Wind Turbine Planetary Gearbox Research Articles

CTNet: A data-driven time-frequency technique for wind turbines fault diagnosis under time-varying speeds

Nonstationary fault signals collected from wind turbine planetary gearboxes and bearings often exhibit close-spaced instantaneous frequencies (IFs), or even crossed IFs, bringing challenges for existing time-frequency analysis (TFA) methods. To address the issue, a data-driven TFA technique, termed CTNet is developed. The CTNet is a novel model that combines a fully convolutional auto-encoder network with the convolutional block attention module (CBAM). In the CTNet, the encoder layer is first designed to extract coarse features of the time-frequency representation (TFR) calculated by the general linear Chirplet transform (GLCT); second, the decoder layer is combined to restore and conserve details of the key time-frequency features; third, the skip connections are designed to accelerate training by linking extracted and reconstructed features; finally, the CBAM is introduced to adaptively explore channel and spatial relationships of the TFR, focusing more on close-spaced or crossed frequency features, and effectively reconstruct the TFR. The effectiveness of the CTNet is validated by numerical signals with close-spaced or crossed IFs, and real-world signals of wind turbine planetary gearbox and bearings. Comparison analysis with state-of-the-art TFA methods shows that the CTNet has high time-frequency resolution in characterizing nonstationary signals and a much better ability to detect wind turbine faults.

Frequency-chirprate synchrosqueezing-based scaling chirplet transform for wind turbine nonstationary fault feature time–frequency representation

As key rotational components of wind turbines, planetary gearboxes, and bearings need special health monitoring and fault diagnosis for reducing downtime and maintenance costs. However, it is still a challenging issue for time–frequency analysis (TFA) techniques to analyze nonstationary and close-spaced fault frequencies of wind turbines. Hence, a high- concentration TFA technique, termed frequency-chirprate synchrosqueezing-based scaling chirplet transform (FCSSCT) is developed. In the FCSSCT, the novel dimension of chirprate is introduced to map the signal into the three-dimensional space of time–frequency-chirprate in contrast to the time–frequency domain in the synchrosqueezing transform (SST), herein, the three-dimensional space of time, frequency and chirprate is calculated based on the scaling-basis chirplet transform (SBCT); then, a frequency-chirprate synchrosqueezing operator (FCSO) is defined in the frequency-chirprate domain to reassign the amplitude coefficients of the SBCT results and a three-dimensional representation of time–frequency-chirprate is obtained; finally, the time–frequency representation (TFR) with concentrated energy is obtained by transforming the three-dimensional representation of the time–frequency-chirprate space into the time–frequency domain. The effectiveness of the developed FCSSCT is verified by the simulated multi-component signals with close-spaced frequencies or crossover frequencies. Experimental analysis results on wind turbine planetary gearbox and bearing show that the developed technique is effective in characterizing nonstationary fault frequencies. Rényi entropies demonstrate that the FCSSCT has much better energy concentration compared with several advanced TFA methods.

Adaptive Intermediate Class-Wise Distribution Alignment: A Universal Domain Adaptation and Generalization Method for Machine Fault Diagnosis.

Many transfer learning methods have been proposed to implement fault transfer diagnosis, and their loss functions are usually composed of task-related losses, distribution distance losses, and correlation regularization losses. The intrinsic parameters and trade-off parameters between losses, however, need to be tuned according to the specific diagnosis tasks; thus, the generalization abilities of these methods in multiple tasks are limited. Besides, the alignment goal of most domain adaptation (DA) mechanisms dynamically changes during the training process, which will result in loss oscillation, slow convergence and poor robustness. To overcome the above-mentioned issues, a novel and simple transfer learning diagnosis method named adaptive intermediate class-wise distribution alignment (AICDA) model is proposed, and it is established via the proposed AICDA mechanism, dynamic intermediate alignment (DIA) adaptive layer and AdaSoftmax loss. The AICDA mechanism develops an adaptive intermediate distribution as the alignment goal of multiple source domains and target domains, and it can simultaneously align the global and class-wise distributions of these domains. The DIA layer is designed to adaptively achieve domain confusion without the distribution distance loss and the correlation regularization loss. Meanwhile, to ensure the classification performance of the AICDA mechanism, AdaSoftmax loss is proposed for boosting the separability of Softmax loss. Finally, in order to evaluate the effectiveness and universality of the AICDA diagnosis model to the most degree, various multisource mixed fault transfer diagnosis tasks of wind turbine planetary gearboxes, including DA and domain generalization (DG), are implemented, and the experimental results indicate that our proposed AICDA model has a higher diagnosis accuracy and a stronger generalization ability than other state-of-the-art transfer learning methods.

