Gearbox Condition Research Articles

Wind turbine gearbox condition monitoring using AI-enabled virtual indicators*

Abstract At present, the condition monitoring of wind turbine gearbox mostly involves selecting monitoring indicators in advance and establishing normal behavior models based on deep learning. However, single physical monitoring indicator cannot fully characterize the operating status of the wind turbine gearbox. To address the above issues, a wind turbine gearbox condition monitoring method using convolutional neural network (CNN)-long and short term memory network (LSTM)-autoencoder (AE) enabled virtual indicators is proposed in this paper. This method first establishes a cleaning principle to preprocess the data of supervisory control and data acquisition (SCADA) system and screen out effective SCADA data further. A CNN-LSTM-AE monitoring model was trained using SCADA data during normal operating process, various characteristic parameters of the gearbox are integrated to construct the AI-enabled virtual indicators, and meanwhile warning thresholds was determined based on the probability density distribution of virtual indicators to analyze the operating status of the gearbox. Finally, the proposed method was validated using real SCADA data from two wind turbines in a cooperated wind farm with my group. Compared with a single physical indicator, the virtual indicator enables to detect gearbox early faults 5 d in advance, indicating that the proposed method can effectively alert wind turbine gearbox failures.

Temporally-preserving latent variable models: Offline and online training for reconstruction and interpretation of fault data for gearbox condition monitoring

Latent variable models can effectively determine the condition of essential rotating machinery without needing labelled data. These models analyse vibration data via an unsupervised learning strategy. Temporal preservation is necessary to obtain an informative latent manifold for the fault diagnosis task. In a temporal-preserving context, two approaches exist to develop a condition-monitoring methodology: offline and online. For latent variable models, the available training modes are no different. While many traditional methods use offline training, online training can dynamically adjust the latent manifold, possibly leading to better fault signature extraction from the vibration data. This study explores online training using temporal-preserving latent variable models. Within online training, there are two main methods: one focuses on reconstructing data and the other on interpreting the data components. Both are considered to evaluate how they diagnose faults over time. Using two experimental datasets, the study confirms that models from both training modes can detect changes in machinery health and identify faults even under varying conditions. Importantly, the complementarity of offline and online models is emphasised, reassuring their versatility in fault diagnostics. Understanding the implications of the training approach and the available model formulations is crucial for further research in latent variable model-based fault diagnostics. Conflict of Interest Statement The authors declare no conflicts of interest.

Wind turbine gearbox oil temperature feature extraction and condition monitoring based on energy flow

Supervisory Control and Data Acquisition (SCADA) data is widely used for wind turbine gearbox condition monitoring (WTGCM) due to its easy access and low cost, thus ensuring the safe and reliable operation of wind turbine gearboxes. However, existing WTGCM methods based on SCADA overlook the fundamental thermal physics and sensor failure. To effectively address the challenges of weak feature generalization and numerous false alarms, we propose a highly robust WTGCM method based on energy flow. Firstly, based on the principles of thermal balance and wind energy conversion, a feature extraction method considering the physical change process of oil temperature is proposed. Secondly, the performance of different feature extraction methods is quantitatively analyzed using data evaluation criteria. The reasons why different feature extraction methods have different effects are revealed through dimensionality reduction analysis. Finally, we compare the proposed method with other feature extraction methods using four models to validate the excellent performance of the proposed method in the early fault warning. The results demonstrate that the proposed method reduces the average root mean square error by 18.21% during the healthy operation of the wind turbine gearboxes. Moreover, the proposed method performs excellently in early warning of mechanical and sensor faults, significantly reducing the number of false alarms. The average warning time for mechanical faults is 32.56 h earlier.

CNC machine gearbox fault detection with convolutional neural network

This study focuses on the development of a deep learning-based approach of gearbox monitoring and fault detection. The project aims to create a solution for early detection of defects in dynamic equipment based on data from vibration sensor by building a binary classifier with convolutional neural network implemented. The gearboxes condition of which is being assessed is stored in three similar computer numerically controlled (CNC) milling machines. Data is collected during 15 milling operations of different duration and with different tool’s speed and feed. Vibration is measured by an accelerometer stored on the body of each gearbox. Convolutional neural network takes vibration spectra as inputs and whether fault is detected makes a prediction of a gearbox condition. To make the whole solution autonomous and be able to embed it into manufacture the project is integrated into a server with an edge-to-cloud architecture. As an end product deep learning fault classifier stored on a server is to detect possible gearbox faults, draw conclusions on condition of dynamic equipment and automate the process of fault detection.

