Soft Computing for Fast Multidisciplinary Design Optimization
【摘要】：正Multidisciplinary design optimization using the traditional hard computing techniques is difficult to perform mainly due to conflicting design objectives from many different disciplines. This paper describes how computationally efficient Taguchi techniques combined with soft computing such as fuzzy logic and neural networks can be used to perform fast multidisciplinary design optimization. An aircraft engine cycle design optimization with four conflicting design objectives is used to validate the presented approach. The result obtained shows significant performance improvement in optimizing single and multiple design objectives whenever possible conflict exists among them.