Gearbox Fault Research Articles

Multi-sensor gearbox fault diagnosis using generalized minimum entropy deconvolution and main frequency center extraction

Accurate diagnosis of gearbox faults is vital to maintain the stability and dependability of rotating machinery. In practical engineering scenarios, the installation of multiple sensors is often necessary to monitor numerous variables and gather extensive information. To effectively utilize the fault information from multiple sensors and improve fault diagnosis performance, this paper presents a gearbox fault diagnosis method using generalized minimum entropy deconvolution (GMED) and main frequency center extraction (MFCE). Firstly, the introduced GMED enhances the fault signals from multiple sensors through the maximization of standardized moments, offering advantages such as stability, wide applicability, and minimal parameter tuning requirements. Subsequently, the proposed MFCE is employed to extract features. MFCE selects main spectral lines and derives a novel feature metric named main frequency center. This not only further reduces the influence of interfering components, but also requires the extraction of only 2 n features (where n is the number of sensors) to achieve a high fault recognition rate, while remaining compatible with multiple classical classifiers. Finally, the effectiveness and robustness of the proposed method are demonstrated through experimental results on two gearbox fault datasets.

FASER: Fault-affected signal energy ratio for fault diagnosis of gearboxes under repetitive operating conditions

Vibration signal analysis is crucial for gearbox fault diagnosis, yet its inherent stochastic nature can challenge the identification of fault-induced changes amidst signal variability. This paper introduces a novel fault diagnosis approach, the Fault-Affected Signal Energy Ratio (FASER), designed to account for the uncertainty in vibration signals under repetitive operating conditions. The uncertainty is quantified using probability distributions of coefficients derived from Short-Time Fourier Transform (STFT) applied to normal state signals, employing Kernel Density Estimation and Kullback-Leibler divergence. This combined approach enables the quantification of uncertainty in signals with non-constant uncertainty, dependent on time and frequency, when converted to STFT. These distributions facilitate the assessment of the FASER in new signals extracted under synchronized operating conditions using our proposed method. This newly proposed FASER, accompanied by adaptive threshold to address feature randomness from STFT indices’ correlation, serves as a robust health indicator. Experimental validation demonstrates the effectiveness of the proposed method in accurate gearbox fault diagnosis under repetitive operating conditions, along with the capability to estimate fault severity levels.

Semi-supervised fault diagnosis of gearbox based on feature pre-extraction mechanism and improved generative adversarial networks under limited labeled samples and noise environment

Gearboxes are the most widely used component to transfer speed and power in many industries, and high precision gearbox fault diagnosis (FD) is pretty crucial for ensuring the safe operation of the machine. However, traditional FD methods often need a great quantity of labeled data, and are prone to noise interference in practical work, resulting in a relatively low diagnosis accuracy. With the intention of overcoming these problems, this paper proposes a semi-supervised FD approach based on feature pre-extraction mechanism and improved generative adversarial network (IGAN). First, the data is preprocessed by the feature pre-extraction mechanism based on wavelet transform. Then, limited labeled samples and a large number of unlabeled samples are sent to the IGAN model. Finally, two typical gearbox fault datasets are utilized to evaluate the feasibility and effectiveness of the proposed approach in limited labeled samples and noise environment. Trial results denote that the proposed approach has better diagnosis accuracy and anti-noise robustness than other approaches.

Self-Attention Parallel Fusion Network for Wind Turbine Gearboxes Fault Diagnosis

Self-Attention Parallel Fusion Network for Wind Turbine Gearboxes Fault Diagnosis

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.

An anomalous frequency band identification method utilising available healthy historical data for gearbox fault detection

Informative frequency band identification methods are used to automatically design bandpass filters to enhance fault signatures in vibration measurements. Blind and targeted features can be used to guide the frequency band selection process. Blind features’ performance is impeded when there are dominant non-stationary extraneous components, whereas targeted features’ performance is impeded when the characteristic frequency of the machine component is unknown, erroneously estimated or the damaged component is not targeted. An anomalous frequency band identification method is proposed that utilises the available historical data to detect weak damage components that deviate from the baseline or reference condition. This makes it possible to ignore dominant extraneous components that are also present in the historical dataset. The proposed method is analysed and compared against conventional and feature ratio methods on numerical and experimental datasets. The results demonstrate that the proposed method has much potential for identifying informative frequency bands for fault detection.

