Self-priming Centrifugal Pump Research Articles

Parallel quantized dual-level fully connected classifier for bearing fault diagnosis

The diagnosis of bearing failures in rotating mechanical equipment is critical to productivity and the quality of the manufacturing process. Traditional methods generally suffer from high human factor interference and low accuracy. This paper proposes a parallel quantized dual-level fully connected classifier (PQDFCC) for fault identification of bearings. The PQDFCC has two parts. The first part of the PQDFCC contains two types of data pre-processing. The first data pre-processing method is calculating absolute values and sorting the acquired raw signals. The second method of data pre-processing is quantizing the raw data. The second part of PQDFCC is a dual-level fully connected classifier. The first-level fully connected classifier performs the first-level fault classification on the quantized and sorted data; then, the output probability of the first-level classifier is considered as the input of the second-level fully connected classifier; finally, the second-level fully connected classifier provides the classification results of bearing faults. The data pre-processing part of the PQDFCC is a simple calculation that can simplify and not lose fault information; the dual-level fully connected classifier can fully exploit the hidden features of the data with high accuracy. The proposed PQDFCC is tested in the bearing failure, axial piston hydraulic pump, and self-priming centrifugal pump datasets; the experimental results show that the PQDFCC achieves 100% fault diagnosis accuracy.

Bi-level binary coded fully connected classifier based on residual network 50 with bottom and deep level features for bearing fault diagnosis

Among the existing bearing fault diagnosis algorithms, the diagnosis time of algorithms with high accuracy is relatively long, and the accuracy of some lightweight methods is low compared to other methods. This work proposes a bi-level binary coded fully connected classifier based on residual network 50 with bottom and deep level features (Bi-BUR) for bearing fault diagnosis, enabling both high accuracy and high-speed characteristics. The Bi-BUR has two levels of classifiers. The first level begins with a signal-to-picture method based on integer binary coding to convert the bearing fault signals into binary pictures; then, the first classification of the converted pictures is performed by the underlying feature extraction-residual network 50, which can extract both the underlying and the advanced features. The second level performs modal decomposition of the signals that are not classified successfully in the first level, performs the second classification with a fully connected classifier inserted into the underlying feature extraction module, and exports the final classification results after weighted summation of the results of each type. The Bi-BUR is simulated on the Case Western Reserve University motor, the self-priming centrifugal pump, and the axial piston hydraulic pump bearing failure datasets. All three experiments achieved more than 95% accuracy in the first level of categorization and 100% diagnosis after the second level of categorization. And the Bi-BUR is faster than other high-accuracy methods.

Gas-liquid flow patterns visualization in a self-priming centrifugal pump

The self-priming pumps are ubiquitous in gas-liquid mixtures lift and transportation areas. The fast self-priming time is a vital evaluation index for a self-priming pump. However, the bubble movement path and the bubble size distribution characteristics during the self-priming process are still an open issue. This paper aims to obtain the gas-liquid flow patterns inside a centrifugal pump during the self-priming process and evaluate the effect of the rotational speed and the position of the back-flow hole on the self-priming time through experiments. A centrifugal pump with a double-blade was designed as a visualization prototype. The high-speed photography technology was used to capture the bubble motion and size in the pump during the self-priming process. The bubble image processing method was used to identify the bubble size distribution in the diffuser during the self-priming process. The bubble number and size distribution images were presented to understand the influence of the rotational speed and the position of the back-flow hole. The higher rotational speed accelerates the gas-liquid mixing rate and shortens the self-priming time. However, there is a limited value of the self-priming time as the speed goes up to a certain high level. Moreover, the position of the back-flow hole slightly affects the self-priming time.

