Artificial Intelligence Applications in the Chemical Manufacturing Industry

This project aims to address the data and analysis gaps by developing a metric-based framework to quantify energy and environmental implications of AI applications in the production of some of the most common energy-intensive chemicals.


Research team

Yuan Yao

Dr. Yao is an Assistant Professor of Sustainability Science and Engineering at North Carolina State University (NCSU), where she leads the Sustainability Systems Analysis Lab and interdisciplinary research for sustainability at the College of Nature Resources. She got her Ph.D. degree in Chemical Engineering from Northwestern University in the U.S. and a B.S. degree in Metallurgical Engineering from Northeastern University in China. She also has a Management for Scientists and Engineers from Kellogg Business School. Dr. Yao received National Science Foundation CAREER Award in 2019, the most prestigious award from NSF to junior faculty in the United States.

Dr. Yao’s research is motivated by the increasing need of sustainable engineering that can support industrial development without compromising the environment or depleting the resources for future generations. She uses interdisciplinary approaches in industrial ecology, sustainable engineering, operations research, and big data analytics to develop systematic and scientific rigorous methodologies to support engineering and policy decisions towards sustainable development of industries. She collaborates with U.S. national labs, energy consulting firms, and universities to develop quantitative analysis for accelerating RD&D in renewable energy technologies, manufacturing processes, and sustainable bioeconomy.

Project description

The chemical industry is responding to increased energy demand and environmental performance expectations by exploring the use of emerging technologies in the manufacturing process. Artificial Intelligence (AI) is one of these technologies, which shows great potential in reducing the energy consumption and environmental footprints of the chemical industry. However, the lack of system assessment methods and credible performance data for quantifying the environmental and energy benefits of AI may deter policymakers and early adopters, whose investments are crucial for accelerating deployment. This project aims to address this gap by exploring and investigating assessment methods that could be applied to understanding the benefits of different AI applications.


Research questions

What types of unit operations, processes, and product lines may be suitable for the short-term and long-term adoption of AI?

What analysis and assessment methods can be used to estimate the potential energy savings and environmental benefits of AI adoptions? 

What are the best level/scale to analyze and investigate AI opportunities for the chemical industry? 

How to choose, select, and develop indicators and analysis to understand the impacts of different AI applications? 


Methodology

The project will start with a comprehensive literature review to collect case studies of AI applications in the chemical industry. Applications will be categorized based on the levels and scales of adoptions (e.g., facility, unit process, plant, and supply chain levels) and functions (e.g., real-time optimization or enhance process robustness). Then analysis methods for emerging technologies in the chemical industry and relevant industrial sectors will be explored and systematically analyzed. A framework will be developed to provide guidance on selecting, integrating, and applying suitable analytical methods and metrics to quantify the energy and environmental benefits of various types of AI applications.


Broader impacts

Although AI shows great potential in enhancing the sustainability of the chemical industry, it is challenging to quantify the benefits and impacts of AI adoptions due to the lack of system analysis methods and assessment metrics. Quantitative understandings of the benefits of AI adoptions are critical information for policymakers and early adopters of  emerging technologies, whose investments are crucial. Addressing these methods and analysis gaps is critical for improving emerging technology adoption such as AI.