Control of motors in drinking water treatment plants using artifical neural networks

Drinking water is very important today as it has been at all times in history. In ancient times, civilization was built around water beds. Today, thanks to dams, water is kept in certain regions and enters our wells through various purification processes. In this study, it is mentioned that the Blue Tunnel Drinking Water Treatment Plant, which provides a large part of Konya's drinking water needs, how the water is purified through which stages and the functions of electric motors to make the water ready for use. Induction motors are present in every aspect of our lives. The squirrel cage asynchronous motor is the most commonly used type of motor in the world. It is inevitable that we see this type of motor most often in drinking water treatment plants. Due to the variable characteristics and complex structure of the induction motor, its sensorless control could not exceed a certain level in industrial applications. Many academic studies have been conducted to eliminate this negative situation. In this study, the motor speed was measured by randomly selecting one of the motors used in the Blue Tunnel drinking water treatment plant and changing the voltage and frequency values using the driver, and training data for the artificial neural networks were obtained. Then, the speed was measured by changing the voltage and frequency values with the help of the driver, along with the values inside the training data and outside the training data. Finally, the artificial neural networks were trained in MATLAB using the training data. Voltage, frequency, and both voltage and frequency data were used as input values. Simulations were performed. The results of the simulations were compared with the actual results obtained from the test. It was found that they were very close to the actual values.