Remaining Useful Life Prediction of a Planetary Gearbox Based on Meta Representation Learning and Adaptive Fractional Generalized Pareto Motion

The remaining useful life (RUL) prediction of wind turbine planetary gearboxes is crucial for the reliable operation of new energy power systems. However, the interpretability of the current RUL prediction models is not satisfactory. To this end, a multi-stage RUL prediction model is proposed in this work, with an interpretable metric-based feature selection algorithm. In the proposed model, the advantages of neural networks and long-range-dependent stochastic processes are combined. In the offline training stage, a general representation of the degradation trend is learned with the meta-long short-term memory neural network (meta-LSTM) model. The inevitable measurement error in the sensor reading is modelled by white Gaussian noise. During the online RUL prediction stage, fractional generalized Pareto motion (fGPm) with an adaptive diffusion is employed to model the stochasticity of the planetary gearbox degradation. In the case study, real planetary gearbox degradation data are used for the model validation.

Spectral ensemble sparse representation classification approach for super-robust health diagnostics of wind turbine planetary gearbox

Health monitoring, diagnostics and prognostics techniques have been deemed as the most promising and essential framework towards smart operation and maintenance of wind energy equipment. Wind turbine planetary gearboxes have remained the most intricate and challenging transmission units to implement intelligent health diagnostics in wind power generation systems. To resolve this issue, we present a novel spectral ensemble sparse representation classification (S-ESRC) approach for super-robust health diagnostics of wind turbine planetary gearboxes. Specifically, S-ESRC implements super-robust health diagnostics via three procedures consisting of data augmentation, spectral dictionary design, and spectral sparse approximation-based diagnostic scheme. Firstly, the prediction translation-invariance is exploited to accomplish vibrational data augmentation. Second, the spectral dictionary design with robust and strong reconstruction capability is achieved via spectrum construction and feature fusion considering the intra-class and inter-class attributes. Thirdly, the spectral sparse approximation error-based diagnostic scheme is applied to accomplish robust health diagnostics. Experimental validations using a wind turbine planetary gearbox system have demonstrated the applicability and superiority of S-ESRC for super-robust health diagnostics. Comparative studies have comprehensively shown the super-robust performances of S-ESRC including superior diagnostic accuracy, strong robustness to random noises, strong robustness to hyperparameters, and efficient computation costs in comparison with several state-of-the-art approaches.

Relationship Transfer Domain Generalization Network for Rotating Machinery Fault Diagnosis Under Different Working Conditions

Many domain adaptation (DA) models have been explored for fault transfer diagnosis. However, their successes completely rely on the availability of target-domain samples during the training process. As target domain is usually unseen, the domain-adaptation-based diagnostic models cannot meet the requirement of real-time diagnosis in actual engineering. To achieve the domain confusion in the actual diagnosis scenario, a novel relationship transfer (RT) diagnosis framework is first proposed, which can indirectly measure and reduce the distribution discrepancy between the source domain and unseen target domain. Based on the proposed RT framework, a new domain generalization transfer method, called relationship transfer domain generalization network (RTDGN) is constructed. RTDGN is divided into two phases including task-irrelevant domain adaptation (TIDA) and task-relevant domain generalization (TRDG). In the TIDA phase, a DA adversarial network with several domain discriminators is built to enhance the domain confusion of RT framework. Furthermore, to bring the adversarial network a more general domain confusion ability, a new inverse entropy loss is designed. In the TRDG phase, a residual fusion classifier is constructed to improve the generalization ability of fault classifier. Finally, the experimental results on the wind turbine planetary gearbox dataset and bearing dataset verify the effectiveness and superiority of the proposed RTDGN.

Wind Turbine Planetary Gearbox Fault Diagnosis via Proportion-Extracting Synchrosqueezing Chirplet Transform

Wind turbine planetary gearboxes usually work under time-varying conditions, leading to nonstationary vibration signals. These signals often consist of multiple time-varying components with close instantaneous frequencies. Therefore, high-quality time-frequency analysis (TFA) is needed to extract the time-frequency feature from such nonstationary signals for fault diagnosis. However, it is difficult to obtain high-quality time-frequency representations (TFRs) through conventional TFA methods due to low resolution and time-frequency blurs. To address this issue, we propose a new TFA method termed the proportion-extracting synchrosqueezing chirplet transform (PESCT). Firstly, the proportion-extracting chirplet transform (PECT) is employed to generate high-resolution underlying TFRs. Then, the energy concentration of the underlying TFRs is enhanced via the synchrosqueezing transform. Finally, wind turbine planetary gearbox fault can be diagnosed by analysis of the dominant time-varying components revealed by the concentrated TFRs with high resolution. The proposed PESCT is suitable for achieving high-quality TFRs for complicated nonstationary signals. Numerical and experimental analyses validate the effectiveness of the PESCT in characterizing the nonstationary signals from wind turbine planetary gearboxes.

