scholarly journals A Parameter Selection Method for Wind Turbine Health Management through SCADA Data

2017 ◽  
Author(s):  
Mian Du ◽  
Jun Yi ◽  
Peyman Mazidi ◽  
Lin Cheng ◽  
Jianbo Guo
Keyword(s):  
Probability Distribution ◽  
Mutual Information ◽  
Wind Turbine ◽  
Health Management ◽  
Estimation Method ◽  
Failure Detection ◽  
Health Condition ◽  
Parameter Selection ◽  
Machine Learning Techniques ◽  
Physical Knowledge

More and more works are using machine learning techniques while adopting supervisory control and data acquisition (SCADA) system for wind turbine anomaly or failure detection. While parameter selection is important for modelling a wind turbine’s health condition, only a few papers have been published focusing on this issue and in those papers interconnections among sub-components in a wind turbine are used to address this problem. However, merely the interconnections for decision making sometimes is too general to provide a parameter list considering the differences of each SCADA dataset. In this paper, a method is proposed to provide more detailed suggestions on parameter selection based on mutual information. Moreover, after proving that Copula, a multivariate probability distribution for which the marginal probability distribution of each variable is uniform is capable of simplifying the estimation of mutual information, an empirical copula based mutual information estimation method (ECMI) is introduced for an application. After that, a real SCADA dataset is adopted to test the method, and the results show the effectiveness of the ECMI in providing parameter selection suggestions when physical knowledge is not accurate enough.

scholarly journals A Parameter Selection Method for Wind Turbine Health Management through SCADA Data

Energies ◽  
2017 ◽  
Vol 10 (2) ◽  
pp. 253 ◽  
Author(s):  
Mian Du ◽  
Jun Yi ◽  
Peyman Mazidi ◽  
Lin Cheng ◽  
Jianbo Guo
Keyword(s):  
Wind Turbine ◽  
Health Management ◽  
Selection Method ◽  
Parameter Selection

scholarly journals Vibration Analysis and Time Series Prediction for Wind Turbine Gearbox Prognostics

2020 ◽  
Vol 4 (3) ◽  
Author(s):  
Sajid Hussain ◽  
Hossam A. Gabbar
Keyword(s):  
Wind Turbine ◽  
Fuzzy Inference ◽  
Health Management ◽  
Time Series Prediction ◽  
Health Condition ◽  
Wind Turbine Gearbox ◽  
Data Set ◽  
Inference System ◽  
Monitoring Index ◽  
Prediction Techniques

Multiple premature failures of a gearbox in a wind turbine pose a high risk of increasing the operational and maintenance costs and decreasing the profit margins. Prognostics and health management (PHM) techniques are widely used to assess the current health condition of the gearbox and project it in future to predict premature failures. This paper proposes such techniques for predicting gearbox health condition index extracted from the vibration signals. The progression of the monitoring index is predicted using two different prediction techniques, adaptive neuro-fuzzy inference system (ANFIS) and nonlinear autoregressive model with exogenous inputs (NARX). The proposed prediction techniques are evaluated through sun-spot data-set and applied on vibration based health related monitoring index calculated through psychoacoustic phenomenon. A comparison is given for their prediction accuracy. The results are helpful in understanding the relationship of machine conditions, the corresponding indicating features, the level of damage/degradation, and their progression.

scholarly journals Azure machine learning studio and SCADA data for failure detection and prediction purposes: A case of wind turbine generator

2021 ◽  
Vol 1201 (1) ◽  
pp. 012086
Author(s):  
A El-Menshawy ◽  
Z Gul ◽  
I El-Thalji
Keyword(s):  
Machine Learning ◽  
Wind Turbine ◽  
Failure Detection ◽  
Health Condition ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Turbine Generator ◽  
Wind Turbine Generator ◽  
Boosted Decision Tree ◽  
Potential Benefits

Abstract Most industrial systems have supervisory control and data acquisition (SCADA) systems that collect and store process parameters. SCADA data is seen as a valuable source to get and extract insights about the asset health condition and associated maintenance operations. It is still unclear how appliable and valid insights SCADA data might provide. The purpose of this paper is to explore the potential benefits of SCADA data for maintenance purposes and discuss the limitations from a machine learning perspective. In this paper, a two-year SCADA data related to a wind turbine generator is extracted and analysed using several machine learning algorithms, i.e., two-class boosted decision tree, two-class decision forest, k-means clustering on Azure ML learning studio. It is concluded that the SCADA data can be useful for failure detection and prediction once rich training data is given. In a failure prediction context, data richness means ensuring that fault features are presented in the training data. Moreover, the logs file can be used as labelled data to supervise some algorithms once they are reported in a more rigorous manner (timing, description).

