Optimisation of Stepped Basin Solar Still with Response Surface Methodology and Machine Learning Methods

Authors

• M. Balamurugan, Department of Mechanical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, SIMATS, Chennai, Tamil Nadu, India 602105
• V. Santhanam, Department of Mechatronics Engineering, Rajalakshmi Engineering College (Autonomous), Chennai, Tamil Nadu, India 602105
• B. Deepanraj, Department of Mechanical Engineering, College of Engineering, Prince Mohammad Bin Fahd University, Al Khobar, 31952, Saudi Arabia
• S. P Manikandan, Department of Mechanical Engineering, Periyar Maniammai Institute of Science and Technology, Vallam, Thanjavur, Tamil Nadu, India 613 403
• M. Yuvaperiyasamy, Department of Mechanical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, SIMATS, Chennai, Tamil Nadu, India 602105
• N. Senthilkumar, Department of Mechanical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, SIMATS, Chennai, Tamil Nadu, India 602105Follow

Corresponding Author

N.Senthilkumar

Subject Area

Mechanical Power Engineering

Article Type

Original Study

Abstract

This research focuses on enhancing the distillate output of a stepped basin solar still by optimizing key operational variables using Response Surface Methodology (RSM) and advanced machine learning techniques. As water scarcity remains a critical global challenge, solar stills offer a viable, sustainable solution for desalination. These systems offer an energy-efficient approach to converting saline water intofreshwater, providing an alternative to conventional desalination methods. The primary objective was to investigate how variations in solar radiation, step height, and water inlet temperature influence the productivity of the stepped basin solar still. The solar radiation ranged from 600 to 1000 W/m², the step height varied between 10 and 30 mm, and the water inlet temperature ranged from 30 to 50°C. A central composite design was employed to systematically investigate the combined effects and interactions of multiple factors on distillate yield. Empirical models were developed using RSM to capture the nonlinear interactions between input parameters and output responses. Additionally, machine learning methods were applied to enhance the model’s predictive capabilities, aiming to better capture complex patterns in the experimental data. This hybrid modeling technique provided a comprehensive understanding of the system’s behavior and enhanced forecast reliability. The experimental findings revealed that the highest distillate yield of 7.42 l/m² was achieved under ideal conditions, which includeda solar radiation of 1000 W/m², a step height of 20 mm, and a water inlet temperature of 50°C. Both the RSM and machine learning models showed excellent agreement with the experimental data, highlighting their effectiveness in accurately capturing the underlying physics of the process and the interactions between the variables.q

Keywords

Freshwater; Desalination; Optimisation; Freshwater Production; Neural network.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Recommended Citation

Balamurugan, M.; Santhanam, V.; Deepanraj, B.; Manikandan, S. P; Yuvaperiyasamy, M.; and Senthilkumar, N. (2026) "Optimisation of Stepped Basin Solar Still with Response Surface Methodology and Machine Learning Methods," Mansoura Engineering Journal: Vol. 51 : Iss. 6 , Article 6.
Available at: https://doi.org/10.58491/2735-4202.3499