Page 36 - 2023

Ph.D.
(Engineering & Technology)
INVESTIGATION ON DESALINATION SYSTEM THROUGH MACHINE
LEARNING AND INTERNET OF THING APPROACH

Ph.D. Scholar : Shrimali Neelkumar Sumanlal
Research Supervisor : Dr. Vijay K. Patel

Regi. No.: 20276351001
Abstract :
Desalination, which is the process of removing salt and other pollutants from seawater or
brackish water in order to produce freshwater, is an essential component in the fight
against water scarcity issues that are prevalent all over the world. In recent years, the
incorporation of Machine Learning (ML) and the Internet of Things (IoT) technologies has
revolutionized the desalination sector by increasing the efficacy and sustainability of
desalination systems. This has led to a significant increase in the demand for desalinated
water. This inquiry focuses on the application of machine learning (ML) and internet of
things (IoT) in desalination operations, providing an in-depth analysis of their potential
benefits and problems.

Thesis starts off by reviewing the fundamental concepts of several desalination
techniques, such as multi-effect distillation and reverse osmosis, and highlighting the
essential aspects that affect the performance of these techniques, such as energy
consumption, membrane fouling, and system maintenance. It highlights the growing
necessity for enhanced solutions for monitoring, control, and optimization to overcome
these issues.

Following that, the inquiry looks into the incorporation of machine learning and the
internet of things in desalination systems, with a focus on the implementation of data
analytics platforms, sensors, and actuators. Real-time data gathering is accomplished by
the utilization of Internet of Things (IoT)-enabled sensors, which enables the continuous
monitoring of crucial factors such as water quality, pressure, and temperature. After that,
machine learning algorithms are used to process this data in order to minimize energy
consumption, increase system reliability, and forecast and avoid any problems.

In addition, this paper examines a number of machine learning strategies, like as
regression, clustering, and deep learning, as well as their applications in desalination
systems. It addresses the benefits of predictive maintenance, early defect detection, and
adaptive control tactics that are made feasible by machine learning models. These
strategies contribute to reduced downtime and better operational efficiency.In addition,
the inquiry tackles issues concerning the implementation of IoT and ML in desalination
facilities, such as the security of data, interoperability, and scalability. It highlights the

11