Design methods and tools for mass personalization of smart wearable products

智能可穿戴产品，如腕带、头饰、鞋类和嵌入式植入物，在学术界和工业界都在迅速发展，预计到2026年市场规模将超过2650亿美元[参考文献：MARKETSANDMARKETS]。这些产品可以提供扩展功能（例如，智能头盔中的通信）或帮助收集和分析个人或使用数据，这些数据可能对智能决策有用（例如，用于运动训练的智能鞋类）。当前可穿戴设备面临的一个紧迫问题是，如何经济有效地解决大规模个性化的设计和制造挑战，以避免长期佩戴不适（例如，covid - 19中呼吸器引起的皮肤损伤问题），并提高客户满意度和采用率。大规模个性化设计（DfMP）的概念提供了这种量身定制的需求。该计划的长期目标是建立实现智能和互联产品开发和应用的方法。短期目标是应用网络物理系统（即具有相互交织的物理和网络对象的智能系统），计算设计和增材制造（AM）技术来解决开发数据驱动的DfMP系统的挑战，以支持广泛的个性化可穿戴设备开发。更具体地说，它将有助于了解如何让客户参与协同设计过程，如何实现大规模客户定制设计，以及如何通过增材制造促进设计创新。因此，将开发一套实用的DfMP工具包，包括用于客户偏好输入和快速产品设计和验证的网络物理客户协同设计系统，用于静态和动态产品（例如面罩和鞋垫）的智能个人数据（即解剖和行为数据）通知定制合身设计工具，以及用于功能集成和性能改进的am -兼容DfMP工具。传统的大规模个性化设计方法存在着即时性强、以单代产品为中心、专业知识密集型、设计制造集中化等缺陷。相比之下，拟议的计划将实现客户偏好的重复使用、自动化定制设计过程和分散制造，从而提高客户满意度（例如舒适度）和成本效益。该项目还将帮助培养人工智能（AI）、网络物理系统、AM等高要求领域的hqp，并根据加拿大的泛加拿大人工智能战略，在体育器材、时尚、医疗保健等各个行业孵化智能大规模个性化服务的衍生公司。它将为快速增长的智能可穿戴设备市场做出重大贡献，并帮助加拿大在这一新兴领域获得全球领导地位。

Smart wearable products such as wristwear, headwear, footwear, and embedded implants, are progressing swiftly in both academia and industry with a forecasted market size of over $265 Billion by 2026 [ref: MARKETSANDMARKETS]. These products can offer expanded functions (e.g., communication in smart helmet) or help to collect and analyze personal or use data that can be useful for smart decision making (e.g., smart footwear for athletic training). One pressing issue of current wearables is how to cost-effectively address the design and fabrication challenges of mass personalization for avoiding long-term wearing discomfort (e.g., respirator-induced skin damage issues in Covid19) and improving customer satisfaction and adoption. The concept of design for mass personalization (DfMP) offers such a tailored need. The long-term objective of this proposed program is to establish methods to enable smart and connected product development and applications. The short-term objective is to apply cyber-physical system (i.e., intelligent system with intertwined physical and cyber objects), computational design, and additive manufacturing (AM) technologies to tackle challenges of developing a data-driven DfMP system in support of a wide range of personalized wearables development. More specifically, it will contribute to knowledge of how to involve customers in the co-design process, how to realize mass customer-specific bespoke design, and how to promote design innovation with AM. Accordingly, a set of practical DfMP toolkits will be developed including a cyber-physical customer co-design system for customer preference intake and rapid product design and validation, a smart personal data (i.e., anatomic and behavior data)-informed custom fit design tool for static and dynamic products (e.g., face mask and shoe insoles), and an AM-compliant DfMP tool for function integration and performance improvement. Traditional mass personalization design approaches have deficiencies such as being ad hoc, single-generation product focused, professional knowledge-intensive, and centralized design and fabrication. In contrast, the proposed program will enable customer preference reuse, automated custom-fit design process, and decentralized fabrication with improved customer satisfaction (e.g., comfort) and cost effectiveness. This program will also help to train HQPs in the demanding fields of artificial intelligence (AI), cyber-physical system, and AM as well as incubate spin-off companies in smart mass personalization services for various industries such as sport equipment, fashion, and healthcare in line with Canada's Pan-Canadian AI Strategy. It will significantly contribute to the fast-growing smart wearable device market and help Canada to gain global leadership in this emerging field.