Collaborative Research: FW-HTF-P: IntelEUI: Artificial Intelligence and Extended Reality to Enhance Workforce Productivity for the Energy and Utilities Industry

合作研究：FW-HTF-P：IntelEUI：人工智能和扩展现实可提高能源和公用事业行业的劳动力生产力

• 批准号: 2129092
• 负责人: Xiaoli Yang
• 金额: $ 8万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2022-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2129092&HistoricalAwards=false
• 关键词: Collaborative; Research; FW; HTF; IntelEUI

Emerging computing technologies have been recently employed for industrial training and predictive maintenance in several industries to improve workforce productivity and increase manufacturing and production. However, there is limited adoption of technologies in Energy and Utilities Industries (EUIs). There is also a wide gap between the jobs to be filled and the skilled pool capable of filling them in EUIs. Additionally, the aging workforce is creating a risk of losing workers with hands-on field expertise. Maintaining contemporary equipment for power generation, storage, transmission, and distribution in EUIs is expensive and arduous as they are more versatile and inherently complicated. Therefore, challenges arise for their efficient and productive maintenance. The project aims to design a framework that will meet the needs of smart training and predictive maintenance in EUIs by employing emerging technologies and develop a working prototype of the framework. The project investigators collaborate with EUIs to design the framework. In the long-term, the improved training will reduce the skill gap between skilled and less-skilled workers and increase situational awareness and safety in the workplace. The predictive maintenance model will reduce costs by predicting maintenance needs and downtime of equipment.The project integrates cutting-edge technologies in the framework design and development including Artificial Intelligence (AI), Machine Learning (ML), and Extended Reality (XR) to improve workforce productivity through customizable and effective training, enhance work efficiency, and reduce cost on unplanned maintenance. State-of-the-art ML methods will be applied to develop the predictive maintenance module of the framework to improve reliability and sustainability of various equipment in EUIs that will eventually save time, human efforts, and increase customer satisfaction. Comprehensive measures and metrics will be employed to assess the technology, economic, and social impact of the framework in the industry context. A set of research questions is proposed to understand how AI and XR technology is transforming work and workforce in EUIs. The project findings will be disseminated to the academic and industry community through a dedicated website, research publications, and social media platforms.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

最近已采用新兴计算技术来进行几个行业的工业培训和预测维护，以提高劳动力生产率并提高制造业和生产。但是，能源和公用事业行业（EUIS）的技术采用有限。在要填补的工作与能够在EUI中填充它们的熟练游泳池之间也存在很大的差距。此外，老龄化的劳动力正在造成失去动手现场专业知识的工人的风险。维护EUIS发电，存储，传输和分销的当代设备昂贵且艰巨，因为它们更具用途和固有的复杂性。因此，其高效和生产性维护会带来挑战。该项目旨在设计一个框架，该框架将通过采用新兴技术并开发框架的工作原型来满足EUIS智能培训和预测性维护的需求。项目调查人员与EUIS合作设计框架。从长远来看，改进的培训将减少熟练和技能较低的工人之间的技能差距，并提高工作场所的情境意识和安全性。预测维护模型将通过预测维护需求和设备的停机时间来降低成本。该项目将尖端技术整合在框架设计和开发中，包括人工智能（AI），机器学习（ML）和扩展现实（XR），以改善通过可定制和有效的培训，提高工作效率并降低计划外维护的成本，劳动力生产力。最先进的ML方法将用于开发框架的预测维护模块，以提高EUI中各种设备的可靠性和可持续性，最终将节省时间，人力努力并提高客户满意度。将采取全面的措施和指标来评估行业背景下框架的技术，经济和社会影响。提出了一系列研究问题，以了解AI和XR技术如何改变EUI的工作和劳动力。该项目的发现将通过专门的网站，研究出版物和社交媒体平台传播给学术和行业社区。该奖项反映了NSF的法定使命，并被认为是值得通过基金会的知识分子和更广泛影响的评估评估的评估来支持的。 。

项目成果

Deep-Learning-Incorporated Augmented Reality Application for Engineering Lab Training

• DOI: 10.3390/app12105159
• 发表时间: 2022-05-01
• 期刊: APPLIED SCIENCES-BASEL
• 影响因子: 2.7
• 作者: Estrada, John;Paheding, Sidike;Niyaz, Quamar
• 通讯作者: Niyaz, Quamar

Augmented Reality and Artificial Intelligence in industry: Trends, tools, and future challenges

• DOI: 10.1016/j.eswa.2022.118002
• 发表时间: 2022-07-08
• 期刊: EXPERT SYSTEMS WITH APPLICATIONS
• 影响因子: 8.5
• 作者: Devagiri, Jeevan S.;Paheding, Sidike;Smith, Samantha
• 通讯作者: Smith, Samantha