Gear Fault Diagnosis Research Articles

A spectral kurtosis based blind deconvolution approach for spur gear fault diagnosis

Unanticipated background noises often convolute fault information in the gearboxes’ vibration response. The Blind Deconvolution strategy has been extensively applied for fault-impulse enhancement to aid gear fault detection. The existing deconvolution strategies involve designing an optimum filter applied in the time domain. Gear tooth wear leads to the excitation of Gear Mesh Frequency harmonics. Hence, spectral analysis is typically used for gearbox fault detection. As such, feature enhancement in the order domain is more practical than existing blind deconvolution approaches. This study proposes a Spectral Kurtosis-based blind deconvolution strategy with filtering done in the order domain, to aid gear fault detection. Experimental analyses show 109.76% and 64.48% better performance for constant and real-world speed operation, respectively, for the proposed method to aid spectral analysis-based fault detection.

RETRACTED ARTICLE: Research on Feature Extraction and Diagnosis Method of Gearbox Vibration Signal Based on VMD and ResNeXt

Aiming at the nonlinear and non-stationarity of gearbox fault signals and the confusion among different fault categories, a gear fault diagnosis method combining variational mode decomposition, reconstruction and ResNeXt is proposed in this paper. In this paper, parameter K of VMD is determined according to the changing trend of sample entropy (SE), K modal components are obtained after decomposition, and the effective modal components are extracted and reconstructed according to Pearson autocorrelation coefficient, so as to remove redundant information from the original signal. Then the reconstructed signal is transformed by time–frequency and output two-dimensional time–frequency information, which is used as the input of ResNeXt model to extract the characteristics of different faults. Moreover, the model performance is improved by changing the learning rate decline rate, and a fault diagnosis model with high precision and good stability is established.

Mechanism analysis for GDTE-based fault diagnosis of planetary gears

Planetary gear transmission systems are widely utilized in production and daily life equipment, and their fault diagnosis is crucial. The most common tool in this field is the vibration monitoring. In this study, a different tool based on global dynamic transmission error (GDTE) is investigated from a mechanism analysis perspective. The aim is to explore the dynamic responses of planetary gears with different pitting degrees, establish the mapping relationships between GDTE and gear damages, and reveal the mechanism of GDTE-based fault diagnosis. To ensure the accuracy of dynamics model, a novel pitting modeling method based on matrix equations is proposed, which makes the growth process of pitting more physically grounded and the model for irregular pitting on tooth surfaces more practical by considering the termination during random expansion of pitting. Meanwhile, the matrix equation-based pitting model and potential energy method-based time-varying meshing stiffness calculation can be perfectly matched to ensure the precision of subsequent dynamic response analysis. More practical pitting model and accuracy stiffness ensure that the planetary gear dynamics model outputs more precise dynamic responses. Simple time and frequency domain analysis performed on GDTE show that GDTE contains rich information about gear health status. The mapping relationships between GDTE and gear pitting damages are revealed and validated by multi-body dynamics methods. GDTE provides a promising tool for gear condition monitoring and fault diagnosis.

A New Hybrid LSTM-GRU Model for Fault Diagnosis of Polymer Gears Using Vibration Signals

A New Hybrid LSTM-GRU Model for Fault Diagnosis of Polymer Gears Using Vibration Signals

A new framework for intelligent fault diagnosis of spiral bevel gears with unbalanced data

A new framework for intelligent fault diagnosis of spiral bevel gears with unbalanced data

A hierarchical adversarial multi-target domain adaptation for gear fault diagnosis under variable working condition based on raw acoustic signal