A Two-Stage Framework for Time-Frequency Analysis and Fault Diagnosis of Planetary Gearboxes

In the operation and maintenance of planetary gearboxes, the growth of monitoring data is often faster than its analysis and classification. Careful data analysis is generally considered to require more expertise. Rendering the machine learning algorithm able to provide more information, not just the diagnosis conclusion, is promising work. This paper proposes an analysis and diagnosis two-stage framework based on time-frequency information analysis. In the first stage, a U-net model is used for the semantic segmentation of vibration time-frequency spectrum to highlight faulty feature regions. Shape features are then calculated to extract useful information from the segmented image. In the second stage, the decision tree algorithm completes the health state classification of the planetary gearboxes using the input of shape features. The real data of wind turbine planetary gearboxes and augmented data are utilized to verify the proposed framework’s effectiveness and superiority. The F1-score of segmentation and the classification accuracy reach 0.942 and 97.4%, respectively, while in the environmental robustness experiment, they reached 0.747 and 83.1%. Equipping the two-stage framework with different analytical methods and diagnostic algorithms can construct flexible diagnostic systems for similar problems in the community.

Investigating the vibration response and modulation mechanism for health monitoring of wind turbine planetary gearboxes using a tribodynamics-based analytical model

In a wind turbine (WT) planetary gearbox system, the characteristics of incipient faults are difficult to recognize with increasing friction under a lack of lubrication condition. To this end, a translational–torsional coupled nonlinear tribodynamic model considering local faults is developed. A fitted time-varying transfer function is obtained using an impact experiment excited by a planet gear with a missing tooth and is further used to represent the modulation effect caused by the carrier. Using the proposed analytical model, the vibration response and modulation mechanism of the resultant signal under the coupling effect of tooth root crack and sliding friction are investigated. It is demonstrated that specific sidebands are greatly excited and the spectrum structure becomes extremely complex after the introduction of friction. Based on these results, sideband indicators are obtained to monitor the lubrication state and detect incipient faults. The experimental results based on an in-house WT drivetrain testbench are in good agreement with the simulation results.

A novel order spectrum-based Vold-Kalman filter bandwidth selection scheme for fault diagnosis of gearbox in offshore wind turbines

Vold-Kalman order tracking filter is an effective technique for dealing with non-stationary vibrations which offshore wind turbines often encounter. It has a unique capability to extract and track the time waveforms of harmonics in short transients without phase bias, and this capability is beneficial to the condition monitoring of offshore wind turbines. In general, the accuracy of the tracking results of the Vold-Kalman filer for condition monitoring is heavily dependent on the selection of filter bandwidth. A fixed filter bandwidth becomes problematic when processing different types of signals under varying operating conditions. Significant errors may arise in the tracking, rendering the condition monitoring of offshore wind turbines unreliable. To address this issue, this paper proposes a novel scheme for Vold-Kalman filter bandwidth selection to guarantee the consistency and accuracy of the offshore wind turbine condition monitoring process, ensuring reliable fault diagnosis. A numerical model is used to evaluate the effectiveness of the proposed bandwidth selection scheme first. Then the proposed scheme is further validated through the offshore wind turbine planetary gearbox datasets, together with the demonstration of the fault diagnosis capability of the filtered results.

Wind turbine planetary gearbox fault diagnosis using circular pitch cyclic vector and a bidirectional gated recurrent unit

A planetary gearbox with large transmission ratio is a critical component of a wind turbine (WT). When the planetary gearbox suffers from failure, the regular variation of circular pitch vibration energy contains fault pattern information. Although deep learning-based fault diagnosis models have the capability for automatic feature extraction, they rarely consider emphasizing the energy variation characteristics related to the planetary transmission structure in the data representation stage, which degrades the fault diagnosis performance. To solve this problem, this paper describes a novel data representation method, circular pitch cyclic vector (CPCV) and, on this basis, proposes a WT planetary gearbox fault diagnosis method using CPCV and a bidirectional gated recurrent unit (BGRU). Firstly, this paper utilizes root mean square value as the energy evaluation metric for calculating the CPCV. Then, the mapping relationship between circular pitch energy and the ring gear mesh phase is captured using the BGRU through its bidirectional learning capability. Finally, a fully connected layer with softmax is used for fault classification. The proposed method is evaluated by analyzing the in-service WT vibration data collected from a wind farm in eastern China. The experimental results and comparison analysis illustrate the superiority of the proposed method.

