Brasil Mineral - Issue 441 - July 2024
EQUIPMENT & TECHNOLOGIES
AI Use Increases Mineral Processing Production
Fabio Suizu, CEO of BrainiAll
Using Artificial Intelligence to optimize industrial processes - this is the focus of BrainiAll, a company that recently came to Brazil and is initially focused on the mining segment, where any productivity improvement results in significant financial gains, given the value of the minerals being produced.
Fabio Suizu, CEO of BrainiAll
According to the company's founder and CEO, Brazilian Fabio Suizu, a former Microsoft executive with a strong leadership background in cutting-edge data technology, AI, and industrial processes, the use of AI in optimizing ore processing can generate very significant productivity gains. He cites the case of a gold mining company in Brazil, where the application of BrainiAll's technology enabled a 6% increase in grinding operation production rates using the same equipment - in other words, using data through AI to generate value, which is BrainiAll's core expertise.
According to the CEO, the decision to focus on the mining sector arose from contacts with mining companies while he was still at Microsoft, where it was found that they faced the challenge of dealing with increasingly lower-grade and harder ores. "The easy, high-grade, and abundant ore has already been mined over the last 200 years," he says. Therefore, ore processing today is increasingly challenging, especially in grinding, because it is very difficult to grind hard, low-grade ore while maintaining process quality.
He also noticed that to face these challenges, mining companies are already well-served in terms of equipment and have a good level of automation and data generation. Therefore, what mining companies need is greater agility in analyzing process parameter data, and this is where the use of Artificial Intelligence is of great help.
"The data is there, but they don't use it. How does it work? There are operators and engineers who sit there, looking at screens, using outdated software. So, they generate billions, or tens or even hundreds of billions of data points in a year, but they hardly use any of it because it's a human being looking at the data, observing what's happening there, and thousands of data points are coming in every second. Typically, the operator looks at one or another data point, makes some adjustment, some machine setpoint. And sometimes they rely on super-simple software supporting those people.
What does our software do? It reads everything - which is what I used to do for Microsoft - all the data, finds where the problems and failures are, and corrects everything automatically, adapting to situations without the need for human intervention," explains the executive, adding that AI controls the machines and makes all parameter adjustments to maintain maximum possible productivity.
In the case of the mentioned gold mining company, production increased by 6% without a drop in particle size quality and using 3% less energy. A positive aspect of BrainiAll's operation, according to Suizu, is that in just two weeks, the software is installed and running.
Additionally, the software can, based on data analysis - in the gold mining company, two years of operational data were analyzed - predict production performance degradation and make micro-adjustments, for example in mill pressure, power, and speed, to maximize production and reduce equipment wear.
"Therefore, we stabilize the process, which has less variance. The equipment is much less stressed. Within a few hours, AI starts adjusting, and the equipment begins to operate in 'cruise mode,' generating the production increase. In the cited example, the increase was 6%, but we plan to soon exceed 10%. Because the future is, using Artificial Intelligence, analyzing data point by data point, meticulously, making these adjustments in millions of data points and performing fine-tuning," says the CEO.
For him, humans weren't made to think about thousands of variables in data points in seconds and make decisions like increasing a SAG mill's power by 3% or accelerating a ball mill's speed by 2%. "But computers and AI were made for this." He adds that AI allows analyzing the entire process, point by point, and making it work in the most optimized way possible. "This is what we're doing: the machines will allow the engineering and operations team to be freed up to take care of other things where human input is needed and generate more value for the company," concludes the Brainiall executive.
"Originally published in Brasil Mineral - Issue 441 - July 2024"