A structurally re-parameterized convolution neural network-based method for gearbox fault diagnosis in edge computing scenarios

Gearboxes operate in harsh environments. Cloud-based techniques have been previously adopted for fault diagnosis in Gearboxes. Cloud-based fault diagnosis methods are prone to time delays and loss of information. Therefore, edge computing-based fault diagnosis becomes an option. However, with limited hardware resources for edge devices, balancing the diagnostic capabilities of the model with operating performance becomes a challenge. This paper proposes a lightweight convolutional neural network for gearbox fault diagnosis in edge computing scenarios to achieve an accurate diagnosis and lightweight deployment of models. By constructing the Mel-Frequency Cepstral Coefficients (MFCC) feature matrix of input data, the methodology can suppress noise interference and improve diagnostic accuracy. Based on the structural re-parameterization, the model structure transforms from multiple branches at training time to a single branch at inference time. This improves the inference speed of the model and reduces the hardware cost when the model is deployed while ensuring that the diagnostic capability of the model remains unchanged. Validation experiments were conducted on a public dataset and a custom experimental device, using the NVIDIA Jetson Xavier NX kit as the edge computing platform. According to the experiment result, after extracting the MFCC feature matrix, the average diagnostic accuracy rate in the noisy environment of the presented methodology is improved by 12.22% and 9.44%, respectively. After structural re-parameterization, the Memory of the model decreases by 52.58%, and the inference speed is increased by 38.83%.

Research on gearbox compound fault diagnosis method and system development based on entire gearbox health maintenance

In general, gearbox is prone to occur compound fault due to its harsh working environment and its fault vibration signal contains multi-components which correspond to each gearbox parts. As the multi-components are often coupled with each other and accompanied by strong noise which brings great difficulties to diagnose fault, however, the existing diagnosis methods are mainly applied on single fault rather than the entire gearbox health maintenance, therefore, this paper presents a gearbox compound fault diagnosis method and develops a diagnosis system which has potential value for gearbox health maintenance. In specific, on account of the morphological difference between multi-components, this paper uses resonance sparse signal decomposition (RSSD) to decompose the fault vibration signal into high and low resonance components respectively for achieving gearbox compound fault separation. Furthermore, as for low resonance component containing rolling bearing fault information, a weak fault feature extraction algorithm based on singular value decomposition (SVD) and cepstrum pre-whitening stochastic resonance is proposed, besides, aiming at the high resonance component containing gear fault information, an early gear fault warning algorithm based on local mean decomposition and two-dimensional approximate entropy of chaotic oscillator is also given. Finally, a gearbox fault diagnosis system, which has the ability such as the gearbox vibration signal acquisition, fault indicator warning, health status evaluation, fault signal storage is developed. Simulation validation and comparison prove the effectiveness of proposed method in this paper.

Optimization of Gearbox Fault Detection Method Based on Deep Residual Neural Network Algorithm.

Because of its long running time, complex working environment, and for other reasons, a gear is prone to failure, and early failure is difficult to detect by direct observation; therefore, fault diagnosis of gears is very necessary. Neural network algorithms have been widely used to realize gear fault diagnosis, but the structure of the neural network model is complicated, the training time is long and the model is not easy to converge. To solve the above problems and combine the advantages of the ResNeXt50 model in the extraction of image features, this paper proposes a gearbox fault detection method that integrates the convolutional block attention module (CBAM). Firstly, the CBAM is embedded in the ResNeXt50 network to enhance the extraction of image channels and spatial features. Secondly, the different time-frequency analysis method was compared and analyzed, and the method with the better effect was selected to convert the one-dimensional vibration signal in the open data set of the gearbox into a two-dimensional image, eliminating the influence of the redundant background noise, and took it as the input of the model for training. Finally, the accuracy and the average training time of the model were obtained by entering the test set into the model, and the results were compared with four other classical convolutional neural network models. The results show that the proposed method performs well both in fault identification accuracy and average training time under two working conditions, and it also provides some references for existing gear failure diagnosis research.

