Compounding process optimization for recycled materials using machine learning algorithms

Barrenetxea, Xabier; García-Arrieta, Sonia; Sedano, Inigo; Palenzuela, Luis; Usatorre, Luis

doi:10.1016/j.procir.2022.02.039

Cited by 5 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the process of cell phone recycling, [26] use a CNN model along with feature engineering in order to increase the amount of training data. In [27], the authors integrate set of classification models, namely Decision Tree (DT), K-Nearest Neighbor (KNN), Adaptive Boosting (Adaboost), Gradient Tree Boosting (GTB), and Multilayer Perceptron (MLP) to setup a system for the selection and optimization of parameters for remanufacturing of recycled fiber. The variety of application of ML algorithms can also be seen in the field of energy management, optimization and production.…”

Section: Applied Machine Learning In the Fields Of Circular Economymentioning

confidence: 99%

Challenges and Opportunities of Artificial Intelligence and Machine Learning in Circular Economy

Despotovic,

Glatschke

2024

Preprint

View full text Add to dashboard Cite

The inherent "take-make-waste" of the current linear economy is a major contributor to exceeding planetary boundaries. The transition to a circular economy (CE) and the associated challenges and opportunities require fast, innovative solutions. Artificial Intelligence (AI) and Machine Learning (ML) can play a key role in the transition to a CE paradigm by overcoming the challenges of increasing material extraction and use and creating a far more environmentally sustainable future. The objective of this article is to provide a status quo on the use of AI and ML in the transition to CE and to discuss the potential and challenges in this regard. The literature survey on Google Scholar using targeted queries with predefined keywords and search operators revealed that the number of experimental scientific contributions to AI and ML in the CE has increased significantly in recent years. As the number of research articles increased, so did the number of ML methods and algorithms covered in experimental CE publications. In addition, we found that there are 84% more AI and ML-affiliated research articles on CE in Google Scholar since 2020, compared to the total number of entries, and 55% more articles since 2023, compared to the respective articles up to 2023. The status quo of the scientific contributions shows that AI and ML are seen as extremely useful tools for the CE and their use is steadily increasing.

show abstract

Section: Applied Machine Learning In the Fields Of Circular Economymentioning

confidence: 99%