基于区间二型模糊的深基坑施工方案属性相似度计算方法

Method for Attributes Similarity of Deep Excavation Construction Plans Based on Interval Type-2 Fuzzy

属性相似度计算是案例推理方法在深基坑工程施工技术方案重用的关键。传统经验进行取值下再转换成同一类型的值计算相似度的方法,存在着属性取值模糊不够准确、属性取值转换带来信息损失等缺点,影响着案例检索的效果。本文引入区间二型模糊方法对方案的不确定属性进行区间模糊取值来提升对不确定属性的表达和刻画,提出依据方案属性取值类型不同的特点,直接选取适应的相似度(距离)算法计算属性相似度。然后再结合属性的权重计算方案综合相似度,该思路能够有效地避免不同属性的含义类型和取值差异在统一化转化中信息损失的缺点。最后,通过地铁车站深基坑工程案例检索分析验证了方法的有效可行性,结果表明该方法能够较好地考虑方案属性的模糊取值进而直接进行相似度计算,提升了检索的效果。

The key of case-based reasoning for the plans reuse in deep excavation construction is to calculate the attribute similarity.Attribute values are traditionally given based on experts’experience and then converted to the sa m e type to calculate their similarity,leading to inaccuracy and information loss during the conversion of attribute value,which affects the performance of case retrieval.Therefore,this paper introduced an interval type 2 fuzzy logic method to obtain the interval fuzzy value of attributes so as to enhance the uncertainty description.Similarity(distance)algorithm is employed to calculate the attribute similarity according to the characteristics of attribute value directly.The comprehensive similarity between projects can be obtained by assigning different weights to the attributes.Finally,a case study was used to test and validate the proposed approach.Results show the proposed approach can effectively consider the uncertainty attribute and calculate similarity directly,which reduces the information loss caused by the conversion of attribute value from one type to another and improves the retrieval performance of construction plans.