Automation Fair 2023: Process Efficiency in the Mining and Cement Industries
ROK Studio Interview
Kalypsonians Kerryn Sakko, regional delivery manager - APAC, and Juliano de Goes Arantes, digital account executive, joined ROK Studio at Automation Fair 2023 to discuss the application of Model Predictive Control (MPC) in the heavy industries.
Mining is one of the most resource-intense industries that comes with unique challenges such as:
- Complex ore minerality
- Remote operations
- Need to deliver the product within specifications to the market as quickly and effectively as possible
What is MPC and when is it best to apply a Pavilion8 solution?
MPC is the next step in optimization after the traditional control system. It is a multi-variable control technology that handles multiple inputs and outputs, control and optimizing industrial processes while complying with defined constraints and optimization objectives. As part of AI, MPC is a closed-loop, prescriptive analytics solution.
We apply MPC for continuous processes, such as mining, minerals and cement. When we look at trying to apply MPC, we're looking to solve problems such as:
- Different performance between shifts
- Large variability in quality
- Lack of information or high-quality information
The FactoryTalk Analytics Pavilion8 Software platform utilizes machine learning (ML) and other techniques to build models to simulate a process's behavior to control and optimize a plant. When looking at your business objectives, MPC can improve throughput, reduce variability, improve quality and reduce energy usage.
We have the expertise and resources to mitigate the above issues using machine learning and process knowledge to create soft sensors, like virtual online analyzers (VOA), to increase controller performance and robustness. Our goal is to understand the process, talk to our clients and understand their needs.
Check out our latest case study to learn more about how we helped Newcrest Mining maximize efficiency and profitability across processing plants with Model Predictive Control
Authors
