Open Access Open Access  Restricted Access Subscription Access

Enhanced Detection of Faults in Water Desalination System Using Machine Learning Approaches

Pooja Khirai, Masira Shaikh, Ankita Kadole, Umarfarooq Anehosur, Ashwini Gavali

Abstract


Water Desalination is the process in which salt or mineral components get separated from saline water. But after filtration of water also there are so many faults like sensor, utility, blockage, process faults are used to be available in water data. To detect those faults Machine Learning Algorithms come into the picture which are having math and computational power to analyze faults and predict the higher accuracy. The algorithms like Decision tree and Linear Regression etc. are used to get higher accuracy. To detect faults the best Machine learning algorithm is identified by doing comparison of Machine Learning Models and we get more accuracy level over 98%. The input is given as collected data and further tested by system model and classified as normal and faulty data. And the good Machine Learning Model is able to predict the higher accuracy.


Full Text:

PDF

References


Tarifa, E. E., & Scenna, N. J. (1998). A methodology for fault diagnosis in large chemical processes and an application to a multistage flash desalination process: Part I. Reliability Engineering & System Safety, 60(1), 29-40.

Bouguecha, S. T., Aly, S. E., Al-Beirutty, M. H., Hamdi, M. M., & Boubakri, A. (2015). Solar driven DCMD: performance evaluation and thermal energy efficiency. Chemical Engineering Research and Design, 100, 331-340.

Tarifa, E. E., Humana, D., Franco, S., Martínez, S. L., Núñez, A. F., & Scenna, N. J. (2003). Fault diagnosis for a MSF using neural networks. Desalination, 152(1-3), 215-222.

Said, S. A., Emtir, M., & Mujtaba, I. M. (2013). Flexible design and operation of multi-stage flash (MSF) desalination process subject to variable fouling and variable freshwater demand. Processes, 1(3), 279-295.


Refbacks

  • There are currently no refbacks.