Quantitative Index and Abnormal Alarm Strategy Using Sensor-Dependent Vibration Data for Blade Crack Identification in Centrifugal Booster Fans

Health monitoring of wind turbine gearboxes has gained considerable attention as wind turbines become larger in size and move to more inaccessible locations. To improve the reliability, extend the lifetime of the turbines, and reduce the operation and maintenance cost caused by the gearbox faults, data-driven condition motoring techniques have been widely investigated, where various sensor monitoring data (such as power, temperature, and pressure, etc.) have been modeled and analyzed. However, wind turbines often work in complex and dynamic operating conditions, such as variable speeds and loads, thus the traditional static monitoring method relying on a certain fixed threshold will lead to unsatisfactory monitoring performance, typically high false alarms and missed detections. To address this issue, this paper proposes a reliable monitoring model for wind turbine gearboxes based on echo state network (ESN) modeling and the dynamic threshold scheme, with a focus on supervisory control and data acquisition (SCADA) vibration data. The aim of the proposed approach is to build the turbine normal behavior model only using normal SCADA vibration data, and then to analyze the unseen SCADA vibration data to detect potential faults based on the model residual evaluation and the dynamic threshold setting. To better capture temporal information inherent in monitored sensor data, the echo state network (ESN) is used to model the complex vibration data due to its simple and fast training ability and powerful learning capability. Additionally, a dynamic threshold monitoring scheme with a sliding window technique is designed to determine dynamic control limits to address the issue of the low detection accuracy and poor adaptability caused by the traditional static monitoring methods. The effectiveness of the proposed monitoring method is verified using the collected SCADA vibration data from a wind farm located at Inner Mongolia in China. The results demonstrated that the proposed method can achieve improved detection accuracy and reliability compared with the traditional static threshold monitoring method.

Download Full-text

Unsupervised Damage Detection for Offshore Jacket Wind Turbine Foundations Based on an Autoencoder Neural Network

Sensors ◽

10.3390/s21103333 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3333

Author(s):

Maria del Cisne Feijóo ◽

Yovana Zambrano ◽

Yolanda Vidal ◽

Christian Tutivén

Keyword(s):

Neural Network ◽

Wind Turbine ◽

Environmental Conditions ◽

Wind Farms ◽

Offshore Wind ◽

Offshore Wind Turbine ◽

Small Subset ◽

Scaled Model ◽

Vibration Data ◽

Large Water

Structural health monitoring for offshore wind turbine foundations is paramount to the further development of offshore fixed wind farms. At present time there are a limited number of foundation designs, the jacket type being the preferred one in large water depths. In this work, a jacket-type foundation damage diagnosis strategy is stated. Normally, most or all the available data are of regular operation, thus methods that focus on the data leading to failures end up using only a small subset of the available data. Furthermore, when there is no historical precedent of a type of fault, those methods cannot be used. In addition, offshore wind turbines work under a wide variety of environmental conditions and regions of operation involving unknown input excitation given by the wind and waves. Taking into account the aforementioned difficulties, the stated strategy in this work is based on an autoencoder neural network model and its contribution is two-fold: (i) the proposed strategy is based only on healthy data, and (ii) it works under different operating and environmental conditions based only on the output vibration data gathered by accelerometer sensors. The proposed strategy has been tested through experimental laboratory tests on a scaled model.

Download Full-text

SVM-Based Bearing Anomaly Identification with Self-Tuning Network-Fuzzy Robust Proportional Multi Integral and Smart Autoregressive Model

Applied Sciences ◽

10.3390/app11062784 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2784

Author(s):

Shahnaz TayebiHaghighi ◽

Insoo Koo

Keyword(s):

Machine Learning ◽

Variable Structure ◽

Rolling Element Bearing ◽

Crack Identification ◽

Original Signal ◽

Signal Modeling ◽

Residual Signal ◽

Average Accuracy ◽

Self Tuning ◽

The Difference

In this paper, the combination of an indirect self-tuning observer, smart signal modeling, and machine learning-based classification is proposed for rolling element bearing (REB) anomaly identification. The proposed scheme has three main stages. In the first stage, the original signal is resampled, and the root mean square (RMS) signal is extracted from it. In the second stage, the normal resampled RMS signal is approximated using the AutoRegressive with eXternal Uncertainty (ARXU) technique. Moreover, the nonlinearity of the bearing signal is solved using the combination of the ARXU and the machine learning-based regression, which is called AMRXU. After signal modeling by AMRXU, the RMS resampled signal is estimated using a combination of the proportional multi-integral (PMI) technique, the variable structure (VS) Lyapunov technique, and a self-tuning network-fuzzy system (SNFS). Finally, in the third stage, the difference between the original signal and the estimated one is calculated to generate the residual signal. A machine learning-based classification technique is utilized to classify the residual signal. The Case Western Reserve University (CWRU) dataset is used to evaluate anomaly identification performance of the proposed scheme. Regarding the experimental results, the average accuracy for REB crack identification is 98.65%, 97.7%, 97.35%, and 97.67%, respectively, when the motor torque loads are 0-hp, 1-hp, 2-hp, and 3-hp.

Download Full-text