Deep Learning for Automated Product Design

Krahe, Carmen; Bräunche, Antonio; Stricker, Nicole; Lanza, Gisela

doi:10.1016/j.procir.2020.01.135

Cited by 27 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning algorithms such as generative adversarial networks (GANs) (Goodfellow et al 2020) and autoencoders (Bank et al 2020) can effectively be used to encode the data in which they are trained and generate new data, and hence are applied to generate designs in 2D (Quan et al 2018; Raina, McComb et al 2019), 3D (Khan and Awan 2018; Shu et al 2020), and point cloud (Achlioptas et al 2018; Krahe et al 2020) formats. With such capabilities, GANs have also been leveraged for data-driven generative design models (Li et al 2021), synthesizing designs with interpart dependencies (Chen and Fuge 2019), generating 3D designs for physics-based simulations (Zhang et al 2019), and generate designs based on class, characteristics, and dimensions conditions (Krahe et al 2020). Such effective utilization of GANs has also been applied to generating designs for topological optimization of designs conducted in the subsequent detailed stage (Oh et al 2019; Kallioras and Lagaros 2020).…”

Section: Findings and Discussionmentioning

confidence: 99%

Mapping artificial intelligence-based methods to engineering design stages: a focused literature review

Khanolkar,

Vrolijk,

Olechowski

2023

AIEDAM

View full text Add to dashboard Cite

Engineering design has proven to be a rich context for applying artificial intelligence (AI) methods, but a categorization of such methods applied in AI-based design research works seems to be lacking. This paper presents a focused literature review of AI-based methods mapped to the different stages of the engineering design process and describes how these methods assist the design process. We surveyed 108 AI-based engineering design papers from peer-reviewed journals and conference proceedings and mapped their contribution to five stages of the engineering design process. We categorized seven AI-based methods in our dataset. Our literature study indicated that most AI-based design research works are targeted at the conceptual and preliminary design stages. Given the open-ended, ambiguous nature of these early stages, these results are unexpected. We conjecture that this is likely a result of several factors, including the iterative nature of design tasks in these stages, the availability of open design data repositories, and the inclination to use AI for processing computationally intensive tasks, like those in these stages. Our study also indicated that these methods support designers by synthesizing and/or analyzing design data, concepts, and models in the design stages. This literature review aims to provide readers with an informative mapping of different AI tools to engineering design stages and to potentially motivate engineers, design researchers, and students to understand the current state-of-the-art and identify opportunities for applying AI applications in engineering design.

show abstract

Section: Findings and Discussionmentioning

confidence: 99%

Mapping artificial intelligence-based methods to engineering design stages: a focused literature review

Khanolkar,

Vrolijk,

Olechowski

2023

AIEDAM

View full text Add to dashboard Cite

show abstract

“…Hence, AI has been defined in many ways. Some AI definitions are shown in [4,[19][20][21]. Wang, et al [4] have provided the following high-level definition of AI : "The theories, methodologies, technologies, and tools that are intended to understand human intelligence, develop artificial systems with intelligence, empower artefacts to perform intellectual tasks, and leverage computational means to simulate intelligent behaviours".…”

Section: Artificial Intelligence In Product Design a Artificial Intel...mentioning

confidence: 99%

“…The paper validated possibility way for using AI-aided design of tissue scaffolds which might lead to an automated design. In addition, Krahe, et al [20] aim to automate product design by implementing Deep Learning algorithms to identify design patterns to a product family out of their underlying latent representation, in this study focus on a class of table, chair and sofa, and use the extracted knowledge to automatically generate new latent object representations fulfilling different product feature specifications. Obviously, this study provides the trend to become an automated design to support smart manufacturing, the product family can be created according to give a product specification, but still need to improve in term of dimension error.…”

Section: B) Product Form Designmentioning

confidence: 99%

“…Decision trees, Multi-Layer Perceptron, and K-means Clustering [23], Nearest Neighbour Search (NNS) [35], CNN [37] Prediction of structure and properties 3D Convolution Neural Network (3D-CNN) [34] Predictive 3D model 3D Convolution Neural Network (3D-CNN) [19], Generative Adversarial Networks (GANs) [20] Probabilistic methods using N-Grams, Neural Network (NNs), and Bayesian Networks (BNs) [38] It can be observed that existing data (e.g., CAD library, existing pattern of product family, previous data design) is attractive to many researchers in order to facilitate designers to reduce design time-consuming and design mistake during product design stage. As mentioned above, Bermejillo Barrera, et al [19] and Krahe, et al [20] aim to use the historic data to transfer the conventional design into automate by using AI. On the other hand, Vasantha, et al [38] use the previous data design, such as features and configurations, to provide a predictive CAD system in order to suggest design engineer for valve design.…”

Section: Materials Selectionmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Artificial Intelligence in Product Design for Smart Manufacturing

Aphirakmethawong

Yang

Mehnen

2022

2022 27th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

Artificial intelligence (AI) has received significant attention nearly from every part of the world because it is a critical technology approach to develop intelligent systems. The manufacturing sector is one part which exploits AI, especially in the product design stage towards smart manufacturing. The aim of this paper is to present an overview on how AI enhances the product design stage for smart manufacturing. First, the paper gives the overall understanding of smart manufacturing about its definition, importance, and characteristics. Then, it delivers a brief overview of product design and product design stages. The essential concepts of AI techniques as well as various AI applications in product design ranging from conceptual design, embodiment design and detail design are discussed. Finally, research challenges and future directions for using AI in product design are provided and discussed.

show abstract

“…With the advancement in digital technologies, we are now employing new digital technologies while developing products. Technologies such as Cloud [17], [18] and [19], Deep Learning [20], [21], [22] and [23], Virtual Reality [24], [25], [26], [27] and [28], Augmented Reality [29], [30], [31], [32] and [33] and Mixed reality [34], [35], [36], [37] and [38] are widely used at different stages of product development. Customer data from various sources especially those from the internet [39], [40], [41], [42], [43], [44] and [45] are extensively used in NPD.…”

Section: Introductionmentioning

confidence: 99%

Designing a Poultry Barn: A Collaborative Design Approach Using Virtual Reality

Pradeep¹,

Selvabharathi²

2021

Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, In

View full text Add to dashboard Cite

Visualizing a new design in Virtual Reality (VR) is now a part of product development pipeline in several industries. Several researchers have demonstrated attaining higher level of immersion by creating photoreal virtual environments and by using advanced devices which are now available in the market to get higher level of tracking accuracy and higher degree of interaction. In this work, we have explored the possibility of using the VR technology during the design phase with a multidisciplinary approach. Through this work, we have demonstrated that a regular Head Mounted Display (HMD) which lacks several features when compared to the pricier ones is sufficient for product development and visualization. Using VR, we even managed to design the building which will house the product that we developed. We have chosen a poultry farm that breeds chickens for this study and solved their problem of repetitive manual work by designing an automated feeding system. We manged to all this with the same virtual environment that we have developed for the purpose of this study.

show abstract

Deep Learning for Automated Product Design

Cited by 27 publications

References 13 publications

Mapping artificial intelligence-based methods to engineering design stages: a focused literature review

Mapping artificial intelligence-based methods to engineering design stages: a focused literature review

An Overview of Artificial Intelligence in Product Design for Smart Manufacturing

Designing a Poultry Barn: A Collaborative Design Approach Using Virtual Reality

Contact Info

Product

Resources

About