Rotor Fault Research Articles

Rotor fault diagnosis of centrifugal pumps in nuclear power plants based on CWGAN-GP-CNN for imbalanced dataset

As a crucial device in nuclear power plants, centrifugal pumps undertake the critical role of cooling water circulation. Centrifugal pump rotor misalignment and unbalanced faults cause pump performance degradation, vibration increase, and equipment damage, thus seriously affecting the safety and reliability of nuclear power plants. In the process of centrifugal pump rotor fault, the difficulty in obtaining data samples and the limited amount of data can lead to an imbalance problem between the quantity of normal state and fault state samples in the dataset. In order to solve the problem, this paper proposed a CWGAN-GP model for generating rotor fault data based on CGAN and WGAN-GP models, and combined it with a two-stream CNN model to realize the rotor fault diagnosis with an imbalanced dataset. The quality and performance of the data generated by the proposed method were evaluated and validated in terms of visualization analysis, statistical indicators, and comparison with different data generation models. The results show that the CWGAN-GP model can generate high-quality data. Meanwhile, compared with other models on datasets with different degrees of imbalance, the two-stream CNN model is more effective in fault diagnosis on the expanded dataset by the CWGAN-GP model, and the improvement of fault diagnosis accuracy ranges from 1.40% to 13.33%.

In-depth research on fault diagnosis of turbine rotor utilizing NGSABO-optimized VMD and CNN-BiLSTM

Abstract To solve the problem of difficulty in extracting and identifying fault types during turbine rotor operation, a fault diagnosis method based on improved subtraction mean optimizer (NGSABO) algorithm to optimize variational mode decomposition (VMD) and CNN-BiLSTM neural network is proposed. Firstly, three improvements are made to the subtraction average optimizer algorithm. Secondly, the optimal VMD parameter combination of NGSABO adaptive selection mode decomposition number K and penalty factor is used to decompose the rotor fault signal, and the minimum sample entropy is used as the fitness function for feature extraction. Combining convolutional neural network and bidirectional long short-term memory network to identify and classify features. Compared with other methods, this method has outstanding performance in the diagnosis of single and coupled rotor faults. The accuracy of fault diagnosis reaches 98.5714%, which has good practical application value.

Rotor dynamic response prediction using physics-informed multi-LSTM networks

The deep learning method provides an effective alternative to numerical simulations for establishing the nonlinear input-output relationship and calculating dynamic responses of rotor systems. To overcome the low generalization capability of pure data-driven long short-term memory (LSTM) networks when predicting dynamic responses to out-of-distribution inputs, a dynamic response prediction method using physics-informed multi-LSTM networks is proposed. This approach incorporates required physical constraints into the deep LSTM network, allowing the model training process to optimize the network parameters within the feasible solution space that adheres to physical laws. Consequently, this enhances the physical interpretability of the deep learning model. Specifically, two physics-informed multi-LSTM network architectures are introduced, and physical laws of equation of motion, state dependency and hysteretic constitutive relationship are considered to construct the physics loss. The feasibility of the proposed method is verified by a Bouc-Wen hysteresis model and a simulated gas generator rotor. The response prediction performance of the two networks is validated on a constructed fault rotor dataset with significant sample differences, along with cross-speed and cross-node prediction validation for the rotor system. The results demonstrate that the trained networks exhibit strong robustness and generalization capabilities, making them suitable as surrogate models for rotor systems.

Diagnosis of Mechanical Rotor Faults in Drones Using Functional Gaussian Mixture Classifier

Diagnosis of Mechanical Rotor Faults in Drones Using Functional Gaussian Mixture Classifier

Efficiency-Centered Fault Diagnosis of In-Service Induction Motors for Digital Twin Applications: A Case Study on Broken Rotor Bars

The uninterrupted operation of induction motors is crucial for industries, ensuring reliability and continuous functionality. To achieve this, we propose an innovative approach that utilizes an efficiency model-based digital shadow system for in situ failure detection and diagnosis (FDD) in induction motors (IMs). The shadow model accurately estimates IM losses and efficiency across various operational conditions. Our proposed method utilizes efficiency as the primary indicator for fault detection, while losses serve as condition indicators for fault diagnosis based on real-time motor parameters and loss sources. We introduce a bond graph as a fault diagnosis network, linking loss sources, motor parameters, and faults. This interconnected approach is the key aspect of our proposed diagnostic method and aims to be used in fault diagnosis as a general method. A case study of a broken rotor bar is used to validate the proposed method using a dataset of five motors. Among these, one motor operates without failure, while the remaining four exhibit broken rotor faults categorized as 1, 2, 3, and 4. The proposed method achieves 99.99% precision in identifying one to four defective rotor bars in IMs. Comparative analysis demonstrates good performance compared to vibration-based FDD approaches. Moreover, our methodology is computationally efficient and aligned with Industry 4.0 requirements.

