Department of Mechanical Engineering, School of Engineering, College of Engineering and Physical Sciences, University of Birmingham Edgbaston Campus, Birmingham, UK.
Department of Industrial Engineering, University of Pelita Harapan, M.H. Thamrin Boulevard 1100 Lippo Village, Tangerang, 15811, Indonesia.
Sci Rep. 2023 Jan 13;13(1):701. doi: 10.1038/s41598-023-27631-2.
Remanufacturing is widely recognised as a key contributor to the circular economy (CE) as it extends the in-use life of products, but its synergy with Industry 4.0 (I4.0) has received little attention when compared to manufacturing. An agglomeration of I4.0 technologies and methodologies is reflected in the emerging digital twin (DT) concept, which has been identified as a life-extending enabler. This article captures the design and demonstration of a DT model that optimises remanufacturing planning using data from different instances in a product's life cycle. The model uses a neural network for remaining useful life predictions and the Bees Algorithm for decision making within a DT. The model is validated using a real case study. The findings support the idea that intelligent tools within a DT can enhance decision-making if they have visibility and access to the product's current status and reliable remanufacturing process information.
再制造被广泛认为是循环经济 (CE) 的关键贡献者，因为它延长了产品的使用寿命，但与制造业相比，其与第四次工业革命 (I4.0) 的协同作用却很少受到关注。I4.0 技术和方法的集聚体反映在新兴的数字孪生 (DT) 概念中，该概念被认为是一种延长使用寿命的推动者。本文介绍了使用产品生命周期中不同实例的数据来优化再制造计划的 DT 模型的设计和演示。该模型使用神经网络进行剩余使用寿命预测，并在 DT 中使用蜜蜂算法进行决策。该模型使用实际案例研究进行了验证。研究结果支持这样一种观点，即如果 DT 中的智能工具能够看到并访问产品的当前状态以及可靠的再制造过程信息，那么它们可以增强决策制定。
