Treffer: Investigation on Intelligent Design Method of Tunnel Portal Based on Case-based Reasoning.

In order to apply the experience of previous tunnel cases to the design of new tunnels to solve the problem of heavy workload and low efficiency of traditional design methods, an intelligent design method of tunnel portals based on case-based reasoning is proposed. Combined with the characteristics of tunnel portal engineering, the main factors affecting tunnel portal design are selected, and the influencing factors are divided into 12 attribute units to represent the project cases. The weight of each attribute unit is assigned by using the hierarchical weighting calculation method of triangular fuzzy number, and the similarity decision-making model of tunnel portal design scheme is established by using the similarity theory. Based on GIS technology, the tunnel portal project case base is developed to realize the storage and management of existing projects. At the same time, the SQL query language and Python calculation script are used to realize the calculation of case attribute eigenvalue and the most similar matching. After further modification, the design decision of tunnel portal construction scheme can be realized. A mountain tunnel is taken as an example to verify the intelligent design method, the results show that: according to the calculation results of attribute unit eigenvalue, the existing project with the highest similarity to the proposed tunnel is Feng Huang Mountain Tunnel, and the similarity is 0.707. Therefore, when the threshold value is set to 0.7, the retrieval rate and matching accuracy of the case base can be accelerated. This method draws on the experiences of existing engineering cases and can be applied to the decision-making design of tunnel portal construction schemes and used as a reference for the intelligent design of tunnel portal schemes in the future. [ABSTRACT FROM AUTHOR]

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)