Fault Diagnosis Of Rotor System Research Articles

Cross Diversity Entropy-Based Feature Extraction for Fault Diagnosis of Rotor System

Cross Diversity Entropy-Based Feature Extraction for Fault Diagnosis of Rotor System

Experimental Research on Dynamic Characteristics of a Multi-Disc Rotor System Supported by Aerostatic Bearings

Gas bearings have the advantages of small friction loss, wide applicable speed range, no pollution, etc., and have important application prospects in micro and small high-speed rotating machinery. However, due to its compressibility and low viscosity, its dynamic stability in high-speed rotating machinery is the key to constraining its development. The experimental study of shaft system dynamics is the main means to explore the mechanism of rotor behavior. On the test platform of dynamic characteristics of multi-disc rotor system supported by aerostatic bearings, experimental research on the nonlinear dynamic characteristics of a rotor system was carried out, and nonlinear vibration test and analysis methods, such as axial orbits, bifurcation diagrams, and spectral characteristics, were adopted, and vibration phenomena, including the critical rotational speed accumulating energy and low-frequency accumulating energy, were presented and the vibration characteristics of bearing fracture faults were presented. The bearing supply pressure and rubber damping pad were introduced as a method to suppress the low-frequency vibration of the aerostatic bearing rotor system, and its vibration-reduction effect was verified by experiments. The above results can provide technical support for vibration control and fault diagnosis of rotor systems supported by aerostatic bearings.

Time-frequency post-processing method based on generalized S-transform and its application to aero engine rotor system fault diagnosis

Time-frequency post-processing method based on generalized S-transform and its application to aero engine rotor system fault diagnosis

Fault diagnosis of rotor systems with breathing slant cracks based on nonlinear output frequency response functions

When it comes to practical engineering, there is a high likelihood of shafts developing slant cracks due to torque transmission. These cracks exhibit breathing characteristics, repeatedly opening and closing under gravity and radial forces. To diagnose rotor systems with breathing slant cracks, the nonlinear output frequency response functions (NOFRFs) method is introduced. Firstly, a dynamic model of rotor systems with breathing slant cracks is established, and the system's frequency spectra are obtained by solving the model with different crack angles, depths, and positions. Secondly, the NOFRFs values at different orders are derived based on the NOFRFs theory. The simulation results display increased nonlinear characteristics with crack angle and depth. The system's nonlinear characteristics are stronger when cracks are closer to the disk. The [Formula: see text] value for the first-order is sensitive to crack angles, the [Formula: see text] value for the second-order is sensitive to crack depths, and the [Formula: see text] value for the fourth-order is sensitive to crack positions. As a result, the NOFRFs response at different orders can detect variations in angles, depths, and positions of the breathing slant crack. Finally, experiments are conducted on a rotor system with breathing slant cracks, and the results match those of the simulation, indicating that the NOFRFs method is feasible for identifying breathing slant cracks.

Multi-fault classification of rotor systems based on phase feature of axis trajectory in noisy environments

As it is difficult to distinguish multiple rotor faults with similar dynamic phenomena in noisy environments, a multi-fault classification method is proposed by combining the extracted trajectory phase feature, a parameter-optimized variational mode decomposition (VMD) method and a light gradient boosting machine (LightGBM) model. The trajectory phase feature is extracted from an axis trajectory by fusing the frequency, amplitude, and phase information related to rotor motion and can comprehensively describe the dynamic characteristics induced by different rotor faults. First, the vibration displacement signals in two orthogonal directions are collected to construct the axis trajectories with 12 rotor states including healthy, unbalance, misalignment, single crack, multiple cracks, and a mixture of them. Second, the trajectory phase feature is extracted from the vectorized axis trajectories, and the frequency spectra of trajectory phase angles under different rotor faults are analyzed through Fourier transform. Finally, a parameter-optimized VMD method combined with a LightGBM model is applied to classify multiple faults of rotor systems in different noisy environments based on the extracted trajectory phase feature. The 12 rotor states can be classified into nine categories based on the harmonic information of 1X–7X components (X is the rotating frequency of a rotor system) and other components with smaller amplitudes in the frequency spectra of trajectory phase angles. The average classification accuracy of the 12 rotor states exceeds 93.0%, and the recognition rate for each kind of fault is greater than 77.5% in noisy environments. The simulated and experimental results demonstrate the effectiveness and adaptability of the proposed multi-fault classification method. This work can provide a reference for the condition monitoring and fault diagnosis of rotor systems in engineering.

