Fault Monitoring of Wind Turbine Generator Brushes: A Data-Mining Approach

2012 ◽  
Vol 134 (2) ◽  
Author(s):  
Anoop Verma ◽  
Andrew Kusiak
Keyword(s):  
Data Mining ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Turbine Generator ◽  
Wind Turbine Generator ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
Carbon Brushes ◽  
Critical Components ◽  
Mining Algorithms

Components of wind turbines are subjected to asymmetric loads caused by variable wind conditions. Carbon brushes are critical components of the wind turbine generator. Adequately maintaining and detecting abnormalities in the carbon brushes early is essential for proper turbine performance. In this paper, data-mining algorithms are applied for early prediction of carbon brush faults. Predicting generator brush faults early enables timely maintenance or replacement of brushes. The results discussed in this paper are based on analyzing generator brush faults that occurred on 27 wind turbines. The datasets used to analyze faults were collected from the supervisory control and data acquisition (SCADA) systems installed at the wind turbines. Twenty-four data-mining models are constructed to predict faults up to 12 h before the actual fault occurs. To increase the prediction accuracy of the models discussed, a data balancing approach is used. Four data-mining algorithms were studied to evaluate the quality of the models for predicting generator brush faults. Among the selected data-mining algorithms, the boosting tree algorithm provided the best prediction results. Research limitations attributed to the available datasets are discussed.

Prediction of Status Patterns of Wind Turbines: A Data-Mining Approach

2011 ◽  
Vol 133 (1) ◽  
Author(s):  
Andrew Kusiak ◽  
Anoop Verma
Keyword(s):  
Data Mining ◽  
Wind Turbines ◽  
Association Rule ◽  
Performance Monitoring ◽  
Prediction Models ◽  
Rule Mining ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
The Status ◽  
Mining Algorithms

This paper presents the application of data-mining techniques for identification and prediction of status patterns in wind turbines. Early prediction of status patterns benefits turbine maintenance by indicating the deterioration of components. An association rule mining algorithm is used to identify frequent status patterns of turbine components and systems that are in turn predicted using historical wind turbine data. The status patterns are predicted at six time periods spaced at 10 min intervals. The prediction models are generated by five data-mining algorithms. The random forest algorithm has produced the best prediction results. The prediction results are used to develop a component performance monitoring scheme.

A Data Mining Approach for Generation of Control Signatures

2002 ◽  
Vol 124 (4) ◽  
pp. 923-926 ◽  
Author(s):  
Andrew Kusiak
Keyword(s):  
Data Mining ◽  
Metal Forming ◽  
Rough Set Theory ◽  
Decision Rules ◽  
Forming Process ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
Metal Forming Process ◽  
Material Forming ◽  
Mining Algorithms

Data mining offers methodologies and tools for data analysis, discovery of new knowledge, and autonomous process control. This paper introduces basic data mining algorithms. An approach based on rough set theory is used to derive associations among control parameters and the product quality in the form of decision rules. The model presented in the paper produces control signatures leading to good quality products of a metal forming process. The computational results reported in the paper indicate that data mining opens a new avenue for decision-making in material forming industry.

Cyclostationary Analysis of a Faulty Bearing in the Wind Turbine

2017 ◽  
Vol 139 (3) ◽  
Author(s):  
Zhiyong Ma ◽  
Yibing Liu ◽  
Dameng Wang ◽  
Wei Teng ◽  
Andrew Kusiak
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Vibration Signal ◽  
Economic Loss ◽  
Turbine Generator ◽  
Bearing Faults ◽  
Outer Race ◽  
Wind Turbine Generator ◽  
Cyclic Frequency ◽  
Fault Features

Bearing faults occur frequently in wind turbines, thus resulting in an unplanned downtime and economic loss. Vibration signal collected from a failing bearing exhibits modulation phenomenon and “cyclostationarity.” In this paper, the cyclostationary analysis is utilized to the vibration signal from the drive-end of the wind turbine generator. Fault features of the inner and outer race become visible in the frequency–cyclic frequency plane. Such fault signatures can not be produced by the traditional demodulation methods. Analysis results demonstrate effectiveness of the cyclostatonary analysis. The disassembled faulty bearing visualizes the fault.

scholarly journals Prediction for rice yield using data mining approach in Ranga Reddy district of Telangana, India

2021 ◽  
Vol 23 (2) ◽  
pp. 242-248
Author(s):  
BABY AKULA ◽  
R.S.PARMAR ◽  
M. P. RAJ ◽  
K. INDUDHAR REDDY
Keyword(s):  
Data Mining ◽  
Logistic Model ◽  
Yield Data ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
Rice Yields ◽  
Using Data ◽  
Mlp Classifier ◽  
Mining Algorithms ◽  
Best Fit

In order to explore the possibility of crop estimation, data mining approach being multidisciplinary was followed. The district of Ranga Reddy, Telangana State, India has been chosen for the study and its year wise average yield data of rice and daily weather over a period of 31 years i.e. from 1988-2019 (30th to 47th Standard Meteorological Weeks). Data mining tool WEKA (V3.8.1). Min- Max Normalization technique followed by Feature Selection algorithm, ‘cfsSubsetEval’ was also adopted to improve quality and accuracy of data mining algorithms. Thus, after cleaning and sorting of data, five classifiers viz., Logistic, MLP (Multi Layer Perceptron), J48 Classifier, LMT (Logistic Model Trees) and PART Classifier were employed over the trained data. The results indicated that the function based and tree based models have better performance over rule based model. In case of function based two models examined, viz., Logistic and MLP, the later performed better over Logistic model. Between tree based two models, LMT performed better over J48. Thus, MLP classifier model found to be the best fit model in predicting rice yields as it recorded an accuracy of 74.19 %, sensitivity of 0.742 and precision of 0.743 as compared with other models. The MLP has also achieved the highest F1 score of (0.742) and MCC (0.581).

