The industrial sector has long been considered as one of the last members to join the digital party. But with Amazon’s new machine learning (ML) services created for industrial customers, things might change and the industrial sector might take a big, unexpected leap ahead.
Photo: AWS Events
And that would be a welcomed change, especially after a rough 2020. This year has been challenging for manufacturers worldwide and those that didn’t shut down had to power through and expedite their digital transformation initiatives. It goes without saying, but everyone in the industrial landscape is now hoping for a brighter 2021. And Amazon Web Services (AWS) seems to be feeding the hopes and expectations of manufacturers with five new services:
- Amazon Monitron: an end-to-end system that uses machine learning to detect abnormal behavior in industrial machinery which enables manufacturers to implement predictive maintenance and reduce unplanned downtime;
- Amazon Lookout for Equipment: a system that uses data from sensors to detect abnormal equipment behavior which enables manufacturers to take action before machine failures occur and avoid unplanned downtime;
- Amazon Lookout for Vision: a machine learning service that spots defects and anomalies in visual representations using computer vision (CV);
- The AWS Panorama Appliance: a machine learning appliance that allows manufacturers to deploy CV applications to the edge when low latency and data privacy are required, and internet bandwidth is limited;
- The AWS Panorama Software Development Kit (SDK): a device software stack for computer vision, sample code, APIs, and tools to enable and test devices for the AWS Panorama service.
In this article, we’ll take a closer look at Amazon Monitron to understand its benefits and potential threats to original equipment manufacturers (OEMs).
The benefits of Amazon Monitron
As previously mentioned, Amazon Monitron is an end-to-end system that uses machine learning to detect abnormal behavior in industrial machinery. This enables manufacturers to implement predictive maintenance and reduce unplanned downtime. That’s great news, especially because predictive maintenance can help manufacturers save time and costs they would otherwise spend on repairs or over-maintenance tasks.
Despite the fact that predictive maintenance is so cost-effective, not many industrial companies have been able to implement it in the past. To successfully implement predictive maintenance, companies have needed the right data infrastructure and the right team of skilled technicians and data scientists. And these resources have been scarce in the industrial landscape.
However, Amazon Monitron promises to fill the gaps with an offering that “includes sensors to capture vibration and temperature data from equipment, a gateway device to securely transfer data to AWS, the Monitron service that analyzes the data for abnormal machine patterns using machine learning, and a companion mobile app to set up the devices and receive reports on operating behavior and alerts to potential failures in your machinery.”
Plus, this service allows manufacturers to start monitoring the health of their equipment in mere minutes and they don’t need any ML experience or development work to set it up.
On top of enabling predictive maintenance for industrial equipment and being easy to set up and use, the new Amazon Monitron service also offers benefits such as:
- Cost-effective equipment monitoring with low upfront hardware investment;
- High data security standards for sensors and gateways and the communication between them and the service itself;
- Increased accuracy with continuous improvement based on the feedback Amazon Monitron receives from technicians via the mobile app;
- Detection of abnormal conditions in industrial machinery, promoting proactive actions that will result in unplanned downtime reduction.
AWS customers like Fender, RS Components, and GE Gas Power have already experienced some of the benefits of Amazon Monitron and their testimonies are compelling. According to Magnus Akesson, CIO at GE Gas Power Manufacturing, which is a leading provider of power generation equipment and solutions:
“Using Amazon Monitron, we are now able to quickly retrofit our assets with sensors and connecting them to real-time analytics in AWS cloud. We can do this without having to require deep technical skills or having to configure our own IT and OT networks. From our initial work on vibration-prone tumblers, we are seeing this vision come to life at an amazing speed: the ease-of-use for the operators and maintenance team, the simplicity, and the ability to implement at scale is extremely attractive to GE.”
Should OEMs be worried about Amazon Monitron?
OEMs understand their customers’ need to have real-time monitoring information available, ensure optimal uptime, and save costs on repairs and over-maintenance. That’s why, in recent years, many have tried to increase the speed with which they serve their customers and support them with maintenance services that prevent or limit the impact of a breakdown. And Industry 4.0 software has helped OEMs achieve that.
However, plenty of OEMs are still falling behind and continue to take the traditional route to maintenance, which is either reactive or preventive. It often involves dispatching teams to repair or replace parts, scheduling regular maintenance, and resulting in delayed production for customers. In an increasingly digital world, this will end up causing frustration and customer churns.
Unless OEMs hurry up and invest in the right technology for remote machine monitoring, data integrity, network security, and also extend remote monitoring as a service, they might be in for a race against Amazon Monitron with slim chances for success.
As disheartening as that sounds, the truth is that OEMs have a great opportunity to provide significant value-add to their service packages by investing in industrial IoT and enabling their customers to predict when their machines and equipment need servicing.
Additionally, through these services, OEMs can innovate further based on the data they receive from their customers. They can use it to derive insights that will enable them to create new, augmented parts and machines that are native to the digital era that exploded and expanded in 2020.