Multi–Output Classification Based on Convolutional Neural Network Model for Untrained Compound Fault Diagnosis of Rotor Systems with Non–Contact Sensors

Fault diagnosis is important in rotor systems because severe damage can occur during the operation of systems under harsh conditions. The advancements in machine learning and deep learning have led to enhanced performance of classification. Two important elements of fault diagnosis using machine learning are data preprocessing and model structure. Multi-class classification is used to classify faults into different single types, whereas multi-label classification classifies faults into compound types. It is valuable to focus on the capability of detecting compound faults because multiple faults can exist simultaneously. Diagnosis of untrained compound faults is also a merit. In this study, input data were first preprocessed with short-time Fourier transform. Then, a model was built for classification of the state of the system based on multi-output classification. Finally, the proposed model was evaluated based on its performance and robustness for classification of compound faults. This study proposes an effective model based on multi-output classification, which can be trained using only single fault data for the classification of compound faults and confirms the robustness of the model to changes in unbalance.

Research of energy characteristics and fault position detection for cracked rotor system

Early crack faults will introduce subtle local changes in the whole rotor system, which may bring difficulties to the fault detection process due to external disturbing factors. Meanwhile, judging the damaged position of rotor systems might be tough only through displacement or velocity. To overcome these issues, the harmonic balance-energy power flow analysis (HB-EPFA) is presented to investigate the rotor system with a transverse crack. Besides, a novel indicator (Time-averaged power flow) is proposed to evaluate the crack faults. For the energy characteristic analysis, the cracked rotor appears a special amplitude-jumping phenomenon, even in the case of shallow crack depth. The influence of crack depth on power flow values under different rotating speeds is obtained. Furthermore, the existence of cracks will lead to the rotation shaft presenting an abrupt energy-changing zone, which can be used to detect crack position. Relevant experiments are applied to validate the proposed detection method, and the experimental results agree with the theoretical analysis. The conclusions achieved in this paper can provide a reference for fault diagnosis of rotor systems in engineering practice.

Novel energy identification method for shallow cracked rotor system

Many factors like period stress or fatigue may lead to cracks in the rotating shaft which can cause economic losses and accidental risk. Early crack faults will introduce very slight local changes in the whole rotor system. And the monitoring data on rotor systems are disturbed by multiple factors. These problems may make subtle fault information be ignored, resulting in the collection of a possible rotor fault becoming tougher. To overcome such issues, novel energy methods including the vibration energy analysis and the 3D energy model representation are presented to investigate the rotor system with transverse crack. For the rotor system with a shallow crack, the energy response analysis shows the existence of shallow cracks mainly affects the peak response values. Meanwhile, the 3D energy model is used to visualize the fault characteristics. The results show that even shallow cracks can cause special phenomena in the 3D energy model, which can promote the identification of crack faults more accurately. The influence of parameters on rotor vibration energy is studied and the corresponding results are obtained. To validate the theoretical analysis results, relevant experiments are applied. The results show that the experimental results agree with the theoretical analysis. The conclusions achieved in this paper can provide a reference for fault diagnosis of rotor systems in engineering practice.

A novel diagnosis indicator for rub-impact of rotor system via energy method

Rub-impact between rotor and stator is a common mechanical fault for rotating machinery, which will bring risks into the normal operation. Detecting the severity of the rub-impact fault accurately is helpful to prevent serious mechanical accidents. However, traditional methods based on the displacements or spectrum analysis may occur some differences toughly distinguished with the naked eyes, and eventually cause inaccurate judgment in some cases. To overcome such shortcomings, this paper proposes a novel diagnosis indicator for rotor systems with rub-impact fault. The dynamic model of the rotor system is established by the finite element method. Based on the vibration power flow theory, the novel indicator is developed by considering the force, velocity, and phase information in a time interval (Time-averaged input power flow). Through theoretical analysis of the rub-impact faults, the energy responses and the law between input power and rub-impact of the rotor system are obtained. Meanwhile, the severity detection of faults by using the proposed indicator has been achieved. The corresponding tests are carried out to validate the accuracy of the theoretical results. The experimental results reveal the proposed indicator can help judge the different severity of rub-impact faults, which means the lower time-averaged input power flow indicates a serious fault. To evaluate the application effect of the proposed indicator in engineering, the rub-impact fault of the GE-T700 power turbine rotor is investigated through theoretical analysis. And the diagnosis results are consistent with the above consequences. The conclusions achieved in this paper can provide a reference for fault diagnosis of rotor systems in engineering practice.

