Industrial solid waste recycling using digital servitisation for decarbonisation to promote Net zero in the circular economy

•Research integrates AI, blockchain, and data analytics for efficient stakeholder coordination in recycling.•The project has 3 phases: Returned product clustering, Requirement Elicitation, and Smart Life Cycle Selection.•IFC-MCA optimises product allocation to centres based on category, return time,...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computers & industrial engineering Jg. 206; S. 111251
Hauptverfasser:	Gao, Pengqun, Zhou, Yang, Sun, Lipeng, Alahmari, Saad, Innab, Nisreen, Venkatachalam, K., Ferrara, Massimiliano
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.08.2025
Schlagworte:	Artificial intelligence (AI) Blockchain Circular Economy Improved Fuzzy C-means clustering algorithm Industrial solid waste Modified Convolutional Neural Network Algorithm (MCNN) Industrial solid waste Circular Economy Improved Fuzzy C-means clustering algorithm Artificial intelligence (AI) Modified Convolutional Neural Network Algorithm (MCNN) Blockchain
ISSN:	0360-8352
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	•Research integrates AI, blockchain, and data analytics for efficient stakeholder coordination in recycling.•The project has 3 phases: Returned product clustering, Requirement Elicitation, and Smart Life Cycle Selection.•IFC-MCA optimises product allocation to centres based on category, return time, price, and location.•LDA identifies consumer needs, analyses return patterns, predicts volumes, enhancing resource use.•MCNN recommends product life cycle options based on quality and life expectancy, enhancing sustainability. The smart circular economy framework proposed in this study encourages a net-zero economy by improving industrial solid waste recycling for decarbonization through the digital service economy. A blockchain-based cloud platform uses advanced technologies like artificial intelligence, blockchain, and data analytics to encourage smooth communication between all parties. These suggested framework developments include requirement elicitation and quality grading, smart life cycle option selection, and returned products clustering. The FuzClu algorithm clusters returned products to improve their allocation to collection centers based on specific features like product type, return time and location. Subsequently, requirement elicitation through Latent Dirichlet Analysis identifies consumer needs and return patterns to produce innovation and predict future return volumes. Finally, the Smart Life Cycle Option Selection applies the Modified Convolutional Neural Network Algorithm to recommend optimal life cycle options based on product quality and lifetime. This approach increases the value of end-of-life products, encourages sustainability and reduces environmental pollution. Overall, this research contributes to addressing industrial solid waste challenges by aligning digital servitisation with circular economy principles, notably supporting decarbonisation with a focus on a net-zero economy.
ISSN:	0360-8352
DOI:	10.1016/j.cie.2025.111251