Computational Product Design with Artificial Intelligence (Closed)

A topical collection in Machines (ISSN 2075-1702).

Viewed by 10031

Editors


E-Mail Website
Collection Editor
School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China
Interests: networked digital manufacturing; service-oriented manufacturing systems engineering; RFID/ IOT; logistics engineering; product family design theory; collaborative engineering
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Collection Editor
School of Engineering, Cardiff University, Cardiff CF10 3AT, UK
Interests: distributed and sustainable manufacturing; circular economy; informatics; advanced manufacturing; artificial intelligence; design; engineering design
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Collection Editor
State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong Univ., Xi’an, China
Interests: social manufacturing; industrial Internet; cyber physical social system

Topical Collection Information

Dear Colleagues,

Computational product design (CPD) can be roughly separated into innovation categories of experience-driven, model-driven, and data-driven design. Experience-driven CPD usually applies methods such as case-based, ontology-based, and rule-based reasoning, knowledge graphs, etc., to reuse explicit design experience from experts. Model-driven CPD usually begins by building the geometrical, functional, or mechanistic models of the design targets and then conducting different kinds of simulations, optimization procedures, or design calculations. Data-driven CPD usually depends on extracting design-related information from historical data with machine learning algorithms to support different forms of design solution generation, optimization, evaluation, decision making, etc.

Rapid-developing artificial intelligence (AI) techniques have recently brought radical changes to the manufacturing industry in the fields of intelligent manufacturing and services. However, the application of AI in CPD is still in its infancy, and the exploitation of AI to realize improved innovation, efficiency, cost reduction, etc., in CPD still requires further exploration.

In this regard, this Topical Collection aims to share research related to AI and its application in CPD, from design requirement analysis to detailed design and design evaluation. Original research articles, reviews, communications and technical notes are welcome, and the topics covered may include, but are not limited to:

  • Theory and framework on computational product design methodology with artificial intelligence;
  • Computational geometry and graphics issues in product design;
  • Datasets and deep learning for 3D shapes and product semantics;
  • Representation learning for 3D shapes and product semantics;
  • Intelligent generative and retrieval models for product design including text2shape, voice2shape, sketch2shape, image2shape, graph2shape, etc.;
  • AI-assisted UX design;
  • AI-assisted design information and knowledge management;
  • AI-assisted decision-making for design;
  • Data-driven approaches for conceptual design;
  • Design process modelling with artificial intelligence including knowledge graphs;
  • Finite element analysis and optimization;
  • Machine learning-based topology optimization;
  • Bond graphs and Modelica for dynamics issues in early-stage product design;
  • Design optimizations with swarm intelligence;
  • Intelligent parameterized CAD;
  • Product design under the context of social manufacturing;
  • Collaborative design with collective intelligence including crowdsourcing;
  • Industrial Internet for open product design;
  • Kansei engineering and emotional computing in product design;
  • Smart generative design for additive manufacturing;
  • Smart conceptual design methods;
  • Design for smart products using AI and machine learning
  • Smart product family and platform design;
  • Intelligent design for product-service systems;
  • Smart maintenance design for products;
  • Computational layout design and digital simulation for manufacturing systems;
  • Case studies for industrial applications.

Please notice that authors can submit their papers to the Topical Collection at any time. Papers will be published online immediately after their acceptance and without delay caused by whether all paper collections are ready. It is different from the policy of traditional special issue.