Research on rotor system fault diagnosis method based on vibration signal feature vector transfer learning

Aiming at the common fault diagnosis problems of rotors in industrial applications. A rotor system fault diagnosis method based on vibration signal feature vector transfer learning is proposed. First, Statistical methods and wavelet packet decomposition are used for vibration signal feature extraction. Then, the ReliefF algorithm is used to evaluate the fault features and screen out the sensitive fault features set. Next, the training data and real time test data are mapped to the kernel Hilbert space using the transfer component analysis method. Finally, the weighted k-nearest neighbor method is used as the fault feature classifier for fault pattern recognition. Model training and validation using typical failure datasets of different equipment and different operating conditions. Compared with other related methods, the results indicate that the proposed method has better generalization and diagnostic accuracy. This research will promote the engineering application of intelligent fault diagnosis of rotor system.

Research on Improved Deep Convolutional Generative Adversarial Networks for Insufficient Samples of Gas Turbine Rotor System Fault Diagnosis

In gas turbine rotor systems, an intelligent data-driven fault diagnosis method is an important means to monitor the health status of the gas turbine, and it is necessary to obtain sufficient fault data to train the intelligent diagnosis model. In the actual operation of a gas turbine, the collected gas turbine fault data are limited, and the small and imbalanced fault samples seriously affect the accuracy of the fault diagnosis method. Focusing on the imbalance of gas turbine fault data, an Improved Deep Convolutional Generative Adversarial Network (Improved DCGAN) suitable for gas turbine signals is proposed here, and a structural optimization of the generator and a gradient penalty improvement in the loss function are introduced to generate effective fault data and improve the classification accuracy. The experimental results of the gas turbine test bench demonstrate that the proposed method can generate effective fault samples as a supplementary set of fault samples to balance the dataset, effectively improve the fault classification and diagnosis performance of gas turbine rotors in the case of small samples, and provide an effective method for gas turbine fault diagnosis.

Research on a Multisource Domain Improved Fault Diagnosis Method of the Rotor System

In this paper, rotor systems of the rotating machinery such as steam turbines, centrifugal compressors and flue gas turbines are selected as the research objects. At present, most of the rotor system fault diagnosis methods based on artificial intelligence algorithms are in the laboratory research stage, and there is still a gap from the actual industrial application. Therefore, the multi-source domain improved fault diagnosis (MSDIFD) method for satisfying engineering applications is proposed in this paper. Firstly, typical labeled data are selected to construct a multi-source domain training feature space. Then, commonality fault features are extracted and screened by the improved adaptive variational mode decomposition (IAVMD), and the feature reconstruction signal is automatically output. Next, the reinforced semi-supervised transfer component analysis (RSSTCA) method based on enhanced kernel function is employed to narrow the disparity between feature vectors of cross domain data. Finally, typical failure case data and real-time monitoring data are used as the training data and test data of the model, respectively, and an ensemble fault recognition classifier is constructed to achieve failure mode identification of the rotor system. Using 40 groups of typical fault engineering cases under different equipment and different operating conditions, the proposed rotor fault identification method has been verified and compared with five published fault identification methods. The results indicate that the proposed method possesses more excellent fault diagnosis accuracy and domain generalization performance, and the MSDIFD method has good application and promotion value for solving cross equipment, cross working condition, and cross domain diagnostic tasks.

Multi-sensor heterogeneous data fusion method for rotor system diagnosis based on multi-mode residual network and discriminant correlation analysis

Deep learning algorithms have become a research hotpot in the field of fault diagnosis due to their powerful feature adaptive extraction capabilities. However, the monitoring data used as the input of deep learning typically includes only single-sensor data (e.g. vibration signals), not the multi-sensor unstructured data (e.g. infrared images) that can provide fault information from different angles, resulting in low diagnostic accuracy and weak generalization ability of the built model. To apply multi-sensor heterogeneous monitoring data fully, a novel fusion diagnosis method based on multi-mode residual network (M-ResNet) and discriminant correlation analysis (DCA) is proposed in this paper. Firstly, M-ResNet composed of one-dimensional ResNet (1D-ResNet) and two-dimensional ResNet (2D-ResNet) is constructed to extract richer and more comprehensive fault features. 1D-ResNet and 2D-ResNet are used to process structured vibration signals and unstructured infrared images respectively, so as to obtain more comprehensive fault information. Secondly, DCA is used to fuse the vibration signal features and infrared image features extracted by M-ResNet to maximize the intra-class correlation and eliminate inter-class correlation of features, thereby improving the accuracy of fault diagnosis. Finally, the fusion features are input into the Softmax classifier to achieve fault classification. The effectiveness of the proposed method is verified by experiments on the rotor system, where it achieves a remarkable classification rate of 99.79%. Compared with the similar methods, the proposed method exhibits outstanding performance, indicating the feasibility of using multi-sensor heterogeneous data for rotor system fault diagnosis.

