Fault Diagnosis Of Pump Research Articles

Unsupervised Fault Diagnosis of Sucker Rod Pump Using Domain Adaptation with Generated Motor Power Curves

The poor real-time performance and high maintenance costs of the dynamometer card (DC) sensors have been significant obstacles to the timely fault diagnosis in the sucker rod pumping system (SRPS). In contrast to the DCs, the motor power curves (MPCs), which are accessible easily and highly associated with the entire system, have been attempted to predict the working conditions of the SRPS in recent years. However, the lack of labeled MPCs limits the successful applications in the industrial scenario. Thereby, this paper presents an unsupervised fault diagnosis methodology to leverage the generated MPCs of different working conditions to diagnose the actual unlabeled MPCs. Firstly, the MPCs of six working conditions are generated with an integrated dynamics mathematical model. Secondly, a framework named mechanism-assisted domain adaptation network (MADAN) is proposed to minimize the distribution discrepancy between the generated and actual MPCs. Specifically, benefiting from introducing the mechanism analysis to label the collected MPCs preliminarily, a conditional distribution discrepancy metric is defined to guarantee a more accurate distribution matching with respect to different working conditions. Eventually, validation experiments are performed to evaluate the mathematical model and the diagnosis method with a set of actual MPCs collected by a self-developed device. The experimental result demonstrates that the proposed method offers a promising approach for the unsupervised diagnosis of the SRPS.

An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal

Hydraulic pump is a critical component of a hydraulic transmission system. Its normal and stable operation will directly affect the reliability of the whole system. Owing to the complexity and concealment of fault information, it is crucial to explore an effective method for fault diagnosis of hydraulic piston pump. The obvious change of vibration signal can be observed when different fault types occur, and the implied characteristics of pressure signals are also varying. In this research, an adaptive convolutional neural network (CNN) is constructed based on the ontology representation of pump. First, time–frequency characteristics of pressure signals are obtained via continuous wavelet transform. Second, a deep CNN is established by setting initial hyperparameters. Third, Bayesian optimization is employed to achieve automatic learning of main important hyperparameters to construct an adaptive CNN. The proposed method has better performance for fault diagnosis of hydraulic piston pump compared with other modern intelligent methods.

Fault diagnosis of Fuel Pump Based on Wavelet Denoising and Deep Learning

Aiming at the problem that the signal collected by the sensor of aircraft fuel system contains much noise, which masks the effective fault characteristics, a fault diagnosis method of aircraft fuel pump based on wavelet threshold denoising and convolutional neural network is proposed. Wavelet threshold denoising is added to the traditional data preprocessing to eliminate the noise contained in the data; the convolution neural network is used to build a fault detection model to identify and locate the fault of the fuel pump. The experimental results show that this method can accurately and effectively identify and locate the fuel pump fault based on the noisy signal, and the recognition accuracy is more than 85%, which proves the effectiveness of this method for aircraft fuel pump detection.

A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images

As an essential part of hydraulic transmission systems, hydraulic piston pumps have a significant role in many state-of-the-art industries. Thus, it is important to implement accurate and effective fault diagnosis of hydraulic piston pumps. Owing to the heavy reliance of shallow machine learning models on the expertise and experience of engineers, fault diagnosis based on deep models has attracted significant attention from academia and industry. To construct a deep model with good performance, it is necessary and challenging to tune the hyperparameters (HPs). Since many existing methods focus on manual tuning and use common search algorithms, it is meaningful to explore more intelligent algorithms that can automatically optimize the HPs. In this paper, Bayesian optimization (BO) is employed for adaptive HP learning, and an improved convolutional neural network (CNN) is established for fault feature extraction and classification in a hydraulic piston pump. First, acoustic signals are transformed into time–frequency distributions by a continuous wavelet transform. Second, a preliminary CNN model is built by setting initial HPs. The range of each HP to be optimized is identified. Third, BO is employed to select the optimal combination of HPs. An improved model called CNN-BO is constructed. Finally, the diagnostic efficiency of CNN-BO is analyzed using a confusion matrix and t-distributed stochastic neighbor embedding. The classification performance of different models is compared. It is found that CNN-BO has a higher accuracy and better robustness in fault diagnosis for a hydraulic piston pump. This research will provide a basis for ensuring the reliability and safety of the hydraulic pump.

Intelligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization

Hydraulic axial piston pump is broadly-used in aerospace, ocean engineering and construction machinery since it is the vital component of fluid power systems. In the light of the undiscoverability of its fault and the potential serious losses, it is valuable and challenging to complete the fault identification of a hydraulic pump accurately and effectively. Owing to the limitations of shallow machine learning methods in the intelligent fault diagnosis, more attention has been paid to deep learning methods. Hyperparameter plays an important role in a deep learning model. Although some manual tuning methods may represent good results in some cases, it is hard to reproduce due to the differences of datasets and other factors. Hence, Bayesian optimization (BO) algorithm is adopted to automatically select the hyperparameters. Firstly, the time–frequency images of vibration signals by continuous wavelet transform are taken as input data. Secondly, by setting some hyperparameters, a preliminary convolutional neural network (CNN) model is established. Thirdly, by identifying the range of each hyperparameter, BO based on Gaussian process is employed to construct an adaptive CNN model named CNN-BO. The performance of CNN-BO is verified by comparing with traditional LeNet 5 and improved LeNet 5 with manual optimization. The results indicate that CNN-BO can accomplish the intelligent fault diagnosis of a hydraulic pump accurately.

Data Augmentation via Randomized Wavelet Expansion and Its Application in Few-Shot Fault Diagnosis of Aviation Hydraulic Pumps

In general, deep learning-based fault diagnosis methods need a large number of training samples, which are often not available in real applications. Aiming at this problem, this article develops a new data augmentation method, i.e., randomized wavelet expansion (RWE), to generate a set of synthesis samples that share similar characteristics with the original sample. The first key point is that the amplitudes of wavelet coefficients at a randomly selected frequency band are enlarged through random expansion. Another key point is that the synthesis samples are processed to have the same mean values and standard deviations as their corresponding original sample. Afterward, the synthesis samples are used as the training dataset to train a deep convolutional neural network (CNN) for implementing the few-shot fault diagnosis of aviation hydraulic pumps. Finally, the performance has been validated through a series of experiments.

Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals

Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals

Empirical mode reconstruction: Preserving intrinsic components in data augmentation for intelligent fault diagnosis of civil aviation hydraulic pumps

A problem in data-driven fault diagnosis of civil aviation hydraulic pumps is that the faulty samples are much fewer than the healthy samples. To solve this problem, this paper develops a data augmentation method, namely empirical mode reconstruction (EMR), to augment faulty samples which preserve the intrinsic components in the original real samples. A significant property of the developed EMR is that the augmented samples are different but share very similar characteristics and category with the corresponding real samples, to properly guide the training of deep learning models, with the ultimate goal of yielding high diagnostic accuracies. First, the faulty training samples are converted to a series of intrinsic mode functions using empirical mode decomposition. Second, an intrinsic mode function is randomly selected and re-scaled with a weight randomly selected from a properly predefined range. Third, these intrinsic mode functions are used to reconstruct the 1-dimensional samples, which serve as the augmented samples. Besides, the mean values and standard deviations of the augmented samples are kept the same with the corresponding original sample. Finally, the efficacy of the developed EMR in imbalanced fault diagnosis of civil aviation hydraulic pumps is validated through a group of experimental comparisons.

