Gearbox Vibration Research Articles

Data-driven modeling of staged planetary gearbox vibration signature

Modeling planetary gearboxes is an important field of research, since it helps in condition based monitoring of the system. Multiple models with different approaches were developed last decades. They showed interesting results, but they did not reflect all involved phenomena. Indeed, specifically in a complex rotating systems such as staged planetary gearboxes, those models only approximated the dynamic behavior of the investigated system. Hence, in this paper, an algorithm of modeling staged planetary gearbox vibration signature is proposed based on exclusively measured vibration signals. First, in section 2, the dynamic mode decomposition (DMD) will be introduced. Second, in section 3, the DMD algorithm will be implemented on simulated mathematical functions to prove its robustness on future state prediction. Then, in section 4, the experimental staged planetary gearbox test rig is presented. Finally, in section 5, the DMD algorithm is applied to multiple measured vibration signals with different operating conditions as given in section 4. Interesting results are conducted and limits of the approach are presented.

Dynamic modeling and analysis of wind turbine gear-bearing coupling system considering tooth root crack and slicing coupling effect

Tooth root cracks would change the meshing stiffness excitation of the gears, increasing the vibration and noise of wind turbine gearbox. Currently, there is relatively little literature that focuses on the slicing coupling effect of cracked gears, leading to incomplete accuracy in solving the time-varying mesh stiffness (TVMS) of gears under cracked conditions, making it difficult to accurately reflect the impact of root crack excitations on the dynamic behavior of wind turbine gear-bearing coupled systems. In this work, The improved analytical calculation method is proposed for the TVMS and system vibration coupling solution of the cracked gear pair, considering the slicing coupling effect. The dynamic model of the wind turbine high-speed stage gear set is developed using the lumped parameter approach, and the rolling bearing is modeled using the Hertz contact theory. Then, the excitations of the gear-bearing coupling system are developed using an improved slicing method. Lastly, the dynamic model of the wind turbine gear-bearing coupling system that considers tooth root cracks and the slicing coupling effect is established and validated. The results indicate that The TVMS modification algorithm considering the slicing coupling effect can better depict the dynamic change of the gear meshing stiffness under the crack failure. Cracks could reduce the TVMS of the gear pair, neglecting the coupling effect between the sliced gear tooth gains the potential risks of overestimating the influence of the gear crack depth on the TVMS. In addition, Gear cracks excitation may alter the dynamic contact load amplitude of the bearing rolling elements, resulting in a tendency for the load-bearing area to decrease. Moreover, When the cracked teeth are involved in meshing, The decrease in mesh stiffness will result in a larger amplitude periodic shock response to the system vibration displacement and a sideband phenomenon near the mesh frequency, neglecting the coupling effect between the sliced gear tooth or simplifying the bearing to a linear support stiffness matrix gain the potential risks of underestimating the influence of the gear crack depth on the vibration displacement of the gear-bearing coupling system.

Study of the Gearbox Meshing Coupling Vibration Law Based on Mechanical Signal and Frequency Signal

In this study, the failure of a certain type of gearbox of a high-speed locomotive group with cracks is examined, and a gearbox failure assessment method that considers the coupled vibration is established and combined with mechanical signal and frequency signal to determine the basis for judging the failure of a faulty gearbox. First, according to the mechanical model of the finite element calculation, we determined the stress weak links and then the layout response stress measurement points and acceleration measurement points. We then calculated the gearbox ratio, meshing frequency, vibration frequency, mechanical response, modal response, and other frequency characteristics using the Hilbert–Huang transform (HHT) method and the fast Fourier transform (FFT) algorithm to analyze the vibration signals generated by different speeds and wheel out-of-roundness conditions. These were used to calculate the frequency of the different vibration sources of the mechanical response on the weak areas. The frequency correlations of the different vibration sources on the mechanical response in the weak areas were then analyzed, and the vibration transmission law of the gearbox case was obtained. The fault determination criterion was then determined, and the final cause of the fault was obtained.