Morphological component analysis under non-convex smoothing penalty framework for gearbox fault diagnosis

The sparse representation methodology has been identified to be a promising tool for gearbox fault diagnosis. The core is how to precisely reconstruct the fault signal from noisy monitoring signals. The non-convex penalty has the ability to induce sparsity more efficiently than convex penalty. However, the introduction of non-convex penalty usually influences the convexity of the model, resulting in the unstable or sub-optimal solution. In this paper, we propose the non-convex smoothing penalty framework (NSPF) and combine it with morphological component analysis (MCA) for gearbox fault diagnosis. The proposed NSPF is a unify penalty construction framework, which contains many classical penalty while a new set of non-convex smoothing penalty functions can be generated. These non-convex penalty can guarantee the convexity of the objective function while enhancing the sparsity, thus the global optimal solution can be acquired. The simulation and engineering experiments validate that the NSPF enjoys more reconstruction precision compared to the existing penalties.

Machinery fault diagnosis using multi-scale feature focused network and adaptive cost-sensitive loss towards imbalanced dataset

The current deep learning based machinery fault diagnosis models still face challenges in effectively capturing rich multi-scale feature information and dynamically compensating training loss when dealing with imbalanced dataset. This paper presents a novel approach for machinery fault diagnosis using multi-scale feature focused network and adaptive cost-sensitive loss. Firstly, a multi-scale feature focused network is constructed with improved multi-scale CNN and point-wise attention mechanism module, in which the former can synthetically fuse the features at different scales to expand the coverage of the equivalent receptive field, and the latter can further refine fine-grained features and filter out irrelevant feature interference. Then, an adaptive cost-sensitive loss function is designed to adjust the cost matrix in the training process, dynamically assigning more loss weights for small samples that are difficult to distinguish. The experimental results of planetary gearbox fault diagnosis demonstrate that the proposed approach exhibits superior diagnostic performance compared to other existing methods.

Application of improved bubble entropy and machine learning in the adaptive diagnosis of rotating machinery faults

This paper proposes an improved bubble entropy algorithm called Improved Hierarchical Refined Composite Multiscale Multichannel Bubble Entropy (IHRCMMCBE) to characterize the fault characteristics of rotating machinery. By introducing the refined composite multiscale analysis algorithm, the improved hierarchical decomposition algorithm, and the multi-channel data analysis method, the bubble entropy algorithm can more fully characterize the fault characteristics. Then, this method is combined with the machine learning algorithm to realize automatic fault diagnosis of rotating machinery. Multi-Cluster Feature Selection (MCFS) is used for feature selection to screen out useless features and improve feature extraction efficiency and feature quality. The MCFS method has excellent performance and does not need parameters, so it is suitable for adaptive fault diagnosis. Meanwhile, the EigenClass classifier using the concept of generalized eigenvalue is used to realize fault recognition. Besides, the recently proposed Gorilla Troops Optimizer (GTO) algorithm is used to improve EigenClass, and a GTO-optimized EigenClass (GTO-EigenClass) classifier is proposed to adaptively select parameters and achieve adaptive fault identification. The proposed fault diagnosis method of rotating machinery based on the improved bubble entropy is independent of data and application scenarios and is hardly affected by subjective factors. The ablation experiment proves the effectiveness of each improvement of bubble entropy. Also, the performance verification experiments and the comparative experiments prove that the method can effectively characterize different types of rotating machinery, different fault types, fault degrees, and composite faults, and it can achieve higher calculation efficiency and classification accuracy. When the sample length is 1024, the average accuracy of bearing and gearbox fault identification can reach 97.85 % and 97.57 % respectively, and when the sample length is 2048, the identification accuracy can reach 100 %.

