AGFSM: An new FSM based on adapted Gaussian membership in case retrieval model for customer-driven design
AGFSM: An new FSM based on adapted Gaussian membership in case retrieval model for customer-driven design
复制标题
DOI：
10.1016/j.eswa.2010.07.067
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Jin Qi;Jie Hu;Ying-hong Peng;Wei-ming Wang;Zhenfei Zhang
中科院分区：
文献类型：
--
作者：
Jin Qi;Jie Hu;Ying-hong Peng;Wei-ming Wang;Zhenfei Zhang
在客户驱动设计中，重用解决先前问题的设计经验是一种潜在的方法论，而案例检索（CR）过程是一个主要步骤过程，其中案例之间的相似性度量（SM）是其核心。然而，针对模糊、模糊和不精确的客户需求执行高检索精度和低计算复杂度的CR模型对研究人员来说是一个巨大的挑战，很少有研究尝试研究客户驱动设计的CR模型。本文在CR模型中提出了一种新的基于自适应高斯隶属度的客户驱动设计模糊SM（FSM）方法，即AGFSM。 AGFSM根据需求信息建立自适应高斯隶属度，同时通过遗传算法（GA）优化调整参数。随后，获得相应的局部相似度（LS）和全局相似度（GS）。为了找到更合适的设计方案，推荐具有较高适合系数（SC）的相似案例，而不是相似度，作为最终的设计方案。此外，我们以电力变压器设计为例，说明采用AGFSM的CR模型的过程，并与其他FSM方法进行比较，验证其优越性。因此，在检索精度和计算复杂度方面，AGFSM 比以前的 FSM 方法更有效。
In customer-driven design, reusing the design experiences of solving previous problems is a potential methodology, and the case retrieval (CR) process is a major step process, in which similarity measurement (SM) among cases is its core. However, performing the CR model with high retrieval accuracy and low computational complexity for the fuzzy, vague and imprecision customer requirements is a huge challenge for researchers and few studies attempt to research the CR model for customer-driven design. This paper proposes a new fuzzy SM (FSM) method in CR model which based on adapted Gaussian membership for customer driven design, i.e., AGFSM. In AGFSM, the adapted Gaussian membership is established based on demand information, meanwhile, the adjustment parameter is optimized via genetic algorithm (GA). Subsequently, the corresponding local similarity (LS) and global similarity (GS) are obtained. In order to find the more proper design solution, the similar case with higher suitable coefficient (SC), instead of similarity degree, is recommended as the finally design solution. Furthermore, we take power transformer design as an example to illustrate the process of the CR model with AGFSM and compare with other FSM methods to validate its superiority. As a result, the AGFSM is more efficient than previous FSM methods on the basis of retrieval accuracy and computational complexity.