Imbalanced Diagnosis Scheme for Incipient Rotor Faults in Inverter-Fed Induction Motors

Recently, fault diagnosing supervised classifiers have been widely proposed to diagnose both electric and mechanical faults in induction motors (IM). However, many of them require a large amount of data, which implies a great effort required for processing fault-related features and building the training set. Furthermore, in real-world datasets, it is required to deal with highly skewed data distributions, also known as class imbalance, which is a limiting issue and can misguide the tuning of machine learning algorithms. Resampling techniques based on a synthetic generation of minority class observations aim to address this problem. Last but not least is the fact that inverter-fed IM introduces undesired harmonics in the monitoring signal altering the diagnosis patterns. This diagnosis scheme is evaluated on experimental imbalanced data oriented to deal with the diagnosis of a rotor in situations where it is fed with an inverter. The results show how this imbalanced approach determines the actual diagnosis performance on a small amount of data. The experimental results demonstrate that balanced training sets built with class balancing techniques improve the classifier and therefore its performance for diagnosing incipient rotor faults in inverter-fed IM with studied and interpretable features recently proposed in this field of study.

UAV propeller fault diagnosis using deep learning of non-traditional χ2-selected Taguchi method-tested Lempel–Ziv complexity and Teager–Kaiser energy features

Fault detection and isolation in unmanned aerial vehicle (UAV) propellers are critical for operational safety and efficiency. Most existing fault diagnosis techniques rely basically on traditional statistical-based methods that necessitate better approaches. This study explores the application of untraditional feature extraction methodologies, namely Permutation Entropy (PE), Lempel–Ziv Complexity (LZC), and Teager–Kaiser Energy Operator (TKEO), on the PADRE dataset, which encapsulates various rotor fault configurations. The extracted features were subjected to a Chi-Square (χ2) feature selection process to identify the most significant features for input into a Deep Neural Network. The Taguchi method was utilized to test the performance of the recorded features, correspondingly. Performance metrics, including Accuracy, F1-Score, Precision, and Recall, were employed to evaluate the model’s effectiveness before and after the feature selection. The achieved accuracy has increased by 0.9% when compared with results utilizing traditional statistical methods. Comparative analysis with prior research reveals that the proposed untraditional features surpass traditional methods in diagnosing UAV propeller faults. It resulted in improved performance metrics with Accuracy, F1-Score, Precision, and Recall reaching 99.6%, 99.5%, 99.5%, and 99.5%, respectively. The results suggest promising directions for future research in UAV maintenance and safety protocols.

Self-powered sensor for online monitoring of eccentricity faults in rotating machinery and its application in spindle eccentricity monitoring of machine tools

