Low-carbon design based on conceptual design methods for mechanical and electrical products

Gao, Guohua; Yang, Xue; Zhang, Zihua; Zhu, Zhenjiang

doi:10.1007/s00170-023-11622-8

Cited by 1 publication

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various emission reduction policies, such as net zero emissions, have been implemented by the government to tackle environmental concerns. The adoption of low-carbon product designs proves to be an effective measure in reducing emissions at their source (Gao et al 2023). Moreover, the structural design significantly impacts carbon emissions during the machining of mechanical parts.…”

Section: Introductionmentioning

confidence: 99%

A carbon emission prediction model of mechanical parts machining driven by structural design parameters

Jiang,

Li,

Zhu

et al. 2023

Preprint

View full text Add to dashboard Cite

Structure design has a direct impact on the carbon emissions produced during the machining of mechanical parts. However, there exists a complex mechanistic relationship between structural design parameters(such as size and shape) and the carbon emissions generated during machining, making it challenging to accurately predict carbon emissions. Consequently, effectively implementing low-carbon structural design becomes a formidable task. To this end, a carbon emission prediction model of mechanical parts machining driven by structural design parameters is introduced. To begin, the influence of structural design parameters and machining processes on the carbon emissions is analyzed, and the structural design parameters are categorized. The optimal Latin hypercube sampling (OLHS) method is employed to construct the initial sample set. Subsequently, a radial-basis function neural network (RBFNN) model for predicting carbon emissions, driven by structural design parameters, is developed, taking into account the intricate nonlinearity of the carbon emissions prediction mechanism model with multiple structural design parameters. The Regularization Coefficient and K-Fold Cross Validation method are implemented to enhance the accuracy of the training model. Finally, the effectiveness of the proposed method is verified by a reducer gear machining.

show abstract

Section: Introductionmentioning

confidence: 99%