Manufacturing facilities are a collection of assets that converts raw material into finished goods. The machines require humans to operate and optimize them to achieve maximum reliability and quality of the final products.
Companies are investing more time and effort into digitizing their assets so that they understand what they are, how they work and how to make them better. This is an important step in each facilities journey to smart manufacturing. It also will assist in workforce development. Imagine a new employee on day one, can get to know how to run that equipment and optimize it.
The nature of manufacturing is shifting rapidly and the trend towards digitalization of assets is accelerating. Let’s start with the assets themselves.
In the past, a manufacturing facilities main asset was a machine, line or small skid. This typically stood alone. The primary goal was to produce as much product as possible, despite a limited amount of a data feedback loop due to the technology that was available.
Fast forward to today and those machines are more connected than ever. Even the devices within the machine now have a digital capability. They have IP addresses. They can connect to each other, to a central system in the plant, and to the business system. So, the first phase of smart manufacturing is the digitization of the assets themselves with the devices on the equipment.
The next stage is applying a software environment that can capture those assets and monitor them. From there comes the cloud, which is getting the data out of the plant. Now comes a whole new world with new opportunities such as Artificial Intelligence (AI), Machine Learning (ML) and remote managed services.
There is estimated to be over 3 billion devices in the industrial sector that can get connected and are creating more data than ever before. With this level of data collection these devices suddenly are creating terabytes a day of data. With this amount of data, contextualizing it becomes critical to get the most value out of it.
What are some of the types of value companies are getting out of their data from their digital assets? Let’s look at a few starting with predictive maintenance.
When a connected machine fails, it records a multitude of data points. This builds up a plethora of data associated with past failure events. Machine learning steps in and watches those same inputs in real time, and begins to predict the next failure before it happens, and even when it’s going to happen again.
Some examples include vibration monitoring on a motor. ML allows the ability to take vibration data points from a mechanical system and apply algorithms to accurately predict where in the lifecycle curve that particular asset is and what the probability of failure is in the future. If an ounce of prevention is worth a pound of cure, then ML improves reliability and machine uptime exponentially.
A second value area is around cyber security.
Imagine seeing all the data sets in a plant floor and the business system it connects to. Now take it a step further and envision the ability to identify anomalies that suggest somebody intruded the plants or gotten a unique access from the data from plant.
Cyber Security anomalies could be detected and alert IT to hone in on the issue. Stop a cybersecurity incident well before it proliferates across an enterprise is possible when a foundation of digital assets is optimized.
Maintenance optimization is a third area to consider.
Once all the assets in the plant are identified and a comparison has been completed in the storeroom, there is an opportunity to identify gaps in critical spares. With digital asset optimization the devices can provide feedback on how assets are performing and if they align to available spares. There is a major opportunity to positively impact carrying costs and increase overall reliability thru an initiative such as this.
Finally, performance optimization should be addressed.
Picture the ability to capture all the assets and understand how they’re impacting productivity. A 1% improvement from a performance standpoint suddenly becomes a big number as you look at an enterprise. The numbers scale quickly given the size of an organization. These are large impacts by improving performance, understanding assets and applying analytics to improve on asset utilization.
The journey starts with embracing digital asset optimization principles and finding ways to evolve your process. The team at EECO is positioned to understand your goals and help develop solutions to make these ideas come to fruition.