With their unique structures and functionalities, rotating machineries are widely employed in various high-end industries. However, eccentric faults of rotors during continuous high-speed operation represent a critical factor in causing safety accidents. Therefore, real-time monitoring of rotor health is crucial for promptly identifying potential safety hazards and fault indications, enabling preventative maintenance, and enhancing safety performance. Nonetheless, traditional monitoring methods rely on sensors installed on rotating components, which are prone to interference in rotational environments, involve complex installation and maintenance procedures, and pose significant challenges to rotor health monitoring. In this study, a self-powered rotor eccentricity monitoring sensor (RE-TENGs) is designed and fabricated, integrating triboelectric nanogenerator technology. This sensor utilizes the rotor as the self-sensing entity, requiring no external power supply and featuring simplified installation, enabling real-time monitoring of rotor health during rotational machinery operation. A linear relationship between the RE-TENG's eccentric response and electrical characteristics was established through dynamic testing. Furthermore, the actual eccentricity orientation of the rotor was successfully determined by employing vector analysis and synthesis methods with multiple RE-TENGs coupled. To further validate the practicality and accuracy of RE-TENGs, a monitoring testbed for eccentric faults of the spindle rotor in a CNC machine tool was constructed, with the spindle rotor's eccentric fault simulated through misaligned installation. Experimental results demonstrate that RE-TENGs can effectively detect rotor faults induced by eccentric forces during the actual operation of machine tools, accurately determining the eccentric direction and displacement. With an actual angle recognition error of less than ±0.824° and an eccentric distance recognition accuracy exceeding 98 %, the exceptional performance of RE-TENGs in monitoring and precise identification of eccentric faults in rotating machinery rotors is unequivocally verified. By integrating triboelectric nanogenerator (TENG) technology, this study realizes real-time monitoring and precise identification of eccentric faults in rotating machinery rotors. It provides a novel solution for health condition monitoring of rotating machinery and offers a reference for overcoming the cumbersome installation and complex wiring of traditional sensors in practical applications.

ResNet diagnosis of rotor faults in oil transfer pumps

To address rotor imbalance and misalignment in oil transfer pumps, an innovative diagnostic framework using Residual Network (ResNet) is proposed. The model incorporates advanced signal processing algorithms and strategic sensor placement to enhance diagnostic efficacy. A fault simulation test rig captured vibration signals from eight key measurement points on the pump. One-dimensional and multi-dimensional signal processing techniques generated comprehensive datasets for training and validating the model. Sensor placement optimization, focusing on the bearing seat's axial direction, inlet flange's vertical direction, and outlet flange's axial direction, increased rotor fault sensitivity. Time-frequency data processed via Short-Time Fourier Transform (STFT) achieved the highest diagnostic accuracy, surpassing 98 %. This study highlights the importance of optimal signal processing and precise sensor placement in improving the accuracy of diagnosing rotor faults in oil transfer pumps, thus enhancing the operational reliability and efficiency of energy transportation systems.

Genetically optimised SMOTE-based adversarial discriminative domain adaptation for rotor fault diagnosis at variable operating conditions

Abstract For safety, reliability, and uninterrupted output of gas turbines, aviation engines, power-generating equipment, pumps, gears, compressors etc., rotor mass imbalance must be detected and diagnosed to avoid catastrophic failure. Industry 4.0 relies on predictive digital maintenance and deep learning-based convolutional neural network (CNN), which predicts defects but fails if the operating conditions change. Research studies in various fields indicate that the domain shift issue occurs due to source and target samples being from different domains, which reduces prediction capability. Moreover, research studies are scarce in examining prediction capability under varying operating speeds for rotor mass imbalance. Hence, this research proposes the adversarial discriminative domain adaptation (ADDA) technique which predicts machine failures under various operational conditions. The efficacy of ADDA has been explored by introducing 1D-CNN as a source and a target encoder inside ADDA's architecture to take advantage of CNN's feature extraction capability. Further, this research effectively tackles CNN's inherent issues of overfitting and hyperparameters value selection. Furthermore, The real-world scenario has more healthy samples than fault condition samples, causing a multiclass imbalance in sample data, which affects the classification decision boundary and causes biased prediction. Hence, the proposed methodology first addresses the class imbalance through synthetic minority oversampling (SMOTE), then genetic algorithm optimizes 1D-CNN's hyperparameters, and the effective dropout layer positioning solves the overfitting. Finally, the deep learning-based SMOTE_ADDA_GO-1D-CNN decreases domain discrepancy with adversarial discriminative domain adaptation. The proposed methodology's efficacy has been explored through F1-Score, which is used as multiclass evaluation metrics, and it has been benchmarked against standard machine learning and deep learning algorithms. The test results of the proposed methodology surpassed all of them with maximum prediction accuracy. Thus, this study contributes to rotor mass imbalance detection and diagnosis for multiclass imbalanced data under varying operational conditions by successfully overcoming potential challenges during fault prediction.