Domain knowledge-informed synthetic fault sample generation with health data map for cross-domain planetary gearbox fault diagnosis

Extensive research has been conducted on fault diagnosis of planetary gearboxes using vibration signals and deep learning (DL) approaches. However, DL-based methods are susceptible to the domain shift problem caused by varying operating conditions of the gearbox. Although domain adaptation and data synthesis methods have been proposed to overcome such domain shifts, they are often not directly applicable in real-world situations where only healthy data is available in the target domain. To tackle the challenge of extreme domain shift scenarios where only healthy data is available in the target domain, this paper proposes two novel domain knowledge-informed data synthesis methods utilizing the health data map (HDMap). The two proposed approaches are referred to as scaled CutPaste and FaultPaste. The HDMap is used to physically represent the vibration signal of the planetary gearbox as an image-like matrix, allowing for visualization of fault-related features. CutPaste and FaultPaste are then applied to generate faulty samples based on the healthy data in the target domain, using domain knowledge and fault signatures extracted from the source domain, respectively. In addition to generating realistic faults, the proposed methods introduce scaling of fault signatures for controlled synthesis of faults with various severity levels. A case study is conducted on a planetary gearbox testbed to evaluate the proposed approaches. The results show that the proposed methods are capable of accurately diagnosing faults, even in cases of extreme domain shifts, and can estimate the severity of faults that have not been previously observed in the target domain.

Fault Detection Method for Wind Turbine Generators Based on Attention-Based Modeling

Aiming at the problem that existing wind turbine gearbox fault prediction models often find it difficult to distinguish the importance of different data frames and are easily interfered with by non-important and irrelevant signals, thus causing a reduction in fault diagnosis accuracy, a wind turbine gearbox fault prediction model based on the attention-weighted long short-term memory network (AW-LSTM) is proposed. Specifically, the gearbox vibration signal is decomposed by empirical modal decomposition (EMD), to contain seven different frequency components and one residual component. The decomposed signal is passed through a four-layer LSTM network, to extract the fault features. The attention mechanism is introduced, to reweight the hidden states, in order to strengthen the attention to the important features. The proposed method captures the intrinsic long-term temporal correlation of timing gearbox signals through a long short-term memory network, and resorts to recursive attentional weighting, to efficiently distinguish the contribution of different frames and to exclude the influence of irrelevant or interfering data on the model. The results show that the proposed AW-LSTM wind turbine gearbox fault prediction model has an inference time of 36 s on two publicly available wind turbine fault detection datasets, with a root mean square error of 1.384, an average absolute error of 0.983, and an average absolute percentage error of 9.638, and that the AW-LSTM prediction model is able to efficiently extract the characteristics of wind turbine gearbox faults, with a shorter inference time and better fault prediction.

Research on gearbox fault detection model based on ridge regression and decision tree

Gearbox is widely used in mechanical equipment and plays an important role in mechanical transmission. Therefore, it is necessary to detect and diagnose the fault of the gearbox in time. This paper needs to establish a fault detection model of the gearbox to detect whether the gearbox is in a fault state. Because the result can only be yes or no, the ridge regression model is first established. However, because the difference between the original sample data is not obvious, the accuracy of the obtained ridge regression model is low. Therefore, this study extracts the features of the data of the four parts, and defines five indicators: effective value, pulse index, skewness index, margin index and kurtosis index. The decision tree model is established with 70 % of the sample data. Firstly, the depth of the largest tree is set to 5. Secondly, the importance of the feature is determined according to the size of the Gini value, and the fault detection decision tree model is constructed. Finally, the model is tested with 30 % of the test data, and the accuracy is 91.17 %. The precision rate is 88.9 %, and the recall rate is 94.12 %. It is considered that the model is more reliable.

An attention mechanism-guided domain adversarial network for gearbox fault diagnosis under different operating conditions

In recent years, transfer learning has been widely used in mechanical fault diagnosis with some achievements. However, most transfer learning methods do not perform well in diagnosis when the speed and load change simultaneously. Inspired by the adversarial learning mechanism, a transfer learning method named attention mechanism-guided domain adversarial network (AMDAN) is proposed in this paper. AMDAN regards the convolutional neural networks (CNNs) as the generator of the domain adversarial network to learn mutually invariant features and the domain classifier as the discriminator of the domain adversarial network. Attention mechanism is introduced to take into account the interchannel and intraspace feature fusion to improve the training efficiency. Then, multi-kernel maximum mean discrepancy (MK-MMD) is used to measure the distance of different feature spaces to achieve domain alignment. Finally, the superiority of AMDAN is verified by two sets of gear fault diagnosis experiments. The experimental results show that AMDAN has the highest classification accuracy and the strongest generalization ability compared with other methods.