Acoustic-based diagnosis (ABD) relied on air-coupled measurement is received great attention in recent years due to its ability in overcoming the limitation of vibration-based diagnosis on contact measurement. However, most of the ABD approaches are only focus on a stable working condition for analysis and research. Main challenge of ABD task is the unstable working condition including variable load and speed in real-industrial scenarios, which involve variation in amplitude and phase of acoustic signal to cause domain shift problem for fault pattern detection. In this condition, to perform ABD task for meeting the requirement of scalability in dealing with multiple targets under continuously variable working condition, a novel hierarchical adversarial multiple-target domains adaptation (HAMT-DA) learning framework is proposed in this paper. Following the naturally solution idea, a target-compress adversarial adaptation (TCAA) mechanism is developed in the first-level of framework to compress multiple-target domains by minimizing the feature distribution discrepancy over all domains, and narrow the divergence between source and target domains concurrently. Then, domain invariant feature refining (DIFR) strategy is designed to take responsibility for second-level domain adaptation in the intermediate of framework by refining domain invariant attribute and encoding the domain invariant feature into high-level semantic representation space. Subsequently, a class-separate adversarial adaptation (CSAA) method is explored in the roof of the hierarchical framework for the exploration of fault-discriminative property by forming third-level domain adaptation. Thus, the entire HAMT-DA learning framework can be obtained for single source to multiple-target (SSMT) cross-domain ABD task. The experiment result in variable working conditions indicate that the proposed method has more than 94% average diagnosis performance for gear fault patterns in five cross-domain validation tasks and achieve the highest recognition accuracy among four verifications, which is about 7% average improvement than that of the optimal comparison method. It verifies the superiority of our method on robustness and generalization for acoustic-based gear fault diagnosis under SSMT setting.

Fault Diagnosis of Wind Turbine Planetary Gear Based on a Digital Twin

Aiming at the problems of the traditional planetary gear fault diagnosis method of wind turbines, such as the poor timeliness of data transmission, weak visualization effect of state monitoring, and untimely feedback of fault information, this paper proposes a planetary gear fault diagnosis method for wind turbines based on a digital twin. The method was used to build the digital twin model of wind turbines and analyze the wind turbines’ operating state utilizing virtual and real data. Empirical mode decomposition (EMD) was used, and an atom search optimization–support vector machine (ASO-SVM) model was established for planetary gear fault diagnosis. The digital twin model diagnoses faults and constantly revises the model based on the diagnostic results. The digital twin fault diagnosis system was implemented in the Unity3D platform. The experimental results demonstrate the feasibility of the proposed early-warning system for the real-time diagnosis of planetary gear faults in wind turbines.

Research on surface defect detection and fault diagnosis of mechanical gear based on R‐CNN

AbstractGears are the basic units in modern power systems. The detection and diagnosis of surface defects and faults in gears are conducive to improving product quality, ensuring the safety of mechanical equipment, and reducing maintenance costs. However, the accuracy of manual and traditional automated target detection algorithms is not satisfactory. Therefore, this research uses the R‐CNN algorithm for gear detection, improves its non‐maximum suppression algorithm and multi‐task loss function, and obtains the improved Faster R‐CNN algorithm. The test was carried out on the built data set. The actual measurement shows that the recall rate of the improved Faster R‐CNN is up to 0.951 and the lowest is 0.816. Its AP value is as low as 0.677 and as high as 0.858, and the mAP value is 0.843. Horizontal comparison, the comparison results show that the mAP of Faster R‐CNN is 0.80 1, second only to R‐CNN among the tested algorithms, and 8.83% higher than the original Faster R‐CNN. Under the condition of AP@0.5:0.95, among all the tested algorithms, its AR index is the highest at 54.3, and the detection speed is 18 FPS/s. Although the detection speed has decreased, the detection and recognition accuracy has been significantly improved, which provides feasibility for the R‐CNN series of algorithms new optimization directions. The research provides a better automatic detection method for product quality inspection in gear manufacturing industry.

Multivariate local fluctuation mode decomposition and its application to gear fault diagnosis

In this paper, we propose a novel method, called multivariate local fluctuation mode decomposition (MLFMD), to improve the accuracy and efficiency of fault diagnosis using multiple channels signals. Compared with multivariate empirical mode decomposition (MEMD), MLFMD uses second-order differentiable local extreme point localization (SDLEPL) to mine the local hidden information and an adaptive non-uniform projection (ANP) technique to improve the decomposition accuracy. In addition, the MLFMD method employs multivariate periodic mean to extract the mean curves, which improves the decomposition efficiency. Compared with traditional MEMD, our proposed MLFMD algorithm has higher decomposition accuracy and efficiency. Furthermore, a new fault diagnosis method based on MLFMD is proposed, which can efficiently fuse data from each channel. The efficacy of the proposed method is validated with both simulated and real-world signals, and the results demonstrate the superiority of the MLFMD.