Machine Learning Approaches for Fault Detection and Diagnosis in Electrical Machines: A Comparative Study of Deep Learning and Classical Methods

Fault detection and diagnosis in electrical machines are crucial for ensuring their safe and reliable operation. In recent years, machine learning techniques have emerged as powerful tools for addressing this challenge, offering the potential for more accurate and efficient fault detection and diagnosis compared to traditional methods. Among these techniques, deep learning has gained significant attention due to its ability to automatically learn relevant features from raw data. However, the performance of deep learning models in this domain has not been extensively compared to classical methods. This paper presents a comparative study of deep learning and classical methods for fault detection and diagnosis in electrical machines. The study evaluates the performance of various machine learning algorithms, including deep neural networks, support vector machines, decision trees, and ensemble methods, in detecting and diagnosing faults such as stator winding faults, rotor faults, and bearing faults. The experimental evaluation is conducted using real-world datasets obtained from electrical machines in industrial settings. Performance metrics such as accuracy, precision, recall, and F1-score are used to assess the effectiveness of each approach in detecting and diagnosing faults accurately and efficiently. The results of the study indicate that deep learning approaches, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), outperform classical methods in terms of fault detection and diagnosis accuracy. These deep learning models demonstrate the ability to automatically extract informative features from raw sensor data, enabling them to effectively identify subtle patterns indicative of faults. The study investigates the interpretability of deep learning models compared to classical methods, examining the extent to which the models can provide insights into the underlying causes of faults. While deep learning models typically operate as black boxes, techniques such as layer-wise relevance propagation (LRP) are employed to enhance their interpretability and facilitate the identification of relevant features contributing to fault detection and diagnosis. This comparative study provides valuable insights into the strengths and limitations of deep learning and classical methods for fault detection and diagnosis in electrical machines, offering guidance for practitioners and researchers in selecting appropriate approaches for their specific applications.

Sparse Tensor Decomposition of Multi-Sensory Data for Fault Localization in Rotating Machinery Health Monitoring

Multi-sensor monitoring is prevalent in modern structural health monitoring (SHM) practice. As the number of sensors and sampling requirements increase, a monitoring sensor network can generate substantial data which are high-volume and high-dimensional, especially for large structure and machinery. In condition-based monitoring (CBM) of rotating machines, e.g., gas turbine, rotor fault diagnosis serves a significant role in the system reliability, safety, and efficiency, which helps reduce potential damage to the on-rotor structures and avoid catastrophic failures. For multi-channel vibration measurement, classical rotor diagnosis approaches typically involve data fusion techniques based on cross spectral analysis for identifying spectral correlation, e.g., cross power spectral density, and/or matrix analysis tool for dimensionality reduction, e.g., principal component analysis. The operation on vectors or matrices may limit their effectiveness for higher-order array or tensor data. To circumvent this limitation, the third order vibrational spectral tensor is generated by representing the multi-channel acceleration spectra as the three-way array. Through nonnegative Tucker decomposition (NTD), the spectral tensor is decomposed into multiple principal factors: the spectral factor, segmental factor, channel-wise factor, and the dense tensor core. The correlations across the characteristic spectral contents and the sensor channels are revealed by the factorization, which enables the diagnosis of rotor fault and facilitates fault localization by identifying the dominant channels of the characteristic spectral factor. The method is validated on an experimental rotor testbed where the faulty channel with crack, rub, or misalignment fault, is effectively localized via 4-channel vibration measurements, which presents a promising approach for multi-sensor fusion and fault diagnosis in rotating machinery health monitoring.

Motor fault diagnosis based on composite multi-scale weighted reverse slope entropy and neighborhood preserving embedding

The motors are critical components of the electromechanical transmission in vehicles, and its operating status directly affects the maneuverability of vehicles. To quickly and accurately identify the operating status of motors, this paper proposes a new entropy - Composite Multi-scale Weighted Reverse Slope Entropy (CMWRSlE) for motor fault diagnosis, which is a more interpretable entropy due to its deep exploration of signals. Firstly, the composite multi-scale weighted reverse slope entropy values are extracted from the vibration signals of the motor in different states; Secondly, the extracted features are dimensionally reduced by the manifold learning algorithm – Neighbourhood Preserving Embedding (NPE) and classified by the hierarchical prototype-based approach (HPA) to achieve the fault diagnosis of the motor. Finally, the method proposed in this paper is validated through two sets of experimental data: motor rotor faults and motor bearing faults. The results show that the accuracy of the proposed method in motor fault diagnosis reaches 100 %, which indicates the effectiveness of the proposed method.

