeeze and excitation networks (ISENets) have been enhanced to concurrently enhance the network’s adaptive perception of the significance of each channel feature. On this basis, a meta-learning strategy is introduced, the learning process of model initialization parameters is improved, the network is optimized by a multi-task learning mechanism, and the initial parameters of the diagnosis model are adaptively adjusted, so that the model can quickly adapt to new fault diagnosis tasks on limited datasets. Then, the overfitting problem under small sample conditions is alleviated, and the accuracy and robustness of fault identification are improved. Finally, the performance of the model is verified on the experimental data of the fault diagnosis of the laboratory plunger pump and the vibration dataset of the centrifugal pump of the Saint Longoval Institute of Engineering and Technology. The results show that the diagnostic accuracy of the proposed method for various diagnostic tasks can reach more than 90% on small samples. Full article

With the aim of addressing the low volumetric efficiency of CO₂ swashplate axial piston pumps, the influence of four volumetric losses—loss of the CO₂ compression retention volume, leakage volume loss of the port pair, leakage volume loss of the plunger pair, and leakage volume loss of the slipper pair—on volumetric efficiency was analyzed using a transient numerical simulation method. The numerical simulation results showed that the real physical property model can accurately describe the compression retention characteristics of CO₂ under high-pressure conditions. CO₂ compression retention volume loss accounted for 28.6% of the volumetric efficiency and was the main factor causing low volumetric efficiency of the piston pump. Leakage volume losses of the slipper pair, the flow distribution pair, and the plunger pair accounted for about 3.4%, 1.5%, and 0.5% of the volumetric efficiency, respectively. These research results provide a reference for volumetric efficiency loss analyses of piston pumps. Full article

The damping groove structure of the port plate plays a crucial role in the pulsation suppression, vibration reduction, and noise optimization of the piston pump. Different damping groove structures have a significant impact on the flow distribution process during the normal operation of the port plate, affecting the pump outlet flow and pressure pulsations, which in turn influence the noise level of the piston pump. Therefore, the damping groove in the piston pump is one of the key structures influencing the pump’s pressure and cavitation behavior. To address the pressure shocks and oscillations caused by the distribution process in the piston pump, this study proposes a novel damping groove and performs CFD simulations on the non-damped groove. The analysis focuses on the pressure pulsation characteristics in the plunger chamber and the cavitation behavior of the pump. Additionally, an optimization analysis of the structural parameters of the new damping groove is conducted, which effectively reduces pressure shocks and cavitation in the swash plate axial piston pump. This study provides a theoretical foundation for improving the performance and lifespan of piston pumps. Full article

Carbon fiber composite sucker rods represent a technological innovation in oil production systems, exhibiting excellent performance. This sucker rod not only improves oil production efficiency and reduces accidents, but also saves energy and lowers the operating costs of oil wells. However, the working conditions of the carbon fiber composite sucker rod oil extraction system are relatively complex. The carbon fiber composite sucker rod body adopts a symmetrical structure formed by one-time solidification of three layers of fiber (carbon/glass fiber) materials, requiring the use of steel sucker rods in combination, and the impact of various system parameters is not fully understood. This paper focuses on the carbon fiber composite sucker rod as the research object, analyzing the external loads of the carbon fiber composite sucker rod oil extraction system. It also establishes a mechanical model of carbon fiber composite sucker rods, adopts a new finite element modeling method for sucker rod pumping systems, conducts transient dynamic analysis on the lifting motion of carbon fiber composite sucker rods in oil wells, and optimizes system parameters. The example verifies the rationality and feasibility of the finite element model. The results show that the higher the dynamic viscosity of crude oil, the more polished rod dynamometer cars tend to approach a “parallelogram”, and the polished rod load becomes more stable during the lifting process. With larger strokes, the maximum polished rod load increases, the longitudinal vibration amplitude of the carbon fiber composite sucker rod increases, and the load variation becomes more unstable. As the number of strokes increases, the maximum polished rod load and the pump plunger stroke length both increase, leading to higher pump efficiency, but the fluctuation amplitude of the polished rod dynamometer cars also increases, which affects the stability of the sucker rod’s lifting motion. When the carbon fiber sucker rod ratio exceeds 0.5, the difference between the self-weight and polished rod load initially decreases, then increases. As the carbon fiber sucker rod ratio increases, the pump plunger stroke length gradually decreases, and pump efficiency declines. Full article

