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-ofThings, 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 multidimensional 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), MultiLayer 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 INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2020, VOL. 33, NO. 7, 643–644 https://doi.org/10.1080/0951192X.2020.1800097

中文翻译：

---

关于设计分析最新进展的特刊

设计分析是通过分析来自各种来源（如 CAD/CAM、知识管理系统、制造物联网、社交网络等）的异构数据来开发成功产品的范式。设计师正试图从大规模数据中提取有价值的知识。考虑到这些数据对制造、采购、环境、可服务性、可靠性、消费等有很大好处，如何有效地利用建模和分析在挖掘潜在知识方面发挥着重要作用。不同领域的海量数据，往往具有异构结构和多媒体维度的特点，具有推动新技术革命的力量。然而，如何将这些有价值的数据与产品设计相结合，需要严谨的数据处理、富有洞察力的数据分析和激励创新管理的环境。今天，工程界越来越关注在决策中使用数据驱动的方法来开发产品。有多种分析技术，包括预测分析、数据挖掘、基于案例的推理、探索性数据分析、商业智能和机器学习技术，可以帮助公司挖掘非结构化数据。然而，设计领域的限制给设计方法和数据分析带来了新的要求和挑战，其中产品开发需要从传统数学模型和新兴技术来处理多维需求和多维数据。本期特刊的目的是为研究人员和从业者提供一个论坛，以回顾最先进的方法和技术，并确定最广泛的设计分析领域未来研究的关键问题和挑战。本期特刊收录了六篇论文。Chan 等人的第一篇论文使用机器学习进行情感设计：一项调查及其结合大数据的前景。介绍了用于情感设计的机器学习技术的调查。产品设计师可以利用数据价值进行更高效的设计。作者对传统调查数据的机器学习技术进行了分类，并指出对大数据进行有效设计的研究是有限的。作者还讨论了将机器学习用于有效数据的优势和局限性，以及小数据和大数据对有效设计的影响。该论文面向使用机器学习进行情感设计的研究人员，并为情感设计中的数据技术研究提供指导。第二篇论文从客户评论中提取情感反应：Li 等人的意见挖掘和机器学习方法。提出了一种基于感性工程（KE）和机器学习的意见挖掘方法，从在线客户评论中提取和衡量用户对产品的情感反应。应用了五种类型的机器学习算法，包括支持向量机 (SVM)、支持向量回归 (SVR)、分类和回归树 (CART)、多层感知器 (MLP) 和岭回归 (RR)。已经进行了一个实验来说明所提出的方法。结果表明，SVM+SVR 的表现最好。对于均方误差最小的软硬属性的分类，它实现了80%以上的召回率、准确率和F1分数。基于所提出的方法，设计师和制造商可以通过输入评论文本来有效地了解客户对产品的反应，从而促进产品设计过程。第三篇论文 丁等人的一种考虑再制造性的机床导轨选择综合决策方法。提出了一种用于产品开发过程中导轨选择的综合多标准决策 (MCDM) 方法，该方法结合了改进的层次分析法 (AHP) 和连接 INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2020, VOL。33，没有。7, 643–644 https://doi.org/10.1080/0951192X.2020.1800097