Influence of clearance and structural coupling parameters on shimmy stability of landing gear

AbstractThere are many factors causing the shimmy of the aircraft landing gear and structural clearance of landing gear is a typical factor. Some aircraft in service or operation did not shimmy before, but suddenly appeared after a period of use. To solve the problem of clearance shimmy during the service of a certain aircraft, we established a dynamic model of rotating gear with clearance based on the flexible multi-body dynamics model of landing gear and L-N contact theory. We defined different types of clearance and established a mechanical model of aircraft pendulum vibration considering the clearance of landing gear structure for dynamic simulation, and studied the effects of different clearance types, clearance size of motion pair and different clearance positions on the stability of pendulum. The results show that the axial clearance has little effect on the shimmy performance of landing gear; the radial clearance has a certain effect on the shimmy performance of medium speed running, which slightly improves the shimmy damping required by medium speed running; the rotational clearance affects the shimmy performance of the nose landing gear by affecting the force transmission of structural components. The required shimmy damping coefficient increases at low speed and decreases at high speed. The main reason for the return clearance is that during the return, the shimmy damper does not work, which leads to the decrease of the shimmy damping performance and the increase of the required shimmy damping coefficient in the whole speed range. Meanwhile, the structural clearance will increase the shimmy frequency of the nose landing gear. By analysing the yaw angle of the nose landing gear and the time domain curve of the yaw angle of the yaw damper, we can determine which structure of the landing gear and which type of clearance is the cause of the yaw. Finally, the coupling effect caused by the main structural parameters of the landing gear in “gap shimmy” was analysed according to different mechanical stability distances and strut stiffness of the nose landing gear, providing reference for aircraft anti-shimmy design, nose landing gear fault diagnosis and nose landing gear maintenance support.

Novel tacholess order tracking method for gear fault diagnosis under speed-up and speed-down conditions

Order analysis is a powerful technique for analysing the vibration signals of rotating machinery under a known variable rotational speed. It requires the installation of speed-measuring devices; however, these devices cannot be installed in most machines due to design or cost reasons. In this study, a new method based on a time delay and resampling technique is introduced to estimate the instantaneous frequency (IF) of the vibration signal of a gear system. Order analysis techniques are used to extract the gear fault features. The performance of the proposed method is validated using simulated data from a gear system under speed-up and speed-down conditions.

Research on gear fault diagnosis method based on SSA–VME–MOMEDA

As a common mechanical part, gear is easy to be damaged because of its complex working environment, which can impact the running of the whole transmission device. Thus, it is very important to evaluate the health of gears in time. A gear fault diagnosis method based on multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) and variational modal extraction (VME) is proposed to solve the problem that the periodic fault features of gears are difficult to be completely extracted from signals. Meanwhile, sparrow search algorithm (SSA) is introduced to optimize the initial parameters of VME and MOMEDA. First, SSA serves to hunt for the best α of VME, VME serves to obtain the signal near the gear fault frequency, and then SSA serves to hunt for the best L and T values of MOMEDA, and MOMEDA serves to strengthen the gear impact features. Finally, the gear impact features are extracted by envelope spectrum. Simulation and experiment show that this method can extract gear fault components from noise effectively with good results.

Theoretical Investigation of Mesh Relationship and Mesh Stiffness of Internal Spur Gears with Tooth Wear

The internal gear is part of the planetary and epicyclic gear pairs in the transmission system of the helicopter. Gear tooth wear is one of the most usual gear failures. This paper establishes an analytical model to evaluate the influence of tooth wear on the mesh relationship. A new mesh relationship can be derived for internal spur gears with tooth wear by the proposed analytical model. Consequently, using the new mesh relationship, the two most important meshing excitations, mesh stiffness and unloaded static transmission error (USTE), are quantitatively evaluated for the internal gear with tooth wear. The results indicate that tooth wear mainly affects the meshing ranges of single-tooth and double-teeth in mesh stiffness, rather than its amplitude. Additionally, the amplitudes of USTE increase with the increasing wear depth. Finally, this study can offer a foundation for the dynamic modeling and fault diagnosis of internal spur gears with wear faults.

Multivariate complex modulation model decomposition and its application to gear fault diagnosis

The single-channel vibration signal of gears contains limited information, and it is easily affected by the transmission path. Therefore, multi-channel signals should be used for fault diagnosis because multi-channel gear signals usually contain richer and more comprehensive information about the equipment status. But the existing single-channel signal processing methods are not applicable to multi-channel signals, and each of the existing multi-channel signal processing methods has its own limitations. Therefore, this study proposes a new multi-channel signal processing method called multivariate complex modulation model decomposition (MCMMD), by which multi-channel signals can be decomposed accurately and adaptively at the same time. The core of the method is to iteratively update the model parameters by combining all channel signals to acquire the pattern alignment property. The decomposition performance is analyzed first. Then MCMMD is applied to simulation and experimental multi-channel gear fault signals. For comparison, ensemble empirical mode decomposition (EEMD), multivariate empirical mode decomposition (MEMD), multivariate variational mode decomposition (MVMD), multivariate local characteristic-scale decomposition (MLCD), and completely adaptive projection MLCD (CAPMLCD) are presented as well. The results show that the decomposition accuracy and robustness of MCMMD are better than those of the other methods compared. Therefore, MCMMD is an accurate and effective multi-channel signal processing method.

