Amway Case Study

AMWAY CASE STUDY
Helping People Live Better Lives!
 Develop a project on the role of Instrumentation in predictive maintenance by enhancing real-

time data acquisition and analysis, thereby minimizing equipment downtime and optimizing
maintenance strategies.
“Technology is like a dash of salt in a predictive maintenance program—it ties the other
ingredients together and makes them shine.”
The goal is to improve the way we collect and analyze real-time data,
which helps reduce the time equipment is not working and makes
maintenance strategies more effective. The aim is to minimize
downtime and make sure maintenance is done at the right times. In
this case, I have personally taken the Distribution center machinery
as just a short example. I have personally suggested some ideas too.
Predictive maintenance is an important way to prevent equipment

failures. It uses data-driven techniques and machine-learning
algorithms to predict when machines might have issues
Smart predictive maintenance is a modern technique that goes

beyond traditional preventive and predictive maintenance in three
ways:
1. Monitors a network of connected assets.

2. Automates some maintenance tasks.
3. Integrates with other maintenance management systems
(CMMS, ERP, MES).
As I mentioned Distribution center machinery, Amway's goals for this

automated facility include a streamlined fulfillment process. Through
the warehouse Control system, we can release those pre-made cartons
and they go through the label application system to get their LPN’s
then they also go through
an automated document insertion process to have the pack list and invoices inserted directly into the
containers. Those orders are routed through several zones of picked align picked a voice and as the
orders are being processed, they also go through several points of inbound weight scale. Those weight
scales help to verify that the right contents are going into the container making sure things are
accurate and if not, they can be handled before the order hits the outbound shipping lanes. After they
go through the picking process and automated leading process where the containers are cut down to
size to reduce shipping volumes and a lid is automatically glued to the top. As soon as the cartons are
lidded, they go through an array to have shipping labels, where the labels are scanned and based on
configuration and then the item will be shipped.
In the above-mentioned example, I can personally suggest ideas to improve here. We can use a
Human-machine interface as a go-to for total system management, not only does it include a DVR
recording system, but it also includes a process for very prompt, fault recovery, total system statistics,
and overall system management.
We can also add sensors like Current Sensors (Measure electrical current draw in motors, control
panels, and power cables to detect anomalies indicative of overloading, shorts, or inefficiencies),
Pressure Sensors (Monitor fluid pressure in hydraulic systems, pumps, and compressed air lines for
leaks, blockages, and wear), Temperature Sensors (Monitor component overheating, potential
lubrication issues, and thermal anomalies) and Vibration Sensors (Detect
imbalances, misalignments, bearing wear, and gear mesh problems in motors, conveyors, and other
rotating equipment).
AI in predictive maintenance performs better than SCADA:- This control system is complex. Hence,
we need a team of skilled operators, analysts, and programmers to maintain and configure it. Hence,
SCADA doesn’t make the most of Big Data. And that is why a growing number of companies are
opting for Machine Learning instead. Machine learning can analyze data in real time. It can
automatically identify anomalies and find correlations. Therefore, there’s no need for manual
intervention. Machine learning operates just by processing the data.
Besides, ML algorithms automatically:

 Identifies potential failures;
 Recommends activities to reduce risk;
 Provides recommendations for the optimum maintenance schedules;
 Reduces downtime and maximizes uptime.
However, we need to hold enough data to train the model. In particular, we require:
 Error history – to provide failure patterns;
 Repair history – to inject error codes and parts order dates;
 Machine operating condition – as a valuable resource of data samples;
 Equipment metadata – basic input values such as start date and system location.
Predictive maintenance challenges
Big Data is the future of predictive maintenance. But to effectively use it, you’ll require specialized
expertise. Both technicians and analysts will make sure the data is interpreted correctly.
To overcome the challenges: -

With my reference knowledge, A system called Machine Metrics can connect to different types of
machines on the factory floor using various protocols. It uses a combination of both edge and cloud
technologies. This hybrid setup allows for quick decision-making at the machine (edge) and also
provides a platform in the cloud for deeper analysis.
It's like having the best of both worlds – quick real-time decisions and the ability to analyze data
deeply for more insights. Machine Metrics can connect with machines using standard protocols like
OPC-UA, MT Connect, Modbus TCP, and Ethernet/IP. It's like having different languages that the
machines can speak to communicate with our system. It can connect to any type of machine,
understand various communication methods, and it even helps make the data speak the same
language. This means we don't have to spend time manually figuring out how to use the data;
Machine Metrics takes care of it automatically.
Some systems, like Machine Metrics, also allow the workers operating the machines to add their own
input. They can categorize why a machine is not working, track when setups happen, report if a piece
is not of good quality, or note when tools are changed.
Machine Metrics, the technology provider mentioned, has achieved AWS Industrial Software
Competency. This means they've aligned with the best practices recommended by AWS (Amazon Web
Services) for building a secure, high-performing, and efficient cloud infrastructure. It's like having a
stamp of approval that assures customers their data is handled with the utmost care and efficiency.
This model, used by services like Machine Metrics, is more flexible. Instead of paying a big amount
upfront, you pay a regular subscription cost, allowing you to decide how many machines you want to
monitor, and this subscription cost covers that.
Machine Metrics is designed to be user-friendly, meaning it's easy for everyone to use. Operators on
the shop floor can keep an eye on their machines, get notifications, and take necessary actions, even
acting as first-level quality inspectors, it has intuitive touch screens that make it easy for them to keep
track of equipment and respond to alerts.
Predictive maintenance can reduce downtime by 30-50% and improve equipment life by 20-
40%.
Jayakerupaa. S
110121041
Instrumentation and Control Engineering

Amway Case Study

Uploaded by

Copyright:

Available Formats

Amway Case Study

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Amway Case Study

Uploaded by

Copyright:

Available Formats

AMWAY CASE STUDY

Helping People Live Better Lives!

 Develop a project on the role of Instrumentation in predictive maintenance by enhancing real-

Predictive maintenance is an important way to prevent equipment

Smart predictive maintenance is a modern technique that goes

1. Monitors a network of connected assets.

As I mentioned Distribution center machinery, Amway's goals for this

Besides, ML algorithms automatically:

To overcome the challenges: -

You might also like