Dynamic Characteristics of Rotor System with a Slant Crack Based on Fractional Damping

The traditional modeling method of rotor system with a slant crack considers only integer-order calculus. However, the model of rotor system based on integer-order calculus can merely describe local characteristics, not historical dependent process. The occur of fractional order calculus just makes up for the deficiency in integer-order calculus. Therefore, a new dynamic model with a slant crack based on fractional damping is proposed. Here, the stiffness of rotor system with a slant crack is solved by zero stress intensity factor method. The proposed model is simulated by Runge-Kutta method and continued fraction Euler method. The influence of the fractional order, rotating speed, and crack depth on the dynamic characteristics of rotor system is discussed. The simulation results show that the amplitude of torsional excitation frequency increases significantly with the increase of the fractional order. With the increase of the rotating speed, the amplitude of first harmonic component becomes gradually larger, the amplitude of the second harmonic becomes smaller, while the amplitude of the other frequency components is almost invariant. The shaft orbit changes gradually from an internal 8-type shape to an ellipse-type shape without overlapping. With the increase of the slant crack depth, the amplitude of the transverse response frequency in the rotor system with a slant crack increases, and the amplitude in the second harmonic component also increases significantly. In addition, the torsional excitation frequency and other coupling frequency components also occur. The proposed model is further verified by the experiment. The valuable conclusion can provide an important guideline for the fault diagnosis of rotor system with a slant crack.

Research Progress of Rotating Machinery Fault Diagnosis Based on Deep Learning

In modern production, the precision and the importance of rotating machinery is higher and higher in the direction of large-scale, high speed and automation development, so that the traditional fault diagnosis methods are insufficient to deal with massive, multi-source and high-dimensional data, cannot meet the requirements of security and reliability. Therefore, several typical deep learning models are briefly introduced at first and the application of deep learning in fault diagnosis of rotor system, gear box and rolling bearing in recent years is studied and analyzed based on its strong feature extraction ability and advantages of clustering analysis. Finally, the advantages and disadvantages of deep learning model are summarized and the fault diagnosis methods of rotating machinery are summarized and prospected based on engineering practice.

Direct Connection-Based Convolutional Neural Network (DC-CNN) for Fault Diagnosis of Rotor Systems

Fault diagnosis of rotor systems is important to prevent unexpected failures. Recently, deep learning (DL) methods, such as a convolutional neural network (CNN), have been utilized in many research areas, including fault diagnosis. DL has gained significant attention thanks to its ability to efficiently learn proper features from input data. It is possible to learn enriched hierarchical features by making the DL architectures deeper; therefore, many studies have been conducted to stack the neural networks, which are the basic building blocks of DL, deeper. However, it becomes difficult to comprehensively train neural network architectures as they become deeper, due to problems in the flow of gradient information during the training phase. In this paper, a direct connection based CNN (DC-CNN) method is proposed to significantly improve training efficiency and diagnosis performance. DC-CNN connects feature maps of different layers within a CNN to improve the gradient information flow over the layers. These additional connections, however, can increase the number of trainable parameters within the network. To prevent problems that might be caused by an increased number of parameters, dimension reduction modules are also developed. Moreover, to consider the anisotropic characteristics inherent in rotor systems, the vibration images containing both spatial and temporal information are generated and utilized. The effectiveness of DC-CNN is validated using experimental data from a rotor testbed. The experimental results indicate that the proposed method outperforms other conventional approaches with a smaller number of parameters. Also, visualizations of the learned features indicate that the proposed method can learn much more effective and significant features. Furthermore, the proposed method outperforms other approaches under conditions of insufficient or noisy data.

