This blog was written in collaboration with Paige Marie Morse, Aspen Technology’s industry marketing director for the chemicals sector.
Many capital-intensive organizations are evolving their Industrial AI and sustainability strategies to lead the way in creating the plant of the future. This is an intriguing development because these two mega-trends are rarely discussed in a unifying context and are often thought of as independent of each other. But, in fact, AI and sustainability are both mutually catalytic and synergistic, as they share the same underlying business drivers of creating a better plant of the future — by enabling safer, greener, longer and faster operations.
In this blog, we look at the three key industry trends that lie at the confluence of AI and sustainability, examine how they impact the future of industrial operations, and share examples of use cases that support companies’ business transformation journeys.
Multi-Dimensional Optimization: A New Reality
We often see industrial organizations faced with tradeoffs and decisions across a multitude of business goals, and one of the more contentious balancing acts is the one between productivity and sustainability goals.
Traditionally, process industries have optimized operations for productivity, quality and profitability. But with heightened awareness on sustainability, societal and industrial shifts driven by climate change and the enforcement of regulations, the operations of tomorrow will need to optimized across multi-dimensional business objectives — including sustainability goals.
Some use cases for this technology include:
AI-enabled modeling and analytics of process data to improve the energy consumption and production capacity of industrial machines — thereby reducing emissions while also delivering on economic goals
Sustainability-related risk assessments of company locations
Deep-learning-optimized APC solutions to stabilize production and enable higher throughput with less resource consumption
Furthermore, Industrial AI can be used to optimize materiality and stakeholder analyses, or to significantly improve the accuracy of calculating emissions. As a result of comprehensive plant digitization initiatives, the data necessary for these complex, multivariable decisions is increasingly available; it just has to be harnessed with intelligent algorithms through Industrial AI.
Real-World Use Case
An AspenTech customer, a leading global ethylene producer, wanted to reduce the energy consumed in their ethylene unit with minimal capital investment. Using the Aspen Plus® modeling system, we created a digital twin of the operation, then analyzed the data from operations and equipment using Aspen Energy Analyzer™.
Based on our recommendations, 20 energy-saving projects were implemented. The customer saw an estimated $10M USD increase in profit, a 3-4% reduction in energy consumption and a 3% contribution to sustainability metrics.
Predictive Analytics Are Pivotal to the Future of Safety, Sustainability and Productivity
As we envision industrial operations in the new normal, safety and sustainability are two of the most important business dimensions for asset-intensive industries of the future. One example is the use of predictive analytics generated through Industrial AI, which can substantially reduce unplanned “flaring.” The World Bank estimates that flaring contributes more than 350 million tons of CO2 emissions globally every year, the equivalent of approximately 90 coal-fired power plants. These emissions could be significantly reduced by increasing equipment reliability to eliminate unplanned shutdowns and the flaring that comes with them.
Predictive maintenance can also dramatically improve safety. The Chemical Safety Board (CSB) asserts that unplanned startups and shutdowns contribute to 50% of safety incidents in the refining industry.
With recent product introductions of Aspen Mtell® and Aspen Fidelis Reliability™, AspenTech helps companies turn unplanned downtime into planned downtime, employing models that provide recommendations on how to maintain greenhouse gas emission limits and operate within safety parameters. AI-driven predictive maintenance can warn industrial operators of potential smart equipment failures days, weeks or months in advance, reduce the number of unplanned shutdowns and keep production within safe operating limits.
Real-World Use Case
Several industrial organizations are employing AI to accelerate their safety, sustainability and productivity goals, and recently China National BlueStar (Group) chose AspenTech to accelerate their digitalization via embedded artificial intelligence. This partnership will enable BlueStar to achieve significant production improvements throughout its specialty chemicals business.
Early prediction of process deviations means they can avoid product quality issues and mitigate unplanned downtime via predictive and prescriptive analytics on all their critical equipment. By accelerating their digital transformation journey, BlueStar is positioned to capitalize on global market opportunities in a volatile, uncertain, complex and ambiguous (VUCA) world.
Greener Operations With Strong ROI: AI-Powered Innovation and Carbon Capture
Environmental regulations, energy and water conservation, air quality and climate change are prime concerns for industrial organizations and their customers alike. In particular, the circular economy of plastics requires a “full-cycle” approach to production and extended use to conserve resources and protect the environment. With solutions that leverage insights enabled by AI and machine learning, companies can pursue renewable energy projects such as bioethanol, biodiesel, carbon capture, solar and wind initiatives — giving them the ability to improve profitability and reliability while reducing capital investments.
Another key area of focus is carbon capture from industrial operations to mitigate climate change. AspenTech is continually investing significant resources in the development of a highly effective embedded AI modeling applications to support design, validation and commercial scale-up of carbon capture technology, an approach that increases model accuracy, quality and performance across the entire industrial asset lifecycle.
Real-World Use Case
An AspenTech customer, a global manufacturing business, wanted to achieve a company-wide goal of a 10.3% reduction in energy consumption and greenhouse gases by 2020. They used Aspen Performance Engineering solutions to identify over 250 methods for reducing energy consumption.
This company has implemented 31 of these methods to date, saving a total of $19.2M USD per year. This means the $22.4M USD capital spent is paid back in 1.2 years, along with a 12% reduction in energy use and carbon emissions, as well as a future opportunity to achieve another 15% reduction in energy use.
An Illustration of Digital Solutions for Chemicals Across the Lifecycle
Based on the trends highlighted in this graphic (adapted from SusChem), it is evident that industrial AI and digital solutions are key enablers of sustainability goals. In fact, digital transformation strategies are increasing their emphasis on sustainability-related objectives, mainly focusing on energy efficiency, pollution control and value chain optimization.
Traditionally, cost savings drove much of the efficiency efforts, but now companies are moving toward the more specific process metrics that consider emissions and resource use. Additionally, companies are increasingly focusing on waste and discharge reduction from production units, as well as efficiency enhancements through digital technology.
The International Energy Agency (IEA) has found that Industrial AI and digital solutions can help boost energy efficiency as much as 30% for industrial operations. The next-generation of asset optimization solutions will provide the visibility, analysis and insight needed to address the challenges inherent in meeting sustainability goals.
To learn more about how digital solutions are helping companies address their responsibility to the environment, please read our recent executive brief Sustainability Takes Center Stage.