Engineering & Mining Journal

MAR 2019

Engineering and Mining Journal - Whether the market is copper, gold, nickel, iron ore, lead/zinc, PGM, diamonds or other commodities, E&MJ takes the lead in projecting trends, following development and reporting on the most efficient operating pr

Issue link:

Contents of this Issue


Page 37 of 67

ENERGY EFFICIENCY 36 E&MJ • MARCH 2019 reported a successful effort to apply ma- chine learning to predict wind-farm power output more than a day in advance. Sims Witherspoon, a program man- ager at Deepmind, and Will Fadrhonc, Carbon Free Energy program lead at Goo- gle, wrote in a February blog post that a program that began last year has applied machine learning algorithms to 700 MW of wind power capacity in the central United States. These wind farms — part of Google's global array of RE projects — collectively generate as much electricity as is needed by a medium-sized city. "Using a neural network trained on widely available weather forecasts and historical turbine data, we configured the DeepMind system to predict wind power output 36 hours ahead of actual generation," they said. "Based on these predictions, our model recommends how to make optimal hourly delivery commit- ments to the power grid a full day in ad- vance. This is important because energy sources that can be scheduled (i.e., can deliver a set amount at a set time) are often more valuable to the grid. "Although we continue to refine our algorithm, our use of machine learning across our wind farms has produced pos- itive results. To date, machine learning has boosted the value of our wind energy by roughly 20%, compared to the base- line scenario of no time-based commit- ments to the grid." The authors didn't explain what the "value" increase of the wind energy was based upon, but it's likely that a large portion of this figure could be attributed to operational cost savings. Efficient Usage Regardless of the source, how electrici- ty is used on-site is critical in achieving improved energy efficiency. Comminution consumes an estimated 50% or more of electricity at most operations, with mo- tors, drives and pumps using the lion's share of that amount. For that reason, it pays to work closely with motor and drive equipment suppliers that can offer spe- cific models, systems and advice to op- timize energy usage — particularly about how new technology, combined with pro- per component selection and attentive maintenance, can make a difference en- ergy-wise. Here are two examples: For customers seeking overall improve- ments in plant performance, including en- ergy efficiency, ABB's announcement of a contract award from KAZ Minerals last year provides a glimpse of available wide-scope, integrated enhancements. ABB said it will deliver a comprehensive process and pow- er solution that will double the capacity of KAZ Minerals' sulphide ore processing plant in Aktogay, Kazakhstan. According to ABB, this project is the third major order from the customer and will reuse the en- gineering and solution configuration from the company's two other production lines in the area. KAZ Minerals is the largest copper producer in Kazakhstan. ABB will provide its ABB Ability Mi- neOptimize integrated process and power control solution, which includes all process control and electrification equipment and infrastructure for the plant. ABB Ability Mi- neOptimize is a framework that encompass- es engineering, systems, applications and services to help mining customers achieve Challenge your material limits Nothing should stand in the way of productivity – least of all the materials you move. Our compact Hägglunds direct drive systems give you high availability, but also the means to adapt to the job at hand. We'll support you too, with an agile global network and smart connectivity to bring you peace of mind. We Move. You Win.

Articles in this issue

Links on this page

Archives of this issue

view archives of Engineering & Mining Journal - MAR 2019