Research on rotor fault diagnosis technology of three-phase asynchronous motor based on NA-MEMD mutual information and SVM

Aiming at the problem of mode aliasing in the adaptive decomposition of nonlinear and non-stationary current signals generated by three-phase asynchronous motor faults, and the fault features contained in signals collected by a single sensor can not be accurately and comprehensively extracted and characterized when early rotor bar breakage and air gap eccentricity faults occur, A fault diagnosis method for three-phase asynchronous motor based on noise assisted multivariate empirical mode decomposition (NA-MEMD) and mutual information is proposed. Firstly, the NA-MEMD algorithm is used to decompose the three-phase stator current signal of the asynchronous motor to obtain multi-scale intrinsic mode functions (IMFs). Then, the correlation algorithm is used to screen the IMFs containing useful information. Then, the filtered IMF components are reconstructed into new signals and their features are extracted, Finally, support vector machines (SVM) are used to identify the rotor broken bars and air gap eccentric faults of the three-phase asynchronous motor. The experimental results show that the NA-MEMD method has a higher recognition rate than the traditional empirical mode decomposition (EMD) and the ensemble empirical mode decomposition (EEMD) methods.

Improved deep-learning rotor fault diagnosis based on multi vibration sensors and recurrence plots

Deep learning techniques are increasingly applied to time series data, offering promising results in various fields. Deep learning techniques can handle data from multiple sensors to detect anomalies in an industrial environment. This paper proposes a new method of anomaly detection based on a multilayer image representation of different vibration sensors’ recurrence plots. Each sensor’s recurrence plot forms a layer. The performance and reliability of our method were assessed using an experimental database collected under different load conditions and with different types of rotor anomalies. Experiment results demonstrate the effectiveness of GoogLeNet using individual and multi-layered recurrence plots to find rotor faults in an induction motors.

Diagnostics of Interior PM Machine Rotor Faults Based on EMF Harmonics

This article presents a detailed study on the diagnosis of rotor faults in an Interior Permanent Magnet Machine based on a mathematical model. The authors provided a wide literature review, mentioning the fault diagnosis methods used for Permanent Magnet Machines. The research emphasizes the necessity of precise assumptions regarding winding construction to accurately analyze the additional harmonics appearing in rotor faults caused by electromotive force (EMF), i.e., rotor eccentricity and magnet damage. The article also discusses specific features appearing in the spectrum of air gap permeance functions and the impact of rotor eccentricity and magnet damage on PM flux density distribution and as a consequence on EMF stator windings. The novelty of the presented content is the analysis of induced EMFs for cases of the simultaneous occurrence of rotor eccentricity and PM damage. The findings of this study provide valuable insights for the diagnosis and understanding of internal asymmetries in Interior PM Machines.

IMWMOTE: A novel oversampling technique for fault diagnosis in heterogeneous imbalanced data

In the realm of smart manufacturing, the urgent necessity of surmounting the technical hurdles associated with developing data-driven fault monitoring and intelligent diagnostic technologies for high-end equipment is imminent. In practical engineering applications, the challenging operating conditions and unfavorable environments for data collection often lead to the acquisition of health data that is not only constrained in terms of sample size but also exhibits imbalances and heterogeneity, collectively referred to as Small-Sample, Imbalanced, and Mixed-Class Scenarios. This poses a considerable challenge to the interpretability modeling of faults in high-end equipment, as identified by the scientific community. Prior investigations have highlighted the distinct benefits of resampling techniques in addressing the complexities of imbalanced fault modeling. Nevertheless, the suboptimal performance of current techniques remains a concern, primarily due to ambiguous representations of sample feature heterogeneity and the lack of sophisticated sampling balance strategies. For instance, the absence of tailored strategies and concomitant optimization approaches specifically designed for each heterogeneous feature remains a notable gap. In this study, we undertake a comprehensive analysis of the heterogeneity mechanisms inherent in fault feature data, with a particular emphasis on components like turbine rotor faults. Building upon these insights, we introduce a fault diagnosis framework utilizing the novel oversampling technique based-MWMOTE (IMWMOTE), to address these challenges effectively. This comprehensive framework not only ensures interpretability in classification but also seamlessly integrates an optimization mechanism. Notably, the efficacy and innovation of our proposed approach have been thoroughly verified through an extensive evaluation involving 20 fault diagnosis instances across three distinct categories: turbine rotor, bearings, and gears. The experimental outcomes clearly illustrate that IMWMOTE exhibits remarkable advantages in tackling the intricate challenges associated with imbalanced fault modeling, particularly when dealing with small sample heterogeneity. Given its demonstrated proficiency, the proposed approach holds significant potential in guiding interpretable fault modeling efforts in related domains, thus contributing to the advancement of fault diagnosis techniques.