Machine Learning Applications for a Wind Turbine Blade under Continuous Fatigue Loading

2013 ◽  
Vol 588 ◽  
pp. 166-174 ◽  
Author(s):  
Nikolaos Dervilis ◽  
M. Choi ◽  
Ifigeneia Antoniadou ◽  
K.M. Farinholt ◽  
S.G. Taylor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Wind Turbine ◽  
Early Stage ◽  
Turbine Blades ◽  
Failure Detection ◽  
Fatigue Loading ◽  
Machine Learning Techniques ◽  
Wind Turbine Blades ◽  
Machine Learning Applications ◽  
Blade Failure

Structural health monitoring (SHM) systems will be one of the leading factors in the successful establishment of wind turbines in the energy arena. Detection of damage at an early stage is a vital issue as blade failure would be a catastrophic result for the entire wind turbine. In this study the SHM analysis will be based on experimental measurements of vibration analysis, extracted of a 9m CX-100 blade under fatigue loading. For analysis, machine learning techniques utilised for failure detection of wind turbine blades will be applied, like non-linear Neural Networks, including Auto-Associative Neural Network (AANN) and Radial Basis Function (RBF) networks models.

scholarly journals Fleet Monitoring and Diagnostics Framework Based on Digital Twin of Aero-Engines

2018 ◽  
Author(s):  
Valentina Zaccaria ◽  
Mikael Stenfelt ◽  
Ioanna Aslanidou ◽  
Konstantinos G. Kyprianidis
Keyword(s):  
Health Management ◽  
Detection System ◽  
Failure Detection ◽  
Optimal Operation ◽  
Fault Isolation ◽  
Performance Model ◽  
Machine Learning Techniques ◽  
Adaptive Models ◽  
Challenges And Opportunities ◽  
Aero Engines

Monitoring aircraft performance in a fleet is fundamental to ensure optimal operation and promptly detect anomalies that can increase fuel consumption or compromise flight safety. Accurate failure detection and life prediction methods also result in reduced maintenance costs. The major challenges in fleet monitoring are the great amount of collected data that need to be processed and the variability between engines of the fleet, which requires adaptive models. In this paper, a framework for monitoring, diagnostics, and health management of a fleet of aircrafts is proposed. The framework consists of a multi-level approach: starting from thresholds exceedance monitoring, problematic engines are isolated, on which a fault detection system is then applied. Different methods for fault isolation, identification, and quantification are presented and compared, and the related challenges and opportunities are discussed. This conceptual strategy is tested on fleet data generated through a performance model of a turbofan engine, considering engine-to-engine and flight-to-flight variations and uncertainties in sensor measurements. Limitations of physics-based methods and machine learning techniques are investigated and the needs for fleet diagnostics are highlighted.

Research on the Distributed Characteristics of the Delay for Network Coding Based Real-Time Multicast in MANETs

2014 ◽  
Vol 530-531 ◽  
pp. 768-772
Author(s):  
Guo Ping Tan ◽  
Lin Feng Tan ◽  
Lei Cao ◽  
Mei Yan Ju
Keyword(s):  
Maximum Likelihood ◽  
Probability Distribution ◽  
Network Coding ◽  
Real Time ◽  
Lognormal Distribution ◽  
Ad Hoc ◽  
Estimation Method ◽  
Likelihood Estimation ◽  
Actual Distribution ◽  
Delay Distribution

For the study of the applications of partial network coding based real-time multicast protocol (PNCRM) in Mobile Ad hoc networks, the researches should be developed in the probability distribution of delay. In this paper, NS2 is used to obtain the delay of data packets through simulations. Because the delay does not obey the strict normal distribution, the maximum likelihood estimate method based on the lognormal distribution is used to process the data. Using MATLAB to obtain the actual distribution of the natural logarithm of delay, then drawing the delay distribution with the maximum likelihood estimation method based on the lognormal distribution, the conclusion that the distributions obtained by the above mentioned methods are basically consistent can be obtained. So the delay distribution of PNCRM meets the lognormal distribution and the characteristic of delay probability distribution can be estimated.

scholarly journals Health Condition Estimation of Bearings with Multiple Faults by a Composite Learning-Based Approach

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4424
Author(s):  
Udeme Inyang ◽  
Ivan Petrunin ◽  
Ian Jennions
Keyword(s):  
Fault Diagnosis ◽  
Health Management ◽  
Network Models ◽  
Health Condition ◽  
Limited Attention ◽  
Neural Network Models ◽  
Multiple Fault ◽  
Multiple Faults ◽  
Multiple Fault Diagnosis ◽  
Non Gaussian

Bearings are critical components found in most rotating machinery; their health condition is of immense importance to many industries. The varied conditions and environments in which bearings operate make them prone to single and multiple faults. Widespread interest in the improvements of single fault diagnosis meant limited attention was spent on multiple fault diagnosis. However, multiple fault diagnosis poses extra challenges due to the submergence of the weak fault by the strong fault, presence of non-Gaussian noise, coupling of the frequency components, etc. A number of existing convolutional neural network models operate on a distinct feature that is not enough to assure reliable results in the presence of these challenges. In this paper, extended feature sets in three homogenous deep learning models are used for multiple fault diagnosis. This ensures a measure of diversity is introduced to the health management dataset to obtain complementary solutions from the models. The outputs of the models are fused through blending ensemble learning. Experiments using vibration datasets based on bearing multiple faults show an accuracy of 98.54%, with an improvement of 2.74% in the overall effectiveness over the single models. Compared with other technologies, the results show that this approach provides an improved generalized diagnostic capability.

Sign in / Sign up

Export Citation Format

Share Document