Improved vibration AM-FM sideband phenomenon models of planetary gear set with distributed faults and fault-induced speed fluctuation

Vibration modulation features are the important indicators for the planetary gear set fault diagnosis. However, the modulation sidebands caused by the distributed faults of planetary gear set are complicated, especially the FM components related to fault-induced periodic speed fluctuation, which have not been clearly revealed. In this paper, the transfer path function, gear meshing force and measuring-direction projection function with FM components are combined to develop a series of phenomenon models when considering the distributed gear fault-induced speed fluctuation, which can theoretically deduce the vibration modulation sidebands. Field test of the wind turbine planetary gearbox and the fault simulation of experiment platform verify the high consistency of the vibration AM-FM sidebands obtained from the phenomenon models and the practical planetary gear sets. The proposed models contribute a clear explanation for the generation mechanism of vibration AM-FM sidebands even the sidebands with small amplitudes caused by the distributed faults of sun and planet gear, and provide the important and effective frequency features to confirm the condition of planetary gear set.

Vibration based fault diagnostics in a wind turbine planetary gearbox using machine learning

To reduce wind turbine operations and maintenance costs, we present a machine learning framework for early damage detection in gearboxes based on the cyclostationary and kurtogram analysis of sensor data. The application focus is fault diagnostics in gearboxes under varying load conditions, particularly turbulent wind. Faults in the gearbox rotating components can leave their signatures in vibrations signals measured by accelerometers. We analyze data stemming from a simulated vibration response of a 5 MW multibody wind turbine model in a healthy and damaged scenarios and under different wind conditions. With cyclostationary and kurtogram analysis applied on acquired sensor data, we generate two types of 2D maps that highlight signatures related to the fault damage. Using these maps, convolutional neural networks are trained to identify faults, including those of small magnitude, in test data with a high accuracy. Benchmark test cases inspired by an NREL study are tested and faults successfully detected.

A dynamic-model-based fault diagnosis method for a wind turbine planetary gearbox using a deep learning network

The planetary gearbox is a critical part of wind turbines, and has great significance for their safety and reliability. Intelligent fault diagnosis methods for these gearboxes have made some achievements based on the availability of large quantities of labeled data. However, the data collected from the diagnosed devices are always unlabeled, and the acquisition of fault data from real gearboxes is time-consuming and laborious. As some gearbox faults can be conveniently simulated by a relatively precise dynamic model, the data from dynamic simulation containing some features are related to those from the actual machines. As a potential tool, transfer learning adapts a network trained in a source domain to its application in a target domain. Therefore, a novel fault diagnosis method combining transfer learning with dynamic model is proposed to identify the health conditions of planetary gearboxes. In the method, a modified lumped-parameter dynamic model of a planetary gear train is established to simulate the resultant vibration signal, while an optimized deep transfer learning network based on a one-dimensional convolutional neural network is built to extract domain-invariant features from different domains to achieve fault classification. Various groups of transfer diagnosis experiments of planetary gearboxes are carried out, and the experimental results demonstrate the effectiveness and the reliability of both the dynamic model and the proposed method.

A novel adaptive bandwidth selection method for Vold–Kalman filtering and its application in wind turbine planetary gearbox diagnostics

The planetary gearbox transmission system in wind turbines has complex structures and generally operates under non-stationary conditions. Thus its measured responses are of high complexity and nonlinearity, which brings a great challenge in the development of reliable condition monitoring techniques for the planetary gearbox transmission system. As a prevalent and effective tool for analyzing the non-stationary vibration signal with strong nonlinearity, the Vold–Kalman filtration technique has excellent capabilities of tracking the targeted harmonic components of vibrations, which can significantly benefit planetary gearbox fault diagnostics. However, the tracking accuracy is heavily enslaved to the selection of the rational bandwidth for the Vold–Kalman filter. An inappropriate bandwidth could impair the characteristics of the targeted harmonic responses, and as a consequence, the monitoring process becomes no longer reliable. To address this issue, a novel bandwidth selection methodology for the Vold–Kalman filter is developed in this paper. Through comprehensively depicting the targeted harmonic response using features in multiple domains, the rational bandwidth can be selected for Vold–Kalman filtering, and then, a reliable monitoring process can be ensured. Additionally, a tacho-less speed estimation procedure is utilized in this paper to acquire the instantaneous rotational speed from the vibration signal directly. With the rational bandwidth and the estimated rotational speed, the desired harmonic components of vibrations can be adaptively extracted and tracked through the Vold–Kalman filter with high accuracy, and at the same time, the irrelevant or unwanted components are excluded completely. The effectiveness and superiority of the proposed adaptive Vold–Kalman filtration for wind turbine planetary gearbox diagnostics are demonstrated and validated experimentally.

