Browsing by Author "Lenka, M."

Now showing 1 - 5 of 5

Isoconversional Kinetic Analysis and ANN-Based Prediction of Metformin Pyrolysis for Sustainable Waste Management
(American Chemical Society, 2025) Potnuri, R.; Lenka, M.; Sankar Rao, C.; Harshini, H.
Pharmaceutical waste poses a growing environmental concern due to its persistence and potential ecological impacts, necessitating effective and sustainable management strategies. This study investigates the pyrolysis of metformin as a means to valorize pharmaceutical waste within a circular economy framework. Pyrolysis experiments conducted on 500 mg of metformin demonstrated the formation of liquid-phase products, characterized by GC–MS, which revealed a high concentration of the active pharmaceutical ingredient (API) alongside carbonaceous, nitro, and acidic compounds. Comprehensive thermogravimetric analyses at heating rates of 10, 20, 30, and 40 °C/min were performed to evaluate the thermal decomposition behavior. Kinetic parameters were determined using four isoconversional methods, namely KAS, FWO, Starink, and FRD, yielding average activation energies of 101.4, 105.8, 101.4, and 111.1 kJ/mol, respectively. Thermodynamic parameters (?G, ?H, and ?S) were also calculated to gain further insights into the decomposition process. Additionally, an ANN model was developed using temperature and heating rate as inputs to predict mass loss, achieving accurate estimations with an optimized architecture comprising two hidden layers. GC–MS analysis of the pyrolysis liquid identified a high concentration of the API, along with carbonaceous, nitro, and acidic compounds. These findings highlight the potential for API recovery and reuse, as well as the valorization of byproducts for energy or chemical synthesis. The potential recovery of APIs for reuse and the utilization of byproducts as fuels or chemical precursors underscore pyrolysis as a promising route for sustainable pharmaceutical waste management and circular economy integration. © 2025 The Authors. Published by American Chemical Society
Leveraging explainable AI framework for predictive modeling of products of microwave pyrolysis of lignocellulosic biomass using machine learning
(Elsevier B.V., 2025) Kale, R.D.; Lenka, M.; Sankar Rao, C.
The accurate prediction of biochar, bio-oil, and biogas yields in biomass pyrolysis is critical for optimizing process efficiency and sustainable biofuel production. In this study, machine learning (ML) models were developed using literature-derived data on biomass composition and pyrolysis conditions to predict product yields. A comparative analysis of multiple ML algorithms revealed that Decision Tree and Extra Trees exhibited the highest predictive accuracy, followed by Random Forest, Gradient Boosting Trees, and Extreme Gradient Boosting. LightGBM, Gaussian Process Regression, and CatBoost provided moderate performance, while AdaBoost demonstrated the lowest accuracy. To enhance interpretability, Explainable Artificial Intelligence (XAI) techniques, specifically SHAP analysis, were employed to identify key factors influencing pyrolysis yields. Temperature, ash content, fixed carbon, and moisture content were the dominant parameters governing biochar yield, whereas heating rate, reaction time, and feedstock properties such as carbon and volatile matter content significantly influenced bio-oil production. The gas yield was primarily driven by temperature, with secondary cracking mechanisms enhancing non-condensable gas formation. These insights provide a data-driven foundation for optimizing biomass pyrolysis processes, enabling targeted valorization strategies for lignocellulosic feedstocks. The integration of ML and XAI in this study establishes a transparent and interpretable modeling framework, facilitating informed decision-making for sustainable biofuel production. © 2025 Elsevier B.V.
Microwave-assisted torrefaction of lignocellulosic biomass: A critical review of its role in sustainable energy
(Elsevier Ltd, 2025) Ramesh, R.; Sankar Rao, C.; Lenka, M.; Sridevi, V.; Basak, T.
Lignocellulosic biomass is a promising renewable energy source that can help reduce reliance on fossil fuels. However, its raw form presents challenges for practical use. To overcome this, the Microwave-assisted torrefaction (MAT) process has emerged as a successful method for enhancing the quality of biomass and generating energy. This article aims to provide a comprehensive review of recent scientific research on MAT of biomass. It explores torrefaction indices and discusses the impact of key parameters such as biomass composition, temperature, residence time, heating rate, particle size, and microwave power on MAT. The article also addresses potential applications and challenges associated with MAT. Furthermore, it evaluates the hurdles in achieving compatibility, acceptability, and sustainability of the process, along with future directions to realize economic benefits even in small-scale applications. Ultimately, MAT holds promise as an energy-efficient approach to enhance the effectiveness of biomass utilization. © 2025
Predictive modeling of product yields in microwave-assisted co-pyrolysis of biomass and plastic with enhanced interpretability using explainable AI approaches
(Elsevier B.V., 2025) Rajpurohit, N.S.; Kamani, P.K.; Lenka, M.; Sankar Rao, C.
Microwave-assisted co-pyrolysis of biomass and plastic offers a transformative approach to converting waste into valuable resources such as bio-oil, biochar, and biogas, while simultaneously addressing critical environmental challenges associated with plastic disposal. This research employs explainable AI methodologies to enhance the prediction and analysis of product yields in biomass-plastic co-pyrolysis. Advanced machine learning techniques, including Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks, were utilized to model yield predictions effectively. The models were fine-tuned through hyper-parameter optimization, achieving high accuracy levels. The study emphasizes the scientific importance of integrating explainable AI with pyrolysis processes to optimize waste-to-resource recovery, contributing significantly to sustainable waste management and circular economy initiatives. Among these, the XGBoost model demonstrated superior performance, achieving R² values of 0.91 for biochar yield, 0.92 for bio-oil yield, and 0.82 for biogas yield on testing sets. To enhance model interpretability, SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) were utilized to assess feature importance and examine parameter influences on yield outcomes, offering valuable insights into process optimization and control. Volatile matter and fixed carbon were key predictors for biochar yield, while moisture content and pyrolysis temperature were significant for predicting bio-oil and biogas yields. This study highlights the potential of explainable AI models in advancing sustainable and efficient bio-product recovery from waste materials. © 2025 Elsevier B.V.
Principles of crystallization process
(Elsevier, 2024) Bhoi, S.; Lenka, M.; Sarkar, D.
Crystallization is an important mass transfer operation, having applications in pharmaceutical, chemical, food industries, etc. It is defined as the process of producing crystals from solution, melt, or vapor phase. The crystallization process is mainly used to purify and separate compounds. Further, it can also be used to perform particle engineering, which in turn has a great effect on the efficiency of downstream operations such as filtration, drying, etc. The driving force of any crystallization process can be commonly termed supersaturation. The supersaturation can be generated by several methods such as evaporation, chemical reaction, cooling, addition of antisolvent, etc. The key events in crystallization processes are nucleation, growth, agglomeration, and breakage. These processes can be mathematically modeled using the population balance equation for the discrete solid phase, and mass and heat balance equation for the continuous liquid phase. The mathematical model is helpful in performing control and optimization-related studies. © 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.