Issue 4, 2025

Boosting engineering strategies for plastic hydrocracking applications: a machine learning-based multi-objective optimization framework

Abstract

The escalating global demand for plastics, combined with inadequate recycling strategies, has resulted in severe environmental challenges. While previous research has explored various waste plastic recycling methods, the development of efficient and sustainable technologies remains a complex, time-intensive endeavor, involving extensive experimental data, catalyst design, and process optimization. In this study, we introduce, for the first time, a novel waste plastic pyrolysis oil hydrocracking process (WPOH) and its optimized variant (WPOH-Pro), which uniquely integrates process simulation with advanced deep learning models for multi-objective optimization. This innovative approach accelerates process parameter optimization, setting it apart from existing studies. By leveraging deep learning and comprehensive process modeling, our framework not only optimizes economic performance but also addresses key environmental concerns. The results of our study indicate that the WPOH-Pro process enhances net profit by 50.44% relative to the WPOH process. This improvement is primarily attributed to increased yields of gasoline and naphtha, with an associated production cost of $4.58 million per annum. Furthermore, lifecycle analysis reveals a 22.9% reduction in non-renewable energy consumption, alongside a substantial decrease in greenhouse gas emissions, quantified at 390.24 tCO2eq. per million GDP. In comparison with the WPOH process, the WPOH-Pro process achieves a reduction in CO2 emissions of 99.38 tCO2eq. per million GDP. These findings highlight the ecological benefits of the WPOH-Pro process. This pioneering work in combining process simulation and deep learning-driven optimization offers a significant leap forward in the waste plastic recycling field. It provides a robust foundation for the engineering application of waste plastic hydrocracking technologies and serves as a valuable reference for promoting the circular economy. By offering practical insights into sustainable waste recycling, this study paves the way for future innovations and the industrial adoption of more efficient and environmentally friendly recycling technologies.

Graphical abstract: Boosting engineering strategies for plastic hydrocracking applications: a machine learning-based multi-objective optimization framework

Supplementary files

Article information

Article type
Paper
Submitted
19 Oct 2024
Accepted
14 Dec 2024
First published
02 Jan 2025

Green Chem., 2025,27, 1169-1182

Boosting engineering strategies for plastic hydrocracking applications: a machine learning-based multi-objective optimization framework

Z. Ma, Z. Zhang, C. Wang, J. Cao, Y. Liu, H. Yan, X. Zhou, X. Feng and D. Chen, Green Chem., 2025, 27, 1169 DOI: 10.1039/D4GC05259E

To request permission to reproduce material from this article, please go to the Copyright Clearance Center request page.

If you are an author contributing to an RSC publication, you do not need to request permission provided correct acknowledgement is given.

If you are the author of this article, you do not need to request permission to reproduce figures and diagrams provided correct acknowledgement is given. If you want to reproduce the whole article in a third-party publication (excluding your thesis/dissertation for which permission is not required) please go to the Copyright Clearance Center request page.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements