文献类型：期刊文献

英文题名：Carbon footprint assessment in manufacturing Industry 4.0 using machine learning with intelligent Internet of things

作者：Liu, Zhao Yang, Gangying Zhang, Yi

第一作者：Liu, Zhao

通信作者：Zhang, Y[1]

机构：[1]Guizhou Inst Technol, Sch Econ & Management, Guiyang 550003, Peoples R China

第一机构：贵州理工学院经济管理学院

通信机构：corresponding author), Guizhou Inst Technol, Sch Econ & Management, Guiyang 550003, Peoples R China.|贵州理工学院经济管理学院;贵州理工学院;

年份：2023

外文期刊名：INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY

收录：;EI(收录号：20233514644619);Scopus(收录号：2-s2.0-85168864398);WOS:【SCI-EXPANDED(收录号:WOS:001060427600002)】；

基金：& nbsp;This work was supported by the Academic Seedlings and Exploration-Innovation Project of Guizhou Institute of Technology, Study on carbon information disclosure and carbon trading quota mechanism of industrial enterprises in Guizhou Province. (GZLGXM-25).

语种：英文

外文关键词：Carbon footprint analysis; Green manufacturing; Industry 4.0; Air monitoring; Machine learning; IIoT

摘要：One important application area for sensor data analytics is Industry 4.0. Industrial furnaces (IFs) are sophisticated devices utilised in industrial production applications that need for unique heat treatment cycles. They are built with specialised thermodynamic materials and methods. emission of black carbon (EoBC) during IF operation as a result of the incomplete combustion of fossil fuels is one of the most important problems. This research proposes novel technique in carbon footprint analysis in environmental data from green manufacturing Industry 4.0 using machine learning with intelligent Internet of things (IIoT). Here, the environmental data from green manufacturing industry is collected and processed for analysing the presence of carbon by air monitoring by hidden fuzzy Gaussian kernel-based principle analysis. The experimental analysis is carried out for various air-monitored data in terms of training accuracy, positive predictive value, precision, robustness, energy consumption. Finally, we suggest ways for reducing carbon emissions and energy usage based on case studies that make use of our methodology. By making accounting simpler, we intend to encourage further investigation into energy-efficient algorithms and advance the long-term development of machine learning studies.