Fault Diagnosis Of Rotor-bearing System Research Articles

Fault Diagnosis of Imbalance and Misalignment in Rotor-Bearing Systems Using Deep Learning

Abstract Rotor-bearing systems are important components of rotating machinery and transmission systems, and imbalance and misalignment are inevitable in such systems. At present, the main challenges faced by state-of-the-art fault diagnosis methods involve the extraction of fault features under strong background noise and the classification of different fault modes. In this paper, a fault diagnosis method based on an improved deep residual shrinkage network (IDRSN) is proposed with the aim of achieving end-to-end fault diagnosis of a rotor-bearing system. First, a method called wavelet threshold denoising and variational mode decomposition (WTD-VMD) is proposed, which can process original noisy signals into intrinsic mode functions (IMFs) with a salient feature. These one-dimensional IMFs are then transformed into two-dimensional images using a Gramian angular field (GAF) to give datasets for the deep residual shrinkage network (DRSN), which can achieve high levels of accuracy under strong background noise. Finally, a comprehensive test platform for a rotor-bearing system is built to verify the effectiveness of the proposed method in the field. The true test accuracy of the model at a 95% confidence interval is found to range from 84.09% to 86.51%. The proposed model exhibits good robustness when dealing with noisy samples and gives the best classification results for fault diagnosis under misalignment, with a test accuracy of 100%. It also achieves a higher testing accuracy compared to fault diagnosis methods based on convolutional neural networks and deep residual networks without improvement. In summary, IDRSN has significant value for deep learning engineering applications involving the fault diagnosis of rotor-bearing systems.

Dual-Threshold Attention-Guided GAN and Limited Infrared Thermal Images for Rotating Machinery Fault Diagnosis Under Speed Fluctuation

End-to-end intelligent diagnosis of rotating machinery under speed fluctuation and limited samples is challenging in industrial practice. The existing limited samples methods usually focus on the data distribution or learning strategy with particularity. Generative adversarial network (GAN) provides a data generation solution with portability in fault diagnosis with limited samples. However, GAN has problems with gradient vanishing, weak extraction of global features, and redundant training. This article proposes a dual-threshold attention-guided GAN (DTAGAN) to generate high-quality infrared thermal (IRT) images to assist fault diagnosis. First, Wasserstein distance and gradient penalty are combined to design loss function to avoid gradient vanishing. Second, attention-guided GAN is constructed to extract global thermal-correlation features of IRT images. Finally, dual-threshold training mechanism is developed to improve the generation quality and training efficiency. The comparative experiments show that DTAGAN is superior to comparison methods in fault diagnosis of rotor-bearing system under speed fluctuation and limited samples.

Fault Diagnosis of Rotor-bearing System under Time-varying Speeds by Using Dual-threshold Attention-embedded GAN and Small Samples

Fault Diagnosis of Rotor-bearing System under Time-varying Speeds by Using Dual-threshold Attention-embedded GAN and Small Samples

IRTCog: Fault Diagnosis of Rotor-Bearing System Based on Modified Transfer Model With Variable Visual Angle Thermal Images

IRTCog: Fault Diagnosis of Rotor-Bearing System Based on Modified Transfer Model With Variable Visual Angle Thermal Images

Multiscale Deep Graph Convolutional Networks for Intelligent Fault Diagnosis of Rotor-Bearing System Under Fluctuating Working Conditions

The rotor-bearing system is widely used in various high-end electro-hydraulic equipment, which provides specific support, rotation, and other integral functions. However, the fluctuating working conditions of the rotor-bearing system will cause more significant disordered fluctuations in the measured signals. This article proposes a new algorithm called multiscale deep graph convolutional networks (MS-DGCNs) to alleviate this problem. The designed MS-DGCNs algorithm combines a new multiscale intra-class fine coarse-grained processing and multiscale graph convolution kernels. Accordingly, an intelligent fault diagnosis method based on MS-DGCNs for the rotor-bearing system under fluctuating conditions is designed to learn more feature representations and accuracy. First, a sliding window is employed to divide the collected vibration signals into a series of subsignals. The multiscale signal processing is performed to obtain different degrees of the fine-coarse time series. Then, a graph convolution with the multiscale convolution kernel is designed. Finally, the soft-max classifier is combined for intelligent fault diagnosis. The experimental results of the double-span rotor-bearing system under fluctuating conditions well demonstrate that the method has the higher accuracy and generalization.

Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images

The existing intelligent fault diagnosis methods of rotor-bearing system mainly focus on vibration analysis under steady operation, which has low adaptability to new scenes. In this article, a new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using modified convolutional neural network (CNN) with transfer learning. First, infrared thermal images are collected and used to characterize the health condition of rotor-bearing system. Second, modified CNN is developed by introducing stochastic pooling and Leaky rectified linear unit to overcome the training problems in classical CNN. Finally, parameter transfer is used to enable the source modified CNN to adapt to the target domain, which solves the problem of limited available training data in the target domain. The proposed method is applied to analyze thermal images of rotor-bearing system collected under different working conditions. The results show that the proposed method outperforms other cutting edge methods in fault diagnosis of rotor-bearing system.

Modified Gaussian convolutional deep belief network and infrared thermal imaging for intelligent fault diagnosis of rotor-bearing system under time-varying speeds

The vast majority of the existing diagnostic studies using deep learning techniques for rotating machinery focus on the vibration analysis under steady rotating speed. Nevertheless, the collected vibration signals are sensitive to time-varying speeds and the vibration sensors may cause structure damage of equipment after long-term close contact. Aiming at these aforementioned problems, a modified Gaussian convolutional deep belief network driven by infrared thermal imaging is proposed to automatically diagnose different faults of rotor-bearing system under time-varying speeds. First, infrared thermal images are measured to characterize the working states of rotor-bearing system to reduce the impact of changeable speeds. Second, Gaussian units are used to construct Gaussian convolutional deep belief network to well deal with infrared thermal images. Finally, trackable learning rate is designed to modify the training algorithm to enhance the performance. The comparison results verify the feasibility of the proposed method, which outperforms the other methods.

Fault Diagnosis of a Rotor-Bearing System Under Variable Rotating Speeds Using Two-Stage Parameter Transfer and Infrared Thermal Images

Current fault diagnosis methods for rotor-bearing system are mostly based on analyzing the vibration signals collected at steady rotating speeds. In those methods, the data collected under one operating condition cannot be accurately used for diagnosis under a different condition. Moreover, in vibration monitoring, installing the necessary sensors will affect the equipment structure and hence the vibration response itself. The present paper proposes a new method based on two-stage parameter transfer and infrared thermal images for fault diagnosis of rotor-bearing system under variable rotating speeds. The method of parameter transfer enables the use of data (or parameters) acquired under one operating condition (called the source domain) to be extended for use in a different operating condition (called the target domain). First, scaled exponential linear unit (SELU) and modified stochastic gradient descent (MSGD) are used to construct an enhanced convolutional neural network (ECNN). Second, a stacked convolutional auto-encoder (CAE) trained based on unlabeled source-domain thermal images is employed to initialize a source-domain ECNN. Third, model parameters from the pre-trained source-domain ECNN are transferred to the target-domain ECNN to adapt to the characteristics of the target domain. The collected thermal images for a rotor-bearing system under variable speeds are used to test the transfer diagnosis performance of the proposed method. The experimental results demonstrate the performance improvement and the advantages of the proposed method.

An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE

Despite deep learning models can largely release the pressure of manual feature engineering in intelligent fault diagnosis of rotor-bearing systems, their performance mostly depends on enough labeled samples constructed from the vibration signals. Acquiring lots of labeled samples is often laborious, and the vibration sensors tightly fixed on the equipment may influence their structures after long time running. To address these two problems, a new framework based on small labeled infrared thermal images and enhanced convolutional neural network (ECNN) transferred from convolutional auto-encoder (CAE) is proposed. First, infrared thermal images are measured to characterize various health states of rotor-bearing system. Second, exponential linear unit (ELU) and stochastic pooling (SP) are used to construct ECNN. Then, the model parameters of a CAE pre-trained with unlabeled thermal images are transferred to initialize the ECNN. Finally, small labeled thermal images are used for training ECNN to further adjust model parameters. The collected thermal images are used to test the diagnosis performance of the proposed method. The analysis and comparison results show that the proposed method outperforms the current mainstream methods.

