Real-Time Monitoring and Optimization of Regeneration Efficiency of Peanut Shell-Based Magnetic Biochar Adsorbent Using Microwave-Assisted Regeneration, IoT Monitoring, and Machine Learning

This research applies to the regeneration rate and recycling capability of peanut shell magnetic biochar adsorbents capturing pollutants from water through IoT sensing and microwave regeneration systems actuated by optimization algorithms. This was done by first crushing peanuts shells and carbonizing them to generate biochar, secondly adding magnetic Fe₃O₄ nanoparticles to enhance the adsorption surface and ease by which the Richards can be separated from the mixture. Microwave-assisted regeneration was also identified to be more efficient than conventional thermal methods, with regeneration yields up to 88% achieving adsorption capacity in methylene blue dye and Lead ions. Though IoT smart sensors became efficient to monitor temperature and other pollutants in the process in order to enhance the process. The application of Machine learning model, Random Forest, on regression yielded a high R² score 0.91 for the prediction of the efficient regeneration and allows for feedback control on the system. The proposed system increases regeneration, and at the same time it is less energy and operating cost consuming in comparison to the conventional practices. The present paper demonstrates that the considered technologies can be successfully applied at large scale both for water and gases purifications with wastewater treatment among the most suitable application areas. Future studies will attempt at proving the possibility to use more agricultural waste materials to produce biochar and use improved algorithms in the rejuvenation processes for better models due to machine learning. This paper provides a green, sustainable and easily scalable method of collecting and recycling or recovering the biochar.