Fault Diagnosis of Bearings and Gears Based on LiteNet With Feature Aggregation

Significant progress has been made in the current fault diagnosis algorithms. However, they do not consider computational resources and require expensive equipment to complete the training of the models. To immediately complete model training and obtain higher accuracy rates using cheaper equipment, reduce the equipment cost in the industry, and build a bridge for industrial fault diagnosis with neural networks, this paper proposes a convolutional neural network-based architecture that uses a small number of computational resources with high accuracy. Simultaneously, a loss function is proposed that can further improve the accuracy of the network model without consuming too many computational resources. According to experimental comparisons, the proposed technique has clear advantages in terms of accuracy, computational resources, training time, and stability.

Optimization Application of Deep Belief Network in Gear Fault Diagnosis

Deep belief networks (DBNs) in the process of the application of the gear vibration signal fault diagnosis, vector network depth, the number of neurons in hidden layer, set the initial parameters, such as there is a certain blindness, and for different data sets, the influence of initial parameters is different also, in order to get ideal fault recognition rate, the initial parameters have to be repeatedly debugging, This process is not only time-consuming and laborious, but also disadvantageous to its universal application in fault diagnosis. To solve this problem, this paper mainly optimizes the number of hidden layer neurons and learning rate of DBNs. The diagnosis example shows that after optimization, the initial parameter setting is more accurate and efficient, and the fault identification rate is significantly improved.

Tensor Denoising Assisted Time-Reassigned Synchrosqueezing Wavelet Transform for Gear Fault Diagnosis

The gear fault signal is characterized by strong and/or weak impulsive features and is often accompanied by strong background noise, which makes the gear fault feature extraction more difficult. Hence, this paper proposes a new time-frequency analysis method called the tensor denoising (TD) assisted time-reassigned synchrosqueezing wavelet transform (TD-TSWT). First, to improve the accuracy of subsequent time-frequency analysis, a TD method based on high-order singular value decomposition is proposed as a preprocessing technique according to the cyclostationary characteristics of gear faults and the Hankel matrix. Meanwhile, combined with the advantages of sample entropy calculation, the concept of using sample entropy to determine the reasonable singular order is proposed. Second, to propose TSWT for revealing gear fault features. TSWT by introducing continuous wavelet transform to obtain the basis function which is more similar to gear fault impulses. Moreover, according to the properties of the gear fault signal, the group delay estimation operator in the frequency domain is designed for TSWT, which is more suitable for the gear fault feature extraction. Finally, the results of simulations and engineering cases show that the method provides a useful tool for the diagnosis of gear faults.

Small Sample Gear Fault Diagnosis Method Based on Transfer Learning

Small Sample Gear Fault Diagnosis Method Based on Transfer Learning

An enhanced minimum entropy deconvolution with adaptive filter parameters for gear fault diagnosis

Blind deconvolution is one of the most effective methods in gear fault diagnosis. However, the deficiency of the deconvolution criterion, dependence on prior knowledge, and requirement of appropriate parameters limit the application of the conventional methods to a certain extent. In this paper, an enhanced minimum entropy deconvolution with adaptive filter parameters (EMED-AFP) is proposed. Within EMED-AFP, a nonlinear transformation is developed and incorporated into the iterative solution process of filter coefficients. By incorporating it, fault impulses are enhanced, making the filter estimation more accurate and effective. Moreover, the EMED-AFP is configured with a parameter-adaptive strategy designed to find the optimal filter parameters. In such a context, the method solves the significant issue that conventional methods specify filter parameters empirically. Both simulation and case studies verify the effectiveness of the method for gear fault diagnosis. Meanwhile, compared with some popular methods, EMED-AFP shows superiority in recovering gear fault impulse trains.

Correction: Highly Accurate Gear Fault Diagnosis Based on Support Vector Machine

Correction: Highly Accurate Gear Fault Diagnosis Based on Support Vector Machine