Affiliation:
1. School of International Education Zhengzhou Railway Vocational & Technical College Zhengzhou China
2. School of Locomotive and Rolling Stock Zhengzhou Railway Vocational & Technical College Zhengzhou China
Abstract
AbstractThe environmental issues brought on by carbon emissions from transport have risen to prominence in recent years. More and more academics are using the multi‐objective path optimization method to solve the multimodal optimization problem from the standpoint of sustainable development in order to address the environmental issues brought on by the transport process. The research proposes a two‐stage method to handle multi‐objective optimization convergence and simplify multimodal transport path optimization. In the first stage, a fuzzy C clustering model is established, and based on the clustering results, the multimodal transport network nodes are identified. In the second stage, a multimodal transport multi‐objective path optimization model is established, and the optimal path is solved using a genetic algorithm. The research method was applied in the Bohai Rim region. Results indicated that the fuzzy C‐clustering method and the genetic method were able to select the optimal node city, thus solving the actual site selection problem of multimodal transportation networks. Using the FCM model, the 86 city nodes were categorized into four types, leading to the establishment of the most proficient multimodal transportation network in the Bohai Rim region. Using a genetic algorithm for optimization, a stable state is reached after 25 iterations. In the validation experiment on path optimization, the cost was reduced by 47.12% compared to the minimum single objective time, and transportation carbon emissions saw a reduction of 28.23%. Similarly, compared to the lowest target for transportation carbon emissions, the cost was reduced by 39.48% and the time was reduced by 38.12%. Compared to the lowest target for transportation carbon emissions, the time was reduced by 32.02% and the carbon emissions were reduced by 19.23%. Notably, the transportation multi‐objective path optimization model showed significant improvement compared to the single‐target model. The research method has been proven to be superior, and can offer the most optimal transportation route guidance for participants in multimodal transportation. Furthermore, it can effectively tackle the issue of node selection convergence and multi‐objective optimization, while also serving as a valuable source of data to support the theoretical advancement of multimodal transportation network path optimization.
Subject
Modeling and Simulation,Control and Systems Engineering,Energy (miscellaneous),Signal Processing,Computer Science Applications,Computer Networks and Communications,Artificial Intelligence
Reference30 articles.
1. A novel method for the detection of road intersections and traffic rules using big floating car data;Hu R;IET Intellig Transp Syst,2022
2. Probing inter‐modality: visual parsing with self‐attention for vision‐and‐language pre‐training;Xue H;Adv Neural Inform Process Syst,2021
3. Non-isomorphic Inter-modality Graph Alignment and Synthesis for Holistic Brain Mapping
4. Intermodality differences in statistical learning: phylogenetic and ontogenetic influences;Polyanskaya L;Ann N Y Acad Sci,2022
5. Resilient marginal cities by encouraging intermodality strategies;Di Ruocco I;TeMA—J Land Use Mobility Environ,2022