The high-pressure common rail (HPCR) injection system, a key technology for enhancing diesel engine performance, plays a decisive role in ensuring fuel injection precision and combustion efficiency through rail pressure stability. This study establishes a coupled simulation model of an electronically controlled HPCR injection system and a diesel engine, using GT-Suite to systematically investigate the effects of fuel supply pressure, camshaft speed, high-pressure pump plunger parameters, and inlet and outlet valve characteristics on rail pressure fluctuations. Gray relational analysis quantifies the correlation between these factors and rail pressure variations. The results demonstrate that increasing camshaft speed, injection pulse width, plunger mass, plunger length, plunger spring preload, inlet valve spring preload, and outlet valve body mass reduces rail pressure fluctuations, while variations in fuel supply pressure, plunger spring stiffness, and valve spring stiffness have minimal impact. Notably, the influence of outlet valve spring preload, inlet valve spring stiffness, and inlet valve body mass on rail pressure is nonlinear, with optimal values observed. Gray relational analysis further identifies inlet valve spring preload as having the highest correlation with rail pressure fluctuations (0.815), followed by inlet valve spring stiffness (0.625), with outlet valve spring preload (0.551) and stiffness (0.527) showing relatively lower correlations. This study provides valuable insights for optimizing the HPCR injection system design and contributes to advancements in diesel engine technology. Full article

Current trends in the development of technology are linked inextricably to the increasing level of automation in technological processes and production systems. In this regard, the development of systems for supplying working fluids with adjustable pumps that have high performance characteristics, an increased service life and low operating costs is an important scientific and technical task. A primary challenge in the development of such systems lies in achieving low fluid flow rates while maintaining stable operating characteristics. This challenge stems from the fact that currently available controlled hydraulic pumps exhibit either a high cost or suboptimal life and efficiency parameters. This work focuses on the development of a plunger hydraulic pump with a small working volume. A mathematical model has been developed to investigate the characteristics, optimize the design of this pump and further expand the size range of such pumps. The solution was implemented on a computer using the dynamic modelling environment MATLAB/Simulink. In order to verify the mathematical model’s adequacy, a plunger pump prototype was built and integrated with a test bench featuring a measurement system. The test results showed higher pump efficiency and a significant reduction in hydraulic losses. An analysis of the obtained data shows that the pump is characterized by increased efficiency due to optimal flow distribution and reduced internal leakage, which makes it promising for use in hydraulic systems requiring improved operating characteristics. The developed pump has more rational characteristics compared to existing alternatives for use in water supply systems for induction superheaters. The experimental external characteristics of the developed pump are 10% higher than the external characteristics of the ULKA EX5 pump selected as an analogue, and the pressure characteristics are 65% higher. It offers production costs that are several times lower compared to existing cam-type plunger or diaphragm pumps with oil sumps and precision valve mechanisms. Additionally, it has significantly better operating characteristics and a longer service life compared to vibrating plunger pumps. Full article

To fully exploit the rich state and fault information embedded in the acoustic signals of a hydraulic plunger pump, this paper proposes an intelligent diagnostic method based on sound signal analysis. First, acoustic signals were collected under normal and various fault conditions. Then, four distinct acoustic features—Mel Frequency Cepstral Coefficients (MFCCs), Inverse Mel Frequency Cepstral Coefficients (IMFCCs), Gammatone Frequency Cepstral Coefficients (GFCCs), and Linear Prediction Cepstral Coefficients (LPCCs)—were extracted and integrated into a novel hybrid cepstral feature called MIGLCCs. This fusion enhances the model’s ability to distinguish both high- and low-frequency characteristics, resist noise interference, and capture resonance peaks, achieving a complementary advantage. Finally, the MIGLCC feature set was input into a double layer long short-term memory (DLSTM) network to enable intelligent recognition of the hydraulic plunger pump’s operational states. The results indicate that the MIGLCC-DLSTM method achieved a diagnostic accuracy of 99.41% under test conditions. Validation on the CWRU bearing dataset and operational data from a high-pressure servo motor in a turbine system yielded overall recognition accuracies of 99.64% and 98.07%, respectively, demonstrating the robustness and broad application potential of the MIGLCC-DLSTM method. Full article