Prof. Dr. Pingyu Jiang
Prof. Dr. Ying Liu
Dr. Maolin Yang
Collection Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the collection website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machines is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (5 papers)

2023

Jump to: 2022

21 pages, 25813 KiB  
Article
Uncertainty Analysis and Design of Air Suspension Systems for City Buses Based on Neural Network Model and True Probability Density
by Cheng Li, Yuan Jing and Jinting Ni
Machines 2023, 11(8), 791; https://doi.org/10.3390/machines11080791 - 01 Aug 2023
Viewed by 784
Abstract
The accuracy of uncertainty analysis in suspension systems is closely tied to the precision of the probability distribution of sprung mass. Consequently, traditional assumptions regarding the probability distribution fail to guarantee the accuracy of uncertainty analyses results. To achieve more precise uncertainty analysis [...] Read more.
The accuracy of uncertainty analysis in suspension systems is closely tied to the precision of the probability distribution of sprung mass. Consequently, traditional assumptions regarding the probability distribution fail to guarantee the accuracy of uncertainty analyses results. To achieve more precise uncertainty analysis outcomes, this paper proposes a data-driven approach for analyzing the uncertainties in bus air suspension systems. Firstly, a bus vehicle dynamics model is established to investigate the influence of sprung mass on suspension system performance. Subsequently, a deep neural network model is trained using road test data, for the accurate identification of the sprung mass. The historical mass of the bus is then computed using vehicle network data to obtain the true probability density of the sprung mass. Lastly, the real probability distribution of the sprung mass is utilized to perform uncertainty analysis on the bus suspension system, and the results are compared with those obtained by assuming a probability distribution. Comparative analysis reveals substantial disparities in uncertainty response, with a maximum relative error of 9% observed for wheel dynamic loads, thus emphasizing the significance of precise probability distribution information concerning the sprung mass. Full article
Show Figures

Figure 1

20 pages, 28072 KiB  
Article
Developing and Testing of the Principle Prototype for Efficient Micro-Damage Fine Stripping of Asphalt on the Surface of Reclaimed Asphalt Pavement
by Long Zhou, Shanshan Wang, Jizhe Zhang, Bin Zou, Meng Wang, Wenwu Zhang, Xin Lv, De’an Meng, Xueliang Hu, Zhanyong Yao and Lei Li
Machines 2023, 11(3), 367; https://doi.org/10.3390/machines11030367 - 08 Mar 2023
Viewed by 1366
Abstract
In the current recycling process of reclaimed asphalt pavement (RAP), due to the serious damage of aggregate gradation and the large amount of aged asphalt still wrapped around the surface of the treated aggregate, the low recycling rate and poor performance of the [...] Read more.
In the current recycling process of reclaimed asphalt pavement (RAP), due to the serious damage of aggregate gradation and the large amount of aged asphalt still wrapped around the surface of the treated aggregate, the low recycling rate and poor performance of the recycled asphalt mixture are the major problems of RAP. In view of the shortcomings of RAP recycling technology, it is urgent to research new treatment methods and design specialized asphalt-stripping equipment to solve the existing problems. In this paper, based on theoretical analysis and EDEM discrete element simulation, a principle prototype for efficient micro-damage fine stripping of asphalt on the RAP surface is developed and tested. The results demonstrate that the principle prototype has a satisfactory asphalt-stripping effect and achieves fine stripping of aged asphalt on the surface of aggregate without large-scale crushing. This principle prototype has significant engineering application values, which provides design solutions and data support for further equipment development. Full article
Show Figures

Figure 1

16 pages, 5402 KiB  
Article
A Blockchain Approach of Model Architecture for Crowdsourcing Design Services under the Context of Social Manufacturing
by Dianting Liu and Dong Liang
Machines 2023, 11(1), 69; https://doi.org/10.3390/machines11010069 - 05 Jan 2023
Cited by 2 | Viewed by 1258
Abstract
Crowdsourcing design is generally monitored by the platform. However, the traditional crowdsourcing platforms face problems such as centralization, lack of credibility and vulnerability to single point of failure. Under the context of social manufacturing, how to address these potential issues has both research [...] Read more.
Crowdsourcing design is generally monitored by the platform. However, the traditional crowdsourcing platforms face problems such as centralization, lack of credibility and vulnerability to single point of failure. Under the context of social manufacturing, how to address these potential issues has both research and substantial value. In this paper, we introduce decentralized blockchain technology for crowdsourcing service systems and propose a method to manage and control the process of crowdsourcing design services. We depict complex crowdsourcing logic by smart contract. The process of crowdsourcing design is not dependent on any third party. It is decentralized, tamper-proof, traceable and protects the privacy of users to a certain extent. We implement this crowdsourcing design system on a specific blockchain test network to experiment and test its functionalities. Experiment results show the feasibility and usability of our crowdsourcing design system. In the future, we will further improve the algorithmic logic of smart contracts so that they can run stably and securely in a complex node network environment. Full article
Show Figures

