Logistic Model Tree Classifier for Condition Monitoring of Wind Turbine Blades
A. Joshuva1, G. Deenadayalan2, S. Siva Kumar3, R. Sathish Kumar4, R. Vishnuvardhan5
1A. Joshuva, Department of Mechanical Engineering, Hindustan Institute of Technology and Science, Old Mahabalipuram Road, Kelambakam, Chennai (Tamil Nadu), India.
2G. Deenadayalan, Department of Mechanical Engineering, Hindustan Institute of Technology and Science, Old Mahabalipuram Road, Kelambakam, Chennai (Tamil Nadu), India.
3S. Siva Kumar, Department of Mechanical Engineering, Hindustan Institute of Technology and Science, Old Mahabalipuram Road, Kelambakam, Chennai (Tamil Nadu), India.
4R. Sathish Kumar, Department of Automobile Engineering, Hindustan Institute of Technology and Science, Old Mahabalipuram Road, Kelambakam, Chennai (Tamil Nadu), India.
5R. Vishnuvardhan, Department of Mechatronics Engineering, Sri Krishna College of Engineering and Technology, Coimbatore, T.N, India.
Manuscript received on 10 October 2019 | Revised Manuscript received on 19 October 2019 | Manuscript Published on 02 November 2019 | PP: 202-209 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B10330982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1033.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Wind energy is one of the essential renewable energy resources because of its consistency due to the development of the technology and relative cost affordability. The wind energy is converted into electrical energy using rotating blades which are connected to the generator. Due to environmental conditions and large construction, the blades are subjected to various faults and cause the lack of productivity. The downtime can be reduced when they are diagnosed periodically using condition monitoring technique. These are considered as a machine learning problem which consists of three phases, namely feature extraction, feature selection and fault classification. In this study, statistical features are extracted from vibration signals, feature selection are carried out using J48 algorithm and the fault classification was carried out using logistic model tree algorithm.
Keywords: Fault Diagnosis; Condition Monitoring; Statistical Features; J48 Algorithm; Logistic Model Tree (LMT) Algorithm.
Scope of the Article: Refrigeration and Air Conditioning