Fault diagnosis of wind turbine gears based on OCSSA-VMD and WOA-CNN-BiLSTM

Abstract The accuracy of wind turbine gearbox fault diagnosis will be compromised if the fault feature data is not adequately extracted during operation. To enhance fault identification efficiency and mitigate human interference in parameter setting, this paper introduces an optimized mode decomposition algorithm OCSSA-VMD, derived from variational mode decomposition (VMD) and further optimized by osprey-Cauchy-sparrow search algorithm (OCSSA). This algorithm offers two key advantages: (1) automatic optimization of parameters such as the number of modes k and penalty factor α; (2) reduction of feature dimensionality through mean impact value (MIV) algorithm based on minimum envelope entropy principle, resulting in a multi-fault feature vector set from 13 time-domain features in the intrinsic mode function (IMF) optimal component of wind turbine gearbox vibration data. Additionally, a fault diagnosis model WOA-CNN-BiLSTM is proposed based on whale optimization algorithm (WOA) and convolutional neural network-bidirectional long-short-term-memory (CNN-BiLSTM), which demonstrates improved fault classification accuracy to 98.3333% and diagnosis accuracy to 98.3853% under conditions of insufficient data when compared with other models.

Noise reduction method for wind turbine gearbox vibration signals based on CVMD-DRDSAE

Abstract Wind turbine gearbox fault feature extraction is difficult due to strong background noise. To address this issue, a noise reduction method combining comprehensive learning particle swarm optimization-variational mode decomposition (CLPSO-VMD) and deep residual denoising self-attention autoencoder (DRDSAE) is proposed. Firstly, the proposed CLPSO-VMD algorithm is used to decompose the noisy wind turbine gearbox vibration signals. Subsequently, the intrinsic mode functions highly correlated with the original signals are selected through the Spearman correlation coefficient and utilized for signal reconstruction, thereby filtering out high-frequency noise outside the fault frequency band in the frequency domain characterization. Secondly, the improved DRDSAE is utilized to learn the latent representations of data in the first-level denoised signal, further reducing the residual noise within the fault frequency band while retaining important signal features. Finally, the envelope spectrum highlights the weak feature of the wind turbine gearbox vibration signal. Experimental results demonstrate the effectiveness of the proposed method in denoising wind turbine gearbox vibration signals under strong noise.

Gearbox fault diagnosis based on RGT-MFFIN and multi-sensor fusion image generation

Abstract In gearbox fault diagnosis based on vibration and torque state data, traditional one-dimensional time-frequency domain analysis methods often suffer from insufficient feature expression and mining, and require complex noise reduction and filtering preprocessing. To address this issue, this paper proposes a fusion image generation method that integrates the advantages of recurrence plot (RP) and Gramian angular summation field (GASF) to generate recurrence Gramian transformed (RGT) images. This approach integrates both global and local fault information, making the fault characteristics more intuitive and easier to analyze. Given that multi-sensor collaboration can enhance feature representation, feature-level fusion increases the computational burden, and decision-level fusion is prone to losing inter-sensor correlation information, this paper adopts data-level fusion for image sample enhancement. In the diagnostic method, the challenge of traditional convolutional neural networks (CNNs) in extracting diverse geometric linear structures from fused images is addressed by introducing deformable convolutional blocks for initial feature extraction. Additionally, a multi-scale feature fusion interaction network (MFFIN) is constructed. This network incorporates a channel-space interactive attention mechanism on top of multi-scale feature extraction, assigning weights to features according to their importance while facilitating the interaction of feature information. Finally, validation is carried out using public datasets, and the experimental results show that the proposed method demonstrates significant advantages in classification accuracy and robustness under variable operating conditions and noise, thereby proving its effectiveness and practicality.

Dual-loss nonlinear independent component estimation for augmenting explainable vibration samples of rotating machinery faults

Obtaining fault samples for diagnosing faults in rotating machinery for engineering applications can be costly. To address this challenge, fault sample augmentation methods are used to train fault diagnosis models. However, existing techniques mainly focus on comparing augmented signal loss with real ones, overlooking the underlying vibration mechanism of rotating machinery faults. Addressing this limitation, a novel approach, called dual-loss nonlinear independent component estimation (DLNICE), is proposed to enhance understanding of fault features in vibration signals. This integrates augmentation losses in both time and frequency domains to enrich fault vibration samples. DLNICE effectively utilizes limited fault samples for augmentation by estimating nonlinear independent components, capturing key fault characteristics like impulsiveness and cyclo-stationarity. Therefore, augmented fault samples become more explainable for analyzing rotating machinery faults. Experimental evaluations on bearing and gearbox vibration samples confirm the effectiveness of DLNICE. Utilizing the augmented samples leads to an average accuracy of 86.27 % in bearing fault diagnosis, and that of 81.60 % in gearbox fault diagnosis. The results demonstrate that DLNICE excels in augmenting high-quality vibration samples of rotating machinery faults.

