Entropy Indicators: An Approach for Low-Speed Bearing Diagnosis

Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM

To reduce the levelized cost of wind energy, through the reduction in operation and maintenance costs, it is imperative that the wind turbine downtime is reduced through maintenance strategies based on condition monitoring. The standard approach toward this challenge is based on vibration monitoring, which requires the installation of specific tailored sensors that incur associated added costs. On the other hand, the life expectancy of wind parks built during the 1990s wind power boom is dwindling, and data-driven maintenance strategies issued from already accessible supervisory control and data acquisition (SCADA) data is an auspicious competitive solution because no additional sensors are required. Note that it is a major issue to provide fault diagnosis approaches built only on SCADA data, as these data were not established with the objective of being used for condition monitoring but rather for control capacities. The present study posits an early fault diagnosis strategy based exclusively on SCADA data and supports it with results on a real wind park with 18 wind turbines. The contributed methodology is an anomaly detection model based on a one-class support vector machine classifier; that is, it is a semi-supervised approach that trains a decision function that categorizes fresh data as similar or dissimilar to the training set. Therefore, only healthy (normal operation) data is required to train the model, which greatly expands the possibility of employing this methodology (because there is no need for faulty data from the past, and only normal operation SCADA data is needed). The results obtained from the real wind park show that this is a promising strategy.

Effective Identification and Localization of Single and Multiple Breathing Cracks in Beams under Gaussian Excitation Using Time-Domain Analysis

The output response of any intact oscillatory system subjected to a Gaussian excitation is also Gaussian in nature. On the contrary, when the system contains any type of underlying nonlinearity, the output signal is definitely non-Gaussian. In beam structures, the presence of fatigue-breathing cracks significantly influences the dynamic response characteristics under Gaussian excitation. The presence of such cracks alters the response to be nonlinear, and the non-Gaussianity of the system will arise. In order to examine the non-Gaussianity features and ability for the detection and localization of fatigue cracks, several breathing crack identification scenarios in beam-like structures are presented in this paper. The effects of single and multiple breathing cracks corresponding to different boundary conditions on the responses of beams are studied. The results are analyzed based on the higher-order time-domain transformations. Higher-order transformations, namely the skewness and kurtosis coefficients in addition to the Shannon entropy, are exploited to provide dynamic details about the response, which the conventional second-order statistics cannot show. The results exhibit that the proposed methods are robust and immune to noise and can detect and localize breathing cracks with different sensitivities.

Improved DBSCAN Spindle Bearing Condition Monitoring Method Based on Kurtosis and Sample Entropy

An improved density-based spatial clustering of applications with noise (IDBSCAN) analysis approach based on kurtosis and sample entropy (SE) is presented for the identification of operational state in order to provide accurate monitoring of spindle operation condition. This is because of the low strength of the shock signal created by bearing of precision spindle of misalignment or imbalanced load, and the difficulties in extracting shock features. Wavelet noise reduction begins by dividing the recorded vibration data into equal lengths. Features like kurtosis and entropy in the frequency domain are used to generate feature vectors that indicate the bearing operation state. IDBSCAN cluster analysis is then utilized to establish the ideal neighborhood radius (Eps) and the minimum number of objects contained within the neighborhood radius (MinPts) of the vector set, which are combined to identify the bearing operating condition features. Finally, utilizing data from the University of Cincinnati, the approach was validated and assessed, attaining a condition detection accuracy of 99.2%. As a follow-up, the spindle’s vibration characteristics were studied utilizing an unbalanced bearing’s load bench. Bearing state recognition accuracy was 98.4%, 98.4%, and 96.7%, respectively, under mild, medium, and overload circumstances, according to the results of the experimental investigation. Moreover, it shows that conditions of bearings under various unbalanced loads can be precisely monitored using the proposed method without picking up on specific sorts of failures.

Investigation of Isolation Forest for Wind Turbine Pitch System Condition Monitoring Using SCADA Data

Wind turbine pitch system condition monitoring is an active area of research, and this paper investigates the use of the Isolation Forest Machine Learning model and Supervisory Control and Data Acquisition system data for this task. This paper examines two case studies, turbines with hydraulic or electric pitch systems, and uses an Isolation Forest to predict failure ahead of time. This novel technique compared several models per turbine, each trained on a different number of months of data. An anomaly proportion for three different time-series window lengths was compared, to observe trends and peaks before failure. The two cases were compared, and it was found that this technique could detect abnormal activity roughly 12 to 18 months before failure for both the hydraulic and electric pitch systems for all unhealthy turbines, and a trend upwards in anomalies could be found in the immediate run up to failure. These peaks in anomalous behaviour could indicate a future failure and this would allow for on-site maintenance to be scheduled. Therefore, this method could improve scheduling planned maintenance activity for pitch systems, regardless of the pitch system employed.

Application of Adaptive MOMEDA with Iterative Autocorrelation to Enhance Weak Features of Hoist Bearings

Low-speed hoist bearings are characterized by fault features that are weak and difficult to extract. Multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) is an effective method for extracting periodic pulses in a signal. However, the decomposition effect of MOMEDA largely depends on the selected pulse period and filter length. To address these drawbacks of MOMEDA and accurately extract features from the vibration signal of a hoist bearing, an adaptive feature extraction method is proposed based on iterative autocorrelation (IAC) and MOMEDA. To automatically identify the pulse period, a new evaluation index named autocorrelation kurtosis entropy (AKE) was constructed to select the optimal IAC. To eliminate the influence of the filter length on the decomposition effect, an iterative MOMEDA strategy was designed to gradually enhance signal impulse features. The Case Western Reserve University bearing dataset and bearing data from a self-made hoisting test setup were used to verify the effectiveness of IAC-MOMEDA in extracting weak features. Moreover, the capability of IAC-MOMEDA for features extraction of normal bearing vibration signal was further confirmed by field test data.

A New Method Based on Time-Varying Filtering Intrinsic Time-Scale Decomposition and General Refined Composite Multiscale Sample Entropy for Rolling-Bearing Feature Extraction

The early fault diagnosis of rolling bearings has always been a difficult problem due to the interference of strong noise. This paper proposes a new method of early fault diagnosis for rolling bearings with entropy participation. First, a new signal decomposition method is proposed in this paper: intrinsic time-scale decomposition based on time-varying filtering. It is introduced into the framework of complete ensemble intrinsic time-scale decomposition with adaptive noise (CEITDAN). Compared with traditional intrinsic time-scale decomposition, intrinsic time-scale decomposition based on time-varying filtering can improve frequency-separation performance. It has strong robustness in the presence of noise interference. However, decomposition parameters (the bandwidth threshold and B-spline order) have significant impacts on the decomposition results of this method, and they need to be artificially set. Aiming to address this problem, this paper proposes rolling-bearing fault diagnosis optimization based on an improved coyote optimization algorithm (COA). First, the minimal generalized refined composite multiscale sample entropy parameter was used as the objective function. Through the improved COA algorithm, optimal intrinsic time-scale decomposition parameters based on time-varying filtering that match the input signal are obtained. By analyzing generalized refined composite multiscale sample entropy (GRCMSE), whether the mode component is dominated by the fault signal is determined. The signal is reconstructed and decomposed again. Finally, the mode component with the highest energy in the central frequency band is selected for envelope spectrum variation for fault diagnosis. Lastly, simulated and experimental signals were used to verify the effectiveness of the proposed method.