Special issue on recent advances in design analytics

Design Analytics is a paradigm to develop a successful product through analysing heterogeneous data from various sources like CAD/CAM, Knowledge Management Systems, Manufacturing Internet-of-Things, Social Network etc. The promise of product and design analytics has been wide-spread and more engineering designers are attempting to extract valuable knowledge from large-scale data.

Considering this data has great benefits for Manufacture, Procurement, Environment, Serviceability, Reliability, Consumption etc., how to utilize modelling and analytics effectively and efficiently plays a great role in mining the potential knowledge. The enormous amount of data in different fields, which often has the characteristics of a heterogeneous structure and multimedia dimension, has the power to promote a new technology revolution. However, how to integrate this valuable data with the product design requires rigorous data processing, insightful data analysis and an environment stimulating innovative management.

Today, growing attention is being drawn in the engineering community to the use of data-driven methods in decision-making to develop products. There are a variety of analytical techniques which contain predictive analytics, data mining, case-based reasoning, exploratory data analysis, business intelligence and machine learning techniques that could help firms to mine unstructured data. However, the constraints in the design domain lead to new requirements and challenges for both design methodologies and data analytics, where product developments are desirable from traditional mathematical models and emerging technologies to deal with the multi-dimensional demands and multi-dimensional data.

The aim of this special issue is to provide a forum for researchers and practitioners to review the state-of-the-art methodologies and technologies, and to identify critical issues and challenges for future research in the broadest field of design analytics. Six papers are included in this special issue.

The first paper Affective design using machine learning: a survey and its prospect of conjoining big data by Chan et al. presents a survey of machine learning technology for affective design. Product designers can exploit data value for more efficient design. The author provides a classification of machine learning technologies for traditional survey data and points out that research about big data for effective design are limited. The author also discusses the advantages and limitations of using machine learning for effective data, as well as the impact of small and big data for effective design. The paper is oriented to researchers who use machine learning for affective design and provides guidelines for data technology research in affective design.

The second paper Extraction of affective responses from customer reviews: An opinion mining and machine learning approach by Li et al. proposes an opinion mining approach based on Kansei Engineering (KE) and machine learning to extract and measure users’ affective responses to products from online customer reviews. Five types of machine learning algorithms are applied, including Support Vector Machine (SVM), Support Vector Regression (SVR), Classification and Regression Tree (CART), Multi-Layer Perceptron (MLP) and Ridge Regression (RR). An experiment has been conducted to illustrate the proposed approach. The results show that SVM+SVR is the best performer. It achieved a recall, precision and F1 score of more than 80% for the classification of the soft-hard attribute with the smallest mean square error. Based on the proposed method, designers and manufacturers can effectively know customers’ responses to products through inputting the review texts to facilitate the process of product design.

The third paper An integrated decision-making method for selecting machine tool guideways considering remanufacturability by Ding et al. presents an integrated multi-criteria decision-making (MCDM) approach for guideway selection during product development, the approach combines an improved analytic hierarchy process(AHP) and connection degree-based technique of ranking preferences by similarity to the ideal solution (CD-TOPSIS) method. This overcomes the traditional shortcomings of AHP and TOPSIS with a more realistic and objective result. Also, sensitivity analysis is provided to evaluate the robustness of the method. Results shows the reliability of the decision support for machine tool guideway selection for remanufacturing.

The fourth paper A blockchain based service composition architecture in cloud manufacturing by Yu et al. proposes a blockchain-based cloud manufacturing architecture to enhance information transparency and decentralisation. In this architecture, timely Qos-attributes can be obtained, smart contract can be used to enable direct negotiation between users and services providers, manufacturing resources as services can be purchased by the user through this platform. Furthmore, a particle swarm optimisation (PSO) is used to solve the quality of service (Qos) aware service composition model. Finally, a simulation service composition in blockchain-based cloud manufacturing is implemented.

The fifth paper Application of green-modified value stream mapping to integrate and implement lean and green practices: A case study by Zhu et al. presents a green-modified value stream mapping model by using carbon efficiency and carbon emission as evaluation indicators. The model identifies the integrating level of time flow, energy flow, material flow, and transportation flow at each phase of the production process from the perspective of seven wasted and converts them into carbon emission flow. Manufacturing process performance can be visualized and assessed according to this framework, challenges related with lean and green practices integration and implemented are also overcome. A carbon efficiency model to eliminate wastes is proposed to analyse carbon emission flow of various wastes. A case study focused on metal stamped parts production is used to evaluate the effectiveness of this method.

The sixth paper A design knowledge management model for civil aircraft cabin based on Markov Logic Networks by Want et al. presents a design knowledge management (DKM) model for the civil aircraft cabin, by analysing design knowledge flow patterns among users, decision-makers, designers, and engineers. This research establishes a mapping model of a civil aircraft cabin between historical design cases and new designs. A Markov Logic Networks based design knowledge management framework is proposed by integrating time series into the DKM system to facilitate the knowledge matching. An application of this framework is provided for a civil aircraft cabin.