Fuzzy control allocation of a positionable rotor quadrotor based on log‐barrier optimization and propulsion system fault toleration

AbstractHerein, a control system and a fault tolerance method for the rotor positionable quadrotor are proposed. Quadrotors that have a variable structure are made for different purposes. The rotor‐positionable quadrotor studied here, is a type of drone with a variable structure that has the ability to change the position of its rotors linearly along the axis of each arm. It can be seen that this capability can improve the drone robustness against disturbances and faults in comparison with regular quadcopters. Due to the over‐actuated dynamics of this type of quadrotor, the control allocation scheme based on log‐barrier optimization is employed to obtain the position and speed of each rotor. In this study, it is experimentally shown that rotor positioning not only reduces power consumption but also increases roll and pitch control inputs magnitude. Furthermore, when a fault occurs as a decrease in rotor speed, a fuzzy method is proposed to position the rotors which tolerates the fault. Finally, numerical simulations and experimental tests verified that rotor positioning can bring more robustness, reduction in power consumption, and fault tolerance in some rotor faults capabilities for quadrotors.

Rotor fault characterization study by considering normalization analysis, feature extraction, and a multi-class classifier

Background. Rotor faults are the most common malfunctions encountered, especially during the manufacturing stage, in asynchronous motors. These faults cause vibration in the motor torque and a decrease in efficiency. In recent years, the detection of rotor faults has been done using motor current. The reflection of rotor faults on motor current depends on slip, and therefore, the effect increases as the current grows. Good results are achieved in fault detection at nominal loads. However, especially when motor manufacturers are considered, testing the motor by loading it requires expensive testing equipment and long-term test procedures. Therefore, the detection of faults in the motor at no load is emphasized. However, since the effect of the fault decreases when the motor is at no load, fault detection becomes difficult. Generally, small-level faults cannot be detected. Objective. This study focuses on fault detection from the motor current at no load. The development current at no load was used to eliminate the negative effects of slip. However, since the slip is not constant, the change in frequency and amplitude values to be used as a feature makes the diagnosis difficult. Method. In this study, the spectrogram was used to evaluate the change during the start-up time. Thus, a standard dataset was determined for comparison. The texture properties of the spectrogram image were extracted using various methods. The extracted features were subjected to normalization analysis and classified using the k-NN algorithm. Results. In the classification phase, a classification accuracy of 98.66% was achieved using the k-NN method, and it was seen that the proposed method could be used for the detection of rotor faults. Conclusions. The study has successfully demonstrated that broken rotor bar faults in asynchronous motors can be diagnosed using the motor start-up data.

A Comprehensive 3-Steps Methodology for Vibration-based Fault Detection, Diagnosis and Localization in Rotating Machines

In any industry, it is the requirement to know whether the machine is healthy or not to operate machine further. If the machine is not healthy then what is the fault in the machine and then finally its location. The paper is proposing a 3-steps methodology for the machine fault diagnosis to meet the industrial requirements to aid the maintenance activity. The Step-1 identifies whether machine is healthy or faulty, then Step-2 detect the type of defect and finally its location in Step-3. This method is extended further from the earlier study on the 2-Steps method for the rotor defects only to the 3-Steps methodology to both rotor and bearing defects. The method uses the optimised vibration parameters and a simple Artificial Neural Network (ANN)-based Machine Learning (ML) model from the earlier studies. The model is initially developed, tested and validated on an experimental rotating rig operating at a speed above 1st critical speed. The proposed method and model are then further validated at 2 different operating speeds, one below 1st critical speed and other above 2nd critical speeds. The machine dynamics are expected to be significantly different at these speeds. This highlights the robustness of the proposed 3-Steps method. Conflict of Interest Statement The authors declare no conflicts of interest.