Pulsation Signal Research Articles

Noise reduction method for mine wind speed sensor data based on CEEMDAN-wavelet threshold

The mine wind speed sensor is an important intelligent sensing equipment in the mine intelligent ventilation system that can provide accurate and key wind speed parameters for the intelligent ventilation system. The turbulent pulsation characteristics of the airflow in the underground tunnel are a major factor for the inaccurate measurement of mine wind speed. Therefore, according to the random non-stationary characteristics of a turbulent pulsation signal, a denoising method based on adaptive complete ensemble empirical mode decomposition (CEEMDAN) combined with the wavelet threshold is proposed for suppressing the turbulent pulsation noise in the wind speed signal. First, the CEEMDAN algorithm is used for decomposing the wind speed signal into a series of IMF components. Second, the continuous mean square error criterion is used for determining the high-frequency IMF components with more noise. The wavelet threshold denoising method is used for denoising the high-frequency IMF components with more noise. Finally, the denoised IMF components and remaining low-frequency IMF components are reconstructed for obtaining the denoised signal. The results of the denoising analysis of measured turbulent pulsation signals, comparative analysis of denoising of simulated turbulent pulsation signals by different joint denoising methods, and denoising analysis of actual mine wind speed sensor data indicate that the joint denoising method proposed in this study has a higher signal-to-noise ratio and lower root mean square error of the wind speed signal after denoising. Compared with the EMD-wavelet threshold and EEMD-wavelet threshold denoising methods, the denoising method proposed in this study is better and has higher denoising accuracy, which provides a new method for processing actual mine wind speed sensor data.

Cavitation state recognition method of centrifugal pump based on multi-dimensional feature fusion and convolutional gate recurrent unit

The rapid and accurate recognition of cavitation in centrifugal pumps has become essential for improving production efficiency and ensuring machinery longevity. To address the limitations of existing methods in terms of applicability, accuracy, and efficiency, a new method based on multi-dimensional feature fusion and convolutional gate recurrent unit (MCGN) was proposed. Experimental monitoring of cavitation of centrifugal pumps was conducted. Five signals at different water temperatures and operating frequencies were collected. Key modulating features were extracted by time-frequency analysis and principal component analysis. The multi-dimensional features are fused by one and two dimensional convolutional neural networks. The cavitation state label was used to label the sample set by cavitation number, net positive suction head, and cavitation evolution images captured by high-speed cameras. Finally, the neural network based on the convolutional gate recurrent unit was used to classify the cavitation state of the centrifugal pump. The experimental results demonstrate that the proposed method achieves recognition accuracies exceeding 98% for vibration signals, noise signals, outlet pressure pulsation signals, and torque signals. Compared with the short-time Fourier transform-autoencoder model, MCGN model can improve the recognition accuracy by 4.03%, computation efficiency by 20%, and loss by 87%. These advances underscore the potential of the method in monitoring and maintenance practices for centrifugal pumps.

Underwater acoustic signal feature extraction of mixed flow pump based on empirical wavelet transform

The pump converts mechanical energy into potential energy, and a mixed-flow-pump combines the characteristics of an axial flow pump and a centrifugal pump. When the mixed-flow-pump operates at low flow conditions, performance instability in the hump region appears on the performance curve. This study investigates the underwater acoustic signal in this area through experiments, computational fluid dynamics (CFD), and computational aero acoustics (CAA). The hysteresis factor calculated by cross correlation (CC) is utilized to improve the dynamic time warping (DTW) signal comparison verification method. The improved method (CC-DTW) improves the ability of DTW in signal comparison and verification. Compared with the fast Fourier transform (FFT) method, it is more convincing in the comparison of experimental and simulation pressure pulsation signals. After verifying the effectiveness of pressure pulsation signals and underwater acoustic signals, a combined empirical wavelet transform and FFT method is used to analyze underwater acoustic signal in instability regions. The results indicate that the depth of instability aligns with the FFT frequence ratio of the intrinsic mode function. Based on the feature, a criterion for determining instability states in mixed-flow-pumps is proposed.