Fault Diagnosis Method for Wind Turbine Gearbox Based on Ensemble-Refined Composite Multiscale Fluctuation-Based Reverse Dispersion Entropy.

The diagnosis of faults in wind turbine gearboxes based on signal processing represents a significant area of research within the field of wind power generation. This paper presents an intelligent fault diagnosis method based on ensemble-refined composite multiscale fluctuation-based reverse dispersion entropy (ERCMFRDE) for a wind turbine gearbox vibration signal that is nonstationary and nonlinear and for noise problems. Firstly, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and stationary wavelet transform (SWT) are adopted for signal decomposition, noise reduction, and restructuring of gearbox signals. Secondly, we extend the single coarse-graining processing method of refined composite multiscale fluctuation-based reverse dispersion entropy (RCMFRDE) to the multiorder moment coarse-grained processing method, extracting mixed fault feature sets for denoised signals. Finally, the diagnostic results are obtained based on the least squares support vector machine (LSSVM). The dataset collected during the gearbox fault simulation on the experimental platform is employed as the research object, and the experiments are conducted using the method proposed in this paper. The experimental results demonstrate that the proposed method is an effective and reliable approach for accurately diagnosing gearbox faults, exhibiting high diagnostic accuracy and a robust performance.

Theoretical and experimental investigation on gearbox vibration signal separation of planetary gear set

The gearbox vibration signal of a planetary gear set contains multiple components caused by different excitations. Separating the gearbox vibration signal to decouple its components can provide core information for operational status monitoring. In this paper, we propose an indirect gearbox vibration signal separation method based on parameter identification. A novel vibration signal model is established using the modal shape of ring gear. A parameter identification method is adopted to determine the parameters of the vibration signal model. The vibration signal components are reconstructed based on the vibration signal model and identified parameters. To evaluate the performance of the proposed method, a ring gear response calculation method derived from the elastic theory of ring gear is presented. The influences of unequal load sharing and meshing position errors on vibration signals are studied through numerical simulations using the calculation method. Experiments are conducted in a planetary gear set test rig. Comparisons between the experimental results obtained by the separation and calculation methods indicate the effectiveness of the proposed separation method.

Exploring evolutionary-tuned autoencoder-based architectures for fault diagnosis in a wind turbine gearbox

ABSTRACT Vibration-based fault diagnosis from rotary machinery requires prior feature extraction, feature selection, or dimensionality reduction. Feature extraction is tedious, and computationally expensive. Feature selection presents unique challenges intrinsic to the method adopted. Nonlinear dimensionality reduction may be achieved through kernel transformations, however there is often a trade-off in information to achieve this. Given the above, this study proposes a novel autoencoder (AE) pre-processing framework for vibration-based fault diagnosis in wind turbine (WT) gearboxes. In this study, AEs are used to learn the features of WT gearbox vibration data while simultaneously compressing the data, obviating the need for costly feature engineering and dimensionality reduction. The effectiveness of the proposed framework was evaluated by training genetically optimized linear discriminant analysis (LDA), multilayer perceptron (MLP), and random forest (RF) models, with the AE’s latent space features. The models were evaluated using known classification metrics. The results showed that the performance of the models depends on the size of the AE’s latent space. As the size of the AE’s latent space increased, the quality of features extracted improved until a plateau was observed at a latent space dimension of 10. The AE pre-processed genetically optimized RF, MLP, and LDA models, designated AE-Pre-GO-RF, AE-Pre-GO-MLP, and AE-Pre-GO-LDA, were evaluated for accuracy, sensitivity, and specificity in the classification of seven (7) gearbox fault conditions. The AE-Pre-GO-RF model outperformed its counterparts, scoring 100% for all evaluated metrics, though with the longest training time (239.50 sec). Comparable results were found comparing this study with similar investigations involving traditional vibration processing techniques. More so, it was established that effective fault diagnosis of the WT gearbox can be achieved through manifold learning with AEs without expensive feature engineering.

Methods of detection and localization of the sources of noise and vibration on car gearboxes: a review

One of the primary sources of noise and vibration in automobiles is gearboxes. Shafts, gears, and bearings are the main causes of noise and vibration in vehicle gearboxes. Various studies have reported that vibrations’ root cause is bearing excitation. Besides bearing fatal defects or extreme structure resonance amplification, gear mesh is the primary source of high-frequency vibration and noise, even in newly built units. Gear damage detection is frequently crucial in automotive gearboxes and vehicle safety. Furthermore, vibrations caused by shaft imbalances, shaft misalignments, and other factors can cause noise and vibrations in the drivetrain's transfer path. In addition, the vibration of an automobile gearbox is closely related to poor design, construction quality, and production accuracy. This paper reviewed previous research and methods on car gearboxes for conventional vehicles. It was obvious that frequency analysis and order analysis were commonly used in noise and vibration analysis on car gearboxes. Envelope analysis is usually used to analyze bearing faults. Finally, rolling-element bearing diagnostic techniques were also reviewed.

