Design is a complex, iterative, and innovative process. By traditional methods, it is difficult for designers to have an integral priori design experience to fully explore a wide range of design solutions. Therefore, refined intelligent design has become an important trend in design research. More powerful design thinking is needed in intelligent design process. Combining cognitive dynamics and a cobweb structure, an intelligent design method is proposed to formalize the innovative design process. The excavation of the dynamic mechanism of the product evolution process during product development is necessary to predict next-generation multi-image product forms from a larger design space. First, different design thinking stimulates the information source and is obtained by analyzing the designers’ thinking process when designing and mining the dynamic mechanism behind it. Based on the nonlinear cognitive cobweb process proposed by Francisco and a natural cobweb structure, the product image cognitive cobweb model (PICCM) is constructed. Then, natural cobweb predation behavior is simulated using a stimulus information source to impact the PICCM. This process uses genetic algorithms to obtain numerous offspring forms, and the PICCM’s mechanical properties are the energy loss parameters in the impact information. Furthermore, feasible solutions are selected from intelligent design sketches by the product artificial form evaluation system based on designers’ cognition, and a new product image cognitive cobweb system is reconstructed. Finally, a case study demonstrates the efficiency and feasibility of the proposed approach.
On the basis of investigation of directional characterization of product kansei image,it is proposed that the quantification-Ⅰ theory should be used.Supported by the investigational theory of kansei engineering system,the form design elements in product design are decomposed and corresponding mathematic model for their analysis is developed to discuss quantitatively the relationship of product form design elements to the psychological kansei image of the consumers.Using foregoing investigation result,a practicable program software has been developed,being a guidance for subsequent design.Finally,a verification from practical application is presented,showing that the method presented is reasonable and feasible as well.
To enhance the segmentation accuracy of car front face elements such as headlights and grilles for car front face design, and to improve the superiority and efficiency of solutions in automotive partial modification design, this paper introduces MD-TransUNet, a semantic segmentation network based on the TransUNet model. MD-TransUNet integrates multi-scale attention gates and dynamic-channel graph convolution networks to enhance image restoration across various design drawings. To improve accuracy and detail retention in segmenting automotive front face elements, dynamic-channel graph convolution networks model global channel relationships between contextual sequences, thereby enhancing the Transformer’s channel encoding capabilities. Additionally, a multi-scale attention-based decoder structure is employed to restore feature map dimensions, mitigating the loss of detail in the local feature encoding by the Transformer. Experimental results demonstrate that the MSAG module significantly enhances the model’s ability to capture details, while the DCGCN module improves the segmentation accuracy of the shapes and edges of headlights and grilles. The MD-TransUNet model outperforms existing models on the automotive front face dataset, achieving mF-score, mIoU, and OA metrics of 95.81%, 92.08%, and 98.86%, respectively. Consequently, the MD-TransUNet model increases the precision of automotive front face element segmentation and achieves a more advanced and efficient approach to partial modification design.
The product form serves as a crucial information carrier for expressing design concepts and encompasses significant valuable references. During the product iteration process, changes in design subjects, such as designers and decision-makers, result in substantial variability and uncertainty in the direction of product form evolution. To address these issues, an evolutionary design method for product forms based on the gray Markov model and an evolutionary algorithm is proposed in this study. Firstly, quadratic curvature entropy is utilized to quantify historical form features of product evolution. Subsequently, the original data on product form feature evolution are fitted and predicted using the gray Markov model, thereby obtaining the predicted value of the latest generation of product form features, which is determined to be 0.14586. Finally, this study uses this predicted value to construct a fitness function in the framework of an evolutionary algorithm, which in turn identifies next-generation product forms that can stimulate designers’ creative thinking. The method’s application is illustrated using the side outer contour of the Audi A4 automobile as an example. The research findings demonstrate that combining the gray Markov model with an evolutionary algorithm can effectively simulate designers’ understanding of previous generations’ design concepts and achieve stable inheritance of these design concepts during product iteration. This approach mitigates the risk of abrupt changes in design concepts caused by designers and decision-makers due to personal cognitive biases, thereby enhancing product development efficiency.
Abstract The use of constant weights reduces the accuracy of cognitive evaluation results, and the current design decision-making methods ignore the relationships between Kansei images. To solve these problems, an improved cobweb grey target decision-making method for multiple Kansei images based on variable weight theory is proposed. We take a hand-held electric drill as an example for exploration. First, according to the initial weight relationships of Kansei images, variable weight theory is used to identify the Kansei image variable weights of samples, and the variable weight comprehensive evaluation results for each sample are obtained. Then, based on the correlation and angle of the Kansei images, a cobweb diagram is drawn to represent the Kansei image relationship of each sample. Combined with the cobweb grey target decision-making model for multiple Kansei images, an improved cobweb grey target decision-making method for multiple Kansei images is constructed. The decision coefficients of 10 samples are obtained as 0.0567, 0, 0.0205, 0.0478, 0.0155, 0.0272, 0.0292, 0.0402, 0.0155 and 0.0470. Through the comparison and ranking of the decision coefficients, sample 2 is determined to be the relatively optimal design reference sample. Finally, the constructed model is compared with the cobweb grey target decision-making model for multiple Kansei images and the technique for order preference by similarity to ideal solution (TOPSIS). The difference coefficients of the three methods are obtained, namely, 0.5627, 0.4957 and 0.3613. The results show that the difference coefficient of the proposed method is the largest, and it can reflect the decision-making thinking of designers and improve the discrimination among the decision-making results to a certain extent.
Customer knowledge of a target image is an important and primary research topic related to the product design and development process. This paper presents research on product target image reasoning based on complex network theory and game theory. First, through an evaluation of the correlations among images, a complex network structure diagram with image words as nodes is constructed, and the network attributes of node degree, betweenness and closeness to the centre of the network are calculated. Then, based on the related methods of game theory, the weights of the three network attributes are evaluated, and a comprehensive calculation is carried out on the image to obtain the target image. Finally, an image entropy algorithm is used to validate the results. Taking a scooter as an example, a complex network of 12 image words is constructed by collecting the evaluations of a total of 12 subjects from different professional fields on 8 scooter samples; thus, the verification of the case is completed. This paper provides a more efficient and accurate target image evaluation method for product design or development, which is a new proposal for the product intelligent design process.
Product serialization design is an effective method for product family development.To explore the development law of product serialization, the kansei image change law within the series, and the interaction mechanisms of kansei image and form between the series, this paper proposes an evolutionary design method of product form inspired by Spider-webs.Inspired by the special structure and mechanical properties of Spider-webs in nature, at the macro level, we use the structure of the Spider-webs to describe the relationship between products in the product family.At the micro level, based on the mechanical properties of spiderwebs, we analyzed the development law of the product form within and between the series in the product family and then proposed a calculation method for the crossover coefficient and variation coefficient (in the genetic algorithm) for product form evolution.This method provides a scientific basis for determining the crossover coefficient and the variation coefficient from a new perspective.The case study results show that this model can effectively simulate the changing laws of design cognition and the evolution laws of product form, thereby providing a theoretical basis for the intelligent design of product form in a product family.
Particle swarm optimization algorithm is a newly developed evolutionary algorithm. Compared with other evolutionary algorithms, it converges more quickly, its rules are more simple and the programming is easier. Based on PSO, a data processing method of profile tolerance error for scroll wrap is presented. Its distinguishing characteristic is that the position of measuring data can be adjusted automatically to adapt to the position of machining data during the process of calculation. As a result, the position error between the measuring data and the machining data is separated and eliminated from the profile tolerance error. Used in practice, this method runs simply, quickly and economically.
Applying the frame and theory of Kansei Engineering system, the product styling design method based on neural network is presented. Firstly, the consumer's preference of kansei image is abstracted with the classifying survey and image survey. Then new samples are designed to carry out the image survey again. Thirdly, the nonlinearity evaluate model of product image is established based on neural network, whose process of back propagation will reason out the design knowledge database and evaluate new designed product. Therefore, the method will be applied to aid product styling design availably. At last, it proves the method is feasible and reasonable using the example validation and designing the applied CAD system.
Delivering the right product experience, which is a user's reflection of a combination of functionality, usage, cost and appearance, is a key factor for product acquisition and commercial success. Establishing and representing the relation between a product's shape and the perceived aesthetic sensibility it elicits on a person (kansei), is a key factor in the design of tools to support designers in delivering the right product's appearance. This paper presents an approach to mathematically represent a product's kansei based on the frequency signature (harmonics) of a shape. This mathematical representation should allow the automatic indexing and retrieval of images from a repository of design precedents. This is done through a series of experiments aiming at determining the relation between images, kansei words and the frequency signatures of those images. Tests suggest the method is promising and can be used for indexing images in Content Based Image Retrieval Systems.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