Analysis and Identification of Eccentricity of Axial-Flow Impeller by Variational Mode Decomposition

The axial-flow impellers are widely applied to industry due to their excellent hydraulic performance and simple structure, but they may be affected by their eccentricity during operation. This study compared and studied the effects of the axial-flow eccentricity of an impeller on hydraulic performance, impeller radial force, and downstream pressure pulsation of the unit. The research results indicate that impeller eccentricity has a small effect on hydraulic performance. Compared with the design conditions, the efficiency, power, and head changes caused by impeller eccentricity are all less than 1%, but the impeller eccentricity leads to a sharp increase in the radial force of the impeller. Under the design conditions, the average value of the radial force of the impeller is 31.38 N; under eccentric conditions, the average value of the radial force of the impeller increased by nine times, reaching 316.30 N. By analyzing the pressure pulsation signals decomposed by the VMD method, it is shown that the influence of eccentricity on pressure pulsation is mainly reflected in the increase in impeller frequency on pressure pulsation. Under design conditions, the corresponding amplitude of the impeller frequency is 2.6; under eccentric conditions, the amplitude corresponding to the impeller frequency increased by 100 times, reaching 274.4. This study elucidates the specific effects of axial impeller eccentricity, providing theoretical guidance for the safe and stable operation of axial-flow units, and has important engineering significance.

Research on the influence of unsteady cavitation on the dynamics structures of a twisted hydrofoil based on variational mode decomposition method

Cavitation will produce complex dynamic effects on hydrofoil structures. In this paper, the effects of unsteady cavitation conditions on the dynamics of twisted hydrofoil structures are studied by using variational mode decomposition (VMD) and pearson correlation coefficient (PCC), etc. The research results indicate that there is a certain synergy between the flow field pressure pulsation signal and the structural field stress-strain signal in the frequency distribution of the hydrofoil under cavitation conditions. The second-order center frequency of ΔP1 and the first-order center frequency of ΔP7 are close to the second-order center frequency of the stress-strain signal of the hydrofoil (1202.4Hz). Unsteady cavitation can lead to the increase of the high effective force region of the hydrofoil, especially the high effective force region connecting the leading edge and the root, which is the reason for the degradation of the hydrofoil performance. Cavitation increases the natural frequency of the hydrofoil, but has no obvious effect on the natural mode of the hydrofoil. The research results of this study reveal the effect of unsteady cavitation on the dynamics of hydrofoil structure, and provide important theoretical support for the optimization design and performance improvement of hydrofoil structure.

Research on the mechanism of severe unsteadiness of PAT braking condition during the power failure

The Pump-As-Turbine (PAT) technology has become popular in micro hydropower stations due to its simple installation and cost-effectiveness. Nevertheless, power failures present a substantial risk to the secure and steady functioning of PAT’s braking system. The commercial CFD code (ANSYSCFX) is improved by incorporating a secondary development to model the power-off transition using Fortran accurately. This enhancement allows for real-time iterative calculations of angular momentum equations for mixed-flow PAT at different speeds. Meanwhile, the time–frequency domain analysis is utilized to analyze pressure pulsation signals and the evolution of the internal flow field in mixed-flow PAT. An investigation was conducted to have a deeper understanding of braking circumstances. The results revealed that the main frequency of the pressure pulsation aligns with the blade frequency at various flow rates, and there is a sudden change in pressure amplitude during the braking phase. The impeller experienced the majority of energy losses, with the draft tube being the subsequent area of concern. In addition, a thorough examination and comparison of the changes in the internal flow field during braking were carried out. This analysis revealed a distinct double helix structure within the draft tube, with a slower inner helix and a faster outer helix. Furthermore, it was observed that there is a strong correlation between wall shear stresses and hydraulic losses on the blade surface. This research enhanced understanding of the flow characteristics of mixed-flow PAT can help improve system safety and provide valuable guidance for future optimization efforts.