Research on bearing fault diagnosis method based on transformer neural network

The Attention mechanism (AM) has been widely used for fault diagnosis and identifying the health of industrial equipment. Existing research has only used AM in combination with deep networks, or to replace certain components of these deep networks. This reliance on deep networks severely limits the feature extraction capability of AM. In this paper, a bearing fault diagnosis method is proposed based on a signal Transformer neural network (SiT) with pure AM. First, the raw one-dimensional vibration time-series signal is segmented and a new segmented learning strategy is introduced. Second, linear encoding and position encoding are performed on the segmented subsequences. Finally, the encoded subsequence is fed to the Transformer for feature extraction to achieve fault identification. The validity of the proposed method is verified using the Case Western Reserve University dataset and the self-priming centrifugal pump bearing dataset. Compared with other existing methods, the proposed method still achieves the highest average diagnostic accuracy without any data preprocessing. The results demonstrate that the proposed SiT based on pure AM can extract features and identify faults from the raw vibration signal, and has superior diagnostic performance.

Influence of Bionic Circular Groove Blade Surface on Wear Performance

In order to improve the anti-wear performance of a double-vane self-priming centrifugal pump during two-phase flow transfer, the construction of a streamline groove structure at the outlet end of the suction side of the vane, based on the bionic principle, is proposed. Different pump characteristics are analysed to investigate the effect of different bionic groove spacing on the resistance to particle wear and the mechanism of improvement of the bionic grooves. The results show that the effect of the bionic blades on the hydraulic characteristics of the pump is within the allowable error (±1.4%). The circular groove structure with different spacing produces a difference in the pressure distribution on the blade. At the same particle concentration, with the increase in the groove spacing distance, the average wear of the blades first decreases and then increases; the average wear rate at the spacing of 7 mm is the smallest. At a particle concentration of 90 kg/m3, the average wear rate at a groove spacing of 7 mm is ~0.63 × 10−4 kg/s∙m2, and the wear area is mainly found in the middle of the blade. The reason why the bionic blade improves the anti-wear performance of the pump is due to the reverse vortex zone in the groove, which changes the particle trajectory and collision frequency. The bionic grooves with a diameter of 2 mm and a spacing of 7 mm significantly reduce the average wear rate of the pump at different particle concentrations, while maintaining hydraulic performance.

Intelligent fault diagnosis of machine under noisy environment using ensemble orthogonal contractive auto-encoder

Despite significant advances in auto-encoder (AE) based intelligent fault diagnosis recently, their assumption of high-quality sensor data is unrealistic due to noisy environment. Aiming at such problem, this work proposes a novel ensemble orthogonal contractive auto-encoder (EOCA) method to improve diagnosis accuracy. By designing a new cost function including contractive term and orthogonal constrain, OCA can learn robust and non-redundant features from noisy input. To make fault patterns separable, fisher discriminant analysis is cascaded with OCA for mapping these features into a new coordinate space with maximum class separability. Considering the limitation of a single model, sixteen different OCAs with complementary activation functions as well as a new ensemble strategy based on expert model are developed to produce a stable diagnosis result. Additionally, to prove the effectiveness, error bound of EOCA is analyzed and theoretical basis is found for supporting OCA design. EOCA is verified on three cases including three-phase flow facility, gear box and self-priming centrifugal pump. Experiments are conducted by introducing various strength of white Gaussian noise. Results show that EOCA is better than single OCA, canonical AE, sparse AE, denoising AE and several advanced ensemble methods under strong noise.

A hidden feature label propagation method based on deep convolution variational autoencoder for fault diagnosis

Vibration signal of mechanical component usually exhibits non-linear and non-stationary characteristics, the key step of fault diagnosis is to extract discriminant features hidden in the vibration signal, in order to improve diagnostic performance and identify new fault class, a novel fault diagnosis method of hidden feature label propagation based on deep convolution variational autoencoder (HFLPDCVA) is proposed. Firstly, the raw vibration signal is transformed into frequency spectrum data by using fast Fourier transform as the input of the model. Secondly, the variational autoencoder is used to construct the convolutional neural network, and the non-fixed dropout parameter is fused to change the network to improve the identification of network hidden layer features. Finally, the label propagation algorithm is applied to process the hidden features of the full connection layer, and the local common features between the unknown label samples and the known label samples are extracted to predict the class of unknown label samples, including the new emerge fault class. The effectiveness of the proposed method is verified on bearing fault data sets under variable working conditions and damage data sets of self-priming centrifugal pump under a single working condition. Experimental results show that the proposed HFLPDCVA method can effectively extract the fault characteristics of the vibration signal, and it also has a significantly higher recognition accuracy rate than other typical deep learning methods and traditional classifiers.