Optimal weight impulse extraction: New impulse extraction methodology for incipient gearbox condition monitoring

Gear faults in a transmission system generally cause impulse components in vibration signals, which is a crucial symbol for gearbox fault diagnosis. However, their related signals are often interfered or even submerged by the noisy meshing components (NMC) of gearboxes in degradation, which introduces challenges for incipient fault detection and condition monitoring. Commonly employed deconvolution-based methods attempt to design a filter to extract impulse components. However, these methods fail to address the interference issue of the NMC on deconvolution process. To overcome this limitation, this paper proposes an optimal weight impulse extraction (OWIE) methodology to suppress the NMC and highlight impulse component in vibration signal. Different from deconvolution-based methods, the proposed method locates impulses adaptively driven by waveform itself. A non-impulse part is suppressed through point-to-point removal, while impulse components are highlighted by subtracting a weighted signal from a raw signal. An iterative procedure is utilized to solve the optimal weight sequence by maximizing the kurtosis of an impulse signal. The effectiveness of the proposed OWIE is validated through a simulation case study and a run-to-failure experiment of gearboxes. Results demonstrate that the OWIE is sensitive to incipient faults and is suitable for the health condition monitoring of gearboxes.

A Review on Gearbox Condition Monitoring and Signal Analysis Techniques

The manufacturing industry propels the globe forward. Every manufacturing business has many machines and gears for power conversion, speed reduction, and torque amplification, and many of them can be controlled. It is projected that 10 million new gearboxes enter service each year, with a total component value of more than $5 billion. The reliability of gear driven machinery and gearboxes is critical to industry's economic viability. Any malfunction in the machinery can lead to a significant breakdown expense. This paper includes a review of the literature on methods for signal analysis and gearbox condition monitoring. The approaches and components utilised in condition monitoring are covered in this paper. The vibration signal of a gearbox contains the signature of a gear failure, so it can be used to identify gearbox breakdowns early on by analysing the signal using various signal processing techniques. For equipment monitoring, gearbox vibration analysis is an easy, affordable, and reliable way to identify issues early on and save expensive gearbox repairs and unplanned shutdowns.

Gearbox Condition Monitoring and Diagnosis of Unlabeled Vibration Signals Using a Supervised Learning Classifier

Data-based equipment fault detection and diagnosis is an important research area in the smart factory era, which began with the Fourth Industrial Revolution. Steel manufacturing is a typical processing industry, and efficient equipment operation can improve product quality and cost. Steel production systems require precise control of the equipment, which is a complex process. A gearbox transmits power between shafts and is an essential piece of mechanical equipment. A gearbox malfunction can cause serious problems not only in production, quality, and delivery but in safety. Many researchers are developing methods for monitoring gearbox condition and for diagnosing failures in order to resolve problems. In most data-driven methods, the analysis data set is derived from a distribution of identical data with failure mode labels. Industrial sites, however, often collect data without information on the failure type or failure status due to varying operating conditions and periodic repair. Therefore, the data sets not only include frequent false alarms, but they cannot explain the causes of the alarms. In this paper, a framework called the Reduced Lagrange Method (R-LM) periodically assigns pseudolabels to vibration signals collected without labels and creates an input data set. In order to monitor the status of equipment and to diagnose failures, the input data set is fed into a supervised learning classifier. To verify the proposed method, we build a test rig using motors and gearboxes that are used on production sites in order to artificially simulate defects in the gears and to operate them to collect vibration data. Data features are extracted from the frequency domain and time domain, and pseudolabeling is applied. There were fewer false alarms when applying R-LM, and it was possible to explain which features were responsible for equipment status changes, which improved field applicability. It was possible to detect changes in equipment conditions before a catastrophic failure, thus providing meaningful alarm and warning information, as well as further promising research topics.

Wind Turbine Gearbox Condition Monitoring Using Hybrid Attentions and Spatio-Temporal BiConvLSTM Network