Figure 1

2022

Jump to: 2023

19 pages, 4448 KiB  
Article
Text2shape Deep Retrieval Model: Generating Initial Cases for Mechanical Part Redesign under the Context of Case-Based Reasoning
by Tianshuo Zang, Maolin Yang, Wentao Yong and Pingyu Jiang
Machines 2022, 10(11), 967; https://doi.org/10.3390/machines10110967 - 22 Oct 2022
Cited by 1 | Viewed by 1664
Abstract
Retrieving the similar solutions from the historical case base for new design requirements is the first step in mechanical part redesign under the context of case-based reasoning. However, the manual retrieving method has the problem of low efficiency when the case base is [...] Read more.
Retrieving the similar solutions from the historical case base for new design requirements is the first step in mechanical part redesign under the context of case-based reasoning. However, the manual retrieving method has the problem of low efficiency when the case base is large. Additionally, it is difficult for simple reasoning algorithms (e.g., rule-based reasoning, decision tree) to cover all the features in complicated design solutions. In this regard, a text2shape deep retrieval model is established in order to support text description-based mechanical part shapes retrieval, where the texts are for describing the structural features of the target mechanical parts. More specifically, feature engineering is applied to identify the key structural features of the target mechanical parts. Based on the identified key structural features, a training set of 1000 samples was constructed, where each sample consisted of a paragraph of text description of a group of structural features and the corresponding 3D shape of the structural features. RNN and 3D CNN algorithms were customized to build the text2shape deep retrieval model. Orthogonal experiments were used for modeling turning. Eventually, the highest accuracy of the model was 0.98; therefore, the model can be effective for retrieving initial cases for mechanical part redesign. Full article
Show Figures

Figure 1

18 pages, 2616 KiB  
Article
A Conceptual Design Specification Based on User Aesthetic Information Analysis and Product Functional Reasoning
by Huicong Hu, Ying Liu, Xin Guo and Chuan Fu
Machines 2022, 10(10), 868; https://doi.org/10.3390/machines10100868 - 27 Sep 2022
Cited by 2 | Viewed by 3061
Abstract
User satisfaction with a product plays a direct role in the purchasing decisions. With the enrichment of material life and the growth of individual requirements, this satisfaction is derived from the requirement for functionality to aesthetics. Conventional product design methods normally focus on [...] Read more.
User satisfaction with a product plays a direct role in the purchasing decisions. With the enrichment of material life and the growth of individual requirements, this satisfaction is derived from the requirement for functionality to aesthetics. Conventional product design methods normally focus on achieving the required functions where its design specifications are mainly related to certain functional or usability requirements. In recent years, researchers have made efforts to develop methods for supporting aesthetic design activities during the product conceptual design phase. However, most of these methods hardly consider product aesthetics or the consumers’ emotional needs. Therefore, this study proposed a user-driven conceptual design specification integrating functional reasoning with aesthetic information analysis. The method consisted of two tasks, the construction of a mapping model and the implementation of the mapping model. Firstly, the mapping model was constructed for capturing the relationships between initial design specifications and user experience (UX). Secondly, the proposed design specifications were selected, refined, and optimized based on the mapping model. A case study on digital camera design was carried out to demonstrate the feasibility and effectiveness of the proposed method. The results showed that, compared with the initial design specification candidates, the UX was enhanced by applying the improved design specifications. Full article
Show Figures

Figure 1

Back to TopTop