3946
Unlocking Real-Time Grinding Optimization:
Insights from Inside the Mill
Eduardo Nunez
Molycop Canada
Dante Garcia
Molycop Peru
Joshua Morales
Molycop Chile
Karl Gugel
Molycop United States of America
ABSTRACT: Achieving operational excellence in real-time requires many elements that work together optimally.
The fundamental aspects of a successful implementation depend on accurate, precise instrumentation, real-
time data collection, data analytics, and an appropriate optimization platform. Additionally, for all of these
components to lead to a successful outcome, the final real-time optimization platform needs to be implemented
within the site’s own internal process control system (Nunez, 2022).
This paper presents practical learnings and best practices for autogenous (AG), semi-autogenous (SAG), and ball
mills (BM) grinding. The discussion includes the implementation of advanced instrumentation consisting of
vibration sensors attached to the mill shell under rotation. Also discussed is the application of advanced analyt-
ics required to create new measurements that accurately represent the real-time grinding activity occurring in
the mill. The application of these Advanced Analytics Measurements (AAM) is compared and contrasted with
well-known grinding curves to identify and select the operating point for optimal grinding. Specifically, three
industry-wide opportunities, liner wear, pegging detection, and Jb/Jc ratios, are discussed, along with support-
ing real-time mill shell vibration results to obtain new correlations and optimal grinding process operation.
These learnings and best practices are not just theoretical, but practical and applicable in your daily operations,
empowering you to optimize your grinding processes.
INTRODUCTION
Reducing ore rocks into smaller particles to liberate valu-
able minerals, known as grinding, has significantly evolved
with new instruments and more efficient process control
strategies. However, the multivariable and continuously
changing nature of the grinding process requires real-time
understanding and monitoring of how the mill is operat-
ing. Luckily, this is now possible due to advancements in
computing power, which yields much faster processing of
large data sets and application of artificial intelligence (AI)
Unlocking Real-Time Grinding Optimization:
Insights from Inside the Mill
Eduardo Nunez
Molycop Canada
Dante Garcia
Molycop Peru
Joshua Morales
Molycop Chile
Karl Gugel
Molycop United States of America
ABSTRACT: Achieving operational excellence in real-time requires many elements that work together optimally.
The fundamental aspects of a successful implementation depend on accurate, precise instrumentation, real-
time data collection, data analytics, and an appropriate optimization platform. Additionally, for all of these
components to lead to a successful outcome, the final real-time optimization platform needs to be implemented
within the site’s own internal process control system (Nunez, 2022).
This paper presents practical learnings and best practices for autogenous (AG), semi-autogenous (SAG), and ball
mills (BM) grinding. The discussion includes the implementation of advanced instrumentation consisting of
vibration sensors attached to the mill shell under rotation. Also discussed is the application of advanced analyt-
ics required to create new measurements that accurately represent the real-time grinding activity occurring in
the mill. The application of these Advanced Analytics Measurements (AAM) is compared and contrasted with
well-known grinding curves to identify and select the operating point for optimal grinding. Specifically, three
industry-wide opportunities, liner wear, pegging detection, and Jb/Jc ratios, are discussed, along with support-
ing real-time mill shell vibration results to obtain new correlations and optimal grinding process operation.
These learnings and best practices are not just theoretical, but practical and applicable in your daily operations,
empowering you to optimize your grinding processes.
INTRODUCTION
Reducing ore rocks into smaller particles to liberate valu-
able minerals, known as grinding, has significantly evolved
with new instruments and more efficient process control
strategies. However, the multivariable and continuously
changing nature of the grinding process requires real-time
understanding and monitoring of how the mill is operat-
ing. Luckily, this is now possible due to advancements in
computing power, which yields much faster processing of
large data sets and application of artificial intelligence (AI)