Retraction Note: Research on Feature Extraction and Diagnosis Method of Gearbox Vibration Signal Based on VMD and ResNeXt

Retraction Note: Research on Feature Extraction and Diagnosis Method of Gearbox Vibration Signal Based on VMD and ResNeXt

Numerical and experimental investigations on the vibration behavior of a high-speed planetary gearbox

Increasing the speed of the electric motor can significantly improve the power density of the powertrain of EVs (Electric Vehicles), resulting in a smaller size and thus weight and cost advantages. Achieving acceptable NVH behavior becomes more difficult at higher speeds, partly because the excitation frequencies of the gears cover a wider frequency range and therefore higher natural frequencies can also be directly excited. In the Speed4E joint research project, a high-speed electromechanical powertrain was developed, manufactured, and tested to investigate the main challenges on the NVH- and efficiency-behavior of high-speed powertrains. The high-speed design of the Speed4E drivetrain results in maximum electric motor speeds of up to 50,000 rpm, combined with a torque of up to 45 Nm at the transmission input shafts. This study presents the experimental results on the vibration behavior of the high-speed planetary gearbox, a comparison with the corresponding results of a highly efficient calculation method of the gearbox vibration excitation, and the theoretical background of the calculation method is presented. The results indicate the potential to improve the vibration behavior of high-speed drives in EVs and provide a deep understanding of the challenges associated with high speeds.

Multivariate multi-scale cross-fuzzy entropy and SSA-SVM-based fault diagnosis method of gearbox

Abstract Fuzzy entropy (FuzzyEn) is widely recognized as a powerful tool for analyzing nonlinear dynamics and measuring the complexity of time series data. It has been utilized as an effective indicator to capture nonlinear fault features in gearbox vibration signals. However, FuzzyEn only measures complexity at a single scale, ignoring the valuable information contained in large-scale features of the time series. Furthermore, FuzzyEn does not account for coupling characteristics between related or synchronized time series. To address these limitations, a novel entropy-based approach called multivariate multi-scale cross-fuzzy entropy (MvMCFE) is proposed in this paper for measuring the complexity and mutual predictability of two multivariate time series. Relying on the advantages of MvMCFE in nonlinear feature extraction, a new fault diagnosis method for gearboxes is proposed based on MvMCFE and an optimized support vector machine (SVM) using the salp swarm algorithm (SSA-SVM). Ultimately, the proposed gearbox diagnostic method is employed to analyze the gearbox experimental data and a comparison with existing fault diagnosis approaches is conducted. The comparison results indicate that the proposed method can effectively extract nonlinear fault features of gearboxes and achieve the highest recognition rate compared to the other methods.

Strategy for Detection and Suppression of Random Impulse Interferences in Gearbox Vibration Signals

Strategy for Detection and Suppression of Random Impulse Interferences in Gearbox Vibration Signals

A lightweight fault diagnosis model for planetary gearbox using domain adaptation and model compression

This article proposes a novel lightweight attention spatiotemporal joint distribution adaptation network fault diagnosis model to address the key challenges of domain transfer and high model complexity in traditional methods. The novelty lies in 1. Using model compression techniques to reduce the complexity of the network model and improve its computational efficiency; 2. Introducing new domain adaptation and adversarial methods to solve the domain transfer problem. The effectiveness of the proposed model is verified through a transfer experiment of planetary gearbox vibration data. The experimental results show that the proposed model reduces the parameters and computational complexity to 18 % and 15 % of the original model, respectively, and has a diagnostic accuracy of over 98 % in cross-condition transfer tasks, and still maintains an accuracy of over 88 % even under high noise levels. This indicates that the proposed model is an efficient and accurate fault diagnosis model.

