Bridges will have various structural problems and damage, and how to maintain and make decisions on them becomes a troublesome problem. In this article, fuzzy logic and genetic algorithm are applied to bridge maintenance decision to provide decision support and optimization scheme. Fuzzy logic is used to deal with the uncertainty and fuzziness in bridge maintenance decision. Fuzzy set, fuzzy rule and fuzzy reasoning are used to transform fuzzy input into fuzzy output. Genetic algorithm is used to optimize multiple decision variables in bridge maintenance decision making. By simulating the process of natural evolution, the optimal solution space is searched, and the value of decision variables is gradually optimized. The experimental results show that the maintenance time of this method is 10–16 days, while the traditional method is between 20–35 days, which means that in the maintenance process, the waste and redundancy of resources are avoided through reasonable resource allocation and decision-making, thereby reducing the maintenance time. The maintenance cost and maintenance time required by the proposed method are lower than that of the traditional method. The model can effectively support bridge maintenance decision-making and provide an accurate and reliable decision scheme.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Application of Fuzzy Logic and Genetic Algorithm in Bridge Maintenance Decision

  • Manli Tian

摘要

Bridges will have various structural problems and damage, and how to maintain and make decisions on them becomes a troublesome problem. In this article, fuzzy logic and genetic algorithm are applied to bridge maintenance decision to provide decision support and optimization scheme. Fuzzy logic is used to deal with the uncertainty and fuzziness in bridge maintenance decision. Fuzzy set, fuzzy rule and fuzzy reasoning are used to transform fuzzy input into fuzzy output. Genetic algorithm is used to optimize multiple decision variables in bridge maintenance decision making. By simulating the process of natural evolution, the optimal solution space is searched, and the value of decision variables is gradually optimized. The experimental results show that the maintenance time of this method is 10–16 days, while the traditional method is between 20–35 days, which means that in the maintenance process, the waste and redundancy of resources are avoided through reasonable resource allocation and decision-making, thereby reducing the maintenance time. The maintenance cost and maintenance time required by the proposed method are lower than that of the traditional method. The model can effectively support bridge maintenance decision-making and provide an accurate and reliable decision scheme.