Development of an Automatic Phase Selector for Nigerian Power Utility Customers

Power utility customers in a developing country like Nigeria have constituted a habit of changing the electricity supply line from an unavailable or unstable phase to the most available or stable phase. The category of customers involved in this character are those on single phase power supply. However, this act is being carried out manually at the meter point using the cut-out fuses. This attitude results in phase unbalances, overheating electrical equipment including feeder pillars, transformer coils, network faults, and overall system instability. Thus, this paper presents the development of an Automatic Phase Selector for Nigerian Power Utility Customers. The device automatically selects an available phase from the three-phase power supply lines. The research comprises designing an automatic phase selector circuit, simulation of the designed circuit, programming code development in C- Language for the microcontroller, construction of the designed circuit, and carrying out tests on completed work done to ascertain the effectiveness of the developed system. The system operation involved a three-phase supply from the closest distribution network of the power utility company which is connected to a three-in-one gang switch while the switching ON and OFF of their static switches represent phase-off in an ideal situation. The operational results of this system are presented in the form of the truth table which indicates that the affected customer would not have a power supply only when the 3-phases are under voltage or overvoltage or unavailable. This implies that one of the three phases that meet the three criteria would be switched ON. A pure sine wave was used as input into the Optocoupler and the output waveform of the rectified pulsating signal is separately displayed. This output waveform is very clean and noiseless. Finally, the system when practically tested with an unbalanced three-phase supply, worked perfectly enhancing the flexibility of operating an Automatic Phase selector and hence avoiding manual switching of the phase selector which has been attributed to changing of cut-out fuses and associated stress as well as having a user-friendly phase selector.

Research into Prediction Method for Pressure Pulsations in a Centrifugal Pump Based on Variational Mode Decomposition-Particle Swarm Optimization and Hybrid Deep Learning Models.

Centrifugal pump pressure pulsation contains various signals in different frequency domains, which interact and superimpose on each other, resulting in characteristics such as intermittency, non-stationarity, and complexity. Computational Fluid Dynamics (CFD) and traditional time series models are unable to handle nonlinear and non-smooth problems, resulting in low accuracy in the prediction of pressure fluctuations. Therefore, this study proposes a new method for predicting pressure fluctuations. The pressure pulsation signals at the inlet of the centrifugal pump are processed using Variational Mode Decomposition-Particle Swarm Optimization (VMD-PSO), and the signal is predicted by Convolutional Neural Networks-Long Short-Term Memory (CNN-LSTM) model. The results indicate that the proposed prediction model combining VMD-PSO with four neural networks outperforms the single neural network prediction model in terms of prediction accuracy. Relatively high accuracy is achieved by the VMD-PSO-CNN-LSTM model for multiple forward prediction steps, particularly for a forward prediction step of 1 (Pre = 1), with a root mean square error of 0.03145 and an average absolute percentage error of 1.007%. This study provides a scientific basis for the intelligent operation of centrifugal pumps.

Analysis of the temporal, spatial, and frequency law of the internal flow in a prototype vaned mixed‐flow pump

AbstractMixed‐flow pump is a typical pump using in low‐head cases of water lifting. The flow field pulsation is usually an important issue in the operation of mixed‐flow pumps and their pumping statins. Due to its large size, it is difficult to monitor the internal flow characteristics well, based on computational fluid dynamics, we use 5678 monitoring points which arranged in the impeller and fixed vane with using the high pulsation tracking network, and the pressure pulsation signals are analyzed by fast Fourier transform and variable mode decomposition to decompose the main frequency and intensity of the pressure pulsation signals, then analyze the energy dissipation with the entropy production rate (EPR). It is found that there are strong low‐frequency (0.416, 0.625, and 1.67 Hz) pressure pulsation near hub, and the pressure pulsation on the shroud is stronger than that on the hub (at least three times or more); there are strong and stable pressure pulsation (25 Hz) on the shroud generated by the rotor–stator interference (RSI); and the EPR in the flow field can be well combined with the signal. Reasonably allocating material strength and controlling the number of vanes and impellers to avoid producing a common multiple can avoid pressure pulsation caused by RSI and reduce energy dissipation. Therefore, it is very effective in improving the efficiency of this part. Under low flow conditions, the siphon outflow passage can predict the high‐frequency (45.833 Hz) attenuation area well through the phase signal decomposition of the signal, which has certain significance for improving its stability and efficiency.

Numerical Study on Valve Closing Criteria during Pump-turbine Start-up on Pump Mode

Abstract Vibrations of exhaust pipes have been observed in some hydropower stations during the exhaust process of pump-turbine start-up on pump mode due to water ingress into the pipes. It may have a safety risk for the pump-turbine start-up process when exhaust pipes are operating under the compressed air-water two phase flow. Since the numerical simulation researches about pump start-up process have been rarely reported and the development of flow field in exhaust pipe is lack of quantitative cognition, it calls for an urgent need to supplement related works. In this paper, the transient full-channel two-phase numerical simulation research on the pump mode return water exhaust process of a pumped power station is carried out by Reynolds-Averaged Navier-Stokes approach. This work put emphasis on the characteristics of cone water level, runner torque and air speed in exhaust pipes after the compressed air released from the runner chamber. Then development laws and relationship with the exhaust valve closing timing are analysed and concluded. Results show that the cone water level, runner torque and air speed pulsation signal of exhaust pipes can be used as exhaust valve closing criteria, and the third criterion has the largest time margin.