Gearbox fault deterioration can significantly impact the safety, reliability, and efficiency of wind turbines, resulting in substantial economic losses for wind farms. However, current condition monitoring methods face challenges in effectively mining the hidden spatio-temporal features within SCADA data and establishing reasonable weight allocations for model input variables. To tackle these issues, we proposed a novel condition monitoring method for wind turbine gearboxes called HBCE, which integrated a feature-time hybrid attention mechanism (HA), the bidirectional convolutional long short-term memory networks (BiConvLSTM), and an improved exponentially weighted moving-average (iEWMA). Specifically, utilizing historical health SCADA data acquired through the modified Thompson tau data-cleaning algorithm, a normal behavior model (HA-BiConvLSTM) of gearbox was constructed to effectively extract the spatio-temporal features and learn normal behavior patterns. An iEWMA-based outlier detection approach was employed to set dynamic adaptive thresholds, and real-time monitor the prediction residuals of HA-BiConvLSTM to identify the early faults of gearbox. The proposed HBCE method was validated through actual gearbox faults and compared with conventional spatio-temporal models (i.e., CNN-LSTM and CNN&LSTM). The results illustrated that the constructed HA-BiConvLSTM model achieved superior prediction precision in terms of RMSE, MAE, MAPE, and R2, and the proposed method HBCE can effectively and reliably identify early anomalies of a wind turbine gearbox in advance.

Condition Monitoring Method for the Gearboxes of Offshore Wind Turbines Based on Oil Temperature Prediction

Traditional machine learning prediction methods usually only predict input parameters through a single model, so the problem of low prediction accuracy is common. Different predictive models extract different information for input, and combining different predictive models can make as much use as possible of all the information contained in the inputs. Therefore, this paper improves the existing oil temperature prediction method of offshore wind turbine gearboxes, and for the actual prediction effect of Supervisory Control And Data Acquisition (SCADA) data in this paper, Bayesian-optimized Light Gradient Boosting Machine (LightGBM) and eXtreme Gradient Boosting(XGBoost) machine learning models are selected to be combined. A method based on the Induced Ordered Weighted Average (IOWA) operator combination prediction model is thus proposed, with simulation results showing that the proposed model improves the accuracy of gearbox condition monitoring. The innovation of this article lies in considering the various negative impacts faced by actual offshore wind turbines and adopting a combination prediction model to improve the accuracy of gearbox condition monitoring.

Measuring instantaneous angular speed using a gear wheel as material measure to detect pitting damage during an endurance test

Gearbox condition monitoring is mostly carried out using accelerometers at the housing. The long transfer path interferes with the information on damaged gears. Therefore, new technologies such as measuring the instantaneous angular speed (IAS) are gaining interest. But these require constructive changes in the power-transmitting elements. Therefore, this contribution uses magnetoresistive (MR) sensors and a minimally invasive integration approach to measure IAS. Three sensor classes are integrated: accelerometers at the gearbox housing, MR sensors, which use a gear wheel as a material measure and MR sensors, which use an encoder magnet at the end of the shaft. These sensor concepts are introduced by Koch et al. 2022 [1] and applied to a 3-stage bevel helical gearbox in this contribution. The first results are on artificial tooth flank damage. Therefore, this contribution focuses on real fatigue pitting damage.A back-to-back test stand is set up for the endurance test. The tests are carried out with an overload load at a constant speed to generate fatigue pitting damage. The results are evaluated in the frequency domain by exploring the gear mesh frequency (GMF) and sidebands modulated with the shaft frequency of the damaged pinion. Results show that with all sensor concepts, the damages can be detected. Influences when using a gear wheel as a material measure are described for one measurement concept. A feature to compare the damage-specific information over the endurance test is introduced and the influence of the transfer path is evaluated through analysis of the relative rise of damage-specific amplitudes.

Multi‐component condition monitoring method for wind turbine gearbox based on adaptive noise reduction

AbstractWind turbine gearbox condition monitoring (C&M) is a key technology to promote wind farm maintenance cost reduction and power generation improvement. Existing gearbox C&M methods usually adopt the component‐by‐component modelling approach. Firstly, this approach is inefficient in modelling; secondly, due to the thermal conduction effect, abnormalities in one gearbox component usually affect other components, making it difficult to identify the source of faults. To solve these problems, a normal behaviour model (NBM) combining data adaptive noise reduction and an improved variational auto‐encoder (VAE) is proposed, which can monitor the operational condition of multiple components of one gearbox simultaneously and takes into account the correlation between components when warning of the specific abnormal component. As verified by practical cases, the method balances the modelling accuracy and efficiency of the multi‐component NBM and achieves effective early warning and accurate localization of gearbox abnormalities. The proposed model has lower false alarm and missed alarm rates compared to other single‐component and multi‐component NBMs.

Tram gearbox condition monitoring method based on trackside acoustic measurement

The article presents the genesis of the work to develop a method of diagnosing a tram transmission from the track position using acoustic signals. Significant influence of the damaged gearbox on acoustic phenomena in the vicinity of a tram line was shown, especially visible changes in psychoacoustic indicators. Due to the non-stationary nature of the acoustic signals, analyses of the microphone matrix were carried out using the empirical mode decomposition. The developed quantitative measure of individual IMFs served as a classifier in decision trees. For the developed CART type decision trees, the indicators of the effectiveness of the diagnosis were calculated, i.e., the level of unnecessary repairs and the level of undetected damage. Based on these results, the most effective tree was selected, which was used to develop the final, not yet developed, algorithm to diagnose the tram transmission without the need to mount the equipment on the vehicle.