Fault Prediction of Centrifugal Pump Based on Improved KNN

To effectively predict the faults of centrifugal pumps, the idea of machine learning k-nearest neighbor algorithm (KNN) was introduced into the traditional Mahalanobis distance fault discrimination, and an improved centrifugal pump fault prediction model of KNN based on the Mahalanobis distance is proposed. In this method, the Mahalanobis distance is used to replace the distance function in the conventional KNN algorithm. Grid search and cross-validation are used to determine the optimal K value of the prediction model. A centrifugal pump test rig was established to solve three common faults of centrifugal pumps: cavitation, impeller damage, and machine seal damage, and the method was verified. The results show that this method can effectively distinguish the specific fault types of centrifugal pumps based on vibration signals, and the fault prediction accuracy of the off-balance condition is up to 82%. This study provides a novel idea and method for centrifugal pump fault prediction and diagnosis and avoids the interaction between parameters when monitoring multiple parameters.

Identification of inlet pipe blockage level in centrifugal pump over a range of speeds by deep learning algorithm using multi-source data

This paper focusses on the identification of the blockage fault in the inlet pipe of centrifugal pump over a range of speed using data obtained from different types of sensors. Acceleration, pressure and motor line current signatures taken using accelerometer, pressure transducer and current probe, respectively, and are used for identification of the pipe blockage level. Methodology is given for the blockage detection based on the multiclass classification using the deep learning algorithm at different blockage levels and speed of rotation of the pump. Importance of the multi-source data collection is emphasized based on the obtained results. Effect of the motor speed is also discussed when considered as an input feature to the classifier. It is observed that the use of combinations of different types of sensors help to identify the blockage level with better accuracy (close to 100% for many combinations). Blockage level prediction at each speed separately, is also given, which can be used for the fault diagnosis of single speed pumps. Finally, the performance of the classifier is tested using some unknown data (different from the data at training speed) to check the blockage prediction accuracy of the classifier.

An improved convolutional neural network with an adaptable learning rate towards multi-signal fault diagnosis of hydraulic piston pump

Hydraulic piston pump is a vital component of hydraulic transmission system and plays a critical role in some modern industrials. On account of the deficiencies of traditional fault diagnosis in preprocessing of original data and feature extraction, the intelligent methods based on deep learning accomplish the automatic learning of fault information by integrating feature extraction and classification. As a popular deep learning model, convolutional neural network (CNN) has been demonstrated to be potent and effective in image classification. In this research, an improved intelligent method based on CNN with adapting learning rate is constructed for fault diagnosis of a hydraulic piston pump. Firstly, three raw signals are converted into two dimensional time–frequency images by continuous wavelet transform, including vibration signal, pressure signal and sound signal. Secondly, an improved deep CNN model is built with an adaptive learning rate strategy for identifying the different fault types. Moreover, t-distributed stochastic neighbor embedding is employed to visualize the distribution of features learned by the main layers of CNN model. Confusion matrix is used to analyze the classification accuracy of each fault type. Compared with the CNN model without adapting learning rate, the improved model achieves a higher accuracy based on the selected three kinds of signals. Experiments indicate that the improved CNN model can effectively and accurately identify various faults for a hydraulic piston pump.

Fault Diagnosis in Centrifugal Pump using Support Vector Machine and Artificial Neural Network

Centrifugal pumps are commonly utilized in thermo-fluidic systems in the industry. Being a rotating machinery, they are prone to vibrations and their premature failure may affect the system predictability and reliability. To avoid their premature breakdown during operation, it is necessary to diagnose the faults in a pump at their initial stage. This study presents the methodology to diagnose fault of a cent rifugal pump using two distinct machine learning techniques, namely, Support vector machine (SVM) and Artificial neural network (ANN). Different statistical features are extracted in the time and the frequency domain of the vibration signal for different working conditions of the pump. Furthermore, to decrease the dimensionality of the obtained features different feature ranking (FR) methods, namely, Chi-square, ReliefF and XGBoost are employed. ANN technique is found to be more efficient in classifying faults in a centrifugal pump as compared to the SVM, and Chi-square and XGBoost ranking techniques are better than ReliefF at sorting more relevant features. The results presented in thus study demonstrate that an ANN based machine learning approach with Chi-square and XGBoost feature ranking techniques can be used effectively for the fault diagnosis of a centrifugal pump.

Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization

The hydraulic axial piston pump is the power heart of the hydraulic transmission system in aerospace equipment and industrial filed. Its stable operation will directly affect the safety and reliability of the whole equipment. It is very significant to realize its health status monitoring and intelligent fault diagnosis. In view of the restrictions of traditional mechanical fault diagnosis in the dependence on a large number of signal processing technologies and expert diagnosis experience, as well as the time-consuming of data preprocessing, it is very meaningful to explore new ideas and methods to realize intelligent fault diagnosis of hydraulic piston pump. Based on the standard LeNet-5 model, the kernel size and kernel number are improved, and the batch normalization layers are added to the network architecture. Based on the Improve-LeNet-5 model, the recognition accuracy is chosen as the target value of the fitness function, the hyperparameters of the Improve-LeNet-5 model are automatically optimized via particle swarm optimization (PSO), including the learning rate, the number of convolution kernels, batch size, and the number of neurons in the fully connected layer. Finally, the PSO-Improve-CNN diagnostic model is constructed. And it is employed to classify and identify five signals data of hydraulic piston pump: normal state, swash plate wear, sliding slipper wear, loose slipper and center spring failure. Research result indicates that the recognition accuracy of PSO-Improve-CNN model can reach 98.71%, and the highest recognition accuracy can reach 99.06%, which are respectively higher than the standard LeNet-5 and Improve-LeNet-5 about 5.23% and 2.25%. By comparing with AlexNet, VGG11, VGG13, VGG16, and GoogleNet, the PSO-Improve-CNN model presents the highest diagnostic accuracy, less time in training and testing, and greater robustness. The comprehensive performance of the proposed model is demonstrated to be much stronger.

Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning

Digital twin (DT) is emerging as a key technology for smart manufacturing. The high fidelity DT model of the physical assets can produce system performance data that is close to reality, which provides remarkable opportunities for machine fault diagnosis when the measured fault condition data are insufficient. This paper presents an intelligent fault diagnosis framework for machinery based on DT and deep transfer learning. First, the DT model of the machine is built by establishing the simulation model and with further updating through continuously measured data from the physical asset. Second, all important machine conditions can be simulated from the built DT. Third, a new-type deep structure based on novel sparse de-noising auto-encoder (NSDAE) is developed and pre-trained with condition data from the source domain, as generated from the DT. Then, to achieve accurate machine fault diagnosis with possible variations in working conditions and system characteristics, the pre-trained NSDAE is fine-tuned using parameter transfer with only one sample from the target domain. The presented method is validated through a case study of triplex pump fault diagnosis. The experimental results demonstrate that the proposed method achieves intelligent fault diagnosis with a limited amount of measured data and outperforms other state-of-the-art data-driven methods.

Dynamic modeling of fluid nonlinear compression loss and flow loss oriented to fault diagnosis of axial piston pump

Volumetric efficiency (VE) is an extremely important index to evaluate the performance of pump and motor. Efforts have been concentrated on the causes and character of leakage loss, but few quantitative analyses of pump kinematic clearances (KCs) identification and nonlinear compression loss caused by air content are discussed. This paper clarifies the nonlinear compression loss resulted from the air content of the oil in detail and proposes an improved flow loss model of the swash-plate axial piston pump (SAPP). Then, combining the improved model with experimental results, the KCs of SAPP are identified. It has been verified that a reasonable sampling path is useful for reducing sampling numbers and guaranteeing identification accuracy. Finally, the identification and quantization of the wear fault of SAPP are realized by analyzing the estimated value of KCs. The proposed method is simple and easy to implement and shows high predictive accuracy. It provides a possible and promoting technology support for the autonomous calibration of the system parameters and the active compensation of the system control.