Physics-Constraint Variational Neural Network for Wear State Assessment of External Gear Pump.

Most current data-driven prognosis approaches suffer from their uncontrollable and unexplainable properties. To address this issue, this article proposes a physics-constraint variational neural network (PCVNN) for wear state assessment of the external gear pump. First, a response model of the pressure pulsation of the gear pump is constructed via a spectral method, and a compound neural network is utilized to extract features from the pressure pulsation signal. Then, the response model is formulated into an objective function to softly constrain the learning process of the neural network, forcing the learned features to have explicit physics meaning. Meanwhile, to characterize the system uncertainty, the variational inference is utilized to extend a Kullback-Leibler (KL) divergence into the objective function. Finally, the wear state is evaluated based on the distance of learned physics features. Experimental results on an external gear pump validate the merits of the proposed method in explainable representation learning and system uncertainty estimation. It also offers a controllable and explainable perspective to understand the dynamic behavior of the system.

Numerical simulation and experimental investigation of pressure pulsation-induced nonlinear characteristics in marine twin-screw pumps under various clearance between rotor and stator

The twin-screw pump (TSP) is widely used in naval engineering for seawater transportation and treatment. However, the diverse composition of seawater, often containing impurities, poses a risk of screw corrosion and jamming of clearances. Detecting the compact internal structure's clearance between rotor and stator (GAPR) proves challenging. To address these challenges, a novel approach combining chaos theory's reconstructive phase space technique was proposed for processing pressure pulsation signals. The research found that only specific monitoring points displayed chaotic characteristics in pressure pulsation signals. The attractor structure complexity increased with GAPR changes, while the chaotic features decreased. Nonlinear analysis of pulsation signals at different GAPR values allowed determining reasonable ranges. Applying support vector classification algorithm based on chaotic dynamics achieved an impressive 89% accuracy in identifying GAPR values. This study offers practical insight for TSP fault detection and operational optimization, holding significance in both theory and practice.

Organic Photoplethysmography Sensor Based on Directional Emission Microcavity Organic Light‐Emitting Device

AbstractWearable photoplethysmography (PPG) sensors provide real‐time monitoring of essential human health parameters by integrating a light source with a photodetector. However, they face a common challenge: the presence of a faint pulsating (AC) signal amidst a highly noisy and drifting non‐pulsatile background. This necessitates fine‐tuning how the light is spread out to make sure that a significant number of emitted photons carry vital physiological information and trigger the detector's photocurrent. An innovative organic PPG sensor with a microcavity organic light‐emitting diode (OLED) that emits light in a controlled direction, coupled with an annular organic photodetector (OPD) is demonstrated here. By adjusting the OLED's cavity lengths, the microcavity resonance peak is shifted, achieving angled directional emission. Placing the microcavity OLEDs at the center of the annular OPD enhances the portion of light that reflects from arterial vessels in the skin and tissues. This increases the AC signal for recording arterial vessel pulsations by 47.66%. This advancement simplifies sensor recognition and achieves an unprecedented low power consumption of only 9.96 µW for heart rate sensing, meeting essential recognition criteria.

A dynamic view of V Hydrae

Context. The well studied carbon star V Hydrae is known to exhibit a complex asymmetric environment made of a dense equatorial wind and high-velocity outflows, hinting at its transition from the AGB phase to the asymmetric planetary nebula phase. In addition, V Hydrae also exhibits a long secondary period of 17 yr in its light curve, suggesting the presence of a binary companion that could shape the circumstellar environment. Aims. In this paper, we aim to confirm the binary nature of V Hydrae by deriving its orbital parameters and investigating the effect of the orbital motion on the circumbinary environment. Methods. In a first step, we used a radial-velocity monitoring performed with the HERMES spectrograph to disentangle the pulsation signal of the AGB from its orbital motion and to obtain the spectroscopic orbit. We combined the spectroscopic results with astrometric information to get the complete set of orbital parameters, including the system inclination. Next, we reported the time variations of the sodium and potassium resonance doublets. Finally, following the methods used for post-AGB stars, we carried out spatio-kinematic modelling of a conical jet to reproduce the observed spectral-line modulation. Results. We found the orbital solution of V Hydrae for a period of 17 yr. We correlated the companion passage across the line of sight with the obscuration event and the blue-shifted absorption of alkaline resonant lines. Those variations were modelled by a conical jet emitted from the companion, whose opening angle is wide and whose sky-projected orientation is found to be consistent with the axis of the large-scale bipolar outflow previously detected in the radio-emission lines of CO. Conclusions. We show that the periodic variation seen for V Hydrae is likely to be due to orbital motion. The presence of a conical jet offers a coherent model to explain the various features of V Hydrae environment.