Evidence Theory based Uncertainty Design Optimization for Planetary Gearbox in Wind Turbine

The planetary gearbox is an important part of the wind turbine. There are many random uncertain factors in the process of design, production, installation, and use, and these uncertain factors greatly influence the service life and reliability of the planetary gearbox. Therefore, the influence of uncertain factors needs to be considered in the design process to reduce the risk of failure. In this paper, an uncertainty design optimization method based on evidence theory is proposed, which can consider both interval variables and random variables in the optimization process. Then the megawatt wind turbine planetary gearbox is taken as the research object to analyze its uncertainty sources. Finally, the planetary gearbox is optimized by the proposed method. By comparing the results, the design scheme obtained by the method proposed in this paper is more reliable.

Condition Monitoring in a Wind Turbine Planetary Gearbox Using Sensor Fusion and Convolutional Neural Network

To meet the requirements of reducing operations and maintenance costs of wind turbines, we present a machine learning framework for early damage detection in gearboxes based on the cyclostationary analysis of sensor data. The application focus is the condition monitoring of wind turbine gearboxes under varying load scenarios, in particular turbulent wind conditions. Faults in the rotating components in the gearbox can leave their signature in the vibrations that can be measured by accelerometers. We analyze data stemming from a simulated vibration response of a 5MW multibody wind turbine model in a healthy and damaged scenarios and under different wind conditions. With cyclostationary analysis applied on acquired sensor data, we generate cyclic spectral coherence maps that highlight signatures related to the fault damage and enable its identification. These maps are used to train convolutional neural networks that then identify faults, including those of small magnitude, in test data with a high accuracy. Benchmark test cases inspired by an NREL study are tested and faults successfully detected.

Investigation on planetary gearbox fault mechanism under variable speed conditions based on rigid-flexible coupling dynamics model

Dynamic behaviors of wind turbine planetary gears are greatly affected by the transfer paths and variable conditions. However, previous studies have mainly considered single transfer path and stationary operating conditions. To overcome this problem, a rigid-flexible coupling dynamics model of wind turbine planetary gearbox under different transfer paths and variable conditions is established. By simulating the modal-based rigid-flexible coupling dynamics model, the gearbox output shaft speed as well as the box vibration response in the stationary condition are obtained well, which can be characterized by its frequency features. By conducting order envelope analysis on the simulated acceleration signals in the variable speed condition, the feature order in the sun gear fault state is obtained on the simulated acceleration signal. The planetary gearbox dynamics tests results are in good agreement with the simulation results. The experiment results verify the correctness of the established rigid-flexible coupling dynamics model. This modeling method provides a new idea for multi-path modeling of wind turbine gearboxes and the study of fault mechanism under variable speed conditions.

Application of Double Q Wavelet-based Sparse Decomposition to Fault Feature Extraction of Wind Turbine Planetary Gearbox

The wind turbine gearbox is a critical equipment transforming the speed of the rotor hub to the generator, the condition of which is the reflection of operational efficiency and reliability of wind turbines. As the initial stage of the wind turbine gearbox, the fault feature extraction of the planetary gear set is challenging since it is prone to be affected by complicated structure, vibration from other high-speed stages and background noise. In this paper, a double Q factor wavelet-based sparse decomposition is applied to the fault feature extraction of the wind turbine planetary gearbox. Considering the sparsest wavelet coefficients, the vibration signal is iteratively decomposed into high Q and low Q components. The fault feature is generally hidden in the low Q component. With further demodulation, the fault information of planetary gears can be easily detected.

Component matching chirplet transform via frequency-dependent chirp rate for wind turbine planetary gearbox fault diagnostics under variable speed condition

A component matching chirplet transform (CMCT) via frequency-dependent chirp rate with high time-frequency (TF) resolution is proposed for wind turbine planetary gearbox (WTPG) fault diagnostics under variable speed condition. The challenge of identifying fault-related frequencies with small intervals, due to the time-varying rotational speed and complex structure of WTPG, can be well addressed. Unlike conventional chirplet transform, CMCT can generate a family of frequency-dependent chirplets, which can match all frequency components with a sufficiently high TF resolution. Furthermore, this proposed method does not require any prior knowledge. The effectiveness of CMCT is validated by a numerical simulation and an experimental data collected from a wind turbine drivetrain test rig.