Fault Diagnosis of Main Pump in Converter Station Based on Deep Neural Network

As the core component of the valve cooling system in a converter station, the main pump plays a major role in ensuring the stable operation of the valve. Thus, accurate and efficient fault diagnosis of the main pump according to vibration signals is of positive significance for the detection of failure equipment and reducing the maintenance cost. This paper proposed a new neural network based on the vibration signals of the main pump to classify four faults and one normal state of the main pump, which consisted of a convolutional neural network (CNN) and long short-term memory (LSTM). Multi-scale features were extracted by two CNNs with different kernel sizes, and temporal features were extracted by LSTM. Moreover, random sampling was used in data processing for imbalanced data, which is meaningful for data symmetry. Experimental results indicated that the accuracy of the network was 0.987 obtained from the test set, and the average values of F1-score, recall, and precision were 0.987, 0.987, and 0.988, respectively. It was found that the proposed network performed well in a multi-label fault diagnosis of the main pump and was superior to other methods.

Cavitation Fault Diagnosis of High-speed Axial Piston Pump Based on Spectrum Analysis and Convolutional Neural Network

Cavitation Fault Diagnosis of High-speed Axial Piston Pump Based on Spectrum Analysis and Convolutional Neural Network

Fault Diagnosis of Axial Piston Pump Based on Polynomial Chirplet Transform and Variational Mode Decomposition Under Variable Speed Conditions

Fault Diagnosis of Axial Piston Pump Based on Polynomial Chirplet Transform and Variational Mode Decomposition Under Variable Speed Conditions

Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump

AbstractThis paper explores artificial intelligent training schemes based on multilayer perceptron, considering back propagation and genetic algorithm (GA). The hybrid scheme is compared with the traditional support vector machine approach in the literature to analyze both fault and normal scenarios of a centrifugal pump. A comparative analysis of the performance of the variables was carried out using both schemes. The study used features extracted for three decomposition levels based on wavelet packet transform. In order to investigate the effectiveness of the extracted features, two mother wavelets were investigated. The salient part of this work is the optimization of the hidden layers numbers using GA. Furthermore, this optimization process was extended to the multilayer perceptron neurons. The evaluation of the model system performance used for the study shows better response of the extracted features, and hidden layers variables including the selected neurons. Moreover, the applied training algorithm used in the work was able to enhance the classifications obtained considering the hybrid artificial intelligent scheme been proposed. This work has achieved a number of contributions like GA‐based selection of hidden layers and neuron, applied in neural network of centrifugal pump condition classification. Furthermore, a hybrid training method combining GA and back propagation (BP) algorithms has been applied for condition classification of a centrifugal pump. The obtained results have shown the good ability of the proposed methods and algorithms.

Fault Diagnosis of Axial Piston Pump Based on Extreme-Point Symmetric Mode Decomposition and Random Forests

Aiming at fault diagnosis of axial piston pumps, a new fusion method based on the extreme-point symmetric mode decomposition method (ESMD) and random forests (RFs) was proposed. Firstly, the vibration signal of the axial piston pump was decomposed by ESMD to get several intrinsic mode functions (IMFs) and an adaptive global mean curve (AGMC) on the local side. Secondly, the total energy was selected as the data of feature extraction by analyzing the whole oscillation intensity of the signal. Thirdly, the data were preprocessed and the labels were set, and then, they were adopted as the training and testing set of machine learning samples. Lastly, the RFs model was created based on machine learning service (MLS) to diagnose the faults of the axial piston pump on the cloud. Using the test and verifying the data set for comparative testing, the fault diagnosis precision rates of the model are above 90.6%, the recall rates are more than 90.9%, the F1 score is higher than 90.7%, and the accuracy rate of this model reached 97.14%. A benchmark data simulation of mechanical transmission systems and an experimental data investigation of an axial piston pump are performed to manifest the superiority of the present method by comparing with classification and regression trees (CART) and support vector machine (SVM).