The emulsion pump’s flow loss directly affects its performance and efficiency. However, the annular plunger chamber leakage and valve core hysteresis are challenging to avoid during operation. This study systematically investigated the impact of the annular gap in the plunger cavity on emulsion pump performance. Using theoretical analysis and computational fluid dynamics methods, it explored the mechanism of the port valve hysteresis during discharge. The simulation results show that the leakage of the annular gap is proportional to the gap thickness and the inlet pressure and inversely proportional to the dynamic viscosity of the emulsion. With the increase of plunger eccentricity, the leakage increases slowly. The increase in the outlet diameter of the port valve will lead to more significant hysteresis of the valve core. The change of outlet pressure has little effect on the hysteresis and flow of the spool, and the response speed of the wing-guided bevel discharge valve is faster than that of the ordinary poppet valve. Considering the above factors, the flow distribution process of the emulsion pump can be accurately analyzed, providing a reference for pump optimization. Full article

Reciprocating pumps are widely used in the current oil extraction process, and the plunger is a vulnerable part of these pumps that directly determines the service life of the reciprocating pump. To improve the service life of plungers, Ni60/WC coatings were applied to the surface of 45-steel plungers via laser cladding technology to improve wear and corrosion resistance. Defect-free and dense Ni60/WC coatings were successfully applied to the plunger surface with strong metallurgical bonding between the coating and the substrate. The coating consists mainly of a γ-(Ni, Fe) phase, which contains isotropic and isotropic-like crystals, dendritic crystals, and columnar crystals in the top, middle, and bottom regions of the coating, respectively. The service performance of the laser cladding coating was compared to the flame-sprayed plunger, which is widely used, and the laser cladding coating has a microhardness of up to 821.8 HV_0.5, which is higher than that of the flame-sprayed coating (545.5 HV_0.5) and the 45-steel substrate (200 HV_0.5). The laser cladding coating has a lower friction coefficient and a smaller volumetric wear rate, and the corrosion current density and corrosion rate in the NaCl solution are 2.52 × 10⁻⁷ A/cm² and 2.96 × 10⁻³ mmPY, respectively, which indicates superior corrosion resistance to the flame-sprayed coating and the substrate. The laser cladding of reciprocating pump plunger surfaces has a significantly improved comprehensive performance and is a promising way to increase the service life of reciprocating pumps. Full article

For the variable speed variable displacement power unit (VSVDPU), achieving power matching between the permanent magnet synchronous motor (PMSM) and the variable displacement plunger pump (VDPP) is the key to reducing system energy consumption. The control method of adjusting the speed of the PMSM and the displacement of the VDPP is the mainstay of current research and application of the VSVDPU. However, the dynamic properties of the PMSM and VDPP have not been balanced, which affects the control effect of the VSVDPU. This paper proposes a control method of variable speed and variable displacement with low energy consumption and high dynamics. The main idea is based on the efficiency model and dynamic response model of the PMSM and VDPP, and the factors that affect the efficiency and dynamic characteristics of the VSVDPU are analyzed. Guided by the multi-objective optimization algorithm, the optimal combination of speed and displacement under specific working conditions is derived. Simulation and experiment results show that the proposed control method is feasible to improve the efficiency and dynamic characteristics of the VSVDPU. Full article

Mechanical condition monitoring data in real engineering are often severely unbalanced, which can lead to a decrease in the stability and accuracy of intelligent diagnosis methods. In this paper, a fault diagnosis method based on the SMOTE + Tomek Link and dual-channel feature fusion is proposed to improve the performance of the sample imbalance fault diagnosis method, taking the piston pump of a turnout rutting machine as the research object. Combining the data undersampling method and the oversampling method to redistribute the collected normal data and fault data makes the diagnostic model have better diagnostic performance in the case of insufficient fault samples. And, in order to fully utilize the global features and local features, a global–local feature complementary module (GLFC) is proposed. Firstly, the generated data similar to the original data are constructed using the SMOTE + Tomek Link method; secondly, the generated data are input into a GLFC module and BiGRU at the same time, the GLFC module extracts the spatial global features and local features of the original vibration data, and BiGRU extracts the temporal information features of the original vibration data, and fuses the extracted feature information, and inputs the fused features into the attention layer; finally, a GLFC module is proposed by the SMOTE + Tomek Link method to make full use of the global features and local features. The extracted feature information is fused, and the fused features are input to the attention layer; finally, the fault classification is completed by the softmax classifier. In this paper, the accuracy and robustness of the proposed model are demonstrated through experiments. Full article