Absolute properties of the oscillating eclipsing Algol XZ Ursae Majoris

Abstract It is known from archival TESS data that the semi-detached Algol system XZ Ursae Majoris (UMa) is one of the candidate binary stars exhibiting short-period oscillations. We secured new high-resolution spectroscopic observations for the program target to better understand its binary and pulsation properties. From the echelle spectra, the radial velocities (RVs) of the eclipsing pair were derived, and the atmosphere parameters of the primary component were measured to be vAsin i = 80 ± 7 km s−1, Teff, A = 7940 ± 120 K, and [M/H] = −0.15 ± 0.20. The combined solution of our double-lined RVs and the TESS data provides robust physical parameters for XZ UMa with mass and radius measurement precision of better than 2%. The outside-eclipse residuals from a mean light curve in the 0.002 phase bin were used for multifrequency analyses, and we extracted 32 significant frequencies (22 in <5.0 d−1 and 10 in 39–52 d−1). The low frequencies may be mostly aliasing sidelobes, while six of the high frequencies may be pulsation signals arising from the detached primary located inside the δ Sct domain. Their periods, pulsation constants, and pulsational–orbital-period ratios indicate that the mass-accreting primary star is a δ Sct pulsator and, hence, XZ UMa is an oscillating eclipsing Algol.

Modeling and Control of Two Degree of Freedom Bionic Foot

Many people are affected by conditions like stroke, spinal cord diseases, cerebral palsy, and nerve injuries, leading to impaired leg function. Bionic foot assist in maintaining stability and posture, offering vital aid to those with mobility issues for improved quality of life and rehabilitation. Consequently, the use of bionic foot has increased. Bionic foot comprising electrical and mechanical components, provide comfort and support for individuals with mobility problems. An encouraging solution is to introduce bionic foot robots to help patients having mobility problems during their recovery journey. Designed to mimic the human skeletal system, these robots offer valuable assistance in restoring the natural gait cycle of patients having mobility problems. The proposed approach introduces a bionic foot designed to support movement of human ankle joint, marking a significant advancement in rehabilitation technology. Although human ankle joint actually exhibits 3 DOF motion, we consider 2 DOF motion of human ankle joint i.e., plantarflexion and dorsiflexion and, inversion and eversion as they are dominant during normal motion of human body. We designed two systems to control the motion of human ankle joint. Firstly, we have used two actuators, one for each degree of freedom to control the motion of ankle joint. Secondly, we have used an actuator to control the plantarflexion and dorsiflexion motion and Spring-Damper system to control the inversion and eversion motion of the human ankle joint. For both systems, we derive the mathematical model and then we design the PD controller using MATLAB/Simulink. For plantarflexion and dorsiflexion motion, we give standard pattern of human ankle gait as input and for inversion and eversion motion, we provide pulsating signal as our input for both the systems. After implementation, the response of the human ankle motion was precise, accurate and smooth. The torque applied by the actuators was also in the acceptable range.

The influence of optimization algorithm on the signal prediction accuracy of VMD-LSTM for the pumped storage hydropower unit

Pumped storage hydropower units, as a crucial type of energy conversion equipment, play a pivotal role in energy storage and balance. Predicting pressure pulsation signals in pump-turbine units can help anticipate potential unit malfunctions within the pump-turbine system. However, conventional prediction methods may be constrained by their ability to extract signal features and perform pattern recognition. With the continuous advancement in the realm of artificial intelligence, there has been a rise in the evolution of prediction involving variational mode decomposition (VMD) for time series decomposition and the utilization of genetic algorithms (GAs) for parameter optimization of long short-term memory (LSTM) networks has emerged. To address the fitness function issue in the context of genetic algorithms, this study employs three optimization algorithms to combine with the VMD-LSTM model. Three different prediction models are formed and compared with both the conventional LSTM and VMD-LSTM prediction methods. The results indicate that, in the prediction of pressure pulsation data at the three monitoring points of the pump-turbine, the predictive performance of the VMD-whale optimization algorithm (WOA)-LSTM model surpasses that of the conventional LSTM model and the VMD-LSTM prediction approach. Furthermore, the magnitude of prediction errors is reduced in comparison to the VMD-sparrow search algorithm (SSA)-LSTM and VMD-improved grey wolf optimization (IGWO)-LSTM prediction models.

