A novel waste-to-energy conversion plant based on catalytic pyrolytic conditions: Modeling and optimization using supervised machine learning and desirability-driven methodologies

被引:3
作者
Ahmad, Aqueel [1 ]
Yadav, Ashok Kumar [2 ]
Hasan, Shifa [3 ]
机构
[1] Graph Era, Dept Mech Engn, Dehra Dun, India
[2] Raj Kumar Goel Inst Technol, Dept Mech Engn, Ghaziabad, India
[3] Netaji Subhas Univ Technol, Dept Management Studies, New Delhi, India
关键词
Catalytic pyrolysis; Machine learning regression; Process optimization; Feature selection; Waste to energy; PLASTIC WASTE; DENSITY POLYETHYLENE; SELECTION; PREDICTION;
D O I
10.1016/j.energy.2025.134648
中图分类号
O414.1 [热力学];
学科分类号
摘要
The persistent nature of plastics significantly contributes to waste generation, making their disposal a critical issue. Pyrolysis, which converts plastic waste into fuel, is a promising solution to the energy crisis. This study evaluates the pyrolysis potential of low-density polyethylene (LDPE) plastic waste, focusing on the influence of process parameters (reactor temperature, residence time, N2 flow rate, and catalyst concentration) and their optimization using seven supervised machine learning models (RF, GB, ET, DT, KNN, AB, and XGB) and a desirability approach. Feature selection techniques (PCC, F-score, and MI) were employed to identify pertinent input features, with MI exhibiting superior performance in accurately identifying and combining the most relevant features for the model's predictive accuracy. The gradient boosting (GB) model demonstrated the highest predictive accuracy with R2 scores of 0.948, 0.9799, and 0.9802 for bio-oil, biochar, and syngas yields, respectively, and the lowest errors (RMSE: 0.6859, 0.1349, and 0.4194; MAE: 0.4505, 0.078, and 0.2673; MAPE: 0.681, 1.1379, and 0.9629). The tree-based pipeline optimization approach shows the optimal conditions of a reactor temperature of 450 degrees C, a residence time of 2 h, an N2 flow rate of 150 mL/min, and a catalyst concentration of 6 wt %, resulting in a maximum bio-oil yield of 72.20 % and biochar and syngas yields of 6.35 % and 23.48 %, respectively. Detailed characterization via GC-MS analysis indicated that bio-oil, which is composed of various organic compounds, such as phenols, ketones, alcohols, esters, and aromatic hydrocarbons, can be upgraded for use as a hydrocarbon fuel. Biochar and syngas can be used in power generation, heating, industrial boilers, cement kilns, and as soil amendments or chemical feedstocks. These findings support the effective use of LDPE as a plastic waste for bioenergy precursor production.
引用
收藏
页数:16
相关论文
共 70 条
[1]   Characterization of biodiesel based on plastic pyrolysis oil (PPO) and coconut oil: Performance and emission analysis using RSM-ANN approach [J].
Afzal, Asif ;
Roy, Roji George ;
Koshy, Chacko Preno ;
Alex, Y. ;
Abbas, Mohamed ;
Cuce, Erdem ;
Razak, R. K. Abdul ;
Shaik, Saboor ;
Saleel, C. Ahamed .
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 2023, 56
[2]   A machine learning-response surface optimization approach to enhance the performance of diesel engine using novel blends of Aloe vera biodiesel with MWCNT nanoparticles and hydrogen [J].
Ahmad, Aqueel ;
Yadav, Ashok Kumar ;
Singh, Achhaibar ;
Singh, Dinesh Kumar .
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2024, 186 :738-755
[3]   A comprehensive machine learning-coupled response surface methodology approach for predictive modeling and optimization of biogas potential in anaerobic Co-digestion of organic waste [J].
Ahmad, Aqueel ;
Yadav, Ashok Kumar ;
Singh, Achhaibar ;
Singh, Dinesh Kumar .
BIOMASS & BIOENERGY, 2024, 180
[4]   Comparative Analysis of Feature Selection Algorithms for Computational Personality Prediction From Social Media [J].
Al Marouf, Ahmed ;
Hasan, Md. Kamrul ;
Mahmud, Hasan .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2020, 7 (03) :587-599
[5]   Catalytic pyrolysis of Padina sp. with ZSM-5 and Amberlyst-15 catalysts to produce aromatic-rich bio-oil [J].
Amrullah, Apip ;
Farobie, Obie ;
Irawansyah, Herry ;
Ismadi ;
Ernawati, Lusi ;
Aziz, Muhammad ;
Fatriasari, Widya .
BIORESOURCE TECHNOLOGY REPORTS, 2024, 28
[6]   Experimental Study of Thermal and Catalytic Pyrolysis of Plastic Waste Components [J].
Anene, Azubuike Francis ;
Fredriksen, Siw Bodil ;
Saetre, Kai Arne ;
Tokheim, Lars-Andre .
SUSTAINABILITY, 2018, 10 (11)
[7]   Life Cycle Assessment of the existing and proposed plastic waste management options in India: A case study [J].
Aryan, Yash ;
Yadav, Pooja ;
Samadder, Sukha Ranjan .
JOURNAL OF CLEANER PRODUCTION, 2019, 211 :1268-1283
[8]   Machine learning methods for modelling the gasification and pyrolysis of biomass and waste [J].
Ascher, Simon ;
Watson, Ian ;
You, Siming .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2022, 155
[9]  
Ayodele TR, 2019, 2019 IEEE PES/IAS POWERAFRICA, P527, DOI [10.1109/powerafrica.2019.8928780, 10.1109/PowerAfrica.2019.8928780]
[10]   Co-Pyrolysis of biomass and plastic waste: Process prediction and optimization based on Artificial Intelligence and response optimizer surrogate model [J].
Ayub, Yousaf ;
Ren, Jingzheng .
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2024, 186 :612-624