The Development of the Knowledge Base System to Assist the Optimal Design of Ship Structure.

辅助船舶结构优化设计知识库系统的开发。

• 批准号: 07455393
• 负责人: OHTSUBO Hideomi
• 金额: $ 4.67万
• 依托单位: THE UNIVERSITY OF TOKYO
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 1995
• 资助国家: 日本
• 起止时间: 1995 至 1996
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-07455393/
• 关键词: Ship Structure; Design Modification; Optimal Design; Modeling Phase; Artificial Intelligence; Finite Element Method; Solution Phase; 構造設計; 知識ベース; モデリングフェ〜ズ; 最適解; モデル調整法; ソリュ〜ションフェ〜ズ

The theory of optimal design that gives design modification automatically has been developed since '60^<th>, but the real application of the optimal design used in the product design of manufacturing company is rare. In most of the cases the design changes are made based on the experience of the engineer, and very few design engineers are doing their design based on the mathematical theory.In this study, the artificial intelligence are used to develop the optimal design system that will help doing optimal design in more friendly way. Two phases, namely modeling phase and solution phase are introduced. The modeling phase is the expression of the design in terms of mathematical terms. It automatically generates the mathematical expression needed in the mathematical programming. Solution phase is the development of the intelligent algorithm of nonlinear programming. The assistance of the reasoning is added to traditional mathematical programming method.Finally, the optimal design of large scale structure by multi-level optimization is proposed by dividing the structure into several parts, and optimizing each parts while over all structure is also optimized at the same time. This process has consistency with the real design process of engineering products in which several engineer cooperate each other to develop the design.

自动给出设计修正的优化设计理论自20世纪60年代以来就已发展起来，但真正将优化设计应用于制造企业的产品设计的却很少。在大多数情况下，设计变更是根据工程师的经验进行的，很少有设计工程师是根据数学理论进行设计的。在本研究中，人工智能被用来开发优化设计系统，帮助以更友好的方式进行优化设计。引入了两个阶段，即建模阶段和求解阶段。建模阶段是用数学术语表达设计。它自动生成数学规划所需的数学表达式。求解阶段是非线性规划智能算法的开发。在传统的数学规划方法中加入推理的辅助。最后，提出了大规模结构的多层次优化设计，将结构划分为若干部分，在对各个部分进行优化的同时，对整体结构进行优化。同一时间。这一过程与工程产品的真实设计过程是一致的，即由多个工程师相互协作开发设计。

项目成果

Katsuyuki SUZUKI et al.: "The Optimal Design of Ship Structure by Multi-level Optimization." JOURNAL OF THE SOCIETY OF NAVAL ARCHITECTS OF JAPAN. Vol.178. 405-411 (1995)

Katsuyuki SUZUKI 等人：“通过多级优化进行船舶结构优化设计”。

鈴木克幸 他: "多段階最適化手法による船体構造最適設計" 日本造船学会論文集. Vol.178. 405〜411 (1996)

Katsuyuki Suzuki 等：“使用多阶段优化方法的船体结构优化设计”日本造船学会汇刊 178. 405-411 (1996)。

鈴木克幸 他: "多段階化による大規模構造最適化作業の協調" 応用力学連合講演会講演集. 第45回. 233〜234 (1996)

Katsuyuki Suzuki 等人：“通过多步骤协调大规模结构优化任务”应用力学联盟会议记录第 45 期（1996 年）。

Hideomi OHTSUBO et al.: "The Finite Element Modeling for Different Analysis Demands." JOURNAL OF THE SOCIETY OF NAVAL ARCHITECTS OF JAPAN. Vol.178. 349-355 (1995)

Hideomi OHTSUBO 等人：“针对不同分析需求的有限元建模。”

Hideomi OHTSUBO: "High Performance Computing in CAE." Transaction of the Japan Society of Mechanical Engineers.Vol.62-603. 2402-2406 (1996)

Hideomi OHTSUBO：“CAE 中的高性能计算。”