A Threshold-Control Generative Adversarial Network Method for Intelligent Fault Diagnosis

Fault diagnosis plays the increasingly vital role to guarantee the machine reliability in the industrial enterprise. Among all the solutions, deep learning (DL) methods have achieved more popularity for their feature extraction ability from the raw historical data. However, the performance of DL relies on the huge amount of labeled data, as it is costly to obtain in the real world as the labeling process for data is usually tagged by hand. To obtain the good performance with limited labeled data, this research proposes a threshold-control generative adversarial network (TCGAN) method. Firstly, the 1D vibration signals are processed to be converted into 2D images, which are used as the input of TCGAN. Secondly, TCGAN would generate pseudo data which have the similar distribution with the limited labeled data. With pseudo data generation, the training dataset can be enlarged and the increase on the labeled data could further promote the performance of TCGAN on fault diagnosis. Thirdly, to mitigate the instability of the generated data, a threshold-control is presented to adjust the relationship between discriminator and generator dynamically and automatically. The proposed TCGAN is validated on the datasets from Case Western Reserve University and Self-Priming Centrifugal Pump. The prediction accuracies with limited labeled data have reached to 99.96% and 99.898%, which are even better than other methods tested under the whole labeled datasets.

Deep Convolutional Neural Network Using Transfer Learning for Fault Diagnosis

Fault diagnosis is critical in industrial systems since early detection of problems can not only save valuable time but also reduce maintenance costs. The feature extraction process of traditional fault diagnosis is time-consuming and laborious work. Recently, with the rapid development of the deep learning (DL) method, it has shown its superiority with an end-to-end process and has been applied to classification and other fields. To a certain extent, it solves the disadvantages of manual feature extraction in the traditional fault diagnosis method. However, the available training data is often limited, and it will degrade the performance of DL methods. A new DL method that combines deep convolutional neural network (DCNN) and transfers learning (TL) for fault diagnosis is proposed in this paper to handle different fault types. A signal processing method that converts one-dimensional time-series signals into grayscale images is firstly applied, and it can eliminate the effect of handcrafted features. Secondly, an optimal DCNN is designed and trained with the ImageNet datasets, which can extract the high-level features of massive images. Finally, TL is further developed to apply the knowledge learned in the source data distribution to the target data distribution, which greatly reduces the dependence on training data and improves the generalization performance of DCNN. Three well-known datasets, including the bearing vibration dataset from the Case Western Reserve University (CWRU), self-priming centrifugal pump dataset (SPCP), and bearing force dataset from the University of Paderborn, are utilized to the performance of the proposed method. Some popular classification methods are also added to the comparison. Results show that the proposed method can precisely identify different fault types and have the highest classification accuracy among other methods.

Ensemble deep contractive auto-encoders for intelligent fault diagnosis of machines under noisy environment

Intelligent fault diagnosis methods based on deep auto-encoder have achieved great success in the past several years. However, these methods cannot effectively handle the data collected under noisy environment. Therefore, this paper proposes a new ensemble deep contractive auto-encoder (EDCAE) to address the problem. First, we design fifteen deep contractive auto-encoders (DCAE) to learn invariant feature representation automatically. Due to the Jacobian penalty term in DCAE and different characteristics, these models can deal with various noisy data effectively. Second, fisher discriminant analysis is applied to select low-dimensional features with the maximum class separability. Softmax classifier is adopted to identify the selected features and produce fifteen classification results. Finally, a new combination strategy is developed to combine these individual results. Benefitting from the combination strategy, it can produce accurate diagnosis results even under strong background noise. Additionally, to prove the effectiveness of EDCAE, theory analysis about error bound is conducted. The proposed method is verified on three case studies including bearing, gear box and self-priming centrifugal pump. Experiments are conducted under seven different signal-to-noise-ratios. Results show that EDCAE is better than other intelligent diagnosis methods, including individual DCAE, deep auto-encoder, sparse deep auto-encoder, deep denoising auto-encoder and several ensemble methods.

