Abstract
As never before, both environmental and geo-political dependencies are in the focus of the entire world. Many decades-old habits are now being challenged. The still limited availability of renewable energy forces companies to minimize their energy consumption across all processes. On the one hand, conveyor systems for material transport are major energy consumers in the mining industry, on the other hand, those systems are an important enabler for decarbonization of mining. Above all, the focus is sustainable energy supply and efficient operation. One important way to get there is digitization. Digitization affects companies across all industries and sectors, which are striving to make their processes more sustainable and efficient.
While data science and artificial intelligence (AI) are getting more and more utilized in the mining industry, the operators still use just a fraction of their potential. Using AI in a production and processing context means using data to make actionable decisions faster and more accurately than a human. It can help to gain clarity on each process in detail and to identify optimization potential that need to be addressed.
This presentation shows both, how efficient drive solutions can improve the energy efficiency of conveyor operation and how advanced data analytics helps to identify optimization potential on top. One essential part of this presentation is the efficiency aspect of Gearless Conveyor Drives (GCD). Based on two customer use cases, the energy saving potential will be illustrated. A definition of a net specific energy consumption (SEC) will be presented as well. This net SEC eliminates conveyor-specific parameters to enable a clean energy consumption and efficiency analysis. Other use cases show how advanced data science techniques, like Parallel Coordinates Plots (PCP) or Self Organizing Maps (SOM), can help to analyze process performance and to identify optimal process parameters regarding energy consumption.
Presenters: Ulf Richter, GCD Product Manager, ABB IAPI PT
Dr. Martin Handreg, Data Scientist, ABB IPAI PT