Applying a hybrid approach based on fuzzy neural network and genetic algorithm to product form design
Applying a hybrid approach based on fuzzy neural network and genetic algorithm to product form design
复制标题
DOI：
10.1016/j.ergon.2004.10.007
复制
发表时间：
2005-05-01
影响因子：
3.1
通讯作者：
Tsai, HC
中科院分区：
文献类型：
--
作者：
Hsiao, SW;Tsai, HC
在产生新的设计概念时，大多数工业设计师倾向于借鉴刻板印象和自己的个人设计经验。在概念设计阶段，评估每个候选设计是否能够满足市场需求是至关重要的一步。因此，本文提出了一种方法，使一个自动的产品形式搜索或产品形象评价的模糊神经网络和遗传算法。首先，基于特征的分层计算机辅助设计（CAD）模型的构建，其中相关的形状参数被彻底定义在适用的域，以促进新的产品形式的自动生成。然后，应用模糊神经网络算法来建立输入表单参数与一系列形容词图像词之间的关系。在逆向过程中，遗传算法被用来搜索一个接近最优的设计，满足设计师所需的产品形象，通过使用训练的神经网络作为适应度函数。所提出的方法提供了一个自动设计系统，它使设计人员能够快速获得产品的形式和相应的图像，或搜索的理想形式，适合所需的图像在较短的交货期。电子门锁设计被选为当前调查的主题。然而，所提出的方法同样适用于其他产品的设计。与工业的相关性在概念设计阶段，如果产品要在市场上取得成功，企业创造出符合消费者心理偏好的产品形式是非常重要的。本研究中提出的自动设计系统旨在通过集成模糊神经网络和遗传算法来帮助企业实现这一目标，使工业设计师能够创建所需的产品形态。(c)2004 Elsevier B.V.保留所有权利。
When generating new design concepts, most industrial designers tend to draw upon stereotypical images and their own personal design experiences. The evaluation of each individual design candidate in terms of its ability to meet the demands of the marketplace is a crucial step within the conceptual design stage. Consequently, this paper proposes a method which enables an automatic product form search or product image evaluation by means of fuzzy neural network and genetic algorithm. Initially, a feature-based hierarchical computer-aided design (CAD) model is constructed, in which the related form parameters are thoroughly defined in applicable domains to facilitate the automatic generation of new product forms. A fuzzy neural network algorithm is then applied to establish the relationships between the input form parameters and a series of adjectival image words. In a reverse process, genetic algorithm is employed to search for a near-optimal design which satisfies the designer's required product image by using the trained neural network as a fitness function. The proposed method provides an automatic design system, which gives designers the ability to rapidly obtain a product form and its corresponding image, or to search for the ideal form which fits a required image in a shorter lead-time. An electronic door lock design is chosen as the subject of the current investigation. However, the proposed method is equally applicable to the design of other products.Relevance to industry At the conceptual design stage, it is very important that an enterprise creates a product form which meets the consumers' psychological preferences if that product is to be successful within the marketplace. The automatic design system presented in this study is intended to assist enterprises in achieving this objective by integrating fuzzy neural network and genetic algorithm to enable industrial designers to create required product form(s). (c) 2004 Elsevier B.V. All rights reserved.