Rolling Bearing Fault Diagnosis Using Time-Frequency Analysis and Deep Transfer Convolutional Neural Network

Due to the advantage of automatically extracting features from raw data, deep learning (DL) has been increasingly favored in the field of machine fault diagnosis. However, DL exposes the problems of large sample size and long training time, and in actual working conditions, the amount of labeled fault data available is relatively small, so a DL model of good generalization and high accuracy is difficult to be trained. In order to solve these problems, a deep transfer convolutional neural network (DTCNN) is proposed in this research. ResNet-50 is selected as the pre-trained model of deep convolutional neural network, and is transferred to solve the problem of bearing fault classification based on the idea of transfer learning. Firstly, raw fault signals are converted into time-frequency images by using continuous wavelet transform (CWT). Then, the images are further converted into RGB formats, which are used as the input of DTCNN. Finally, an end-to-end fault diagnosis model based on DTCNN is designed. The proposed method is validated on two datasets collected from motor bearing and self-priming centrifugal pump, respectively. Most sub-datasets from motor bearing show the prediction accuracies near 100%, and in the self-priming centrifugal pump dataset, we achieve improvement in accuracy from 99.48%±0.1966 to 99.98%±0.0332. The experimental results demonstrate that the proposed method outperforms other DL methods and traditional machine-learning methods.

CNN-based Single-Fault Diagnosis of Self-Priming Centrifugal Pump

CNN is a very powerful deep learning technique for classification when the size of data is significant. It has been observed that it fails to give any reasonable classification when size of the data is small. This paper deals with an enhanced data technique, which is very useful for smaller size of available data. We proposed to increase the size of data to multiple times until a good classification accuracy is acquired. The paper shows that the neural networks perform very efficiently when such type of enhancement is done. It has been elaborated for evaluating the classification of faults of centrifugal pumps. The CNN-2D and CNN-1D yield 100% accuracy for diagnosing the faults of in this case. The performance is also compared with that of ANN. The number of epochs required to reach 100% accuracy for multiple different sizes of data is used to evaluate the performance. The enhanced data approach also shows that there is a drastic fall in overall classification time of CNN.

Experimental Optimization of Jet Self-Priming Centrifugal Pump Based on Orthogonal Design and Grey-Correlational Method

The novel jet self-priming centrifugal pump, as important modern irrigation equipment, is widely used in large-scale irrigation, mine drainage and so on. In order to improve the profile streamline of blade, the inlet shape of impeller was designed as distorted and the outlet shape as cylindrical, which can not only improve the pump efficiency, but also shorten the self-priming time. Further, the novel jet self-priming system was proposed, by employing the jet nozzle and check valve to improve the velocity of self-priming. Meanwhile, nine different structure jet nozzles were designed based on the orthogonal design method, and the relevant self-priming experiments were performed on I level accuracy test bench in Jiangsu University. According to the grey-correlational analysis, the influence of the nozzle geometry parameters on the self-priming performance was obtained. The relationship between self-priming time and self-priming height was discussed. The test results showed that the hydraulic design of jet self-priming centrifugal pump was reasonable; all indicators met the Chinese national standard; the head reached 21.04 m and efficiency was 72.8% under the design flow condition. What is more, the self-priming performance was obviously improved by adjusting the geometrical parameters of nozzle. When the height of the self-priming process was 5.3 m, the self-priming time reached 62 s, which was much shorter than the national standard. Therefore, this research could provide reference for designing the structure of jet self-priming centrifugal pump.

