Product Design Award Prediction Modeling: Design Visual Aesthetic Quality Assessment via DCNNs

Wu, Jianfeng; Xing, Baixi; Si, Huahao; Dou, Jian; Wang, Jin; Zhu, Yanzi; Liu, Xiaojian

doi:10.1109/access.2020.3039715

Cited by 12 publications

(5 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of this cycle is to improve mechanical properties through the design, production, and evaluation cycle in the first three stages. However, 3D model sets are limited for reasons such as differences in model representation methods [35].…”

Section: Methodsmentioning

confidence: 99%

“…Although the presented approach obtained coarser results than topology optimization methods, it converged faster. In another design evaluation study, Wu et al [35] proposed a CNN model that predicts the success of a product from product sheets generated for design competitions. In another study, Oh et al [20] aimed to produce aesthetic wheel designs with high engineering performance by integrating topology optimization and boundary equilibrium GANs (BeGANs).…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components

Yüksel,

Börklü

2024

Applied Sciences

View full text Add to dashboard Cite

This study aimed to improve the mechanical properties of 3D concept designs by combining the design capability of a generative adversarial network with finite element analysis. This approach offers an innovative perspective on the conditioning of generative models while improving design properties and automation. A new design and evaluation framework has been developed for GAN models to generate 3D models with improved mechanical properties. The framework is an iterative process that includes dataset generation, GAN training, and finite element analysis. A “joint” component used in the aerospace industry is considered to demonstrate the proposed method’s effectiveness. Over six iterations, an increase of 20% is recorded in the average safety factor of the designs, and the variety of designs produced is narrowed in the desired direction. These findings suggest that the direct generation of structural components with generative models can expand the potential of deep learning in engineering design. Another innovative aspect of this study is that it provides a new option for the conditioning of data-dependent generative design models.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components

Yüksel,

Börklü

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In the field of product design evaluation, ResNet is starting to be applied for design evaluation, enhancing traditional design evaluation methods. For example, Wu et al [51] developed an evaluation prediction model for the products of an industrial design competition based on a deep neural convolutional network (DCNN) and introduced the SEFL-ResNet (squeeze-and-excitation Focal-ResNet) model to accurately predict the evaluation of product design awards. Wang et al [52] trained the side profiles of lifting machinery using ResNet and presented an artificial intelligence decision-making model for lifting machinery.…”

Section: Residual Neural Networkmentioning

confidence: 99%

A Study of Sustainable Product Design Evaluation Based on the Analytic Hierarchy Process and Deep Residual Networks

Lin,

Deng,

et al. 2023

Sustainability

View full text Add to dashboard Cite

Traditional product design evaluation processes are resource-intensive and time-consuming, resulting in unsustainably higher costs and longer lead times. Therefore, sustainable product design evaluation has become an increasingly crucial aspect of product design, focusing on creating a high-efficiency, high-reliability, and low-carbon-emission approach. In this study, we proposed an integrated approach that combines manual design evaluation based on the analytic hierarchy process (AHP) with an automatic design evaluation based on a ResNet-50 network in order to develop a sustainable design evaluation method. First, the evaluation level and indicators for the shape design of a tail-light were defined using the AHP. We followed this by establishing a determination matrix and weight coefficients for the design indicators to create a manual design evaluation model. Second, tail-light shape image datasets were manually annotated based on the evaluation indicators, and design datasets were constructed. The ResNet-50 algorithm was introduced to train the datasets, and the automatic evaluation model for product design was constructed through training and tuning. Finally, we validated the feasibility and effectiveness of the product design evaluation method, which was based on AHP and ResNet-50, by comparing the results obtained using both manual design and automatic design evaluations. The results showed that the proposed sustainable product design evaluation model provides an efficient and reliable method for evaluating product design, improves the decision-making process, and empowers the design and development process. The model enhances resource efficiency and economic sustainability.

show abstract

“…Such assessments can be of benefit to professional and amateur food makers, restaurant critics, photographers and travelers. Wu [19] reveals the overall quality of the design through the analysis of the image features. It is assumed that visual aesthetics can be used as a clue for the modeling of prize classification, and this hypothesis is proven by the design competition submissions.…”

Section: B Convolutional Neural Networkmentioning

confidence: 99%

Evaluation and Design Method for Product Form Aesthetics Based on Deep Learning

et al. 2021

View full text Add to dashboard Cite

Currently, evaluations of products from aesthetics are mostly carried out with knowledge expressions of aesthetic features as tools, achieving remarkable results. However, obtaining a large aesthetic feature vocabulary is a challenge because of the experience of researchers and the comprehension abilities of subjects. In addition, due to manual feature extraction, the sample sizes of experimental dataset are generally small, leading to results with poor generalization. To address this problem, a method of aesthetic evaluation and form design for products based on deep learning was proposed. First, a crawler tool was used to collect the front images of cars with corresponding appearance ratings, and a dataset was constructed with users' intuitive and simple ratings as the labels. A deep convolutional neural network (CNN) was designed, and a grading threshold was used as the classification basis. During the process of training the network, batch normalization and other methods were used to optimize the network, and good classification effects were achieved. Based on the above work, an adversarial neural network was used for the aesthetic design of a product form, a shape sketch of an automobile front face was generated, the proposed evaluation model was used to evaluate it, and the result obtained was excellent. These results show that the method used in this study can correctly evaluate product form aesthetics and then generate a design scheme with a high aesthetic level, thereby providing powerful technical support for the intelligent design of product forms.

show abstract

Product Design Award Prediction Modeling: Design Visual Aesthetic Quality Assessment via DCNNs

Cited by 12 publications

References 80 publications

A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components

A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components

A Study of Sustainable Product Design Evaluation Based on the Analytic Hierarchy Process and Deep Residual Networks

Evaluation and Design Method for Product Form Aesthetics Based on Deep Learning

Contact Info

Product

Resources

About