A System Behavioral Approach to Big Data-driven Nonlinear Process Control

大数据驱动的非线性过程控制的系统行为方法

• 批准号: DP210101978
• 负责人: Prof Jie Bao
• 金额: $ 31.5万
• 依托单位: The University of New South Wales
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2021
• 资助国家: 澳大利亚
• 起止时间: 2021-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP210101978
• 关键词: System; Behavioral; Approach; Big; Data

This project aims to develop a novel process control approach that utilises big process data to improve the cost-effectiveness of industrial processes. Existing monitoring systems in the industry have been collecting a tremendous amount of process operation data but little effort has been made to use the big process data to enhance process operations. Based on the system behavioural approach and dissipativity theory, integrated with machine learning techniques, this project expects to develop a novel framework for data-driven control using big process data. The outcomes are expected to benefit the Australian process industry, where many processes are controlled by inadequate logic controllers, by improving their operational efficiency.

该项目旨在开发一种新颖的过程控制方法，利用大过程数据来提高工业过程的成本效益。行业中现有的监控系统已经收集了大量的过程操作数据，但在利用过程大数据来增强过程操作方面却很少做出努力。该项目基于系统行为方法和耗散理论，结合机器学习技术，期望开发一种利用大过程数据进行数据驱动控制的新颖框架。预计这些成果将有利于澳大利亚流程工业，通过提高其运营效率，澳大利亚流程工业的许多流程都是由不充分的逻辑控制器控制的。