Experimental startup characteristics of a prototype pump delivering tap water

As an important period of self-priming process, the startup process of self-priming pump is inevitable. In this paper, a small overhung self-priming centrifugal pump is tested to reveal the effect of startup time on startup performance. As a first step, the startup performance of the pump delivering water is tried firstly. Through testing, the transient characteristics of performance variables against time are emphatically analyzed in three lengths of startup time/duration and four typical steady flow rates. The test results show that with extension of the startup time, the steady rotational speeds present a slight rise trend. The flow rate curves overall rapidly rise and then grow slowly. The shorter the length of the startup time, the closer the head curves tend to be linear. Conversely, the head curve more likely can be best fitted by quadratic polynomial. At the beginning of rapid startup, there is a sudden-rise-and-sudden-drop oscillation phenomenon in the inlet static pressures curves, and a pressure impact phenomenon can be found in the outlet static pressure curves. However, the above two phenomena do not exist in the moderate and slow startups. The transient characteristics of dimensionless flow rate and head are associated with the length of startup time, while the dimensionless shaft power is not. There is no similarity in transient performance between rapid, moderate, and slow startup cases.

Numerical Study on the Gas-Water Two-Phase Flow in the Self-Priming Process of Self-Priming Centrifugal Pump

A self-priming centrifugal pump can be used in various areas such as agricultural irrigation, urban greening, and building water-supply. In order to simulate the gas-water two-phase flow in the self-priming process of a self-priming centrifugal pump, the unsteady numerical calculation of a typical self-priming centrifugal pump was performed using the ANSYS Computational Fluid X (ANSYS CFX) software. It was found that the whole self-priming process of a self-priming pump can be divided into three stages: the initial self-priming stage, the middle self-priming stage, and the final self-priming stage. Moreover, the self-priming time of the initial and final self-priming stages accounts for a small percentage of the whole self-priming process, while the middle self-priming stage is the main stage in the self-priming process and further determines the length of the self-priming time.

Effect of Reflux Hole on the Transient Flow Characteristics of the Self-Priming Sewage Centrifugal Pump

The reflux hole has a large effect on the performance of self-priming centrifugal pumps. In order to study the effects of the reflux hole on the performance and transient flow characteristics of the self-priming centrifugal pump, four different areas of the reflux hole inside an external mixed self-priming pump were proposed. The 3D transient flow was numerically simulated under different operating conditions for the investigated pump. The differential pressure, reflux quantity and transient flow characteristics near the reflux hole were analysed, and then the effects of the reflux hole area on the pressure fluctuation characteristics and performance of the pump were further researched. The results show that the differential pressure and reflux quantity is zero around the best-efficiency point. The vorticity magnitude near the exit of the reflux hole is significant, and the unsymmetrical flow structures represent periodic motion over time in the cross-section. The pressure fluctuation intensities of monitoring points P2-P5 upstream of the reflux hole were generally larger than others and decreased with a decrease in reflux hole area. With a decrease of the reflux hole area, the performance of the pump improved to some extent.

Numerical and experimental study of the self‐priming process of a multistage self‐priming centrifugal pump

Pumps are a type of general machine with many varieties and extensive application. To simulate really the self-priming process of multistage self-priming centrifugal pump, the numerical calculation of gas-water two-phase flow on a four-stage self-priming pump was performed based on ANSYS CFX software. Moreover, a transparent plastic tube was installed at the pump outlet, and the photographic technology was used to observe the appearance of gas-water escape during the self-priming process of multistage self-priming centrifugal pump. The experimental results were compared with the numerical results. It is found that the whole self-priming process of self-priming pump can be divided into three stages: the initial self-priming stage, the middle self-priming stage, and the final self-priming stage. Moreover, the self-priming time of the initial and final self-priming stages accounts for a small percentage of the whole self-priming process, while the middle self-priming stage is the main stage in the self-priming process, which determines the length of self-priming time. The experimental results are very close to the numerical results in the initial and middle self-priming stages.