Weighted contribution rate of nonlinear output frequency response functions and its application to rotor system fault diagnosis

Rotor cracking is a common fault in rotating machinery, that can often be detected based on the vibrations of such machinery. Therefore, many vibration signal based techniques have been developed for rotor fault detection. However, signal based fault diagnosis is often affected by noise and cannot be used to fully quantify the operating conditions of rotors, which are often more relevant to rotor structural characteristics compared to vibration behaviours. Nonlinear output frequency response functions (NOFRFs) represent a nonlinear system frequency analysis approach that was proposed to address challenges associated with applying signal based fault detection. NOFRFs have a wide range of applications in industry, including rotor fault diagnosis. In this study, a novel NOFRFs based criterion called the weighted contribution rate of NOFRFs is proposed to enhance the capability of the NOFRFs based rotor crack detection and quantification. The proposed criterion can amplify the impact of rotor characteristics that are sensitive to rotor cracks, which considerably improves the crack diagnosis performance. The effectiveness and advantages of the proposed rotor damage detection method are verified both experimentally and through simulations, demonstrating its potential applications in the early stages of rotor crack diagnosis.

A high-speed D-CART online fault diagnosis algorithm for rotor systems

Intelligent manufacturing poses a challenge for fault diagnosis of rotor systems to meet the three tasks: whether exists faults, faults location and quantitative diagnosis. Traditional methods hardly meet all the three tasks in online fault diagnosis. This paper proposes a modified classification and regression tree (CART) algorithm named D-CART algorithm to provide much faster fault classification by reducing the iteration times in computation while still ensuring accuracy. Experiments are carried on to achieve a comprehensive online fault diagnosis for rotor systems such as faults location, faults types and quantitative analysis of unbalanced mass in this paper. In comparison with the other 4 novel CART-based algorithms, the experimental results indicate that the speed of D-CART algorithm is improved by a factor of 23.92 compared to the fastest improved algorithm (Adaboost-CART) and a model accuracy of up to 96.77%. Thus demonstrating the speed superiority of D-CART algorithm in both diagnosing locations of different faults types and determining the loading masses of unbalanced faults. The proposed method has the potential to realize high-accuracy online fault diagnosis for rotor systems.

A novel fusion diagnosis method for rotor system fault based on deep learning and multi-sourced heterogeneous monitoring data

Deep learning-based fault diagnosis has been acclaimed for its superiority in adaptively mining salient features. The monitoring data used as the input of deep learning typically includes only structured data (e.g. vibration signals, voltage signals, and acoustic emission signals), not unstructured data (e.g. infrared images), which provides another perspective on the mechanical health condition. To apply multi-sourced heterogeneous monitoring data fully, this paper presents a novel fusion diagnosis method integrating structured and unstructured data for rotor system faults. A novel multi-mode convolutional neural network (M-CNN) is first proposed to automatically learn fault-sensitive features from raw multisensory data composed of vibration signals and infrared images. M-CNN equipped with adjustable filter banks can identify data types and adaptively adopt the appropriate convolution mode. Then, t-distributed stochastic neighbor embedding (t-SNE) is introduced to fuse the deep features to further improve the quality of the learned features. Finally, the fused features are employed to conduct fault classification tasks. The effectiveness of the scheme is verified by fault diagnosis experiments in a rotor system, where it achieves a remarkable classification rate of 98.97%. Compared with similar methods, the proposed method exhibits outstanding performance, indicating the feasibility of using multi-sourced heterogeneous data for rotor system fault-diagnosis.

Effects of misalignment on the nonlinear dynamics of a two-shaft rotor-bearing-gear coupling system with rub-impact fault

In rotor-bearing system, the misalignment can lead to secondary faults, such as the rub-impact fault. How the development of misalignment could affect the rub-impact force and other dynamic responses is important for the vibration control and fault diagnosis of rotor system. In this paper, a mathematical model of a two-shaft rotor-bearing- gear coupling system is established. The model is validated through the misaligned force of gear coupling, the supporting force of the lubricated ball bearing and the whole rotor response. To overcome the limit of traditional approaches and further dig out fault characteristics, the time-frequency method is introduced to analyze the dynamic response from both the time and frequency domains points of view. It is found the misalignment effect on rotor dynamic responses is mainly focused in high rotating speed range. The development of misalignment has an obvious adverse effect on the rotor stability. Some intermittent components in low frequency range due to the occurrence and development of misalignment can be found affecting the rotor stability at low speed range, and the high frequency rub-impact components can be found responsible for the unstable state of rotor.