Analysis of Stress–Strain Characteristics and Signal Coherence of Low-Specific-Speed Impeller Based on Fluid–Structure Interaction

In this study, an analysis of a low-specific-speed pump is carried out based on the methods of one-way and two-way fluid–structure interactions (FSIs). This study analyzes the influence of FSIs on the internal flow field and external characteristics of the pump. Utilizing a two-way FSI, the signal coherence analysis method is employed to analyze the coherence of signals between the flow field and the structural field. Addressing the issue of a lack of a connection between the two signals, this study bridges a gap in the existing research. The results indicate that different interaction methods have certain influences on impeller stress and deformation. However, in both coupling modes, the maximum deformation and the maximum equivalent stress have the same distribution position. The head error obtained using the two-way coupling method is lower than that of the uncoupled results, which indicates that the two-way FSI calculation results are closer to the experimental results. The pressure pulsation signals at the interface of the impeller and volute exhibit strong coherence with the structural field signals. For low-specific-speed centrifugal pumps, establishing a clear connection between the flow field signals and structural field signals will help guide further optimization of their performance through design.

Research on the flow-induced vibration characteristics based on heat–fluid–structure coupling in natural gas loop

To research the flow-induced vibration characteristics of the natural gas loop, unsteady numerical simulation is carried out on the loop calculation model under different ambient temperatures and different flow rates, and the influence of different flow rates on the dynamic characteristics of the flow field and its induced vibration characteristics is obtained. The results show that the inherent frequency of the natural gas loop increases slightly under the action of heat–fluid–solid coupling. The maximum equivalent stress of the loop increases with the increase in ambient temperature under low flow conditions, but it is almost constant under high flow conditions. The smaller the cross-sectional area of the loop pipeline inlet, the greater the pressure, and the more significant the pressure gradient along the flow direction. The pressure pulsation of monitoring points in the pipeline under different flow rates presents different rules, and the pulsation amplitude of pipes with different diameters is different, among which the amplitude of the pipe with a diameter of 250 mm is the largest and that of the pipe with a diameter of 150 mm is the smallest. The pressure pulsation signals are concentrated in the low-frequency band of 0–10 Hz, and the range of the band decreases with the increase in the flow rate. The vibration frequency of the loop structure is close to the fluid pressure pulsation frequency and the inherent frequency under the action of heat–fluid–solid coupling, which causes a resonance of about 2 Hz.

Recognition of cavitation characteristics in non-clogging pumps based on the improved Lévy flight bat algorithm

The performance and operational stability of non-clogging pumps can be affected by cavitation. To accurately identify the cavitation state of the non-clogging pump and provide technical references for monitoring its operation, a study was conducted on the optimization of Elman neural networks for cavitation monitoring and identification using the Improved Lévy Flight Bat Algorithm (ILBA) on the basis of the traditional Bat Algorithm (BA). The ILBA employs multiple bats to interact and search for targets and utilizes the local search strategy of Lévy flight, effectively avoiding local minima by taking advantage of the non-uniform random walk characteristics of large jumps. The ILBA algorithm demonstrates superior performance compared to other traditional algorithms through simulation testing and comparative calculations with eight benchmark test functions. On this basis, the optimization of the weights and thresholds of the Elman neural network was carried out by the improved bat algorithm. This leads to an enhancement in the accuracy of the neural network for identifying and classifying cavitation data, and the establishment of the ILBA-Elman cavitation diagnosis model was achieved. Collect pressure pulsation signals at the tongue of the non-clogging pump volute through cavitation tests. Through the cavitation feature extraction method based on Variational Mode Decomposition (VMD) and Multi-scale Dispersion Entropy (MDE), the interference signal can be effectively suppressed and the complexity of the time series can be measured from multiple angles, thereby creating a cavitation feature data set. The improved cavitation diagnosis model (ILBA-Elman) can realize the effective identification of the cavitation characteristics of non-clogging pumps through a variety of algorithm comparison experiments.