Condition Monitoring of Spur Gear Box based on Acoustic Emission Signal Analysis

Abstract: Monitoring the condition of rotating machinery, such as gearbox is an important task in order to enhance its performance. Acoustic Emission (AE) and vibration analyses are some of the most accomplished techniques used for this purpose. Acoustic emission technique has the ability to detect the initial phase of component degradation. This paper presents the experimental investigation of gearbox condition using acoustic emission techniques. AE signals of gearbox under different conditions are acquired. AE signal parameters such as RMS, amplitude and rise time have provided information about the condition of the gearbox. Hence, AE technique can also be used for monitoring the gearbox.

Detection of Uniform Gearbox Wear in Induction Motors Based on the Analysis of Stray Flux Signals Through Statistical Time-Domain Features and Dimensionality Reduction Techniques

Gearboxes are core elements in power transmission systems. Although gearboxes are reliable and high-efficiency components, the occurrence of different faults is frequent since they are often subjected to adverse operating conditions. Classical gearbox condition monitoring approaches are based on the analysis of vibration and current motor signals and rely on the identification of specific fault-related frequency patterns. In this regard, this article proposes a novel diagnosis methodology based on the analysis of stray flux signals for detecting uniform wear in the gear teeth. The proposed methodology is based on the processing of the stray flux signals through feature calculation and extraction stages that lead to a high-performance signal characterization by estimating a set of statistical time domain-based features and then reducing the dimensionally by means of the principal component analysis and linear discriminant analysis techniques. Additionally, an automatic fault diagnosis is achieved through a neural network-based classifier for the detection and identification of uniform wear in a gearbox. The obtained results prove the potential of the proposal for its incorporation in condition maintenance programs in the industry, becoming an excellent alternative to classical approaches.

Gearbox fault diagnosis under nonstationary condition using nonlinear chirp components extracted from bearing force

The main challenges in gearbox condition monitoring and fault diagnosis are the heavy noises caused by harsh operating environments and the complicatednonstationary condition during the runtime. It is extremely difficult and even impossible to obtain sensitive faultcharacteristics through direct measurements. Thus, it is ofgreat significance of faultcharacteristic inversion based on the structure vibration transfer paths for complicated mechanical systems fault diagnosis. This paper proposes a gearbox fault diagnosis method under nonstationary condition through using nonlinear chirp components extracted from bearing force (BFNCC). In the proposed method, the bearing dynamic forces are first identified based on the vibration transfer function matrix, and the intrinsic signal components are then decomposed through a nonlinear chirp mode decomposition method. The proposed method improved the quality of vibration signals by removing the effect of the structure vibration transfer paths. In comparison with order tracking, the BFNCC is capable of clearly reflecting the magnitude increase phenomenon under gear fault condition. Numerical simulation and experimental studies show that the proposed method is effective for gear fault diagnosis under nonstationary condition. The proposed method is demonstrated to be superior to the existing approaches and robust to the location of measuring points, and thus shows potential in machinery fault diagnosis under the interference of complicated structure transfer paths.

A novel method for condition monitoring of wind turbine gearbox in wind farm

In this paper, the gearbox of wind turbine in a wind farm is taken as research object, and its operation condition monitoring model is established by using multivariable long-short term memory networks (LSTM). Firstly, parameters with high correlation are obtained by using maximum information coefficient (MIC) as the input vectors of monitoring model. Then, the oil temperature prediction model of gearbox is constructed based on LSTM network. The residual between actual value and predicted value of gearbox oil temperature is obtained. After that, a gearbox condition monitoring model is established by using residual sequence, exponential weighted moving average (EWMA), and kernel density estimation algorithm. The case analysis shows that the proposed method can carry out fault early warning about 15.7 hours in advance. Compared with univariate LSTM condition monitoring model and SVR condition monitoring model, it can find faults more timely and can be applied to fault early warning of wind turbines in wind farm.