Distributed fault diagnosis of rotor-bearing system using dimensional analysis and experimental methods

Distributed defects in rolling element bearing arise due to the progression of small localized pits. If not monitored on time, this leads to premature or may turn into catastrophic failure of a rotor system and thus increases the cost of maintenance of machinery in industries. This research work introduced a novel method for the diagnosis of rolling element bearings to detect distributed defects using Dimensional Analysis (DA). The rolling element bearing system is modeled using DA with Buckingham’s theorem to study the vibration characteristics theoretically. Significant geometrical and response parameters are considered for modeling the rotor-bearing system. The in-house experimental test rig is designed and fabricated to study the vibration characteristics of distributed defects experimentally. Geometrical imperfections are created intentionally on the bearings surfaces using electro-discharge machining and vibration signatures generated are studied under different operating conditions. Experimental results are compared with analytical models developed using the DA. A comparison is made between distributed and localized defects and vibrations signatures from both are correlated with healthy bearings. It is noticed that there is a good correlation between theoretical and experimental results. The present study contributes as a simple and effective diagnosis of rolling element bearings for distributed defects and useful for condition monitoring of industrial machinery.

A novel identification method of Volterra series in rotor-bearing system for fault diagnosis

Volterra series is widely employed in the fault diagnosis of rotor-bearing system to prevent dangerous accidents and improve economic efficiency. The identification of the Volterra series involves the infinite-solution problems which is caused by the periodic characteristic of the excitation signal of rotor-bearing system. But this problem has not been considered in the current identification methods of the Volterra series. In this paper, a key kernels-PSO (KK-PSO) method is proposed for Volterra series identification. Instead of identifying the Volterra series directly, the key kernels of Volterra are found out to simply the Volterra model firstly. Then, the Volterra series with the simplest formation is identified by the PSO method. Next, simulation verification is utilized to verify the feasibility and effectiveness of the KK-PSO method by comparison to the least square (LS) method and traditional PSO method. Finally, experimental tests have been done to get the Volterra series of a rotor-bearing test rig in different states, and a fault diagnosis system is built with a neural network to classify different fault conditions by the kernels of the Volterra series. The analysis results indicate that the KK-PSO method performs good capability on the identification of Volterra series of rotor-bearing system, and the proposed method can further improve the accuracy of fault diagnosis.

Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis

Rolling element bearing faults are among the main causes of breakdown in rotating machines. In this paper, a rolling bearing fault model is proposed based on the dynamic load analysis of a rotor-bearing system. The rotor impact factor is taken into consideration in the rolling bearing fault signal model. The defect load on the surface of the bearing is divided into two parts, the alternate load and the determinate load. The vibration response of the proposed fault signal model is investigated and the fault signal calculating equation is derived through dynamic and kinematic analysis. Outer race and inner race fault simulations are realized in the paper. The simulation process includes consideration of several parameters, such as the gravity of the rotor-bearing system, the imbalance of the rotor, and the location of the defect on the surface. The simulation results show that different amplitude contributions of the alternate load and determinate load will cause different envelope spectrum expressions. The rotating frequency sidebands will occur in the envelope spectrum in addition to the fault characteristic frequency. This appearance of sidebands will increase the difficulty of fault recognition in intelligent fault diagnosis. The experiments given in the paper have successfully verified the proposed signal model simulation results. The test rig design of the rotor bearing system simulated several operating conditions: (1) rotor bearing only; (2) rotor bearing with loader added; (3) rotor bearing with loader and rotor disk; and (4) bearing fault simulation without rotor influence. The results of the experiments have verified that the proposed rolling bearing signal model is important to the rolling bearing fault diagnosis of rotor-bearing systems.

Dynamics analysis of a cracked dual-disk over-hung rotor-bearing system

A dynamic model of a dual-disk vertical over-hung rotor-bearing system is developed, taking into account nonlinear oil-film force. Its dynamic behaviors are investigated by numerical Runge-Kutta method. Its bifurcation and chaos characteristics are analyzed with crack fault and without crack fault. By analyzing the bifurcation plot, Poincare section plots and amplitude spectra, we found that the crack greatly influences the dynamic characteristics of the rotor-bearing system. Because of the strong effect of the nonlinear oil-film force and crack to the system, 1/2 times, 1/3 times frequency components appear in the response spectrum map. The results may bring up theoretical references for fault diagnosis of rotor-bearing systems.