Case Studies Optimizing Smelting and Refining Equipment Reliability with Prescriptive Analytics

Edit This Case Study Record

	Optimizing Smelting and Refining Equipment Reliability with Prescriptive Analytics

Optimizing Smelting and Refining Equipment Reliability with Prescriptive Analytics

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Predictive Analytics
Applicable Industries	Metals Mining
Applicable Functions	Discrete Manufacturing Maintenance
Use Cases	Machine Condition Monitoring Predictive Maintenance
Services	Data Science Services
Challenge	One of the world’s largest fully integrated zinc and lead smelting and refining complexes wanted to improve their metallurgical operations. The team recognized they had an opportunity to improve preventative maintenance by using information from their process signal historian. In addition, they wanted a solution that could help as the company developed a comprehensive approach to strengthen environmental, employee and community safeguards. The operations group’s reliability team needed a technology to track, detect and prevent equipment failures. Read More
About Customer	The customer is one of the world’s largest fully integrated zinc and lead smelting and refining complexes. As a producer of refined zinc and lead, a variety of precious and specialty metals, chemicals and fertilizer products, their team’s success is based on improving best practices, optimizing efficient processes, reducing failures and increasing the bottom line. They wanted to improve their metallurgical operations and recognized an opportunity to improve preventative maintenance by using information from their process signal historian. They also wanted a solution that could help as the company developed a comprehensive approach to strengthen environmental, employee and community safeguards. Read More
Solution	The customer utilized Aspen Mtell machine learning to track and predict equipment failure as well as determine the precise process signature leading to a failure. Mtell has the ability to read process signals and calculate how much runtime a piece of equipment has left, and even automatically file a work order. The agent within Mtell provided guidance of a time-to-failure of roughly 40 days on a process crucial pump. The maintenance and reliability team acted and performed a detailed SWOT analysis to determine the best course of action based not only on the tool’s guidance, but on the site’s production forecast as well. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Predictive Analytics

Applicable Industries

Metals

Mining

Applicable Functions

Discrete Manufacturing

Maintenance

Use Cases

Machine Condition Monitoring

Predictive Maintenance

Services

Data Science Services

Challenge

One of the world’s largest fully integrated zinc and lead smelting and refining complexes wanted to improve their metallurgical operations. The team recognized they had an opportunity to improve preventative maintenance by using information from their process signal historian. In addition, they wanted a solution that could help as the company developed a comprehensive approach to strengthen environmental, employee and community safeguards. The operations group’s reliability team needed a technology to track, detect and prevent equipment failures.

About Customer

The customer is one of the world’s largest fully integrated zinc and lead smelting and refining complexes. As a producer of refined zinc and lead, a variety of precious and specialty metals, chemicals and fertilizer products, their team’s success is based on improving best practices, optimizing efficient processes, reducing failures and increasing the bottom line. They wanted to improve their metallurgical operations and recognized an opportunity to improve preventative maintenance by using information from their process signal historian. They also wanted a solution that could help as the company developed a comprehensive approach to strengthen environmental, employee and community safeguards.

Solution

The customer utilized Aspen Mtell machine learning to track and predict equipment failure as well as determine the precise process signature leading to a failure. Mtell has the ability to read process signals and calculate how much runtime a piece of equipment has left, and even automatically file a work order. The agent within Mtell provided guidance of a time-to-failure of roughly 40 days on a process crucial pump. The maintenance and reliability team acted and performed a detailed SWOT analysis to determine the best course of action based not only on the tool’s guidance, but on the site’s production forecast as well.

Impact #1	Provides insights into what might lead to a future failure or impact production
Impact #2	Triggers a warning when similar detrimental operation scenarios arise, predicting number of days to failure
Impact #3	Improves safety and environmental performance by highlighting potential risks before they become dangerous

Impact #1

Provides insights into what might lead to a future failure or impact production

Impact #2

Triggers a warning when similar detrimental operation scenarios arise, predicting number of days to failure

Impact #3

Improves safety and environmental performance by highlighting potential risks before they become dangerous

Benefit #1	Cost avoidance of $2.1M USD in 2016 and greater savings in 2017

Benefit #1

Cost avoidance of $2.1M USD in 2016 and greater savings in 2017

Download PDF Version

Overview

Optimizing Smelting and Refining Equipment Reliability with Prescriptive Analytics

Operational Impact

Quantitative Benefit