Sustainability initiatives often include energy management and emissions management as focus areas for performance improvements. Measurements from the process and added measurements for non-control related monitoring require operational analytics to translate this broad stream of data into actionable information.
In this 4:44 YouTube video, Achieving More Effective Energy Management for Sustainable Operations, Emerson’s Michael Tworzydlo shares how the Plantweb digital ecosystem improves the sustainability of operations by applying advanced analytics to energy and emissions management by using powerful, real-time analytics and artificial intelligence technologies.
Michael opens describing how Plantweb Optics Analytics provides a full energy management information system (EMIS). It collects and interprets operational data and information scattered across the plants, eliminating the need for gathering, analyzing, and reasoning over data and information from control systems, databases, plant applications, and operation procedures. By using artificial intelligence (AI) and machine learning (ML) techniques, Plantweb Optics Analytics can detect abnormal behavior of process and assets in real time and help predict future performance.
He showed a Plantweb Optics Analytics display that provided a broad overview of overall plant energy consumption and unit energy consumption for key units with their current trends.
While this top-level EMIS information has been common in most systems, what’s added is being able to drill down to specific plant assets—pumps, distillation columns, boilers, and many others. This drill-down view shows what is consuming more energy compared to baseline performance. This capability provides a great way to zoom in and see exactly how energy is being used.
Embedded AI and ML technology enables dynamic targets to be set based on current operating conditions within the plant, such as when a piece of equipment is out of service or production rates are changed. These dynamic targets automatically adjust to show the optimal energy usage under these changed conditions and identify gaps.
Another key element is root cause analysis which identifies suboptimal performance, the impact of the issue, and why it is suboptimal. For example, if a boiler is not operating at optimal performance levels, not only is the problem flagged and communicated to the right staff members, but also the source or sources of the problem and suggested corrective actions.
Another key component in sustainability is emissions management. The traditional approach has been to continuously monitor emissions in the flare stack, gas-powered turbines and other emission areas. Using the power of AI and ML, continuous monitoring becomes predictive emissions management.
Plantweb Optics Analytics also serves as a predictive emissions monitoring system (PEMS), taking process parameters such as pressures, temperatures and flow rates and builds a model to see how these process variables equate with greenhouse gas emissions, sulfur oxides (SOx), nitrogen oxides (NOx), and other emissions.
Just like dynamic targets in energy management, dynamic targets can be set for emissions to identify when these emissions aren’t within their specified ranges.
The Plantweb Optics Analytics software provides a scalable approach to energy management and emissions management and provides actionable information to the right people at the right time to drive sustainability performance improvements.
Visit the Plantweb section on Emerson.com for more on Plantweb Optics Analytics and other key technologies and solutions in the Plantweb digital ecosystem. You can also connect and interact with other operational analytics experts in the IIoT & Digital Transformation group in the Emerson Exchange 365 community.
The post Improving Sustainability through Effective Energy and Emissions Management appeared first on the Emerson Automation Experts blog.