Iqbal Asif, Akhter Sonia, Mahmud Shahed, Noyon Lion Mahmud
Department of Industrial & Production Engineering, Rajshahi University of Engineering & Technology, Rajshahi-6204, Bangladesh.
Heliyon. 2024 Sep 27;10(19):e38609. doi: 10.1016/j.heliyon.2024.e38609. eCollection 2024 Oct 15.
In an era of resource scarcity and environmental concerns, integrating Internet of Things (IoT) technology into the circular economy (CE), particularly for household appliances like microwaves, is crucial. The lack of systematic assessment of their post-use residual values often reduces utilization and shortens lifespans. Inadequate disposal and management contribute to electronic waste and environmental pollution. Addressing these challenges is vital for efficient appliance management within resource constraints, ensuring meaningful contributions to sustainable resource management. Thus, this study addresses these concerns by integrating IoT technology into microwave ovens, enabling real-time monitoring of key parameters such as voltage, current, door closures, and motor/blade rotations. Data from integrated sensors enables performance analysis and trend tracking, offering potential for advancing CE practices and sustainable product management. Subsequently, utilizing the insights stored from IoT data analysis and tailored surveys, a predictive maintenance model is developed, aiming to predict the life cycles of microwave oven components and categorize them within the CE principles, including reuse, repair, remanufacturing, and cascade. Finally, to mitigate the challenges of lower effective utilization and shortened operating lifespans observed in household appliances, this research employs machine learning models such as Random Forest, Gradient Boosting, and Decision Tree to accurately predict the residual values of IoT-enabled microwaves. Notably, Random Forest demonstrates superior accuracy compared to the other models. Therefore, these technological advancements allow household appliances to be utilized more effectively, thereby enhancing resource utilization.
在资源稀缺和环境问题备受关注的时代，将物联网（IoT）技术融入循环经济（CE），尤其是应用于微波炉等家用电器至关重要。对其使用后残值缺乏系统评估，常常会降低利用率并缩短使用寿命。处置和管理不当会导致电子垃圾和环境污染。在资源限制范围内有效管理家电，应对这些挑战对于确保对可持续资源管理做出有意义的贡献至关重要。因此，本研究通过将物联网技术集成到微波炉中，解决了这些问题，实现了对电压、电流、门关闭状态以及电机/叶片旋转等关键参数的实时监测。来自集成传感器的数据可进行性能分析和趋势跟踪，为推进循环经济实践和可持续产品管理提供了潜力。随后，利用从物联网数据分析和定制调查中存储的见解，开发了一种预测性维护模型，旨在预测微波炉组件的生命周期，并根据循环经济原则对其进行分类，包括再利用、维修、再制造和级联利用。最后，为了缓解在家用电器中观察到的有效利用率较低和运行寿命缩短的挑战，本研究采用了随机森林、梯度提升和决策树等机器学习模型来准确预测物联网微波炉的残值。值得注意的是，与其他模型相比，随机森林显示出更高的准确性。因此，这些技术进步使家用电器能够得到更有效的利用，从而提高资源利用率。
