Artificial intelligence applied to mill optimization

Variability controlled with artificial intelligence (AI) software. A digital twin-based AI optimizer was deployed to run alongside advanced process controllers (APCs). Results include a 1% increase in mill production throughput with annual topline impact of $3-4 million for the mine. See 4 objectives for recurrent neural networks and self-adaptive tuning.

By Dominic Gallello February 10, 2021


Learning Objectives

  • Changing raw materials required tighter controls, and AI helped.
  • Digital twin model is driven by AI.
  • Four objectives were applied to recurrent neural networks, self-adaptive tuning.

The grinding mill is one of the largest pieces of equipment used in the mining and minerals industries, and artificial intelligence has been applied to help advanced process control increase throughput 1% and decrease variability for millions of dollars in annual impact for the mine.

Grinding mills often pulverize hard ores and as a result, is subject to large forces that affect its wear, life, and safety. The grinding circuits often consists of sag (semi-autogenous grinding) mills, ball mills, pebble crushers, screens and hydro cyclones to produce the desired particle size distribution in the powdered ore. Mills often process ores of variable hardness, shape, and size. This inherent variability is important to account for during the control of mills since there is always a possibility of a build-up of ore inside the mill to an extent that it damages the equipment or causes an overload condition. As a result, it is not uncommon to find plants running below peak conditions.

Changing raw materials required tighter controls; AI helps

A large gold mine operation had similar issues. An investment in advanced process controllers were not delivering the intended benefit of maximizing production at the grinding mills. The APC models were tuned for a certain type of ores and were struggling to maintain performance in the light of changed ore conditions. The grinding mill was processing ores of variable size, shape, hardness, etc., and had to be controlled to mitigate the possibility of ore build-up inside the mill and subsequent overload or runaway conditions. In fact, this dynamic variability of ore-feed along with other process uncertainties soon created a bottleneck of automated control operations by the APC and often had to be turned off intermittently for plant operators to take direct control.

The APC parameters needed constant adjustments from experts, which was not available at the mines. Since the mill’s APC system lacked the ability to automatically and adaptively deal with the inherent variability and uncertainty, operators ran conservative strategies that reduced the chance of runaway or overload conditions. However, this also reduced the mill’s throughput, which meant reduced gold production.

Digital twin model driven by AI

AI-driven digital twin models offer dynamic process optimization that can predict process uncertainties and recommend optimized control strategies to increase throughput and reduce the chance of failures. The digital twin models use highly performant, adaptive self-tuning AI models that can capture operating dynamics, predict unknown quantities and find optimal control parameters in real time.

In this case, the digital twin-based optimizer was deployed to run alongside the APC. As part of the digital twin model development, a detailed exploratory data analysis of one year’s worth of historical process time-series data at 1-minute frequency intervals, lab analysis of ore feed data, production and maintenance logs were undertaken to glean model features and identify baseline operating data for model training and testing.

4 objectives for recurrent neural networks, self-adaptive tuning

The heart of the digital twin model was based on recurrent neural networks with self-adaptive tuning mechanism to take into account of process changes with an aim to meet the following objectives:

  1. AI-based approach with a supervisory level of decision-making support for APC
  2. Coordinated constraint management across the mill circuit to get the best out of mill controllers including APC
  3. Cognitive learning-based approach, factoring in operator and metallurgical engineer expertise and insights
  4. Continuous adaptation of AI-models to dynamically account for ore and process variations.

Typical advisories from the digital twin optimizer would include mill ore feed, power, load, water additions and mill speeds.

The trained digital model deployed online with live data ingestion capabilities from plant distributed control system (DCS), lab computer systems and asset management systems, continuously predict, and run optimizers to provide adjustments of the APC control parameters in real-time. This allowed the APC to adapt with changing conditions and enable the grinding mill to perform at higher throughput levels.

The installation of AI software caused no disruptions to existing operations. This aspect is an important consideration when considering AI solutions at a plant. Process disruptions or additional hardware and instrumentation can cause potential roadblocks to successfully implement an AI program.

The outcome from this AI implementation showed an uptick of more than 1% increase in mill production throughput with annual topline impact of $3 to $4 million for the mine.

Dominic Gallello is chief executive officer at Symphony AzimaAI. Edited by Mark T. Hoske, content manager, Control Engineering, CFE Media,


Automation implementation advice, artificial intelligence (AI)


Do you know of widely variable processes that could benefit from a 1% increase in throughput and quality increase to offer $3 million in annual benefits?

See related New Products for Engineers at

Author Bio: Dominic Gallello is CEO of Symphony AzimaAI.