A Smart Data Driven Monitoring and Control Approach: Application to Rotomolding

智能数据驱动的监测和控制方法：在滚塑中的应用

• 批准号: 543532-2019
• 负责人: Mhaskar, Prashant
• 金额: $ 5.83万
• 依托单位: McMaster University
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=699612
• 关键词: Smart; Data; Driven; Monitoring; Control

Increased availability of sensing and computing, and the increasingly competitive market conditions have opened up challenges and opportunities to utilize this new data to improve the process economics. The aim of the present proposal is generally aligned with the goals of Smart Manufacturing 4.0, Use of Big Data, Machine learning approaches and utiliziation of the appropriate modeling technique to address the specific needs of the industrial partner, Imperial Oil. In particular, while there has been a significant resurgence of Machine Learning in the recent past, many of the application have typically been in pattern recognition. The excellent success also motivates the evaluation of these approaches in the context of process manufacturing, and comparing with other traditional and recent advances in data driven modelling approaches. The aim of the proposal is to provide a tool that can be readily implemented and utilize the appropriate data driven modeling algorithm within an automation framework. The project will result in the plants making better use of the available resources through improved automation and utilizing process systems engineering techniques.

传感和计算可用性的提高，以及竞争日益激烈的市场条件，为利用这些新数据来改善工艺经济性带来了挑战和机遇。本提案的目的大体上与智能制造4.0的目标一致，使用大数据、机器学习方法和利用适当的建模技术来满足工业合作伙伴帝国石油公司的特定需求。特别是，虽然机器学习在最近出现了显著的复兴，但许多应用通常是在模式识别方面。这种巨大的成功也促使人们在流程制造的背景下对这些方法进行评估，并将其与数据驱动建模方法中的其他传统和最新进展进行比较。该提案的目的是提供一种易于实现的工具，并在自动化框架内利用适当的数据驱动的建模算法。该项目将通过改进自动化和利用工艺系统工程技术，使工厂更好地利用现有资源。