Introduction, applications and scope of predictive data analysis in boiler feed systems
- 1Department of Mechanical Engineering, University Institute of Technology, RGPV, Bhopal, MP, India
Res. J. Recent Sci., Volume 6, Issue (10), Pages 14-16, October,2 (2017)
In this rapidly advancing technological world increasingly driven by myriad amount of data, a need is generated to deal with these massive tons of information. Termed as \'Big data’, this bulk of information can be really helpful in dealing with future shortcomings or present case scenarios if used in the best way. Although many methods have been developed for its processing and some are still being developed, One of the ways to tame big data is by predictive data analytics. It has found many applications at management level and IT corporations and its believed that its incorporation can be of great significance in the field of mechanical engineering too, as it not only gives a futuristic approach of handling a situation but also helps to predict the shortcomings and results in any operation. Predictive analytics often known as the future way of reducing the data. It works on various techniques including statistics to study various types of data including recent and past data and thus helps in making predictions about what might happen in future. In this study, we have analyzed a privately operated boiler feed plant its data variations and the use of 3 way decision tree model to look for prediction into a boiler plant efficiency while varying the variables. With its help we will segregate the variables based on all values of sub variables and identify that variable, which has greater significance on the final output i.e the efficiency. Currently though the use of data analytics in the field of mechanical engineering is significantly less, it looks like its use in most of mechanical engineering sector might prove to be a boon for this field making working more efficient and results more desirable.
- Kulkarni Parag, Joshi Sarang and Brown Meta S. (2016)., Big Data Analytics., PHI learning Pvt Limited, Delhi. ISBN 978-81-203-5116-5.
- Modell Martin E. (1992)., Data Analysis, Data Modeling and Classification., McGraw Hill Higher Education. ISBN-10: 0070426341 ISBN-13: 978-0070426344.
- Bari Anasse, Chaouchi Mohamed and Jung Tommy (2014)., Predictive Analytics For Dummies., John Wiley & Sons. ISBN-10: 1118728963 ISBN-13: 978-1118728963.
- Miller Thomas W. (2014)., Modeling Techniques in Predictive Analytics., Pearson FT Press. ISBN-10: 0133892069 ISBN-13: 978-0133892062.
- Kumar Ashish (2016)., Learning Predictive Analytics with Python., Packt Publishing Limited, ISBN-10: 1783983264 ISBN-13: 978-1783983261.
- Simha Jay B. (2010)., Data mining for boiler efficiency modeling., https://jbsimha.wordpress.com/2010/06/21/data-mining-for-boiler-efficiency-modeling/ (27/06/2017).
- Shah Sunit and Adhyaru D.M. (2011)., Boiler efficiency analysis using direct method., IEEE Xplore, Ahemdabad, India, Electronic ISBN: 978-1-4577-2168-7 Print ISBN: 978-1-4577-2169-4.
- U.S. Department of Energy Efficiency and Renewable Energy (2004)., Waste Heat Reduction and Recovery for Improving Furnace Efficiency Productivity and Emissions performance., EERE Information Center 1-877-EERE-INF (1-877-337-3463)
- Kelleher John D., Brian Mac Namee and Aoife D, The MIT Press., ISBN-10: 0262029448 ISBN-13: 978-0262029445.
- Bijli Muhamed Muzaiyen S.M., Paneerselvam T., Alahiyanambi K. and Basha Jafar M.A. (2015)., Optimization of Boiler Efficiency at Mettur Thermal Power Station., Advances in Intelligent Systems and Computing, 581-592. ISSN 2194-5357, ISBN 978-81-322-2669.