scholarly journals Evaluation of wind potential for an optimum choice of wind turbine generator on the sites of Lomé, Accra, and Cotonou located in the gulf of Guinea

2016 ◽  
Vol 5 (3) ◽  
pp. 211-223 ◽  
Author(s):  
Akim Adekunlé Salami ◽  
Ayité Sénah Akoda Ajavon ◽  
Mawugno Koffi Kodjo ◽  
Koffi-Sa Bedja
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Wind Farms ◽  
Gulf Of Guinea ◽  
Energy Potential ◽  
Turbine Generator ◽  
Average Speed ◽  
Wind Turbine Generator ◽  
Optimum Choice ◽  
Wind Potential

This work presents the characterization and assessment of wind energy potential in annual and monthly levels of the sites of Lomé, Accra and Cotonou located in the Gulf of Guinea, and the optimal characteristics of wind turbines to be installed on these sites. Studies of characterization and the wind potential of these sites from the wind speed data collected over a period of thirteen years at a height of 10 meters above the ground, show an annual average speed of 3.52 m/s for Lomé, 3.99 m/s for Cotonou and 4.16 m/s for Accra. These studies also showed that a monthly average speed exceeding 4 m/s was observed on the sites of Cotonou and Accra during the months of February, March, April, July, August and September and during the months of July, August and September on the site of Lomé. After a series of simulation conducted using the software named PotEol that we have developed in Scilab, we have retained that the wind turbines rated speeds of ~8 to 9 m/s at the sites of Lomé and Cotonou and ~ 9 to 10 m/s on the site of Accra would be the most appropriate speeds for optimal exploitation of electric energy from wind farms at a height of 50 m above the ground.Article History: Received May 26th 2016; Received in revised form August 24th 2016; Accepted August 30th 2016; Available onlineHow to Cite This Article: Salami, A.A., Ajavon, A.S.A , Kodjo, M.K. and Bédja, K. (2016) Evaluation of Wind Potential for an Optimum Choice of Wind Turbine Generator on the Sites of Lomé, Accra, and Cotonou Located in the Gulf of Guinea. Int. Journal of Renewable Energy Development, 5(3), 211-223.http://dx.doi.org/10.14710/ijred.5.3.211-223

scholarly journals An In-Depth Analysis of The Data Mining Algorithms and Their Effective Applicability in Health and Biomedical Informatics

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Deeya Tangri
Keyword(s):  
Data Mining ◽  
Health Care ◽  
Medical Science ◽  
Massive Data ◽  
Medical Field ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
Depth Analysis ◽  
Data Extract ◽  
Mining Algorithms

Nowadays, the Health care industry is one of the fastest-growing industries. As we already know, health care has researched very widely, introducing many medical data that is not easy to mine. Data mining is an approach that helps to discover essential data from massive data or collection of data. So, in medical Science, there is a need for tools that help analyses the data, extract the significant result from massive data, and discover efficient use of information. Generally, three things are mandatory in medical for every patient. First is patient details, diagnosis and medications. Converting these data into a basic pattern for predicting the patient disease helps in early diagnosis. This research mainly focuses on the data mining approach, which is widely considered in the medical field.

Hybrid Data Mining for Medical Applications

2009 ◽  
pp. 523-543
Author(s):  
Syed Zahid Hassan ◽  
Brijesh Verma
Keyword(s):  
Data Mining ◽  
Medical Applications ◽  
Medical Database ◽  
Data Repositories ◽  
Data Mining Algorithms ◽  
Hybrid Approaches ◽  
Data Mining Approach ◽  
Hybrid Data ◽  
Mining Algorithms ◽  
Existing Data

This chapter focuses on hybrid data mining algorithms and their use in medical applications. It reviews existing data mining algorithms and presents a novel hybrid data mining approach, which takes advantage of intelligent and statistical modeling of data mining algorithms to extract meaningful patterns from medical data repositories. Various hybrid combinations of data mining algorithms are formulated and tested on a benchmark medical database. The chapter includes the experimental results with existing and new hybrid approaches to demonstrate the superiority of hybrid data mining algorithms over standard algorithms.

scholarly journals An Entropy-Based Car Failure Detection Method Based on Data Acquisition Pipeline

Entropy ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. 426 ◽  
Author(s):  
Bartosz Kowalik ◽  
Marcin Szpyrka
Keyword(s):  
Data Mining ◽  
Detection Method ◽  
Electronic Devices ◽  
Failure Detection ◽  
Point Of View ◽  
Electronic Control ◽  
Data Mining Algorithms ◽  
Data Mining Approach ◽  
Control Units ◽  
Mining Algorithms

Modern cars are equipped with plenty of electronic devices called Electronic Control Units (ECU). ECUs collect diagnostic data from a car’s components such as the engine, brakes etc. These data are then processed, and the appropriate information is communicated to the driver. From the point of view of safety of the driver and the passengers, the information about the car faults is vital. Regardless of the development of on-board computers, only a small amount of information is passed on to the driver. With the data mining approach, it is possible to obtain much more information from the data than it is provided by standard car equipment. This paper describes the environment built by the authors for data collection from ECUs. The collected data have been processed using parameterized entropies and data mining algorithms. Finally, we built a classifier able to detect a malfunctioning thermostat even if the car equipment does not indicate it.

Sign in / Sign up

Export Citation Format

Share Document