基于模糊推理网的高层结构智能型式优化方法与系统

A high-rised structural intelligent form optimization method and support system based on fuzzy inference network

首先,给出了一种改进加权模糊推理网,建立了基于该推理网的结构性能评价过程与方法,该网兼有模糊综合评判、模糊推理与模糊推理网等算法共同优点;然后,给出了一种基于模糊综合评判的优选法,将其与六个目标级性能的评价网集成,形成了兼有性能评价与优选功能的集成推理网络系统,给出了该集成系统的网络结构图及其决策函数,同时,建立了基于上述方法的结构智能型式优化支持系统;最后,给出了工程实例,结果与实际吻合。实践表明:该方法能以直观的方式表征、存储与利用领域专家在型式优化时的知识与策略,并克服了传统基于模糊逻辑与神经网络的型式优化系统的不足,是解决具有多目标、多层次及不确定信息的型式优化问题的有效方法。

At first, an improved weight fuzzy inference network having the common algorithms＂ advantages of fuzzy composite evaluation, fuzzy inference and fuzzy inference network is set up and the topologi- cal structure and algorism of the network are also given. Then, an optimum selection method which based on fuzzy composite evaluation is given. With the integration of the optimum selection method with six performance evaluating networks, an integral inference network framework of performance evaluation and optimum selection decision is set up and its topological structure diagram and decision functions are also given. At the same time, the structural intelligent form-optimization support system based on the above method is also constructed. Finally, a case study of an engineering application is given, the result fits well with real engineering projects, which proves that the method presented in this paper can in an intuitive manner express, store up and make use of all kinds of information and maneuver used by domain experts. The result also proves that the method which can effectively overcome the deficiency of traditional form-optimization system based on fuzzy logic and neural network, is an effective way in solring multi-objective, multi-level and un-certain problems of structural form optimization.