Acoustics Based Monitoring and Diagnostics for the Progressive Deterioration of Helical Gearboxes

Gearbox condition monitoring (CM) plays a significant role in ensuring the operational reliability and efficiency of a wide range of critical industrial systems such as wind turbines and helicopters. Accurate and timely diagnosis of gear faults will improve the maintenance of gearboxes operating under sub-optimal conditions, avoid excessive energy consumption and prevent avoidable damages to systems. This study focuses on developing CM for a multi-stage helical gearbox using airborne sound. Based on signal phase alignments, Modulation Signal Bispectrum (MSB) analysis allows random noise and interrupting events in sound signals to be suppressed greatly and obtains nonlinear modulation features in association with gear dynamics. MSB coherence is evaluated for selecting the reliable bi-spectral peaks for indication of gear deterioration. A run-to-failure test of two industrial gearboxes was tested under various loading conditions. Two omnidirectional microphones were fixed near the gearboxes to sense acoustic information during operation. It has been shown that compared against vibration based CM, acoustics can perceive the responses of vibration in a larger areas and contains more comprehensive and stable information related to gear dynamics variation due to wear. Also, the MSB magnitude peaks at the first three harmonic components of gear mesh and rotation components are demonstrated to be sufficient in characterizing the gradual deterioration of gear transmission. Consequently, the combining of MSB peaks with baseline normalization yields more accurate monitoring trends and diagnostics, allowing the gradual deterioration process and gear wear location to be represented more consistently.

Fuzzy diagnostics for gearbox failures based on induction motor current and wavelet entropy

In this work, a strategy is proposed for the automatic diagnosis of failures in gearboxes using current signals from an induction motor. The stator currents were represented by the extended Park vector approach technique and decomposed by the wavelet packet transform. The calculation of the wavelet packet entropy promoted the distinction between broken tooth failures and the levels of severity of surface wear. The entropies of two wavelet details were used as inputs for a fuzzy inference for automatic classification of the gearbox condition. The experimental results presented a high rate of correctness in the fuzzy diagnosis, confirming the efficiency of the strategy for high rotation (60 Hz) and low rotation (20 Hz). The strategy presents simplicities related to the practical implementation and reduction of the amount of data analyzed.

Development of a wind turbine gearbox virtual load sensor using multibody simulation and artificial neural networks

A current development trend in wind energy is characterized by the installation of wind turbines (WT) with increasing rated power output. Higher towers and larger rotor diameters increase rated power leading to an intensification of the load situation on the drive train and the main gearbox. However, current main gearbox condition monitoring systems (CMS) do not record the 6‑degree of freedom (6-DOF) input loads to the transmission as it is too expensive. Therefore, this investigation aims to present an approach to develop and validate a low-cost virtual sensor for measuring the input loads of a WT main gearbox. A prototype of the virtual sensor system was developed in a virtual environment using a multi-body simulation (MBS) model of a WT drivetrain and artificial neural network (ANN) models. Simulated wind fields according to IEC 61400‑1 covering a variety of wind speeds were generated and applied to a MBS model of a Vestas V52 wind turbine. The turbine contains a high-speed drivetrain with 4‑points bearing suspension, a common drivetrain configuration. The simulation was used to generate time-series data of the target and input parameters for the virtual sensor algorithm, an ANN model. After the ANN was trained using the time-series data collected from the MBS, the developed virtual sensor algorithm was tested by comparing the estimated 6‑DOF transmission input loads from the ANN to the simulated 6‑DOF transmission input loads from the MBS. The results show high potential for virtual sensing 6‑DOF wind turbine transmission input loads using the presented method.

Fault early warning of wind turbine gearbox based on multi‐input support vector regression and improved ant lion optimization

AbstractGearbox oil temperature is one of the important indicators for gearbox condition monitoring and faults early warning. Accurately predicting the gearbox oil temperature change trend can maintain the gearbox in advance and ensure the safety and reliability of the wind turbine gearbox. The purpose of this article is to analyze the supervisory control and data acquisition (SCADA) data in wind turbines. A method based on multi‐input improved ant lion optimization and support vector regression (M‐IALO‐SVR) proposed, which can accurately predict the gearbox oil temperature. The prediction method is compared with back propagation neural network (BPNN) and ALO‐SVR methods to verify the effectiveness of the M‐IALO‐SVR method. To further analyze the prediction results, the 95% confidence interval processing is performed on the residuals of the prediction model, and then the trends of the mean and standard deviation of the moving window residuals are calculated. Testing SCADA data from a wind farm in northeast China, the test results show that when the gearbox is operating normally, the predicted value of the gearbox oil temperature follows the measured value very well. When the gearbox operates abnormally, its temperature deviates from the normal range, and the statistical characteristics of the residuals also change. According to the trend of the residuals statistical characteristics, the abnormal state of the gearbox can be found in time.