A transfer convolutional neural network for fault diagnosis based on ResNet-50

With the rapid development of smart manufacturing, data-driven fault diagnosis has attracted increasing attentions. As one of the most popular methods applied in fault diagnosis, deep learning (DL) has achieved remarkable results. However, due to the fact that the volume of labeled samples is small in fault diagnosis, the depths of DL models for fault diagnosis are shallow compared with convolutional neural network in other areas (including ImageNet), which limits their final prediction accuracies. In this research, a new TCNN(ResNet-50) with the depth of 51 convolutional layers is proposed for fault diagnosis. By combining with transfer learning, TCNN(ResNet-50) applies ResNet-50 trained on ImageNet as feature extractor for fault diagnosis. Firstly, a signal-to-image method is developed to convert time-domain fault signals to RGB images format as the input datatype of ResNet-50. Then, a new structure of TCNN(ResNet-50) is proposed. Finally, the proposed TCNN(ResNet-50) has been tested on three datasets, including bearing damage dataset provided by KAT datacenter, motor bearing dataset provided by Case Western Reserve University (CWRU) and self-priming centrifugal pump dataset. It achieved state-of-the-art results. The prediction accuracies of TCNN(ResNet-50) are as high as 98.95% ± 0.0074, 99.99% ± 0 and 99.20% ± 0, which demonstrates that TCNN(ResNet-50) outperforms other DL models and traditional methods.

A New Snapshot Ensemble Convolutional Neural Network for Fault Diagnosis

Deep learning (DL) has been widely applied in fault diagnosis field. The ensemble of DL can significantly improve the generalization ability of DL. Snapshot ensemble learning, which uses the cyclic learning rate scheduler (CLR) and then combines the local minima in once training to form an ensemble method, has shown powerful performance. However, the learning rate range of CLR should be pre-defined by experiences, which may limit its prediction accuracy. In this paper, a new snapshot ensemble convolutional neural network (SECNN) is proposed, which can find the proper range of learning rate for SECNN automatically when facing a new dataset. First, a max–min cosine cyclic learning rate scheduler (MMCCLR) is designed to avoid learning rate range being affected by other parameters. Then, a new learning rate testing (logLR Test) is applied to estimate the proper learning rate range for MMCCLR. Finally, the SECNN with MMCCLR is developed. The SECNN is tested on three famous datasets, including bearing dataset of Case Western Reserve University, self-priming centrifugal pump dataset, and bearing dataset provided by the Machinery Failure Prevention Technology. The results have been improved a lot by the proposed SECNN methods. The SECNN has also achieved the start-of-the-art prediction accuracies by comparing with other DL and traditional methods.

INFLUENCING FACTORS OF SELF-PRIMING TIME OF MULTISTAGE SELF-PRIMING CENTRIFUGAL PUMP

Self-priming centrifugal pump are a type of drainage and irrigation equipment applied in crop irrigation, urban landscaping, dust prevention and cooling, and building water supply. At present, single-stage self-priming centrifugal pumps dominate the pump market. Hence, the market share for multistage self-priming pumps, which can provide high-pressure liquid, is barely adequate. Self-priming time is an important parameter that measures the self-priming performance of multistage self-priming centrifugal pumps. Although many studies have focused on the influences of a single factor on the self-priming time of single-stage self-priming centrifugal pumps, only a few have discussed the self-priming time of multistage self-priming pumps. In the current work, we conducted an experimental study that combined the orthogonal, grey correlation, and self-priming time tests to investigate the influencing factors of the self-priming time of a multistage self-priming centrifugal pump and shorten the corresponding self-priming time. The outlet width of the impeller blade, the radial gap between the impeller and the diffuser, the area of backflow hole, and the number of stages of the multistage self-priming centrifugal pump were selected as the influencing factors in the orthogonal test. The orthogonal analysis of the self-priming time of the multistage self-priming centrifugal pump was conducted, and the results were used as the basis in obtaining the order of importance of all influencing factors through the grey correlation test. Results demonstrate that self-priming time increases gradually with an increase in impeller blade outlet width but that it decreases continuously with an increase in stage number and area of backflow hole. As radial gap increases, self-priming time increases and then decreases. In summary, the area of backflow hole is the most important influencing factor of self-priming time of the multistage self-priming centrifugal pump, followed by impeller blade outlet width, radial gap, and stage number. These findings provide important references for shortening the self-priming time of multistage self-priming centrifugal pumps. Keywords: Multistage self-priming centrifugal pump, Grey correlation test, Orthogonal test; Self-priming time rrelation test, Bomba centrífuga autocebante multietapa, Ensayo de correlación Grey, Ensayo orthogonal, Ensayo de rrelación de tiempo autocebante