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

Although data-driven methods have been widely used in planetary gearbox fault diagnosis, the difficulty and high cost of manual labeling leads to little labeled training data, which limits the classification performance of traditional data-driven methods. Therefore, the semi-supervised fault diagnosis method with few labeled samples becomes one of the main research directions. Graph attention network (GAT) is distinguished from traditional classification network by using graph structure for fault node information aggregation and feature extraction, which is an effective semi-supervised learning algorithm. This paper uses fast Fourier transform to process the original vibration signal of gearbox and use it as graph nodes, and propose a KNN graph construction method using pooling for fuzzy distance calculation. In addition, this paper improves the distribution of attention weights by introducing dynamic graph attention networks to correct the problem that classical static GATs cannot clearly distinguish the weights of different categories of nodes. Experiments show that the method proposed in this paper can better extract fault features in complex gearbox vibration signals with an accuracy of more than 99% with very few labeled samples, and has better diagnostic performance compared with other graph neural network architectures and traditional classification networks.

Design and application of gearbox vibration testing system

Judging the working status of a gearbox through the characteristics of vibration signals was an effective fault diagnosis method. In order to improve the efficiency and reliability of vibration detection, a multi node testing system based on a microcontroller was designed and validated. The system mainly consists of signal processing equipment, signal collector, upper computer, sensors, and experimental workbench. Under different types of gear faults, the vibration signals of ten sets of gearboxes were synchronously collected and processed. In order to ensure the resolution of frequency conversion and accurately locate frequency conversion, the low-pass filtered spectrum with a filtering frequency of 1000 was verified and used to calculate the amplitude of frequency conversion. The normalization of amplitude was more conducive to feature recognition, and the frequency amplitude was proportional to its corresponding energy. According to standard spectral data and spectral analysis, wear, pitting, fracture, and bonding faults in the gearbox were identified and classified. Through the verification of three order feature spectrum, it can be seen that the accuracy of fault prediction for gearbox through vibration signals is high, which can effectively reduce maintenance and repair costs.

Torque effect on vibration behavior of high-speed train gearbox under internal and external excitations

AbstractThe high-speed train transmission system, experiencing both the internal excitation originating from gear meshing and the external excitation originating from the wheel–rail interaction, exhibits complex dynamic behavior in the actual service environment. This paper focuses on the gearbox in the high-speed train to carry out the bench test, in which various operating conditions (torques and rotation speeds) were set up and the excitation condition covering both internal and external was created. Acceleration responses on multiple positions of the gearbox were acquired in the test and the vibration behavior of the gearbox was studied. Meanwhile, a stochastic excitation modal test was also carried out on the test bench under different torques, and the modal parameter of the gearbox was identified. Finally, the sweep frequency response of the gearbox under gear meshing excitation was analyzed through dynamic modeling. The results showed that the torque has an attenuating effect on the amplitude of gear meshing frequency on the gearbox, and the effect of external excitation on the gearbox vibration cannot be ignored, especially under the rated operating condition. It was also found that the torque affects the modal parameter of the gearbox significantly. The torque has a great effect on both the gear meshing stiffness and the bearing stiffness in the transmission system, which is the inherent reason for the changed modal characteristics observed in the modal test and affects the vibration behavior of the gearbox consequently.

Research on the dynamic characteristics of wind turbine gearboxes under the spatiotemporal inhomogeneous in the wake

In response to the problem of increasing fatigue load and frequent faults caused by the wake effect, the dynamic characteristics and fatigue life analysis of wind turbine gearbox under the Spatial-temporal non-uniformity of wake region were carried out in this paper. A rigid-flexible coupling model of gears transmission system for a 2 MW wind turbine was established. Based on the three-dimensional Station-temporal inhomogeneous wake model proposed in our previous work, the wind speed distribution of six typical locations in the wake region was obtained. Results show that, the spatiotemporal inhomogeneous effects of the wake expansion have great impact on the dynamic characteristics of the gearboxes for the downwind turbines located in different positions. Vibration energy representing the magnitude of impact energy during the operation of the gearbox is significantly higher under wake conditions than under upstream conditions; meanwhile, the gearbox vibration signal contains more impact component in the wake. The velocity deficit and increased turbulence intensity results in less intense but more complex vibration non-smoothness in the turbine transmission system. As the downwind distance downwind increases, the vibration frequency distribution of the transmission system at each moment is larger, but the vibration energy is reduced. Under the 3D spatiotemporal inhomogeneous effects of the wake expansion, the downstream turbine with staggered arrangement is less affected by wake and has a smoother vibration than the tandem arrangement. At the same downstream distance, the gear life is better in a tandem arrangement than in a staggered arrangement (a maximum value happens at the downstream distance of 6D). Research in this paper can provide references for the study of the dynamic characteristics of large wind turbine transmission systems under the wake effects as well as for the micro-siting of wind farms.