Li T, Zhu E, Bai Z, Cai W, Jian H, Liu H. Predicting and assessing greenhouse gas emissions during the construction of monorail systems using artificial intelligence.
Environ Sci Pollut Res Int 2024;
31:12229-12244. [PMID:
38225496 DOI:
10.1007/s11356-023-31783-z]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Accepted: 12/26/2023] [Indexed: 01/17/2024]
Abstract
Based on partial data, this paper uses BP neural network optimised by particle swarm optimisation algorithm to predict the total greenhouse gas (GHG) emissions of the line in the construction phase. The GHG emission efficiency is analysed by SBM (Slacks-Based Measure) super efficiency method. Finally, the grey relational analysis (GRA) is applied to sort the GHG emission correlation factors. Based on the existing design and quota document data of 16 stations and 16 sections of the Wuhu Monorail Line 1, we have employed a neural network optimized by particle swarm optimization algorithm to predict the total emissions of greenhouse gases during the construction phase of the entire line consisting of 25 stations and 24 sections. The GHG emissions of all stations and sections are 29,300 tons and 21,000 tons. The technical efficiency, pure technical efficiency, and scale efficiency of the stations and sections were high. As for stations, the order of influence degree is metal material consumption (0.9731) > cost (0.9486) > electric energy consumption (0.9481) > station area (0.9109) > concrete and cement consumption (0.9032) > other material consumption (0.8831) > gasoline and diesel consumption (0.7258). For the section, the order of influence degree is cost (0.9766) > concrete (0.9581) > steel reinforcement (0.9483) > other steels (0.874) > section length (0.8337) > power energy consumption (0.7169) > wood consumption (0.6684).
Collapse