Based on the effect of damped shear deformation on energy dissipation, a new constrained damping base for a polymer injection platform deck is proposed to reduce the excessive vibrations caused when multiple plunger pumps are jointly operated. A model for analyzing the vibration response of an I-beam-constrained damping base for a polymer injection platform with multiple plunger pumps was established using Abaqus 6.14 software and compared with rigid base and traditional rubber vibration isolators in terms of its vibration isolation performance. Furthermore, the effects of the damping material’s loss factor, the thickness of the damping layer, and the number of expansion layers on the vibration isolation characteristics of the constrained damping base were explored. This study shows that, with an increase in the damping material’s loss factor, the thickness of the damping layer and the number of extended layers, the vibration isolation performance of the constrained damping base is gradually enhanced. When the damping material’s loss factor is 1.0, the thickness of the damping layer is 20 mm, and the number of extended layers is 3, the constrained damping base’s vibration damping effect is optimized, and its vibration isolation rate becomes as high as 46.63%, which can significantly reduce the vibration response of the polymer injection platform. Full article

In order to realize the accurate and reliable fault diagnosis of hydraulic systems, a diagnostic model based on improved tuna swarm optimization (ITSO), optimized convolutional neural networks (CNNs), and bi-directional long short-term memory (BiLSTM) networks is proposed. Firstly, sensor selection is implemented using the random forest algorithm to select useful signals from six kinds of physical or virtual sensors including pressure, temperature, flow rate, vibration, motor power, and motor efficiency coefficient. After that, fused features are extracted by CNN, and then, BiLSTM is applied to learn the forward and backward information contained in the data. The ITSO algorithm is adopted to adaptively optimize the learning rate, regularization coefficient, and node number to obtain the optimal CNN-BiLSTM network. Improved Chebyshev chaotic mapping and the nonlinear reduction strategy are adopted to improve population initialization and individual position updating, further promoting the optimization effect of TSO. The experimental results show that the proposed method can automatically extract fusion features and effectively utilize multi-sensor information. The diagnostic accuracies of the plunger pump, cooler, throttle valve, and accumulator are 99.07%, 99.4%, 98.81%, and 98.51%, respectively. The diagnostic results of noisy data with 0 dB, 5 dB, and 10 dB signal-to-noise ratios (SNRs) show that the ITSO-CNN-BiLSTM model has good robustness to noise interference. Full article

Most energy-saving testing methods for plunger pumps use hydraulic motors. The loading test of coal mine emulsion pumps generally uses an overflow valve as the loading unit, which is characterized by high energy consumption. The coal mine emulsion pump uses emulsion as the transmission medium, and the viscosity and lubricity of the emulsion are much lower than those of hydraulic oil, which creates great difficulties in the development of high water-based hydraulic products. The nominal flow rate of the emulsion motor is much smaller than that of the emulsion pump, and there is no mature and reliable water-based flow control valve. Based on the above reasons, traditional energy-saving testing methods cannot be utilized for the testing process of emulsion pumps. The loading test of emulsion pumps generally uses an overflow valve as the loading unit, and during the testing process, all electrical energy is converted into internal energy, resulting in very high energy consumption. This article proposes an energy-saving testing system for emulsion pumps based on multiple emulsion motors in parallel. In order to solve the flow regulation problem of each parallel branch, a flow-intelligent control algorithm is proposed that utilizes the pressure difference flow characteristics of digital relief valves combined with artificial neural network predictive control. Firstly, the feasibility of the proposed system and method is theoretically verified through the analysis of the mathematical model of the digital relief valve. Secondly, further verification is carried out by establishing simulation and testing platforms. The simulation results show that the energy recovery efficiency of the system exceeds 53%. The experimental results show that the proposed testing system has a pressure control error of less than 1%, a flow control error of about 5%, and a maximum overshoot of about 9 L/min relative to the steady-state flow rate. The control accuracy and system stability are high. Full article

The vibration signal of a pump is often used for analysis in the study of hydraulic-pump fault diagnosis methods. In this study, for the analysis, sound signals were used, which can be used to acquire data in a non-contact manner to expand the use scenarios of hydraulic-pump fault-diagnosis methods. First, the original data are denoised using complete ensemble empirical mode decomposition with adaptive noise and the minimum redundancy maximum relevance algorithm. Second, the noise-reduced data are plotted as mean spectrogram bar graphs, and the datasets are divided. Third, the training set graphs are input into the ResNet-50 network to train the base model for fault diagnosis. Fourth, all the layers of the base model are frozen, except for the fully connected and softmax layers, and the support set graphs are used to train the base model through transfer learning. Finally, a fault diagnosis model is obtained. The model is tested using data from two test pumps, resulting in accuracies of 86.1% and 90.8% and providing evidence for the effectiveness of the proposed method for diagnosing faults in hydraulic plunger pumps. Full article