Multiview Feature Selection With Information Complementarity and Consensus for Fault Diagnosis

Feature selection plays a critical role in data-driven fault diagnosis. Existing works often perform feature selection on a single overcomplete feature pool that is collected from various feature extraction approaches, such as signal processing and deep learning. However, simple concatenation of these “multiview” features may neglect the inherent properties and cross-feature correlations, often leading to ineffectiveness in feature selection for fault diagnosis. Therefore, a multiview feature selection with information complementarity and consensus (MFSICC) is proposed in this article to efficiently select relevant features for fault diagnosis. In particular, both complementary and consensus properties that are shared among the multiview features are incorporated based on a structured sparsity learning model. Besides, an iterative algorithm is proposed to solve the MFSICC problem with theoretically approved convergence. Experiments on bearing and gearbox fault diagnosis with real-world datasets validate the effectiveness of MFSICC. Important model parameters and empirical convergence are also discussed to facilitate practical use.

An adaptive selective ensemble algorithm for fault classification

With the aim of improving the classification performance of a single extreme learning machine (ELM) for fault diagnosis, an adaptive selective ensemble classification algorithm is proposed based on the idea of ensemble learning. The proposed algorithm achieves better classification performance than a single model and the selected ELM subnetworks are selected adaptively and the ensemble weights of selected ELM subnetworks are calculated adaptively, which avoids the complex process of manually selecting subnetworks and calculating ensemble weights. First, a regularized error weight adjustment ELM is constructed by introducing regularization parameters and error weight adjustment matrix to a standard ELM, where the error weight adjustment matrix is obtained by the method of adaptive Gaussian kernel density estimation. Then, discrepancy subnetworks are constructed using six different activation functionsand the ensemble weights of subnetworks are obtained adaptively according to the normalized ratio of mean and variance of subnetwork F-scores to achieve the ensemble of subnetworks. Finally, the adaptive selective ensemble classification algorithm is validated using the UCI dataset and experimental acoustic emission signals of gearbox faults. The results show that the adaptive selective ensemble method can improve the stability and accuracy of classification algorithms and the achieved classification accuracy for experimental acoustic emission was 0.9773.

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.

An Improved Coupled Dynamic Modeling for Exploring Gearbox Vibrations Considering Local Defects

Gearbox is a key part in machinery, in which gear, shaft and bearing operate together to transmit motion and power. The wide usage and high failure rate of gearbox make it attract much attention on its health monitoring and fault diagnosis. Dynamic modeling can study the mechanism under different faults and provide theoretical foundation for fault detection. However, current commonly used gear dynamic model usually neglects the influence of bearing and shaft, resulting in incomplete understanding on gearbox fault diagnosis especially under the effect of local defects on gear and shaft. To address this problem, an improved gear-shaft-bearing-housing dynamic model is proposed to reveal the vibration mechanism and responses considering shaft whirling and gear local defects. Firstly, an eighteen degree-of-freedom gearbox dynamic model is proposed, taking into account the interaction among gear, bearing and shaft. Secondly, the dynamic model is iteratively solved. Then, vibration responses are expounded and analyzed considering gear spalling and shaft crack. Numerical results show that the gear mesh frequency and its harmonics have higher amplitude through the spectrum. Vibration RMS and the shaft rotating frequency increase with the spalling size and shaft crack angle in general. An experiment is designed to verify the rationality of the proposed gearbox model. Lastly, comprehensive analysis under different spalling size and shaft crack angle are analyzed. Results show that when spalling size and crack angle is lager, RMS and the amplitude of shaft rotating frequency will not increase linearly. The dynamic model can accurately simulate the vibration of gear transmission system, which is helpful to gearbox fault diagnosis.